diff options
180 files changed, 2705 insertions, 790 deletions
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/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/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/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index acdfb5d2bcaa..e2142fe40cda 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 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/MAINTAINERS b/MAINTAINERS index 09f43f1bdd15..5c38f21aee78 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3121,6 +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 @@ -8707,6 +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 @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 1 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = -rc7 NAME = Shy Crocodile # *DOCUMENTATION* 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/arm/Kconfig b/arch/arm/Kconfig index 850b4805e2d1..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) 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/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/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/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 07b298120182..65a51331088e 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -103,10 +103,15 @@ 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 (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/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/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/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/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/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/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/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/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/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/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/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/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/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index c0d6c560df69..5a237e8dbf8d 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -352,7 +352,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, boot_params->hdr.loadflags &= ~KASLR_FLAG; /* Save RSDP address for later use. */ - boot_params->acpi_rsdp_addr = get_rsdp_addr(); + /* boot_params->acpi_rsdp_addr = get_rsdp_addr(); */ sanitize_boot_params(boot_params); 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/mm/init.c b/arch/x86/mm/init.c index f905a2371080..8dacdb96899e 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -5,6 +5,7 @@ #include <linux/memblock.h> #include <linux/swapfile.h> #include <linux/swapops.h> +#include <linux/kmemleak.h> #include <asm/set_memory.h> #include <asm/e820/api.h> @@ -766,6 +767,11 @@ void free_init_pages(const char *what, unsigned long begin, unsigned long end) if (debug_pagealloc_enabled()) { pr_info("debug: unmapping init [mem %#010lx-%#010lx]\n", begin, end - 1); + /* + * Inform kmemleak about the hole in the memory since the + * corresponding pages will be unmapped. + */ + kmemleak_free_part((void *)begin, end - begin); set_memory_np(begin, (end - begin) >> PAGE_SHIFT); } else { /* 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/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/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/arm64/iort.c b/drivers/acpi/arm64/iort.c index e48894e002ba..4000902e57f0 100644 --- a/drivers/acpi/arm64/iort.c +++ b/drivers/acpi/arm64/iort.c @@ -1028,6 +1028,14 @@ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size) dev_dbg(dev, "dma_pfn_offset(%#08llx)\n", offset); } +static bool iort_pci_rc_supports_ats(struct acpi_iort_node *node) +{ + struct acpi_iort_root_complex *pci_rc; + + pci_rc = (struct acpi_iort_root_complex *)node->node_data; + return pci_rc->ats_attribute & ACPI_IORT_ATS_SUPPORTED; +} + /** * iort_iommu_configure - Set-up IOMMU configuration for a device. * @@ -1063,6 +1071,9 @@ const struct iommu_ops *iort_iommu_configure(struct device *dev) info.node = node; err = pci_for_each_dma_alias(to_pci_dev(dev), iort_pci_iommu_init, &info); + + if (!err && iort_pci_rc_supports_ats(node)) + dev->iommu_fwspec->flags |= IOMMU_FWSPEC_PCI_RC_ATS; } else { int i = 0; 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/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 399cad7daae7..d58a359a6622 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -774,18 +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); } /* @@ -798,6 +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/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/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/gpiolib.c b/drivers/gpio/gpiolib.c index 0495bf1d480a..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); diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c index db761329a1e3..ab7968c8f6a2 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c @@ -1046,6 +1046,10 @@ static bool dw_hdmi_support_scdc(struct dw_hdmi *hdmi) 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) @@ -1684,13 +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 @@ -1706,7 +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); } } @@ -1800,6 +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) { @@ -1808,7 +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/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index ab4e60dfd6a3..98cea1f4b3bf 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -3862,14 +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_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 8891f29a8c7f..48da4a969a0a 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -1886,6 +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; @@ -2116,9 +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_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/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/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/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 0fa5034b9f9e..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", @@ -1531,12 +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); } @@ -1548,7 +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/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/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/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/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/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 f2e7ffe6fc54..7843e89235c3 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->vm_start); + 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 +1039,7 @@ 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); @@ -1006,11 +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); skip_mm: - up_write(&mm->mmap_sem); + up_read(&mm->mmap_sem); mmput(mm); } } diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c index 66cdf625534f..60cf9f03e941 100644 --- a/drivers/infiniband/hw/hns/hns_roce_qp.c +++ b/drivers/infiniband/hw/hns/hns_roce_qp.c @@ -533,7 +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/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/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/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/Kconfig b/drivers/iommu/Kconfig index 6f07f3b21816..15b831113ded 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -359,6 +359,31 @@ config ARM_SMMU Say Y here if your SoC includes an IOMMU device implementing the ARM SMMU architecture. +config ARM_SMMU_DISABLE_BYPASS_BY_DEFAULT + bool "Default to disabling bypass on ARM SMMU v1 and v2" + depends on ARM_SMMU + default y + help + Say Y here to (by default) disable bypass streams such that + incoming transactions from devices that are not attached to + an iommu domain will report an abort back to the device and + will not be allowed to pass through the SMMU. + + Any old kernels that existed before this KConfig was + introduced would default to _allowing_ bypass (AKA the + equivalent of NO for this config). However the default for + this option is YES because the old behavior is insecure. + + There are few reasons to allow unmatched stream bypass, and + even fewer good ones. If saying YES here breaks your board + you should work on fixing your board. This KConfig option + is expected to be removed in the future and we'll simply + hardcode the bypass disable in the code. + + NOTE: the kernel command line parameter + 'arm-smmu.disable_bypass' will continue to override this + config. + config ARM_SMMU_V3 bool "ARM Ltd. System MMU Version 3 (SMMUv3) Support" depends on ARM64 diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index f7cdd2ab7f11..fde16c5b0a70 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -1723,31 +1723,6 @@ static void dma_ops_free_iova(struct dma_ops_domain *dma_dom, * ****************************************************************************/ -/* - * This function adds a protection domain to the global protection domain list - */ -static void add_domain_to_list(struct protection_domain *domain) -{ - unsigned long flags; - - spin_lock_irqsave(&amd_iommu_pd_lock, flags); - list_add(&domain->list, &amd_iommu_pd_list); - spin_unlock_irqrestore(&amd_iommu_pd_lock, flags); -} - -/* - * This function removes a protection domain to the global - * protection domain list - */ -static void del_domain_from_list(struct protection_domain *domain) -{ - unsigned long flags; - - spin_lock_irqsave(&amd_iommu_pd_lock, flags); - list_del(&domain->list); - spin_unlock_irqrestore(&amd_iommu_pd_lock, flags); -} - static u16 domain_id_alloc(void) { int id; @@ -1838,8 +1813,6 @@ static void dma_ops_domain_free(struct dma_ops_domain *dom) if (!dom) return; - del_domain_from_list(&dom->domain); - put_iova_domain(&dom->iovad); free_pagetable(&dom->domain); @@ -1880,8 +1853,6 @@ static struct dma_ops_domain *dma_ops_domain_alloc(void) /* Initialize reserved ranges */ copy_reserved_iova(&reserved_iova_ranges, &dma_dom->iovad); - add_domain_to_list(&dma_dom->domain); - return dma_dom; free_dma_dom: @@ -2122,23 +2093,6 @@ out_err: return ret; } -/* FIXME: Move this to PCI code */ -#define PCI_PRI_TLP_OFF (1 << 15) - -static bool pci_pri_tlp_required(struct pci_dev *pdev) -{ - u16 status; - int pos; - - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI); - if (!pos) - return false; - - pci_read_config_word(pdev, pos + PCI_PRI_STATUS, &status); - - return (status & PCI_PRI_TLP_OFF) ? true : false; -} - /* * If a device is not yet associated with a domain, this function makes the * device visible in the domain @@ -2167,7 +2121,7 @@ static int attach_device(struct device *dev, dev_data->ats.enabled = true; dev_data->ats.qdep = pci_ats_queue_depth(pdev); - dev_data->pri_tlp = pci_pri_tlp_required(pdev); + dev_data->pri_tlp = pci_prg_resp_pasid_required(pdev); } } else if (amd_iommu_iotlb_sup && pci_enable_ats(pdev, PAGE_SHIFT) == 0) { @@ -2897,8 +2851,6 @@ static void protection_domain_free(struct protection_domain *domain) if (!domain) return; - del_domain_from_list(domain); - if (domain->id) domain_id_free(domain->id); @@ -2928,8 +2880,6 @@ static struct protection_domain *protection_domain_alloc(void) if (protection_domain_init(domain)) goto out_err; - add_domain_to_list(domain); - return domain; out_err: diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index ff40ba758cf3..f977df90d2a4 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -189,12 +189,6 @@ static bool amd_iommu_pc_present __read_mostly; bool amd_iommu_force_isolation __read_mostly; /* - * List of protection domains - used during resume - */ -LIST_HEAD(amd_iommu_pd_list); -spinlock_t amd_iommu_pd_lock; - -/* * Pointer to the device table which is shared by all AMD IOMMUs * it is indexed by the PCI device id or the HT unit id and contains * information about the domain the device belongs to as well as the @@ -2526,8 +2520,6 @@ static int __init early_amd_iommu_init(void) */ __set_bit(0, amd_iommu_pd_alloc_bitmap); - spin_lock_init(&amd_iommu_pd_lock); - /* * now the data structures are allocated and basically initialized * start the real acpi table scan diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index 87965e4d9647..85c488b8daea 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -675,12 +675,6 @@ extern struct list_head amd_iommu_list; extern struct amd_iommu *amd_iommus[MAX_IOMMUS]; /* - * Declarations for the global list of all protection domains - */ -extern spinlock_t amd_iommu_pd_lock; -extern struct list_head amd_iommu_pd_list; - -/* * Structure defining one entry in the device table */ struct dev_table_entry { diff --git a/drivers/iommu/arm-smmu-regs.h b/drivers/iommu/arm-smmu-regs.h index a1226e4ab5f8..e9132a926761 100644 --- a/drivers/iommu/arm-smmu-regs.h +++ b/drivers/iommu/arm-smmu-regs.h @@ -147,6 +147,8 @@ enum arm_smmu_s2cr_privcfg { #define CBAR_IRPTNDX_SHIFT 24 #define CBAR_IRPTNDX_MASK 0xff +#define ARM_SMMU_GR1_CBFRSYNRA(n) (0x400 + ((n) << 2)) + #define ARM_SMMU_GR1_CBA2R(n) (0x800 + ((n) << 2)) #define CBA2R_RW64_32BIT (0 << 0) #define CBA2R_RW64_64BIT (1 << 0) diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index d3880010c6cf..4d5a694f02c2 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -29,6 +29,7 @@ #include <linux/of_iommu.h> #include <linux/of_platform.h> #include <linux/pci.h> +#include <linux/pci-ats.h> #include <linux/platform_device.h> #include <linux/amba/bus.h> @@ -86,6 +87,7 @@ #define IDR5_VAX_52_BIT 1 #define ARM_SMMU_CR0 0x20 +#define CR0_ATSCHK (1 << 4) #define CR0_CMDQEN (1 << 3) #define CR0_EVTQEN (1 << 2) #define CR0_PRIQEN (1 << 1) @@ -294,6 +296,7 @@ #define CMDQ_ERR_CERROR_NONE_IDX 0 #define CMDQ_ERR_CERROR_ILL_IDX 1 #define CMDQ_ERR_CERROR_ABT_IDX 2 +#define CMDQ_ERR_CERROR_ATC_INV_IDX 3 #define CMDQ_0_OP GENMASK_ULL(7, 0) #define CMDQ_0_SSV (1UL << 11) @@ -312,6 +315,12 @@ #define CMDQ_TLBI_1_VA_MASK GENMASK_ULL(63, 12) #define CMDQ_TLBI_1_IPA_MASK GENMASK_ULL(51, 12) +#define CMDQ_ATC_0_SSID GENMASK_ULL(31, 12) +#define CMDQ_ATC_0_SID GENMASK_ULL(63, 32) +#define CMDQ_ATC_0_GLOBAL (1UL << 9) +#define CMDQ_ATC_1_SIZE GENMASK_ULL(5, 0) +#define CMDQ_ATC_1_ADDR_MASK GENMASK_ULL(63, 12) + #define CMDQ_PRI_0_SSID GENMASK_ULL(31, 12) #define CMDQ_PRI_0_SID GENMASK_ULL(63, 32) #define CMDQ_PRI_1_GRPID GENMASK_ULL(8, 0) @@ -433,6 +442,16 @@ struct arm_smmu_cmdq_ent { u64 addr; } tlbi; + #define CMDQ_OP_ATC_INV 0x40 + #define ATC_INV_SIZE_ALL 52 + struct { + u32 sid; + u32 ssid; + u64 addr; + u8 size; + bool global; + } atc; + #define CMDQ_OP_PRI_RESP 0x41 struct { u32 sid; @@ -505,19 +524,6 @@ struct arm_smmu_s2_cfg { u64 vtcr; }; -struct arm_smmu_strtab_ent { - /* - * An STE is "assigned" if the master emitting the corresponding SID - * is attached to a domain. The behaviour of an unassigned STE is - * determined by the disable_bypass parameter, whereas an assigned - * STE behaves according to s1_cfg/s2_cfg, which themselves are - * configured according to the domain type. - */ - bool assigned; - struct arm_smmu_s1_cfg *s1_cfg; - struct arm_smmu_s2_cfg *s2_cfg; -}; - struct arm_smmu_strtab_cfg { __le64 *strtab; dma_addr_t strtab_dma; @@ -591,9 +597,14 @@ struct arm_smmu_device { }; /* SMMU private data for each master */ -struct arm_smmu_master_data { +struct arm_smmu_master { struct arm_smmu_device *smmu; - struct arm_smmu_strtab_ent ste; + struct device *dev; + struct arm_smmu_domain *domain; + struct list_head domain_head; + u32 *sids; + unsigned int num_sids; + bool ats_enabled :1; }; /* SMMU private data for an IOMMU domain */ @@ -618,6 +629,9 @@ struct arm_smmu_domain { }; struct iommu_domain domain; + + struct list_head devices; + spinlock_t devices_lock; }; struct arm_smmu_option_prop { @@ -820,6 +834,14 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent) case CMDQ_OP_TLBI_S12_VMALL: cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, ent->tlbi.vmid); break; + case CMDQ_OP_ATC_INV: + cmd[0] |= FIELD_PREP(CMDQ_0_SSV, ent->substream_valid); + cmd[0] |= FIELD_PREP(CMDQ_ATC_0_GLOBAL, ent->atc.global); + cmd[0] |= FIELD_PREP(CMDQ_ATC_0_SSID, ent->atc.ssid); + cmd[0] |= FIELD_PREP(CMDQ_ATC_0_SID, ent->atc.sid); + cmd[1] |= FIELD_PREP(CMDQ_ATC_1_SIZE, ent->atc.size); + cmd[1] |= ent->atc.addr & CMDQ_ATC_1_ADDR_MASK; + break; case CMDQ_OP_PRI_RESP: cmd[0] |= FIELD_PREP(CMDQ_0_SSV, ent->substream_valid); cmd[0] |= FIELD_PREP(CMDQ_PRI_0_SSID, ent->pri.ssid); @@ -864,6 +886,7 @@ static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu) [CMDQ_ERR_CERROR_NONE_IDX] = "No error", [CMDQ_ERR_CERROR_ILL_IDX] = "Illegal command", [CMDQ_ERR_CERROR_ABT_IDX] = "Abort on command fetch", + [CMDQ_ERR_CERROR_ATC_INV_IDX] = "ATC invalidate timeout", }; int i; @@ -883,6 +906,14 @@ static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu) dev_err(smmu->dev, "retrying command fetch\n"); case CMDQ_ERR_CERROR_NONE_IDX: return; + case CMDQ_ERR_CERROR_ATC_INV_IDX: + /* + * ATC Invalidation Completion timeout. CONS is still pointing + * at the CMD_SYNC. Attempt to complete other pending commands + * by repeating the CMD_SYNC, though we might well end up back + * here since the ATC invalidation may still be pending. + */ + return; case CMDQ_ERR_CERROR_ILL_IDX: /* Fallthrough */ default: @@ -999,7 +1030,7 @@ static int __arm_smmu_cmdq_issue_sync(struct arm_smmu_device *smmu) return ret; } -static void arm_smmu_cmdq_issue_sync(struct arm_smmu_device *smmu) +static int arm_smmu_cmdq_issue_sync(struct arm_smmu_device *smmu) { int ret; bool msi = (smmu->features & ARM_SMMU_FEAT_MSI) && @@ -1009,6 +1040,7 @@ static void arm_smmu_cmdq_issue_sync(struct arm_smmu_device *smmu) : __arm_smmu_cmdq_issue_sync(smmu); if (ret) dev_err_ratelimited(smmu->dev, "CMD_SYNC timeout\n"); + return ret; } /* Context descriptor manipulation functions */ @@ -1025,7 +1057,6 @@ static u64 arm_smmu_cpu_tcr_to_cd(u64 tcr) val |= ARM_SMMU_TCR2CD(tcr, EPD0); val |= ARM_SMMU_TCR2CD(tcr, EPD1); val |= ARM_SMMU_TCR2CD(tcr, IPS); - val |= ARM_SMMU_TCR2CD(tcr, TBI0); return val; } @@ -1085,8 +1116,8 @@ static void arm_smmu_sync_ste_for_sid(struct arm_smmu_device *smmu, u32 sid) arm_smmu_cmdq_issue_sync(smmu); } -static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid, - __le64 *dst, struct arm_smmu_strtab_ent *ste) +static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid, + __le64 *dst) { /* * This is hideously complicated, but we only really care about @@ -1106,6 +1137,10 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid, */ u64 val = le64_to_cpu(dst[0]); bool ste_live = false; + struct arm_smmu_device *smmu = NULL; + struct arm_smmu_s1_cfg *s1_cfg = NULL; + struct arm_smmu_s2_cfg *s2_cfg = NULL; + struct arm_smmu_domain *smmu_domain = NULL; struct arm_smmu_cmdq_ent prefetch_cmd = { .opcode = CMDQ_OP_PREFETCH_CFG, .prefetch = { @@ -1113,6 +1148,25 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid, }, }; + if (master) { + smmu_domain = master->domain; + smmu = master->smmu; + } + + if (smmu_domain) { + switch (smmu_domain->stage) { + case ARM_SMMU_DOMAIN_S1: + s1_cfg = &smmu_domain->s1_cfg; + break; + case ARM_SMMU_DOMAIN_S2: + case ARM_SMMU_DOMAIN_NESTED: + s2_cfg = &smmu_domain->s2_cfg; + break; + default: + break; + } + } + if (val & STRTAB_STE_0_V) { switch (FIELD_GET(STRTAB_STE_0_CFG, val)) { case STRTAB_STE_0_CFG_BYPASS: @@ -1133,8 +1187,8 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid, val = STRTAB_STE_0_V; /* Bypass/fault */ - if (!ste->assigned || !(ste->s1_cfg || ste->s2_cfg)) { - if (!ste->assigned && disable_bypass) + if (!smmu_domain || !(s1_cfg || s2_cfg)) { + if (!smmu_domain && disable_bypass) val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_ABORT); else val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_BYPASS); @@ -1152,41 +1206,42 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid, return; } - if (ste->s1_cfg) { + if (s1_cfg) { BUG_ON(ste_live); dst[1] = cpu_to_le64( FIELD_PREP(STRTAB_STE_1_S1CIR, STRTAB_STE_1_S1C_CACHE_WBRA) | FIELD_PREP(STRTAB_STE_1_S1COR, STRTAB_STE_1_S1C_CACHE_WBRA) | FIELD_PREP(STRTAB_STE_1_S1CSH, ARM_SMMU_SH_ISH) | -#ifdef CONFIG_PCI_ATS - FIELD_PREP(STRTAB_STE_1_EATS, STRTAB_STE_1_EATS_TRANS) | -#endif FIELD_PREP(STRTAB_STE_1_STRW, STRTAB_STE_1_STRW_NSEL1)); if (smmu->features & ARM_SMMU_FEAT_STALLS && !(smmu->features & ARM_SMMU_FEAT_STALL_FORCE)) dst[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD); - val |= (ste->s1_cfg->cdptr_dma & STRTAB_STE_0_S1CTXPTR_MASK) | + val |= (s1_cfg->cdptr_dma & STRTAB_STE_0_S1CTXPTR_MASK) | FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S1_TRANS); } - if (ste->s2_cfg) { + if (s2_cfg) { BUG_ON(ste_live); dst[2] = cpu_to_le64( - FIELD_PREP(STRTAB_STE_2_S2VMID, ste->s2_cfg->vmid) | - FIELD_PREP(STRTAB_STE_2_VTCR, ste->s2_cfg->vtcr) | + FIELD_PREP(STRTAB_STE_2_S2VMID, s2_cfg->vmid) | + FIELD_PREP(STRTAB_STE_2_VTCR, s2_cfg->vtcr) | #ifdef __BIG_ENDIAN STRTAB_STE_2_S2ENDI | #endif STRTAB_STE_2_S2PTW | STRTAB_STE_2_S2AA64 | STRTAB_STE_2_S2R); - dst[3] = cpu_to_le64(ste->s2_cfg->vttbr & STRTAB_STE_3_S2TTB_MASK); + dst[3] = cpu_to_le64(s2_cfg->vttbr & STRTAB_STE_3_S2TTB_MASK); val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S2_TRANS); } + if (master->ats_enabled) + dst[1] |= cpu_to_le64(FIELD_PREP(STRTAB_STE_1_EATS, + STRTAB_STE_1_EATS_TRANS)); + arm_smmu_sync_ste_for_sid(smmu, sid); dst[0] = cpu_to_le64(val); arm_smmu_sync_ste_for_sid(smmu, sid); @@ -1199,10 +1254,9 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid, static void arm_smmu_init_bypass_stes(u64 *strtab, unsigned int nent) { unsigned int i; - struct arm_smmu_strtab_ent ste = { .assigned = false }; for (i = 0; i < nent; ++i) { - arm_smmu_write_strtab_ent(NULL, -1, strtab, &ste); + arm_smmu_write_strtab_ent(NULL, -1, strtab); strtab += STRTAB_STE_DWORDS; } } @@ -1390,6 +1444,96 @@ static irqreturn_t arm_smmu_combined_irq_handler(int irq, void *dev) return IRQ_WAKE_THREAD; } +static void +arm_smmu_atc_inv_to_cmd(int ssid, unsigned long iova, size_t size, + struct arm_smmu_cmdq_ent *cmd) +{ + size_t log2_span; + size_t span_mask; + /* ATC invalidates are always on 4096-bytes pages */ + size_t inval_grain_shift = 12; + unsigned long page_start, page_end; + + *cmd = (struct arm_smmu_cmdq_ent) { + .opcode = CMDQ_OP_ATC_INV, + .substream_valid = !!ssid, + .atc.ssid = ssid, + }; + + if (!size) { + cmd->atc.size = ATC_INV_SIZE_ALL; + return; + } + + page_start = iova >> inval_grain_shift; + page_end = (iova + size - 1) >> inval_grain_shift; + + /* + * In an ATS Invalidate Request, the address must be aligned on the + * range size, which must be a power of two number of page sizes. We + * thus have to choose between grossly over-invalidating the region, or + * splitting the invalidation into multiple commands. For simplicity + * we'll go with the first solution, but should refine it in the future + * if multiple commands are shown to be more efficient. + * + * Find the smallest power of two that covers the range. The most + * significant differing bit between the start and end addresses, + * fls(start ^ end), indicates the required span. For example: + * + * We want to invalidate pages [8; 11]. This is already the ideal range: + * x = 0b1000 ^ 0b1011 = 0b11 + * span = 1 << fls(x) = 4 + * + * To invalidate pages [7; 10], we need to invalidate [0; 15]: + * x = 0b0111 ^ 0b1010 = 0b1101 + * span = 1 << fls(x) = 16 + */ + log2_span = fls_long(page_start ^ page_end); + span_mask = (1ULL << log2_span) - 1; + + page_start &= ~span_mask; + + cmd->atc.addr = page_start << inval_grain_shift; + cmd->atc.size = log2_span; +} + +static int arm_smmu_atc_inv_master(struct arm_smmu_master *master, + struct arm_smmu_cmdq_ent *cmd) +{ + int i; + + if (!master->ats_enabled) + return 0; + + for (i = 0; i < master->num_sids; i++) { + cmd->atc.sid = master->sids[i]; + arm_smmu_cmdq_issue_cmd(master->smmu, cmd); + } + + return arm_smmu_cmdq_issue_sync(master->smmu); +} + +static int arm_smmu_atc_inv_domain(struct arm_smmu_domain *smmu_domain, + int ssid, unsigned long iova, size_t size) +{ + int ret = 0; + unsigned long flags; + struct arm_smmu_cmdq_ent cmd; + struct arm_smmu_master *master; + + if (!(smmu_domain->smmu->features & ARM_SMMU_FEAT_ATS)) + return 0; + + arm_smmu_atc_inv_to_cmd(ssid, iova, size, &cmd); + + spin_lock_irqsave(&smmu_domain->devices_lock, flags); + list_for_each_entry(master, &smmu_domain->devices, domain_head) + ret |= arm_smmu_atc_inv_master(master, &cmd); + spin_unlock_irqrestore(&smmu_domain->devices_lock, flags); + + return ret ? -ETIMEDOUT : 0; +} + /* IO_PGTABLE API */ static void arm_smmu_tlb_sync(void *cookie) { @@ -1493,6 +1637,9 @@ static struct iommu_domain *arm_smmu_domain_alloc(unsigned type) } mutex_init(&smmu_domain->init_mutex); + INIT_LIST_HEAD(&smmu_domain->devices); + spin_lock_init(&smmu_domain->devices_lock); + return &smmu_domain->domain; } @@ -1688,55 +1835,97 @@ static __le64 *arm_smmu_get_step_for_sid(struct arm_smmu_device *smmu, u32 sid) return step; } -static void arm_smmu_install_ste_for_dev(struct iommu_fwspec *fwspec) +static void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master) { int i, j; - struct arm_smmu_master_data *master = fwspec->iommu_priv; struct arm_smmu_device *smmu = master->smmu; - for (i = 0; i < fwspec->num_ids; ++i) { - u32 sid = fwspec->ids[i]; + for (i = 0; i < master->num_sids; ++i) { + u32 sid = master->sids[i]; __le64 *step = arm_smmu_get_step_for_sid(smmu, sid); /* Bridged PCI devices may end up with duplicated IDs */ for (j = 0; j < i; j++) - if (fwspec->ids[j] == sid) + if (master->sids[j] == sid) break; if (j < i) continue; - arm_smmu_write_strtab_ent(smmu, sid, step, &master->ste); + arm_smmu_write_strtab_ent(master, sid, step); } } -static void arm_smmu_detach_dev(struct device *dev) +static int arm_smmu_enable_ats(struct arm_smmu_master *master) { - struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); - struct arm_smmu_master_data *master = fwspec->iommu_priv; + int ret; + size_t stu; + struct pci_dev *pdev; + struct arm_smmu_device *smmu = master->smmu; + struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(master->dev); - master->ste.assigned = false; - arm_smmu_install_ste_for_dev(fwspec); + if (!(smmu->features & ARM_SMMU_FEAT_ATS) || !dev_is_pci(master->dev) || + !(fwspec->flags & IOMMU_FWSPEC_PCI_RC_ATS) || pci_ats_disabled()) + return -ENXIO; + + pdev = to_pci_dev(master->dev); + if (pdev->untrusted) + return -EPERM; + + /* Smallest Translation Unit: log2 of the smallest supported granule */ + stu = __ffs(smmu->pgsize_bitmap); + + ret = pci_enable_ats(pdev, stu); + if (ret) + return ret; + + master->ats_enabled = true; + return 0; +} + +static void arm_smmu_disable_ats(struct arm_smmu_master *master) +{ + if (!master->ats_enabled || !dev_is_pci(master->dev)) + return; + + pci_disable_ats(to_pci_dev(master->dev)); + master->ats_enabled = false; +} + +static void arm_smmu_detach_dev(struct arm_smmu_master *master) +{ + unsigned long flags; + struct arm_smmu_domain *smmu_domain = master->domain; + + if (!smmu_domain) + return; + + spin_lock_irqsave(&smmu_domain->devices_lock, flags); + list_del(&master->domain_head); + spin_unlock_irqrestore(&smmu_domain->devices_lock, flags); + + master->domain = NULL; + arm_smmu_install_ste_for_dev(master); + + /* Disabling ATS invalidates all ATC entries */ + arm_smmu_disable_ats(master); } static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) { int ret = 0; + unsigned long flags; struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); struct arm_smmu_device *smmu; struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); - struct arm_smmu_master_data *master; - struct arm_smmu_strtab_ent *ste; + struct arm_smmu_master *master; if (!fwspec) return -ENOENT; master = fwspec->iommu_priv; smmu = master->smmu; - ste = &master->ste; - /* Already attached to a different domain? */ - if (ste->assigned) - arm_smmu_detach_dev(dev); + arm_smmu_detach_dev(master); mutex_lock(&smmu_domain->init_mutex); @@ -1756,21 +1945,19 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) goto out_unlock; } - ste->assigned = true; + master->domain = smmu_domain; - if (smmu_domain->stage == ARM_SMMU_DOMAIN_BYPASS) { - ste->s1_cfg = NULL; - ste->s2_cfg = NULL; - } else if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) { - ste->s1_cfg = &smmu_domain->s1_cfg; - ste->s2_cfg = NULL; - arm_smmu_write_ctx_desc(smmu, ste->s1_cfg); - } else { - ste->s1_cfg = NULL; - ste->s2_cfg = &smmu_domain->s2_cfg; - } + spin_lock_irqsave(&smmu_domain->devices_lock, flags); + list_add(&master->domain_head, &smmu_domain->devices); + spin_unlock_irqrestore(&smmu_domain->devices_lock, flags); - arm_smmu_install_ste_for_dev(fwspec); + if (smmu_domain->stage != ARM_SMMU_DOMAIN_BYPASS) + arm_smmu_enable_ats(master); + + if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) + arm_smmu_write_ctx_desc(smmu, &smmu_domain->s1_cfg); + + arm_smmu_install_ste_for_dev(master); out_unlock: mutex_unlock(&smmu_domain->init_mutex); return ret; @@ -1790,12 +1977,18 @@ static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova, static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size) { - struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops; + int ret; + struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); + struct io_pgtable_ops *ops = smmu_domain->pgtbl_ops; if (!ops) return 0; - return ops->unmap(ops, iova, size); + ret = ops->unmap(ops, iova, size); + if (ret && arm_smmu_atc_inv_domain(smmu_domain, 0, iova, size)) + return 0; + + return ret; } static void arm_smmu_flush_iotlb_all(struct iommu_domain *domain) @@ -1860,7 +2053,7 @@ static int arm_smmu_add_device(struct device *dev) { int i, ret; struct arm_smmu_device *smmu; - struct arm_smmu_master_data *master; + struct arm_smmu_master *master; struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); struct iommu_group *group; @@ -1882,13 +2075,16 @@ static int arm_smmu_add_device(struct device *dev) if (!master) return -ENOMEM; + master->dev = dev; master->smmu = smmu; + master->sids = fwspec->ids; + master->num_sids = fwspec->num_ids; fwspec->iommu_priv = master; } /* Check the SIDs are in range of the SMMU and our stream table */ - for (i = 0; i < fwspec->num_ids; i++) { - u32 sid = fwspec->ids[i]; + for (i = 0; i < master->num_sids; i++) { + u32 sid = master->sids[i]; if (!arm_smmu_sid_in_range(smmu, sid)) return -ERANGE; @@ -1913,7 +2109,7 @@ static int arm_smmu_add_device(struct device *dev) static void arm_smmu_remove_device(struct device *dev) { struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); - struct arm_smmu_master_data *master; + struct arm_smmu_master *master; struct arm_smmu_device *smmu; if (!fwspec || fwspec->ops != &arm_smmu_ops) @@ -1921,8 +2117,7 @@ static void arm_smmu_remove_device(struct device *dev) master = fwspec->iommu_priv; smmu = master->smmu; - if (master && master->ste.assigned) - arm_smmu_detach_dev(dev); + arm_smmu_detach_dev(master); iommu_group_remove_device(dev); iommu_device_unlink(&smmu->iommu, dev); kfree(master); @@ -2454,13 +2649,9 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass) /* Clear CR0 and sync (disables SMMU and queue processing) */ reg = readl_relaxed(smmu->base + ARM_SMMU_CR0); if (reg & CR0_SMMUEN) { - if (is_kdump_kernel()) { - arm_smmu_update_gbpa(smmu, GBPA_ABORT, 0); - arm_smmu_device_disable(smmu); - return -EBUSY; - } - dev_warn(smmu->dev, "SMMU currently enabled! Resetting...\n"); + WARN_ON(is_kdump_kernel() && !disable_bypass); + arm_smmu_update_gbpa(smmu, GBPA_ABORT, 0); } ret = arm_smmu_device_disable(smmu); @@ -2547,12 +2738,24 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass) } } + if (smmu->features & ARM_SMMU_FEAT_ATS) { + enables |= CR0_ATSCHK; + ret = arm_smmu_write_reg_sync(smmu, enables, ARM_SMMU_CR0, + ARM_SMMU_CR0ACK); + if (ret) { + dev_err(smmu->dev, "failed to enable ATS check\n"); + return ret; + } + } + ret = arm_smmu_setup_irqs(smmu); if (ret) { dev_err(smmu->dev, "failed to setup irqs\n"); return ret; } + if (is_kdump_kernel()) + enables &= ~(CR0_EVTQEN | CR0_PRIQEN); /* Enable the SMMU interface, or ensure bypass */ if (!bypass || disable_bypass) { diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index 045d93884164..5e54cc0a28b3 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -110,7 +110,8 @@ static int force_stage; module_param(force_stage, int, S_IRUGO); MODULE_PARM_DESC(force_stage, "Force SMMU mappings to be installed at a particular stage of translation. A value of '1' or '2' forces the corresponding stage. All other values are ignored (i.e. no stage is forced). Note that selecting a specific stage will disable support for nested translation."); -static bool disable_bypass; +static bool disable_bypass = + IS_ENABLED(CONFIG_ARM_SMMU_DISABLE_BYPASS_BY_DEFAULT); module_param(disable_bypass, bool, S_IRUGO); MODULE_PARM_DESC(disable_bypass, "Disable bypass streams such that incoming transactions from devices that are not attached to an iommu domain will report an abort back to the device and will not be allowed to pass through the SMMU."); @@ -569,12 +570,13 @@ static const struct iommu_gather_ops arm_smmu_s2_tlb_ops_v1 = { static irqreturn_t arm_smmu_context_fault(int irq, void *dev) { - u32 fsr, fsynr; + u32 fsr, fsynr, cbfrsynra; unsigned long iova; struct iommu_domain *domain = dev; struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); struct arm_smmu_cfg *cfg = &smmu_domain->cfg; struct arm_smmu_device *smmu = smmu_domain->smmu; + void __iomem *gr1_base = ARM_SMMU_GR1(smmu); void __iomem *cb_base; cb_base = ARM_SMMU_CB(smmu, cfg->cbndx); @@ -585,10 +587,11 @@ static irqreturn_t arm_smmu_context_fault(int irq, void *dev) fsynr = readl_relaxed(cb_base + ARM_SMMU_CB_FSYNR0); iova = readq_relaxed(cb_base + ARM_SMMU_CB_FAR); + cbfrsynra = readl_relaxed(gr1_base + ARM_SMMU_GR1_CBFRSYNRA(cfg->cbndx)); dev_err_ratelimited(smmu->dev, - "Unhandled context fault: fsr=0x%x, iova=0x%08lx, fsynr=0x%x, cb=%d\n", - fsr, iova, fsynr, cfg->cbndx); + "Unhandled context fault: fsr=0x%x, iova=0x%08lx, fsynr=0x%x, cbfrsynra=0x%x, cb=%d\n", + fsr, iova, fsynr, cbfrsynra, cfg->cbndx); writel(fsr, cb_base + ARM_SMMU_CB_FSR); return IRQ_HANDLED; diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index 9c49300e9fb7..6d969a172fbb 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -145,7 +145,7 @@ dmar_alloc_pci_notify_info(struct pci_dev *dev, unsigned long event) for (tmp = dev; tmp; tmp = tmp->bus->self) level++; - size = sizeof(*info) + level * sizeof(info->path[0]); + size = struct_size(info, path, level); if (size <= sizeof(dmar_pci_notify_info_buf)) { info = (struct dmar_pci_notify_info *)dmar_pci_notify_info_buf; } else { diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 28cb713d728c..a320bda2c305 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -2341,32 +2341,33 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, } static int domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, - struct scatterlist *sg, unsigned long phys_pfn, - unsigned long nr_pages, int prot) -{ - int ret; - struct intel_iommu *iommu; - - /* Do the real mapping first */ - ret = __domain_mapping(domain, iov_pfn, sg, phys_pfn, nr_pages, prot); - if (ret) - return ret; - - /* Notify about the new mapping */ - if (domain_type_is_vm(domain)) { - /* VM typed domains can have more than one IOMMUs */ - int iommu_id; - for_each_domain_iommu(iommu_id, domain) { - iommu = g_iommus[iommu_id]; - __mapping_notify_one(iommu, domain, iov_pfn, nr_pages); - } - } else { - /* General domains only have one IOMMU */ - iommu = domain_get_iommu(domain); - __mapping_notify_one(iommu, domain, iov_pfn, nr_pages); - } + struct scatterlist *sg, unsigned long phys_pfn, + unsigned long nr_pages, int prot) +{ + int ret; + struct intel_iommu *iommu; + + /* Do the real mapping first */ + ret = __domain_mapping(domain, iov_pfn, sg, phys_pfn, nr_pages, prot); + if (ret) + return ret; + + /* Notify about the new mapping */ + if (domain_type_is_vm(domain)) { + /* VM typed domains can have more than one IOMMUs */ + int iommu_id; + + for_each_domain_iommu(iommu_id, domain) { + iommu = g_iommus[iommu_id]; + __mapping_notify_one(iommu, domain, iov_pfn, nr_pages); + } + } else { + /* General domains only have one IOMMU */ + iommu = domain_get_iommu(domain); + __mapping_notify_one(iommu, domain, iov_pfn, nr_pages); + } - return 0; + return 0; } static inline int domain_sg_mapping(struct dmar_domain *domain, unsigned long iov_pfn, @@ -2485,6 +2486,8 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu, info->domain = domain; info->iommu = iommu; info->pasid_table = NULL; + info->auxd_enabled = 0; + INIT_LIST_HEAD(&info->auxiliary_domains); if (dev && dev_is_pci(dev)) { struct pci_dev *pdev = to_pci_dev(info->dev); @@ -3412,9 +3415,12 @@ static int __init init_dmars(void) iommu_identity_mapping |= IDENTMAP_ALL; #ifdef CONFIG_INTEL_IOMMU_BROKEN_GFX_WA - iommu_identity_mapping |= IDENTMAP_GFX; + dmar_map_gfx = 0; #endif + if (!dmar_map_gfx) + iommu_identity_mapping |= IDENTMAP_GFX; + check_tylersburg_isoch(); if (iommu_identity_mapping) { @@ -3496,7 +3502,13 @@ domains_done: #ifdef CONFIG_INTEL_IOMMU_SVM if (pasid_supported(iommu) && ecap_prs(iommu->ecap)) { + /* + * Call dmar_alloc_hwirq() with dmar_global_lock held, + * could cause possible lock race condition. + */ + up_write(&dmar_global_lock); ret = intel_svm_enable_prq(iommu); + down_write(&dmar_global_lock); if (ret) goto free_iommu; } @@ -3606,45 +3618,40 @@ out: } /* Check if the dev needs to go through non-identity map and unmap process.*/ -static int iommu_no_mapping(struct device *dev) +static bool iommu_need_mapping(struct device *dev) { int found; if (iommu_dummy(dev)) - return 1; + return false; if (!iommu_identity_mapping) - return 0; + return true; found = identity_mapping(dev); if (found) { if (iommu_should_identity_map(dev, 0)) - return 1; - else { - /* - * 32 bit DMA is removed from si_domain and fall back - * to non-identity mapping. - */ - dmar_remove_one_dev_info(dev); - dev_info(dev, "32bit DMA uses non-identity mapping\n"); - return 0; - } + return false; + + /* + * 32 bit DMA is removed from si_domain and fall back to + * non-identity mapping. + */ + dmar_remove_one_dev_info(dev); + dev_info(dev, "32bit DMA uses non-identity mapping\n"); } else { /* * In case of a detached 64 bit DMA device from vm, the device * is put into si_domain for identity mapping. */ - if (iommu_should_identity_map(dev, 0)) { - int ret; - ret = domain_add_dev_info(si_domain, dev); - if (!ret) { - dev_info(dev, "64bit DMA uses identity mapping\n"); - return 1; - } + if (iommu_should_identity_map(dev, 0) && + !domain_add_dev_info(si_domain, dev)) { + dev_info(dev, "64bit DMA uses identity mapping\n"); + return false; } } - return 0; + return true; } static dma_addr_t __intel_map_single(struct device *dev, phys_addr_t paddr, @@ -3660,9 +3667,6 @@ static dma_addr_t __intel_map_single(struct device *dev, phys_addr_t paddr, BUG_ON(dir == DMA_NONE); - if (iommu_no_mapping(dev)) - return paddr; - domain = get_valid_domain_for_dev(dev); if (!domain) return DMA_MAPPING_ERROR; @@ -3711,15 +3715,20 @@ static dma_addr_t intel_map_page(struct device *dev, struct page *page, enum dma_data_direction dir, unsigned long attrs) { - return __intel_map_single(dev, page_to_phys(page) + offset, size, - dir, *dev->dma_mask); + if (iommu_need_mapping(dev)) + return __intel_map_single(dev, page_to_phys(page) + offset, + size, dir, *dev->dma_mask); + return dma_direct_map_page(dev, page, offset, size, dir, attrs); } static dma_addr_t intel_map_resource(struct device *dev, phys_addr_t phys_addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { - return __intel_map_single(dev, phys_addr, size, dir, *dev->dma_mask); + if (iommu_need_mapping(dev)) + return __intel_map_single(dev, phys_addr, size, dir, + *dev->dma_mask); + return dma_direct_map_resource(dev, phys_addr, size, dir, attrs); } static void intel_unmap(struct device *dev, dma_addr_t dev_addr, size_t size) @@ -3730,9 +3739,7 @@ static void intel_unmap(struct device *dev, dma_addr_t dev_addr, size_t size) unsigned long iova_pfn; struct intel_iommu *iommu; struct page *freelist; - - if (iommu_no_mapping(dev)) - return; + struct pci_dev *pdev = NULL; domain = find_domain(dev); BUG_ON(!domain); @@ -3745,11 +3752,14 @@ static void intel_unmap(struct device *dev, dma_addr_t dev_addr, size_t size) start_pfn = mm_to_dma_pfn(iova_pfn); last_pfn = start_pfn + nrpages - 1; + if (dev_is_pci(dev)) + pdev = to_pci_dev(dev); + dev_dbg(dev, "Device unmapping: pfn %lx-%lx\n", start_pfn, last_pfn); freelist = domain_unmap(domain, start_pfn, last_pfn); - if (intel_iommu_strict) { + if (intel_iommu_strict || (pdev && pdev->untrusted)) { iommu_flush_iotlb_psi(iommu, domain, start_pfn, nrpages, !freelist, 0); /* free iova */ @@ -3769,7 +3779,17 @@ static void intel_unmap_page(struct device *dev, dma_addr_t dev_addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { - intel_unmap(dev, dev_addr, size); + if (iommu_need_mapping(dev)) + intel_unmap(dev, dev_addr, size); + else + dma_direct_unmap_page(dev, dev_addr, size, dir, attrs); +} + +static void intel_unmap_resource(struct device *dev, dma_addr_t dev_addr, + size_t size, enum dma_data_direction dir, unsigned long attrs) +{ + if (iommu_need_mapping(dev)) + intel_unmap(dev, dev_addr, size); } static void *intel_alloc_coherent(struct device *dev, size_t size, @@ -3779,28 +3799,17 @@ static void *intel_alloc_coherent(struct device *dev, size_t size, struct page *page = NULL; int order; + if (!iommu_need_mapping(dev)) + return dma_direct_alloc(dev, size, dma_handle, flags, attrs); + size = PAGE_ALIGN(size); order = get_order(size); - if (!iommu_no_mapping(dev)) - flags &= ~(GFP_DMA | GFP_DMA32); - else if (dev->coherent_dma_mask < dma_get_required_mask(dev)) { - if (dev->coherent_dma_mask < DMA_BIT_MASK(32)) - flags |= GFP_DMA; - else - flags |= GFP_DMA32; - } - if (gfpflags_allow_blocking(flags)) { unsigned int count = size >> PAGE_SHIFT; page = dma_alloc_from_contiguous(dev, count, order, flags & __GFP_NOWARN); - if (page && iommu_no_mapping(dev) && - page_to_phys(page) + size > dev->coherent_dma_mask) { - dma_release_from_contiguous(dev, page, count); - page = NULL; - } } if (!page) @@ -3826,6 +3835,9 @@ static void intel_free_coherent(struct device *dev, size_t size, void *vaddr, int order; struct page *page = virt_to_page(vaddr); + if (!iommu_need_mapping(dev)) + return dma_direct_free(dev, size, vaddr, dma_handle, attrs); + size = PAGE_ALIGN(size); order = get_order(size); @@ -3843,6 +3855,9 @@ static void intel_unmap_sg(struct device *dev, struct scatterlist *sglist, struct scatterlist *sg; int i; + if (!iommu_need_mapping(dev)) + return dma_direct_unmap_sg(dev, sglist, nelems, dir, attrs); + for_each_sg(sglist, sg, nelems, i) { nrpages += aligned_nrpages(sg_dma_address(sg), sg_dma_len(sg)); } @@ -3850,20 +3865,6 @@ static void intel_unmap_sg(struct device *dev, struct scatterlist *sglist, intel_unmap(dev, startaddr, nrpages << VTD_PAGE_SHIFT); } -static int intel_nontranslate_map_sg(struct device *hddev, - struct scatterlist *sglist, int nelems, int dir) -{ - int i; - struct scatterlist *sg; - - for_each_sg(sglist, sg, nelems, i) { - BUG_ON(!sg_page(sg)); - sg->dma_address = sg_phys(sg); - sg->dma_length = sg->length; - } - return nelems; -} - static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nelems, enum dma_data_direction dir, unsigned long attrs) { @@ -3878,8 +3879,8 @@ static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nele struct intel_iommu *iommu; BUG_ON(dir == DMA_NONE); - if (iommu_no_mapping(dev)) - return intel_nontranslate_map_sg(dev, sglist, nelems, dir); + if (!iommu_need_mapping(dev)) + return dma_direct_map_sg(dev, sglist, nelems, dir, attrs); domain = get_valid_domain_for_dev(dev); if (!domain) @@ -3929,7 +3930,7 @@ static const struct dma_map_ops intel_dma_ops = { .map_page = intel_map_page, .unmap_page = intel_unmap_page, .map_resource = intel_map_resource, - .unmap_resource = intel_unmap_page, + .unmap_resource = intel_unmap_resource, .dma_supported = dma_direct_supported, }; @@ -4055,9 +4056,7 @@ static void __init init_no_remapping_devices(void) /* This IOMMU has *only* gfx devices. Either bypass it or set the gfx_mapped flag, as appropriate */ - if (dmar_map_gfx) { - intel_iommu_gfx_mapped = 1; - } else { + if (!dmar_map_gfx) { drhd->ignored = 1; for_each_active_dev_scope(drhd->devices, drhd->devices_cnt, i, dev) @@ -4086,7 +4085,7 @@ static int init_iommu_hw(void) iommu_disable_protect_mem_regions(iommu); continue; } - + iommu_flush_write_buffer(iommu); iommu_set_root_entry(iommu); @@ -4896,6 +4895,9 @@ int __init intel_iommu_init(void) goto out_free_reserved_range; } + if (dmar_map_gfx) + intel_iommu_gfx_mapped = 1; + init_no_remapping_devices(); ret = init_dmars(); @@ -5065,35 +5067,139 @@ static void intel_iommu_domain_free(struct iommu_domain *domain) domain_exit(to_dmar_domain(domain)); } -static int intel_iommu_attach_device(struct iommu_domain *domain, - struct device *dev) +/* + * Check whether a @domain could be attached to the @dev through the + * aux-domain attach/detach APIs. + */ +static inline bool +is_aux_domain(struct device *dev, struct iommu_domain *domain) { - struct dmar_domain *dmar_domain = to_dmar_domain(domain); - struct intel_iommu *iommu; - int addr_width; - u8 bus, devfn; + struct device_domain_info *info = dev->archdata.iommu; - if (device_is_rmrr_locked(dev)) { - dev_warn(dev, "Device is ineligible for IOMMU domain attach due to platform RMRR requirement. Contact your platform vendor.\n"); - return -EPERM; - } + return info && info->auxd_enabled && + domain->type == IOMMU_DOMAIN_UNMANAGED; +} - /* normally dev is not mapped */ - if (unlikely(domain_context_mapped(dev))) { - struct dmar_domain *old_domain; +static void auxiliary_link_device(struct dmar_domain *domain, + struct device *dev) +{ + struct device_domain_info *info = dev->archdata.iommu; - old_domain = find_domain(dev); - if (old_domain) { - rcu_read_lock(); - dmar_remove_one_dev_info(dev); - rcu_read_unlock(); + assert_spin_locked(&device_domain_lock); + if (WARN_ON(!info)) + return; - if (!domain_type_is_vm_or_si(old_domain) && - list_empty(&old_domain->devices)) - domain_exit(old_domain); + domain->auxd_refcnt++; + list_add(&domain->auxd, &info->auxiliary_domains); +} + +static void auxiliary_unlink_device(struct dmar_domain *domain, + struct device *dev) +{ + struct device_domain_info *info = dev->archdata.iommu; + + assert_spin_locked(&device_domain_lock); + if (WARN_ON(!info)) + return; + + list_del(&domain->auxd); + domain->auxd_refcnt--; + + if (!domain->auxd_refcnt && domain->default_pasid > 0) + intel_pasid_free_id(domain->default_pasid); +} + +static int aux_domain_add_dev(struct dmar_domain *domain, + struct device *dev) +{ + int ret; + u8 bus, devfn; + unsigned long flags; + struct intel_iommu *iommu; + + iommu = device_to_iommu(dev, &bus, &devfn); + if (!iommu) + return -ENODEV; + + if (domain->default_pasid <= 0) { + int pasid; + + pasid = intel_pasid_alloc_id(domain, PASID_MIN, + pci_max_pasids(to_pci_dev(dev)), + GFP_KERNEL); + if (pasid <= 0) { + pr_err("Can't allocate default pasid\n"); + return -ENODEV; } + domain->default_pasid = pasid; } + spin_lock_irqsave(&device_domain_lock, flags); + /* + * iommu->lock must be held to attach domain to iommu and setup the + * pasid entry for second level translation. + */ + spin_lock(&iommu->lock); + ret = domain_attach_iommu(domain, iommu); + if (ret) + goto attach_failed; + + /* Setup the PASID entry for mediated devices: */ + ret = intel_pasid_setup_second_level(iommu, domain, dev, + domain->default_pasid); + if (ret) + goto table_failed; + spin_unlock(&iommu->lock); + + auxiliary_link_device(domain, dev); + + spin_unlock_irqrestore(&device_domain_lock, flags); + + return 0; + +table_failed: + domain_detach_iommu(domain, iommu); +attach_failed: + spin_unlock(&iommu->lock); + spin_unlock_irqrestore(&device_domain_lock, flags); + if (!domain->auxd_refcnt && domain->default_pasid > 0) + intel_pasid_free_id(domain->default_pasid); + + return ret; +} + +static void aux_domain_remove_dev(struct dmar_domain *domain, + struct device *dev) +{ + struct device_domain_info *info; + struct intel_iommu *iommu; + unsigned long flags; + + if (!is_aux_domain(dev, &domain->domain)) + return; + + spin_lock_irqsave(&device_domain_lock, flags); + info = dev->archdata.iommu; + iommu = info->iommu; + + auxiliary_unlink_device(domain, dev); + + spin_lock(&iommu->lock); + intel_pasid_tear_down_entry(iommu, dev, domain->default_pasid); + domain_detach_iommu(domain, iommu); + spin_unlock(&iommu->lock); + + spin_unlock_irqrestore(&device_domain_lock, flags); +} + +static int prepare_domain_attach_device(struct iommu_domain *domain, + struct device *dev) +{ + struct dmar_domain *dmar_domain = to_dmar_domain(domain); + struct intel_iommu *iommu; + int addr_width; + u8 bus, devfn; + iommu = device_to_iommu(dev, &bus, &devfn); if (!iommu) return -ENODEV; @@ -5126,7 +5232,58 @@ static int intel_iommu_attach_device(struct iommu_domain *domain, dmar_domain->agaw--; } - return domain_add_dev_info(dmar_domain, dev); + return 0; +} + +static int intel_iommu_attach_device(struct iommu_domain *domain, + struct device *dev) +{ + int ret; + + if (device_is_rmrr_locked(dev)) { + dev_warn(dev, "Device is ineligible for IOMMU domain attach due to platform RMRR requirement. Contact your platform vendor.\n"); + return -EPERM; + } + + if (is_aux_domain(dev, domain)) + return -EPERM; + + /* normally dev is not mapped */ + if (unlikely(domain_context_mapped(dev))) { + struct dmar_domain *old_domain; + + old_domain = find_domain(dev); + if (old_domain) { + rcu_read_lock(); + dmar_remove_one_dev_info(dev); + rcu_read_unlock(); + + if (!domain_type_is_vm_or_si(old_domain) && + list_empty(&old_domain->devices)) + domain_exit(old_domain); + } + } + + ret = prepare_domain_attach_device(domain, dev); + if (ret) + return ret; + + return domain_add_dev_info(to_dmar_domain(domain), dev); +} + +static int intel_iommu_aux_attach_device(struct iommu_domain *domain, + struct device *dev) +{ + int ret; + + if (!is_aux_domain(dev, domain)) + return -EPERM; + + ret = prepare_domain_attach_device(domain, dev); + if (ret) + return ret; + + return aux_domain_add_dev(to_dmar_domain(domain), dev); } static void intel_iommu_detach_device(struct iommu_domain *domain, @@ -5135,6 +5292,12 @@ static void intel_iommu_detach_device(struct iommu_domain *domain, dmar_remove_one_dev_info(dev); } +static void intel_iommu_aux_detach_device(struct iommu_domain *domain, + struct device *dev) +{ + aux_domain_remove_dev(to_dmar_domain(domain), dev); +} + static int intel_iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t hpa, size_t size, int iommu_prot) @@ -5223,6 +5386,42 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain, return phys; } +static inline bool scalable_mode_support(void) +{ + struct dmar_drhd_unit *drhd; + struct intel_iommu *iommu; + bool ret = true; + + rcu_read_lock(); + for_each_active_iommu(iommu, drhd) { + if (!sm_supported(iommu)) { + ret = false; + break; + } + } + rcu_read_unlock(); + + return ret; +} + +static inline bool iommu_pasid_support(void) +{ + struct dmar_drhd_unit *drhd; + struct intel_iommu *iommu; + bool ret = true; + + rcu_read_lock(); + for_each_active_iommu(iommu, drhd) { + if (!pasid_supported(iommu)) { + ret = false; + break; + } + } + rcu_read_unlock(); + + return ret; +} + static bool intel_iommu_capable(enum iommu_cap cap) { if (cap == IOMMU_CAP_CACHE_COHERENCY) @@ -5307,8 +5506,7 @@ static void intel_iommu_put_resv_regions(struct device *dev, } } -#ifdef CONFIG_INTEL_IOMMU_SVM -int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sdev) +int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct device *dev) { struct device_domain_info *info; struct context_entry *context; @@ -5317,7 +5515,7 @@ int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sd u64 ctx_lo; int ret; - domain = get_valid_domain_for_dev(sdev->dev); + domain = get_valid_domain_for_dev(dev); if (!domain) return -EINVAL; @@ -5325,7 +5523,7 @@ int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sd spin_lock(&iommu->lock); ret = -EINVAL; - info = sdev->dev->archdata.iommu; + info = dev->archdata.iommu; if (!info || !info->pasid_supported) goto out; @@ -5335,14 +5533,13 @@ int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sd ctx_lo = context[0].lo; - sdev->did = FLPT_DEFAULT_DID; - sdev->sid = PCI_DEVID(info->bus, info->devfn); - if (!(ctx_lo & CONTEXT_PASIDE)) { ctx_lo |= CONTEXT_PASIDE; context[0].lo = ctx_lo; wmb(); - iommu->flush.flush_context(iommu, sdev->did, sdev->sid, + iommu->flush.flush_context(iommu, + domain->iommu_did[iommu->seq_id], + PCI_DEVID(info->bus, info->devfn), DMA_CCMD_MASK_NOBIT, DMA_CCMD_DEVICE_INVL); } @@ -5351,12 +5548,6 @@ int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sd if (!info->pasid_enabled) iommu_enable_dev_iotlb(info); - if (info->ats_enabled) { - sdev->dev_iotlb = 1; - sdev->qdep = info->ats_qdep; - if (sdev->qdep >= QI_DEV_EIOTLB_MAX_INVS) - sdev->qdep = 0; - } ret = 0; out: @@ -5366,6 +5557,7 @@ int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sd return ret; } +#ifdef CONFIG_INTEL_IOMMU_SVM struct intel_iommu *intel_svm_device_to_iommu(struct device *dev) { struct intel_iommu *iommu; @@ -5387,12 +5579,142 @@ struct intel_iommu *intel_svm_device_to_iommu(struct device *dev) } #endif /* CONFIG_INTEL_IOMMU_SVM */ +static int intel_iommu_enable_auxd(struct device *dev) +{ + struct device_domain_info *info; + struct intel_iommu *iommu; + unsigned long flags; + u8 bus, devfn; + int ret; + + iommu = device_to_iommu(dev, &bus, &devfn); + if (!iommu || dmar_disabled) + return -EINVAL; + + if (!sm_supported(iommu) || !pasid_supported(iommu)) + return -EINVAL; + + ret = intel_iommu_enable_pasid(iommu, dev); + if (ret) + return -ENODEV; + + spin_lock_irqsave(&device_domain_lock, flags); + info = dev->archdata.iommu; + info->auxd_enabled = 1; + spin_unlock_irqrestore(&device_domain_lock, flags); + + return 0; +} + +static int intel_iommu_disable_auxd(struct device *dev) +{ + struct device_domain_info *info; + unsigned long flags; + + spin_lock_irqsave(&device_domain_lock, flags); + info = dev->archdata.iommu; + if (!WARN_ON(!info)) + info->auxd_enabled = 0; + spin_unlock_irqrestore(&device_domain_lock, flags); + + return 0; +} + +/* + * A PCI express designated vendor specific extended capability is defined + * in the section 3.7 of Intel scalable I/O virtualization technical spec + * for system software and tools to detect endpoint devices supporting the + * Intel scalable IO virtualization without host driver dependency. + * + * Returns the address of the matching extended capability structure within + * the device's PCI configuration space or 0 if the device does not support + * it. + */ +static int siov_find_pci_dvsec(struct pci_dev *pdev) +{ + int pos; + u16 vendor, id; + + pos = pci_find_next_ext_capability(pdev, 0, 0x23); + while (pos) { + pci_read_config_word(pdev, pos + 4, &vendor); + pci_read_config_word(pdev, pos + 8, &id); + if (vendor == PCI_VENDOR_ID_INTEL && id == 5) + return pos; + + pos = pci_find_next_ext_capability(pdev, pos, 0x23); + } + + return 0; +} + +static bool +intel_iommu_dev_has_feat(struct device *dev, enum iommu_dev_features feat) +{ + if (feat == IOMMU_DEV_FEAT_AUX) { + int ret; + + if (!dev_is_pci(dev) || dmar_disabled || + !scalable_mode_support() || !iommu_pasid_support()) + return false; + + ret = pci_pasid_features(to_pci_dev(dev)); + if (ret < 0) + return false; + + return !!siov_find_pci_dvsec(to_pci_dev(dev)); + } + + return false; +} + +static int +intel_iommu_dev_enable_feat(struct device *dev, enum iommu_dev_features feat) +{ + if (feat == IOMMU_DEV_FEAT_AUX) + return intel_iommu_enable_auxd(dev); + + return -ENODEV; +} + +static int +intel_iommu_dev_disable_feat(struct device *dev, enum iommu_dev_features feat) +{ + if (feat == IOMMU_DEV_FEAT_AUX) + return intel_iommu_disable_auxd(dev); + + return -ENODEV; +} + +static bool +intel_iommu_dev_feat_enabled(struct device *dev, enum iommu_dev_features feat) +{ + struct device_domain_info *info = dev->archdata.iommu; + + if (feat == IOMMU_DEV_FEAT_AUX) + return scalable_mode_support() && info && info->auxd_enabled; + + return false; +} + +static int +intel_iommu_aux_get_pasid(struct iommu_domain *domain, struct device *dev) +{ + struct dmar_domain *dmar_domain = to_dmar_domain(domain); + + return dmar_domain->default_pasid > 0 ? + dmar_domain->default_pasid : -EINVAL; +} + const struct iommu_ops intel_iommu_ops = { .capable = intel_iommu_capable, .domain_alloc = intel_iommu_domain_alloc, .domain_free = intel_iommu_domain_free, .attach_dev = intel_iommu_attach_device, .detach_dev = intel_iommu_detach_device, + .aux_attach_dev = intel_iommu_aux_attach_device, + .aux_detach_dev = intel_iommu_aux_detach_device, + .aux_get_pasid = intel_iommu_aux_get_pasid, .map = intel_iommu_map, .unmap = intel_iommu_unmap, .iova_to_phys = intel_iommu_iova_to_phys, @@ -5401,6 +5723,10 @@ const struct iommu_ops intel_iommu_ops = { .get_resv_regions = intel_iommu_get_resv_regions, .put_resv_regions = intel_iommu_put_resv_regions, .device_group = pci_device_group, + .dev_has_feat = intel_iommu_dev_has_feat, + .dev_feat_enabled = intel_iommu_dev_feat_enabled, + .dev_enable_feat = intel_iommu_dev_enable_feat, + .dev_disable_feat = intel_iommu_dev_disable_feat, .pgsize_bitmap = INTEL_IOMMU_PGSIZES, }; diff --git a/drivers/iommu/intel-pasid.c b/drivers/iommu/intel-pasid.c index 03b12d2ee213..2fefeafda437 100644 --- a/drivers/iommu/intel-pasid.c +++ b/drivers/iommu/intel-pasid.c @@ -154,8 +154,10 @@ int intel_pasid_alloc_table(struct device *dev) order = size ? get_order(size) : 0; pages = alloc_pages_node(info->iommu->node, GFP_KERNEL | __GFP_ZERO, order); - if (!pages) + if (!pages) { + kfree(pasid_table); return -ENOMEM; + } pasid_table->table = page_address(pages); pasid_table->order = order; diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c index 3a4b09ae8561..8f87304f915c 100644 --- a/drivers/iommu/intel-svm.c +++ b/drivers/iommu/intel-svm.c @@ -228,6 +228,7 @@ static LIST_HEAD(global_svm_list); int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_ops *ops) { struct intel_iommu *iommu = intel_svm_device_to_iommu(dev); + struct device_domain_info *info; struct intel_svm_dev *sdev; struct intel_svm *svm = NULL; struct mm_struct *mm = NULL; @@ -291,13 +292,29 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_ } sdev->dev = dev; - ret = intel_iommu_enable_pasid(iommu, sdev); + ret = intel_iommu_enable_pasid(iommu, dev); if (ret || !pasid) { /* If they don't actually want to assign a PASID, this is * just an enabling check/preparation. */ kfree(sdev); goto out; } + + info = dev->archdata.iommu; + if (!info || !info->pasid_supported) { + kfree(sdev); + goto out; + } + + sdev->did = FLPT_DEFAULT_DID; + sdev->sid = PCI_DEVID(info->bus, info->devfn); + if (info->ats_enabled) { + sdev->dev_iotlb = 1; + sdev->qdep = info->ats_qdep; + if (sdev->qdep >= QI_DEV_EIOTLB_MAX_INVS) + sdev->qdep = 0; + } + /* Finish the setup now we know we're keeping it */ sdev->users = 1; sdev->ops = ops; diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c index 2d74641b7f7b..634d8f059019 100644 --- a/drivers/iommu/intel_irq_remapping.c +++ b/drivers/iommu/intel_irq_remapping.c @@ -548,8 +548,7 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu) goto out_free_table; } - bitmap = kcalloc(BITS_TO_LONGS(INTR_REMAP_TABLE_ENTRIES), - sizeof(long), GFP_ATOMIC); + bitmap = bitmap_zalloc(INTR_REMAP_TABLE_ENTRIES, GFP_ATOMIC); if (bitmap == NULL) { pr_err("IR%d: failed to allocate bitmap\n", iommu->seq_id); goto out_free_pages; @@ -616,7 +615,7 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu) return 0; out_free_bitmap: - kfree(bitmap); + bitmap_free(bitmap); out_free_pages: __free_pages(pages, INTR_REMAP_PAGE_ORDER); out_free_table: @@ -640,7 +639,7 @@ static void intel_teardown_irq_remapping(struct intel_iommu *iommu) } free_pages((unsigned long)iommu->ir_table->base, INTR_REMAP_PAGE_ORDER); - kfree(iommu->ir_table->bitmap); + bitmap_free(iommu->ir_table->bitmap); kfree(iommu->ir_table); iommu->ir_table = NULL; } diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 109de67d5d72..67ee6623f9b2 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -45,10 +45,6 @@ static unsigned int iommu_def_domain_type = IOMMU_DOMAIN_DMA; #endif static bool iommu_dma_strict __read_mostly = true; -struct iommu_callback_data { - const struct iommu_ops *ops; -}; - struct iommu_group { struct kobject kobj; struct kobject *devices_kobj; @@ -1217,9 +1213,6 @@ static int iommu_bus_init(struct bus_type *bus, const struct iommu_ops *ops) { int err; struct notifier_block *nb; - struct iommu_callback_data cb = { - .ops = ops, - }; nb = kzalloc(sizeof(struct notifier_block), GFP_KERNEL); if (!nb) @@ -1231,7 +1224,7 @@ static int iommu_bus_init(struct bus_type *bus, const struct iommu_ops *ops) if (err) goto out_free; - err = bus_for_each_dev(bus, NULL, &cb, add_iommu_group); + err = bus_for_each_dev(bus, NULL, NULL, add_iommu_group); if (err) goto out_err; @@ -1240,7 +1233,7 @@ static int iommu_bus_init(struct bus_type *bus, const struct iommu_ops *ops) out_err: /* Clean up */ - bus_for_each_dev(bus, NULL, &cb, remove_iommu_group); + bus_for_each_dev(bus, NULL, NULL, remove_iommu_group); bus_unregister_notifier(bus, nb); out_free: @@ -2039,3 +2032,203 @@ int iommu_fwspec_add_ids(struct device *dev, u32 *ids, int num_ids) return 0; } EXPORT_SYMBOL_GPL(iommu_fwspec_add_ids); + +/* + * Per device IOMMU features. + */ +bool iommu_dev_has_feature(struct device *dev, enum iommu_dev_features feat) +{ + const struct iommu_ops *ops = dev->bus->iommu_ops; + + if (ops && ops->dev_has_feat) + return ops->dev_has_feat(dev, feat); + + return false; +} +EXPORT_SYMBOL_GPL(iommu_dev_has_feature); + +int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features feat) +{ + const struct iommu_ops *ops = dev->bus->iommu_ops; + + if (ops && ops->dev_enable_feat) + return ops->dev_enable_feat(dev, feat); + + return -ENODEV; +} +EXPORT_SYMBOL_GPL(iommu_dev_enable_feature); + +/* + * The device drivers should do the necessary cleanups before calling this. + * For example, before disabling the aux-domain feature, the device driver + * should detach all aux-domains. Otherwise, this will return -EBUSY. + */ +int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features feat) +{ + const struct iommu_ops *ops = dev->bus->iommu_ops; + + if (ops && ops->dev_disable_feat) + return ops->dev_disable_feat(dev, feat); + + return -EBUSY; +} +EXPORT_SYMBOL_GPL(iommu_dev_disable_feature); + +bool iommu_dev_feature_enabled(struct device *dev, enum iommu_dev_features feat) +{ + const struct iommu_ops *ops = dev->bus->iommu_ops; + + if (ops && ops->dev_feat_enabled) + return ops->dev_feat_enabled(dev, feat); + + return false; +} +EXPORT_SYMBOL_GPL(iommu_dev_feature_enabled); + +/* + * Aux-domain specific attach/detach. + * + * Only works if iommu_dev_feature_enabled(dev, IOMMU_DEV_FEAT_AUX) returns + * true. Also, as long as domains are attached to a device through this + * interface, any tries to call iommu_attach_device() should fail + * (iommu_detach_device() can't fail, so we fail when trying to re-attach). + * This should make us safe against a device being attached to a guest as a + * whole while there are still pasid users on it (aux and sva). + */ +int iommu_aux_attach_device(struct iommu_domain *domain, struct device *dev) +{ + int ret = -ENODEV; + + if (domain->ops->aux_attach_dev) + ret = domain->ops->aux_attach_dev(domain, dev); + + if (!ret) + trace_attach_device_to_domain(dev); + + return ret; +} +EXPORT_SYMBOL_GPL(iommu_aux_attach_device); + +void iommu_aux_detach_device(struct iommu_domain *domain, struct device *dev) +{ + if (domain->ops->aux_detach_dev) { + domain->ops->aux_detach_dev(domain, dev); + trace_detach_device_from_domain(dev); + } +} +EXPORT_SYMBOL_GPL(iommu_aux_detach_device); + +int iommu_aux_get_pasid(struct iommu_domain *domain, struct device *dev) +{ + int ret = -ENODEV; + + if (domain->ops->aux_get_pasid) + ret = domain->ops->aux_get_pasid(domain, dev); + + return ret; +} +EXPORT_SYMBOL_GPL(iommu_aux_get_pasid); + +/** + * iommu_sva_bind_device() - Bind a process address space to a device + * @dev: the device + * @mm: the mm to bind, caller must hold a reference to it + * + * Create a bond between device and address space, allowing the device to access + * the mm using the returned PASID. If a bond already exists between @device and + * @mm, it is returned and an additional reference is taken. Caller must call + * iommu_sva_unbind_device() to release each reference. + * + * iommu_dev_enable_feature(dev, IOMMU_DEV_FEAT_SVA) must be called first, to + * initialize the required SVA features. + * + * On error, returns an ERR_PTR value. + */ +struct iommu_sva * +iommu_sva_bind_device(struct device *dev, struct mm_struct *mm, void *drvdata) +{ + struct iommu_group *group; + struct iommu_sva *handle = ERR_PTR(-EINVAL); + const struct iommu_ops *ops = dev->bus->iommu_ops; + + if (!ops || !ops->sva_bind) + return ERR_PTR(-ENODEV); + + group = iommu_group_get(dev); + if (!group) + return ERR_PTR(-ENODEV); + + /* Ensure device count and domain don't change while we're binding */ + mutex_lock(&group->mutex); + + /* + * To keep things simple, SVA currently doesn't support IOMMU groups + * with more than one device. Existing SVA-capable systems are not + * affected by the problems that required IOMMU groups (lack of ACS + * isolation, device ID aliasing and other hardware issues). + */ + if (iommu_group_device_count(group) != 1) + goto out_unlock; + + handle = ops->sva_bind(dev, mm, drvdata); + +out_unlock: + mutex_unlock(&group->mutex); + iommu_group_put(group); + + return handle; +} +EXPORT_SYMBOL_GPL(iommu_sva_bind_device); + +/** + * iommu_sva_unbind_device() - Remove a bond created with iommu_sva_bind_device + * @handle: the handle returned by iommu_sva_bind_device() + * + * Put reference to a bond between device and address space. The device should + * not be issuing any more transaction for this PASID. All outstanding page + * requests for this PASID must have been flushed to the IOMMU. + * + * Returns 0 on success, or an error value + */ +void iommu_sva_unbind_device(struct iommu_sva *handle) +{ + struct iommu_group *group; + struct device *dev = handle->dev; + const struct iommu_ops *ops = dev->bus->iommu_ops; + + if (!ops || !ops->sva_unbind) + return; + + group = iommu_group_get(dev); + if (!group) + return; + + mutex_lock(&group->mutex); + ops->sva_unbind(handle); + mutex_unlock(&group->mutex); + + iommu_group_put(group); +} +EXPORT_SYMBOL_GPL(iommu_sva_unbind_device); + +int iommu_sva_set_ops(struct iommu_sva *handle, + const struct iommu_sva_ops *sva_ops) +{ + if (handle->ops && handle->ops != sva_ops) + return -EEXIST; + + handle->ops = sva_ops; + return 0; +} +EXPORT_SYMBOL_GPL(iommu_sva_set_ops); + +int iommu_sva_get_pasid(struct iommu_sva *handle) +{ + const struct iommu_ops *ops = handle->dev->bus->iommu_ops; + + if (!ops || !ops->sva_get_pasid) + return IOMMU_PASID_INVALID; + + return ops->sva_get_pasid(handle); +} +EXPORT_SYMBOL_GPL(iommu_sva_get_pasid); diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index 5182c7d6171e..463ee08f7d3a 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -102,7 +102,6 @@ static inline u32 smmu_readl(struct tegra_smmu *smmu, unsigned long offset) #define SMMU_TLB_FLUSH_VA_MATCH_ALL (0 << 0) #define SMMU_TLB_FLUSH_VA_MATCH_SECTION (2 << 0) #define SMMU_TLB_FLUSH_VA_MATCH_GROUP (3 << 0) -#define SMMU_TLB_FLUSH_ASID(x) (((x) & 0x7f) << 24) #define SMMU_TLB_FLUSH_VA_SECTION(addr) ((((addr) & 0xffc00000) >> 12) | \ SMMU_TLB_FLUSH_VA_MATCH_SECTION) #define SMMU_TLB_FLUSH_VA_GROUP(addr) ((((addr) & 0xffffc000) >> 12) | \ @@ -146,8 +145,6 @@ static inline u32 smmu_readl(struct tegra_smmu *smmu, unsigned long offset) #define SMMU_PDE_ATTR (SMMU_PDE_READABLE | SMMU_PDE_WRITABLE | \ SMMU_PDE_NONSECURE) -#define SMMU_PTE_ATTR (SMMU_PTE_READABLE | SMMU_PTE_WRITABLE | \ - SMMU_PTE_NONSECURE) static unsigned int iova_pd_index(unsigned long iova) { @@ -205,8 +202,12 @@ static inline void smmu_flush_tlb_asid(struct tegra_smmu *smmu, { u32 value; - value = SMMU_TLB_FLUSH_ASID_MATCH | SMMU_TLB_FLUSH_ASID(asid) | - SMMU_TLB_FLUSH_VA_MATCH_ALL; + if (smmu->soc->num_asids == 4) + value = (asid & 0x3) << 29; + else + value = (asid & 0x7f) << 24; + + value |= SMMU_TLB_FLUSH_ASID_MATCH | SMMU_TLB_FLUSH_VA_MATCH_ALL; smmu_writel(smmu, value, SMMU_TLB_FLUSH); } @@ -216,8 +217,12 @@ static inline void smmu_flush_tlb_section(struct tegra_smmu *smmu, { u32 value; - value = SMMU_TLB_FLUSH_ASID_MATCH | SMMU_TLB_FLUSH_ASID(asid) | - SMMU_TLB_FLUSH_VA_SECTION(iova); + if (smmu->soc->num_asids == 4) + value = (asid & 0x3) << 29; + else + value = (asid & 0x7f) << 24; + + value |= SMMU_TLB_FLUSH_ASID_MATCH | SMMU_TLB_FLUSH_VA_SECTION(iova); smmu_writel(smmu, value, SMMU_TLB_FLUSH); } @@ -227,8 +232,12 @@ static inline void smmu_flush_tlb_group(struct tegra_smmu *smmu, { u32 value; - value = SMMU_TLB_FLUSH_ASID_MATCH | SMMU_TLB_FLUSH_ASID(asid) | - SMMU_TLB_FLUSH_VA_GROUP(iova); + if (smmu->soc->num_asids == 4) + value = (asid & 0x3) << 29; + else + value = (asid & 0x7f) << 24; + + value |= SMMU_TLB_FLUSH_ASID_MATCH | SMMU_TLB_FLUSH_VA_GROUP(iova); smmu_writel(smmu, value, SMMU_TLB_FLUSH); } @@ -316,6 +325,9 @@ static void tegra_smmu_domain_free(struct iommu_domain *domain) /* TODO: free page directory and page tables */ + WARN_ON_ONCE(as->use_count); + kfree(as->count); + kfree(as->pts); kfree(as); } @@ -645,6 +657,7 @@ static int tegra_smmu_map(struct iommu_domain *domain, unsigned long iova, { struct tegra_smmu_as *as = to_smmu_as(domain); dma_addr_t pte_dma; + u32 pte_attrs; u32 *pte; pte = as_get_pte(as, iova, &pte_dma); @@ -655,8 +668,16 @@ static int tegra_smmu_map(struct iommu_domain *domain, unsigned long iova, if (*pte == 0) tegra_smmu_pte_get_use(as, iova); + pte_attrs = SMMU_PTE_NONSECURE; + + if (prot & IOMMU_READ) + pte_attrs |= SMMU_PTE_READABLE; + + if (prot & IOMMU_WRITE) + pte_attrs |= SMMU_PTE_WRITABLE; + tegra_smmu_set_pte(as, iova, pte, pte_dma, - __phys_to_pfn(paddr) | SMMU_PTE_ATTR); + __phys_to_pfn(paddr) | pte_attrs); return 0; } 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/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/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_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 76a3d01a489e..78dc8fe2a83c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1586,7 +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", diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index f7eb521db580..46157e2a1e5a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3777,7 +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; } @@ -4212,7 +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; } 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/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/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/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/norm_desc.c b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c index b7dd4e3c760d..6d690678c20e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c +++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c @@ -140,7 +140,7 @@ static void ndesc_init_rx_desc(struct dma_desc *p, int disable_rx_ic, int mode, p->des0 |= cpu_to_le32(RDES0_OWN); bfsize1 = min(bfsize, BUF_SIZE_2KiB - 1); - p->des1 |= cpu_to_le32(bfsize & RDES1_BUFFER1_SIZE_MASK); + p->des1 |= cpu_to_le32(bfsize1 & RDES1_BUFFER1_SIZE_MASK); if (mode == STMMAC_CHAIN_MODE) ndesc_rx_set_on_chain(p, end); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index a26e36dbb5df..48712437d0da 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2616,8 +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) { @@ -4303,6 +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..cc1e887e47b5 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: IOT20202 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/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 9ce61b019aad..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"); diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index cd15c32b2e43..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, @@ -1274,6 +1275,7 @@ 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; /* VRF devices do not care about MTU, but if the MTU is set * too low then the ipv4 and ipv6 protocols are disabled 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/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/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/vfio/mdev/mdev_core.c b/drivers/vfio/mdev/mdev_core.c index b96fedc77ee5..1b6435529166 100644 --- a/drivers/vfio/mdev/mdev_core.c +++ b/drivers/vfio/mdev/mdev_core.c @@ -390,6 +390,24 @@ int mdev_device_remove(struct device *dev, bool force_remove) return 0; } +int mdev_set_iommu_device(struct device *dev, struct device *iommu_device) +{ + struct mdev_device *mdev = to_mdev_device(dev); + + mdev->iommu_device = iommu_device; + + return 0; +} +EXPORT_SYMBOL(mdev_set_iommu_device); + +struct device *mdev_get_iommu_device(struct device *dev) +{ + struct mdev_device *mdev = to_mdev_device(dev); + + return mdev->iommu_device; +} +EXPORT_SYMBOL(mdev_get_iommu_device); + static int __init mdev_init(void) { return mdev_bus_register(); diff --git a/drivers/vfio/mdev/mdev_private.h b/drivers/vfio/mdev/mdev_private.h index 379758c52b1b..f4eba723fea5 100644 --- a/drivers/vfio/mdev/mdev_private.h +++ b/drivers/vfio/mdev/mdev_private.h @@ -33,6 +33,7 @@ struct mdev_device { struct kref ref; struct list_head next; struct kobject *type_kobj; + struct device *iommu_device; bool active; }; diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index d0f731c9920a..3be1db3501cc 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -97,6 +97,7 @@ struct vfio_dma { struct vfio_group { struct iommu_group *iommu_group; struct list_head next; + bool mdev_group; /* An mdev group */ }; /* @@ -564,7 +565,7 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data, mutex_lock(&iommu->lock); /* Fail if notifier list is empty */ - if ((!iommu->external_domain) || (!iommu->notifier.head)) { + if (!iommu->notifier.head) { ret = -EINVAL; goto pin_done; } @@ -646,11 +647,6 @@ static int vfio_iommu_type1_unpin_pages(void *iommu_data, mutex_lock(&iommu->lock); - if (!iommu->external_domain) { - mutex_unlock(&iommu->lock); - return -EINVAL; - } - do_accounting = !IS_IOMMU_CAP_DOMAIN_IN_CONTAINER(iommu); for (i = 0; i < npage; i++) { struct vfio_dma *dma; @@ -1311,13 +1307,109 @@ static bool vfio_iommu_has_sw_msi(struct iommu_group *group, phys_addr_t *base) return ret; } +static struct device *vfio_mdev_get_iommu_device(struct device *dev) +{ + struct device *(*fn)(struct device *dev); + struct device *iommu_device; + + fn = symbol_get(mdev_get_iommu_device); + if (fn) { + iommu_device = fn(dev); + symbol_put(mdev_get_iommu_device); + + return iommu_device; + } + + return NULL; +} + +static int vfio_mdev_attach_domain(struct device *dev, void *data) +{ + struct iommu_domain *domain = data; + struct device *iommu_device; + + iommu_device = vfio_mdev_get_iommu_device(dev); + if (iommu_device) { + if (iommu_dev_feature_enabled(iommu_device, IOMMU_DEV_FEAT_AUX)) + return iommu_aux_attach_device(domain, iommu_device); + else + return iommu_attach_device(domain, iommu_device); + } + + return -EINVAL; +} + +static int vfio_mdev_detach_domain(struct device *dev, void *data) +{ + struct iommu_domain *domain = data; + struct device *iommu_device; + + iommu_device = vfio_mdev_get_iommu_device(dev); + if (iommu_device) { + if (iommu_dev_feature_enabled(iommu_device, IOMMU_DEV_FEAT_AUX)) + iommu_aux_detach_device(domain, iommu_device); + else + iommu_detach_device(domain, iommu_device); + } + + return 0; +} + +static int vfio_iommu_attach_group(struct vfio_domain *domain, + struct vfio_group *group) +{ + if (group->mdev_group) + return iommu_group_for_each_dev(group->iommu_group, + domain->domain, + vfio_mdev_attach_domain); + else + return iommu_attach_group(domain->domain, group->iommu_group); +} + +static void vfio_iommu_detach_group(struct vfio_domain *domain, + struct vfio_group *group) +{ + if (group->mdev_group) + iommu_group_for_each_dev(group->iommu_group, domain->domain, + vfio_mdev_detach_domain); + else + iommu_detach_group(domain->domain, group->iommu_group); +} + +static bool vfio_bus_is_mdev(struct bus_type *bus) +{ + struct bus_type *mdev_bus; + bool ret = false; + + mdev_bus = symbol_get(mdev_bus_type); + if (mdev_bus) { + ret = (bus == mdev_bus); + symbol_put(mdev_bus_type); + } + + return ret; +} + +static int vfio_mdev_iommu_device(struct device *dev, void *data) +{ + struct device **old = data, *new; + + new = vfio_mdev_get_iommu_device(dev); + if (!new || (*old && *old != new)) + return -EINVAL; + + *old = new; + + return 0; +} + static int vfio_iommu_type1_attach_group(void *iommu_data, struct iommu_group *iommu_group) { struct vfio_iommu *iommu = iommu_data; struct vfio_group *group; struct vfio_domain *domain, *d; - struct bus_type *bus = NULL, *mdev_bus; + struct bus_type *bus = NULL; int ret; bool resv_msi, msi_remap; phys_addr_t resv_msi_base; @@ -1352,23 +1444,30 @@ static int vfio_iommu_type1_attach_group(void *iommu_data, if (ret) goto out_free; - mdev_bus = symbol_get(mdev_bus_type); + if (vfio_bus_is_mdev(bus)) { + struct device *iommu_device = NULL; - if (mdev_bus) { - if ((bus == mdev_bus) && !iommu_present(bus)) { - symbol_put(mdev_bus_type); + group->mdev_group = true; + + /* Determine the isolation type */ + ret = iommu_group_for_each_dev(iommu_group, &iommu_device, + vfio_mdev_iommu_device); + if (ret || !iommu_device) { if (!iommu->external_domain) { INIT_LIST_HEAD(&domain->group_list); iommu->external_domain = domain; - } else + } else { kfree(domain); + } list_add(&group->next, &iommu->external_domain->group_list); mutex_unlock(&iommu->lock); + return 0; } - symbol_put(mdev_bus_type); + + bus = iommu_device->bus; } domain->domain = iommu_domain_alloc(bus); @@ -1386,7 +1485,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data, goto out_domain; } - ret = iommu_attach_group(domain->domain, iommu_group); + ret = vfio_iommu_attach_group(domain, group); if (ret) goto out_domain; @@ -1418,8 +1517,8 @@ static int vfio_iommu_type1_attach_group(void *iommu_data, list_for_each_entry(d, &iommu->domain_list, next) { if (d->domain->ops == domain->domain->ops && d->prot == domain->prot) { - iommu_detach_group(domain->domain, iommu_group); - if (!iommu_attach_group(d->domain, iommu_group)) { + vfio_iommu_detach_group(domain, group); + if (!vfio_iommu_attach_group(d, group)) { list_add(&group->next, &d->group_list); iommu_domain_free(domain->domain); kfree(domain); @@ -1427,7 +1526,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data, return 0; } - ret = iommu_attach_group(domain->domain, iommu_group); + ret = vfio_iommu_attach_group(domain, group); if (ret) goto out_domain; } @@ -1453,7 +1552,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data, return 0; out_detach: - iommu_detach_group(domain->domain, iommu_group); + vfio_iommu_detach_group(domain, group); out_domain: iommu_domain_free(domain->domain); out_free: @@ -1544,7 +1643,7 @@ static void vfio_iommu_type1_detach_group(void *iommu_data, if (!group) continue; - iommu_detach_group(domain->domain, iommu_group); + vfio_iommu_detach_group(domain, group); list_del(&group->next); kfree(group); /* @@ -1610,7 +1709,7 @@ static void vfio_release_domain(struct vfio_domain *domain, bool external) list_for_each_entry_safe(group, group_tmp, &domain->group_list, next) { if (!external) - iommu_detach_group(domain->domain, group->iommu_group); + vfio_iommu_detach_group(domain, group); list_del(&group->next); kfree(group); } 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/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/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 2d61ddda9bf5..c2feb310ac1e 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -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/file.c b/fs/cifs/file.c index 9c0ccc06d172..7037a137fa53 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -2877,7 +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); @@ -2941,10 +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); @@ -3582,7 +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); @@ -3666,15 +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) 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 1e1626a2cfc3..0dc6f08020ac 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -789,6 +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; @@ -807,7 +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/smb2pdu.c b/fs/cifs/smb2pdu.c index b8f7262ac354..a37774a55f3a 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -3466,6 +3466,7 @@ 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, diff --git a/fs/io_uring.c b/fs/io_uring.c index f65f85d89217..0e9fb2cb1984 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -740,7 +740,7 @@ 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; @@ -938,7 +938,7 @@ 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; @@ -947,7 +947,7 @@ 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; @@ -985,7 +985,7 @@ 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; @@ -994,7 +994,7 @@ 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; @@ -1336,8 +1336,7 @@ 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; @@ -1353,18 +1352,18 @@ 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); @@ -1457,7 +1456,7 @@ 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, @@ -1623,7 +1622,7 @@ 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); + ret = __io_submit_sqe(ctx, req, s, true); if (ret == -EAGAIN) { struct io_uring_sqe *sqe_copy; @@ -1739,7 +1738,8 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s) 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]); @@ -1864,7 +1864,8 @@ 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()) { @@ -2574,7 +2575,8 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait) poll_wait(file, &ctx->cq_wait, wait); /* See comment at the top of this file */ 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; @@ -2934,6 +2936,14 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, { 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); /* 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/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index d65390727541..7325baa8f9d4 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1626,9 +1626,11 @@ static void drop_sysctl_table(struct ctl_table_header *header) if (--header->nreg) return; - if (parent) + if (parent) { put_links(header); - start_unregistering(header); + start_unregistering(header); + } + if (!--header->count) kfree_rcu(header, rcu); diff --git a/fs/splice.c b/fs/splice.c index 98943d9b219c..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; } 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/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/intel-iommu.h b/include/linux/intel-iommu.h index fa364de9db18..6925a18a5ca3 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -489,9 +489,11 @@ struct dmar_domain { /* Domain ids per IOMMU. Use u16 since * domain ids are 16 bit wide according * to VT-d spec, section 9.3 */ + unsigned int auxd_refcnt; /* Refcount of auxiliary attaching */ bool has_iotlb_device; struct list_head devices; /* all devices' list */ + struct list_head auxd; /* link to device's auxiliary list */ struct iova_domain iovad; /* iova's that belong to this domain */ struct dma_pte *pgd; /* virtual address */ @@ -510,6 +512,11 @@ struct dmar_domain { 2 == 1GiB, 3 == 512GiB, 4 == 1TiB */ u64 max_addr; /* maximum mapped address */ + int default_pasid; /* + * The default pasid used for non-SVM + * traffic on mediated devices. + */ + struct iommu_domain domain; /* generic domain data structure for iommu core */ }; @@ -559,6 +566,9 @@ struct device_domain_info { struct list_head link; /* link to domain siblings */ struct list_head global; /* link to global list */ struct list_head table; /* link to pasid table */ + struct list_head auxiliary_domains; /* auxiliary domains + * attached to this device + */ u8 bus; /* PCI bus number */ u8 devfn; /* PCI devfn number */ u16 pfsid; /* SRIOV physical function source ID */ @@ -568,6 +578,7 @@ struct device_domain_info { u8 pri_enabled:1; u8 ats_supported:1; u8 ats_enabled:1; + u8 auxd_enabled:1; /* Multiple domains per device */ u8 ats_qdep; struct device *dev; /* it's NULL for PCIe-to-PCI bridge */ struct intel_iommu *iommu; /* IOMMU used by this device */ @@ -650,6 +661,7 @@ struct intel_iommu *domain_get_iommu(struct dmar_domain *domain); int for_each_device_domain(int (*fn)(struct device_domain_info *info, void *data), void *data); void iommu_flush_write_buffer(struct intel_iommu *iommu); +int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct device *dev); #ifdef CONFIG_INTEL_IOMMU_SVM int intel_svm_init(struct intel_iommu *iommu); @@ -679,7 +691,6 @@ struct intel_svm { struct list_head list; }; -extern int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sdev); extern struct intel_iommu *intel_svm_device_to_iommu(struct device *dev); #endif diff --git a/include/linux/iommu.h b/include/linux/iommu.h index ffbbc7e39cee..a815cf6f6f47 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -48,6 +48,7 @@ struct bus_type; struct device; struct iommu_domain; struct notifier_block; +struct iommu_sva; /* iommu fault flags */ #define IOMMU_FAULT_READ 0x0 @@ -55,6 +56,8 @@ struct notifier_block; typedef int (*iommu_fault_handler_t)(struct iommu_domain *, struct device *, unsigned long, int, void *); +typedef int (*iommu_mm_exit_handler_t)(struct device *dev, struct iommu_sva *, + void *); struct iommu_domain_geometry { dma_addr_t aperture_start; /* First address that can be mapped */ @@ -156,6 +159,33 @@ struct iommu_resv_region { enum iommu_resv_type type; }; +/* Per device IOMMU features */ +enum iommu_dev_features { + IOMMU_DEV_FEAT_AUX, /* Aux-domain feature */ + IOMMU_DEV_FEAT_SVA, /* Shared Virtual Addresses */ +}; + +#define IOMMU_PASID_INVALID (-1U) + +/** + * struct iommu_sva_ops - device driver callbacks for an SVA context + * + * @mm_exit: called when the mm is about to be torn down by exit_mmap. After + * @mm_exit returns, the device must not issue any more transaction + * with the PASID given as argument. + * + * The @mm_exit handler is allowed to sleep. Be careful about the + * locks taken in @mm_exit, because they might lead to deadlocks if + * they are also held when dropping references to the mm. Consider the + * following call chain: + * mutex_lock(A); mmput(mm) -> exit_mm() -> @mm_exit() -> mutex_lock(A) + * Using mmput_async() prevents this scenario. + * + */ +struct iommu_sva_ops { + iommu_mm_exit_handler_t mm_exit; +}; + #ifdef CONFIG_IOMMU_API /** @@ -186,6 +216,14 @@ struct iommu_resv_region { * @of_xlate: add OF master IDs to iommu grouping * @is_attach_deferred: Check if domain attach should be deferred from iommu * driver init to device driver init (default no) + * @dev_has/enable/disable_feat: per device entries to check/enable/disable + * iommu specific features. + * @dev_feat_enabled: check enabled feature + * @aux_attach/detach_dev: aux-domain specific attach/detach entries. + * @aux_get_pasid: get the pasid given an aux-domain + * @sva_bind: Bind process address space to device + * @sva_unbind: Unbind process address space from device + * @sva_get_pasid: Get PASID associated to a SVA handle * @pgsize_bitmap: bitmap of all possible supported page sizes */ struct iommu_ops { @@ -230,6 +268,22 @@ struct iommu_ops { int (*of_xlate)(struct device *dev, struct of_phandle_args *args); bool (*is_attach_deferred)(struct iommu_domain *domain, struct device *dev); + /* Per device IOMMU features */ + bool (*dev_has_feat)(struct device *dev, enum iommu_dev_features f); + bool (*dev_feat_enabled)(struct device *dev, enum iommu_dev_features f); + int (*dev_enable_feat)(struct device *dev, enum iommu_dev_features f); + int (*dev_disable_feat)(struct device *dev, enum iommu_dev_features f); + + /* Aux-domain specific attach/detach entries */ + int (*aux_attach_dev)(struct iommu_domain *domain, struct device *dev); + void (*aux_detach_dev)(struct iommu_domain *domain, struct device *dev); + int (*aux_get_pasid)(struct iommu_domain *domain, struct device *dev); + + struct iommu_sva *(*sva_bind)(struct device *dev, struct mm_struct *mm, + void *drvdata); + void (*sva_unbind)(struct iommu_sva *handle); + int (*sva_get_pasid)(struct iommu_sva *handle); + unsigned long pgsize_bitmap; }; @@ -392,10 +446,22 @@ struct iommu_fwspec { const struct iommu_ops *ops; struct fwnode_handle *iommu_fwnode; void *iommu_priv; + u32 flags; unsigned int num_ids; u32 ids[1]; }; +/* ATS is supported */ +#define IOMMU_FWSPEC_PCI_RC_ATS (1 << 0) + +/** + * struct iommu_sva - handle to a device-mm bond + */ +struct iommu_sva { + struct device *dev; + const struct iommu_sva_ops *ops; +}; + int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode, const struct iommu_ops *ops); void iommu_fwspec_free(struct device *dev); @@ -416,6 +482,22 @@ static inline void dev_iommu_fwspec_set(struct device *dev, int iommu_probe_device(struct device *dev); void iommu_release_device(struct device *dev); +bool iommu_dev_has_feature(struct device *dev, enum iommu_dev_features f); +int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features f); +int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features f); +bool iommu_dev_feature_enabled(struct device *dev, enum iommu_dev_features f); +int iommu_aux_attach_device(struct iommu_domain *domain, struct device *dev); +void iommu_aux_detach_device(struct iommu_domain *domain, struct device *dev); +int iommu_aux_get_pasid(struct iommu_domain *domain, struct device *dev); + +struct iommu_sva *iommu_sva_bind_device(struct device *dev, + struct mm_struct *mm, + void *drvdata); +void iommu_sva_unbind_device(struct iommu_sva *handle); +int iommu_sva_set_ops(struct iommu_sva *handle, + const struct iommu_sva_ops *ops); +int iommu_sva_get_pasid(struct iommu_sva *handle); + #else /* CONFIG_IOMMU_API */ struct iommu_ops {}; @@ -700,6 +782,68 @@ const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode) return NULL; } +static inline bool +iommu_dev_has_feature(struct device *dev, enum iommu_dev_features feat) +{ + return false; +} + +static inline bool +iommu_dev_feature_enabled(struct device *dev, enum iommu_dev_features feat) +{ + return false; +} + +static inline int +iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features feat) +{ + return -ENODEV; +} + +static inline int +iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features feat) +{ + return -ENODEV; +} + +static inline int +iommu_aux_attach_device(struct iommu_domain *domain, struct device *dev) +{ + return -ENODEV; +} + +static inline void +iommu_aux_detach_device(struct iommu_domain *domain, struct device *dev) +{ +} + +static inline int +iommu_aux_get_pasid(struct iommu_domain *domain, struct device *dev) +{ + return -ENODEV; +} + +static inline struct iommu_sva * +iommu_sva_bind_device(struct device *dev, struct mm_struct *mm, void *drvdata) +{ + return NULL; +} + +static inline void iommu_sva_unbind_device(struct iommu_sva *handle) +{ +} + +static inline int iommu_sva_set_ops(struct iommu_sva *handle, + const struct iommu_sva_ops *ops) +{ + return -EINVAL; +} + +static inline int iommu_sva_get_pasid(struct iommu_sva *handle) +{ + return IOMMU_PASID_INVALID; +} + #endif /* CONFIG_IOMMU_API */ #ifdef CONFIG_IOMMU_DEBUGFS diff --git a/include/linux/iova.h b/include/linux/iova.h index 0b93bf96693e..28a5128405f8 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -76,6 +76,14 @@ struct iova_domain { unsigned long start_pfn; /* Lower limit for this domain */ unsigned long dma_32bit_pfn; unsigned long max32_alloc_size; /* Size of last failed allocation */ + struct iova_fq __percpu *fq; /* Flush Queue */ + + atomic64_t fq_flush_start_cnt; /* Number of TLB flushes that + have been started */ + + atomic64_t fq_flush_finish_cnt; /* Number of TLB flushes that + have been finished */ + struct iova anchor; /* rbtree lookup anchor */ struct iova_rcache rcaches[IOVA_RANGE_CACHE_MAX_SIZE]; /* IOVA range caches */ @@ -85,14 +93,6 @@ struct iova_domain { iova_entry_dtor entry_dtor; /* IOMMU driver specific destructor for iova entry */ - struct iova_fq __percpu *fq; /* Flush Queue */ - - atomic64_t fq_flush_start_cnt; /* Number of TLB flushes that - have been started */ - - atomic64_t fq_flush_finish_cnt; /* Number of TLB flushes that - have been finished */ - struct timer_list fq_timer; /* Timer to regularily empty the flush-queues */ atomic_t fq_timer_on; /* 1 when timer is active, 0 diff --git a/include/linux/mdev.h b/include/linux/mdev.h index d7aee90e5da5..df2ea39f47ee 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -15,6 +15,20 @@ struct mdev_device; +/* + * Called by the parent device driver to set the device which represents + * this mdev in iommu protection scope. By default, the iommu device is + * NULL, that indicates using vendor defined isolation. + * + * @dev: the mediated device that iommu will isolate. + * @iommu_device: a pci device which represents the iommu for @dev. + * + * Return 0 for success, otherwise negative error value. + */ +int mdev_set_iommu_device(struct device *dev, struct device *iommu_device); + +struct device *mdev_get_iommu_device(struct device *dev); + /** * struct mdev_parent_ops - Structure to be registered for each parent device to * register the device to mdev module. diff --git a/include/linux/pci.h b/include/linux/pci.h index 77448215ef5b..61d7cd888bad 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1521,21 +1521,6 @@ static inline void pcie_ecrc_get_policy(char *str) { } bool pci_ats_disabled(void); -#ifdef CONFIG_PCI_ATS -/* Address Translation Service */ -void pci_ats_init(struct pci_dev *dev); -int pci_enable_ats(struct pci_dev *dev, int ps); -void pci_disable_ats(struct pci_dev *dev); -int pci_ats_queue_depth(struct pci_dev *dev); -int pci_ats_page_aligned(struct pci_dev *dev); -#else -static inline void pci_ats_init(struct pci_dev *d) { } -static inline int pci_enable_ats(struct pci_dev *d, int ps) { return -ENODEV; } -static inline void pci_disable_ats(struct pci_dev *d) { } -static inline int pci_ats_queue_depth(struct pci_dev *d) { return -ENODEV; } -static inline int pci_ats_page_aligned(struct pci_dev *dev) { return 0; } -#endif - #ifdef CONFIG_PCIE_PTM int pci_enable_ptm(struct pci_dev *dev, u8 *granularity); #else @@ -1728,8 +1713,24 @@ static inline int pci_irqd_intx_xlate(struct irq_domain *d, static inline const struct pci_device_id *pci_match_id(const struct pci_device_id *ids, struct pci_dev *dev) { return NULL; } +static inline bool pci_ats_disabled(void) { return true; } #endif /* CONFIG_PCI */ +#ifdef CONFIG_PCI_ATS +/* Address Translation Service */ +void pci_ats_init(struct pci_dev *dev); +int pci_enable_ats(struct pci_dev *dev, int ps); +void pci_disable_ats(struct pci_dev *dev); +int pci_ats_queue_depth(struct pci_dev *dev); +int pci_ats_page_aligned(struct pci_dev *dev); +#else +static inline void pci_ats_init(struct pci_dev *d) { } +static inline int pci_enable_ats(struct pci_dev *d, int ps) { return -ENODEV; } +static inline void pci_disable_ats(struct pci_dev *d) { } +static inline int pci_ats_queue_depth(struct pci_dev *d) { return -ENODEV; } +static inline int pci_ats_page_aligned(struct pci_dev *dev) { return 0; } +#endif + /* Include architecture-dependent settings and functions */ #include <asm/pci.h> diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index abb2dac3da9b..5c626fdc10db 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -176,6 +176,7 @@ void free_pipe_info(struct pipe_inode_info *); 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/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/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/kernel/sched/fair.c b/kernel/sched/fair.c index a4d9e14bf138..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; 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 6c24755655c7..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; } @@ -7025,19 +7028,23 @@ 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; } @@ -7046,10 +7053,10 @@ static bool buffer_pipe_buf_get(struct pipe_inode_info *pipe, { struct buffer_ref *ref = (struct buffer_ref *)buf->private; - if (ref->ref > INT_MAX/2) + if (refcount_read(&ref->refcount) > INT_MAX/2) return false; - ref->ref++; + refcount_inc(&ref->refcount); return true; } @@ -7057,7 +7064,7 @@ static bool buffer_pipe_buf_get(struct pipe_inode_info *pipe, 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, }; @@ -7070,11 +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; } @@ -7129,7 +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/lib/Kconfig.debug b/lib/Kconfig.debug index 00dbcdbc9a0d..d5a4a4036d2f 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -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/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/memory_hotplug.c b/mm/memory_hotplug.c index 0082d699be94..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); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c6ce20aaf80b..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 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/ipv4/route.c b/net/ipv4/route.c index 88ce038dd495..6fdf1c195d8e 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1183,25 +1183,39 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) return dst; } -static void ipv4_link_failure(struct sk_buff *skb) +static void ipv4_send_dest_unreach(struct sk_buff *skb) { struct ip_options opt; - struct rtable *rt; int res; /* Recompile ip options since IPCB may not be valid anymore. + * Also check we have a reasonable ipv4 header. */ - memset(&opt, 0, sizeof(opt)); - opt.optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr); + if (!pskb_network_may_pull(skb, sizeof(struct iphdr)) || + ip_hdr(skb)->version != 4 || ip_hdr(skb)->ihl < 5) + return; - rcu_read_lock(); - res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL); - rcu_read_unlock(); + 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); - if (res) - return; + 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; + + 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/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/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/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_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 ef7772e976cc..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 && 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/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/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/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/rxrpc/input.c b/net/rxrpc/input.c index 4c6f9d0a00e7..c2c35cf4e308 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -1161,19 +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; @@ -1181,6 +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/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/tls/tls_device.c b/net/tls/tls_device.c index 9f3bdbc1e593..cc0256939eb6 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -904,7 +904,9 @@ 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: @@ -939,8 +941,6 @@ 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..a3ebd4b02714 100644 --- a/net/tls/tls_device_fallback.c +++ b/net/tls/tls_device_fallback.c @@ -194,6 +194,9 @@ 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); @@ -201,11 +204,15 @@ static void complete_skb(struct sk_buff *nskb, struct sk_buff *skb, int 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); + + 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 9547cea0ce3b..478603f43964 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -293,11 +293,8 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) #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 b50ced862f6f..29d6af43dd24 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2078,6 +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/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 |