- Kernel - mailweb.openeuler.org

[PATCH openEuler-21.09] eulerfs: add the /proc/idle file.
by Hongyu Li 30 Sep '21

30 Sep '21

openEuler inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4CIJQ CVE: NA ---------------------------------------------------------------------- The default way of calculating CPU utilization is to check which task is executed during the interval of two ticks. This leads to the inaccurate results of CPU utilization. This problem can be solved by counting the idle time via scheduler rather than the tick interval. We can record the time before executing idle process and calculate the execute time before quiting the idle process. The idle time of each CPU is given in the /proc/stat2 file. This way can give higher precision in accounting the CPU idle time compared with the /proc/stat. Signed-off-by: Hongyu Li <543306408(a)qq.com> --- fs/proc/Kconfig | 7 ++++ fs/proc/Makefile | 1 + fs/proc/stat2.c | 91 ++++++++++++++++++++++++++++++++++++++++++ kernel/sched/cputime.c | 34 ++++++++++++++++ kernel/sched/idle.c | 28 +++++++++++++ 5 files changed, 161 insertions(+) create mode 100644 fs/proc/stat2.c diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig index c930001056f9..33588a37579e 100644 --- a/fs/proc/Kconfig +++ b/fs/proc/Kconfig @@ -107,3 +107,10 @@ config PROC_PID_ARCH_STATUS config PROC_CPU_RESCTRL def_bool n depends on PROC_FS + +config PROC_IDLE + bool "include /proc/stat2 file" + depends on PROC_FS + default y + help + Provide the CPU idle time in the /proc/stat2 file. diff --git a/fs/proc/Makefile b/fs/proc/Makefile index 8704d41dd67c..b0d5f2b347d7 100644 --- a/fs/proc/Makefile +++ b/fs/proc/Makefile @@ -34,5 +34,6 @@ proc-$(CONFIG_PROC_VMCORE) += vmcore.o proc-$(CONFIG_PRINTK) += kmsg.o proc-$(CONFIG_PROC_PAGE_MONITOR) += page.o proc-$(CONFIG_BOOT_CONFIG) += bootconfig.o +proc-$(CONFIG_PROC_IDLE) += stat2.o obj-$(CONFIG_ETMEM_SCAN) += etmem_scan.o obj-$(CONFIG_ETMEM_SWAP) += etmem_swap.o diff --git a/fs/proc/stat2.c b/fs/proc/stat2.c new file mode 100644 index 000000000000..6036a946c71d --- /dev/null +++ b/fs/proc/stat2.c @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/fs/proc/stat2.c + * + * Copyright (C) 2007 + * + * cpu idle time accouting + */ + +#include <linux/cpumask.h> +#include <linux/device.h> +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/kernel_stat.h> +#include <linux/module.h> +#include <linux/proc_fs.h> +#include <linux/sched.h> +#include <linux/sched/stat.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/time.h> +#include <linux/irqnr.h> +#include <linux/sched/cputime.h> +#include <linux/tick.h> + +#ifdef CONFIG_PROC_IDLE + +#define PROC_NAME "stat2" + +extern u64 cal_idle_sum_exec_runtime(int cpu); + +static u64 get_idle_sum_exec_runtime(int cpu) +{ + u64 idle = cal_idle_sum_exec_runtime(cpu); + + return idle; +} + +static int show_idle(struct seq_file *p, void *v) +{ + int i; + u64 idle; + + idle = 0; + + for_each_possible_cpu(i) { + + idle += get_idle_sum_exec_runtime(i); + + } + + seq_put_decimal_ull(p, "cpu ", nsec_to_clock_t(idle)); + seq_putc(p, '\n'); + + for_each_online_cpu(i) { + + idle = get_idle_sum_exec_runtime(i); + + seq_printf(p, "cpu%d", i); + seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle)); + seq_putc(p, '\n'); + } + + return 0; +} + +static int idle_open(struct inode *inode, struct file *file) +{ + unsigned int size = 32 + 32 * num_online_cpus(); + + return single_open_size(file, show_idle, NULL, size); +} + +static struct proc_ops idle_procs_ops = { + .proc_open = idle_open, + .proc_read_iter = seq_read_iter, + .proc_lseek = seq_lseek, + .proc_release = single_release, +}; + +static int __init kernel_module_init(void) +{ + proc_create(PROC_NAME, 0, NULL, &idle_procs_ops); + return 0; +} + +fs_initcall(kernel_module_init); + +#endif /*CONFIG_PROC_IDLE*/ diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 5a55d2300452..25218a8f822f 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -19,6 +19,8 @@ */ DEFINE_PER_CPU(struct irqtime, cpu_irqtime); +extern struct static_key_true proc_idle; + static int sched_clock_irqtime; void enable_sched_clock_irqtime(void) @@ -1078,3 +1080,35 @@ void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu) EXPORT_SYMBOL_GPL(kcpustat_cpu_fetch); #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ + + +#ifdef CONFIG_PROC_IDLE + + +u64 cal_idle_sum_exec_runtime(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + struct sched_entity *idle_se = &rq->idle->se; + u64 idle = idle_se->sum_exec_runtime; + + if (!static_branch_likely(&proc_idle)) + return 0ULL; + + if (rq->curr == rq->idle) { + u64 now = sched_clock(); + u64 delta_exec; + + delta_exec = now - idle_se->exec_start; + if (unlikely((s64)delta_exec <= 0)) + return idle; + + schedstat_set(idle_se->statistics.exec_max, + max(delta_exec, idle_se->statistics.exec_max)); + + idle += delta_exec; + } + + return idle; +} + +#endif /* CONFIG_PROC_IDLE */ diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 36b545f17206..15f076ab5823 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -10,6 +10,8 @@ #include <trace/events/power.h> +DEFINE_STATIC_KEY_TRUE(proc_idle); + /* Linker adds these: start and end of __cpuidle functions */ extern char __cpuidle_text_start[], __cpuidle_text_end[]; @@ -424,6 +426,23 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl static void put_prev_task_idle(struct rq *rq, struct task_struct *prev) { +#ifdef CONFIG_PROC_IDLE + if (!static_branch_likely(&proc_idle)) + return; + + struct sched_entity *idle_se = &rq->idle->se; + u64 now = sched_clock(); + u64 delta_exec; + + delta_exec = now - idle_se->exec_start; + if (unlikely((s64)delta_exec <= 0)) + return; + + schedstat_set(idle_se->statistics.exec_max, + max(delta_exec, idle_se->statistics.exec_max)); + + idle_se->sum_exec_runtime += delta_exec; +#endif } static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first) @@ -436,6 +455,15 @@ struct task_struct *pick_next_task_idle(struct rq *rq) { struct task_struct *next = rq->idle; +#ifdef CONFIG_PROC_IDLE + if (static_branch_likely(&proc_idle)) { + struct sched_entity *idle_se = &rq->idle->se; + u64 now = sched_clock(); + + idle_se->exec_start = now; + } +#endif + set_next_task_idle(rq, next, true); return next; -- 2.17.1

1 0

[PATCH OLK-5.10 1/9] mm: add Kernel Electric-Fence infrastructure
by 1415317271＠qq.com 30 Sep '21

30 Sep '21

From: Alexander Potapenko <glider(a)google.com> Patch series "KFENCE: A low-overhead sampling-based memory safety error detector", v7. This adds the Kernel Electric-Fence (KFENCE) infrastructure. KFENCE is a low-overhead sampling-based memory safety error detector of heap use-after-free, invalid-free, and out-of-bounds access errors. This series enables KFENCE for the x86 and arm64 architectures, and adds KFENCE hooks to the SLAB and SLUB allocators. KFENCE is designed to be enabled in production kernels, and has near zero performance overhead. Compared to KASAN, KFENCE trades performance for precision. The main motivation behind KFENCE's design, is that with enough total uptime KFENCE will detect bugs in code paths not typically exercised by non-production test workloads. One way to quickly achieve a large enough total uptime is when the tool is deployed across a large fleet of machines. KFENCE objects each reside on a dedicated page, at either the left or right page boundaries. The pages to the left and right of the object page are "guard pages", whose attributes are changed to a protected state, and cause page faults on any attempted access to them. Such page faults are then intercepted by KFENCE, which handles the fault gracefully by reporting a memory access error. Guarded allocations are set up based on a sample interval (can be set via kfence.sample_interval). After expiration of the sample interval, the next allocation through the main allocator (SLAB or SLUB) returns a guarded allocation from the KFENCE object pool. At this point, the timer is reset, and the next allocation is set up after the expiration of the interval. To enable/disable a KFENCE allocation through the main allocator's fast-path without overhead, KFENCE relies on static branches via the static keys infrastructure. The static branch is toggled to redirect the allocation to KFENCE. The KFENCE memory pool is of fixed size, and if the pool is exhausted no further KFENCE allocations occur. The default config is conservative with only 255 objects, resulting in a pool size of 2 MiB (with 4 KiB pages). We have verified by running synthetic benchmarks (sysbench I/O, hackbench) and production server-workload benchmarks that a kernel with KFENCE (using sample intervals 100-500ms) is performance-neutral compared to a non-KFENCE baseline kernel. KFENCE is inspired by GWP-ASan [1], a userspace tool with similar properties. The name "KFENCE" is a homage to the Electric Fence Malloc Debugger [2]. For more details, see Documentation/dev-tools/kfence.rst added in the series -- also viewable here: https://raw.githubusercontent.com/google/kasan/kfence/Documentation/dev-too… [1] http://llvm.org/docs/GwpAsan.html [2] https://linux.die.net/man/3/efence This patch (of 9): This adds the Kernel Electric-Fence (KFENCE) infrastructure. KFENCE is a low-overhead sampling-based memory safety error detector of heap use-after-free, invalid-free, and out-of-bounds access errors. KFENCE is designed to be enabled in production kernels, and has near zero performance overhead. Compared to KASAN, KFENCE trades performance for precision. The main motivation behind KFENCE's design, is that with enough total uptime KFENCE will detect bugs in code paths not typically exercised by non-production test workloads. One way to quickly achieve a large enough total uptime is when the tool is deployed across a large fleet of machines. KFENCE objects each reside on a dedicated page, at either the left or right page boundaries. The pages to the left and right of the object page are "guard pages", whose attributes are changed to a protected state, and cause page faults on any attempted access to them. Such page faults are then intercepted by KFENCE, which handles the fault gracefully by reporting a memory access error. To detect out-of-bounds writes to memory within the object's page itself, KFENCE also uses pattern-based redzones. The following figure illustrates the page layout: ---+-----------+-----------+-----------+-----------+-----------+--- | xxxxxxxxx | O : | xxxxxxxxx | : O | xxxxxxxxx | | xxxxxxxxx | B : | xxxxxxxxx | : B | xxxxxxxxx | | x GUARD x | J : RED- | x GUARD x | RED- : J | x GUARD x | | xxxxxxxxx | E : ZONE | xxxxxxxxx | ZONE : E | xxxxxxxxx | | xxxxxxxxx | C : | xxxxxxxxx | : C | xxxxxxxxx | | xxxxxxxxx | T : | xxxxxxxxx | : T | xxxxxxxxx | ---+-----------+-----------+-----------+-----------+-----------+--- Guarded allocations are set up based on a sample interval (can be set via kfence.sample_interval). After expiration of the sample interval, a guarded allocation from the KFENCE object pool is returned to the main allocator (SLAB or SLUB). At this point, the timer is reset, and the next allocation is set up after the expiration of the interval. To enable/disable a KFENCE allocation through the main allocator's fast-path without overhead, KFENCE relies on static branches via the static keys infrastructure. The static branch is toggled to redirect the allocation to KFENCE. To date, we have verified by running synthetic benchmarks (sysbench I/O, hackbench) that a kernel compiled with KFENCE is performance-neutral compared to the non-KFENCE baseline. For more details, see Documentation/dev-tools/kfence.rst (added later in the series). [elver(a)google.com: fix parameter description for kfence_object_start()] Link: https://lkml.kernel.org/r/20201106092149.GA2851373@elver.google.com [elver(a)google.com: avoid stalling work queue task without allocations] Link: https://lkml.kernel.org/r/CADYN=9J0DQhizAGB0-jz4HOBBh+05kMBXb4c0cXMS7Qi5NAJ… Link: https://lkml.kernel.org/r/20201110135320.3309507-1-elver@google.com [elver(a)google.com: fix potential deadlock due to wake_up()] Link: https://lkml.kernel.org/r/000000000000c0645805b7f982e4@google.com Link: https://lkml.kernel.org/r/20210104130749.1768991-1-elver@google.com [elver(a)google.com: add option to use KFENCE without static keys] Link: https://lkml.kernel.org/r/20210111091544.3287013-1-elver@google.com [elver(a)google.com: add missing copyright and description headers] Link: https://lkml.kernel.org/r/20210118092159.145934-1-elver@google.com Link: https://lkml.kernel.org/r/20201103175841.3495947-2-elver@google.com Signed-off-by: Marco Elver <elver(a)google.com> Signed-off-by: Alexander Potapenko <glider(a)google.com> Reviewed-by: Dmitry Vyukov <dvyukov(a)google.com> Reviewed-by: SeongJae Park <sjpark(a)amazon.de> Co-developed-by: Marco Elver <elver(a)google.com> Reviewed-by: Jann Horn <jannh(a)google.com> Cc: "H. Peter Anvin" <hpa(a)zytor.com> Cc: Paul E. McKenney <paulmck(a)kernel.org> Cc: Andrey Konovalov <andreyknvl(a)google.com> Cc: Andrey Ryabinin <aryabinin(a)virtuozzo.com> Cc: Andy Lutomirski <luto(a)kernel.org> Cc: Borislav Petkov <bp(a)alien8.de> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Christopher Lameter <cl(a)linux.com> Cc: Dave Hansen <dave.hansen(a)linux.intel.com> Cc: David Rientjes <rientjes(a)google.com> Cc: Eric Dumazet <edumazet(a)google.com> Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: Hillf Danton <hdanton(a)sina.com> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Jonathan Corbet <corbet(a)lwn.net> Cc: Joonsoo Kim <iamjoonsoo.kim(a)lge.com> Cc: Joern Engel <joern(a)purestorage.com> Cc: Kees Cook <keescook(a)chromium.org> Cc: Mark Rutland <mark.rutland(a)arm.com> Cc: Pekka Enberg <penberg(a)kernel.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: Will Deacon <will(a)kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Yingjie Shang <1415317271(a)qq.com> Reviewed-by: Bixuan Cui <cuibixuan(a)huawei.com> --- include/linux/kfence.h | 216 +++++++++++ init/main.c | 3 + lib/Kconfig.debug | 1 + lib/Kconfig.kfence | 67 ++++ mm/Makefile | 1 + mm/kfence/Makefile | 3 + mm/kfence/core.c | 840 +++++++++++++++++++++++++++++++++++++++++ mm/kfence/kfence.h | 113 ++++++ mm/kfence/report.c | 240 ++++++++++++ 9 files changed, 1484 insertions(+) create mode 100644 include/linux/kfence.h create mode 100644 lib/Kconfig.kfence create mode 100644 mm/kfence/Makefile create mode 100644 mm/kfence/core.c create mode 100644 mm/kfence/kfence.h create mode 100644 mm/kfence/report.c diff --git a/include/linux/kfence.h b/include/linux/kfence.h new file mode 100644 index 000000000000..81f3911cb298 --- /dev/null +++ b/include/linux/kfence.h @@ -0,0 +1,216 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Kernel Electric-Fence (KFENCE). Public interface for allocator and fault + * handler integration. For more info see Documentation/dev-tools/kfence.rst. + * + * Copyright (C) 2020, Google LLC. + */ + +#ifndef _LINUX_KFENCE_H +#define _LINUX_KFENCE_H + +#include <linux/mm.h> +#include <linux/types.h> + +#ifdef CONFIG_KFENCE + +/* + * We allocate an even number of pages, as it simplifies calculations to map + * address to metadata indices; effectively, the very first page serves as an + * extended guard page, but otherwise has no special purpose. + */ +#define KFENCE_POOL_SIZE ((CONFIG_KFENCE_NUM_OBJECTS + 1) * 2 * PAGE_SIZE) +extern char *__kfence_pool; + +#ifdef CONFIG_KFENCE_STATIC_KEYS +#include <linux/static_key.h> +DECLARE_STATIC_KEY_FALSE(kfence_allocation_key); +#else +#include <linux/atomic.h> +extern atomic_t kfence_allocation_gate; +#endif + +/** + * is_kfence_address() - check if an address belongs to KFENCE pool + * @addr: address to check + * + * Return: true or false depending on whether the address is within the KFENCE + * object range. + * + * KFENCE objects live in a separate page range and are not to be intermixed + * with regular heap objects (e.g. KFENCE objects must never be added to the + * allocator freelists). Failing to do so may and will result in heap + * corruptions, therefore is_kfence_address() must be used to check whether + * an object requires specific handling. + * + * Note: This function may be used in fast-paths, and is performance critical. + * Future changes should take this into account; for instance, we want to avoid + * introducing another load and therefore need to keep KFENCE_POOL_SIZE a + * constant (until immediate patching support is added to the kernel). + */ +static __always_inline bool is_kfence_address(const void *addr) +{ + /* + * The non-NULL check is required in case the __kfence_pool pointer was + * never initialized; keep it in the slow-path after the range-check. + */ + return unlikely((unsigned long)((char *)addr - __kfence_pool) < KFENCE_POOL_SIZE && addr); +} + +/** + * kfence_alloc_pool() - allocate the KFENCE pool via memblock + */ +void __init kfence_alloc_pool(void); + +/** + * kfence_init() - perform KFENCE initialization at boot time + * + * Requires that kfence_alloc_pool() was called before. This sets up the + * allocation gate timer, and requires that workqueues are available. + */ +void __init kfence_init(void); + +/** + * kfence_shutdown_cache() - handle shutdown_cache() for KFENCE objects + * @s: cache being shut down + * + * Before shutting down a cache, one must ensure there are no remaining objects + * allocated from it. Because KFENCE objects are not referenced from the cache + * directly, we need to check them here. + * + * Note that shutdown_cache() is internal to SL*B, and kmem_cache_destroy() does + * not return if allocated objects still exist: it prints an error message and + * simply aborts destruction of a cache, leaking memory. + * + * If the only such objects are KFENCE objects, we will not leak the entire + * cache, but instead try to provide more useful debug info by making allocated + * objects "zombie allocations". Objects may then still be used or freed (which + * is handled gracefully), but usage will result in showing KFENCE error reports + * which include stack traces to the user of the object, the original allocation + * site, and caller to shutdown_cache(). + */ +void kfence_shutdown_cache(struct kmem_cache *s); + +/* + * Allocate a KFENCE object. Allocators must not call this function directly, + * use kfence_alloc() instead. + */ +void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags); + +/** + * kfence_alloc() - allocate a KFENCE object with a low probability + * @s: struct kmem_cache with object requirements + * @size: exact size of the object to allocate (can be less than @s->size + * e.g. for kmalloc caches) + * @flags: GFP flags + * + * Return: + * * NULL - must proceed with allocating as usual, + * * non-NULL - pointer to a KFENCE object. + * + * kfence_alloc() should be inserted into the heap allocation fast path, + * allowing it to transparently return KFENCE-allocated objects with a low + * probability using a static branch (the probability is controlled by the + * kfence.sample_interval boot parameter). + */ +static __always_inline void *kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) +{ +#ifdef CONFIG_KFENCE_STATIC_KEYS + if (static_branch_unlikely(&kfence_allocation_key)) +#else + if (unlikely(!atomic_read(&kfence_allocation_gate))) +#endif + return __kfence_alloc(s, size, flags); + return NULL; +} + +/** + * kfence_ksize() - get actual amount of memory allocated for a KFENCE object + * @addr: pointer to a heap object + * + * Return: + * * 0 - not a KFENCE object, must call __ksize() instead, + * * non-0 - this many bytes can be accessed without causing a memory error. + * + * kfence_ksize() returns the number of bytes requested for a KFENCE object at + * allocation time. This number may be less than the object size of the + * corresponding struct kmem_cache. + */ +size_t kfence_ksize(const void *addr); + +/** + * kfence_object_start() - find the beginning of a KFENCE object + * @addr: address within a KFENCE-allocated object + * + * Return: address of the beginning of the object. + * + * SL[AU]B-allocated objects are laid out within a page one by one, so it is + * easy to calculate the beginning of an object given a pointer inside it and + * the object size. The same is not true for KFENCE, which places a single + * object at either end of the page. This helper function is used to find the + * beginning of a KFENCE-allocated object. + */ +void *kfence_object_start(const void *addr); + +/** + * __kfence_free() - release a KFENCE heap object to KFENCE pool + * @addr: object to be freed + * + * Requires: is_kfence_address(addr) + * + * Release a KFENCE object and mark it as freed. + */ +void __kfence_free(void *addr); + +/** + * kfence_free() - try to release an arbitrary heap object to KFENCE pool + * @addr: object to be freed + * + * Return: + * * false - object doesn't belong to KFENCE pool and was ignored, + * * true - object was released to KFENCE pool. + * + * Release a KFENCE object and mark it as freed. May be called on any object, + * even non-KFENCE objects, to simplify integration of the hooks into the + * allocator's free codepath. The allocator must check the return value to + * determine if it was a KFENCE object or not. + */ +static __always_inline __must_check bool kfence_free(void *addr) +{ + if (!is_kfence_address(addr)) + return false; + __kfence_free(addr); + return true; +} + +/** + * kfence_handle_page_fault() - perform page fault handling for KFENCE pages + * @addr: faulting address + * + * Return: + * * false - address outside KFENCE pool, + * * true - page fault handled by KFENCE, no additional handling required. + * + * A page fault inside KFENCE pool indicates a memory error, such as an + * out-of-bounds access, a use-after-free or an invalid memory access. In these + * cases KFENCE prints an error message and marks the offending page as + * present, so that the kernel can proceed. + */ +bool __must_check kfence_handle_page_fault(unsigned long addr); + +#else /* CONFIG_KFENCE */ + +static inline bool is_kfence_address(const void *addr) { return false; } +static inline void kfence_alloc_pool(void) { } +static inline void kfence_init(void) { } +static inline void kfence_shutdown_cache(struct kmem_cache *s) { } +static inline void *kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) { return NULL; } +static inline size_t kfence_ksize(const void *addr) { return 0; } +static inline void *kfence_object_start(const void *addr) { return NULL; } +static inline void __kfence_free(void *addr) { } +static inline bool __must_check kfence_free(void *addr) { return false; } +static inline bool __must_check kfence_handle_page_fault(unsigned long addr) { return false; } + +#endif + +#endif /* _LINUX_KFENCE_H */ diff --git a/init/main.c b/init/main.c index fc0277a9e7a3..2d027dc11b10 100644 --- a/init/main.c +++ b/init/main.c @@ -40,6 +40,7 @@ #include <linux/security.h> #include <linux/smp.h> #include <linux/profile.h> +#include <linux/kfence.h> #include <linux/rcupdate.h> #include <linux/moduleparam.h> #include <linux/kallsyms.h> @@ -828,6 +829,7 @@ static void __init mm_init(void) */ page_ext_init_flatmem(); init_debug_pagealloc(); + kfence_alloc_pool(); report_meminit(); mem_init(); kmem_cache_init(); @@ -956,6 +958,7 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void) hrtimers_init(); softirq_init(); timekeeping_init(); + kfence_init(); /* * For best initial stack canary entropy, prepare it after: diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 799e49a29797..29e64b4cd412 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -878,6 +878,7 @@ config DEBUG_STACKOVERFLOW If in doubt, say "N". source "lib/Kconfig.kasan" +source "lib/Kconfig.kfence" endmenu # "Memory Debugging" diff --git a/lib/Kconfig.kfence b/lib/Kconfig.kfence new file mode 100644 index 000000000000..b88ac9d6b2e6 --- /dev/null +++ b/lib/Kconfig.kfence @@ -0,0 +1,67 @@ +# SPDX-License-Identifier: GPL-2.0-only + +config HAVE_ARCH_KFENCE + bool + +menuconfig KFENCE + bool "KFENCE: low-overhead sampling-based memory safety error detector" + depends on HAVE_ARCH_KFENCE && !KASAN && (SLAB || SLUB) + select STACKTRACE + help + KFENCE is a low-overhead sampling-based detector of heap out-of-bounds + access, use-after-free, and invalid-free errors. KFENCE is designed + to have negligible cost to permit enabling it in production + environments. + + Note that, KFENCE is not a substitute for explicit testing with tools + such as KASAN. KFENCE can detect a subset of bugs that KASAN can + detect, albeit at very different performance profiles. If you can + afford to use KASAN, continue using KASAN, for example in test + environments. If your kernel targets production use, and cannot + enable KASAN due to its cost, consider using KFENCE. + +if KFENCE + +config KFENCE_STATIC_KEYS + bool "Use static keys to set up allocations" + default y + depends on JUMP_LABEL # To ensure performance, require jump labels + help + Use static keys (static branches) to set up KFENCE allocations. Using + static keys is normally recommended, because it avoids a dynamic + branch in the allocator's fast path. However, with very low sample + intervals, or on systems that do not support jump labels, a dynamic + branch may still be an acceptable performance trade-off. + +config KFENCE_SAMPLE_INTERVAL + int "Default sample interval in milliseconds" + default 100 + help + The KFENCE sample interval determines the frequency with which heap + allocations will be guarded by KFENCE. May be overridden via boot + parameter "kfence.sample_interval". + + Set this to 0 to disable KFENCE by default, in which case only + setting "kfence.sample_interval" to a non-zero value enables KFENCE. + +config KFENCE_NUM_OBJECTS + int "Number of guarded objects available" + range 1 65535 + default 255 + help + The number of guarded objects available. For each KFENCE object, 2 + pages are required; with one containing the object and two adjacent + ones used as guard pages. + +config KFENCE_STRESS_TEST_FAULTS + int "Stress testing of fault handling and error reporting" if EXPERT + default 0 + help + The inverse probability with which to randomly protect KFENCE object + pages, resulting in spurious use-after-frees. The main purpose of + this option is to stress test KFENCE with concurrent error reports + and allocations/frees. A value of 0 disables stress testing logic. + + Only for KFENCE testing; set to 0 if you are not a KFENCE developer. + +endif # KFENCE diff --git a/mm/Makefile b/mm/Makefile index 2b1991759835..3d81a67d66a2 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -82,6 +82,7 @@ obj-$(CONFIG_PAGE_POISONING) += page_poison.o obj-$(CONFIG_SLAB) += slab.o obj-$(CONFIG_SLUB) += slub.o obj-$(CONFIG_KASAN) += kasan/ +obj-$(CONFIG_KFENCE) += kfence/ obj-$(CONFIG_FAILSLAB) += failslab.o obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o obj-$(CONFIG_MEMTEST) += memtest.o diff --git a/mm/kfence/Makefile b/mm/kfence/Makefile new file mode 100644 index 000000000000..d991e9a349f0 --- /dev/null +++ b/mm/kfence/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-$(CONFIG_KFENCE) := core.o report.o diff --git a/mm/kfence/core.c b/mm/kfence/core.c new file mode 100644 index 000000000000..d6a32c13336b --- /dev/null +++ b/mm/kfence/core.c @@ -0,0 +1,840 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KFENCE guarded object allocator and fault handling. + * + * Copyright (C) 2020, Google LLC. + */ + +#define pr_fmt(fmt) "kfence: " fmt + +#include <linux/atomic.h> +#include <linux/bug.h> +#include <linux/debugfs.h> +#include <linux/kcsan-checks.h> +#include <linux/kfence.h> +#include <linux/list.h> +#include <linux/lockdep.h> +#include <linux/memblock.h> +#include <linux/moduleparam.h> +#include <linux/random.h> +#include <linux/rcupdate.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/string.h> + +#include <asm/kfence.h> + +#include "kfence.h" + +/* Disables KFENCE on the first warning assuming an irrecoverable error. */ +#define KFENCE_WARN_ON(cond) \ + ({ \ + const bool __cond = WARN_ON(cond); \ + if (unlikely(__cond)) \ + WRITE_ONCE(kfence_enabled, false); \ + __cond; \ + }) + +/* === Data ================================================================= */ + +static bool kfence_enabled __read_mostly; + +static unsigned long kfence_sample_interval __read_mostly = CONFIG_KFENCE_SAMPLE_INTERVAL; + +#ifdef MODULE_PARAM_PREFIX +#undef MODULE_PARAM_PREFIX +#endif +#define MODULE_PARAM_PREFIX "kfence." + +static int param_set_sample_interval(const char *val, const struct kernel_param *kp) +{ + unsigned long num; + int ret = kstrtoul(val, 0, &num); + + if (ret < 0) + return ret; + + if (!num) /* Using 0 to indicate KFENCE is disabled. */ + WRITE_ONCE(kfence_enabled, false); + else if (!READ_ONCE(kfence_enabled) && system_state != SYSTEM_BOOTING) + return -EINVAL; /* Cannot (re-)enable KFENCE on-the-fly. */ + + *((unsigned long *)kp->arg) = num; + return 0; +} + +static int param_get_sample_interval(char *buffer, const struct kernel_param *kp) +{ + if (!READ_ONCE(kfence_enabled)) + return sprintf(buffer, "0\n"); + + return param_get_ulong(buffer, kp); +} + +static const struct kernel_param_ops sample_interval_param_ops = { + .set = param_set_sample_interval, + .get = param_get_sample_interval, +}; +module_param_cb(sample_interval, &sample_interval_param_ops, &kfence_sample_interval, 0600); + +/* The pool of pages used for guard pages and objects. */ +char *__kfence_pool __ro_after_init; +EXPORT_SYMBOL(__kfence_pool); /* Export for test modules. */ + +/* + * Per-object metadata, with one-to-one mapping of object metadata to + * backing pages (in __kfence_pool). + */ +static_assert(CONFIG_KFENCE_NUM_OBJECTS > 0); +struct kfence_metadata kfence_metadata[CONFIG_KFENCE_NUM_OBJECTS]; + +/* Freelist with available objects. */ +static struct list_head kfence_freelist = LIST_HEAD_INIT(kfence_freelist); +static DEFINE_RAW_SPINLOCK(kfence_freelist_lock); /* Lock protecting freelist. */ + +#ifdef CONFIG_KFENCE_STATIC_KEYS +/* The static key to set up a KFENCE allocation. */ +DEFINE_STATIC_KEY_FALSE(kfence_allocation_key); +#endif + +/* Gates the allocation, ensuring only one succeeds in a given period. */ +atomic_t kfence_allocation_gate = ATOMIC_INIT(1); + +/* Statistics counters for debugfs. */ +enum kfence_counter_id { + KFENCE_COUNTER_ALLOCATED, + KFENCE_COUNTER_ALLOCS, + KFENCE_COUNTER_FREES, + KFENCE_COUNTER_ZOMBIES, + KFENCE_COUNTER_BUGS, + KFENCE_COUNTER_COUNT, +}; +static atomic_long_t counters[KFENCE_COUNTER_COUNT]; +static const char *const counter_names[] = { + [KFENCE_COUNTER_ALLOCATED] = "currently allocated", + [KFENCE_COUNTER_ALLOCS] = "total allocations", + [KFENCE_COUNTER_FREES] = "total frees", + [KFENCE_COUNTER_ZOMBIES] = "zombie allocations", + [KFENCE_COUNTER_BUGS] = "total bugs", +}; +static_assert(ARRAY_SIZE(counter_names) == KFENCE_COUNTER_COUNT); + +/* === Internals ============================================================ */ + +static bool kfence_protect(unsigned long addr) +{ + return !KFENCE_WARN_ON(!kfence_protect_page(ALIGN_DOWN(addr, PAGE_SIZE), true)); +} + +static bool kfence_unprotect(unsigned long addr) +{ + return !KFENCE_WARN_ON(!kfence_protect_page(ALIGN_DOWN(addr, PAGE_SIZE), false)); +} + +static inline struct kfence_metadata *addr_to_metadata(unsigned long addr) +{ + long index; + + /* The checks do not affect performance; only called from slow-paths. */ + + if (!is_kfence_address((void *)addr)) + return NULL; + + /* + * May be an invalid index if called with an address at the edge of + * __kfence_pool, in which case we would report an "invalid access" + * error. + */ + index = (addr - (unsigned long)__kfence_pool) / (PAGE_SIZE * 2) - 1; + if (index < 0 || index >= CONFIG_KFENCE_NUM_OBJECTS) + return NULL; + + return &kfence_metadata[index]; +} + +static inline unsigned long metadata_to_pageaddr(const struct kfence_metadata *meta) +{ + unsigned long offset = (meta - kfence_metadata + 1) * PAGE_SIZE * 2; + unsigned long pageaddr = (unsigned long)&__kfence_pool[offset]; + + /* The checks do not affect performance; only called from slow-paths. */ + + /* Only call with a pointer into kfence_metadata. */ + if (KFENCE_WARN_ON(meta < kfence_metadata || + meta >= kfence_metadata + CONFIG_KFENCE_NUM_OBJECTS)) + return 0; + + /* + * This metadata object only ever maps to 1 page; verify that the stored + * address is in the expected range. + */ + if (KFENCE_WARN_ON(ALIGN_DOWN(meta->addr, PAGE_SIZE) != pageaddr)) + return 0; + + return pageaddr; +} + +/* + * Update the object's metadata state, including updating the alloc/free stacks + * depending on the state transition. + */ +static noinline void metadata_update_state(struct kfence_metadata *meta, + enum kfence_object_state next) +{ + struct kfence_track *track = + next == KFENCE_OBJECT_FREED ? &meta->free_track : &meta->alloc_track; + + lockdep_assert_held(&meta->lock); + + /* + * Skip over 1 (this) functions; noinline ensures we do not accidentally + * skip over the caller by never inlining. + */ + track->num_stack_entries = stack_trace_save(track->stack_entries, KFENCE_STACK_DEPTH, 1); + track->pid = task_pid_nr(current); + + /* + * Pairs with READ_ONCE() in + * kfence_shutdown_cache(), + * kfence_handle_page_fault(). + */ + WRITE_ONCE(meta->state, next); +} + +/* Write canary byte to @addr. */ +static inline bool set_canary_byte(u8 *addr) +{ + *addr = KFENCE_CANARY_PATTERN(addr); + return true; +} + +/* Check canary byte at @addr. */ +static inline bool check_canary_byte(u8 *addr) +{ + if (likely(*addr == KFENCE_CANARY_PATTERN(addr))) + return true; + + atomic_long_inc(&counters[KFENCE_COUNTER_BUGS]); + kfence_report_error((unsigned long)addr, addr_to_metadata((unsigned long)addr), + KFENCE_ERROR_CORRUPTION); + return false; +} + +/* __always_inline this to ensure we won't do an indirect call to fn. */ +static __always_inline void for_each_canary(const struct kfence_metadata *meta, bool (*fn)(u8 *)) +{ + const unsigned long pageaddr = ALIGN_DOWN(meta->addr, PAGE_SIZE); + unsigned long addr; + + lockdep_assert_held(&meta->lock); + + /* + * We'll iterate over each canary byte per-side until fn() returns + * false. However, we'll still iterate over the canary bytes to the + * right of the object even if there was an error in the canary bytes to + * the left of the object. Specifically, if check_canary_byte() + * generates an error, showing both sides might give more clues as to + * what the error is about when displaying which bytes were corrupted. + */ + + /* Apply to left of object. */ + for (addr = pageaddr; addr < meta->addr; addr++) { + if (!fn((u8 *)addr)) + break; + } + + /* Apply to right of object. */ + for (addr = meta->addr + meta->size; addr < pageaddr + PAGE_SIZE; addr++) { + if (!fn((u8 *)addr)) + break; + } +} + +static void *kfence_guarded_alloc(struct kmem_cache *cache, size_t size, gfp_t gfp) +{ + struct kfence_metadata *meta = NULL; + unsigned long flags; + struct page *page; + void *addr; + + /* Try to obtain a free object. */ + raw_spin_lock_irqsave(&kfence_freelist_lock, flags); + if (!list_empty(&kfence_freelist)) { + meta = list_entry(kfence_freelist.next, struct kfence_metadata, list); + list_del_init(&meta->list); + } + raw_spin_unlock_irqrestore(&kfence_freelist_lock, flags); + if (!meta) + return NULL; + + if (unlikely(!raw_spin_trylock_irqsave(&meta->lock, flags))) { + /* + * This is extremely unlikely -- we are reporting on a + * use-after-free, which locked meta->lock, and the reporting + * code via printk calls kmalloc() which ends up in + * kfence_alloc() and tries to grab the same object that we're + * reporting on. While it has never been observed, lockdep does + * report that there is a possibility of deadlock. Fix it by + * using trylock and bailing out gracefully. + */ + raw_spin_lock_irqsave(&kfence_freelist_lock, flags); + /* Put the object back on the freelist. */ + list_add_tail(&meta->list, &kfence_freelist); + raw_spin_unlock_irqrestore(&kfence_freelist_lock, flags); + + return NULL; + } + + meta->addr = metadata_to_pageaddr(meta); + /* Unprotect if we're reusing this page. */ + if (meta->state == KFENCE_OBJECT_FREED) + kfence_unprotect(meta->addr); + + /* + * Note: for allocations made before RNG initialization, will always + * return zero. We still benefit from enabling KFENCE as early as + * possible, even when the RNG is not yet available, as this will allow + * KFENCE to detect bugs due to earlier allocations. The only downside + * is that the out-of-bounds accesses detected are deterministic for + * such allocations. + */ + if (prandom_u32_max(2)) { + /* Allocate on the "right" side, re-calculate address. */ + meta->addr += PAGE_SIZE - size; + meta->addr = ALIGN_DOWN(meta->addr, cache->align); + } + + addr = (void *)meta->addr; + + /* Update remaining metadata. */ + metadata_update_state(meta, KFENCE_OBJECT_ALLOCATED); + /* Pairs with READ_ONCE() in kfence_shutdown_cache(). */ + WRITE_ONCE(meta->cache, cache); + meta->size = size; + for_each_canary(meta, set_canary_byte); + + /* Set required struct page fields. */ + page = virt_to_page(meta->addr); + page->slab_cache = cache; + + raw_spin_unlock_irqrestore(&meta->lock, flags); + + /* Memory initialization. */ + + /* + * We check slab_want_init_on_alloc() ourselves, rather than letting + * SL*B do the initialization, as otherwise we might overwrite KFENCE's + * redzone. + */ + if (unlikely(slab_want_init_on_alloc(gfp, cache))) + memzero_explicit(addr, size); + if (cache->ctor) + cache->ctor(addr); + + if (CONFIG_KFENCE_STRESS_TEST_FAULTS && !prandom_u32_max(CONFIG_KFENCE_STRESS_TEST_FAULTS)) + kfence_protect(meta->addr); /* Random "faults" by protecting the object. */ + + atomic_long_inc(&counters[KFENCE_COUNTER_ALLOCATED]); + atomic_long_inc(&counters[KFENCE_COUNTER_ALLOCS]); + + return addr; +} + +static void kfence_guarded_free(void *addr, struct kfence_metadata *meta, bool zombie) +{ + struct kcsan_scoped_access assert_page_exclusive; + unsigned long flags; + + raw_spin_lock_irqsave(&meta->lock, flags); + + if (meta->state != KFENCE_OBJECT_ALLOCATED || meta->addr != (unsigned long)addr) { + /* Invalid or double-free, bail out. */ + atomic_long_inc(&counters[KFENCE_COUNTER_BUGS]); + kfence_report_error((unsigned long)addr, meta, KFENCE_ERROR_INVALID_FREE); + raw_spin_unlock_irqrestore(&meta->lock, flags); + return; + } + + /* Detect racy use-after-free, or incorrect reallocation of this page by KFENCE. */ + kcsan_begin_scoped_access((void *)ALIGN_DOWN((unsigned long)addr, PAGE_SIZE), PAGE_SIZE, + KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ASSERT, + &assert_page_exclusive); + + if (CONFIG_KFENCE_STRESS_TEST_FAULTS) + kfence_unprotect((unsigned long)addr); /* To check canary bytes. */ + + /* Restore page protection if there was an OOB access. */ + if (meta->unprotected_page) { + kfence_protect(meta->unprotected_page); + meta->unprotected_page = 0; + } + + /* Check canary bytes for memory corruption. */ + for_each_canary(meta, check_canary_byte); + + /* + * Clear memory if init-on-free is set. While we protect the page, the + * data is still there, and after a use-after-free is detected, we + * unprotect the page, so the data is still accessible. + */ + if (!zombie && unlikely(slab_want_init_on_free(meta->cache))) + memzero_explicit(addr, meta->size); + + /* Mark the object as freed. */ + metadata_update_state(meta, KFENCE_OBJECT_FREED); + + raw_spin_unlock_irqrestore(&meta->lock, flags); + + /* Protect to detect use-after-frees. */ + kfence_protect((unsigned long)addr); + + kcsan_end_scoped_access(&assert_page_exclusive); + if (!zombie) { + /* Add it to the tail of the freelist for reuse. */ + raw_spin_lock_irqsave(&kfence_freelist_lock, flags); + KFENCE_WARN_ON(!list_empty(&meta->list)); + list_add_tail(&meta->list, &kfence_freelist); + raw_spin_unlock_irqrestore(&kfence_freelist_lock, flags); + + atomic_long_dec(&counters[KFENCE_COUNTER_ALLOCATED]); + atomic_long_inc(&counters[KFENCE_COUNTER_FREES]); + } else { + /* See kfence_shutdown_cache(). */ + atomic_long_inc(&counters[KFENCE_COUNTER_ZOMBIES]); + } +} + +static void rcu_guarded_free(struct rcu_head *h) +{ + struct kfence_metadata *meta = container_of(h, struct kfence_metadata, rcu_head); + + kfence_guarded_free((void *)meta->addr, meta, false); +} + +static bool __init kfence_init_pool(void) +{ + unsigned long addr = (unsigned long)__kfence_pool; + struct page *pages; + int i; + + if (!__kfence_pool) + return false; + + if (!arch_kfence_init_pool()) + goto err; + + pages = virt_to_page(addr); + + /* + * Set up object pages: they must have PG_slab set, to avoid freeing + * these as real pages. + * + * We also want to avoid inserting kfence_free() in the kfree() + * fast-path in SLUB, and therefore need to ensure kfree() correctly + * enters __slab_free() slow-path. + */ + for (i = 0; i < KFENCE_POOL_SIZE / PAGE_SIZE; i++) { + if (!i || (i % 2)) + continue; + + /* Verify we do not have a compound head page. */ + if (WARN_ON(compound_head(&pages[i]) != &pages[i])) + goto err; + + __SetPageSlab(&pages[i]); + } + + /* + * Protect the first 2 pages. The first page is mostly unnecessary, and + * merely serves as an extended guard page. However, adding one + * additional page in the beginning gives us an even number of pages, + * which simplifies the mapping of address to metadata index. + */ + for (i = 0; i < 2; i++) { + if (unlikely(!kfence_protect(addr))) + goto err; + + addr += PAGE_SIZE; + } + + for (i = 0; i < CONFIG_KFENCE_NUM_OBJECTS; i++) { + struct kfence_metadata *meta = &kfence_metadata[i]; + + /* Initialize metadata. */ + INIT_LIST_HEAD(&meta->list); + raw_spin_lock_init(&meta->lock); + meta->state = KFENCE_OBJECT_UNUSED; + meta->addr = addr; /* Initialize for validation in metadata_to_pageaddr(). */ + list_add_tail(&meta->list, &kfence_freelist); + + /* Protect the right redzone. */ + if (unlikely(!kfence_protect(addr + PAGE_SIZE))) + goto err; + + addr += 2 * PAGE_SIZE; + } + + return true; + +err: + /* + * Only release unprotected pages, and do not try to go back and change + * page attributes due to risk of failing to do so as well. If changing + * page attributes for some pages fails, it is very likely that it also + * fails for the first page, and therefore expect addr==__kfence_pool in + * most failure cases. + */ + memblock_free_late(__pa(addr), KFENCE_POOL_SIZE - (addr - (unsigned long)__kfence_pool)); + __kfence_pool = NULL; + return false; +} + +/* === DebugFS Interface ==================================================== */ + +static int stats_show(struct seq_file *seq, void *v) +{ + int i; + + seq_printf(seq, "enabled: %i\n", READ_ONCE(kfence_enabled)); + for (i = 0; i < KFENCE_COUNTER_COUNT; i++) + seq_printf(seq, "%s: %ld\n", counter_names[i], atomic_long_read(&counters[i])); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(stats); + +/* + * debugfs seq_file operations for /sys/kernel/debug/kfence/objects. + * start_object() and next_object() return the object index + 1, because NULL is used + * to stop iteration. + */ +static void *start_object(struct seq_file *seq, loff_t *pos) +{ + if (*pos < CONFIG_KFENCE_NUM_OBJECTS) + return (void *)((long)*pos + 1); + return NULL; +} + +static void stop_object(struct seq_file *seq, void *v) +{ +} + +static void *next_object(struct seq_file *seq, void *v, loff_t *pos) +{ + ++*pos; + if (*pos < CONFIG_KFENCE_NUM_OBJECTS) + return (void *)((long)*pos + 1); + return NULL; +} + +static int show_object(struct seq_file *seq, void *v) +{ + struct kfence_metadata *meta = &kfence_metadata[(long)v - 1]; + unsigned long flags; + + raw_spin_lock_irqsave(&meta->lock, flags); + kfence_print_object(seq, meta); + raw_spin_unlock_irqrestore(&meta->lock, flags); + seq_puts(seq, "---------------------------------\n"); + + return 0; +} + +static const struct seq_operations object_seqops = { + .start = start_object, + .next = next_object, + .stop = stop_object, + .show = show_object, +}; + +static int open_objects(struct inode *inode, struct file *file) +{ + return seq_open(file, &object_seqops); +} + +static const struct file_operations objects_fops = { + .open = open_objects, + .read = seq_read, + .llseek = seq_lseek, +}; + +static int __init kfence_debugfs_init(void) +{ + struct dentry *kfence_dir = debugfs_create_dir("kfence", NULL); + + debugfs_create_file("stats", 0444, kfence_dir, NULL, &stats_fops); + debugfs_create_file("objects", 0400, kfence_dir, NULL, &objects_fops); + return 0; +} + +late_initcall(kfence_debugfs_init); + +/* === Allocation Gate Timer ================================================ */ + +/* + * Set up delayed work, which will enable and disable the static key. We need to + * use a work queue (rather than a simple timer), since enabling and disabling a + * static key cannot be done from an interrupt. + * + * Note: Toggling a static branch currently causes IPIs, and here we'll end up + * with a total of 2 IPIs to all CPUs. If this ends up a problem in future (with + * more aggressive sampling intervals), we could get away with a variant that + * avoids IPIs, at the cost of not immediately capturing allocations if the + * instructions remain cached. + */ +static struct delayed_work kfence_timer; +static void toggle_allocation_gate(struct work_struct *work) +{ + if (!READ_ONCE(kfence_enabled)) + return; + + /* Enable static key, and await allocation to happen. */ + atomic_set(&kfence_allocation_gate, 0); +#ifdef CONFIG_KFENCE_STATIC_KEYS + static_branch_enable(&kfence_allocation_key); + /* + * Await an allocation. Timeout after 1 second, in case the kernel stops + * doing allocations, to avoid stalling this worker task for too long. + */ + { + unsigned long end_wait = jiffies + HZ; + + do { + set_current_state(TASK_UNINTERRUPTIBLE); + if (atomic_read(&kfence_allocation_gate) != 0) + break; + schedule_timeout(1); + } while (time_before(jiffies, end_wait)); + __set_current_state(TASK_RUNNING); + } + /* Disable static key and reset timer. */ + static_branch_disable(&kfence_allocation_key); +#endif + schedule_delayed_work(&kfence_timer, msecs_to_jiffies(kfence_sample_interval)); +} +static DECLARE_DELAYED_WORK(kfence_timer, toggle_allocation_gate); + +/* === Public interface ===================================================== */ + +void __init kfence_alloc_pool(void) +{ + if (!kfence_sample_interval) + return; + + __kfence_pool = memblock_alloc(KFENCE_POOL_SIZE, PAGE_SIZE); + + if (!__kfence_pool) + pr_err("failed to allocate pool\n"); +} + +void __init kfence_init(void) +{ + /* Setting kfence_sample_interval to 0 on boot disables KFENCE. */ + if (!kfence_sample_interval) + return; + + if (!kfence_init_pool()) { + pr_err("%s failed\n", __func__); + return; + } + + WRITE_ONCE(kfence_enabled, true); + schedule_delayed_work(&kfence_timer, 0); + pr_info("initialized - using %lu bytes for %d objects", KFENCE_POOL_SIZE, + CONFIG_KFENCE_NUM_OBJECTS); + if (IS_ENABLED(CONFIG_DEBUG_KERNEL)) + pr_cont(" at 0x%px-0x%px\n", (void *)__kfence_pool, + (void *)(__kfence_pool + KFENCE_POOL_SIZE)); + else + pr_cont("\n"); +} + +void kfence_shutdown_cache(struct kmem_cache *s) +{ + unsigned long flags; + struct kfence_metadata *meta; + int i; + + for (i = 0; i < CONFIG_KFENCE_NUM_OBJECTS; i++) { + bool in_use; + + meta = &kfence_metadata[i]; + + /* + * If we observe some inconsistent cache and state pair where we + * should have returned false here, cache destruction is racing + * with either kmem_cache_alloc() or kmem_cache_free(). Taking + * the lock will not help, as different critical section + * serialization will have the same outcome. + */ + if (READ_ONCE(meta->cache) != s || + READ_ONCE(meta->state) != KFENCE_OBJECT_ALLOCATED) + continue; + + raw_spin_lock_irqsave(&meta->lock, flags); + in_use = meta->cache == s && meta->state == KFENCE_OBJECT_ALLOCATED; + raw_spin_unlock_irqrestore(&meta->lock, flags); + + if (in_use) { + /* + * This cache still has allocations, and we should not + * release them back into the freelist so they can still + * safely be used and retain the kernel's default + * behaviour of keeping the allocations alive (leak the + * cache); however, they effectively become "zombie + * allocations" as the KFENCE objects are the only ones + * still in use and the owning cache is being destroyed. + * + * We mark them freed, so that any subsequent use shows + * more useful error messages that will include stack + * traces of the user of the object, the original + * allocation, and caller to shutdown_cache(). + */ + kfence_guarded_free((void *)meta->addr, meta, /*zombie=*/true); + } + } + + for (i = 0; i < CONFIG_KFENCE_NUM_OBJECTS; i++) { + meta = &kfence_metadata[i]; + + /* See above. */ + if (READ_ONCE(meta->cache) != s || READ_ONCE(meta->state) != KFENCE_OBJECT_FREED) + continue; + + raw_spin_lock_irqsave(&meta->lock, flags); + if (meta->cache == s && meta->state == KFENCE_OBJECT_FREED) + meta->cache = NULL; + raw_spin_unlock_irqrestore(&meta->lock, flags); + } +} + +void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) +{ + /* + * allocation_gate only needs to become non-zero, so it doesn't make + * sense to continue writing to it and pay the associated contention + * cost, in case we have a large number of concurrent allocations. + */ + if (atomic_read(&kfence_allocation_gate) || atomic_inc_return(&kfence_allocation_gate) > 1) + return NULL; + + if (!READ_ONCE(kfence_enabled)) + return NULL; + + if (size > PAGE_SIZE) + return NULL; + + return kfence_guarded_alloc(s, size, flags); +} + +size_t kfence_ksize(const void *addr) +{ + const struct kfence_metadata *meta = addr_to_metadata((unsigned long)addr); + + /* + * Read locklessly -- if there is a race with __kfence_alloc(), this is + * either a use-after-free or invalid access. + */ + return meta ? meta->size : 0; +} + +void *kfence_object_start(const void *addr) +{ + const struct kfence_metadata *meta = addr_to_metadata((unsigned long)addr); + + /* + * Read locklessly -- if there is a race with __kfence_alloc(), this is + * either a use-after-free or invalid access. + */ + return meta ? (void *)meta->addr : NULL; +} + +void __kfence_free(void *addr) +{ + struct kfence_metadata *meta = addr_to_metadata((unsigned long)addr); + + /* + * If the objects of the cache are SLAB_TYPESAFE_BY_RCU, defer freeing + * the object, as the object page may be recycled for other-typed + * objects once it has been freed. meta->cache may be NULL if the cache + * was destroyed. + */ + if (unlikely(meta->cache && (meta->cache->flags & SLAB_TYPESAFE_BY_RCU))) + call_rcu(&meta->rcu_head, rcu_guarded_free); + else + kfence_guarded_free(addr, meta, false); +} + +bool kfence_handle_page_fault(unsigned long addr) +{ + const int page_index = (addr - (unsigned long)__kfence_pool) / PAGE_SIZE; + struct kfence_metadata *to_report = NULL; + enum kfence_error_type error_type; + unsigned long flags; + + if (!is_kfence_address((void *)addr)) + return false; + + if (!READ_ONCE(kfence_enabled)) /* If disabled at runtime ... */ + return kfence_unprotect(addr); /* ... unprotect and proceed. */ + + atomic_long_inc(&counters[KFENCE_COUNTER_BUGS]); + + if (page_index % 2) { + /* This is a redzone, report a buffer overflow. */ + struct kfence_metadata *meta; + int distance = 0; + + meta = addr_to_metadata(addr - PAGE_SIZE); + if (meta && READ_ONCE(meta->state) == KFENCE_OBJECT_ALLOCATED) { + to_report = meta; + /* Data race ok; distance calculation approximate. */ + distance = addr - data_race(meta->addr + meta->size); + } + + meta = addr_to_metadata(addr + PAGE_SIZE); + if (meta && READ_ONCE(meta->state) == KFENCE_OBJECT_ALLOCATED) { + /* Data race ok; distance calculation approximate. */ + if (!to_report || distance > data_race(meta->addr) - addr) + to_report = meta; + } + + if (!to_report) + goto out; + + raw_spin_lock_irqsave(&to_report->lock, flags); + to_report->unprotected_page = addr; + error_type = KFENCE_ERROR_OOB; + + /* + * If the object was freed before we took the look we can still + * report this as an OOB -- the report will simply show the + * stacktrace of the free as well. + */ + } else { + to_report = addr_to_metadata(addr); + if (!to_report) + goto out; + + raw_spin_lock_irqsave(&to_report->lock, flags); + error_type = KFENCE_ERROR_UAF; + /* + * We may race with __kfence_alloc(), and it is possible that a + * freed object may be reallocated. We simply report this as a + * use-after-free, with the stack trace showing the place where + * the object was re-allocated. + */ + } + +out: + if (to_report) { + kfence_report_error(addr, to_report, error_type); + raw_spin_unlock_irqrestore(&to_report->lock, flags); + } else { + /* This may be a UAF or OOB access, but we can't be sure. */ + kfence_report_error(addr, NULL, KFENCE_ERROR_INVALID); + } + + return kfence_unprotect(addr); /* Unprotect and let access proceed. */ +} diff --git a/mm/kfence/kfence.h b/mm/kfence/kfence.h new file mode 100644 index 000000000000..1014060f9707 --- /dev/null +++ b/mm/kfence/kfence.h @@ -0,0 +1,113 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Kernel Electric-Fence (KFENCE). For more info please see + * Documentation/dev-tools/kfence.rst. + * + * Copyright (C) 2020, Google LLC. + */ + +#ifndef MM_KFENCE_KFENCE_H +#define MM_KFENCE_KFENCE_H + +#include <linux/mm.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/types.h> + +#include "../slab.h" /* for struct kmem_cache */ + +/* For non-debug builds, avoid leaking kernel pointers into dmesg. */ +#ifdef CONFIG_DEBUG_KERNEL +#define PTR_FMT "%px" +#else +#define PTR_FMT "%p" +#endif + +/* + * Get the canary byte pattern for @addr. Use a pattern that varies based on the + * lower 3 bits of the address, to detect memory corruptions with higher + * probability, where similar constants are used. + */ +#define KFENCE_CANARY_PATTERN(addr) ((u8)0xaa ^ (u8)((unsigned long)(addr) & 0x7)) + +/* Maximum stack depth for reports. */ +#define KFENCE_STACK_DEPTH 64 + +/* KFENCE object states. */ +enum kfence_object_state { + KFENCE_OBJECT_UNUSED, /* Object is unused. */ + KFENCE_OBJECT_ALLOCATED, /* Object is currently allocated. */ + KFENCE_OBJECT_FREED, /* Object was allocated, and then freed. */ +}; + +/* Alloc/free tracking information. */ +struct kfence_track { + pid_t pid; + int num_stack_entries; + unsigned long stack_entries[KFENCE_STACK_DEPTH]; +}; + +/* KFENCE metadata per guarded allocation. */ +struct kfence_metadata { + struct list_head list; /* Freelist node; access under kfence_freelist_lock. */ + struct rcu_head rcu_head; /* For delayed freeing. */ + + /* + * Lock protecting below data; to ensure consistency of the below data, + * since the following may execute concurrently: __kfence_alloc(), + * __kfence_free(), kfence_handle_page_fault(). However, note that we + * cannot grab the same metadata off the freelist twice, and multiple + * __kfence_alloc() cannot run concurrently on the same metadata. + */ + raw_spinlock_t lock; + + /* The current state of the object; see above. */ + enum kfence_object_state state; + + /* + * Allocated object address; cannot be calculated from size, because of + * alignment requirements. + * + * Invariant: ALIGN_DOWN(addr, PAGE_SIZE) is constant. + */ + unsigned long addr; + + /* + * The size of the original allocation. + */ + size_t size; + + /* + * The kmem_cache cache of the last allocation; NULL if never allocated + * or the cache has already been destroyed. + */ + struct kmem_cache *cache; + + /* + * In case of an invalid access, the page that was unprotected; we + * optimistically only store one address. + */ + unsigned long unprotected_page; + + /* Allocation and free stack information. */ + struct kfence_track alloc_track; + struct kfence_track free_track; +}; + +extern struct kfence_metadata kfence_metadata[CONFIG_KFENCE_NUM_OBJECTS]; + +/* KFENCE error types for report generation. */ +enum kfence_error_type { + KFENCE_ERROR_OOB, /* Detected a out-of-bounds access. */ + KFENCE_ERROR_UAF, /* Detected a use-after-free access. */ + KFENCE_ERROR_CORRUPTION, /* Detected a memory corruption on free. */ + KFENCE_ERROR_INVALID, /* Invalid access of unknown type. */ + KFENCE_ERROR_INVALID_FREE, /* Invalid free. */ +}; + +void kfence_report_error(unsigned long address, const struct kfence_metadata *meta, + enum kfence_error_type type); + +void kfence_print_object(struct seq_file *seq, const struct kfence_metadata *meta); + +#endif /* MM_KFENCE_KFENCE_H */ diff --git a/mm/kfence/report.c b/mm/kfence/report.c new file mode 100644 index 000000000000..64f27c8d46a3 --- /dev/null +++ b/mm/kfence/report.c @@ -0,0 +1,240 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KFENCE reporting. + * + * Copyright (C) 2020, Google LLC. + */ + +#include <stdarg.h> + +#include <linux/kernel.h> +#include <linux/lockdep.h> +#include <linux/printk.h> +#include <linux/seq_file.h> +#include <linux/stacktrace.h> +#include <linux/string.h> + +#include <asm/kfence.h> + +#include "kfence.h" + +/* Helper function to either print to a seq_file or to console. */ +__printf(2, 3) +static void seq_con_printf(struct seq_file *seq, const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + if (seq) + seq_vprintf(seq, fmt, args); + else + vprintk(fmt, args); + va_end(args); +} + +/* + * Get the number of stack entries to skip to get out of MM internals. @type is + * optional, and if set to NULL, assumes an allocation or free stack. + */ +static int get_stack_skipnr(const unsigned long stack_entries[], int num_entries, + const enum kfence_error_type *type) +{ + char buf[64]; + int skipnr, fallback = 0; + bool is_access_fault = false; + + if (type) { + /* Depending on error type, find different stack entries. */ + switch (*type) { + case KFENCE_ERROR_UAF: + case KFENCE_ERROR_OOB: + case KFENCE_ERROR_INVALID: + is_access_fault = true; + break; + case KFENCE_ERROR_CORRUPTION: + case KFENCE_ERROR_INVALID_FREE: + break; + } + } + + for (skipnr = 0; skipnr < num_entries; skipnr++) { + int len = scnprintf(buf, sizeof(buf), "%ps", (void *)stack_entries[skipnr]); + + if (is_access_fault) { + if (!strncmp(buf, KFENCE_SKIP_ARCH_FAULT_HANDLER, len)) + goto found; + } else { + if (str_has_prefix(buf, "kfence_") || str_has_prefix(buf, "__kfence_") || + !strncmp(buf, "__slab_free", len)) { + /* + * In case of tail calls from any of the below + * to any of the above. + */ + fallback = skipnr + 1; + } + + /* Also the *_bulk() variants by only checking prefixes. */ + if (str_has_prefix(buf, "kfree") || + str_has_prefix(buf, "kmem_cache_free") || + str_has_prefix(buf, "__kmalloc") || + str_has_prefix(buf, "kmem_cache_alloc")) + goto found; + } + } + if (fallback < num_entries) + return fallback; +found: + skipnr++; + return skipnr < num_entries ? skipnr : 0; +} + +static void kfence_print_stack(struct seq_file *seq, const struct kfence_metadata *meta, + bool show_alloc) +{ + const struct kfence_track *track = show_alloc ? &meta->alloc_track : &meta->free_track; + + if (track->num_stack_entries) { + /* Skip allocation/free internals stack. */ + int i = get_stack_skipnr(track->stack_entries, track->num_stack_entries, NULL); + + /* stack_trace_seq_print() does not exist; open code our own. */ + for (; i < track->num_stack_entries; i++) + seq_con_printf(seq, " %pS\n", (void *)track->stack_entries[i]); + } else { + seq_con_printf(seq, " no %s stack\n", show_alloc ? "allocation" : "deallocation"); + } +} + +void kfence_print_object(struct seq_file *seq, const struct kfence_metadata *meta) +{ + const int size = abs(meta->size); + const unsigned long start = meta->addr; + const struct kmem_cache *const cache = meta->cache; + + lockdep_assert_held(&meta->lock); + + if (meta->state == KFENCE_OBJECT_UNUSED) { + seq_con_printf(seq, "kfence-#%zd unused\n", meta - kfence_metadata); + return; + } + + seq_con_printf(seq, + "kfence-#%zd [0x" PTR_FMT "-0x" PTR_FMT + ", size=%d, cache=%s] allocated by task %d:\n", + meta - kfence_metadata, (void *)start, (void *)(start + size - 1), size, + (cache && cache->name) ? cache->name : "<destroyed>", meta->alloc_track.pid); + kfence_print_stack(seq, meta, true); + + if (meta->state == KFENCE_OBJECT_FREED) { + seq_con_printf(seq, "\nfreed by task %d:\n", meta->free_track.pid); + kfence_print_stack(seq, meta, false); + } +} + +/* + * Show bytes at @addr that are different from the expected canary values, up to + * @max_bytes. + */ +static void print_diff_canary(unsigned long address, size_t bytes_to_show, + const struct kfence_metadata *meta) +{ + const unsigned long show_until_addr = address + bytes_to_show; + const u8 *cur, *end; + + /* Do not show contents of object nor read into following guard page. */ + end = (const u8 *)(address < meta->addr ? min(show_until_addr, meta->addr) + : min(show_until_addr, PAGE_ALIGN(address))); + + pr_cont("["); + for (cur = (const u8 *)address; cur < end; cur++) { + if (*cur == KFENCE_CANARY_PATTERN(cur)) + pr_cont(" ."); + else if (IS_ENABLED(CONFIG_DEBUG_KERNEL)) + pr_cont(" 0x%02x", *cur); + else /* Do not leak kernel memory in non-debug builds. */ + pr_cont(" !"); + } + pr_cont(" ]"); +} + +void kfence_report_error(unsigned long address, const struct kfence_metadata *meta, + enum kfence_error_type type) +{ + unsigned long stack_entries[KFENCE_STACK_DEPTH] = { 0 }; + int num_stack_entries = stack_trace_save(stack_entries, KFENCE_STACK_DEPTH, 1); + int skipnr = get_stack_skipnr(stack_entries, num_stack_entries, &type); + const ptrdiff_t object_index = meta ? meta - kfence_metadata : -1; + + /* Require non-NULL meta, except if KFENCE_ERROR_INVALID. */ + if (WARN_ON(type != KFENCE_ERROR_INVALID && !meta)) + return; + + if (meta) + lockdep_assert_held(&meta->lock); + /* + * Because we may generate reports in printk-unfriendly parts of the + * kernel, such as scheduler code, the use of printk() could deadlock. + * Until such time that all printing code here is safe in all parts of + * the kernel, accept the risk, and just get our message out (given the + * system might already behave unpredictably due to the memory error). + * As such, also disable lockdep to hide warnings, and avoid disabling + * lockdep for the rest of the kernel. + */ + lockdep_off(); + + pr_err("==================================================================\n"); + /* Print report header. */ + switch (type) { + case KFENCE_ERROR_OOB: { + const bool left_of_object = address < meta->addr; + + pr_err("BUG: KFENCE: out-of-bounds in %pS\n\n", (void *)stack_entries[skipnr]); + pr_err("Out-of-bounds access at 0x" PTR_FMT " (%luB %s of kfence-#%zd):\n", + (void *)address, + left_of_object ? meta->addr - address : address - meta->addr, + left_of_object ? "left" : "right", object_index); + break; + } + case KFENCE_ERROR_UAF: + pr_err("BUG: KFENCE: use-after-free in %pS\n\n", (void *)stack_entries[skipnr]); + pr_err("Use-after-free access at 0x" PTR_FMT " (in kfence-#%zd):\n", + (void *)address, object_index); + break; + case KFENCE_ERROR_CORRUPTION: + pr_err("BUG: KFENCE: memory corruption in %pS\n\n", (void *)stack_entries[skipnr]); + pr_err("Corrupted memory at 0x" PTR_FMT " ", (void *)address); + print_diff_canary(address, 16, meta); + pr_cont(" (in kfence-#%zd):\n", object_index); + break; + case KFENCE_ERROR_INVALID: + pr_err("BUG: KFENCE: invalid access in %pS\n\n", (void *)stack_entries[skipnr]); + pr_err("Invalid access at 0x" PTR_FMT ":\n", (void *)address); + break; + case KFENCE_ERROR_INVALID_FREE: + pr_err("BUG: KFENCE: invalid free in %pS\n\n", (void *)stack_entries[skipnr]); + pr_err("Invalid free of 0x" PTR_FMT " (in kfence-#%zd):\n", (void *)address, + object_index); + break; + } + + /* Print stack trace and object info. */ + stack_trace_print(stack_entries + skipnr, num_stack_entries - skipnr, 0); + + if (meta) { + pr_err("\n"); + kfence_print_object(NULL, meta); + } + + /* Print report footer. */ + pr_err("\n"); + dump_stack_print_info(KERN_ERR); + pr_err("==================================================================\n"); + + lockdep_on(); + + if (panic_on_warn) + panic("panic_on_warn set ...\n"); + + /* We encountered a memory unsafety error, taint the kernel! */ + add_taint(TAINT_BAD_PAGE, LOCKDEP_STILL_OK); +} -- 2.25.1

2 1

[PATCH kernel-4.19 1/2] ACPI / APEI: Add a notifier chain for unknown (vendor) CPER records
by Yang Yingliang 30 Sep '21

30 Sep '21

From: Shiju Jose <shiju.jose(a)huawei.com> mainline inclusion from mainline-v5.10-rc1 commit 9aa9cf3ee9451d08adafc03cef8e44c7ea3898e7 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4CMAR CVE: NA -------------------------------- CPER records describing a firmware-first error are identified by GUID. The ghes driver currently logs, but ignores any unknown CPER records. This prevents describing errors that can't be represented by a standard entry, that would otherwise allow a driver to recover from an error. The UEFI spec calls these 'Non-standard Section Body' (N.2.3 of version 2.8). Add a notifier chain for these non-standard/vendor-records. Callers must identify their type of records by GUID. Record data is copied to memory from the ghes_estatus_pool to allow us to keep it until after the notifier has run. Co-developed-by: James Morse <james.morse(a)arm.com> Link: https://lore.kernel.org/r/20200903123456.1823-2-shiju.jose@huawei.com Signed-off-by: James Morse <james.morse(a)arm.com> Signed-off-by: Shiju Jose <shiju.jose(a)huawei.com> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi(a)arm.com> Acked-by: "Rafael J. Wysocki" <rjw(a)rjwysocki.net> Signed-off-by: Weilong Chen <chenweilong(a)huawei.com> Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/acpi/apei/ghes.c | 64 ++++++++++++++++++++++++++++++++++++++++ include/acpi/ghes.h | 18 +++++++++++ 2 files changed, 82 insertions(+) diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index e807e8f74d1e0..08658c433b1fc 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -84,6 +84,12 @@ ((struct acpi_hest_generic_status *) \ ((struct ghes_estatus_node *)(estatus_node) + 1)) +#define GHES_VENDOR_ENTRY_LEN(gdata_len) \ + (sizeof(struct ghes_vendor_record_entry) + (gdata_len)) +#define GHES_GDATA_FROM_VENDOR_ENTRY(vendor_entry) \ + ((struct acpi_hest_generic_data *) \ + ((struct ghes_vendor_record_entry *)(vendor_entry) + 1)) + static inline bool is_hest_type_generic_v2(struct ghes *ghes) { return ghes->generic->header.type == ACPI_HEST_TYPE_GENERIC_ERROR_V2; @@ -126,6 +132,12 @@ EXPORT_SYMBOL(ghes_ts_err_chain); static DEFINE_RAW_SPINLOCK(ghes_ioremap_lock_nmi); static DEFINE_SPINLOCK(ghes_ioremap_lock_irq); +struct ghes_vendor_record_entry { + struct work_struct work; + int error_severity; + char vendor_record[]; +}; + static struct gen_pool *ghes_estatus_pool; static unsigned long ghes_estatus_pool_size_request; @@ -464,6 +476,57 @@ static void ghes_handle_aer(struct acpi_hest_generic_data *gdata) #endif } +static BLOCKING_NOTIFIER_HEAD(vendor_record_notify_list); + +int ghes_register_vendor_record_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&vendor_record_notify_list, nb); +} +EXPORT_SYMBOL_GPL(ghes_register_vendor_record_notifier); + +void ghes_unregister_vendor_record_notifier(struct notifier_block *nb) +{ + blocking_notifier_chain_unregister(&vendor_record_notify_list, nb); +} +EXPORT_SYMBOL_GPL(ghes_unregister_vendor_record_notifier); + +static void ghes_vendor_record_work_func(struct work_struct *work) +{ + struct ghes_vendor_record_entry *entry; + struct acpi_hest_generic_data *gdata; + u32 len; + + entry = container_of(work, struct ghes_vendor_record_entry, work); + gdata = GHES_GDATA_FROM_VENDOR_ENTRY(entry); + + blocking_notifier_call_chain(&vendor_record_notify_list, + entry->error_severity, gdata); + + len = GHES_VENDOR_ENTRY_LEN(acpi_hest_get_record_size(gdata)); + gen_pool_free(ghes_estatus_pool, (unsigned long)entry, len); +} + +static void ghes_defer_non_standard_event(struct acpi_hest_generic_data *gdata, + int sev) +{ + struct acpi_hest_generic_data *copied_gdata; + struct ghes_vendor_record_entry *entry; + u32 len; + + len = GHES_VENDOR_ENTRY_LEN(acpi_hest_get_record_size(gdata)); + entry = (void *)gen_pool_alloc(ghes_estatus_pool, len); + if (!entry) + return; + + copied_gdata = GHES_GDATA_FROM_VENDOR_ENTRY(entry); + memcpy(copied_gdata, gdata, acpi_hest_get_record_size(gdata)); + entry->error_severity = sev; + + INIT_WORK(&entry->work, ghes_vendor_record_work_func); + schedule_work(&entry->work); +} + + void __weak ghes_arm_process_error(struct ghes *ghes, struct cper_sec_proc_arm *err, int sec_sev) { @@ -517,6 +580,7 @@ static void ghes_do_proc(struct ghes *ghes, } else { void *err = acpi_hest_get_payload(gdata); + ghes_defer_non_standard_event(gdata, sev); log_non_standard_event(sec_type, fru_id, fru_text, sec_sev, err, gdata->error_data_length); diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h index 9aaeaaa3d1a7f..0e96c78f9f180 100644 --- a/include/acpi/ghes.h +++ b/include/acpi/ghes.h @@ -52,6 +52,24 @@ enum { GHES_SEV_PANIC = 0x3, }; +#ifdef CONFIG_ACPI_APEI_GHES +/** + * ghes_register_vendor_record_notifier - register a notifier for vendor + * records that the kernel would otherwise ignore. + * @nb: pointer to the notifier_block structure of the event handler. + * + * return 0 : SUCCESS, non-zero : FAIL + */ +int ghes_register_vendor_record_notifier(struct notifier_block *nb); + +/** + * ghes_unregister_vendor_record_notifier - unregister the previously + * registered vendor record notifier. + * @nb: pointer to the notifier_block structure of the vendor record handler. + */ +void ghes_unregister_vendor_record_notifier(struct notifier_block *nb); +#endif + /* From drivers/edac/ghes_edac.c */ #ifdef CONFIG_EDAC_GHES -- 2.25.1

1 1

[PATCH kernel-4.19] blk-mq-sched: Fix blk_mq_sched_alloc_tags() error handling
by Yang Yingliang 30 Sep '21

30 Sep '21

From: John Garry <john.garry(a)huawei.com> mainline inclusion from mainline-v5.14-rc1 commit b93af3055d6f32d3b0361cfdb110c9399c1241ba category: bugfix bugzilla: 177012 CVE: NA --------------------------- If the blk_mq_sched_alloc_tags() -> blk_mq_alloc_rqs() call fails, then we call blk_mq_sched_free_tags() -> blk_mq_free_rqs(). It is incorrect to do so, as any rqs would have already been freed in the blk_mq_alloc_rqs() call. Fix by calling blk_mq_free_rq_map() only directly. Fixes: 6917ff0b5bd41 ("blk-mq-sched: refactor scheduler initialization") Signed-off-by: John Garry <john.garry(a)huawei.com> Reviewed-by: Ming Lei <ming.lei(a)redhat.com> Link: https://lore.kernel.org/r/1627378373-148090-1-git-send-email-john.garry@hua… Signed-off-by: Jens Axboe <axboe(a)kernel.dk> conflicts: block/blk-mq-sched.c Signed-off-by: Laibin Qiu <qiulaibin(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- block/blk-mq-sched.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index ce4b2ac6d6977..3521eca1b2984 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -513,8 +513,10 @@ static int blk_mq_sched_alloc_tags(struct request_queue *q, return -ENOMEM; ret = blk_mq_alloc_rqs(set, hctx->sched_tags, hctx_idx, q->nr_requests); - if (ret) - blk_mq_sched_free_tags(set, hctx, hctx_idx); + if (ret) { + blk_mq_free_rq_map(hctx->sched_tags); + hctx->sched_tags = NULL; + } return ret; } -- 2.25.1

1 0

[PATCH kernel-4.19 1/3] jbd2: Drop unnecessary branch from jbd2_journal_forget()
by Yang Yingliang 30 Sep '21

30 Sep '21

From: Jan Kara <jack(a)suse.cz> mainline inclusion from mainline-5.5-rc1 commit 6d69843e5d3f0c394e1e3004cc2b36efbe402b71 category: bugfix bugzilla: 176007 CVE: NA --------------------------- We have cleared both dirty & jbddirty bits from the bh. So there's no difference between bforget() and brelse(). Thus there's no point jumping to no_jbd branch. Signed-off-by: Jan Kara <jack(a)suse.cz> Link: https://lore.kernel.org/r/20190809124233.13277-5-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Conflicts: fs/jbd2/transaction.c Signed-off-by: yangerkun <yangerkun(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/jbd2/transaction.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 4055929a043cf..c48658a4d53c0 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1639,10 +1639,6 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh) __jbd2_journal_file_buffer(jh, transaction, BJ_Forget); } else { __jbd2_journal_unfile_buffer(jh); - if (!buffer_jbd(bh)) { - spin_unlock(&journal->j_list_lock); - goto not_jbd; - } } spin_unlock(&journal->j_list_lock); } else if (jh->b_transaction) { -- 2.25.1

1 2

[PATCH openEuler-1.0-LTS] USB: ehci: fix an interrupt calltrace error
by Yang Yingliang 30 Sep '21

30 Sep '21

From: Longfang Liu <liulongfang(a)huawei.com> mainline inclusion from mainline-v5.11-rc5 commit 643a4df7fe3f6831d14536fd692be85f92670a52 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4CDK3?from=project-issue CVE: NA ---------------------------------------- The system that use Synopsys USB host controllers goes to suspend when using USB audio player. This causes the USB host controller continuous send interrupt signal to system, When the number of interrupts exceeds 100000, the system will forcibly close the interrupts and output a calltrace error. When the system goes to suspend, the last interrupt is reported to the driver. At this time, the system has set the state to suspend. This causes the last interrupt to not be processed by the system and not clear the interrupt flag. This uncleared interrupt flag constantly triggers new interrupt event. This causing the driver to receive more than 100,000 interrupts, which causes the system to forcibly close the interrupt report and report the calltrace error. so, when the driver goes to sleep and changes the system state to suspend, the interrupt flag needs to be cleared. Signed-off-by: Longfang Liu <liulongfang(a)huawei.com> Acked-by: Alan Stern <stern(a)rowland.harvard.edu> Link: https://lore.kernel.org/r/1610416647-45774-1-git-send-email-liulongfang@hua… Cc: stable <stable(a)vger.kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Longfang Liu <liulongfang(a)huawei.com> Acked-by: Xie XiuQi <xiexiuqi(a)huawei.com> Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/usb/host/ehci-hub.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/usb/host/ehci-hub.c b/drivers/usb/host/ehci-hub.c index ce0eaf7d7c12a..a99c1ac5d8c8b 100644 --- a/drivers/usb/host/ehci-hub.c +++ b/drivers/usb/host/ehci-hub.c @@ -346,8 +346,12 @@ static int ehci_bus_suspend (struct usb_hcd *hcd) unlink_empty_async_suspended(ehci); + /* Some Synopsys controllers mistakenly leave IAA turned on */ + ehci_writel(ehci, STS_IAA, &ehci->regs->status); + /* Any IAA cycle that started before the suspend is now invalid */ end_iaa_cycle(ehci); + ehci_handle_start_intr_unlinks(ehci); ehci_handle_intr_unlinks(ehci); end_free_itds(ehci); -- 2.25.1

1 0

[PATCH kernel-4.19 1/2] sched/topology: Warn when NUMA diameter > 2
by Yang Yingliang 30 Sep '21

30 Sep '21

From: Valentin Schneider <valentin.schneider(a)arm.com> mainline inclusion from mainline-v5.11-rc1 commit b5b217346de85ed1b03fdecd5c5076b34fbb2f0b category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4CAA9 CVE: NA ---------------------------------------------------------- NUMA topologies where the shortest path between some two nodes requires three or more hops (i.e. diameter > 2) end up being misrepresented in the scheduler topology structures. This is currently detected when booting a kernel with CONFIG_SCHED_DEBUG=y + sched_debug on the cmdline, although this will only yield a warning about sched_group spans not matching sched_domain spans: ERROR: groups don't span domain->span Add an explicit warning for that case, triggered regardless of CONFIG_SCHED_DEBUG, and decorate it with an appropriate comment. The topology described in the comment can be booted up on QEMU by appending the following to your usual QEMU incantation: -smp cores=4 \ -numa node,cpus=0,nodeid=0 -numa node,cpus=1,nodeid=1, \ -numa node,cpus=2,nodeid=2, -numa node,cpus=3,nodeid=3, \ -numa dist,src=0,dst=1,val=20, -numa dist,src=0,dst=2,val=30, \ -numa dist,src=0,dst=3,val=40, -numa dist,src=1,dst=2,val=20, \ -numa dist,src=1,dst=3,val=30, -numa dist,src=2,dst=3,val=20 A somewhat more realistic topology (6-node mesh) with the same affliction can be conjured with: -smp cores=6 \ -numa node,cpus=0,nodeid=0 -numa node,cpus=1,nodeid=1, \ -numa node,cpus=2,nodeid=2, -numa node,cpus=3,nodeid=3, \ -numa node,cpus=4,nodeid=4, -numa node,cpus=5,nodeid=5, \ -numa dist,src=0,dst=1,val=20, -numa dist,src=0,dst=2,val=30, \ -numa dist,src=0,dst=3,val=40, -numa dist,src=0,dst=4,val=30, \ -numa dist,src=0,dst=5,val=20, \ -numa dist,src=1,dst=2,val=20, -numa dist,src=1,dst=3,val=30, \ -numa dist,src=1,dst=4,val=20, -numa dist,src=1,dst=5,val=30, \ -numa dist,src=2,dst=3,val=20, -numa dist,src=2,dst=4,val=30, \ -numa dist,src=2,dst=5,val=40, \ -numa dist,src=3,dst=4,val=20, -numa dist,src=3,dst=5,val=30, \ -numa dist,src=4,dst=5,val=20 Signed-off-by: Valentin Schneider <valentin.schneider(a)arm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Acked-by: Mel Gorman <mgorman(a)techsingularity.net> Link: https://lore.kernel.org/lkml/jhjtux5edo2.mognet@arm.com Signed-off-by: Cheng Jian <cj.chengjian(a)huawei.com> Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- kernel/sched/topology.c | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 0002b269ed3da..cd2005832d59c 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -461,6 +461,7 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) { struct rq *rq = cpu_rq(cpu); struct sched_domain *tmp; + int numa_distance = 0; /* Remove the sched domains which do not contribute to scheduling. */ for (tmp = sd; tmp; ) { @@ -492,6 +493,38 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) sd->child = NULL; } + for (tmp = sd; tmp; tmp = tmp->parent) + numa_distance += !!(tmp->flags & SD_NUMA); + + /* + * FIXME: Diameter >=3 is misrepresented. + * + * Smallest diameter=3 topology is: + * + * node 0 1 2 3 + * 0: 10 20 30 40 + * 1: 20 10 20 30 + * 2: 30 20 10 20 + * 3: 40 30 20 10 + * + * 0 --- 1 --- 2 --- 3 + * + * NUMA-3 0-3 N/A N/A 0-3 + * groups: {0-2},{1-3} {1-3},{0-2} + * + * NUMA-2 0-2 0-3 0-3 1-3 + * groups: {0-1},{1-3} {0-2},{2-3} {1-3},{0-1} {2-3},{0-2} + * + * NUMA-1 0-1 0-2 1-3 2-3 + * groups: {0},{1} {1},{2},{0} {2},{3},{1} {3},{2} + * + * NUMA-0 0 1 2 3 + * + * The NUMA-2 groups for nodes 0 and 3 are obviously buggered, as the + * group span isn't a subset of the domain span. + */ + WARN_ONCE(numa_distance > 2, "Shortest NUMA path spans too many nodes\n"); + sched_domain_debug(sd, cpu); rq_attach_root(rq, rd); -- 2.25.1

1 1

[PATCH kernel-4.19] ipc: replace costly bailout check in sysvipc_find_ipc()
by Yang Yingliang 30 Sep '21

30 Sep '21

From: Rafael Aquini <aquini(a)redhat.com> mainline inclusion from mainline-v5.15 commit 20401d1058f3f841f35a594ac2fc1293710e55b9 category: bugfix bugzilla: NA CVE: CVE-2021-3669 -------------------------------- sysvipc_find_ipc() was left with a costly way to check if the offset position fed to it is bigger than the total number of IPC IDs in use. So much so that the time it takes to iterate over /proc/sysvipc/* files grows exponentially for a custom benchmark that creates "N" SYSV shm segments and then times the read of /proc/sysvipc/shm (milliseconds): 12 msecs to read 1024 segs from /proc/sysvipc/shm 18 msecs to read 2048 segs from /proc/sysvipc/shm 65 msecs to read 4096 segs from /proc/sysvipc/shm 325 msecs to read 8192 segs from /proc/sysvipc/shm 1303 msecs to read 16384 segs from /proc/sysvipc/shm 5182 msecs to read 32768 segs from /proc/sysvipc/shm The root problem lies with the loop that computes the total amount of ids in use to check if the "pos" feeded to sysvipc_find_ipc() grew bigger than "ids->in_use". That is a quite inneficient way to get to the maximum index in the id lookup table, specially when that value is already provided by struct ipc_ids.max_idx. This patch follows up on the optimization introduced via commit 15df03c879836 ("sysvipc: make get_maxid O(1) again") and gets rid of the aforementioned costly loop replacing it by a simpler checkpoint based on ipc_get_maxidx() returned value, which allows for a smooth linear increase in time complexity for the same custom benchmark: 2 msecs to read 1024 segs from /proc/sysvipc/shm 2 msecs to read 2048 segs from /proc/sysvipc/shm 4 msecs to read 4096 segs from /proc/sysvipc/shm 9 msecs to read 8192 segs from /proc/sysvipc/shm 19 msecs to read 16384 segs from /proc/sysvipc/shm 39 msecs to read 32768 segs from /proc/sysvipc/shm Link: https://lkml.kernel.org/r/20210809203554.1562989-1-aquini@redhat.com Signed-off-by: Rafael Aquini <aquini(a)redhat.com> Acked-by: Davidlohr Bueso <dbueso(a)suse.de> Acked-by: Manfred Spraul <manfred(a)colorfullife.com> Cc: Waiman Long <llong(a)redhat.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Conflicts: ipc/util.c Signed-off-by: zhiwentao <zhiwentao(a)huawei.com> Reviewed-by: Wang Hui <john.wanghui(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- ipc/util.c | 17 +++++------------ 1 file changed, 5 insertions(+), 12 deletions(-) diff --git a/ipc/util.c b/ipc/util.c index af1b572effb14..53204b1d2e207 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -725,21 +725,14 @@ struct pid_namespace *ipc_seq_pid_ns(struct seq_file *s) static struct kern_ipc_perm *sysvipc_find_ipc(struct ipc_ids *ids, loff_t pos, loff_t *new_pos) { - struct kern_ipc_perm *ipc; - int total, id; - - total = 0; - for (id = 0; id < pos && total < ids->in_use; id++) { - ipc = idr_find(&ids->ipcs_idr, id); - if (ipc != NULL) - total++; - } - ipc = NULL; - if (total >= ids->in_use) + struct kern_ipc_perm *ipc = NULL; + int max_idx = ipc_get_maxidx(ids); + + if (max_idx == -1 || pos > max_idx) goto out; - for (; pos < IPCMNI; pos++) { + for (; pos <= max_idx; pos++) { ipc = idr_find(&ids->ipcs_idr, pos); if (ipc != NULL) { rcu_read_lock(); -- 2.25.1

1 0

[PATCH kernel-4.19 1/4] net: hns3: fix memory override when bd_num is bigger than port info size
by Yang Yingliang 30 Sep '21

30 Sep '21

From: Yonglong Liu <liuyonglong(a)huawei.com> driver inclusion category: bugfix bugzilla: NA CVE: NA ---------------------------- The bd_num is from firmware, it may be bigger than the size of struct hclge_port_info, and may cause memory override problem. Signed-off-by: Yonglong Liu <liuyonglong(a)huawei.com> Reviewed-by: Jian Shen <shenjian15(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- .../net/ethernet/hisilicon/hns3/hns3_cae/hns3_cae_port.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_cae/hns3_cae_port.c b/drivers/net/ethernet/hisilicon/hns3/hns3_cae/hns3_cae_port.c index 5404048ad60d1..ebbc25cc86940 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_cae/hns3_cae_port.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_cae/hns3_cae_port.c @@ -88,9 +88,9 @@ int hns3_get_port_info(const struct hns3_nic_priv *net_priv, desc_data = (__le32 *)(&desc.data[0]); bd_num = le32_to_cpu(*desc_data); - if (bd_num > hdev->hw.cmq.csq.desc_num) { - dev_err(&hdev->pdev->dev, "get invalid BD num %u(max %u)\n", - bd_num, hdev->hw.cmq.csq.desc_num); + if (bd_num * sizeof(struct hclge_desc) > + sizeof(struct hclge_port_info)) { + dev_err(&hdev->pdev->dev, "get invalid BD num %u\n", bd_num); return -EINVAL; } -- 2.25.1

1 3

[PATCH kernel-4.19] scsi: hisi_sas: Optimize the code flow of setting sense data when ssp I/O abnormally completed
by Yang Yingliang 30 Sep '21

30 Sep '21

From: yangxingui <yangxingui(a)huawei.com> driver inclusion category: bugfix bugzilla: NA CVE: NA --------------------------- In the data underflow scenario, if correct sense data and response frame have been written to the host memory and the CQ RSPNS_GOOD bit is 0, then driver sends the sense data to the upper layer. Signed-off-by: yangxingui <yangxingui(a)huawei.com> Reviewed-by: Xiang Chen <chenxiang66(a)hisilicon.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/scsi/hisi_sas/hisi_sas.h | 8 +++++-- drivers/scsi/hisi_sas/hisi_sas_main.c | 17 ------------- drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 33 ++++++++++++++++++++++---- 3 files changed, 34 insertions(+), 24 deletions(-) diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h index 193fc960d87fd..742ffcaeaa95c 100644 --- a/drivers/scsi/hisi_sas/hisi_sas.h +++ b/drivers/scsi/hisi_sas/hisi_sas.h @@ -102,6 +102,12 @@ enum hisi_sas_dev_type { HISI_SAS_DEV_TYPE_SATA, }; +enum datapres_field { + NO_DATA = 0, + RESPONSE_DATA = 1, + SENSE_DATA = 2, +}; + struct hisi_sas_hw_error { u32 irq_msk; u32 msk; @@ -571,8 +577,6 @@ extern void hisi_sas_free(struct hisi_hba *hisi_hba); extern u8 hisi_sas_get_ata_protocol(struct host_to_dev_fis *fis, int direction); extern struct hisi_sas_port *to_hisi_sas_port(struct asd_sas_port *sas_port); -extern void hisi_sas_set_sense_data(struct sas_task *task, - struct hisi_sas_slot *slot); extern void hisi_sas_sata_done(struct sas_task *task, struct hisi_sas_slot *slot); extern int hisi_sas_get_fw_info(struct hisi_hba *hisi_hba); diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index ea08d53c11495..67befcc033126 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -105,23 +105,6 @@ u8 hisi_sas_get_ata_protocol(struct host_to_dev_fis *fis, int direction) } EXPORT_SYMBOL_GPL(hisi_sas_get_ata_protocol); -void hisi_sas_set_sense_data(struct sas_task *task, - struct hisi_sas_slot *slot) -{ - struct ssp_response_iu *iu = - hisi_sas_status_buf_addr_mem(slot) + - sizeof(struct hisi_sas_err_record); - if (iu->datapres == 2) { - struct task_status_struct *ts = &task->task_status; - - ts->buf_valid_size = - min_t(int, SAS_STATUS_BUF_SIZE, - be32_to_cpu(iu->sense_data_len)); - memcpy(ts->buf, iu->sense_data, ts->buf_valid_size); - } -} -EXPORT_SYMBOL_GPL(hisi_sas_set_sense_data); - void hisi_sas_sata_done(struct sas_task *task, struct hisi_sas_slot *slot) { diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index 06b4f2db62f7b..9ce1177a8e455 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -395,6 +395,8 @@ #define CMPLT_HDR_ERROR_PHASE_MSK (0xff << CMPLT_HDR_ERROR_PHASE_OFF) #define CMPLT_HDR_RSPNS_XFRD_OFF 10 #define CMPLT_HDR_RSPNS_XFRD_MSK (0x1 << CMPLT_HDR_RSPNS_XFRD_OFF) +#define CMPLT_HDR_RSPNS_GOOD_OFF 11 +#define CMPLT_HDR_RSPNS_GOOD_MSK (0x1 << CMPLT_HDR_RSPNS_GOOD_OFF) #define CMPLT_HDR_ERX_OFF 12 #define CMPLT_HDR_ERX_MSK (0x1 << CMPLT_HDR_ERX_OFF) #define CMPLT_HDR_ABORT_STAT_OFF 13 @@ -2208,6 +2210,24 @@ static irqreturn_t fatal_axi_int_v3_hw(int irq_no, void *p) return IRQ_HANDLED; } +static void hisi_sas_set_sense_data(struct sas_task *task, + struct hisi_sas_slot *slot) +{ + struct ssp_response_iu *iu = + hisi_sas_status_buf_addr_mem(slot) + + sizeof(struct hisi_sas_err_record); + if ((iu->status == SAM_STAT_CHECK_CONDITION) && + (iu->datapres == SENSE_DATA)) { + struct task_status_struct *ts = &task->task_status; + + ts->buf_valid_size = + min_t(int, SAS_STATUS_BUF_SIZE, + be32_to_cpu(iu->sense_data_len)); + memcpy(ts->buf, iu->sense_data, ts->buf_valid_size); + ts->stat = SAM_STAT_CHECK_CONDITION; + } +} + static void slot_err_v3_hw(struct hisi_hba *hisi_hba, struct sas_task *task, struct hisi_sas_slot *slot) @@ -2224,17 +2244,20 @@ slot_err_v3_hw(struct hisi_hba *hisi_hba, struct sas_task *task, switch (task->task_proto) { case SAS_PROTOCOL_SSP: - if (complete_hdr->dw3 & CMPLT_HDR_IO_IN_TARGET_MSK) { - ts->stat = SAS_QUEUE_FULL; - slot->abort = 1; - } else if (dma_rx_err_type & RX_DATA_LEN_UNDERFLOW_MSK) { + if (dma_rx_err_type & RX_DATA_LEN_UNDERFLOW_MSK) { ts->residual = trans_tx_fail_type; ts->stat = SAS_DATA_UNDERRUN; + if ((!(complete_hdr->dw0 & CMPLT_HDR_RSPNS_GOOD_MSK)) && + (complete_hdr->dw0 & CMPLT_HDR_RSPNS_XFRD_MSK)) { + hisi_sas_set_sense_data(task, slot); + } + } else if (complete_hdr->dw3 & CMPLT_HDR_IO_IN_TARGET_MSK) { + ts->stat = SAS_QUEUE_FULL; + slot->abort = 1; } else { ts->stat = SAS_OPEN_REJECT; ts->open_rej_reason = SAS_OREJ_RSVD_RETRY; } - hisi_sas_set_sense_data(task, slot); break; case SAS_PROTOCOL_SATA: case SAS_PROTOCOL_STP: -- 2.25.1

1 0

How can I get the kernel config values in EulerOS 2.9?
by Wangpeng (Forest, ISCP SRE) 29 Sep '21

29 Sep '21

Hi Community: How can I get the kernel config values in EulerOS? For example, in other release, I can do that by "zcat /proc/config.gz" B.R.

2 1

openEuler Summit 2021 诚挚的邀请您提交演讲议题、成为共建单位、贡献展示方案
by Marketing openEuler 29 Sep '21

29 Sep '21

openEuler Summit 是由欧拉开源社区举办的开发者峰会。全新升级后的首场峰会将于 11 月10日在北京举行。 openEuler 从服务器操作系统，升级为数字基础设施的操作系统，支持 IT、CT、OT 等数字基础设施全场景，覆盖服务器、云、边、嵌入式等各种形态的需求。伴随 openEuler 21.09 的发布，openEuler 已经包含了服务器、云原生、边缘计算和嵌入式的四大应用场景。 openEuler 通过开源开放，不断探索科技创新的边界。开发者、用户、社区贡献者、软件爱好者在 openEuler Summit 汇聚，共同解读 openEuler 的最新版，探讨未来的技术路线，让技术、生态、商业在这里产生奇妙的化学反应。 *本次峰会旨在推动 openEuler 在多样性计算、云计算、边缘计算、嵌入式等技术方向的持续探索和创新。* 开源是一种态度、分享是一种精神。Call for Speaker、Call for Sponsor、Call for Demo 现已全面开放报名。大会报名通道同步开启。 *我们诚挚的邀请您提交演讲议题、发表联合演讲、成为共建单位、贡献展示方案、参与社区建设。* - *大会官网：*https://www.openeuler.org/zh/interaction/summit-list/summit2021/ - *Call for Speaker：*https://shimowendang.com/forms/X6X9jj9KPcdQwVr8/fill - *Call for Sponsor：*https://shimowendang.com/forms/k76zTLKvumYwRdsP/fill - *Call for Demo：*https://shimowendang.com/forms/LjHs8JlsLSsW92kl/fill

1 0

[PATCH] eulerfs: add the /proc/idle file.
by Hongyu Li 29 Sep '21

29 Sep '21

From: Hongyu Li <“543306408(a)qq.xn--com-9o0a> openEuler inclusion category: bugfix bugzilla: https://gitee.com/openeuler-competition/summer-2021/issues/I3EBT6 CVE: NA ---------------------------------------------------------------------- The /proc/idle can give higher precision in accounting the CPU idle time compared with the traditional /proc/stat ways. Signed-off-by: Hongyu Li <“543306408(a)qq.xn--com-9o0a> --- fs/proc/Kconfig | 7 ++++ fs/proc/Makefile | 1 + fs/proc/proc_idle.c | 82 ++++++++++++++++++++++++++++++++++++++++++ kernel/sched/cputime.c | 16 +++++++++ kernel/sched/idle.c | 21 +++++++++++ 5 files changed, 127 insertions(+) create mode 100644 fs/proc/proc_idle.c diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig index c930001056f9..46620afe9cac 100644 --- a/fs/proc/Kconfig +++ b/fs/proc/Kconfig @@ -107,3 +107,10 @@ config PROC_PID_ARCH_STATUS config PROC_CPU_RESCTRL def_bool n depends on PROC_FS + +config PROC_IDLE + bool "include /proc/idle file" + depends on PROC_FS + default y + help + Provide the CPU idle time in the /proc/idle file. diff --git a/fs/proc/Makefile b/fs/proc/Makefile index 8704d41dd67c..69dd2da3a080 100644 --- a/fs/proc/Makefile +++ b/fs/proc/Makefile @@ -34,5 +34,6 @@ proc-$(CONFIG_PROC_VMCORE) += vmcore.o proc-$(CONFIG_PRINTK) += kmsg.o proc-$(CONFIG_PROC_PAGE_MONITOR) += page.o proc-$(CONFIG_BOOT_CONFIG) += bootconfig.o +proc-$(CONFIG_PROC_IDLE) += proc_idle.o obj-$(CONFIG_ETMEM_SCAN) += etmem_scan.o obj-$(CONFIG_ETMEM_SWAP) += etmem_swap.o diff --git a/fs/proc/proc_idle.c b/fs/proc/proc_idle.c new file mode 100644 index 000000000000..bbb52e247448 --- /dev/null +++ b/fs/proc/proc_idle.c @@ -0,0 +1,82 @@ +#include <linux/cpumask.h> +#include <linux/device.h> +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/kernel_stat.h> +#include <linux/module.h> +#include <linux/proc_fs.h> +#include <linux/sched.h> +#include <linux/sched/stat.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/time.h> +#include <linux/irqnr.h> +#include <linux/sched/cputime.h> +#include <linux/tick.h> + +#ifdef CONFIG_PROC_IDLE + +#define PROC_NAME "idle" + +extern u64 cpu_rq_get(int cpu); + +static u64 get_idle_sum_exec_runtime(int cpu) +{ + u64 idle = cpu_rq_get(cpu); + + return idle; +} + +static int show_idle(struct seq_file *p, void *v) +{ + int i; + u64 idle; + + idle = 0; + + for_each_possible_cpu(i) { + + idle += get_idle_sum_exec_runtime(i); + + } + + seq_put_decimal_ull(p, "cpu ", nsec_to_clock_t(idle)); + seq_putc(p, '\n'); + + for_each_online_cpu(i) { + + idle = get_idle_sum_exec_runtime(i); + + seq_printf(p, "cpu%d", i); + seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle)); + seq_putc(p, '\n'); + } + + return 0; +} + +static int idle_open(struct inode *inode, struct file *file) +{ + unsigned int size = 1024 + 128 * num_online_cpus(); + + return single_open_size(file, show_idle, NULL, size); +} + +static struct proc_ops idle_procs_ops = { + .proc_open = idle_open, + .proc_read_iter = seq_read_iter, + .proc_lseek = seq_lseek, + .proc_release = single_release, +}; + +static int __init kernel_module_init(void) +{ + proc_create(PROC_NAME, 0, NULL, &idle_procs_ops); + return 0; +} + +fs_initcall(kernel_module_init); + +#endif /*CONFIG_PROC_IDLE*/ diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 5a55d2300452..bb280852bb06 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -1078,3 +1078,19 @@ void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu) EXPORT_SYMBOL_GPL(kcpustat_cpu_fetch); #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ + + +#ifdef CONFIG_PROC_IDLE + + +u64 cpu_rq_get(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + struct sched_entity *idle_se = &rq->idle->se; + u64 idle = idle_se->sum_exec_runtime; + + return idle; +} +EXPORT_SYMBOL_GPL(cpu_rq_get); + +#endif /* CONFIG_PROC_IDLE */ diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 36b545f17206..e3fb940a61e8 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -424,6 +424,20 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl static void put_prev_task_idle(struct rq *rq, struct task_struct *prev) { +#ifdef CONFIG_PROC_IDLE + struct sched_entity *idle_se = &rq->idle->se; + u64 now = sched_clock(); + u64 delta_exec; + + delta_exec = now - idle_se->exec_start; + if (unlikely((s64)delta_exec <= 0)) + return; + + schedstat_set(idle_se->statistics.exec_max, + max(delta_exec, idle_se->statistics.exec_max)); + + idle_se->sum_exec_runtime += delta_exec; +#endif } static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first) @@ -436,6 +450,13 @@ struct task_struct *pick_next_task_idle(struct rq *rq) { struct task_struct *next = rq->idle; +#ifdef CONFIG_PROC_IDLE + struct sched_entity *idle_se = &rq->idle->se; + u64 now = sched_clock(); + + idle_se->exec_start = now; +#endif + set_next_task_idle(rq, next, true); return next; -- 2.17.1

2 1

[PATCH kernel-4.19] Bluetooth: fix use-after-free error in lock_sock_nested()
by Yang Yingliang 29 Sep '21

29 Sep '21

From: Wang ShaoBo <bobo.shaobowang(a)huawei.com> mainline inclusion from mainline-v5.16 commit 1bff51ea59a9afb67d2dd78518ab0582a54a472c category: bugfix bugzilla: NA CVE: CVE-2021-3752 --------------------------- use-after-free error in lock_sock_nested is reported: [ 179.140137][ T3731] ===================================================== [ 179.142675][ T3731] BUG: KMSAN: use-after-free in lock_sock_nested+0x280/0x2c0 [ 179.145494][ T3731] CPU: 4 PID: 3731 Comm: kworker/4:2 Not tainted 5.12.0-rc6+ #54 [ 179.148432][ T3731] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 [ 179.151806][ T3731] Workqueue: events l2cap_chan_timeout [ 179.152730][ T3731] Call Trace: [ 179.153301][ T3731] dump_stack+0x24c/0x2e0 [ 179.154063][ T3731] kmsan_report+0xfb/0x1e0 [ 179.154855][ T3731] __msan_warning+0x5c/0xa0 [ 179.155579][ T3731] lock_sock_nested+0x280/0x2c0 [ 179.156436][ T3731] ? kmsan_get_metadata+0x116/0x180 [ 179.157257][ T3731] l2cap_sock_teardown_cb+0xb8/0x890 [ 179.158154][ T3731] ? __msan_metadata_ptr_for_load_8+0x10/0x20 [ 179.159141][ T3731] ? kmsan_get_metadata+0x116/0x180 [ 179.159994][ T3731] ? kmsan_get_shadow_origin_ptr+0x84/0xb0 [ 179.160959][ T3731] ? l2cap_sock_recv_cb+0x420/0x420 [ 179.161834][ T3731] l2cap_chan_del+0x3e1/0x1d50 [ 179.162608][ T3731] ? kmsan_get_metadata+0x116/0x180 [ 179.163435][ T3731] ? kmsan_get_shadow_origin_ptr+0x84/0xb0 [ 179.164406][ T3731] l2cap_chan_close+0xeea/0x1050 [ 179.165189][ T3731] ? kmsan_internal_unpoison_shadow+0x42/0x70 [ 179.166180][ T3731] l2cap_chan_timeout+0x1da/0x590 [ 179.167066][ T3731] ? __msan_metadata_ptr_for_load_8+0x10/0x20 [ 179.168023][ T3731] ? l2cap_chan_create+0x560/0x560 [ 179.168818][ T3731] process_one_work+0x121d/0x1ff0 [ 179.169598][ T3731] worker_thread+0x121b/0x2370 [ 179.170346][ T3731] kthread+0x4ef/0x610 [ 179.171010][ T3731] ? process_one_work+0x1ff0/0x1ff0 [ 179.171828][ T3731] ? kthread_blkcg+0x110/0x110 [ 179.172587][ T3731] ret_from_fork+0x1f/0x30 [ 179.173348][ T3731] [ 179.173752][ T3731] Uninit was created at: [ 179.174409][ T3731] kmsan_internal_poison_shadow+0x5c/0xf0 [ 179.175373][ T3731] kmsan_slab_free+0x76/0xc0 [ 179.176060][ T3731] kfree+0x3a5/0x1180 [ 179.176664][ T3731] __sk_destruct+0x8af/0xb80 [ 179.177375][ T3731] __sk_free+0x812/0x8c0 [ 179.178032][ T3731] sk_free+0x97/0x130 [ 179.178686][ T3731] l2cap_sock_release+0x3d5/0x4d0 [ 179.179457][ T3731] sock_close+0x150/0x450 [ 179.180117][ T3731] __fput+0x6bd/0xf00 [ 179.180787][ T3731] ____fput+0x37/0x40 [ 179.181481][ T3731] task_work_run+0x140/0x280 [ 179.182219][ T3731] do_exit+0xe51/0x3e60 [ 179.182930][ T3731] do_group_exit+0x20e/0x450 [ 179.183656][ T3731] get_signal+0x2dfb/0x38f0 [ 179.184344][ T3731] arch_do_signal_or_restart+0xaa/0xe10 [ 179.185266][ T3731] exit_to_user_mode_prepare+0x2d2/0x560 [ 179.186136][ T3731] syscall_exit_to_user_mode+0x35/0x60 [ 179.186984][ T3731] do_syscall_64+0xc5/0x140 [ 179.187681][ T3731] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 179.188604][ T3731] ===================================================== In our case, there are two Thread A and B: Context: Thread A: Context: Thread B: l2cap_chan_timeout() __se_sys_shutdown() l2cap_chan_close() l2cap_sock_shutdown() l2cap_chan_del() l2cap_chan_close() l2cap_sock_teardown_cb() l2cap_sock_teardown_cb() Once l2cap_sock_teardown_cb() excuted, this sock will be marked as SOCK_ZAPPED, and can be treated as killable in l2cap_sock_kill() if sock_orphan() has excuted, at this time we close sock through sock_close() which end to call l2cap_sock_kill() like Thread C: Context: Thread C: sock_close() l2cap_sock_release() sock_orphan() l2cap_sock_kill() #free sock if refcnt is 1 If C completed, Once A or B reaches l2cap_sock_teardown_cb() again, use-after-free happened. We should set chan->data to NULL if sock is destructed, for telling teardown operation is not allowed in l2cap_sock_teardown_cb(), and also we should avoid killing an already killed socket in l2cap_sock_close_cb(). Signed-off-by: Wang ShaoBo <bobo.shaobowang(a)huawei.com> Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz(a)intel.com> Signed-off-by: Marcel Holtmann <marcel(a)holtmann.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- net/bluetooth/l2cap_sock.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index d1d5fa35dcc9a..b4f6b74c40038 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1308,6 +1308,9 @@ static void l2cap_sock_close_cb(struct l2cap_chan *chan) { struct sock *sk = chan->data; + if (!sk) + return; + l2cap_sock_kill(sk); } @@ -1316,6 +1319,9 @@ static void l2cap_sock_teardown_cb(struct l2cap_chan *chan, int err) struct sock *sk = chan->data; struct sock *parent; + if (!sk) + return; + BT_DBG("chan %p state %s", chan, state_to_string(chan->state)); /* This callback can be called both for server (BT_LISTEN) @@ -1498,8 +1504,10 @@ static void l2cap_sock_destruct(struct sock *sk) { BT_DBG("sk %p", sk); - if (l2cap_pi(sk)->chan) + if (l2cap_pi(sk)->chan) { + l2cap_pi(sk)->chan->data = NULL; l2cap_chan_put(l2cap_pi(sk)->chan); + } if (l2cap_pi(sk)->rx_busy_skb) { kfree_skb(l2cap_pi(sk)->rx_busy_skb); -- 2.25.1

1 0

[PATCH openEuler-5.10 01/17] slub: fix unreclaimable slab stat for bulk free
by Zheng Zengkai 29 Sep '21

29 Sep '21

From: Shakeel Butt <shakeelb(a)google.com> mainline inclusion from mainline-v5.14-rc4 commit f227f0faf63b46a113c4d1aca633c80195622dd2 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4C12I CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ---------------------------------------------------------------------- SLUB uses page allocator for higher order allocations and update unreclaimable slab stat for such allocations. At the moment, the bulk free for SLUB does not share code with normal free code path for these type of allocations and have missed the stat update. So, fix the stat update by common code. The user visible impact of the bug is the potential of inconsistent unreclaimable slab stat visible through meminfo and vmstat. Link: https://lkml.kernel.org/r/20210728155354.3440560-1-shakeelb@google.com Fixes: 6a486c0ad4dc ("mm, sl[ou]b: improve memory accounting") Signed-off-by: Shakeel Butt <shakeelb(a)google.com> Acked-by: Michal Hocko <mhocko(a)suse.com> Acked-by: Roman Gushchin <guro(a)fb.com> Reviewed-by: Muchun Song <songmuchun(a)bytedance.com> Cc: Christoph Lameter <cl(a)linux.com> Cc: Pekka Enberg <penberg(a)kernel.org> Cc: David Rientjes <rientjes(a)google.com> Cc: Joonsoo Kim <iamjoonsoo.kim(a)lge.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Chen Huang <chenhuang5(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- mm/slub.c | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) diff --git a/mm/slub.c b/mm/slub.c index f06f002bb098..4a83fa347672 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3164,6 +3164,16 @@ struct detached_freelist { struct kmem_cache *s; }; +static inline void free_nonslab_page(struct page *page) +{ + unsigned int order = compound_order(page); + + VM_BUG_ON_PAGE(!PageCompound(page), page); + kfree_hook(page_address(page)); + mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B, -(PAGE_SIZE << order)); + __free_pages(page, order); +} + /* * This function progressively scans the array with free objects (with * a limited look ahead) and extract objects belonging to the same @@ -3200,9 +3210,7 @@ int build_detached_freelist(struct kmem_cache *s, size_t size, if (!s) { /* Handle kalloc'ed objects */ if (unlikely(!PageSlab(page))) { - BUG_ON(!PageCompound(page)); - kfree_hook(object); - __free_pages(page, compound_order(page)); + free_nonslab_page(page); p[size] = NULL; /* mark object processed */ return size; } @@ -4102,13 +4110,7 @@ void kfree(const void *x) page = virt_to_head_page(x); if (unlikely(!PageSlab(page))) { - unsigned int order = compound_order(page); - - BUG_ON(!PageCompound(page)); - kfree_hook(object); - mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B, - -(PAGE_SIZE << order)); - __free_pages(page, order); + free_nonslab_page(page); return; } slab_free(page->slab_cache, page, object, NULL, 1, _RET_IP_); -- 2.20.1

1 16

[PATCH openEuler-21.09] eulerfs: add the /proc/idle file.
by Hongyu Li 29 Sep '21

29 Sep '21

From: Hongyu Li <“543306408(a)qq.xn--com-9o0a> openEuler inclusion category: bugfix bugzilla: https://gitee.com/openeuler-competition/summer-2021/issues/I3EBT6 CVE: NA ---------------------------------------------------------------------- The /proc/idle can give higher precision in accounting the CPU idle time compared with the traditional /proc/stat ways. Signed-off-by: Hongyu Li <“543306408(a)qq.xn--com-9o0a> --- fs/proc/Kconfig | 7 ++++ fs/proc/Makefile | 1 + fs/proc/proc_idle.c | 82 ++++++++++++++++++++++++++++++++++++++++++ kernel/sched/cputime.c | 16 +++++++++ kernel/sched/idle.c | 21 +++++++++++ 5 files changed, 127 insertions(+) create mode 100644 fs/proc/proc_idle.c diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig index c930001056f9..46620afe9cac 100644 --- a/fs/proc/Kconfig +++ b/fs/proc/Kconfig @@ -107,3 +107,10 @@ config PROC_PID_ARCH_STATUS config PROC_CPU_RESCTRL def_bool n depends on PROC_FS + +config PROC_IDLE + bool "include /proc/idle file" + depends on PROC_FS + default y + help + Provide the CPU idle time in the /proc/idle file. diff --git a/fs/proc/Makefile b/fs/proc/Makefile index 8704d41dd67c..69dd2da3a080 100644 --- a/fs/proc/Makefile +++ b/fs/proc/Makefile @@ -34,5 +34,6 @@ proc-$(CONFIG_PROC_VMCORE) += vmcore.o proc-$(CONFIG_PRINTK) += kmsg.o proc-$(CONFIG_PROC_PAGE_MONITOR) += page.o proc-$(CONFIG_BOOT_CONFIG) += bootconfig.o +proc-$(CONFIG_PROC_IDLE) += proc_idle.o obj-$(CONFIG_ETMEM_SCAN) += etmem_scan.o obj-$(CONFIG_ETMEM_SWAP) += etmem_swap.o diff --git a/fs/proc/proc_idle.c b/fs/proc/proc_idle.c new file mode 100644 index 000000000000..bbb52e247448 --- /dev/null +++ b/fs/proc/proc_idle.c @@ -0,0 +1,82 @@ +#include <linux/cpumask.h> +#include <linux/device.h> +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/kernel_stat.h> +#include <linux/module.h> +#include <linux/proc_fs.h> +#include <linux/sched.h> +#include <linux/sched/stat.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/time.h> +#include <linux/irqnr.h> +#include <linux/sched/cputime.h> +#include <linux/tick.h> + +#ifdef CONFIG_PROC_IDLE + +#define PROC_NAME "idle" + +extern u64 cpu_rq_get(int cpu); + +static u64 get_idle_sum_exec_runtime(int cpu) +{ + u64 idle = cpu_rq_get(cpu); + + return idle; +} + +static int show_idle(struct seq_file *p, void *v) +{ + int i; + u64 idle; + + idle = 0; + + for_each_possible_cpu(i) { + + idle += get_idle_sum_exec_runtime(i); + + } + + seq_put_decimal_ull(p, "cpu ", nsec_to_clock_t(idle)); + seq_putc(p, '\n'); + + for_each_online_cpu(i) { + + idle = get_idle_sum_exec_runtime(i); + + seq_printf(p, "cpu%d", i); + seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle)); + seq_putc(p, '\n'); + } + + return 0; +} + +static int idle_open(struct inode *inode, struct file *file) +{ + unsigned int size = 1024 + 128 * num_online_cpus(); + + return single_open_size(file, show_idle, NULL, size); +} + +static struct proc_ops idle_procs_ops = { + .proc_open = idle_open, + .proc_read_iter = seq_read_iter, + .proc_lseek = seq_lseek, + .proc_release = single_release, +}; + +static int __init kernel_module_init(void) +{ + proc_create(PROC_NAME, 0, NULL, &idle_procs_ops); + return 0; +} + +fs_initcall(kernel_module_init); + +#endif /*CONFIG_PROC_IDLE*/ diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 5a55d2300452..bb280852bb06 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -1078,3 +1078,19 @@ void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu) EXPORT_SYMBOL_GPL(kcpustat_cpu_fetch); #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ + + +#ifdef CONFIG_PROC_IDLE + + +u64 cpu_rq_get(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + struct sched_entity *idle_se = &rq->idle->se; + u64 idle = idle_se->sum_exec_runtime; + + return idle; +} +EXPORT_SYMBOL_GPL(cpu_rq_get); + +#endif /* CONFIG_PROC_IDLE */ diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 36b545f17206..e3fb940a61e8 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -424,6 +424,20 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl static void put_prev_task_idle(struct rq *rq, struct task_struct *prev) { +#ifdef CONFIG_PROC_IDLE + struct sched_entity *idle_se = &rq->idle->se; + u64 now = sched_clock(); + u64 delta_exec; + + delta_exec = now - idle_se->exec_start; + if (unlikely((s64)delta_exec <= 0)) + return; + + schedstat_set(idle_se->statistics.exec_max, + max(delta_exec, idle_se->statistics.exec_max)); + + idle_se->sum_exec_runtime += delta_exec; +#endif } static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first) @@ -436,6 +450,13 @@ struct task_struct *pick_next_task_idle(struct rq *rq) { struct task_struct *next = rq->idle; +#ifdef CONFIG_PROC_IDLE + struct sched_entity *idle_se = &rq->idle->se; + u64 now = sched_clock(); + + idle_se->exec_start = now; +#endif + set_next_task_idle(rq, next, true); return next; -- 2.17.1

1 0

[PATCH kernel-4.19] bpf, mips: Validate conditional branch offsets
by Yang Yingliang 29 Sep '21

29 Sep '21

From: Piotr Krysiuk <piotras(a)gmail.com> mainline inclusion from mainline-v5.16 commit 37cb28ec7d3a36a5bace7063a3dba633ab110f8b category: bugfix bugzilla: NA CVE: CVE-2021-38300 ------------------------------------------------- The conditional branch instructions on MIPS use 18-bit signed offsets allowing for a branch range of 128 KBytes (backward and forward). However, this limit is not observed by the cBPF JIT compiler, and so the JIT compiler emits out-of-range branches when translating certain cBPF programs. A specific example of such a cBPF program is included in the "BPF_MAXINSNS: exec all MSH" test from lib/test_bpf.c that executes anomalous machine code containing incorrect branch offsets under JIT. Furthermore, this issue can be abused to craft undesirable machine code, where the control flow is hijacked to execute arbitrary Kernel code. The following steps can be used to reproduce the issue: # echo 1 > /proc/sys/net/core/bpf_jit_enable # modprobe test_bpf test_name="BPF_MAXINSNS: exec all MSH" This should produce multiple warnings from build_bimm() similar to: ------------[ cut here ]------------ WARNING: CPU: 0 PID: 209 at arch/mips/mm/uasm-mips.c:210 build_insn+0x558/0x590 Micro-assembler field overflow Modules linked in: test_bpf(+) CPU: 0 PID: 209 Comm: modprobe Not tainted 5.14.3 #1 Stack : 00000000 807bb824 82b33c9c 801843c0 00000000 00000004 00000000 63c9b5ee 82b33af4 80999898 80910000 80900000 82fd6030 00000001 82b33a98 82087180 00000000 00000000 80873b28 00000000 000000fc 82b3394c 00000000 2e34312e 6d6d6f43 809a180f 809a1836 6f6d203a 80900000 00000001 82b33bac 80900000 00027f80 00000000 00000000 807bb824 00000000 804ed790 001cc317 00000001 [...] Call Trace: [<80108f44>] show_stack+0x38/0x118 [<807a7aac>] dump_stack_lvl+0x5c/0x7c [<807a4b3c>] __warn+0xcc/0x140 [<807a4c3c>] warn_slowpath_fmt+0x8c/0xb8 [<8011e198>] build_insn+0x558/0x590 [<8011e358>] uasm_i_bne+0x20/0x2c [<80127b48>] build_body+0xa58/0x2a94 [<80129c98>] bpf_jit_compile+0x114/0x1e4 [<80613fc4>] bpf_prepare_filter+0x2ec/0x4e4 [<8061423c>] bpf_prog_create+0x80/0xc4 [<c0a006e4>] test_bpf_init+0x300/0xba8 [test_bpf] [<8010051c>] do_one_initcall+0x50/0x1d4 [<801c5e54>] do_init_module+0x60/0x220 [<801c8b20>] sys_finit_module+0xc4/0xfc [<801144d0>] syscall_common+0x34/0x58 [...] ---[ end trace a287d9742503c645 ]--- Then the anomalous machine code executes: => 0xc0a18000: addiu sp,sp,-16 0xc0a18004: sw s3,0(sp) 0xc0a18008: sw s4,4(sp) 0xc0a1800c: sw s5,8(sp) 0xc0a18010: sw ra,12(sp) 0xc0a18014: move s5,a0 0xc0a18018: move s4,zero 0xc0a1801c: move s3,zero # __BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0) 0xc0a18020: lui t6,0x8012 0xc0a18024: ori t4,t6,0x9e14 0xc0a18028: li a1,0 0xc0a1802c: jalr t4 0xc0a18030: move a0,s5 0xc0a18034: bnez v0,0xc0a1ffb8 # incorrect branch offset 0xc0a18038: move v0,zero 0xc0a1803c: andi s4,s3,0xf 0xc0a18040: b 0xc0a18048 0xc0a18044: sll s4,s4,0x2 [...] # __BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0) 0xc0a1ffa0: lui t6,0x8012 0xc0a1ffa4: ori t4,t6,0x9e14 0xc0a1ffa8: li a1,0 0xc0a1ffac: jalr t4 0xc0a1ffb0: move a0,s5 0xc0a1ffb4: bnez v0,0xc0a1ffb8 # incorrect branch offset 0xc0a1ffb8: move v0,zero 0xc0a1ffbc: andi s4,s3,0xf 0xc0a1ffc0: b 0xc0a1ffc8 0xc0a1ffc4: sll s4,s4,0x2 # __BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0) 0xc0a1ffc8: lui t6,0x8012 0xc0a1ffcc: ori t4,t6,0x9e14 0xc0a1ffd0: li a1,0 0xc0a1ffd4: jalr t4 0xc0a1ffd8: move a0,s5 0xc0a1ffdc: bnez v0,0xc0a3ffb8 # correct branch offset 0xc0a1ffe0: move v0,zero 0xc0a1ffe4: andi s4,s3,0xf 0xc0a1ffe8: b 0xc0a1fff0 0xc0a1ffec: sll s4,s4,0x2 [...] # epilogue 0xc0a3ffb8: lw s3,0(sp) 0xc0a3ffbc: lw s4,4(sp) 0xc0a3ffc0: lw s5,8(sp) 0xc0a3ffc4: lw ra,12(sp) 0xc0a3ffc8: addiu sp,sp,16 0xc0a3ffcc: jr ra 0xc0a3ffd0: nop To mitigate this issue, we assert the branch ranges for each emit call that could generate an out-of-range branch. Fixes: 36366e367ee9 ("MIPS: BPF: Restore MIPS32 cBPF JIT") Fixes: c6610de353da ("MIPS: net: Add BPF JIT") Signed-off-by: Piotr Krysiuk <piotras(a)gmail.com> Signed-off-by: Daniel Borkmann <daniel(a)iogearbox.net> Tested-by: Johan Almbladh <johan.almbladh(a)anyfinetworks.com> Acked-by: Johan Almbladh <johan.almbladh(a)anyfinetworks.com> Cc: Paul Burton <paulburton(a)kernel.org> Cc: Thomas Bogendoerfer <tsbogend(a)alpha.franken.de> Link: https://lore.kernel.org/bpf/20210915160437.4080-1-piotras@gmail.com Signed-off-by: Pu Lehui <pulehui(a)huawei.com> Reviewed-by: Kuohai Xu <xukuohai(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/mips/net/bpf_jit.c | 57 +++++++++++++++++++++++++++++++---------- 1 file changed, 43 insertions(+), 14 deletions(-) diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c index 4d8cb9bb8365d..43e6597c720c2 100644 --- a/arch/mips/net/bpf_jit.c +++ b/arch/mips/net/bpf_jit.c @@ -662,6 +662,11 @@ static void build_epilogue(struct jit_ctx *ctx) ((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative : func) : \ func##_positive) +static bool is_bad_offset(int b_off) +{ + return b_off > 0x1ffff || b_off < -0x20000; +} + static int build_body(struct jit_ctx *ctx) { const struct bpf_prog *prog = ctx->skf; @@ -728,7 +733,10 @@ static int build_body(struct jit_ctx *ctx) /* Load return register on DS for failures */ emit_reg_move(r_ret, r_zero, ctx); /* Return with error */ - emit_b(b_imm(prog->len, ctx), ctx); + b_off = b_imm(prog->len, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_b(b_off, ctx); emit_nop(ctx); break; case BPF_LD | BPF_W | BPF_IND: @@ -775,8 +783,10 @@ static int build_body(struct jit_ctx *ctx) emit_jalr(MIPS_R_RA, r_s0, ctx); emit_reg_move(MIPS_R_A0, r_skb, ctx); /* delay slot */ /* Check the error value */ - emit_bcond(MIPS_COND_NE, r_ret, 0, - b_imm(prog->len, ctx), ctx); + b_off = b_imm(prog->len, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_bcond(MIPS_COND_NE, r_ret, 0, b_off, ctx); emit_reg_move(r_ret, r_zero, ctx); /* We are good */ /* X <- P[1:K] & 0xf */ @@ -855,8 +865,10 @@ static int build_body(struct jit_ctx *ctx) /* A /= X */ ctx->flags |= SEEN_X | SEEN_A; /* Check if r_X is zero */ - emit_bcond(MIPS_COND_EQ, r_X, r_zero, - b_imm(prog->len, ctx), ctx); + b_off = b_imm(prog->len, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_bcond(MIPS_COND_EQ, r_X, r_zero, b_off, ctx); emit_load_imm(r_ret, 0, ctx); /* delay slot */ emit_div(r_A, r_X, ctx); break; @@ -864,8 +876,10 @@ static int build_body(struct jit_ctx *ctx) /* A %= X */ ctx->flags |= SEEN_X | SEEN_A; /* Check if r_X is zero */ - emit_bcond(MIPS_COND_EQ, r_X, r_zero, - b_imm(prog->len, ctx), ctx); + b_off = b_imm(prog->len, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_bcond(MIPS_COND_EQ, r_X, r_zero, b_off, ctx); emit_load_imm(r_ret, 0, ctx); /* delay slot */ emit_mod(r_A, r_X, ctx); break; @@ -926,7 +940,10 @@ static int build_body(struct jit_ctx *ctx) break; case BPF_JMP | BPF_JA: /* pc += K */ - emit_b(b_imm(i + k + 1, ctx), ctx); + b_off = b_imm(i + k + 1, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_b(b_off, ctx); emit_nop(ctx); break; case BPF_JMP | BPF_JEQ | BPF_K: @@ -1056,12 +1073,16 @@ static int build_body(struct jit_ctx *ctx) break; case BPF_RET | BPF_A: ctx->flags |= SEEN_A; - if (i != prog->len - 1) + if (i != prog->len - 1) { /* * If this is not the last instruction * then jump to the epilogue */ - emit_b(b_imm(prog->len, ctx), ctx); + b_off = b_imm(prog->len, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_b(b_off, ctx); + } emit_reg_move(r_ret, r_A, ctx); /* delay slot */ break; case BPF_RET | BPF_K: @@ -1075,7 +1096,10 @@ static int build_body(struct jit_ctx *ctx) * If this is not the last instruction * then jump to the epilogue */ - emit_b(b_imm(prog->len, ctx), ctx); + b_off = b_imm(prog->len, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_b(b_off, ctx); emit_nop(ctx); } break; @@ -1133,8 +1157,10 @@ static int build_body(struct jit_ctx *ctx) /* Load *dev pointer */ emit_load_ptr(r_s0, r_skb, off, ctx); /* error (0) in the delay slot */ - emit_bcond(MIPS_COND_EQ, r_s0, r_zero, - b_imm(prog->len, ctx), ctx); + b_off = b_imm(prog->len, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_bcond(MIPS_COND_EQ, r_s0, r_zero, b_off, ctx); emit_reg_move(r_ret, r_zero, ctx); if (code == (BPF_ANC | SKF_AD_IFINDEX)) { BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); @@ -1244,7 +1270,10 @@ void bpf_jit_compile(struct bpf_prog *fp) /* Generate the actual JIT code */ build_prologue(&ctx); - build_body(&ctx); + if (build_body(&ctx)) { + module_memfree(ctx.target); + goto out; + } build_epilogue(&ctx); /* Update the icache */ -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] scsi: qla2xxx: Fix crash in qla2xxx_mqueuecommand()
by Yang Yingliang 29 Sep '21

29 Sep '21

From: Arun Easi <aeasi(a)marvell.com> stable inclusion from linux-4.19.191 commit c5ab9b67d8b061de74e2ca51bf787ee599bd7f89 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4AFG0?from=project-issue CVE: NA -------------------------------- commit 6641df81ab799f28a5d564f860233dd26cca0d93 upstream. RIP: 0010:kmem_cache_free+0xfa/0x1b0 Call Trace: qla2xxx_mqueuecommand+0x2b5/0x2c0 [qla2xxx] scsi_queue_rq+0x5e2/0xa40 __blk_mq_try_issue_directly+0x128/0x1d0 blk_mq_request_issue_directly+0x4e/0xb0 Fix incorrect call to free srb in qla2xxx_mqueuecommand(), as srb is now allocated by upper layers. This fixes smatch warning of srb unintended free. Link: https://lore.kernel.org/r/20210329085229.4367-7-njavali@marvell.com Fixes: af2a0c51b120 ("scsi: qla2xxx: Fix SRB leak on switch command timeout") Cc: stable(a)vger.kernel.org # 5.5 Reported-by: Laurence Oberman <loberman(a)redhat.com> Reported-by: Dan Carpenter <dan.carpenter(a)oracle.com> Reviewed-by: Himanshu Madhani <himanshu.madhani(a)oracle.com> Signed-off-by: Arun Easi <aeasi(a)marvell.com> Signed-off-by: Nilesh Javali <njavali(a)marvell.com> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: yin-xiujiang <yinxiujiang(a)kylinos.cn> # openEuler_contributor Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/scsi/qla2xxx/qla_os.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index bfbf213b15c0b..8e9d386146ac6 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -1028,8 +1028,6 @@ qla2xxx_mqueuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd, if (rval != QLA_SUCCESS) { ql_dbg(ql_dbg_io + ql_dbg_verbose, vha, 0x3078, "Start scsi failed rval=%d for cmd=%p.\n", rval, cmd); - if (rval == QLA_INTERFACE_ERROR) - goto qc24_free_sp_fail_command; goto qc24_host_busy_free_sp; } @@ -1044,11 +1042,6 @@ qla2xxx_mqueuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd, qc24_target_busy: return SCSI_MLQUEUE_TARGET_BUSY; -qc24_free_sp_fail_command: - sp->free(sp); - CMD_SP(cmd) = NULL; - qla2xxx_rel_qpair_sp(sp->qpair, sp); - qc24_fail_command: cmd->scsi_done(cmd); -- 2.25.1

1 0

[PATCH kernel-4.19] crypto: ccp - fix resource leaks in ccp_run_aes_gcm_cmd()
by Yang Yingliang 28 Sep '21

28 Sep '21

From: Dan Carpenter <dan.carpenter(a)oracle.com> mainline inclusion from mainline-v5.16 commit 505d9dcb0f7ddf9d075e729523a33d38642ae680 category: bugfix bugzilla: NA CVE: CVE-2021-3764, CVE-2021-3744 --------------------------- There are three bugs in this code: 1) If we ccp_init_data() fails for &src then we need to free aad. Use goto e_aad instead of goto e_ctx. 2) The label to free the &final_wa was named incorrectly as "e_tag" but it should have been "e_final_wa". One error path leaked &final_wa. 3) The &tag was leaked on one error path. In that case, I added a free before the goto because the resource was local to that block. Fixes: 36cf515b9bbe ("crypto: ccp - Enable support for AES GCM on v5 CCPs") Reported-by: "minihanshen(沈明航)" <minihanshen(a)tencent.com> Signed-off-by: Dan Carpenter <dan.carpenter(a)oracle.com> Reviewed-by: John Allen <john.allen(a)amd.com> Tested-by: John Allen <john.allen(a)amd.com> Signed-off-by: Herbert Xu <herbert(a)gondor.apana.org.au> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: weiyang wang <wangweiyang2(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/crypto/ccp/ccp-ops.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/crypto/ccp/ccp-ops.c b/drivers/crypto/ccp/ccp-ops.c index 4dca1c7b9d47b..cdffff7c8abb9 100644 --- a/drivers/crypto/ccp/ccp-ops.c +++ b/drivers/crypto/ccp/ccp-ops.c @@ -768,7 +768,7 @@ static int ccp_run_aes_gcm_cmd(struct ccp_cmd_queue *cmd_q, in_place ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE); if (ret) - goto e_ctx; + goto e_aad; if (in_place) { dst = src; @@ -853,7 +853,7 @@ static int ccp_run_aes_gcm_cmd(struct ccp_cmd_queue *cmd_q, op.u.aes.size = 0; ret = cmd_q->ccp->vdata->perform->aes(&op); if (ret) - goto e_dst; + goto e_final_wa; if (aes->action == CCP_AES_ACTION_ENCRYPT) { /* Put the ciphered tag after the ciphertext. */ @@ -863,17 +863,19 @@ static int ccp_run_aes_gcm_cmd(struct ccp_cmd_queue *cmd_q, ret = ccp_init_dm_workarea(&tag, cmd_q, authsize, DMA_BIDIRECTIONAL); if (ret) - goto e_tag; + goto e_final_wa; ret = ccp_set_dm_area(&tag, 0, p_tag, 0, authsize); - if (ret) - goto e_tag; + if (ret) { + ccp_dm_free(&tag); + goto e_final_wa; + } ret = crypto_memneq(tag.address, final_wa.address, authsize) ? -EBADMSG : 0; ccp_dm_free(&tag); } -e_tag: +e_final_wa: ccp_dm_free(&final_wa); e_dst: -- 2.25.1

1 0

[PATCH OLK-5.10 0/2] net: spnic: initial commit Ramaxel NIC driver
by Yanling Song 28 Sep '21

28 Sep '21

This initial commit contains Ramaxel's spnic module Yanling Song (2): spnic: initial commit the common module of Ramaxel NIC driver spnic: add NIC layer arch/arm64/configs/openeuler_defconfig | 2 + arch/x86/configs/openeuler_defconfig | 2 + drivers/net/ethernet/Kconfig | 1 + drivers/net/ethernet/Makefile | 1 + drivers/net/ethernet/ramaxel/Kconfig | 20 + drivers/net/ethernet/ramaxel/Makefile | 6 + drivers/net/ethernet/ramaxel/spnic/Kconfig | 15 + drivers/net/ethernet/ramaxel/spnic/Makefile | 40 + .../ethernet/ramaxel/spnic/hw/sphw_api_cmd.c | 1165 +++++++++++ .../ethernet/ramaxel/spnic/hw/sphw_api_cmd.h | 277 +++ .../ethernet/ramaxel/spnic/hw/sphw_cfg_cmd.h | 126 ++ .../net/ethernet/ramaxel/spnic/hw/sphw_cmdq.c | 1606 +++++++++++++++ .../net/ethernet/ramaxel/spnic/hw/sphw_cmdq.h | 196 ++ .../ethernet/ramaxel/spnic/hw/sphw_comm_cmd.h | 60 + .../ramaxel/spnic/hw/sphw_comm_msg_intf.h | 273 +++ .../ethernet/ramaxel/spnic/hw/sphw_common.c | 88 + .../ethernet/ramaxel/spnic/hw/sphw_common.h | 118 ++ .../net/ethernet/ramaxel/spnic/hw/sphw_crm.h | 984 +++++++++ .../net/ethernet/ramaxel/spnic/hw/sphw_csr.h | 171 ++ .../net/ethernet/ramaxel/spnic/hw/sphw_eqs.c | 1374 +++++++++++++ .../net/ethernet/ramaxel/spnic/hw/sphw_eqs.h | 157 ++ .../net/ethernet/ramaxel/spnic/hw/sphw_hw.h | 649 ++++++ .../ethernet/ramaxel/spnic/hw/sphw_hw_cfg.c | 1339 ++++++++++++ .../ethernet/ramaxel/spnic/hw/sphw_hw_cfg.h | 327 +++ .../ethernet/ramaxel/spnic/hw/sphw_hw_comm.c | 1253 ++++++++++++ .../ethernet/ramaxel/spnic/hw/sphw_hw_comm.h | 42 + .../ethernet/ramaxel/spnic/hw/sphw_hwdev.c | 1402 +++++++++++++ .../ethernet/ramaxel/spnic/hw/sphw_hwdev.h | 93 + .../net/ethernet/ramaxel/spnic/hw/sphw_hwif.c | 911 +++++++++ .../net/ethernet/ramaxel/spnic/hw/sphw_hwif.h | 102 + .../net/ethernet/ramaxel/spnic/hw/sphw_mbox.c | 1808 +++++++++++++++++ .../net/ethernet/ramaxel/spnic/hw/sphw_mbox.h | 274 +++ .../net/ethernet/ramaxel/spnic/hw/sphw_mgmt.c | 1382 +++++++++++++ .../net/ethernet/ramaxel/spnic/hw/sphw_mgmt.h | 156 ++ .../ramaxel/spnic/hw/sphw_mgmt_msg_base.h | 19 + .../net/ethernet/ramaxel/spnic/hw/sphw_mt.h | 534 +++++ .../ramaxel/spnic/hw/sphw_prof_adap.c | 94 + .../ramaxel/spnic/hw/sphw_prof_adap.h | 49 + .../ethernet/ramaxel/spnic/hw/sphw_profile.h | 36 + .../net/ethernet/ramaxel/spnic/hw/sphw_wq.c | 152 ++ .../net/ethernet/ramaxel/spnic/hw/sphw_wq.h | 119 ++ .../net/ethernet/ramaxel/spnic/spnic_dbg.c | 753 +++++++ .../net/ethernet/ramaxel/spnic/spnic_dcb.c | 965 +++++++++ .../net/ethernet/ramaxel/spnic/spnic_dcb.h | 56 + .../ethernet/ramaxel/spnic/spnic_dev_mgmt.c | 811 ++++++++ .../ethernet/ramaxel/spnic/spnic_dev_mgmt.h | 78 + .../ethernet/ramaxel/spnic/spnic_ethtool.c | 983 +++++++++ .../ramaxel/spnic/spnic_ethtool_stats.c | 1035 ++++++++++ .../net/ethernet/ramaxel/spnic/spnic_filter.c | 412 ++++ .../net/ethernet/ramaxel/spnic/spnic_irq.c | 178 ++ .../net/ethernet/ramaxel/spnic/spnic_lld.c | 937 +++++++++ .../net/ethernet/ramaxel/spnic/spnic_lld.h | 75 + .../ethernet/ramaxel/spnic/spnic_mag_cfg.c | 778 +++++++ .../ethernet/ramaxel/spnic/spnic_mag_cmd.h | 643 ++++++ .../net/ethernet/ramaxel/spnic/spnic_main.c | 925 +++++++++ .../ramaxel/spnic/spnic_mgmt_interface.h | 617 ++++++ .../ethernet/ramaxel/spnic/spnic_netdev_ops.c | 1526 ++++++++++++++ .../net/ethernet/ramaxel/spnic/spnic_nic.h | 148 ++ .../ethernet/ramaxel/spnic/spnic_nic_cfg.c | 1321 ++++++++++++ .../ethernet/ramaxel/spnic/spnic_nic_cfg.h | 724 +++++++ .../ethernet/ramaxel/spnic/spnic_nic_cfg_vf.c | 647 ++++++ .../ethernet/ramaxel/spnic/spnic_nic_cmd.h | 105 + .../ethernet/ramaxel/spnic/spnic_nic_dbg.c | 151 ++ .../ethernet/ramaxel/spnic/spnic_nic_dbg.h | 16 + .../ethernet/ramaxel/spnic/spnic_nic_dev.h | 353 ++++ .../ethernet/ramaxel/spnic/spnic_nic_event.c | 506 +++++ .../net/ethernet/ramaxel/spnic/spnic_nic_io.c | 1124 ++++++++++ .../net/ethernet/ramaxel/spnic/spnic_nic_io.h | 309 +++ .../net/ethernet/ramaxel/spnic/spnic_nic_qp.h | 421 ++++ .../net/ethernet/ramaxel/spnic/spnic_ntuple.c | 841 ++++++++ .../ethernet/ramaxel/spnic/spnic_pci_id_tbl.h | 13 + .../net/ethernet/ramaxel/spnic/spnic_rss.c | 750 +++++++ .../net/ethernet/ramaxel/spnic/spnic_rss.h | 48 + .../ethernet/ramaxel/spnic/spnic_rss_cfg.c | 391 ++++ drivers/net/ethernet/ramaxel/spnic/spnic_rx.c | 1250 ++++++++++++ drivers/net/ethernet/ramaxel/spnic/spnic_rx.h | 118 ++ .../net/ethernet/ramaxel/spnic/spnic_sriov.c | 200 ++ .../net/ethernet/ramaxel/spnic/spnic_sriov.h | 24 + drivers/net/ethernet/ramaxel/spnic/spnic_tx.c | 879 ++++++++ drivers/net/ethernet/ramaxel/spnic/spnic_tx.h | 129 ++ 80 files changed, 38663 insertions(+) create mode 100644 drivers/net/ethernet/ramaxel/Kconfig create mode 100644 drivers/net/ethernet/ramaxel/Makefile create mode 100644 drivers/net/ethernet/ramaxel/spnic/Kconfig create mode 100644 drivers/net/ethernet/ramaxel/spnic/Makefile create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_api_cmd.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_api_cmd.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_cfg_cmd.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_cmdq.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_cmdq.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_comm_cmd.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_comm_msg_intf.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_common.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_common.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_crm.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_csr.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_eqs.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_eqs.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hw.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hw_cfg.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hw_cfg.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hw_comm.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hw_comm.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hwdev.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hwdev.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hwif.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_hwif.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_mbox.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_mbox.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_mgmt.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_mgmt.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_mgmt_msg_base.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_mt.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_prof_adap.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_prof_adap.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_profile.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_wq.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/hw/sphw_wq.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_dbg.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_dcb.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_dcb.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_dev_mgmt.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_dev_mgmt.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_ethtool.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_ethtool_stats.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_filter.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_irq.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_lld.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_lld.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_mag_cfg.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_mag_cmd.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_main.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_mgmt_interface.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_netdev_ops.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_cfg.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_cfg.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_cfg_vf.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_cmd.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_dbg.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_dbg.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_dev.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_event.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_io.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_io.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_nic_qp.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_ntuple.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_pci_id_tbl.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_rss.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_rss.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_rss_cfg.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_rx.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_rx.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_sriov.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_sriov.h create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_tx.c create mode 100644 drivers/net/ethernet/ramaxel/spnic/spnic_tx.h -- 2.30.0

1 2

[PATCH OLK-5.10 01/31] mm: fix page_owner initializing issue for arm32
by Zheng Zengkai 28 Sep '21

28 Sep '21

From: Zhenhua Huang <zhenhuah(a)codeaurora.org> mainline inclusion from mainline-v5.11-rc1 commit 7fb7ab6d618a4dc7ea3f3eafc92388a35b4f8894 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I49LXW CVE: NA ------------------------------------------------- Page owner of pages used by page owner itself used is missing on arm32 targets. The reason is dummy_handle and failure_handle is not initialized correctly. Buddy allocator is used to initialize these two handles. However, buddy allocator is not ready when page owner calls it. This change fixed that by initializing page owner after buddy initialization. The working flow before and after this change are: original logic: 1. allocated memory for page_ext(using memblock). 2. invoke the init callback of page_ext_ops like page_owner(using buddy allocator). 3. initialize buddy. after this change: 1. allocated memory for page_ext(using memblock). 2. initialize buddy. 3. invoke the init callback of page_ext_ops like page_owner(using buddy allocator). with the change, failure/dummy_handle can get its correct value and page owner output for example has the one for page owner itself: Page allocated via order 2, mask 0x6202c0(GFP_USER|__GFP_NOWARN), pid 1006, ts 67278156558 ns PFN 543776 type Unmovable Block 531 type Unmovable Flags 0x0() init_page_owner+0x28/0x2f8 invoke_init_callbacks_flatmem+0x24/0x34 start_kernel+0x33c/0x5d8 Link: https://lkml.kernel.org/r/1603104925-5888-1-git-send-email-zhenhuah@codeaur… Signed-off-by: Zhenhua Huang <zhenhuah(a)codeaurora.org> Acked-by: Vlastimil Babka <vbabka(a)suse.cz> Cc: Joonsoo Kim <iamjoonsoo.kim(a)lge.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> (cherry picked from commit 7fb7ab6d618a4dc7ea3f3eafc92388a35b4f8894) Signed-off-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Yuanzheng Song <songyuanzheng(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- include/linux/page_ext.h | 8 ++++++++ init/main.c | 2 ++ mm/page_ext.c | 10 ++++++++-- 3 files changed, 18 insertions(+), 2 deletions(-) diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index cfce186f0c4e..aff81ba31bd8 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -44,8 +44,12 @@ static inline void page_ext_init_flatmem(void) { } extern void page_ext_init(void); +static inline void page_ext_init_flatmem_late(void) +{ +} #else extern void page_ext_init_flatmem(void); +extern void page_ext_init_flatmem_late(void); static inline void page_ext_init(void) { } @@ -76,6 +80,10 @@ static inline void page_ext_init(void) { } +static inline void page_ext_init_flatmem_late(void) +{ +} + static inline void page_ext_init_flatmem(void) { } diff --git a/init/main.c b/init/main.c index fc0277a9e7a3..f6fe37a744b7 100644 --- a/init/main.c +++ b/init/main.c @@ -830,6 +830,8 @@ static void __init mm_init(void) init_debug_pagealloc(); report_meminit(); mem_init(); + /* page_owner must be initialized after buddy is ready */ + page_ext_init_flatmem_late(); kmem_cache_init(); kmemleak_init(); pgtable_init(); diff --git a/mm/page_ext.c b/mm/page_ext.c index cf931ebb58d7..df6f74aac8e1 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -99,12 +99,19 @@ static void __init invoke_init_callbacks(void) } } +#ifndef CONFIG_SPARSEMEM +void __init page_ext_init_flatmem_late(void) +{ + invoke_init_callbacks(); +} +#endif + static inline struct page_ext *get_entry(void *base, unsigned long index) { return base + page_ext_size * index; } -#if !defined(CONFIG_SPARSEMEM) +#ifndef CONFIG_SPARSEMEM void __meminit pgdat_page_ext_init(struct pglist_data *pgdat) @@ -177,7 +184,6 @@ void __init page_ext_init_flatmem(void) goto fail; } pr_info("allocated %ld bytes of page_ext\n", total_usage); - invoke_init_callbacks(); return; fail: -- 2.20.1

1 30

[PATCH openEuler-1.0-LTS] net:fix tcp timeout retransmits are always missing 2 times
by jiazhenyuan 28 Sep '21

28 Sep '21

mainline inclusion from mainline-v5.3.0 commit 3256a2d6ab1f71f9a1bd2d7f6f18eb8108c48d17 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4AFRJ?from=project-issue CVE: NA --------------------------------------------------------------- tcp: adjust rto_base in retransmits_timed_out() The cited commit exposed an old retransmits_timed_out() bug which assumed it could call tcp_model_timeout() with TCP_RTO_MIN as rto_base for all states. But flows in SYN_SENT or SYN_RECV state uses a different RTO base (1 sec instead of 200 ms, unless BPF choses another value) This caused a reduction of SYN retransmits from 6 to 4 with the default /proc/sys/net/ipv4/tcp_syn_retries value. Fixes: a41e8a8 ("tcp: better handle TCP_USER_TIMEOUT in SYN_SENT state") Signed-off-by: Eric Dumazet <edumazet(a)google.com> Cc: Yuchung Cheng <ycheng(a)google.com> Cc: Marek Majkowski <marek(a)cloudflare.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: jiazhenyuan <jiazhenyuan(a)uniontech.com> --- net/ipv4/tcp_timer.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 681882a40968..81a47e87c35d 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -190,7 +190,7 @@ static bool retransmits_timed_out(struct sock *sk, unsigned int boundary, unsigned int timeout) { - const unsigned int rto_base = TCP_RTO_MIN; + unsigned int rto_base = TCP_RTO_MIN; unsigned int linear_backoff_thresh, start_ts; if (!inet_csk(sk)->icsk_retransmits) @@ -201,6 +201,9 @@ static bool retransmits_timed_out(struct sock *sk, return false; if (likely(timeout == 0)) { + if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) + rto_base = tcp_timeout_init(sk); + linear_backoff_thresh = ilog2(TCP_RTO_MAX/rto_base); if (boundary <= linear_backoff_thresh) -- 2.27.0

2 1

[PATCH openEuler-1.0-LTS 01/14] Revert "bpf: Fix truncation handling for mod32 dst reg wrt zero"
by Yang Yingliang 28 Sep '21

28 Sep '21

From: He Fengqing <hefengqing(a)huawei.com> hulk inclusion category: bugfix bugzilla: NA CVE: CVE-2021-3444 ------------------------------------------------- This reverts commit 946dd60de74146a418f62275e5a6f83496f74dcd. Signed-off-by: He Fengqing <hefengqing(a)huawei.com> Reviewed-by: Kuohai Xu <xukuohai(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- kernel/bpf/verifier.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 962dc7c48430f..61a535eec0a9b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6322,7 +6322,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) bool isdiv = BPF_OP(insn->code) == BPF_DIV; struct bpf_insn *patchlet; struct bpf_insn chk_and_div[] = { - /* [R,W]x div 0 -> 0 */ + /* Rx div 0 -> 0 */ BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) | BPF_JNE | BPF_K, insn->src_reg, 0, 2, 0), @@ -6331,18 +6331,16 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) *insn, }; struct bpf_insn chk_and_mod[] = { - /* [R,W]x mod 0 -> [R,W]x */ + /* Rx mod 0 -> Rx */ BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) | BPF_JEQ | BPF_K, insn->src_reg, - 0, 1 + (is64 ? 0 : 1), 0), + 0, 1, 0), *insn, - BPF_JMP_IMM(BPF_JA, 0, 0, 1), - BPF_MOV32_REG(insn->dst_reg, insn->dst_reg), }; patchlet = isdiv ? chk_and_div : chk_and_mod; cnt = isdiv ? ARRAY_SIZE(chk_and_div) : - ARRAY_SIZE(chk_and_mod) - (is64 ? 2 : 0); + ARRAY_SIZE(chk_and_mod); new_prog = bpf_patch_insn_data(env, i + delta, patchlet, cnt); if (!new_prog) -- 2.25.1

1 13

[PATCH openEuler-1.0-LTS] net:fix tcp timeout retransmits are always missing 2 times
by jiazhenyuan 28 Sep '21

28 Sep '21

mainline inclusion from mainline-v5.3.0 commit 3256a2d6ab1f71f9a1bd2d7f6f18eb8108c48d17 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4AFRJ?from=project-issue CVE: NA --------------------------------------------------------------- tcp: adjust rto_base in retransmits_timed_out() The cited commit exposed an old retransmits_timed_out() bug which assumed it could call tcp_model_timeout() with TCP_RTO_MIN as rto_base for all states. But flows in SYN_SENT or SYN_RECV state uses a different RTO base (1 sec instead of 200 ms, unless BPF choses another value) This caused a reduction of SYN retransmits from 6 to 4 with the default /proc/sys/net/ipv4/tcp_syn_retries value. Fixes: a41e8a8 ("tcp: better handle TCP_USER_TIMEOUT in SYN_SENT state") Signed-off-by: Eric Dumazet <edumazet(a)google.com> Cc: Yuchung Cheng <ycheng(a)google.com> Cc: Marek Majkowski <marek(a)cloudflare.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: jiazhenyuan <jiazhenyuan(a)uniontech.com> --- net/ipv4/tcp_timer.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 681882a40968..81a47e87c35d 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -190,7 +190,7 @@ static bool retransmits_timed_out(struct sock *sk, unsigned int boundary, unsigned int timeout) { - const unsigned int rto_base = TCP_RTO_MIN; + unsigned int rto_base = TCP_RTO_MIN; unsigned int linear_backoff_thresh, start_ts; if (!inet_csk(sk)->icsk_retransmits) @@ -201,6 +201,9 @@ static bool retransmits_timed_out(struct sock *sk, return false; if (likely(timeout == 0)) { + if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) + rto_base = tcp_timeout_init(sk); + linear_backoff_thresh = ilog2(TCP_RTO_MAX/rto_base); if (boundary <= linear_backoff_thresh) -- 2.27.0

3 2

[PATCH kernel-4.19] block: fix wrong define name
by Yang Yingliang 28 Sep '21

28 Sep '21

From: Laibin Qiu <qiulaibin(a)huawei.com> hulk inclusion category: bugfix bugzilla: 182135 CVE: NA ------------------------------------------------- Fix wrong define name. Fixes: 8abeeaef3fbf ("block: fix compile error when CONFIG_BLK_DEV_THROTTLING disable") Signed-off-by: Laibin Qiu <qiulaibin(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- block/blk-cgroup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index ce04c5a5ebb11..36cccf6005c44 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1342,7 +1342,7 @@ void blkcg_drain_queue(struct request_queue *q) * @q could be exiting and q->td has not been initialized. * If so, don't need drain any throttled bios. */ -#ifdef CONFIG_BLK_DEV_THROTTLIN +#ifdef CONFIG_BLK_DEV_THROTTLING if (!q->td) return; #endif -- 2.25.1

1 0

[PATCH kernel-4.19 01/13] Revert "bpf: Fix truncation handling for mod32 dst reg wrt zero"
by Yang Yingliang 28 Sep '21

28 Sep '21

From: He Fengqing <hefengqing(a)huawei.com> hulk inclusion category: bugfix bugzilla: NA CVE: CVE-2021-3444 ------------------------------------------------- This reverts commit de207ba498fa2bbd29db790c4571b91617cab889. Signed-off-by: He Fengqing <hefengqing(a)huawei.com> Reviewed-by: Kuohai Xu <xukuohai(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- kernel/bpf/verifier.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 21986716e56ff..0d2211c6352c3 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6426,7 +6426,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) bool isdiv = BPF_OP(insn->code) == BPF_DIV; struct bpf_insn *patchlet; struct bpf_insn chk_and_div[] = { - /* [R,W]x div 0 -> 0 */ + /* Rx div 0 -> 0 */ BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) | BPF_JNE | BPF_K, insn->src_reg, 0, 2, 0), @@ -6435,18 +6435,16 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) *insn, }; struct bpf_insn chk_and_mod[] = { - /* [R,W]x mod 0 -> [R,W]x */ + /* Rx mod 0 -> Rx */ BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) | BPF_JEQ | BPF_K, insn->src_reg, - 0, 1 + (is64 ? 0 : 1), 0), + 0, 1, 0), *insn, - BPF_JMP_IMM(BPF_JA, 0, 0, 1), - BPF_MOV32_REG(insn->dst_reg, insn->dst_reg), }; patchlet = isdiv ? chk_and_div : chk_and_mod; cnt = isdiv ? ARRAY_SIZE(chk_and_div) : - ARRAY_SIZE(chk_and_mod) - (is64 ? 2 : 0); + ARRAY_SIZE(chk_and_mod); new_prog = bpf_patch_insn_data(env, i + delta, patchlet, cnt); if (!new_prog) -- 2.25.1

1 12

[PATCH kernel-4.19 00/31] backport linux-4.19.208
by Yang Yingliang 28 Sep '21

28 Sep '21

Andy Shevchenko (2): apparmor: remove duplicate macro list_entry_is_head() dmaengine: acpi: Avoid comparison GSI with Linux vIRQ Christophe Leroy (1): crypto: talitos - fix max key size for sha384 and sha512 Cyrill Gorcunov (1): prctl: allow to setup brk for et_dyn executables Dan Carpenter (1): thermal/drivers/exynos: Fix an error code in exynos_tmu_probe() Greg Kroah-Hartman (1): Linux 4.19.208 Guenter Roeck (2): parisc: Move pci_dev_is_behind_card_dino to where it is used drm/nouveau/nvkm: Replace -ENOSYS with -ENODEV Ilya Leoshkevich (1): s390/bpf: Fix optimizing out zero-extensions Jeff Layton (1): ceph: lockdep annotations for try_nonblocking_invalidate Johannes Berg (1): dmaengine: ioat: depends on !UML Li Huafei (1): tracing/kprobe: Fix kprobe_on_func_entry() modification Lukas Bulwahn (1): Kconfig.debug: drop selecting non-existing HARDLOCKUP_DETECTOR_ARCH Nanyong Sun (6): nilfs2: fix memory leak in nilfs_sysfs_create_device_group nilfs2: fix NULL pointer in nilfs_##name##_attr_release nilfs2: fix memory leak in nilfs_sysfs_create_##name##_group nilfs2: fix memory leak in nilfs_sysfs_delete_##name##_group nilfs2: fix memory leak in nilfs_sysfs_create_snapshot_group nilfs2: fix memory leak in nilfs_sysfs_delete_snapshot_group Neeraj Upadhyay (1): rcu: Fix missed wakeup of exp_wq waiters Pavel Skripkin (1): profiling: fix shift-out-of-bounds bugs Radhey Shyam Pandey (1): dmaengine: xilinx_dma: Set DMA mask for coherent APIs Radim Krčmář (1): KVM: remember position in kvm->vcpus array Thomas Gleixner (1): drivers: base: cacheinfo: Get rid of DEFINE_SMP_CALL_CACHE_FUNCTION() Uwe Kleine-König (4): pwm: lpc32xx: Don't modify HW state in .probe() after the PWM chip was registered pwm: img: Don't modify HW state in .remove() callback pwm: rockchip: Don't modify HW state in .remove() callback pwm: stm32-lp: Don't modify HW state in .remove() callback Xie Yongji (1): 9p/trans_virtio: Remove sysfs file on probe failure Zhen Lei (1): nilfs2: use refcount_dec_and_lock() to fix potential UAF Zou Wei (1): dmaengine: sprd: Add missing MODULE_DEVICE_TABLE Makefile | 2 +- arch/arm64/kernel/cacheinfo.c | 7 +-- arch/mips/kernel/cacheinfo.c | 7 +-- arch/riscv/kernel/cacheinfo.c | 7 +-- arch/s390/net/bpf_jit_comp.c | 50 ++++++++++--------- arch/x86/kernel/cpu/cacheinfo.c | 7 +-- drivers/crypto/talitos.c | 2 +- drivers/dma/Kconfig | 2 +- drivers/dma/acpi-dma.c | 10 ++-- drivers/dma/sprd-dma.c | 1 + drivers/dma/xilinx/xilinx_dma.c | 2 +- .../gpu/drm/nouveau/nvkm/engine/device/ctrl.c | 2 +- drivers/parisc/dino.c | 18 +++---- drivers/pwm/pwm-img.c | 16 ------ drivers/pwm/pwm-lpc32xx.c | 10 ++-- drivers/pwm/pwm-rockchip.c | 14 ------ drivers/pwm/pwm-stm32-lp.c | 2 - drivers/thermal/samsung/exynos_tmu.c | 1 + fs/ceph/caps.c | 2 + fs/nilfs2/sysfs.c | 26 ++++------ fs/nilfs2/the_nilfs.c | 9 ++-- include/linux/cacheinfo.h | 18 ------- include/linux/kvm_host.h | 11 ++-- kernel/profile.c | 21 ++++---- kernel/rcu/tree_exp.h | 2 +- kernel/sys.c | 7 --- kernel/trace/trace_kprobe.c | 3 +- lib/Kconfig.debug | 1 - net/9p/trans_virtio.c | 4 +- security/apparmor/apparmorfs.c | 3 -- virt/kvm/kvm_main.c | 5 +- 31 files changed, 102 insertions(+), 170 deletions(-) -- 2.25.1

1 31

[PATCH kernel-4.19 000/280] backport linux-4.19.207
by Yang Yingliang 27 Sep '21

27 Sep '21

Adrian Bunk (1): bnx2x: Fix enabling network interfaces without VFs Alexander Tsoy (1): ALSA: usb-audio: Add registration quirk for JBL Quantum 800 Alexei Starovoitov (1): selftests/bpf: fix tests due to const spill/fill Andreas Obergschwandtner (1): ARM: tegra: tamonten: Fix UART pad setting Andrey Grodzovsky (1): drm/amdgpu: Fix BUG_ON assert Andrey Ignatov (5): bpf: Support variable offset stack access from helpers bpf: Reject indirect var_off stack access in raw mode bpf: Reject indirect var_off stack access in unpriv mode bpf: Sanity check max value for var_off stack access selftests/bpf: Test variable offset stack access Andy Duan (1): tty: serial: fsl_lpuart: fix the wrong mapbase value Andy Shevchenko (3): include/linux/list.h: add a macro to test if entry is pointing to the head ata: sata_dwc_460ex: No need to call phy_exit() befre phy_init() PCI: Sync __pci_register_driver() stub for CONFIG_PCI=n Anirudh Rayabharam (1): usbip: give back URBs for unsent unlink requests during cleanup Anson Jacob (1): drm/amd/amdgpu: Update debugfs link_settings output link_rate field in hex Arne Welzel (1): dm crypt: Avoid percpu_counter spinlock contention in crypt_page_alloc() Austin Kim (1): IMA: remove -Wmissing-prototypes warning Babu Moger (1): x86/resctrl: Fix a maybe-uninitialized build warning treated as error Baptiste Lepers (1): events: Reuse value read using READ_ONCE instead of re-reading it Ben Dooks (1): ARM: 8918/2: only build return_address() if needed Benjamin Hesmans (1): netfilter: socket: icmp6: fix use-after-scope Bob Peterson (1): gfs2: Don't call dlm after protocol is unmounted Chao Yu (2): f2fs: fix to account missing .skipped_gc_rwsem f2fs: fix to unmap pages from userspace process in punch_hole() Chih-Kang Chang (1): mac80211: Fix insufficient headroom issue for AMSDU Christoph Hellwig (2): cryptoloop: add a deprecation warning bcache: add proper error unwinding in bcache_device_init Christophe JAILLET (4): drm/msm/dsi: Fix some reference counted resource leaks usb: bdc: Fix an error handling path in 'bdc_probe()' when no suitable DMA config is available staging: ks7010: Fix the initialization of the 'sleep_status' structure mtd: rawnand: cafe: Fix a resource leak in the error handling path of 'cafe_nand_probe()' Christophe Leroy (1): crypto: talitos - reduce max key size for SEC1 Chunfeng Yun (2): usb: mtu3: use @mult for HS isoc or intr usb: mtu3: fix the wrong HS mult value Chunyan Zhang (1): spi: sprd: Fix the wrong WDG_LOAD_VAL Colin Ian King (4): ARM: imx: fix missing 3rd argument in macro imx_mmdc_perf_init media: venus: venc: Fix potential null pointer dereference on pointer fmt Bluetooth: increase BTNAMSIZ to 21 chars to fix potential buffer overflow parport: remove non-zero check on count Damien Le Moal (2): libata: fix ata_host_start() block: bfq: fix bfq_set_next_ioprio_data() Dan Carpenter (4): Bluetooth: sco: prevent information leak in sco_conn_defer_accept() ath6kl: wmi: fix an error code in ath6kl_wmi_sync_point() scsi: qedi: Fix error codes in qedi_alloc_global_queues() PCI: Fix pci_dev_str_match_path() alloc while atomic bug Daniel Borkmann (1): bpf: Fix pointer arithmetic mask tightening under state pruning Daniel Thompson (1): backlight: pwm_bl: Improve bootloader/kernel device handover Daniele Palmas (1): net: usb: cdc_mbim: avoid altsetting toggling for Telit LN920 David Heidelberg (2): ARM: 9105/1: atags_to_fdt: don't warn about stack size ARM: dts: qcom: apq8064: correct clock names David Hildenbrand (1): mm/memory_hotplug: use "unsigned long" for PFN in zone_for_pfn_range() David Howells (1): fscache: Fix cookie key hashing Desmond Cheong Zhi Xi (4): fcntl: fix potential deadlock for &fasync_struct.fa_lock Bluetooth: fix repeated calls to sco_sock_kill btrfs: reset replace target device to allocation state on close Bluetooth: skip invalid hci_sync_conn_complete_evt Dietmar Eggemann (1): sched/deadline: Fix missing clock update in migrate_task_rq_dl() Ding Hui (1): cifs: fix wrong release in sess_alloc_buffer() failed path Dinghao Liu (1): qlcnic: Remove redundant unlock in qlcnic_pinit_from_rom Dmitry Baryshkov (1): drm/msm/dpu: make dpu_hw_ctl_clear_all_blendstages clear necessary LMs Dmitry Osipenko (1): rtc: tps65910: Correct driver module alias Dmitry Torokhov (1): HID: input: do not report stylus battery state as "full" Dongliang Mu (3): media: dvb-usb: fix uninit-value in dvb_usb_adapter_dvb_init media: dvb-usb: fix uninit-value in vp702x_read_mac_addr media: em28xx-input: fix refcount bug in em28xx_usb_disconnect Eric Biggers (4): fscrypt: add fscrypt_symlink_getattr() for computing st_size ext4: report correct st_size for encrypted symlinks f2fs: report correct st_size for encrypted symlinks ubifs: report correct st_size for encrypted symlinks Eric Dumazet (5): ipv4: make exception cache less predictible ipv4: fix endianness issue in inet_rtm_getroute_build_skb() net-caif: avoid user-triggerable WARN_ON(1) net/af_unix: fix a data-race in unix_dgram_poll fq_codel: reject silly quantum parameters Esben Haabendal (1): net: ll_temac: Remove left-over debug message Evan Quan (1): PCI: Add AMD GPU multi-function power dependencies Evgeny Novikov (2): usb: ehci-orion: Handle errors of clk_prepare_enable() in probe media: tegra-cec: Handle errors of clk_prepare_enable() Fangrui Song (1): powerpc/boot: Delete unneeded .globl _zimage_start Florian Fainelli (1): r6040: Restore MDIO clock frequency after MAC reset Geert Uytterhoeven (2): soc: rockchip: ROCKCHIP_GRF should not default to y, unconditionally staging: board: Fix uninitialized spinlock when attaching genpd George Cherian (1): PCI: Add ACS quirks for Cavium multi-function devices Giovanni Cabiddu (4): crypto: qat - do not ignore errors from enable_vf2pf_comms() crypto: qat - handle both source of interrupt in VF ISR crypto: qat - do not export adf_iov_putmsg() crypto: qat - use proper type for vf_mask Greg Kroah-Hartman (2): serial: 8250_pci: make setup_port() parameters explicitly unsigned Linux 4.19.207 Guillaume Nault (1): netns: protect netns ID lookups with RCU Gustavo A. R. Silva (2): ipv4: ip_output.c: Fix out-of-bounds warning in ip_copy_addrs() flow_dissector: Fix out-of-bounds warnings Halil Pasic (1): KVM: s390: index kvm->arch.idle_mask by vcpu_idx Hans Verkuil (1): media: v4l2-dv-timings.c: fix wrong condition in two for-loops Hans de Goede (5): power: supply: axp288_fuel_gauge: Report register-address on readb / writeb errors libata: add ATA_HORKAGE_NO_NCQ_TRIM for Samsung 860 and 870 SSDs platform/x86: dell-smbios-wmi: Add missing kfree in error-exit from run_smbios_call ASoC: Intel: bytcr_rt5640: Move "Platform Clock" routes to the maps for the matching in-/output mfd: axp20x: Update AXP288 volatile ranges Harini Katakam (1): net: macb: Add a NULL check on desc_ptp Harshvardhan Jha (1): 9p/xen: Fix end of loop tests for list_for_each_entry Heiko Carstens (1): s390/jump_label: print real address in a case of a jump label bug Hoang Le (1): tipc: increase timeout in tipc_sk_enqueue() Hongbo Li (1): lib/mpi: use kcalloc in mpi_resize Hyun Kwon (1): PCI: xilinx-nwl: Enable the clock through CCF Ilya Leoshkevich (1): s390/bpf: Fix 64-bit subtraction of the -0x80000000 constant Iwona Winiarska (1): soc: aspeed: lpc-ctrl: Fix boundary check for mmap J. Bruce Fields (1): rpc: fix gss_svc_init cleanup on failure Jack Pham (1): usb: gadget: composite: Allow bMaxPower=0 if self-powered Jaehyoung Choi (1): pinctrl: samsung: Fix pinctrl bank pin count Jan Kara (1): udf: Check LVID earlier Jason Gunthorpe (1): vfio: Use config not menuconfig for VFIO_NOIOMMU Jeongtae Park (1): regmap: fix the offset of register error log Jiong Wang (1): bpf: correct slot_type marking logic to allow more stack slot sharing Jiri Slaby (2): xtensa: ISS: don't panic in rs_init hvsi: don't panic on tty_register_driver failure Johan Almbladh (2): bpf/tests: Fix copy-and-paste error in double word test bpf/tests: Do not PASS tests without actually testing the result Jonathan Cameron (1): iio: dac: ad5624r: Fix incorrect handling of an optional regulator. Juergen Gross (3): xen: fix setting of max_pfn in shared_info xen: reset legacy rtc flag for PV domU PM: base: power: don't try to use non-existing RTC for storing data Juhee Kang (1): samples: bpf: Fix tracex7 error raised on the missing argument Kai-Heng Feng (1): Bluetooth: Move shutdown callback before flushing tx and rx queue Kajol Jain (1): powerpc/perf/hv-gpci: Fix counter value parsing Kees Cook (1): staging: rts5208: Fix get_ms_information() heap buffer size Kelly Devilliv (2): usb: host: fotg210: fix the endpoint's transactional opportunities calculation usb: host: fotg210: fix the actual_length of an iso packet Kim Phillips (1): perf/x86/amd/ibs: Work around erratum #1197 Krzysztof Hałasa (3): gpu: ipu-v3: Fix i.MX IPU-v3 offset calculations for (semi)planar U/V formats media: TDA1997x: enable EDID support media: TDA1997x: fix tda1997x_query_dv_timings() return value Krzysztof Kozlowski (2): arm64: dts: exynos: correct GIC CPU interfaces address range on Exynos7 power: supply: max17042: handle fails of reading status register Krzysztof Wilczyński (1): PCI: Return ~0 data on pciconfig_read() CAP_SYS_ADMIN failure Laurent Pinchart (1): media: imx258: Rectify mismatch of VTS value Len Baker (1): CIFS: Fix a potencially linear read overflow Leon Romanovsky (2): RDMA/iwcm: Release resources if iw_cm module initialization fails docs: Fix infiniband uverbs minor number Li Zhijian (1): selftests/bpf: Enlarge select() timeout for test_maps Lin, Zhenpeng (1): dccp: don't duplicate ccid when cloning dccp sock Linus Walleij (1): clk: kirkwood: Fix a clocking boot regression Liu Zixian (1): mm/hugetlb: initialize hugetlb_usage in mm_init Lorenz Bauer (1): bpf: verifier: Allocate idmap scratch in verifier env Luiz Augusto von Dentz (1): Bluetooth: Fix handling of LE Enhanced Connection Complete Luke Hsiao (1): tcp: enable data-less, empty-cookie SYN with TFO_SERVER_COOKIE_NOT_REQD Maciej W. Rozycki (2): serial: 8250: Define RX trigger levels for OxSemi 950 devices scsi: BusLogic: Fix missing pr_cont() use Maciej Żenczykowski (1): usb: gadget: u_ether: fix a potential null pointer dereference Manish Narani (1): mmc: sdhci-of-arasan: Check return value of non-void funtions Maor Gottlieb (1): net/mlx5: Fix potential sleeping in atomic context Marc Zyngier (2): of: Don't allow __of_attached_node_sysfs() without CONFIG_SYSFS mfd: Don't use irq_create_mapping() to resolve a mapping Marco Chiappero (2): crypto: qat - fix reuse of completion variable crypto: qat - fix naming for init/shutdown VF to PF notifications Marek Behún (2): PCI: Call Max Payload Size-related fixup quirks early PCI: Restrict ASMedia ASM1062 SATA Max Payload Size Supported Marek Marczykowski-Górecki (1): PCI/MSI: Skip masking MSI-X on Xen PV Mark Brown (1): arm64/sve: Use correct size when reinitialising SVE state Mark Rutland (1): arm64: head: avoid over-mapping in map_memory Martin KaFai Lau (1): tcp: seq_file: Avoid skipping sk during tcp_seek_last_pos Mathias Nyman (1): Revert "USB: xhci: fix U1/U2 handling for hardware with XHCI_INTEL_HOST quirk set" Mathieu Desnoyers (1): ipv4/icmp: l3mdev: Perform icmp error route lookup on source device routing table (v2) Mauro Carvalho Chehab (2): media: uvc: don't do DMA on stack media: dib8000: rewrite the init prbs logic Miaoqing Pan (1): ath9k: fix sleeping in atomic context Michael Ellerman (1): powerpc/module64: Fix comment in R_PPC64_ENTRY handling Michael Petlan (1): perf machine: Initialize srcline string member in add_location struct Michal Suchanek (1): powerpc/stacktrace: Include linux/delay.h Mike Rapoport (1): x86/mm: Fix kern_addr_valid() to cope with existing but not present entries Mikulas Patocka (1): parisc: fix crash with signals and alloca Miquel Raynal (1): dt-bindings: mtd: gpmc: Fix the ECC bytes vs. OOB bytes equation Nadav Amit (1): userfaultfd: prevent concurrent API initialization Nadezda Lutovinova (2): usb: gadget: mv_u3d: request_irq() after initializing UDC usb: musb: musb_dsps: request_irq() after initializing musb Nathan Chancellor (1): net: ethernet: stmmac: Do not use unreachable() in ipq806x_gmac_probe() Nguyen Dinh Phi (1): tty: Fix data race between tiocsti() and flush_to_ldisc() Niklas Cassel (2): blk-zoned: allow zone management send operations without CAP_SYS_ADMIN blk-zoned: allow BLKREPORTZONE without CAP_SYS_ADMIN Nishad Kamdar (1): mmc: core: Return correct emmc response in case of ioctl error Oleksij Rempel (1): MIPS: Malta: fix alignment of the devicetree buffer Oliver Upton (1): KVM: arm64: Handle PSCI resets before userspace touches vCPU state Pali Rohár (3): isofs: joliet: Fix iocharset=utf8 mount option PCI: aardvark: Increase polling delay to 1.5s while waiting for PIO response PCI: aardvark: Fix masking and unmasking legacy INTx interrupts Paolo Valente (1): block, bfq: honor already-setup queue merges Patryk Duda (1): platform/chrome: cros_ec_proto: Send command again when timeout occurs Paul Gortmaker (1): x86/reboot: Limit Dell Optiplex 990 quirk to early BIOS versions Pavel Skripkin (5): media: stkwebcam: fix memory leak in stk_camera_probe m68k: emu: Fix invalid free in nfeth_cleanup() media: go7007: remove redundant initialization net: cipso: fix warnings in netlbl_cipsov4_add_std Bluetooth: add timeout sanity check to hci_inquiry Peter Zijlstra (1): locking/mutex: Fix HANDOFF condition Phong Hoang (1): clocksource/drivers/sh_cmt: Fix wrong setting if don't request IRQ for clock source channel Pratik R. Sampat (1): cpufreq: powernv: Fix init_chip_info initialization in numa=off Qu Wenruo (1): Revert "btrfs: compression: don't try to compress if we don't have enough pages" Quentin Perret (1): sched/deadline: Fix reset_on_fork reporting of DL tasks Rafael J. Wysocki (3): PCI: PM: Avoid forcing PCI_D0 for wakeup reasons inconsistently PCI: PM: Enable PME if it can be signaled from D3cold PCI: Use pci_update_current_state() in pci_enable_device_flags() Rafał Miłecki (1): net: dsa: b53: Fix calculating number of switch ports Randy Dunlap (4): xtensa: fix kconfig unmet dependency warning for HAVE_FUTEX_CMPXCHG openrisc: don't printk() unconditionally ptp: dp83640: don't define PAGE0 ARC: export clear_user_page() for modules Rolf Eike Beer (1): tools/thermal/tmon: Add cross compiling support Saurav Kashyap (1): scsi: qla2xxx: Sync queue idx with queue_pair_map idx Sean Anderson (2): crypto: mxs-dcp - Check for DMA mapping errors crypto: mxs-dcp - Use sg_mapping_iter to copy data Sean Young (1): media: rc-loopback: return number of emitters rather than error Sebastian Krzyszkowiak (1): power: supply: max17042_battery: fix typo in MAx17042_TOFF Sebastian Reichel (1): ARM: dts: imx53-ppd: Fix ACHC entry Sergey Shtylyov (9): i2c: highlander: add IRQ check usb: gadget: udc: at91: add IRQ check usb: phy: fsl-usb: add IRQ check usb: phy: twl6030: add IRQ checks usb: host: ohci-tmio: add IRQ check usb: phy: tahvo: add IRQ check i2c: iop3xx: fix deferred probing i2c: s3c2410: fix IRQ check i2c: mt65xx: fix IRQ check Shai Malin (3): qed: Fix the VF msix vectors flow qede: Fix memset corruption qed: Handle management FW error Shuah Khan (1): usbip:vhci_hcd USB port can get stuck in the disabled state Stefan Berger (1): certs: Trigger creation of RSA module signing key if it's not an RSA key Stefan Wahren (1): net: qualcomm: fix QCA7000 checksum handling Stephan Gerhold (1): soc: qcom: smsm: Fix missed interrupts if state changes while masked Stian Skjelstad (1): udf_get_extendedattr() had no boundary checks. Sugar Zhang (1): ASoC: rockchip: i2s: Fix regmap_ops hang Sukadev Bhattiprolu (1): ibmvnic: check failover_pending in login response THOBY Simon (1): IMA: remove the dependency on CRYPTO_MD5 Tetsuo Handa (1): fbmem: don't allow too huge resolutions Thomas Gleixner (1): hrtimer: Avoid double reprogramming in __hrtimer_start_range_ns() Thomas Hebb (1): mmc: rtsx_pci: Fix long reads when clock is prescaled Tianjia Zhang (1): Smack: Fix wrong semantics in smk_access_entry() Tom Rix (1): USB: serial: mos7720: improve OOM-handling in read_mos_reg() Tony Lindgren (5): crypto: omap-sham - clear dma flags only after omap_sham_update_dma_stop() spi: spi-fsl-dspi: Fix issue with uninitialized dma_slave_config spi: spi-pic32: Fix issue with uninitialized dma_slave_config mmc: dw_mmc: Fix issue with uninitialized dma_slave_config mmc: moxart: Fix issue with uninitialized dma_slave_config Tuo Li (1): gpu: drm: amd: amdgpu: amdgpu_i2c: fix possible uninitialized-variable access in amdgpu_i2c_router_select_ddc_port() Ulrich Hecht (1): serial: sh-sci: fix break handling for sysrq Umang Jain (1): media: imx258: Limit the max analogue gain to 480 Vineeth Vijayan (1): s390/cio: add dev_busid sysfs entry for each subchannel Vinod Koul (1): arm64: dts: qcom: sdm660: use reg value for memory node Vladimir Oltean (1): net: dsa: destroy the phylink instance on any error in dsa_slave_phy_setup Wang Hai (1): VMCI: fix NULL pointer dereference when unmapping queue pair Willem de Bruijn (1): ip_gre: validate csum_start only on pull Xiaotan Luo (1): ASoC: rockchip: i2s: Fixup config for DAIFMT_DSP_A/B Xiaoyao Li (1): perf/x86/intel/pt: Fix mask of num_address_ranges Xin Long (2): tipc: keep the skb in rcv queue until the whole data is read tipc: fix an use-after-free issue in tipc_recvmsg Xiyu Yang (2): net: sched: Fix qdisc_rate_table refcount leak when get tcf_block failed net/l2tp: Fix reference count leak in l2tp_udp_recv_core Yajun Deng (1): netlink: Deal with ESRCH error in nlmsg_notify() Yang Li (2): ethtool: Fix an error code in cxgb2.c NTB: perf: Fix an error code in perf_setup_inbuf() Yang Yingliang (2): ARM: imx: add missing clk_disable_unprepare() net: w5100: check return value after calling platform_get_resource() Yoshihiro Shimoda (2): usb: host: xhci-rcar: Don't reload firmware after the completion net: renesas: sh_eth: Fix freeing wrong tx descriptor Yufeng Mo (1): bonding: 3ad: fix the concurrency between __bond_release_one() and bond_3ad_state_machine_handler() Zekun Shen (1): ath9k: fix OOB read ar9300_eeprom_restore_internal Zelin Deng (1): KVM: x86: Update vCPU's hv_clock before back to guest when tsc_offset is adjusted Zenghui Yu (1): bcma: Fix memory leak for internally-handled cores Zhen Lei (1): pinctrl: single: Fix error return code in pcs_parse_bits_in_pinctrl_entry() Zheyu Ma (5): video: fbdev: kyro: fix a DoS bug by restricting user input tty: serial: jsm: hold port lock when reporting modem line changes video: fbdev: asiliantfb: Error out if 'pixclock' equals zero video: fbdev: kyro: Error out if 'pixclock' equals zero video: fbdev: riva: Error out if 'pixclock' equals zero Zubin Mithra (1): ALSA: pcm: fix divide error in snd_pcm_lib_ioctl chenying (1): ovl: fix BUG_ON() in may_delete() when called from ovl_cleanup() zhenggy (1): tcp: fix tp->undo_retrans accounting in tcp_sacktag_one() zhenwei pi (1): crypto: public_key: fix overflow during implicit conversion 王贇 (1): net: fix NULL pointer reference in cipso_v4_doi_free Documentation/admin-guide/devices.txt | 6 +- .../devicetree/bindings/mtd/gpmc-nand.txt | 2 +- Makefile | 2 +- arch/arc/mm/cache.c | 2 +- arch/arm/boot/compressed/Makefile | 2 + arch/arm/boot/dts/imx53-ppd.dts | 23 ++- arch/arm/boot/dts/qcom-apq8064.dtsi | 6 +- arch/arm/boot/dts/tegra20-tamonten.dtsi | 14 +- arch/arm/kernel/Makefile | 6 +- arch/arm/kernel/return_address.c | 4 - arch/arm/mach-imx/mmdc.c | 14 +- arch/arm64/boot/dts/exynos/exynos7.dtsi | 2 +- arch/arm64/boot/dts/qcom/ipq8074-hk01.dts | 2 +- arch/arm64/include/asm/kernel-pgtable.h | 4 +- arch/arm64/kernel/fpsimd.c | 2 +- arch/arm64/kernel/head.S | 11 +- arch/m68k/emu/nfeth.c | 4 +- arch/mips/mti-malta/malta-dtshim.c | 2 +- arch/openrisc/kernel/entry.S | 2 + arch/parisc/kernel/signal.c | 6 + arch/powerpc/boot/crt0.S | 3 - arch/powerpc/kernel/module_64.c | 2 +- arch/powerpc/kernel/stacktrace.c | 1 + arch/powerpc/perf/hv-gpci.c | 2 +- arch/s390/kernel/jump_label.c | 2 +- arch/s390/kvm/interrupt.c | 4 +- arch/s390/kvm/kvm-s390.h | 2 +- arch/s390/net/bpf_jit_comp.c | 9 +- arch/x86/events/amd/ibs.c | 8 + arch/x86/events/intel/pt.c | 2 +- arch/x86/kernel/cpu/intel_rdt_monitor.c | 6 + arch/x86/kernel/reboot.c | 3 +- arch/x86/kvm/x86.c | 4 + arch/x86/mm/init_64.c | 6 +- arch/x86/xen/enlighten_pv.c | 7 + arch/x86/xen/p2m.c | 4 +- arch/xtensa/Kconfig | 2 +- arch/xtensa/platforms/iss/console.c | 17 +- block/bfq-iosched.c | 18 +- block/blk-zoned.c | 6 - certs/Makefile | 8 + drivers/ata/libata-core.c | 6 +- drivers/ata/sata_dwc_460ex.c | 12 +- drivers/base/power/trace.c | 10 + drivers/base/regmap/regmap.c | 2 +- drivers/bcma/main.c | 6 +- drivers/block/Kconfig | 4 +- drivers/block/cryptoloop.c | 2 + drivers/clk/mvebu/kirkwood.c | 1 + drivers/clocksource/sh_cmt.c | 30 +-- drivers/cpufreq/powernv-cpufreq.c | 16 +- drivers/crypto/mxs-dcp.c | 81 ++++---- drivers/crypto/omap-sham.c | 2 +- .../qat/qat_c3xxxvf/adf_c3xxxvf_hw_data.c | 4 +- .../qat/qat_c62xvf/adf_c62xvf_hw_data.c | 4 +- .../crypto/qat/qat_common/adf_common_drv.h | 8 +- drivers/crypto/qat/qat_common/adf_init.c | 5 +- drivers/crypto/qat/qat_common/adf_isr.c | 7 +- drivers/crypto/qat/qat_common/adf_pf2vf_msg.c | 3 +- drivers/crypto/qat/qat_common/adf_vf2pf_msg.c | 12 +- drivers/crypto/qat/qat_common/adf_vf_isr.c | 7 +- .../qat_dh895xccvf/adf_dh895xccvf_hw_data.c | 4 +- drivers/crypto/talitos.c | 4 + drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 2 +- .../amd/display/amdgpu_dm/amdgpu_dm_debugfs.c | 16 +- drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c | 10 +- drivers/gpu/drm/msm/dsi/dsi.c | 6 +- drivers/gpu/ipu-v3/ipu-cpmem.c | 30 +-- drivers/hid/hid-input.c | 2 - drivers/i2c/busses/i2c-highlander.c | 2 +- drivers/i2c/busses/i2c-iop3xx.c | 6 +- drivers/i2c/busses/i2c-mt65xx.c | 2 +- drivers/i2c/busses/i2c-s3c2410.c | 2 +- drivers/iio/dac/ad5624r_spi.c | 18 +- drivers/infiniband/core/iwcm.c | 19 +- drivers/md/bcache/super.c | 16 +- drivers/md/dm-crypt.c | 7 +- drivers/media/dvb-frontends/dib8000.c | 58 ++++-- drivers/media/i2c/imx258.c | 4 +- drivers/media/i2c/tda1997x.c | 6 +- drivers/media/platform/qcom/venus/venc.c | 2 + drivers/media/platform/tegra-cec/tegra_cec.c | 10 +- drivers/media/rc/rc-loopback.c | 2 +- drivers/media/usb/dvb-usb/nova-t-usb2.c | 6 +- drivers/media/usb/dvb-usb/vp702x.c | 12 +- drivers/media/usb/em28xx/em28xx-input.c | 1 - drivers/media/usb/go7007/go7007-driver.c | 26 --- drivers/media/usb/stkwebcam/stk-webcam.c | 6 +- drivers/media/usb/uvc/uvc_v4l2.c | 34 ++-- drivers/media/v4l2-core/v4l2-dv-timings.c | 4 +- drivers/mfd/ab8500-core.c | 2 +- drivers/mfd/axp20x.c | 3 +- drivers/mfd/stmpe.c | 4 +- drivers/mfd/tc3589x.c | 2 +- drivers/mfd/wm8994-irq.c | 2 +- drivers/misc/aspeed-lpc-ctrl.c | 2 +- drivers/misc/vmw_vmci/vmci_queue_pair.c | 6 +- drivers/mmc/core/block.c | 3 +- drivers/mmc/host/dw_mmc.c | 1 + drivers/mmc/host/moxart-mmc.c | 1 + drivers/mmc/host/rtsx_pci_sdmmc.c | 36 ++-- drivers/mmc/host/sdhci-of-arasan.c | 18 +- drivers/mtd/nand/raw/cafe_nand.c | 4 +- drivers/net/bonding/bond_main.c | 3 +- drivers/net/dsa/b53/b53_common.c | 3 +- .../net/ethernet/broadcom/bnx2x/bnx2x_sriov.c | 2 +- drivers/net/ethernet/cadence/macb_ptp.c | 11 +- drivers/net/ethernet/chelsio/cxgb/cxgb2.c | 1 + drivers/net/ethernet/ibm/ibmvnic.c | 8 + .../net/ethernet/mellanox/mlx5/core/fs_core.c | 5 +- drivers/net/ethernet/qlogic/qed/qed_main.c | 7 +- drivers/net/ethernet/qlogic/qed/qed_mcp.c | 6 +- drivers/net/ethernet/qlogic/qede/qede_main.c | 2 +- .../net/ethernet/qlogic/qlcnic/qlcnic_init.c | 1 - drivers/net/ethernet/qualcomm/qca_spi.c | 2 +- drivers/net/ethernet/qualcomm/qca_uart.c | 2 +- drivers/net/ethernet/rdc/r6040.c | 9 +- drivers/net/ethernet/renesas/sh_eth.c | 1 + .../ethernet/stmicro/stmmac/dwmac-ipq806x.c | 18 +- drivers/net/ethernet/wiznet/w5100.c | 2 + drivers/net/ethernet/xilinx/ll_temac_main.c | 4 +- drivers/net/phy/dp83640_reg.h | 2 +- drivers/net/usb/cdc_mbim.c | 5 + drivers/net/wireless/ath/ath6kl/wmi.c | 4 +- .../net/wireless/ath/ath9k/ar9003_eeprom.c | 3 +- drivers/net/wireless/ath/ath9k/hw.c | 12 +- drivers/ntb/test/ntb_perf.c | 1 + drivers/of/kobj.c | 2 +- drivers/parport/ieee1284_ops.c | 2 +- drivers/pci/controller/pci-aardvark.c | 11 +- drivers/pci/controller/pcie-xilinx-nwl.c | 12 ++ drivers/pci/msi.c | 3 + drivers/pci/pci.c | 33 ++-- drivers/pci/quirks.c | 26 ++- drivers/pci/syscall.c | 4 +- drivers/pinctrl/pinctrl-single.c | 1 + drivers/pinctrl/samsung/pinctrl-samsung.c | 2 +- drivers/platform/chrome/cros_ec_proto.c | 9 + drivers/platform/x86/dell-smbios-wmi.c | 1 + drivers/power/supply/axp288_fuel_gauge.c | 4 +- drivers/power/supply/max17042_battery.c | 8 +- drivers/rtc/rtc-tps65910.c | 2 +- drivers/s390/cio/css.c | 17 ++ drivers/scsi/BusLogic.c | 4 +- drivers/scsi/qedi/qedi_main.c | 14 +- drivers/scsi/qla2xxx/qla_nvme.c | 5 +- drivers/soc/qcom/smsm.c | 11 +- drivers/soc/rockchip/Kconfig | 4 +- drivers/spi/spi-fsl-dspi.c | 1 + drivers/spi/spi-pic32.c | 1 + drivers/spi/spi-sprd-adi.c | 2 +- drivers/staging/board/board.c | 7 +- drivers/staging/ks7010/ks7010_sdio.c | 2 +- drivers/staging/rts5208/rtsx_scsi.c | 10 +- drivers/tty/hvc/hvsi.c | 19 +- drivers/tty/serial/8250/8250_pci.c | 2 +- drivers/tty/serial/8250/8250_port.c | 3 +- drivers/tty/serial/fsl_lpuart.c | 2 +- drivers/tty/serial/jsm/jsm_neo.c | 2 + drivers/tty/serial/jsm/jsm_tty.c | 3 + drivers/tty/serial/sh-sci.c | 7 +- drivers/tty/tty_io.c | 4 +- drivers/usb/gadget/composite.c | 8 +- drivers/usb/gadget/function/u_ether.c | 5 +- drivers/usb/gadget/udc/at91_udc.c | 4 +- drivers/usb/gadget/udc/bdc/bdc_core.c | 3 +- drivers/usb/gadget/udc/mv_u3d_core.c | 19 +- drivers/usb/host/ehci-orion.c | 8 +- drivers/usb/host/fotg210-hcd.c | 41 ++-- drivers/usb/host/fotg210.h | 5 - drivers/usb/host/ohci-tmio.c | 3 + drivers/usb/host/xhci-rcar.c | 7 + drivers/usb/host/xhci.c | 24 +-- drivers/usb/mtu3/mtu3_gadget.c | 6 +- drivers/usb/musb/musb_dsps.c | 13 +- drivers/usb/phy/phy-fsl-usb.c | 2 + drivers/usb/phy/phy-tahvo.c | 4 +- drivers/usb/phy/phy-twl6030-usb.c | 5 + drivers/usb/serial/mos7720.c | 4 +- drivers/usb/usbip/vhci_hcd.c | 32 +++- drivers/vfio/Kconfig | 2 +- drivers/video/backlight/pwm_bl.c | 54 +++--- drivers/video/fbdev/asiliantfb.c | 3 + drivers/video/fbdev/core/fbmem.c | 6 + drivers/video/fbdev/kyro/fbdev.c | 8 + drivers/video/fbdev/riva/fbdev.c | 3 + fs/btrfs/inode.c | 2 +- fs/btrfs/volumes.c | 3 + fs/cifs/cifs_unicode.c | 9 +- fs/cifs/sess.c | 2 +- fs/crypto/hooks.c | 44 +++++ fs/ext4/symlink.c | 11 +- fs/f2fs/file.c | 4 +- fs/f2fs/gc.c | 4 +- fs/f2fs/namei.c | 11 +- fs/fcntl.c | 5 +- fs/fscache/cookie.c | 14 +- fs/fscache/internal.h | 2 + fs/fscache/main.c | 39 ++++ fs/gfs2/lock_dlm.c | 5 + fs/isofs/inode.c | 27 ++- fs/isofs/isofs.h | 1 - fs/isofs/joliet.c | 4 +- fs/overlayfs/dir.c | 6 +- fs/ubifs/file.c | 12 +- fs/udf/misc.c | 13 +- fs/udf/super.c | 25 ++- fs/userfaultfd.c | 93 +++++----- include/crypto/public_key.h | 4 +- include/linux/bpf_verifier.h | 9 + include/linux/fscrypt_notsupp.h | 6 + include/linux/fscrypt_supp.h | 1 + include/linux/hugetlb.h | 9 + include/linux/list.h | 29 ++- include/linux/memory_hotplug.h | 4 +- include/linux/pci.h | 5 +- include/linux/power/max17042_battery.h | 2 +- include/linux/skbuff.h | 2 +- include/uapi/linux/pkt_sched.h | 2 + include/uapi/linux/serial_reg.h | 1 + kernel/bpf/verifier.c | 175 ++++++++++++------ kernel/events/core.c | 2 +- kernel/fork.c | 1 + kernel/locking/mutex.c | 15 +- kernel/sched/deadline.c | 8 +- kernel/sched/sched.h | 2 + kernel/time/hrtimer.c | 60 +++++- lib/mpi/mpiutil.c | 2 +- lib/test_bpf.c | 13 +- mm/memory_hotplug.c | 4 +- net/9p/trans_xen.c | 4 +- net/bluetooth/cmtp/cmtp.h | 2 +- net/bluetooth/hci_core.c | 14 ++ net/bluetooth/hci_event.c | 108 +++++++---- net/bluetooth/sco.c | 11 +- net/caif/chnl_net.c | 19 +- net/core/flow_dissector.c | 12 +- net/core/net_namespace.c | 18 +- net/dccp/minisocks.c | 2 + net/dsa/slave.c | 12 +- net/ipv4/icmp.c | 23 ++- net/ipv4/ip_gre.c | 9 +- net/ipv4/ip_output.c | 5 +- net/ipv4/route.c | 48 +++-- net/ipv4/tcp_fastopen.c | 3 +- net/ipv4/tcp_input.c | 2 +- net/ipv4/tcp_ipv4.c | 5 +- net/ipv6/netfilter/nf_socket_ipv6.c | 4 +- net/l2tp/l2tp_core.c | 4 +- net/mac80211/tx.c | 4 +- net/netlabel/netlabel_cipso_v4.c | 12 +- net/netlink/af_netlink.c | 4 +- net/sched/sch_cbq.c | 2 +- net/sched/sch_fq_codel.c | 12 +- net/sunrpc/auth_gss/svcauth_gss.c | 2 +- net/tipc/socket.c | 36 +++- net/unix/af_unix.c | 2 +- samples/bpf/test_override_return.sh | 1 + samples/bpf/tracex7_user.c | 5 + security/integrity/ima/Kconfig | 1 - security/integrity/ima/ima_mok.c | 2 +- security/smack/smack_access.c | 17 +- sound/core/pcm_lib.c | 2 +- sound/soc/intel/boards/bytcr_rt5640.c | 9 +- sound/soc/rockchip/rockchip_i2s.c | 35 ++-- sound/usb/quirks.c | 1 + tools/perf/util/machine.c | 1 + tools/testing/selftests/bpf/test_maps.c | 2 +- tools/testing/selftests/bpf/test_verifier.c | 144 ++++++++++++-- tools/thermal/tmon/Makefile | 2 +- virt/kvm/arm/arm.c | 8 + 272 files changed, 1866 insertions(+), 915 deletions(-) -- 2.25.1

1 280

[PATCH openEuler-1.0-LTS v2 0/9] ascend inclusion mpam feature
by Wang Xingang 27 Sep '21

27 Sep '21

From: Xingang Wang <wangxingang5(a)huawei.com> v1->v2: - fix bugs and review suggestions, add result check when update rmid This series patches introduce mpam feature for ascend: - 1. The mpam driver resctrlfs need to add write interface for rmid, so that the rmid can be configured from userspace. - 2. Add support to configure SMMU mpam from svm. bugzilla: https://gitee.com/openeuler/kernel/issues/I49RB2 Xingang Wang (9): iommu/arm-smmu-v3: Add support to configure mpam in STE/CD context iommu/arm-smmu-v3: Add support to get SMMU mpam configuration iommu/arm-smmu-v3: Add support to enable/disable SMMU user_mpam_en svm: Add support to get svm mpam configuration svm: Add support to set svm mpam configuration svm: Add svm_set_user_mpam_en to enable/disable mpam for smmu mpam: enable rdt_mon_capable for mbw monitor mpam: Add support for group rmid modify mpam: update monitor rmid and group configuration arch/arm64/kernel/mpam/mpam_ctrlmon.c | 33 ++-- arch/arm64/kernel/mpam/mpam_resctrl.c | 138 +++++++++++++- arch/arm64/kernel/mpam/mpam_setup.c | 1 + drivers/char/svm.c | 228 ++++++++++++++++++++++ drivers/iommu/arm-smmu-v3-context.c | 42 ++++ drivers/iommu/arm-smmu-v3.c | 265 ++++++++++++++++++++++++++ include/linux/ascend_smmu.h | 21 ++ 7 files changed, 709 insertions(+), 19 deletions(-) create mode 100644 include/linux/ascend_smmu.h -- 2.19.1

2 10

[PATCH kernel-4.19 1/4] block: fix race between adding/removing rq qos and normal IO
by Yang Yingliang 27 Sep '21

27 Sep '21

From: Ming Lei <ming.lei(a)redhat.com> mainline inclusion from mainline-v5.14 commit 2cafe29a8d03f02a3d16193bdaae2f3e82a423f9 category: bugfix bugzilla: 182135 CVE: NA ------------------------------------------------- Yi reported several kernel panics on: [16687.001777] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000008 ... [16687.163549] pc : __rq_qos_track+0x38/0x60 or [ 997.690455] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000020 ... [ 997.850347] pc : __rq_qos_done+0x2c/0x50 Turns out it is caused by race between adding rq qos(wbt) and normal IO because rq_qos_add can be run when IO is being submitted, fix this issue by freezing queue before adding/deleting rq qos to queue. rq_qos_exit() needn't to freeze queue because it is called after queue has been frozen. iolatency calls rq_qos_add() during allocating queue, so freezing won't add delay because queue usage refcount works at atomic mode at that time. iocost calls rq_qos_add() when writing cgroup attribute file, that is fine to freeze queue at that time since we usually freeze queue when storing to queue sysfs attribute, meantime iocost only exists on the root cgroup. wbt_init calls it in blk_register_queue() and queue sysfs attribute store(queue_wb_lat_store() when write it 1st time in case of !BLK_WBT_MQ), the following patch will speedup the queue freezing in wbt_init. Reported-by: Yi Zhang <yi.zhang(a)redhat.com> Cc: Bart Van Assche <bvanassche(a)acm.org> Signed-off-by: Ming Lei <ming.lei(a)redhat.com> Reviewed-by: Bart Van Assche <bvanassche(a)acm.org> Tested-by: Yi Zhang <yi.zhang(a)redhat.com> Link: https://lore.kernel.org/r/20210609015822.103433-2-ming.lei@redhat.com Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Conflict: block/blk-rq-qos.h Signed-off-by: Laibin Qiu <qiulaibin(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- block/blk-rq-qos.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h index efb3e5430ce3c..7c36442ba7f7f 100644 --- a/block/blk-rq-qos.h +++ b/block/blk-rq-qos.h @@ -6,6 +6,7 @@ #include <linux/blk_types.h> #include <linux/atomic.h> #include <linux/wait.h> +#include <linux/blk-mq.h> enum rq_qos_id { RQ_QOS_WBT, @@ -77,20 +78,43 @@ static inline void rq_wait_init(struct rq_wait *rq_wait) static inline void rq_qos_add(struct request_queue *q, struct rq_qos *rqos) { + /* + * No IO can be in-flight when adding rqos, so freeze queue, which + * is fine since we only support rq_qos for blk-mq queue. + * + * Reuse ->queue_lock for protecting against other concurrent + * rq_qos adding/deleting + */ + blk_mq_freeze_queue(q); + + spin_lock_irq(q->queue_lock); rqos->next = q->rq_qos; q->rq_qos = rqos; + spin_unlock_irq(q->queue_lock); + + blk_mq_unfreeze_queue(q); } static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos) { struct rq_qos **cur; + /* + * See comment in rq_qos_add() about freezing queue & using + * ->queue_lock. + */ + blk_mq_freeze_queue(q); + + spin_lock_irq(q->queue_lock); for (cur = &q->rq_qos; *cur; cur = &(*cur)->next) { if (*cur == rqos) { *cur = rqos->next; break; } } + spin_unlock_irq(q->queue_lock); + + blk_mq_unfreeze_queue(q); } bool rq_wait_inc_below(struct rq_wait *rq_wait, unsigned int limit); -- 2.25.1

1 3

[PATCH openEuler-1.0-LTS] pid: fix imbalanced calling of cgroup_threadgroup_change_begin/end()
by Yang Yingliang 26 Sep '21

26 Sep '21

hulk inclusion category: bugfix bugzilla: 182255 CVE: NA ------------------------------------------------- cgroup_threadgroup_change_begin() is called after allocating futex_exit_mutex, cgroup_threadgroup_change_end() don't need be called on error path of allocating futex_exit_mutex. Fixes: 04d0e96b230ac ("futex: sched: fix kabi broken in task_struct") Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- kernel/fork.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/fork.c b/kernel/fork.c index adc8fc99246fb..e17aaa526c593 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2176,10 +2176,10 @@ static __latent_entropy struct task_struct *copy_process( write_unlock_irq(&tasklist_lock); cgroup_cancel_fork(p); bad_fork_free_futex_mutex: + cgroup_threadgroup_change_end(current); kfree(p->futex_exit_mutex); p->futex_exit_mutex = NULL; bad_fork_free_pid: - cgroup_threadgroup_change_end(current); if (pid != &init_struct_pid) free_pid(pid); bad_fork_cleanup_thread: -- 2.25.1

1 0

[PATCH kernel_4.19 v2 01/30] delayacct: track delays from thrashing cache pages
by Liu Xinpeng 26 Sep '21

26 Sep '21

mainline inclusion from mainline-v5.4 commit b1d29ba82cf2bc784f4c963ddd6a2cf29e229b33 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I47QS2 CVE: NA -------------------------------- Delay accounting already measures the time a task spends in direct reclaim and waiting for swapin, but in low memory situations tasks spend can spend a significant amount of their time waiting on thrashing page cache. This isn't tracked right now. To know the full impact of memory contention on an individual task, measure the delay when waiting for a recently evicted active cache page to read back into memory. Also update tools/accounting/getdelays.c: [hannes@computer accounting]$ sudo ./getdelays -d -p 1 print delayacct stats ON PID 1 CPU count real total virtual total delay total delay average 50318 745000000 847346785 400533713 0.008ms IO count delay total delay average 435 122601218 0ms SWAP count delay total delay average 0 0 0ms RECLAIM count delay total delay average 0 0 0ms THRASHING count delay total delay average 19 12621439 0ms Link: http://lkml.kernel.org/r/20180828172258.3185-4-hannes@cmpxchg.org Signed-off-by: Johannes Weiner <hannes(a)cmpxchg.org> Acked-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Tested-by: Daniel Drake <drake(a)endlessm.com> Tested-by: Suren Baghdasaryan <surenb(a)google.com> Cc: Christopher Lameter <cl(a)linux.com> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Johannes Weiner <jweiner(a)fb.com> Cc: Mike Galbraith <efault(a)gmx.de> Cc: Peter Enderborg <peter.enderborg(a)sony.com> Cc: Randy Dunlap <rdunlap(a)infradead.org> Cc: Shakeel Butt <shakeelb(a)google.com> Cc: Tejun Heo <tj(a)kernel.org> Cc: Vinayak Menon <vinmenon(a)codeaurora.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Liu Xinpeng <liuxp11(a)chinatelecom.cn> Signed-off-by: Ctyun Kernel <ctyuncommiter01(a)chinatelecom.cn> --- include/linux/delayacct.h | 23 +++++++++++++++++++++++ include/uapi/linux/taskstats.h | 6 +++++- kernel/delayacct.c | 15 +++++++++++++++ mm/filemap.c | 11 +++++++++++ tools/accounting/getdelays.c | 8 +++++++- 5 files changed, 61 insertions(+), 2 deletions(-) diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 31c865d..577d1b2 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -57,7 +57,12 @@ struct task_delay_info { u64 freepages_start; u64 freepages_delay; /* wait for memory reclaim */ + + u64 thrashing_start; + u64 thrashing_delay; /* wait for thrashing page */ + u32 freepages_count; /* total count of memory reclaim */ + u32 thrashing_count; /* total count of thrash waits */ }; #endif @@ -76,6 +81,8 @@ struct task_delay_info { extern __u64 __delayacct_blkio_ticks(struct task_struct *); extern void __delayacct_freepages_start(void); extern void __delayacct_freepages_end(void); +extern void __delayacct_thrashing_start(void); +extern void __delayacct_thrashing_end(void); static inline int delayacct_is_task_waiting_on_io(struct task_struct *p) { @@ -156,6 +163,18 @@ static inline void delayacct_freepages_end(void) __delayacct_freepages_end(); } +static inline void delayacct_thrashing_start(void) +{ + if (current->delays) + __delayacct_thrashing_start(); +} + +static inline void delayacct_thrashing_end(void) +{ + if (current->delays) + __delayacct_thrashing_end(); +} + #else static inline void delayacct_set_flag(int flag) {} @@ -182,6 +201,10 @@ static inline void delayacct_freepages_start(void) {} static inline void delayacct_freepages_end(void) {} +static inline void delayacct_thrashing_start(void) +{} +static inline void delayacct_thrashing_end(void) +{} #endif /* CONFIG_TASK_DELAY_ACCT */ diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h index b7aa7bb..5e8ca16 100644 --- a/include/uapi/linux/taskstats.h +++ b/include/uapi/linux/taskstats.h @@ -34,7 +34,7 @@ */ -#define TASKSTATS_VERSION 8 +#define TASKSTATS_VERSION 9 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -164,6 +164,10 @@ struct taskstats { /* Delay waiting for memory reclaim */ __u64 freepages_count; __u64 freepages_delay_total; + + /* Delay waiting for thrashing page */ + __u64 thrashing_count; + __u64 thrashing_delay_total; }; diff --git a/kernel/delayacct.c b/kernel/delayacct.c index ca8ac28..2a12b98 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -135,9 +135,12 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) d->swapin_delay_total = (tmp < d->swapin_delay_total) ? 0 : tmp; tmp = d->freepages_delay_total + tsk->delays->freepages_delay; d->freepages_delay_total = (tmp < d->freepages_delay_total) ? 0 : tmp; + tmp = d->thrashing_delay_total + tsk->delays->thrashing_delay; + d->thrashing_delay_total = (tmp < d->thrashing_delay_total) ? 0 : tmp; d->blkio_count += tsk->delays->blkio_count; d->swapin_count += tsk->delays->swapin_count; d->freepages_count += tsk->delays->freepages_count; + d->thrashing_count += tsk->delays->thrashing_count; raw_spin_unlock_irqrestore(&tsk->delays->lock, flags); return 0; @@ -169,3 +172,15 @@ void __delayacct_freepages_end(void) &current->delays->freepages_count); } +void __delayacct_thrashing_start(void) +{ + current->delays->thrashing_start = ktime_get_ns(); +} + +void __delayacct_thrashing_end(void) +{ + delayacct_end(&current->delays->lock, + &current->delays->thrashing_start, + &current->delays->thrashing_delay, + &current->delays->thrashing_count); +} diff --git a/mm/filemap.c b/mm/filemap.c index 4cf4b09..6c964d8 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -36,6 +36,7 @@ #include <linux/cleancache.h> #include <linux/shmem_fs.h> #include <linux/rmap.h> +#include <linux/delayacct.h> #include "internal.h" #define CREATE_TRACE_POINTS @@ -1183,8 +1184,15 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, { struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; + bool thrashing = false; int ret = 0; + if (bit_nr == PG_locked && !PageSwapBacked(page) && + !PageUptodate(page) && PageWorkingset(page)) { + delayacct_thrashing_start(); + thrashing = true; + } + init_wait(wait); wait->flags = lock ? WQ_FLAG_EXCLUSIVE : 0; wait->func = wake_page_function; @@ -1223,6 +1231,9 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, finish_wait(q, wait); + if (thrashing) + delayacct_thrashing_end(); + /* * A signal could leave PageWaiters set. Clearing it here if * !waitqueue_active would be possible (by open-coding finish_wait), diff --git a/tools/accounting/getdelays.c b/tools/accounting/getdelays.c index 6bf6a20..5ef1c15 100644 --- a/tools/accounting/getdelays.c +++ b/tools/accounting/getdelays.c @@ -203,6 +203,8 @@ static void print_delayacct(struct taskstats *t) "SWAP %15s%15s%15s\n" " %15llu%15llu%15llums\n" "RECLAIM %12s%15s%15s\n" + " %15llu%15llu%15llums\n" + "THRASHING%12s%15s%15s\n" " %15llu%15llu%15llums\n", "count", "real total", "virtual total", "delay total", "delay average", @@ -222,7 +224,11 @@ static void print_delayacct(struct taskstats *t) "count", "delay total", "delay average", (unsigned long long)t->freepages_count, (unsigned long long)t->freepages_delay_total, - average_ms(t->freepages_delay_total, t->freepages_count)); + average_ms(t->freepages_delay_total, t->freepages_count), + "count", "delay total", "delay average", + (unsigned long long)t->thrashing_count, + (unsigned long long)t->thrashing_delay_total, + average_ms(t->thrashing_delay_total, t->thrashing_count)); } static void task_context_switch_counts(struct taskstats *t) -- 1.8.3.1

3 30

[PATCH v3 OLK-5.10 0/2] spraid: support Ramaxel raid controller
by Yanling Song 24 Sep '21

24 Sep '21

Support Ramaxel raid controller Changes since v2: - Improve IO error handling - Add new functions to get controller's information: firmware version, the ability of chip - Support pass through command of admin Changes since v1: - Add "OLK-5.10" to subject - Add commit header into commit message - Add CONFIG_RAMAXEL_SPRAID in defconfig Yanling Song (2): spraid: support Ramaxel raid controller spraid: Add CONFIG_RAMAXEL_SPRAID in defconfig of arch arm64 and x86 arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + drivers/scsi/Kconfig | 1 + drivers/scsi/Makefile | 1 + drivers/scsi/spraid/Kconfig | 11 + drivers/scsi/spraid/Makefile | 7 + drivers/scsi/spraid/spraid.h | 655 +++++ drivers/scsi/spraid/spraid_main.c | 3616 ++++++++++++++++++++++++ 8 files changed, 4293 insertions(+) create mode 100644 drivers/scsi/spraid/Kconfig create mode 100644 drivers/scsi/spraid/Makefile create mode 100644 drivers/scsi/spraid/spraid.h create mode 100644 drivers/scsi/spraid/spraid_main.c -- 2.17.1

1 2

[PATCH openEuler-1.0-LTS] pid: fix return value when copy_process() failed
by Yang Yingliang 24 Sep '21

24 Sep '21

hulk inclusion category: bugfix bugzilla: 182255 CVE: NA ------------------------------------------------- When allocating futex_exit_mutex fails in copy_process(), it needs return an error code, or it will lead a null-ptr-deref when it's used in get_task_pid(). Fixes: 04d0e96b230ac ("futex: sched: fix kabi broken in task_struct") Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- kernel/fork.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/kernel/fork.c b/kernel/fork.c index b4fee9799c153..adc8fc99246fb 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2000,8 +2000,10 @@ static __latent_entropy struct task_struct *copy_process( #endif futex_init_task(p); p->futex_exit_mutex = kmalloc(sizeof(struct mutex), GFP_KERNEL); - if (!p->futex_exit_mutex) + if (!p->futex_exit_mutex) { + retval = -ENOMEM; goto bad_fork_free_pid; + } mutex_init(p->futex_exit_mutex); /* -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] block: fix NULL pointer in blkcg_drain_queue()
by Yang Yingliang 24 Sep '21

24 Sep '21

From: Laibin Qiu <qiulaibin(a)huawei.com> hulk inclusion category: bugfix bugzilla: 182135 CVE: NA ------------------------------------------------- blkcg_init_queue blk_iolatency_init blk_mq_freeze_queue blk_throtl_drain <- blk_throtl will be initialized later, so q->td is NULL and trigger this NULL pointer BUG. blk_throtl_init The following is the log of the problem. ------------[ cut here ]------------ [ 8.516269] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 [ 8.516296] RIP: 0010:blk_throtl_drain+0x142/0x760 [ 8.520477] Call Trace: [ 8.520477] blkcg_drain_queue+0x90/0x120 [ 8.520477] __blk_drain_queue+0x18a/0x760 [ 8.520477] blk_drain_queue+0x45/0x80 [ 8.520477] blk_freeze_queue+0x58/0x70 [ 8.520477] blk_iolatency_init+0xdc/0x3e7 [ 8.520477] blkcg_init_queue+0x214/0x5e0 [ 8.520477] blk_alloc_queue_node+0x826/0xc10 [ 8.520477] ? ramdisk_size+0x27/0x27 [ 8.520477] brd_alloc+0x118/0x540 [ 8.520477] ? ramdisk_size+0x27/0x27 [ 8.520477] brd_init+0x179/0x4be [ 8.520477] ? do_one_initcall+0x5fe/0x783 [ 8.520477] ? ramdisk_size+0x27/0x27 [ 8.520477] do_one_initcall+0xf7/0x783 [ 8.520477] ? initcall_blacklisted+0x1b0/0x1b0 [ 8.520477] ? __wake_up_common+0x600/0x620 [ 8.520477] ? lock_downgrade+0x720/0x720 [ 8.520477] ? check_preemption_disabled+0x40/0x2a0 [ 8.520477] kernel_init_freeable+0xb34/0xc27 [ 8.520477] ? rest_init+0x41c/0x41c [ 8.520477] kernel_init+0x10/0x1e0 [ 8.520477] ? rest_init+0x41c/0x41c [ 8.520477] ret_from_fork+0x24/0x30 [ 8.520477] Modules linked in: [ 8.520477] Dumping ftrace buffer: [ 8.520477] (ftrace buffer empty) [ 8.520477] ---[ end trace 74cf51ecec6ee7a1 ]--- Fix this by judging whether q->td is NULL. If so, Indicates that the io_throttle module has not been initialized. Fixes: ee3147b403e5e ("block: fix race between adding/removing rq qos and normal IO") Signed-off-by: Laibin Qiu <qiulaibin(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- block/blk-cgroup.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 592befc26584f..9511330bfebc7 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1314,6 +1314,13 @@ void blkcg_drain_queue(struct request_queue *q) if (!q->root_blkg) return; + /* + * @q could be exiting and q->td has not been initialized. + * If so, don't need drain any throttled bios. + */ + if (!q->td) + return; + blk_throtl_drain(q); } -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS 0/9] ascend inclusion mpam feature
by Wang Xingang 24 Sep '21

24 Sep '21

From: Xingang Wang <wangxingang5(a)huawei.com> This series patches introduce mpam feature for ascend: - 1. The mpam driver resctrlfs need to add write interface for rmid, so that the rmid can be configured from userspace. - 2. Add support to configure SMMU mpam from svm. bugzilla: https://gitee.com/openeuler/kernel/issues/I49RB2 Xingang Wang (9): iommu/arm-smmu-v3: Add support to configure mpam in STE/CD context iommu/arm-smmu-v3: Add support to get SMMU mpam configuration iommu/arm-smmu-v3: Add support to enable/disable SMMU user_mpam_en svm: Add support to get svm mpam configuration svm: Add support to set svm mpam configuration svm: Add svm_set_user_mpam_en to enable/disable mpam for smmu mpam: enable rdt_mon_capable for mbw monitor mpam: Add support for group rmid modify mpam: update monitor rmid and group configuration arch/arm64/kernel/mpam/mpam_ctrlmon.c | 33 ++-- arch/arm64/kernel/mpam/mpam_resctrl.c | 104 +++++++++- arch/arm64/kernel/mpam/mpam_setup.c | 1 + drivers/char/svm.c | 227 ++++++++++++++++++++++ drivers/iommu/arm-smmu-v3-context.c | 42 ++++ drivers/iommu/arm-smmu-v3.c | 265 ++++++++++++++++++++++++++ include/linux/ascend_smmu.h | 21 ++ 7 files changed, 674 insertions(+), 19 deletions(-) create mode 100644 include/linux/ascend_smmu.h -- 2.19.1

2 10

[PATCH openEuler-1.0-LTS 1/3] block: fix race between adding/removing rq qos and normal IO
by Yang Yingliang 24 Sep '21

24 Sep '21

From: Ming Lei <ming.lei(a)redhat.com> mainline inclusion from mainline-v5.14 commit 2cafe29a8d03f02a3d16193bdaae2f3e82a423f9 category: bugfix bugzilla: 182135 CVE: NA ------------------------------------------------- Yi reported several kernel panics on: [16687.001777] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000008 ... [16687.163549] pc : __rq_qos_track+0x38/0x60 or [ 997.690455] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000020 ... [ 997.850347] pc : __rq_qos_done+0x2c/0x50 Turns out it is caused by race between adding rq qos(wbt) and normal IO because rq_qos_add can be run when IO is being submitted, fix this issue by freezing queue before adding/deleting rq qos to queue. rq_qos_exit() needn't to freeze queue because it is called after queue has been frozen. iolatency calls rq_qos_add() during allocating queue, so freezing won't add delay because queue usage refcount works at atomic mode at that time. iocost calls rq_qos_add() when writing cgroup attribute file, that is fine to freeze queue at that time since we usually freeze queue when storing to queue sysfs attribute, meantime iocost only exists on the root cgroup. wbt_init calls it in blk_register_queue() and queue sysfs attribute store(queue_wb_lat_store() when write it 1st time in case of !BLK_WBT_MQ), the following patch will speedup the queue freezing in wbt_init. Reported-by: Yi Zhang <yi.zhang(a)redhat.com> Cc: Bart Van Assche <bvanassche(a)acm.org> Signed-off-by: Ming Lei <ming.lei(a)redhat.com> Reviewed-by: Bart Van Assche <bvanassche(a)acm.org> Tested-by: Yi Zhang <yi.zhang(a)redhat.com> Link: https://lore.kernel.org/r/20210609015822.103433-2-ming.lei@redhat.com Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Conflict: block/blk-rq-qos.h Signed-off-by: Laibin Qiu <qiulaibin(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- block/blk-rq-qos.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h index 98caba3e962ee..c99b2facd9ffd 100644 --- a/block/blk-rq-qos.h +++ b/block/blk-rq-qos.h @@ -6,6 +6,7 @@ #include <linux/blk_types.h> #include <linux/atomic.h> #include <linux/wait.h> +#include <linux/blk-mq.h> enum rq_qos_id { RQ_QOS_WBT, @@ -74,20 +75,43 @@ static inline void rq_wait_init(struct rq_wait *rq_wait) static inline void rq_qos_add(struct request_queue *q, struct rq_qos *rqos) { + /* + * No IO can be in-flight when adding rqos, so freeze queue, which + * is fine since we only support rq_qos for blk-mq queue. + * + * Reuse ->queue_lock for protecting against other concurrent + * rq_qos adding/deleting + */ + blk_mq_freeze_queue(q); + + spin_lock_irq(q->queue_lock); rqos->next = q->rq_qos; q->rq_qos = rqos; + spin_unlock_irq(q->queue_lock); + + blk_mq_unfreeze_queue(q); } static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos) { struct rq_qos **cur; + /* + * See comment in rq_qos_add() about freezing queue & using + * ->queue_lock. + */ + blk_mq_freeze_queue(q); + + spin_lock_irq(q->queue_lock); for (cur = &q->rq_qos; *cur; cur = &(*cur)->next) { if (*cur == rqos) { *cur = rqos->next; break; } } + spin_unlock_irq(q->queue_lock); + + blk_mq_unfreeze_queue(q); } bool rq_wait_inc_below(struct rq_wait *rq_wait, unsigned int limit); -- 2.25.1

1 2

[PATCH openEuler-1.0-LTS] Fix incorrect call to free srb in qla2xxx_mqueuecommand()
by yinxiujiang 23 Sep '21

23 Sep '21

From: yin-xiujiang <yinxiujiang(a)kylinos.cn> Fix incorrect call to free srb in qla2xxx_mqueuecommand(), as srb is now allocated by upper layers. This fixes smatch warning of srb unintended free. Signed-off-by: yin-xiujiang <yinxiujiang(a)kylinos.cn> --- drivers/scsi/qla2xxx/qla_os.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index bfbf213b15c0..8e9d386146ac 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -1028,8 +1028,6 @@ qla2xxx_mqueuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd, if (rval != QLA_SUCCESS) { ql_dbg(ql_dbg_io + ql_dbg_verbose, vha, 0x3078, "Start scsi failed rval=%d for cmd=%p.\n", rval, cmd); - if (rval == QLA_INTERFACE_ERROR) - goto qc24_free_sp_fail_command; goto qc24_host_busy_free_sp; } @@ -1044,11 +1042,6 @@ qla2xxx_mqueuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd, qc24_target_busy: return SCSI_MLQUEUE_TARGET_BUSY; -qc24_free_sp_fail_command: - sp->free(sp); - CMD_SP(cmd) = NULL; - qla2xxx_rel_qpair_sp(sp->qpair, sp); - qc24_fail_command: cmd->scsi_done(cmd); -- 2.27.0

2 1

[PATCH openEuler-1.0-LTS 0/34] arm64 support kexec -l -s
by xuhuijie 23 Sep '21

23 Sep '21

support arm64 kexec_file(23): kexec_file: add kexec_file_load system call to unistd.h kexec_file: make kexec_image_post_load_cleanup_default() global kexec_file: drop arch_kexec_mem_walk() kexec_file: factor out memblock-based arch_kexec_walk_mem() kexec_file: kexec_walk_memblock() only walks a dedicated region at kdump kexec_file: add image head flag definitions kexec_file: cpufeature: add MMFR0 helper functions kexec_file: enable KEXEC_FILE config kexec_file: load initrd and device-tree kexec_file: allow for loading Image-format kernel kexec_file: invoke the kernel without purgatory kexec_file: pe.h: remove message[] from mz header definition kexec_file: add kernel signature verification support kexec_file: add kaslr support kexec_file: forbid kdump via kexec_file_load() kexec_file: include fdt_addresses.c kexec_file: include linux/vmalloc.h kexec_file: Refactor setup_dtb() to consolidate error checking kexec_file: add rng-seed support kexec_file: add crash dump support kexec_file: Update to upstream version v1.5.0-23-g87963ee20693 kexec_file: handle empty command-line kexec_file: fix memory leakage in create_dtb() when fdt_open_into() fails support platform keyring(10): integrity: Define a trusted platform keyring integrity: Load certs to the platform keyring integrity: Add EFI signature data types integrity: Add an EFI signature blob parser integrity: Import certificates from UEFI Secure Boot integrity: Allow the "db" UEFI variable to be suppressed integrity: Support platform keyring for kernel appraisal integrity, KEYS: add a reference to platform keyring integrity: Make use of platform keyring for signature verify integrity: Fix __integrity_init_keyring() section mismatch fix kabi(1): kexec_file: fix kabi because of the new system call sys_kexec_file_load --- arch/arm64/Kconfig | 33 ++ arch/arm64/include/asm/cpufeature.h | 48 +++ arch/arm64/include/asm/image.h | 59 +++ arch/arm64/include/asm/kexec.h | 23 ++ arch/arm64/kernel/Makefile | 3 +- arch/arm64/kernel/cpu-reset.S | 8 +- arch/arm64/kernel/head.S | 3 +- arch/arm64/kernel/image.h | 21 +- arch/arm64/kernel/kexec_image.c | 126 +++++++ arch/arm64/kernel/machine_kexec.c | 12 +- arch/arm64/kernel/machine_kexec_file.c | 342 ++++++++++++++++++ arch/arm64/kernel/relocate_kernel.S | 3 +- arch/powerpc/kernel/machine_kexec_file_64.c | 54 --- arch/s390/kernel/machine_kexec_file.c | 10 - arch/x86/kernel/kexec-bzimage64.c | 14 +- certs/system_keyring.c | 23 +- include/keys/system_keyring.h | 8 + include/linux/efi.h | 34 ++ include/linux/kexec.h | 15 +- include/linux/pe.h | 2 +- include/linux/verification.h | 1 + include/uapi/linux/kexec.h | 1 + kernel/kexec.c | 10 + kernel/kexec_file.c | 160 +++++++- lib/Makefile | 2 +- lib/fdt_addresses.c | 2 + scripts/dtc/libfdt/fdt_addresses.c | 47 +++ scripts/dtc/libfdt/libfdt.h | 61 ++++ security/integrity/Kconfig | 11 + security/integrity/Makefile | 5 + security/integrity/digsig.c | 114 ++++-- security/integrity/ima/ima_appraise.c | 14 +- security/integrity/integrity.h | 23 +- .../integrity/platform_certs/efi_parser.c | 108 ++++++ security/integrity/platform_certs/load_uefi.c | 194 ++++++++++ .../platform_certs/platform_keyring.c | 58 +++ 36 files changed, 1518 insertions(+), 134 deletions(-) create mode 100644 arch/arm64/include/asm/image.h create mode 100644 arch/arm64/kernel/kexec_image.c create mode 100644 arch/arm64/kernel/machine_kexec_file.c create mode 100644 lib/fdt_addresses.c create mode 100644 security/integrity/platform_certs/efi_parser.c create mode 100644 security/integrity/platform_certs/load_uefi.c create mode 100644 security/integrity/platform_certs/platform_keyring.c diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 9dfbd052b..5381d21bb 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -957,6 +957,39 @@ config KEXEC but it is independent of the system firmware. And like a reboot you can start any kernel with it, not just Linux. +config KEXEC_FILE + bool "kexec file based system call" + select KEXEC_CORE + help + This is new version of kexec system call. This system call is + file based and takes file descriptors as system call argument + for kernel and initramfs as opposed to list of segments as + accepted by previous system call. + +config KEXEC_VERIFY_SIG + bool "Verify kernel signature during kexec_file_load() syscall" + depends on KEXEC_FILE + help + Select this option to verify a signature with loaded kernel + image. If configured, any attempt of loading a image without + valid signature will fail. + + In addition to that option, you need to enable signature + verification for the corresponding kernel image type being + loaded in order for this to work. + +config KEXEC_IMAGE_VERIFY_SIG + bool "Enable Image signature verification support" + default y + depends on KEXEC_VERIFY_SIG + depends on EFI && SIGNED_PE_FILE_VERIFICATION + help + Enable Image signature verification support. + +comment "Support for PE file signature verification disabled" + depends on KEXEC_VERIFY_SIG + depends on !EFI || !SIGNED_PE_FILE_VERIFICATION + config CRASH_DUMP bool "Build kdump crash kernel" help diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index c43d02365..211aa994b 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -497,11 +497,59 @@ static inline bool system_supports_32bit_el0(void) return cpus_have_const_cap(ARM64_HAS_32BIT_EL0); } +static inline bool system_supports_4kb_granule(void) +{ + u64 mmfr0; + u32 val; + + mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); + val = cpuid_feature_extract_unsigned_field(mmfr0, + ID_AA64MMFR0_TGRAN4_SHIFT); + + return val == ID_AA64MMFR0_TGRAN4_SUPPORTED; +} + +static inline bool system_supports_64kb_granule(void) +{ + u64 mmfr0; + u32 val; + + mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); + val = cpuid_feature_extract_unsigned_field(mmfr0, + ID_AA64MMFR0_TGRAN64_SHIFT); + + return val == ID_AA64MMFR0_TGRAN64_SUPPORTED; +} + +static inline bool system_supports_16kb_granule(void) +{ + u64 mmfr0; + u32 val; + + mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); + val = cpuid_feature_extract_unsigned_field(mmfr0, + ID_AA64MMFR0_TGRAN16_SHIFT); + + return val == ID_AA64MMFR0_TGRAN16_SUPPORTED; +} + static inline bool system_supports_mixed_endian_el0(void) { return id_aa64mmfr0_mixed_endian_el0(read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1)); } +static inline bool system_supports_mixed_endian(void) +{ + u64 mmfr0; + u32 val; + + mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); + val = cpuid_feature_extract_unsigned_field(mmfr0, + ID_AA64MMFR0_BIGENDEL_SHIFT); + + return val == 0x1; +} + static inline bool system_supports_fpsimd(void) { return !cpus_have_const_cap(ARM64_HAS_NO_FPSIMD); diff --git a/arch/arm64/include/asm/image.h b/arch/arm64/include/asm/image.h new file mode 100644 index 000000000..e2c27a227 --- /dev/null +++ b/arch/arm64/include/asm/image.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __ASM_IMAGE_H +#define __ASM_IMAGE_H + +#define ARM64_IMAGE_MAGIC "ARM\x64" + +#define ARM64_IMAGE_FLAG_BE_SHIFT 0 +#define ARM64_IMAGE_FLAG_PAGE_SIZE_SHIFT (ARM64_IMAGE_FLAG_BE_SHIFT + 1) +#define ARM64_IMAGE_FLAG_PHYS_BASE_SHIFT \ + (ARM64_IMAGE_FLAG_PAGE_SIZE_SHIFT + 2) +#define ARM64_IMAGE_FLAG_BE_MASK 0x1 +#define ARM64_IMAGE_FLAG_PAGE_SIZE_MASK 0x3 +#define ARM64_IMAGE_FLAG_PHYS_BASE_MASK 0x1 + +#define ARM64_IMAGE_FLAG_LE 0 +#define ARM64_IMAGE_FLAG_BE 1 +#define ARM64_IMAGE_FLAG_PAGE_SIZE_4K 1 +#define ARM64_IMAGE_FLAG_PAGE_SIZE_16K 2 +#define ARM64_IMAGE_FLAG_PAGE_SIZE_64K 3 +#define ARM64_IMAGE_FLAG_PHYS_BASE 1 + +#ifndef __ASSEMBLY__ + +#define arm64_image_flag_field(flags, field) \ + (((flags) >> field##_SHIFT) & field##_MASK) + +/* + * struct arm64_image_header - arm64 kernel image header + * See Documentation/arm64/booting.txt for details + * + * @code0: Executable code, or + * @mz_header alternatively used for part of MZ header + * @code1: Executable code + * @text_offset: Image load offset + * @image_size: Effective Image size + * @flags: kernel flags + * @reserved: reserved + * @magic: Magic number + * @reserved5: reserved, or + * @pe_header: alternatively used for PE COFF offset + */ + +struct arm64_image_header { + __le32 code0; + __le32 code1; + __le64 text_offset; + __le64 image_size; + __le64 flags; + __le64 res2; + __le64 res3; + __le64 res4; + __le32 magic; + __le32 res5; +}; + +#endif /* __ASSEMBLY__ */ + +#endif /* __ASM_IMAGE_H */ diff --git a/arch/arm64/include/asm/kexec.h b/arch/arm64/include/asm/kexec.h index 30ab1fa34..286950227 100644 --- a/arch/arm64/include/asm/kexec.h +++ b/arch/arm64/include/asm/kexec.h @@ -101,6 +101,29 @@ static inline void crash_prepare_suspend(void) {} static inline void crash_post_resume(void) {} #endif +#ifdef CONFIG_KEXEC_FILE +#define ARCH_HAS_KIMAGE_ARCH + +struct kimage_arch { + void *dtb; + unsigned long dtb_mem; + /* Core ELF header buffer */ + void *elf_headers; + unsigned long elf_headers_mem; + unsigned long elf_headers_sz; +}; + +extern const struct kexec_file_ops kexec_image_ops; + +struct kimage; + +extern int arch_kimage_file_post_load_cleanup(struct kimage *image); +extern int load_other_segments(struct kimage *image, + unsigned long kernel_load_addr, unsigned long kernel_size, + char *initrd, unsigned long initrd_len, + char *cmdline); +#endif + void machine_kexec_mask_interrupts(void); #endif /* __ASSEMBLY__ */ diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index fe759f364..2e21303b6 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -54,8 +54,9 @@ arm64-obj-$(CONFIG_ARM64_ACPI_PARKING_PROTOCOL) += acpi_parking_protocol.o arm64-obj-$(CONFIG_PARAVIRT) += paravirt.o paravirt-spinlocks.o arm64-obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o arm64-obj-$(CONFIG_HIBERNATION) += hibernate.o hibernate-asm.o -arm64-obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o \ +arm64-obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o relocate_kernel.o \ cpu-reset.o +arm64-obj-$(CONFIG_KEXEC_FILE) += machine_kexec_file.o kexec_image.o arm64-obj-$(CONFIG_ARM64_CPU_PARK) += cpu-park.o arm64-obj-$(CONFIG_ARM64_RELOC_TEST) += arm64-reloc-test.o arm64-reloc-test-y := reloc_test_core.o reloc_test_syms.o diff --git a/arch/arm64/kernel/cpu-reset.S b/arch/arm64/kernel/cpu-reset.S index 8021b46c9..a2be30275 100644 --- a/arch/arm64/kernel/cpu-reset.S +++ b/arch/arm64/kernel/cpu-reset.S @@ -22,11 +22,11 @@ * __cpu_soft_restart(el2_switch, entry, arg0, arg1, arg2) - Helper for * cpu_soft_restart. * - * @el2_switch: Flag to indicate a swich to EL2 is needed. + * @el2_switch: Flag to indicate a switch to EL2 is needed. * @entry: Location to jump to for soft reset. - * arg0: First argument passed to @entry. - * arg1: Second argument passed to @entry. - * arg2: Third argument passed to @entry. + * arg0: First argument passed to @entry. (relocation list) + * arg1: Second argument passed to @entry.(physical kernel entry) + * arg2: Third argument passed to @entry. (physical dtb address) * * Put the CPU into the same state as it would be if it had been reset, and * branch to what would be the reset vector. It must be executed with the diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 34bd0790d..5edfb9cfd 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -31,6 +31,7 @@ #include <asm/cache.h> #include <asm/cputype.h> #include <asm/elf.h> +#include <asm/image.h> #include <asm/kernel-pgtable.h> #include <asm/kvm_arm.h> #include <asm/memory.h> @@ -91,7 +92,7 @@ _head: .quad 0 // reserved .quad 0 // reserved .quad 0 // reserved - .ascii "ARM\x64" // Magic number + .ascii ARM64_IMAGE_MAGIC // Magic number #ifdef CONFIG_EFI .long pe_header - _head // Offset to the PE header. diff --git a/arch/arm64/kernel/image.h b/arch/arm64/kernel/image.h index eff6a564a..b22e8ad07 100644 --- a/arch/arm64/kernel/image.h +++ b/arch/arm64/kernel/image.h @@ -15,13 +15,15 @@ * You should have received a copy of the GNU General Public License * along with this program. If not, see <http://www.gnu.org/licenses/>. */ -#ifndef __ASM_IMAGE_H -#define __ASM_IMAGE_H +#ifndef __ARM64_KERNEL_IMAGE_H +#define __ARM64_KERNEL_IMAGE_H #ifndef LINKER_SCRIPT #error This file should only be included in vmlinux.lds.S #endif +#include <asm/image.h> + /* * There aren't any ELF relocations we can use to endian-swap values known only * at link time (e.g. the subtraction of two symbol addresses), so we must get @@ -47,19 +49,22 @@ sym##_lo32 = DATA_LE32((data) & 0xffffffff); \ sym##_hi32 = DATA_LE32((data) >> 32) +#define __HEAD_FLAG(field) (__HEAD_FLAG_##field << \ + ARM64_IMAGE_FLAG_##field##_SHIFT) + #ifdef CONFIG_CPU_BIG_ENDIAN -#define __HEAD_FLAG_BE 1 +#define __HEAD_FLAG_BE ARM64_IMAGE_FLAG_BE #else -#define __HEAD_FLAG_BE 0 +#define __HEAD_FLAG_BE ARM64_IMAGE_FLAG_LE #endif #define __HEAD_FLAG_PAGE_SIZE ((PAGE_SHIFT - 10) / 2) #define __HEAD_FLAG_PHYS_BASE 1 -#define __HEAD_FLAGS ((__HEAD_FLAG_BE << 0) | \ - (__HEAD_FLAG_PAGE_SIZE << 1) | \ - (__HEAD_FLAG_PHYS_BASE << 3)) +#define __HEAD_FLAGS (__HEAD_FLAG(BE) | \ + __HEAD_FLAG(PAGE_SIZE) | \ + __HEAD_FLAG(PHYS_BASE)) /* * These will output as part of the Image header, which should be little-endian @@ -113,4 +118,4 @@ __efistub_screen_info = screen_info; #endif -#endif /* __ASM_IMAGE_H */ +#endif /* __ARM64_KERNEL_IMAGE_H */ diff --git a/arch/arm64/kernel/kexec_image.c b/arch/arm64/kernel/kexec_image.c new file mode 100644 index 000000000..1ad1d5f8f --- /dev/null +++ b/arch/arm64/kernel/kexec_image.c @@ -0,0 +1,126 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Kexec image loader + + * Copyright (C) 2018 Linaro Limited + * Author: AKASHI Takahiro <takahiro.akashi(a)linaro.org> + */ + +#define pr_fmt(fmt) "kexec_file(Image): " fmt + +#include <linux/err.h> +#include <linux/errno.h> +#include <linux/kernel.h> +#include <linux/kexec.h> +#include <linux/pe.h> +#include <linux/string.h> +#include <linux/verification.h> +#include <asm/byteorder.h> +#include <asm/cpufeature.h> +#include <asm/image.h> +#include <asm/memory.h> + +static int image_probe(const char *kernel_buf, unsigned long kernel_len) +{ + const struct arm64_image_header *h = + (const struct arm64_image_header *)(kernel_buf); + + if (!h || (kernel_len < sizeof(*h))) + return -EINVAL; + + if (memcmp(&h->magic, ARM64_IMAGE_MAGIC, sizeof(h->magic))) + return -EINVAL; + + return 0; +} + +static void *image_load(struct kimage *image, + char *kernel, unsigned long kernel_len, + char *initrd, unsigned long initrd_len, + char *cmdline, unsigned long cmdline_len) +{ + struct arm64_image_header *h; + u64 flags, value; + bool be_image, be_kernel; + struct kexec_buf kbuf; + unsigned long text_offset; + struct kexec_segment *kernel_segment; + int ret; + + /* + * We require a kernel with an unambiguous Image header. Per + * Documentation/booting.txt, this is the case when image_size + * is non-zero (practically speaking, since v3.17). + */ + h = (struct arm64_image_header *)kernel; + if (!h->image_size) + return ERR_PTR(-EINVAL); + + /* Check cpu features */ + flags = le64_to_cpu(h->flags); + be_image = arm64_image_flag_field(flags, ARM64_IMAGE_FLAG_BE); + be_kernel = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN); + if ((be_image != be_kernel) && !system_supports_mixed_endian()) + return ERR_PTR(-EINVAL); + + value = arm64_image_flag_field(flags, ARM64_IMAGE_FLAG_PAGE_SIZE); + if (((value == ARM64_IMAGE_FLAG_PAGE_SIZE_4K) && + !system_supports_4kb_granule()) || + ((value == ARM64_IMAGE_FLAG_PAGE_SIZE_64K) && + !system_supports_64kb_granule()) || + ((value == ARM64_IMAGE_FLAG_PAGE_SIZE_16K) && + !system_supports_16kb_granule())) + return ERR_PTR(-EINVAL); + + /* Load the kernel */ + kbuf.image = image; + kbuf.buf_min = 0; + kbuf.buf_max = ULONG_MAX; + kbuf.top_down = false; + + kbuf.buffer = kernel; + kbuf.bufsz = kernel_len; + kbuf.mem = 0; + kbuf.memsz = le64_to_cpu(h->image_size); + text_offset = le64_to_cpu(h->text_offset); + kbuf.buf_align = MIN_KIMG_ALIGN; + + /* Adjust kernel segment with TEXT_OFFSET */ + kbuf.memsz += text_offset; + + ret = kexec_add_buffer(&kbuf); + if (ret) + return ERR_PTR(ret); + + kernel_segment = &image->segment[image->nr_segments - 1]; + kernel_segment->mem += text_offset; + kernel_segment->memsz -= text_offset; + image->start = kernel_segment->mem; + + pr_debug("Loaded kernel at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + kernel_segment->mem, kbuf.bufsz, + kernel_segment->memsz); + + /* Load additional data */ + ret = load_other_segments(image, + kernel_segment->mem, kernel_segment->memsz, + initrd, initrd_len, cmdline); + + return ERR_PTR(ret); +} + +#ifdef CONFIG_KEXEC_IMAGE_VERIFY_SIG +static int image_verify_sig(const char *kernel, unsigned long kernel_len) +{ + return verify_pefile_signature(kernel, kernel_len, NULL, + VERIFYING_KEXEC_PE_SIGNATURE); +} +#endif + +const struct kexec_file_ops kexec_image_ops = { + .probe = image_probe, + .load = image_load, +#ifdef CONFIG_KEXEC_IMAGE_VERIFY_SIG + .verify_sig = image_verify_sig, +#endif +}; diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c index b41d6d482..213d0053e 100644 --- a/arch/arm64/kernel/machine_kexec.c +++ b/arch/arm64/kernel/machine_kexec.c @@ -214,9 +214,17 @@ void machine_kexec(struct kimage *kimage) * uses physical addressing to relocate the new image to its final * position and transfers control to the image entry point when the * relocation is complete. + * In kexec case, kimage->start points to purgatory assuming that + * kernel entry and dtb address are embedded in purgatory by + * userspace (kexec-tools). + * In kexec_file case, the kernel starts directly without purgatory. */ - - cpu_soft_restart(reboot_code_buffer_phys, kimage->head, kimage->start, 0); + cpu_soft_restart(reboot_code_buffer_phys, kimage->head, kimage->start, +#ifdef CONFIG_KEXEC_FILE + kimage->arch.dtb_mem); +#else + 0); +#endif BUG(); /* Should never get here. */ } diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c new file mode 100644 index 000000000..ec3b72dc0 --- /dev/null +++ b/arch/arm64/kernel/machine_kexec_file.c @@ -0,0 +1,342 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * kexec_file for arm64 + * + * Copyright (C) 2018 Linaro Limited + * Author: AKASHI Takahiro <takahiro.akashi(a)linaro.org> + * + * Most code is derived from arm64 port of kexec-tools + */ + +#define pr_fmt(fmt) "kexec_file: " fmt + +#include <linux/ioport.h> +#include <linux/kernel.h> +#include <linux/kexec.h> +#include <linux/libfdt.h> +#include <linux/memblock.h> +#include <linux/of_fdt.h> +#include <linux/random.h> +#include <linux/slab.h> +#include <linux/string.h> +#include <linux/types.h> +#include <linux/vmalloc.h> +#include <asm/byteorder.h> + +/* relevant device tree properties */ +#define FDT_PROP_KEXEC_ELFHDR "linux,elfcorehdr" +#define FDT_PROP_MEM_RANGE "linux,usable-memory-range" +#define FDT_PROP_INITRD_START "linux,initrd-start" +#define FDT_PROP_INITRD_END "linux,initrd-end" +#define FDT_PROP_BOOTARGS "bootargs" +#define FDT_PROP_KASLR_SEED "kaslr-seed" +#define FDT_PROP_RNG_SEED "rng-seed" +#define RNG_SEED_SIZE 128 + +const struct kexec_file_ops * const kexec_file_loaders[] = { + &kexec_image_ops, + NULL +}; + +int arch_kimage_file_post_load_cleanup(struct kimage *image) +{ + vfree(image->arch.dtb); + image->arch.dtb = NULL; + + vfree(image->arch.elf_headers); + image->arch.elf_headers = NULL; + image->arch.elf_headers_sz = 0; + + return kexec_image_post_load_cleanup_default(image); +} + +static int setup_dtb(struct kimage *image, + unsigned long initrd_load_addr, unsigned long initrd_len, + char *cmdline, void *dtb) +{ + int off, ret; + + ret = fdt_path_offset(dtb, "/chosen"); + if (ret < 0) + goto out; + + off = ret; + + ret = fdt_delprop(dtb, off, FDT_PROP_KEXEC_ELFHDR); + if (ret && ret != -FDT_ERR_NOTFOUND) + goto out; + ret = fdt_delprop(dtb, off, FDT_PROP_MEM_RANGE); + if (ret && ret != -FDT_ERR_NOTFOUND) + goto out; + + if (image->type == KEXEC_TYPE_CRASH) { + /* add linux,elfcorehdr */ + ret = fdt_appendprop_addrrange(dtb, 0, off, + FDT_PROP_KEXEC_ELFHDR, + image->arch.elf_headers_mem, + image->arch.elf_headers_sz); + if (ret) + return (ret == -FDT_ERR_NOSPACE ? -ENOMEM : -EINVAL); + + /* add linux,usable-memory-range */ + ret = fdt_appendprop_addrrange(dtb, 0, off, + FDT_PROP_MEM_RANGE, + crashk_res.start, + crashk_res.end - crashk_res.start + 1); + if (ret) + return (ret == -FDT_ERR_NOSPACE ? -ENOMEM : -EINVAL); + } + + /* add bootargs */ + if (cmdline) { + ret = fdt_setprop_string(dtb, off, FDT_PROP_BOOTARGS, cmdline); + if (ret) + goto out; + } else { + ret = fdt_delprop(dtb, off, FDT_PROP_BOOTARGS); + if (ret && (ret != -FDT_ERR_NOTFOUND)) + goto out; + } + + /* add initrd-* */ + if (initrd_load_addr) { + ret = fdt_setprop_u64(dtb, off, FDT_PROP_INITRD_START, + initrd_load_addr); + if (ret) + goto out; + + ret = fdt_setprop_u64(dtb, off, FDT_PROP_INITRD_END, + initrd_load_addr + initrd_len); + if (ret) + goto out; + } else { + ret = fdt_delprop(dtb, off, FDT_PROP_INITRD_START); + if (ret && (ret != -FDT_ERR_NOTFOUND)) + goto out; + + ret = fdt_delprop(dtb, off, FDT_PROP_INITRD_END); + if (ret && (ret != -FDT_ERR_NOTFOUND)) + goto out; + } + + /* add kaslr-seed */ + ret = fdt_delprop(dtb, off, FDT_PROP_KASLR_SEED); + if (ret && (ret != -FDT_ERR_NOTFOUND)) + goto out; + + if (rng_is_initialized()) { + u64 seed = get_random_u64(); + ret = fdt_setprop_u64(dtb, off, FDT_PROP_KASLR_SEED, seed); + if (ret) + goto out; + } else { + pr_notice("RNG is not initialised: omitting \"%s\" property\n", + FDT_PROP_KASLR_SEED); + } + + /* add rng-seed */ + if (rng_is_initialized()) { + u8 rng_seed[RNG_SEED_SIZE]; + get_random_bytes(rng_seed, RNG_SEED_SIZE); + ret = fdt_setprop(dtb, off, FDT_PROP_RNG_SEED, rng_seed, + RNG_SEED_SIZE); + if (ret) + goto out; + } else { + pr_notice("RNG is not initialised: omitting \"%s\" property\n", + FDT_PROP_RNG_SEED); + } + +out: + if (ret) + return (ret == -FDT_ERR_NOSPACE) ? -ENOMEM : -EINVAL; + + return 0; +} + +/* + * More space needed so that we can add initrd, bootargs, kaslr-seed, + * rng-seed, userable-memory-range and elfcorehdr. + */ +#define DTB_EXTRA_SPACE 0x1000 + +static int create_dtb(struct kimage *image, + unsigned long initrd_load_addr, unsigned long initrd_len, + char *cmdline, void **dtb) +{ + void *buf; + size_t buf_size; + size_t cmdline_len; + int ret; + + cmdline_len = cmdline ? strlen(cmdline) : 0; + buf_size = fdt_totalsize(initial_boot_params) + + cmdline_len + DTB_EXTRA_SPACE; + + for (;;) { + buf = vmalloc(buf_size); + if (!buf) + return -ENOMEM; + + /* duplicate a device tree blob */ + ret = fdt_open_into(initial_boot_params, buf, buf_size); + if (ret) { + vfree(buf); + return -EINVAL; + } + + ret = setup_dtb(image, initrd_load_addr, initrd_len, + cmdline, buf); + if (ret) { + vfree(buf); + if (ret == -ENOMEM) { + /* unlikely, but just in case */ + buf_size += DTB_EXTRA_SPACE; + continue; + } else { + return ret; + } + } + + /* trim it */ + fdt_pack(buf); + *dtb = buf; + + return 0; + } +} + +static int prepare_elf_headers(void **addr, unsigned long *sz) +{ + struct crash_mem *cmem; + unsigned int nr_ranges; + int ret; + u64 i; + phys_addr_t start, end; + + nr_ranges = 1; /* for exclusion of crashkernel region */ + for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE, + MEMBLOCK_NONE, &start, &end, NULL) + nr_ranges++; + + cmem = kmalloc(sizeof(struct crash_mem) + + sizeof(struct crash_mem_range) * nr_ranges, GFP_KERNEL); + if (!cmem) + return -ENOMEM; + + cmem->max_nr_ranges = nr_ranges; + cmem->nr_ranges = 0; + for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE, + MEMBLOCK_NONE, &start, &end, NULL) { + cmem->ranges[cmem->nr_ranges].start = start; + cmem->ranges[cmem->nr_ranges].end = end - 1; + cmem->nr_ranges++; + } + + /* Exclude crashkernel region */ + ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end); + + if (!ret) + ret = crash_prepare_elf64_headers(cmem, true, addr, sz); + + kfree(cmem); + return ret; +} + +int load_other_segments(struct kimage *image, + unsigned long kernel_load_addr, + unsigned long kernel_size, + char *initrd, unsigned long initrd_len, + char *cmdline) +{ + struct kexec_buf kbuf; + void *headers, *dtb = NULL; + unsigned long headers_sz, initrd_load_addr = 0, dtb_len; + int ret = 0; + + kbuf.image = image; + /* not allocate anything below the kernel */ + kbuf.buf_min = kernel_load_addr + kernel_size; + + /* load elf core header */ + if (image->type == KEXEC_TYPE_CRASH) { + ret = prepare_elf_headers(&headers, &headers_sz); + if (ret) { + pr_err("Preparing elf core header failed\n"); + goto out_err; + } + + kbuf.buffer = headers; + kbuf.bufsz = headers_sz; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + kbuf.memsz = headers_sz; + kbuf.buf_align = SZ_64K; /* largest supported page size */ + kbuf.buf_max = ULONG_MAX; + kbuf.top_down = true; + + ret = kexec_add_buffer(&kbuf); + if (ret) { + vfree(headers); + goto out_err; + } + image->arch.elf_headers = headers; + image->arch.elf_headers_mem = kbuf.mem; + image->arch.elf_headers_sz = headers_sz; + + pr_debug("Loaded elf core header at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + image->arch.elf_headers_mem, headers_sz, headers_sz); + } + + /* load initrd */ + if (initrd) { + kbuf.buffer = initrd; + kbuf.bufsz = initrd_len; + kbuf.mem = 0; + kbuf.memsz = initrd_len; + kbuf.buf_align = 0; + /* within 1GB-aligned window of up to 32GB in size */ + kbuf.buf_max = round_down(kernel_load_addr, SZ_1G) + + (unsigned long)SZ_1G * 32; + kbuf.top_down = false; + + ret = kexec_add_buffer(&kbuf); + if (ret) + goto out_err; + initrd_load_addr = kbuf.mem; + + pr_debug("Loaded initrd at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + initrd_load_addr, initrd_len, initrd_len); + } + + /* load dtb */ + ret = create_dtb(image, initrd_load_addr, initrd_len, cmdline, &dtb); + if (ret) { + pr_err("Preparing for new dtb failed\n"); + goto out_err; + } + + dtb_len = fdt_totalsize(dtb); + kbuf.buffer = dtb; + kbuf.bufsz = dtb_len; + kbuf.mem = 0; + kbuf.memsz = dtb_len; + /* not across 2MB boundary */ + kbuf.buf_align = SZ_2M; + kbuf.buf_max = ULONG_MAX; + kbuf.top_down = true; + + ret = kexec_add_buffer(&kbuf); + if (ret) + goto out_err; + image->arch.dtb = dtb; + image->arch.dtb_mem = kbuf.mem; + + pr_debug("Loaded dtb at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + kbuf.mem, dtb_len, dtb_len); + + return 0; + +out_err: + vfree(dtb); + return ret; +} diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S index f407e422a..95fd94209 100644 --- a/arch/arm64/kernel/relocate_kernel.S +++ b/arch/arm64/kernel/relocate_kernel.S @@ -32,6 +32,7 @@ ENTRY(arm64_relocate_new_kernel) /* Setup the list loop variables. */ + mov x18, x2 /* x18 = dtb address */ mov x17, x1 /* x17 = kimage_start */ mov x16, x0 /* x16 = kimage_head */ raw_dcache_line_size x15, x0 /* x15 = dcache line size */ @@ -107,7 +108,7 @@ ENTRY(arm64_relocate_new_kernel) isb /* Start new image. */ - mov x0, xzr + mov x0, x18 mov x1, xzr mov x2, xzr mov x3, xzr diff --git a/arch/powerpc/kernel/machine_kexec_file_64.c b/arch/powerpc/kernel/machine_kexec_file_64.c index c77e95e9b..0d20c7ad4 100644 --- a/arch/powerpc/kernel/machine_kexec_file_64.c +++ b/arch/powerpc/kernel/machine_kexec_file_64.c @@ -24,7 +24,6 @@ #include <linux/slab.h> #include <linux/kexec.h> -#include <linux/memblock.h> #include <linux/of_fdt.h> #include <linux/libfdt.h> #include <asm/ima.h> @@ -46,59 +45,6 @@ int arch_kexec_kernel_image_probe(struct kimage *image, void *buf, return kexec_image_probe_default(image, buf, buf_len); } -/** - * arch_kexec_walk_mem - call func(data) for each unreserved memory block - * @kbuf: Context info for the search. Also passed to @func. - * @func: Function to call for each memory block. - * - * This function is used by kexec_add_buffer and kexec_locate_mem_hole - * to find unreserved memory to load kexec segments into. - * - * Return: The memory walk will stop when func returns a non-zero value - * and that value will be returned. If all free regions are visited without - * func returning non-zero, then zero will be returned. - */ -int arch_kexec_walk_mem(struct kexec_buf *kbuf, - int (*func)(struct resource *, void *)) -{ - int ret = 0; - u64 i; - phys_addr_t mstart, mend; - struct resource res = { }; - - if (kbuf->top_down) { - for_each_free_mem_range_reverse(i, NUMA_NO_NODE, 0, - &mstart, &mend, NULL) { - /* - * In memblock, end points to the first byte after the - * range while in kexec, end points to the last byte - * in the range. - */ - res.start = mstart; - res.end = mend - 1; - ret = func(&res, kbuf); - if (ret) - break; - } - } else { - for_each_free_mem_range(i, NUMA_NO_NODE, 0, &mstart, &mend, - NULL) { - /* - * In memblock, end points to the first byte after the - * range while in kexec, end points to the last byte - * in the range. - */ - res.start = mstart; - res.end = mend - 1; - ret = func(&res, kbuf); - if (ret) - break; - } - } - - return ret; -} - /** * setup_purgatory - initialize the purgatory's global variables * @image: kexec image. diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c index f413f57f8..32023b4f9 100644 --- a/arch/s390/kernel/machine_kexec_file.c +++ b/arch/s390/kernel/machine_kexec_file.c @@ -134,16 +134,6 @@ int kexec_file_add_initrd(struct kimage *image, struct s390_load_data *data, return ret; } -/* - * The kernel is loaded to a fixed location. Turn off kexec_locate_mem_hole - * and provide kbuf->mem by hand. - */ -int arch_kexec_walk_mem(struct kexec_buf *kbuf, - int (*func)(struct resource *, void *)) -{ - return 1; -} - int arch_kexec_apply_relocations_add(struct purgatory_info *pi, Elf_Shdr *section, const Elf_Shdr *relsec, diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index 70caa60b4..8977de5ad 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -535,9 +535,17 @@ static int bzImage64_cleanup(void *loader_data) #ifdef CONFIG_KEXEC_BZIMAGE_VERIFY_SIG static int bzImage64_verify_sig(const char *kernel, unsigned long kernel_len) { - return verify_pefile_signature(kernel, kernel_len, - VERIFY_USE_SECONDARY_KEYRING, - VERIFYING_KEXEC_PE_SIGNATURE); + int ret; + + ret = verify_pefile_signature(kernel, kernel_len, + VERIFY_USE_SECONDARY_KEYRING, + VERIFYING_KEXEC_PE_SIGNATURE); + if (ret == -ENOKEY && IS_ENABLED(CONFIG_INTEGRITY_PLATFORM_KEYRING)) { + ret = verify_pefile_signature(kernel, kernel_len, + VERIFY_USE_PLATFORM_KEYRING, + VERIFYING_KEXEC_PE_SIGNATURE); + } + return ret; } #endif diff --git a/certs/system_keyring.c b/certs/system_keyring.c index 817287175..c05c29ae4 100644 --- a/certs/system_keyring.c +++ b/certs/system_keyring.c @@ -24,6 +24,9 @@ static struct key *builtin_trusted_keys; #ifdef CONFIG_SECONDARY_TRUSTED_KEYRING static struct key *secondary_trusted_keys; #endif +#ifdef CONFIG_INTEGRITY_PLATFORM_KEYRING +static struct key *platform_trusted_keys; +#endif extern __initconst const u8 system_certificate_list[]; extern __initconst const unsigned long system_certificate_list_size; @@ -237,11 +240,22 @@ int verify_pkcs7_signature(const void *data, size_t len, #else trusted_keys = builtin_trusted_keys; #endif + } else if (trusted_keys == VERIFY_USE_PLATFORM_KEYRING) { +#ifdef CONFIG_INTEGRITY_PLATFORM_KEYRING + trusted_keys = platform_trusted_keys; +#else + trusted_keys = NULL; +#endif + if (!trusted_keys) { + ret = -ENOKEY; + pr_devel("PKCS#7 platform keyring is not available\n"); + goto error; + } } ret = pkcs7_validate_trust(pkcs7, trusted_keys); if (ret < 0) { if (ret == -ENOKEY) - pr_err("PKCS#7 signature not signed with a trusted key\n"); + pr_devel("PKCS#7 signature not signed with a trusted key\n"); goto error; } @@ -266,3 +280,10 @@ int verify_pkcs7_signature(const void *data, size_t len, EXPORT_SYMBOL_GPL(verify_pkcs7_signature); #endif /* CONFIG_SYSTEM_DATA_VERIFICATION */ + +#ifdef CONFIG_INTEGRITY_PLATFORM_KEYRING +void __init set_platform_trusted_keys(struct key *keyring) +{ + platform_trusted_keys = keyring; +} +#endif diff --git a/include/keys/system_keyring.h b/include/keys/system_keyring.h index 359c2f936..42a93eda3 100644 --- a/include/keys/system_keyring.h +++ b/include/keys/system_keyring.h @@ -61,5 +61,13 @@ static inline struct key *get_ima_blacklist_keyring(void) } #endif /* CONFIG_IMA_BLACKLIST_KEYRING */ +#if defined(CONFIG_INTEGRITY_PLATFORM_KEYRING) && \ + defined(CONFIG_SYSTEM_TRUSTED_KEYRING) +extern void __init set_platform_trusted_keys(struct key *keyring); +#else +static inline void set_platform_trusted_keys(struct key *keyring) +{ +} +#endif #endif /* _KEYS_SYSTEM_KEYRING_H */ diff --git a/include/linux/efi.h b/include/linux/efi.h index 34c255c2a..b8a6df5df 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -676,6 +676,10 @@ void efi_native_runtime_setup(void); #define EFI_IMAGE_SECURITY_DATABASE_GUID EFI_GUID(0xd719b2cb, 0x3d3a, 0x4596, 0xa3, 0xbc, 0xda, 0xd0, 0x0e, 0x67, 0x65, 0x6f) #define EFI_SHIM_LOCK_GUID EFI_GUID(0x605dab50, 0xe046, 0x4300, 0xab, 0xb6, 0x3d, 0xd8, 0x10, 0xdd, 0x8b, 0x23) +#define EFI_CERT_SHA256_GUID EFI_GUID(0xc1c41626, 0x504c, 0x4092, 0xac, 0xa9, 0x41, 0xf9, 0x36, 0x93, 0x43, 0x28) +#define EFI_CERT_X509_GUID EFI_GUID(0xa5c059a1, 0x94e4, 0x4aa7, 0x87, 0xb5, 0xab, 0x15, 0x5c, 0x2b, 0xf0, 0x72) +#define EFI_CERT_X509_SHA256_GUID EFI_GUID(0x3bd2a492, 0x96c0, 0x4079, 0xb4, 0x20, 0xfc, 0xf9, 0x8e, 0xf1, 0x03, 0xed) + /* * This GUID is used to pass to the kernel proper the struct screen_info * structure that was populated by the stub based on the GOP protocol instance @@ -947,6 +951,27 @@ typedef struct { efi_memory_desc_t entry[0]; } efi_memory_attributes_table_t; +typedef struct { + efi_guid_t signature_owner; + u8 signature_data[]; +} efi_signature_data_t; + +typedef struct { + efi_guid_t signature_type; + u32 signature_list_size; + u32 signature_header_size; + u32 signature_size; + u8 signature_header[]; + /* efi_signature_data_t signatures[][] */ +} efi_signature_list_t; + +typedef u8 efi_sha256_hash_t[32]; + +typedef struct { + efi_sha256_hash_t to_be_signed_hash; + efi_time_t time_of_revocation; +} efi_cert_x509_sha256_t; + /* * All runtime access to EFI goes through this structure: */ @@ -1129,6 +1154,15 @@ extern int efi_memattr_apply_permissions(struct mm_struct *mm, char * __init efi_md_typeattr_format(char *buf, size_t size, const efi_memory_desc_t *md); + +typedef void (*efi_element_handler_t)(const char *source, + const void *element_data, + size_t element_size); +extern int __init parse_efi_signature_list( + const char *source, + const void *data, size_t size, + efi_element_handler_t (*get_handler_for_guid)(const efi_guid_t *)); + /** * efi_range_is_wc - check the WC bit on an address range * @start: starting kvirt address diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 98cf0fb09..542a15c91 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -147,6 +147,19 @@ extern const struct kexec_file_ops * const kexec_file_loaders[]; int kexec_image_probe_default(struct kimage *image, void *buf, unsigned long buf_len); +int kexec_image_post_load_cleanup_default(struct kimage *image); + +int wrap_kexec_file_load(int kernel_fd, int initrd_fd, + unsigned long cmdline_len, const char __user *cmdline_ptr, + unsigned long flags); + +/* + * If kexec_buf.mem is set to this value, kexec_locate_mem_hole() + * will try to allocate free memory. Arch may overwrite it. + */ +#ifndef KEXEC_BUF_MEM_UNKNOWN +#define KEXEC_BUF_MEM_UNKNOWN 0 +#endif /** * struct kexec_buf - parameters for finding a place for a buffer in memory @@ -187,8 +200,6 @@ int __weak arch_kexec_apply_relocations(struct purgatory_info *pi, const Elf_Shdr *relsec, const Elf_Shdr *symtab); -int __weak arch_kexec_walk_mem(struct kexec_buf *kbuf, - int (*func)(struct resource *, void *)); extern int kexec_add_buffer(struct kexec_buf *kbuf); int kexec_locate_mem_hole(struct kexec_buf *kbuf); diff --git a/include/linux/pe.h b/include/linux/pe.h index 143ce75be..3482b18a4 100644 --- a/include/linux/pe.h +++ b/include/linux/pe.h @@ -166,7 +166,7 @@ struct mz_hdr { uint16_t oem_info; /* oem specific */ uint16_t reserved1[10]; /* reserved */ uint32_t peaddr; /* address of pe header */ - char message[64]; /* message to print */ + char message[]; /* message to print */ }; struct mz_reloc { diff --git a/include/linux/verification.h b/include/linux/verification.h index cfa4730d6..018fb5f13 100644 --- a/include/linux/verification.h +++ b/include/linux/verification.h @@ -17,6 +17,7 @@ * should be used. */ #define VERIFY_USE_SECONDARY_KEYRING ((struct key *)1UL) +#define VERIFY_USE_PLATFORM_KEYRING ((struct key *)2UL) /* * The use to which an asymmetric key is being put. diff --git a/include/uapi/linux/kexec.h b/include/uapi/linux/kexec.h index ca3cebebd..9385ecba2 100644 --- a/include/uapi/linux/kexec.h +++ b/include/uapi/linux/kexec.h @@ -25,6 +25,7 @@ #define KEXEC_FILE_UNLOAD 0x00000001 #define KEXEC_FILE_ON_CRASH 0x00000002 #define KEXEC_FILE_NO_INITRAMFS 0x00000004 +#define KEXEC_FILE_LOAD_WRAP 0x100000000 /* These values match the ELF architecture values. * Unless there is a good reason that should continue to be the case. diff --git a/kernel/kexec.c b/kernel/kexec.c index 47dfad722..d44a55202 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -238,6 +238,16 @@ SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments, { int result; + if (flags & KEXEC_FILE_LOAD_WRAP) { + int kernel_fd, initrd_fd; + + kernel_fd = entry >> 32; + initrd_fd = entry & 0x00000000ffffffff; + flags &= ~KEXEC_FILE_LOAD_WRAP; + return wrap_kexec_file_load(kernel_fd, initrd_fd, nr_segments, + (char __user *)segments, flags); + } + result = kexec_load_check(nr_segments, flags); if (result) return result; diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index 04f99368b..2a25db8dd 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -16,6 +16,7 @@ #include <linux/file.h> #include <linux/slab.h> #include <linux/kexec.h> +#include <linux/memblock.h> #include <linux/mutex.h> #include <linux/list.h> #include <linux/fs.h> @@ -78,7 +79,7 @@ void * __weak arch_kexec_kernel_image_load(struct kimage *image) return kexec_image_load_default(image); } -static int kexec_image_post_load_cleanup_default(struct kimage *image) +int kexec_image_post_load_cleanup_default(struct kimage *image) { if (!image->fops || !image->fops->cleanup) return 0; @@ -407,6 +408,96 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, return ret; } +int wrap_kexec_file_load(int kernel_fd, int initrd_fd, + unsigned long cmdline_len, const char __user *cmdline_ptr, + unsigned long flags) +{ + int ret = 0, i; + struct kimage **dest_image, *image; + + /* We only trust the superuser with rebooting the system. */ + if (!capable(CAP_SYS_BOOT) || kexec_load_disabled) + return -EPERM; + + /* Make sure we have a legal set of flags */ + if (flags != (flags & KEXEC_FILE_FLAGS)) + return -EINVAL; + + image = NULL; + + if (!mutex_trylock(&kexec_mutex)) + return -EBUSY; + + dest_image = &kexec_image; + if (flags & KEXEC_FILE_ON_CRASH) { + dest_image = &kexec_crash_image; + if (kexec_crash_image) + arch_kexec_unprotect_crashkres(); + } + + if (flags & KEXEC_FILE_UNLOAD) + goto exchange; + + /* + * In case of crash, new kernel gets loaded in reserved region. It is + * same memory where old crash kernel might be loaded. Free any + * current crash dump kernel before we corrupt it. + */ + if (flags & KEXEC_FILE_ON_CRASH) + kimage_free(xchg(&kexec_crash_image, NULL)); + + ret = kimage_file_alloc_init(&image, kernel_fd, initrd_fd, cmdline_ptr, + cmdline_len, flags); + if (ret) + goto out; + + ret = machine_kexec_prepare(image); + if (ret) + goto out; + + /* + * Some architecture(like S390) may touch the crash memory before + * machine_kexec_prepare(), we must copy vmcoreinfo data after it. + */ + ret = kimage_crash_copy_vmcoreinfo(image); + if (ret) + goto out; + + ret = kexec_calculate_store_digests(image); + if (ret) + goto out; + + for (i = 0; i < image->nr_segments; i++) { + struct kexec_segment *ksegment; + + ksegment = &image->segment[i]; + pr_debug("Loading segment %d: buf=0x%p bufsz=0x%zx mem=0x%lx memsz=0x%zx\n", + i, ksegment->buf, ksegment->bufsz, ksegment->mem, + ksegment->memsz); + + ret = kimage_load_segment(image, &image->segment[i]); + if (ret) + goto out; + } + + kimage_terminate(image); + + /* + * Free up any temporary buffers allocated which are not needed + * after image has been loaded + */ + kimage_file_post_load_cleanup(image); +exchange: + image = xchg(dest_image, image); +out: + if ((flags & KEXEC_FILE_ON_CRASH) && kexec_crash_image) + arch_kexec_protect_crashkres(); + + mutex_unlock(&kexec_mutex); + kimage_free(image); + return ret; +} + static int locate_mem_hole_top_down(unsigned long start, unsigned long end, struct kexec_buf *kbuf) { @@ -501,8 +592,60 @@ static int locate_mem_hole_callback(struct resource *res, void *arg) return locate_mem_hole_bottom_up(start, end, kbuf); } +#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK +static int kexec_walk_memblock(struct kexec_buf *kbuf, + int (*func)(struct resource *, void *)) +{ + return 0; +} +#else +static int kexec_walk_memblock(struct kexec_buf *kbuf, + int (*func)(struct resource *, void *)) +{ + int ret = 0; + u64 i; + phys_addr_t mstart, mend; + struct resource res = { }; + + if (kbuf->image->type == KEXEC_TYPE_CRASH) + return func(&crashk_res, kbuf); + + if (kbuf->top_down) { + for_each_free_mem_range_reverse(i, NUMA_NO_NODE, MEMBLOCK_NONE, + &mstart, &mend, NULL) { + /* + * In memblock, end points to the first byte after the + * range while in kexec, end points to the last byte + * in the range. + */ + res.start = mstart; + res.end = mend - 1; + ret = func(&res, kbuf); + if (ret) + break; + } + } else { + for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, + &mstart, &mend, NULL) { + /* + * In memblock, end points to the first byte after the + * range while in kexec, end points to the last byte + * in the range. + */ + res.start = mstart; + res.end = mend - 1; + ret = func(&res, kbuf); + if (ret) + break; + } + } + + return ret; +} +#endif + /** - * arch_kexec_walk_mem - call func(data) on free memory regions + * kexec_walk_resources - call func(data) on free memory regions * @kbuf: Context info for the search. Also passed to @func. * @func: Function to call for each memory region. * @@ -510,8 +653,8 @@ static int locate_mem_hole_callback(struct resource *res, void *arg) * and that value will be returned. If all free regions are visited without * func returning non-zero, then zero will be returned. */ -int __weak arch_kexec_walk_mem(struct kexec_buf *kbuf, - int (*func)(struct resource *, void *)) +static int kexec_walk_resources(struct kexec_buf *kbuf, + int (*func)(struct resource *, void *)) { if (kbuf->image->type == KEXEC_TYPE_CRASH) return walk_iomem_res_desc(crashk_res.desc, @@ -534,7 +677,14 @@ int kexec_locate_mem_hole(struct kexec_buf *kbuf) { int ret; - ret = arch_kexec_walk_mem(kbuf, locate_mem_hole_callback); + /* Arch knows where to place */ + if (kbuf->mem != KEXEC_BUF_MEM_UNKNOWN) + return 0; + + if (IS_ENABLED(CONFIG_ARCH_DISCARD_MEMBLOCK)) + ret = kexec_walk_resources(kbuf, locate_mem_hole_callback); + else + ret = kexec_walk_memblock(kbuf, locate_mem_hole_callback); return ret == 1 ? 0 : -EADDRNOTAVAIL; } diff --git a/lib/Makefile b/lib/Makefile index 01f8051b4..455797430 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -213,7 +213,7 @@ KASAN_SANITIZE_stackdepot.o := n KCOV_INSTRUMENT_stackdepot.o := n libfdt_files = fdt.o fdt_ro.o fdt_wip.o fdt_rw.o fdt_sw.o fdt_strerror.o \ - fdt_empty_tree.o + fdt_empty_tree.o fdt_addresses.o $(foreach file, $(libfdt_files), \ $(eval CFLAGS_$(file) = -I$(src)/../scripts/dtc/libfdt)) lib-$(CONFIG_LIBFDT) += $(libfdt_files) diff --git a/lib/fdt_addresses.c b/lib/fdt_addresses.c new file mode 100644 index 000000000..23610bcf3 --- /dev/null +++ b/lib/fdt_addresses.c @@ -0,0 +1,2 @@ +#include <linux/libfdt_env.h> +#include "../scripts/dtc/libfdt/fdt_addresses.c" diff --git a/scripts/dtc/libfdt/fdt_addresses.c b/scripts/dtc/libfdt/fdt_addresses.c index eff4dbcc7..8211d00ba 100644 --- a/scripts/dtc/libfdt/fdt_addresses.c +++ b/scripts/dtc/libfdt/fdt_addresses.c @@ -94,3 +94,50 @@ int fdt_size_cells(const void *fdt, int nodeoffset) return val; } + +/* This function assumes that [address|size]_cells is 1 or 2 */ +int fdt_appendprop_addrrange(void *fdt, int parent, int nodeoffset, + const char *name, uint64_t addr, uint64_t size) +{ + int addr_cells, size_cells, ret; + uint8_t data[sizeof(fdt64_t) * 2], *prop; + + ret = fdt_address_cells(fdt, parent); + if (ret < 0) + return ret; + addr_cells = ret; + + ret = fdt_size_cells(fdt, parent); + if (ret < 0) + return ret; + size_cells = ret; + + /* check validity of address */ + prop = data; + if (addr_cells == 1) { + if ((addr > UINT32_MAX) || ((UINT32_MAX + 1 - addr) < size)) + return -FDT_ERR_BADVALUE; + + fdt32_st(prop, (uint32_t)addr); + } else if (addr_cells == 2) { + fdt64_st(prop, addr); + } else { + return -FDT_ERR_BADNCELLS; + } + + /* check validity of size */ + prop += addr_cells * sizeof(fdt32_t); + if (size_cells == 1) { + if (size > UINT32_MAX) + return -FDT_ERR_BADVALUE; + + fdt32_st(prop, (uint32_t)size); + } else if (size_cells == 2) { + fdt64_st(prop, size); + } else { + return -FDT_ERR_BADNCELLS; + } + + return fdt_appendprop(fdt, nodeoffset, name, data, + (addr_cells + size_cells) * sizeof(fdt32_t)); +} diff --git a/scripts/dtc/libfdt/libfdt.h b/scripts/dtc/libfdt/libfdt.h index 1e27780e1..da72b54c4 100644 --- a/scripts/dtc/libfdt/libfdt.h +++ b/scripts/dtc/libfdt/libfdt.h @@ -153,6 +153,30 @@ static inline void *fdt_offset_ptr_w(void *fdt, int offset, int checklen) uint32_t fdt_next_tag(const void *fdt, int offset, int *nextoffset); +static inline void fdt32_st(void *property, uint32_t value) +{ + uint8_t *bp = property; + + bp[0] = value >> 24; + bp[1] = (value >> 16) & 0xff; + bp[2] = (value >> 8) & 0xff; + bp[3] = value & 0xff; +} + +static inline void fdt64_st(void *property, uint64_t value) +{ + uint8_t *bp = property; + + bp[0] = value >> 56; + bp[1] = (value >> 48) & 0xff; + bp[2] = (value >> 40) & 0xff; + bp[3] = (value >> 32) & 0xff; + bp[4] = (value >> 24) & 0xff; + bp[5] = (value >> 16) & 0xff; + bp[6] = (value >> 8) & 0xff; + bp[7] = value & 0xff; +} + /**********************************************************************/ /* Traversal functions */ /**********************************************************************/ @@ -1765,6 +1789,43 @@ static inline int fdt_appendprop_cell(void *fdt, int nodeoffset, #define fdt_appendprop_string(fdt, nodeoffset, name, str) \ fdt_appendprop((fdt), (nodeoffset), (name), (str), strlen(str)+1) +/** + * fdt_appendprop_addrrange - append a address range property + * @fdt: pointer to the device tree blob + * @parent: offset of the parent node + * @nodeoffset: offset of the node to add a property at + * @name: name of property + * @addr: start address of a given range + * @size: size of a given range + * + * fdt_appendprop_addrrange() appends an address range value (start + * address and size) to the value of the named property in the given + * node, or creates a new property with that value if it does not + * already exist. + * If "name" is not specified, a default "reg" is used. + * Cell sizes are determined by parent's #address-cells and #size-cells. + * + * This function may insert data into the blob, and will therefore + * change the offsets of some existing nodes. + * + * returns: + * 0, on success + * -FDT_ERR_BADLAYOUT, + * -FDT_ERR_BADMAGIC, + * -FDT_ERR_BADNCELLS, if the node has a badly formatted or invalid + * #address-cells property + * -FDT_ERR_BADOFFSET, nodeoffset did not point to FDT_BEGIN_NODE tag + * -FDT_ERR_BADSTATE, + * -FDT_ERR_BADSTRUCTURE, + * -FDT_ERR_BADVERSION, + * -FDT_ERR_BADVALUE, addr or size doesn't fit to respective cells size + * -FDT_ERR_NOSPACE, there is insufficient free space in the blob to + * contain a new property + * -FDT_ERR_TRUNCATED, standard meanings + */ +int fdt_appendprop_addrrange(void *fdt, int parent, int nodeoffset, + const char *name, uint64_t addr, uint64_t size); + /** * fdt_delprop - delete a property * @fdt: pointer to the device tree blob diff --git a/security/integrity/Kconfig b/security/integrity/Kconfig index da9565891..4b4d2aeef 100644 --- a/security/integrity/Kconfig +++ b/security/integrity/Kconfig @@ -51,6 +51,17 @@ config INTEGRITY_TRUSTED_KEYRING .evm keyrings be signed by a key on the system trusted keyring. +config INTEGRITY_PLATFORM_KEYRING + bool "Provide keyring for platform/firmware trusted keys" + depends on INTEGRITY_ASYMMETRIC_KEYS + depends on SYSTEM_BLACKLIST_KEYRING + depends on EFI + help + Provide a separate, distinct keyring for platform trusted keys, which + the kernel automatically populates during initialization from values + provided by the platform for verifying the kexec'ed kerned image + and, possibly, the initramfs signature. + config INTEGRITY_AUDIT bool "Enables integrity auditing support " depends on AUDIT diff --git a/security/integrity/Makefile b/security/integrity/Makefile index 04d6e462b..86df9aba8 100644 --- a/security/integrity/Makefile +++ b/security/integrity/Makefile @@ -9,6 +9,11 @@ integrity-y := iint.o integrity-$(CONFIG_INTEGRITY_AUDIT) += integrity_audit.o integrity-$(CONFIG_INTEGRITY_SIGNATURE) += digsig.o integrity-$(CONFIG_INTEGRITY_ASYMMETRIC_KEYS) += digsig_asymmetric.o +integrity-$(CONFIG_INTEGRITY_PLATFORM_KEYRING) += platform_certs/platform_keyring.o \ + platform_certs/efi_parser.o \ + platform_certs/load_uefi.o +obj-$(CONFIG_LOAD_UEFI_KEYS) += platform_certs/load_uefi.o +$(obj)/load_uefi.o: KBUILD_CFLAGS += -fshort-wchar subdir-$(CONFIG_IMA) += ima obj-$(CONFIG_IMA) += ima/ diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c index 9bb0a7f28..c585ca8db 100644 --- a/security/integrity/digsig.c +++ b/security/integrity/digsig.c @@ -35,6 +35,7 @@ static const char *keyring_name[INTEGRITY_KEYRING_MAX] = { ".ima", #endif "_module", + ".platform", }; #ifdef CONFIG_INTEGRITY_TRUSTED_KEYRING @@ -79,12 +80,42 @@ int integrity_digsig_verify(const unsigned int id, const char *sig, int siglen, return -EOPNOTSUPP; } -int __init integrity_init_keyring(const unsigned int id) +static int __init __integrity_init_keyring(const unsigned int id, + key_perm_t perm, + struct key_restriction *restriction) { const struct cred *cred = current_cred(); - struct key_restriction *restriction; int err = 0; + keyring[id] = keyring_alloc(keyring_name[id], KUIDT_INIT(0), + KGIDT_INIT(0), cred, perm, + KEY_ALLOC_NOT_IN_QUOTA, restriction, NULL); + if (IS_ERR(keyring[id])) { + err = PTR_ERR(keyring[id]); + pr_info("Can't allocate %s keyring (%d)\n", + keyring_name[id], err); + keyring[id] = NULL; + } else { + if (id == INTEGRITY_KEYRING_PLATFORM) + set_platform_trusted_keys(keyring[id]); + } + + return err; +} + +int __init integrity_init_keyring(const unsigned int id) +{ + struct key_restriction *restriction; + key_perm_t perm; + + perm = (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW + | KEY_USR_READ | KEY_USR_SEARCH; + + if (id == INTEGRITY_KEYRING_PLATFORM) { + restriction = NULL; + goto out; + } + if (!init_keyring) return 0; @@ -93,32 +124,43 @@ int __init integrity_init_keyring(const unsigned int id) return -ENOMEM; restriction->check = restrict_link_to_ima; + perm |= KEY_USR_WRITE; - keyring[id] = keyring_alloc(keyring_name[id], KUIDT_INIT(0), - KGIDT_INIT(0), cred, - ((KEY_POS_ALL & ~KEY_POS_SETATTR) | - KEY_USR_VIEW | KEY_USR_READ | - KEY_USR_WRITE | KEY_USR_SEARCH), - KEY_ALLOC_NOT_IN_QUOTA, - restriction, NULL); - if (IS_ERR(keyring[id])) { - err = PTR_ERR(keyring[id]); - pr_info("Can't allocate %s keyring (%d)\n", - keyring_name[id], err); - keyring[id] = NULL; +out: + return __integrity_init_keyring(id, perm, restriction); +} + +int __init integrity_add_key(const unsigned int id, const void *data, + off_t size, key_perm_t perm) +{ + key_ref_t key; + int rc = 0; + + if (!keyring[id]) + return -EINVAL; + + key = key_create_or_update(make_key_ref(keyring[id], 1), "asymmetric", + NULL, data, size, perm, + KEY_ALLOC_NOT_IN_QUOTA); + if (IS_ERR(key)) { + rc = PTR_ERR(key); + pr_err("Problem loading X.509 certificate %d\n", rc); + } else { + pr_notice("Loaded X.509 cert '%s'\n", + key_ref_to_ptr(key)->description); + key_ref_put(key); } - return err; + + return rc; + } int __init integrity_load_x509(const unsigned int id, const char *path) { - key_ref_t key; void *data; loff_t size; int rc; - - if (!keyring[id]) - return -EINVAL; + key_perm_t perm; rc = kernel_read_file_from_path(path, &data, &size, 0, READING_X509_CERTIFICATE); @@ -127,23 +169,21 @@ int __init integrity_load_x509(const unsigned int id, const char *path) return rc; } - key = key_create_or_update(make_key_ref(keyring[id], 1), - "asymmetric", - NULL, - data, - size, - ((KEY_POS_ALL & ~KEY_POS_SETATTR) | - KEY_USR_VIEW | KEY_USR_READ), - KEY_ALLOC_NOT_IN_QUOTA); - if (IS_ERR(key)) { - rc = PTR_ERR(key); - pr_err("Problem loading X.509 certificate (%d): %s\n", - rc, path); - } else { - pr_notice("Loaded X.509 cert '%s': %s\n", - key_ref_to_ptr(key)->description, path); - key_ref_put(key); - } + perm = (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW | KEY_USR_READ; + + pr_info("Loading X.509 certificate: %s\n", path); + rc = integrity_add_key(id, (const void *)data, size, perm); + vfree(data); - return 0; + return rc; +} + +int __init integrity_load_cert(const unsigned int id, const char *source, + const void *data, size_t len, key_perm_t perm) +{ + if (!data) + return -EINVAL; + + pr_info("Loading X.509 certificate: %s\n", source); + return integrity_add_key(id, data, len, perm); } diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c index 08aabf763..ad285f17d 100644 --- a/security/integrity/ima/ima_appraise.c +++ b/security/integrity/ima/ima_appraise.c @@ -294,12 +294,22 @@ int ima_appraise_measurement(enum ima_hooks func, case EVM_IMA_XATTR_DIGSIG: set_bit(IMA_DIGSIG, &iint->atomic_flags); rc = integrity_digsig_verify(INTEGRITY_KEYRING_IMA, - (const char *)xattr_value, rc, + (const char *)xattr_value, + xattr_len, iint->ima_hash->digest, iint->ima_hash->length); if (rc == -EOPNOTSUPP) { status = INTEGRITY_UNKNOWN; - } else if (rc) { + break; + } + if (IS_ENABLED(CONFIG_INTEGRITY_PLATFORM_KEYRING) && rc && + func == KEXEC_KERNEL_CHECK) + rc = integrity_digsig_verify(INTEGRITY_KEYRING_PLATFORM, + (const char *)xattr_value, + xattr_len, + iint->ima_hash->digest, + iint->ima_hash->length); + if (rc) { cause = "invalid-signature"; status = INTEGRITY_FAIL; } else { diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h index 0ec551223..0750bab0d 100644 --- a/security/integrity/integrity.h +++ b/security/integrity/integrity.h @@ -142,7 +142,8 @@ int integrity_kernel_read(struct file *file, loff_t offset, #define INTEGRITY_KEYRING_EVM 0 #define INTEGRITY_KEYRING_IMA 1 #define INTEGRITY_KEYRING_MODULE 2 -#define INTEGRITY_KEYRING_MAX 3 +#define INTEGRITY_KEYRING_PLATFORM 3 +#define INTEGRITY_KEYRING_MAX 4 extern struct dentry *integrity_dir; @@ -153,6 +154,8 @@ int integrity_digsig_verify(const unsigned int id, const char *sig, int siglen, int __init integrity_init_keyring(const unsigned int id); int __init integrity_load_x509(const unsigned int id, const char *path); +int __init integrity_load_cert(const unsigned int id, const char *source, + const void *data, size_t len, key_perm_t perm); #else static inline int integrity_digsig_verify(const unsigned int id, @@ -166,6 +169,14 @@ static inline int integrity_init_keyring(const unsigned int id) { return 0; } + +static inline int __init integrity_load_cert(const unsigned int id, + const char *source, + const void *data, size_t len, + key_perm_t perm) +{ + return 0; +} #endif /* CONFIG_INTEGRITY_SIGNATURE */ #ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS @@ -222,3 +233,13 @@ integrity_audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type) } #endif + +#ifdef CONFIG_INTEGRITY_PLATFORM_KEYRING +void __init add_to_platform_keyring(const char *source, const void *data, + size_t len); +#else +static inline void __init add_to_platform_keyring(const char *source, + const void *data, size_t len) +{ +} +#endif diff --git a/security/integrity/platform_certs/efi_parser.c b/security/integrity/platform_certs/efi_parser.c new file mode 100644 index 000000000..18f01f36f --- /dev/null +++ b/security/integrity/platform_certs/efi_parser.c @@ -0,0 +1,108 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* EFI signature/key/certificate list parser + * + * Copyright (C) 2012, 2016 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells(a)redhat.com) + */ + +#define pr_fmt(fmt) "EFI: "fmt +#include <linux/module.h> +#include <linux/printk.h> +#include <linux/err.h> +#include <linux/efi.h> + +/** + * parse_efi_signature_list - Parse an EFI signature list for certificates + * @source: The source of the key + * @data: The data blob to parse + * @size: The size of the data blob + * @get_handler_for_guid: Get the handler func for the sig type (or NULL) + * + * Parse an EFI signature list looking for elements of interest. A list is + * made up of a series of sublists, where all the elements in a sublist are of + * the same type, but sublists can be of different types. + * + * For each sublist encountered, the @get_handler_for_guid function is called + * with the type specifier GUID and returns either a pointer to a function to + * handle elements of that type or NULL if the type is not of interest. + * + * If the sublist is of interest, each element is passed to the handler + * function in turn. + * + * Error EBADMSG is returned if the list doesn't parse correctly and 0 is + * returned if the list was parsed correctly. No error can be returned from + * the @get_handler_for_guid function or the element handler function it + * returns. + */ +int __init parse_efi_signature_list( + const char *source, + const void *data, size_t size, + efi_element_handler_t (*get_handler_for_guid)(const efi_guid_t *)) +{ + efi_element_handler_t handler; + unsigned int offs = 0; + + pr_devel("-->%s(,%zu)\n", __func__, size); + + while (size > 0) { + const efi_signature_data_t *elem; + efi_signature_list_t list; + size_t lsize, esize, hsize, elsize; + + if (size < sizeof(list)) + return -EBADMSG; + + memcpy(&list, data, sizeof(list)); + pr_devel("LIST[%04x] guid=%pUl ls=%x hs=%x ss=%x\n", + offs, + list.signature_type.b, list.signature_list_size, + list.signature_header_size, list.signature_size); + + lsize = list.signature_list_size; + hsize = list.signature_header_size; + esize = list.signature_size; + elsize = lsize - sizeof(list) - hsize; + + if (lsize > size) { + pr_devel("<--%s() = -EBADMSG [overrun @%x]\n", + __func__, offs); + return -EBADMSG; + } + + if (lsize < sizeof(list) || + lsize - sizeof(list) < hsize || + esize < sizeof(*elem) || + elsize < esize || + elsize % esize != 0) { + pr_devel("- bad size combo @%x\n", offs); + return -EBADMSG; + } + + handler = get_handler_for_guid(&list.signature_type); + if (!handler) { + data += lsize; + size -= lsize; + offs += lsize; + continue; + } + + data += sizeof(list) + hsize; + size -= sizeof(list) + hsize; + offs += sizeof(list) + hsize; + + for (; elsize > 0; elsize -= esize) { + elem = data; + + pr_devel("ELEM[%04x]\n", offs); + handler(source, + &elem->signature_data, + esize - sizeof(*elem)); + + data += esize; + size -= esize; + offs += esize; + } + } + + return 0; +} diff --git a/security/integrity/platform_certs/load_uefi.c b/security/integrity/platform_certs/load_uefi.c new file mode 100644 index 000000000..81b19c528 --- /dev/null +++ b/security/integrity/platform_certs/load_uefi.c @@ -0,0 +1,194 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/cred.h> +#include <linux/err.h> +#include <linux/efi.h> +#include <linux/slab.h> +#include <keys/asymmetric-type.h> +#include <keys/system_keyring.h> +#include "../integrity.h" + +static efi_guid_t efi_cert_x509_guid __initdata = EFI_CERT_X509_GUID; +static efi_guid_t efi_cert_x509_sha256_guid __initdata = + EFI_CERT_X509_SHA256_GUID; +static efi_guid_t efi_cert_sha256_guid __initdata = EFI_CERT_SHA256_GUID; + +/* + * Look to see if a UEFI variable called MokIgnoreDB exists and return true if + * it does. + * + * This UEFI variable is set by the shim if a user tells the shim to not use + * the certs/hashes in the UEFI db variable for verification purposes. If it + * is set, we should ignore the db variable also and the true return indicates + * this. + */ +static __init bool uefi_check_ignore_db(void) +{ + efi_status_t status; + unsigned int db = 0; + unsigned long size = sizeof(db); + efi_guid_t guid = EFI_SHIM_LOCK_GUID; + + status = efi.get_variable(L"MokIgnoreDB", &guid, NULL, &size, &db); + return status == EFI_SUCCESS; +} + +/* + * Get a certificate list blob from the named EFI variable. + */ +static __init void *get_cert_list(efi_char16_t *name, efi_guid_t *guid, + unsigned long *size) +{ + efi_status_t status; + unsigned long lsize = 4; + unsigned long tmpdb[4]; + void *db; + + status = efi.get_variable(name, guid, NULL, &lsize, &tmpdb); + if (status != EFI_BUFFER_TOO_SMALL) { + pr_err("Couldn't get size: 0x%lx\n", status); + return NULL; + } + + db = kmalloc(lsize, GFP_KERNEL); + if (!db) + return NULL; + + status = efi.get_variable(name, guid, NULL, &lsize, db); + if (status != EFI_SUCCESS) { + kfree(db); + pr_err("Error reading db var: 0x%lx\n", status); + return NULL; + } + + *size = lsize; + return db; +} + +/* + * Blacklist a hash. + */ +static __init void uefi_blacklist_hash(const char *source, const void *data, + size_t len, const char *type, + size_t type_len) +{ + char *hash, *p; + + hash = kmalloc(type_len + len * 2 + 1, GFP_KERNEL); + if (!hash) + return; + p = memcpy(hash, type, type_len); + p += type_len; + bin2hex(p, data, len); + p += len * 2; + *p = 0; + + mark_hash_blacklisted(hash); + kfree(hash); +} + +/* + * Blacklist an X509 TBS hash. + */ +static __init void uefi_blacklist_x509_tbs(const char *source, + const void *data, size_t len) +{ + uefi_blacklist_hash(source, data, len, "tbs:", 4); +} + +/* + * Blacklist the hash of an executable. + */ +static __init void uefi_blacklist_binary(const char *source, + const void *data, size_t len) +{ + uefi_blacklist_hash(source, data, len, "bin:", 4); +} + +/* + * Return the appropriate handler for particular signature list types found in + * the UEFI db and MokListRT tables. + */ +static __init efi_element_handler_t get_handler_for_db(const efi_guid_t * + sig_type) +{ + if (efi_guidcmp(*sig_type, efi_cert_x509_guid) == 0) + return add_to_platform_keyring; + return 0; +} + +/* + * Return the appropriate handler for particular signature list types found in + * the UEFI dbx and MokListXRT tables. + */ +static __init efi_element_handler_t get_handler_for_dbx(const efi_guid_t * + sig_type) +{ + if (efi_guidcmp(*sig_type, efi_cert_x509_sha256_guid) == 0) + return uefi_blacklist_x509_tbs; + if (efi_guidcmp(*sig_type, efi_cert_sha256_guid) == 0) + return uefi_blacklist_binary; + return 0; +} + +/* + * Load the certs contained in the UEFI databases into the platform trusted + * keyring and the UEFI blacklisted X.509 cert SHA256 hashes into the blacklist + * keyring. + */ +static int __init load_uefi_certs(void) +{ + efi_guid_t secure_var = EFI_IMAGE_SECURITY_DATABASE_GUID; + efi_guid_t mok_var = EFI_SHIM_LOCK_GUID; + void *db = NULL, *dbx = NULL, *mok = NULL; + unsigned long dbsize = 0, dbxsize = 0, moksize = 0; + int rc = 0; + + if (!efi.get_variable) + return false; + + /* Get db, MokListRT, and dbx. They might not exist, so it isn't + * an error if we can't get them. + */ + if (!uefi_check_ignore_db()) { + db = get_cert_list(L"db", &secure_var, &dbsize); + if (!db) { + pr_err("MODSIGN: Couldn't get UEFI db list\n"); + } else { + rc = parse_efi_signature_list("UEFI:db", + db, dbsize, get_handler_for_db); + if (rc) + pr_err("Couldn't parse db signatures: %d\n", + rc); + kfree(db); + } + } + + mok = get_cert_list(L"MokListRT", &mok_var, &moksize); + if (!mok) { + pr_info("Couldn't get UEFI MokListRT\n"); + } else { + rc = parse_efi_signature_list("UEFI:MokListRT", + mok, moksize, get_handler_for_db); + if (rc) + pr_err("Couldn't parse MokListRT signatures: %d\n", rc); + kfree(mok); + } + + dbx = get_cert_list(L"dbx", &secure_var, &dbxsize); + if (!dbx) { + pr_info("Couldn't get UEFI dbx list\n"); + } else { + rc = parse_efi_signature_list("UEFI:dbx", + dbx, dbxsize, + get_handler_for_dbx); + if (rc) + pr_err("Couldn't parse dbx signatures: %d\n", rc); + kfree(dbx); + } + + return rc; +} +late_initcall(load_uefi_certs); diff --git a/security/integrity/platform_certs/platform_keyring.c b/security/integrity/platform_certs/platform_keyring.c new file mode 100644 index 000000000..bcafd7387 --- /dev/null +++ b/security/integrity/platform_certs/platform_keyring.c @@ -0,0 +1,58 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Platform keyring for firmware/platform keys + * + * Copyright IBM Corporation, 2018 + * Author(s): Nayna Jain <nayna(a)linux.ibm.com> + */ + +#include <linux/export.h> +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/cred.h> +#include <linux/err.h> +#include <linux/slab.h> +#include "../integrity.h" + +/** + * add_to_platform_keyring - Add to platform keyring without validation. + * @source: Source of key + * @data: The blob holding the key + * @len: The length of the data blob + * + * Add a key to the platform keyring without checking its trust chain. This + * is available only during kernel initialisation. + */ +void __init add_to_platform_keyring(const char *source, const void *data, + size_t len) +{ + key_perm_t perm; + int rc; + + perm = (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW; + + rc = integrity_load_cert(INTEGRITY_KEYRING_PLATFORM, source, data, len, + perm); + if (rc) + pr_info("Error adding keys to platform keyring %s\n", source); +} + +/* + * Create the trusted keyrings. + */ +static __init int platform_keyring_init(void) +{ + int rc; + + rc = integrity_init_keyring(INTEGRITY_KEYRING_PLATFORM); + if (rc) + return rc; + + pr_notice("Platform Keyring initialized\n"); + return 0; +} + +/* + * Must be initialised before we try and load the keys into the keyring. + */ +device_initcall(platform_keyring_init); -- 2.27.0

2 35

[PATCH kernel-4.19] scsi: hisi_sas: set sense data when the sas disk's I/O abnormally completed
by Yang Yingliang 23 Sep '21

23 Sep '21

From: yangxingui <yangxingui(a)huawei.com> driver inclusion category: bugfix bugzilla: NA CVE: NA --------------------------- The sense data of the sas disk is used by the kernel and upper layers to perform some policies on disks when the I/O is abnormally completed. Such as the logs as follow, if the driver transmit sense data to the upper layer, the disk may be repaired by remap policy of disk management system. [Wed Sep 15 13:03:04 2021] hisi_sas_v3_hw 0000:74:02.0: erroneous completion iptt=3342 task= pK-error dev id=0 sas_addr=0x5541310520e0b000 CQ hdr: 0x1503 0xd0e 0x0 0x20000 Error info: 0x1200 0x0 0x0 0x40 [Wed Sep 15 13:03:04 2021] hisi_sas_v3_hw 0000:74:02.0: data underflow, rsp_code:0x72, sensekey:0x3, ASC:0x11, ASCQ:0x0. Signed-off-by: yangxingui <yangxingui(a)huawei.com> Reviewed-by: ouyangdelong < ouyangdelong(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/scsi/hisi_sas/hisi_sas.h | 2 ++ drivers/scsi/hisi_sas/hisi_sas_main.c | 17 +++++++++++++++++ drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 1 + 3 files changed, 20 insertions(+) diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h index eae0e533ce7fc..193fc960d87fd 100644 --- a/drivers/scsi/hisi_sas/hisi_sas.h +++ b/drivers/scsi/hisi_sas/hisi_sas.h @@ -571,6 +571,8 @@ extern void hisi_sas_free(struct hisi_hba *hisi_hba); extern u8 hisi_sas_get_ata_protocol(struct host_to_dev_fis *fis, int direction); extern struct hisi_sas_port *to_hisi_sas_port(struct asd_sas_port *sas_port); +extern void hisi_sas_set_sense_data(struct sas_task *task, + struct hisi_sas_slot *slot); extern void hisi_sas_sata_done(struct sas_task *task, struct hisi_sas_slot *slot); extern int hisi_sas_get_fw_info(struct hisi_hba *hisi_hba); diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index f944371ac3133..51555cfc40578 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -105,6 +105,23 @@ u8 hisi_sas_get_ata_protocol(struct host_to_dev_fis *fis, int direction) } EXPORT_SYMBOL_GPL(hisi_sas_get_ata_protocol); +void hisi_sas_set_sense_data(struct sas_task *task, + struct hisi_sas_slot *slot) +{ + struct ssp_response_iu *iu = + hisi_sas_status_buf_addr_mem(slot) + + sizeof(struct hisi_sas_err_record); + if (iu->datapres == 2) { + struct task_status_struct *ts = &task->task_status; + + ts->buf_valid_size = + min_t(int, SAS_STATUS_BUF_SIZE, + be32_to_cpu(iu->sense_data_len)); + memcpy(ts->buf, iu->sense_data, ts->buf_valid_size); + } +} +EXPORT_SYMBOL_GPL(hisi_sas_set_sense_data); + void hisi_sas_sata_done(struct sas_task *task, struct hisi_sas_slot *slot) { diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index a9f53dbb91679..06b4f2db62f7b 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -2234,6 +2234,7 @@ slot_err_v3_hw(struct hisi_hba *hisi_hba, struct sas_task *task, ts->stat = SAS_OPEN_REJECT; ts->open_rej_reason = SAS_OREJ_RSVD_RETRY; } + hisi_sas_set_sense_data(task, slot); break; case SAS_PROTOCOL_SATA: case SAS_PROTOCOL_STP: -- 2.25.1

1 0

[PATCH kernel-4.19 1/2] kyber: introduce kyber_depth_updated()
by Yang Yingliang 23 Sep '21

23 Sep '21

From: Yang Yang <yang.yang(a)vivo.com> mainline inclusion from mainline-5.12-rc1 commit ffa772cfe9356ce94d3061335c2681f60e7c1c5b category: bugfix bugzilla: 182133 CVE: NA ------------------------------------------------- Hang occurs when user changes the scheduler queue depth, by writing to the 'nr_requests' sysfs file of that device. The details of the environment that we found the problem are as follows: an eMMC block device total driver tags: 16 default queue_depth: 32 kqd->async_depth initialized in kyber_init_sched() with queue_depth=32 Then we change queue_depth to 256, by writing to the 'nr_requests' sysfs file. But kqd->async_depth don't be updated after queue_depth changes. Now the value of async depth is too small for queue_depth=256, this may cause hang. This patch introduces kyber_depth_updated(), so that kyber can update async depth when queue depth changes. Signed-off-by: Yang Yang <yang.yang(a)vivo.com> Reviewed-by: Omar Sandoval <osandov(a)fb.com> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Conflict: block/kyber-iosched.c Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- block/kyber-iosched.c | 29 +++++++++++++---------------- 1 file changed, 13 insertions(+), 16 deletions(-) diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c index a1660bafc9124..9eeb60d97f0ca 100644 --- a/block/kyber-iosched.c +++ b/block/kyber-iosched.c @@ -288,15 +288,6 @@ static void kyber_stat_timer_fn(struct blk_stat_callback *cb) blk_stat_activate_msecs(kqd->cb, 100); } -static unsigned int kyber_sched_tags_shift(struct kyber_queue_data *kqd) -{ - /* - * All of the hardware queues have the same depth, so we can just grab - * the shift of the first one. - */ - return kqd->q->queue_hw_ctx[0]->sched_tags->bitmap_tags.sb.shift; -} - static int kyber_bucket_fn(const struct request *rq) { return kyber_sched_domain(rq->cmd_flags); @@ -306,7 +297,6 @@ static struct kyber_queue_data *kyber_queue_data_alloc(struct request_queue *q) { struct kyber_queue_data *kqd; unsigned int max_tokens; - unsigned int shift; int ret = -ENOMEM; int i; @@ -341,9 +331,6 @@ static struct kyber_queue_data *kyber_queue_data_alloc(struct request_queue *q) sbitmap_queue_resize(&kqd->domain_tokens[i], kyber_depth[i]); } - shift = kyber_sched_tags_shift(kqd); - kqd->async_depth = (1U << shift) * KYBER_ASYNC_PERCENT / 100U; - kqd->read_lat_nsec = 2000000ULL; kqd->write_lat_nsec = 10000000ULL; @@ -403,9 +390,19 @@ static void kyber_ctx_queue_init(struct kyber_ctx_queue *kcq) INIT_LIST_HEAD(&kcq->rq_list[i]); } -static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) +static void kyber_depth_updated(struct blk_mq_hw_ctx *hctx) { struct kyber_queue_data *kqd = hctx->queue->elevator->elevator_data; + struct blk_mq_tags *tags = hctx->sched_tags; + unsigned int shift = tags->bitmap_tags.sb.shift; + + kqd->async_depth = (1U << shift) * KYBER_ASYNC_PERCENT / 100U; + + sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, kqd->async_depth); +} + +static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) +{ struct kyber_hctx_data *khd; int i; @@ -446,8 +443,7 @@ static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) khd->batching = 0; hctx->sched_data = khd; - sbitmap_queue_min_shallow_depth(&hctx->sched_tags->bitmap_tags, - kqd->async_depth); + kyber_depth_updated(hctx); return 0; @@ -966,6 +962,7 @@ static struct elevator_type kyber_sched = { .completed_request = kyber_completed_request, .dispatch_request = kyber_dispatch_request, .has_work = kyber_has_work, + .depth_updated = kyber_depth_updated, }, .uses_mq = true, #ifdef CONFIG_BLK_DEBUG_FS -- 2.25.1

1 1

[PATCH kernel-4.19 openEuler-1.0-LTS] blk-mq: handle all throttled io in blk_cleanup_queue()
by Cheng Jian 22 Sep '21

22 Sep '21

From: Yu Kuai <yukuai3(a)huawei.com> hulk inclusion category: bugfix bugzilla: 182132 CVE: NA ------------------------------------------------- All throttled io will never be issued after blk_throtl_exit() in blk_cleanup_queue(), which will lead to hung. Thus handle throttled io before calling blk_throtl_exit() from blk_exit_queue(). Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> --- block/blk-core.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/block/blk-core.c b/block/blk-core.c index 9d2a5a8c78d4..dd3719be9581 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -783,6 +783,16 @@ void blk_cleanup_queue(struct request_queue *q) */ blk_freeze_queue(q); + /* + * All throttled io will never be issued after blk_throtl_exit(), which + * will lead to hung. Thus we need to issue them before calling + * blk_throtl_exit() from blk_exit_queue(). + */ + if (q->mq_ops) { + spin_lock_irq(lock); + blkcg_drain_queue(q); + spin_unlock_irq(lock); + } rq_qos_exit(q); spin_lock_irq(lock); -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS 1/7] memcg: enable accounting for pids in nested pid namespaces
by Yang Yingliang 22 Sep '21

22 Sep '21

From: Vasily Averin <vvs(a)virtuozzo.com> mainline inclusion from mainline-v5.15-rc1 commit fab827dbee8c2e06ca4ba000fa6c48bcf9054aba category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4A0WD CVE: NA -------------------------------- Commit 5d097056c9a0 ("kmemcg: account certain kmem allocations to memcg") enabled memcg accounting for pids allocated from init_pid_ns.pid_cachep, but forgot to adjust the setting for nested pid namespaces. As a result, pid memory is not accounted exactly where it is really needed, inside memcg-limited containers with their own pid namespaces. Pid was one the first kernel objects enabled for memcg accounting. init_pid_ns.pid_cachep marked by SLAB_ACCOUNT and we can expect that any new pids in the system are memcg-accounted. Though recently I've noticed that it is wrong. nested pid namespaces creates own slab caches for pid objects, nested pids have increased size because contain id both for all parent and for own pid namespaces. The problem is that these slab caches are _NOT_ marked by SLAB_ACCOUNT, as a result any pids allocated in nested pid namespaces are not memcg-accounted. Pid struct in nested pid namespace consumes up to 500 bytes memory, 100000 such objects gives us up to ~50Mb unaccounted memory, this allow container to exceed assigned memcg limits. Link: https://lkml.kernel.org/r/8b6de616-fd1a-02c6-cbdb-976ecdcfa604@virtuozzo.com Fixes: 5d097056c9a0 ("kmemcg: account certain kmem allocations to memcg") Cc: stable(a)vger.kernel.org Signed-off-by: Vasily Averin <vvs(a)virtuozzo.com> Reviewed-by: Michal Koutný <mkoutny(a)suse.com> Reviewed-by: Shakeel Butt <shakeelb(a)google.com> Acked-by: Christian Brauner <christian.brauner(a)ubuntu.com> Acked-by: Roman Gushchin <guro(a)fb.com> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Li Ming <limingming.li(a)huawei.com> Signed-off-by: Lu Jialin <lujialin4(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- kernel/pid_namespace.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index dd7a0e41d4016..ad95ca43b51ee 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -52,7 +52,8 @@ static struct kmem_cache *create_pid_cachep(unsigned int level) mutex_lock(&pid_caches_mutex); /* Name collision forces to do allocation under mutex. */ if (!*pkc) - *pkc = kmem_cache_create(name, len, 0, SLAB_HWCACHE_ALIGN, 0); + *pkc = kmem_cache_create(name, len, 0, + SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, 0); mutex_unlock(&pid_caches_mutex); /* current can fail, but someone else can succeed. */ return READ_ONCE(*pkc); -- 2.25.1

1 6

[PATCH openEuler-1.0-LTS] KVM: do not allow mapping valid but non-reference-counted pages
by Yang Yingliang 22 Sep '21

22 Sep '21

From: Nicholas Piggin <npiggin(a)gmail.com> stable inclusion from linux-4.19.199 commit 117777467bc015f0dc5fc079eeba0fa80c965149 CVE: CVE-2021-22543 -------------------------------- commit f8be156be163a052a067306417cd0ff679068c97 upstream. It's possible to create a region which maps valid but non-refcounted pages (e.g., tail pages of non-compound higher order allocations). These host pages can then be returned by gfn_to_page, gfn_to_pfn, etc., family of APIs, which take a reference to the page, which takes it from 0 to 1. When the reference is dropped, this will free the page incorrectly. Fix this by only taking a reference on valid pages if it was non-zero, which indicates it is participating in normal refcounting (and can be released with put_page). This addresses CVE-2021-22543. Signed-off-by: Nicholas Piggin <npiggin(a)gmail.com> Tested-by: Paolo Bonzini <pbonzini(a)redhat.com> Cc: stable(a)vger.kernel.org Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> Signed-off-by: Ovidiu Panait <ovidiu.panait(a)windriver.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- virt/kvm/kvm_main.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 20c53b5cf4837..78bcd465c4f4f 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1484,6 +1484,13 @@ static bool vma_is_valid(struct vm_area_struct *vma, bool write_fault) return true; } +static int kvm_try_get_pfn(kvm_pfn_t pfn) +{ + if (kvm_is_reserved_pfn(pfn)) + return 1; + return get_page_unless_zero(pfn_to_page(pfn)); +} + static int hva_to_pfn_remapped(struct vm_area_struct *vma, unsigned long addr, bool *async, bool write_fault, bool *writable, @@ -1526,11 +1533,19 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma, * Whoever called remap_pfn_range is also going to call e.g. * unmap_mapping_range before the underlying pages are freed, * causing a call to our MMU notifier. + * + * Certain IO or PFNMAP mappings can be backed with valid + * struct pages, but be allocated without refcounting e.g., + * tail pages of non-compound higher order allocations, which + * would then underflow the refcount when the caller does the + * required put_page. Don't allow those pages here. */ - kvm_get_pfn(pfn); + if (!kvm_try_get_pfn(pfn)) + r = -EFAULT; *p_pfn = pfn; - return 0; + + return r; } /* -- 2.25.1

1 0

[PATCH kernel-4.19 1/7] memcg: enable accounting for pids in nested pid namespaces
by Yang Yingliang 22 Sep '21

22 Sep '21

From: Vasily Averin <vvs(a)virtuozzo.com> mainline inclusion from mainline-v5.15-rc1 commit fab827dbee8c2e06ca4ba000fa6c48bcf9054aba category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4A0WD CVE: NA -------------------------------- Commit 5d097056c9a0 ("kmemcg: account certain kmem allocations to memcg") enabled memcg accounting for pids allocated from init_pid_ns.pid_cachep, but forgot to adjust the setting for nested pid namespaces. As a result, pid memory is not accounted exactly where it is really needed, inside memcg-limited containers with their own pid namespaces. Pid was one the first kernel objects enabled for memcg accounting. init_pid_ns.pid_cachep marked by SLAB_ACCOUNT and we can expect that any new pids in the system are memcg-accounted. Though recently I've noticed that it is wrong. nested pid namespaces creates own slab caches for pid objects, nested pids have increased size because contain id both for all parent and for own pid namespaces. The problem is that these slab caches are _NOT_ marked by SLAB_ACCOUNT, as a result any pids allocated in nested pid namespaces are not memcg-accounted. Pid struct in nested pid namespace consumes up to 500 bytes memory, 100000 such objects gives us up to ~50Mb unaccounted memory, this allow container to exceed assigned memcg limits. Link: https://lkml.kernel.org/r/8b6de616-fd1a-02c6-cbdb-976ecdcfa604@virtuozzo.com Fixes: 5d097056c9a0 ("kmemcg: account certain kmem allocations to memcg") Cc: stable(a)vger.kernel.org Signed-off-by: Vasily Averin <vvs(a)virtuozzo.com> Reviewed-by: Michal Koutný <mkoutny(a)suse.com> Reviewed-by: Shakeel Butt <shakeelb(a)google.com> Acked-by: Christian Brauner <christian.brauner(a)ubuntu.com> Acked-by: Roman Gushchin <guro(a)fb.com> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Li Ming <limingming.li(a)huawei.com> Signed-off-by: Lu Jialin <lujialin4(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- kernel/pid_namespace.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index dd7a0e41d4016..ad95ca43b51ee 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -52,7 +52,8 @@ static struct kmem_cache *create_pid_cachep(unsigned int level) mutex_lock(&pid_caches_mutex); /* Name collision forces to do allocation under mutex. */ if (!*pkc) - *pkc = kmem_cache_create(name, len, 0, SLAB_HWCACHE_ALIGN, 0); + *pkc = kmem_cache_create(name, len, 0, + SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, 0); mutex_unlock(&pid_caches_mutex); /* current can fail, but someone else can succeed. */ return READ_ONCE(*pkc); -- 2.25.1

1 6

[PATCH] arm64 support kexec -l -s
by xuhuijie 22 Sep '21

22 Sep '21

support arm64 kexec_file(23): kexec_file: add kexec_file_load system call to unistd.h kexec_file: make kexec_image_post_load_cleanup_default() global kexec_file: drop arch_kexec_mem_walk() kexec_file: factor out memblock-based arch_kexec_walk_mem() kexec_file: kexec_walk_memblock() only walks a dedicated region at kdump kexec_file: add image head flag definitions kexec_file: cpufeature: add MMFR0 helper functions kexec_file: enable KEXEC_FILE config kexec_file: load initrd and device-tree kexec_file: allow for loading Image-format kernel kexec_file: invoke the kernel without purgatory kexec_file: pe.h: remove message[] from mz header definition kexec_file: add kernel signature verification support kexec_file: add kaslr support kexec_file: forbid kdump via kexec_file_load() kexec_file: include fdt_addresses.c kexec_file: include linux/vmalloc.h kexec_file: Refactor setup_dtb() to consolidate error checking kexec_file: add rng-seed support kexec_file: add crash dump support kexec_file: Update to upstream version v1.5.0-23-g87963ee20693 kexec_file: handle empty command-line kexec_file: fix memory leakage in create_dtb() when fdt_open_into() fails support arm64 platform keyring(10): integrity: Define a trusted platform keyring integrity: Load certs to the platform keyring integrity: Add EFI signature data types integrity: Add an EFI signature blob parser integrity: Import certificates from UEFI Secure Boot integrity: Allow the "db" UEFI variable to be suppressed integrity: Support platform keyring for kernel appraisal integrity, KEYS: add a reference to platform keyring integrity: Make use of platform keyring for signature verify integrity: Fix __integrity_init_keyring() section mismatch fix kabi(1): kexec_file: fix kabi because of the new system call sys_kexec_file_load --- arch/arm64/Kconfig | 33 ++ arch/arm64/include/asm/cpufeature.h | 48 +++ arch/arm64/include/asm/image.h | 59 +++ arch/arm64/include/asm/kexec.h | 23 ++ arch/arm64/kernel/Makefile | 3 +- arch/arm64/kernel/cpu-reset.S | 8 +- arch/arm64/kernel/head.S | 3 +- arch/arm64/kernel/image.h | 21 +- arch/arm64/kernel/kexec_image.c | 126 +++++++ arch/arm64/kernel/machine_kexec.c | 12 +- arch/arm64/kernel/machine_kexec_file.c | 342 ++++++++++++++++++ arch/arm64/kernel/relocate_kernel.S | 3 +- arch/powerpc/kernel/machine_kexec_file_64.c | 54 --- arch/s390/kernel/machine_kexec_file.c | 10 - arch/x86/kernel/kexec-bzimage64.c | 14 +- certs/system_keyring.c | 23 +- include/keys/system_keyring.h | 8 + include/linux/efi.h | 34 ++ include/linux/kexec.h | 15 +- include/linux/pe.h | 2 +- include/linux/verification.h | 1 + include/uapi/linux/kexec.h | 1 + kernel/kexec.c | 10 + kernel/kexec_file.c | 160 +++++++- lib/Makefile | 2 +- lib/fdt_addresses.c | 2 + scripts/dtc/libfdt/fdt_addresses.c | 47 +++ scripts/dtc/libfdt/libfdt.h | 61 ++++ security/integrity/Kconfig | 11 + security/integrity/Makefile | 5 + security/integrity/digsig.c | 114 ++++-- security/integrity/ima/ima_appraise.c | 14 +- security/integrity/integrity.h | 23 +- .../integrity/platform_certs/efi_parser.c | 108 ++++++ security/integrity/platform_certs/load_uefi.c | 194 ++++++++++ .../platform_certs/platform_keyring.c | 58 +++ 36 files changed, 1518 insertions(+), 134 deletions(-) create mode 100644 arch/arm64/include/asm/image.h create mode 100644 arch/arm64/kernel/kexec_image.c create mode 100644 arch/arm64/kernel/machine_kexec_file.c create mode 100644 lib/fdt_addresses.c create mode 100644 security/integrity/platform_certs/efi_parser.c create mode 100644 security/integrity/platform_certs/load_uefi.c create mode 100644 security/integrity/platform_certs/platform_keyring.c diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 9dfbd052b..5381d21bb 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -957,6 +957,39 @@ config KEXEC but it is independent of the system firmware. And like a reboot you can start any kernel with it, not just Linux. +config KEXEC_FILE + bool "kexec file based system call" + select KEXEC_CORE + help + This is new version of kexec system call. This system call is + file based and takes file descriptors as system call argument + for kernel and initramfs as opposed to list of segments as + accepted by previous system call. + +config KEXEC_VERIFY_SIG + bool "Verify kernel signature during kexec_file_load() syscall" + depends on KEXEC_FILE + help + Select this option to verify a signature with loaded kernel + image. If configured, any attempt of loading a image without + valid signature will fail. + + In addition to that option, you need to enable signature + verification for the corresponding kernel image type being + loaded in order for this to work. + +config KEXEC_IMAGE_VERIFY_SIG + bool "Enable Image signature verification support" + default y + depends on KEXEC_VERIFY_SIG + depends on EFI && SIGNED_PE_FILE_VERIFICATION + help + Enable Image signature verification support. + +comment "Support for PE file signature verification disabled" + depends on KEXEC_VERIFY_SIG + depends on !EFI || !SIGNED_PE_FILE_VERIFICATION + config CRASH_DUMP bool "Build kdump crash kernel" help diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index c43d02365..211aa994b 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -497,11 +497,59 @@ static inline bool system_supports_32bit_el0(void) return cpus_have_const_cap(ARM64_HAS_32BIT_EL0); } +static inline bool system_supports_4kb_granule(void) +{ + u64 mmfr0; + u32 val; + + mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); + val = cpuid_feature_extract_unsigned_field(mmfr0, + ID_AA64MMFR0_TGRAN4_SHIFT); + + return val == ID_AA64MMFR0_TGRAN4_SUPPORTED; +} + +static inline bool system_supports_64kb_granule(void) +{ + u64 mmfr0; + u32 val; + + mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); + val = cpuid_feature_extract_unsigned_field(mmfr0, + ID_AA64MMFR0_TGRAN64_SHIFT); + + return val == ID_AA64MMFR0_TGRAN64_SUPPORTED; +} + +static inline bool system_supports_16kb_granule(void) +{ + u64 mmfr0; + u32 val; + + mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); + val = cpuid_feature_extract_unsigned_field(mmfr0, + ID_AA64MMFR0_TGRAN16_SHIFT); + + return val == ID_AA64MMFR0_TGRAN16_SUPPORTED; +} + static inline bool system_supports_mixed_endian_el0(void) { return id_aa64mmfr0_mixed_endian_el0(read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1)); } +static inline bool system_supports_mixed_endian(void) +{ + u64 mmfr0; + u32 val; + + mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); + val = cpuid_feature_extract_unsigned_field(mmfr0, + ID_AA64MMFR0_BIGENDEL_SHIFT); + + return val == 0x1; +} + static inline bool system_supports_fpsimd(void) { return !cpus_have_const_cap(ARM64_HAS_NO_FPSIMD); diff --git a/arch/arm64/include/asm/image.h b/arch/arm64/include/asm/image.h new file mode 100644 index 000000000..e2c27a227 --- /dev/null +++ b/arch/arm64/include/asm/image.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __ASM_IMAGE_H +#define __ASM_IMAGE_H + +#define ARM64_IMAGE_MAGIC "ARM\x64" + +#define ARM64_IMAGE_FLAG_BE_SHIFT 0 +#define ARM64_IMAGE_FLAG_PAGE_SIZE_SHIFT (ARM64_IMAGE_FLAG_BE_SHIFT + 1) +#define ARM64_IMAGE_FLAG_PHYS_BASE_SHIFT \ + (ARM64_IMAGE_FLAG_PAGE_SIZE_SHIFT + 2) +#define ARM64_IMAGE_FLAG_BE_MASK 0x1 +#define ARM64_IMAGE_FLAG_PAGE_SIZE_MASK 0x3 +#define ARM64_IMAGE_FLAG_PHYS_BASE_MASK 0x1 + +#define ARM64_IMAGE_FLAG_LE 0 +#define ARM64_IMAGE_FLAG_BE 1 +#define ARM64_IMAGE_FLAG_PAGE_SIZE_4K 1 +#define ARM64_IMAGE_FLAG_PAGE_SIZE_16K 2 +#define ARM64_IMAGE_FLAG_PAGE_SIZE_64K 3 +#define ARM64_IMAGE_FLAG_PHYS_BASE 1 + +#ifndef __ASSEMBLY__ + +#define arm64_image_flag_field(flags, field) \ + (((flags) >> field##_SHIFT) & field##_MASK) + +/* + * struct arm64_image_header - arm64 kernel image header + * See Documentation/arm64/booting.txt for details + * + * @code0: Executable code, or + * @mz_header alternatively used for part of MZ header + * @code1: Executable code + * @text_offset: Image load offset + * @image_size: Effective Image size + * @flags: kernel flags + * @reserved: reserved + * @magic: Magic number + * @reserved5: reserved, or + * @pe_header: alternatively used for PE COFF offset + */ + +struct arm64_image_header { + __le32 code0; + __le32 code1; + __le64 text_offset; + __le64 image_size; + __le64 flags; + __le64 res2; + __le64 res3; + __le64 res4; + __le32 magic; + __le32 res5; +}; + +#endif /* __ASSEMBLY__ */ + +#endif /* __ASM_IMAGE_H */ diff --git a/arch/arm64/include/asm/kexec.h b/arch/arm64/include/asm/kexec.h index 30ab1fa34..286950227 100644 --- a/arch/arm64/include/asm/kexec.h +++ b/arch/arm64/include/asm/kexec.h @@ -101,6 +101,29 @@ static inline void crash_prepare_suspend(void) {} static inline void crash_post_resume(void) {} #endif +#ifdef CONFIG_KEXEC_FILE +#define ARCH_HAS_KIMAGE_ARCH + +struct kimage_arch { + void *dtb; + unsigned long dtb_mem; + /* Core ELF header buffer */ + void *elf_headers; + unsigned long elf_headers_mem; + unsigned long elf_headers_sz; +}; + +extern const struct kexec_file_ops kexec_image_ops; + +struct kimage; + +extern int arch_kimage_file_post_load_cleanup(struct kimage *image); +extern int load_other_segments(struct kimage *image, + unsigned long kernel_load_addr, unsigned long kernel_size, + char *initrd, unsigned long initrd_len, + char *cmdline); +#endif + void machine_kexec_mask_interrupts(void); #endif /* __ASSEMBLY__ */ diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index fe759f364..2e21303b6 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -54,8 +54,9 @@ arm64-obj-$(CONFIG_ARM64_ACPI_PARKING_PROTOCOL) += acpi_parking_protocol.o arm64-obj-$(CONFIG_PARAVIRT) += paravirt.o paravirt-spinlocks.o arm64-obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o arm64-obj-$(CONFIG_HIBERNATION) += hibernate.o hibernate-asm.o -arm64-obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o \ +arm64-obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o relocate_kernel.o \ cpu-reset.o +arm64-obj-$(CONFIG_KEXEC_FILE) += machine_kexec_file.o kexec_image.o arm64-obj-$(CONFIG_ARM64_CPU_PARK) += cpu-park.o arm64-obj-$(CONFIG_ARM64_RELOC_TEST) += arm64-reloc-test.o arm64-reloc-test-y := reloc_test_core.o reloc_test_syms.o diff --git a/arch/arm64/kernel/cpu-reset.S b/arch/arm64/kernel/cpu-reset.S index 8021b46c9..a2be30275 100644 --- a/arch/arm64/kernel/cpu-reset.S +++ b/arch/arm64/kernel/cpu-reset.S @@ -22,11 +22,11 @@ * __cpu_soft_restart(el2_switch, entry, arg0, arg1, arg2) - Helper for * cpu_soft_restart. * - * @el2_switch: Flag to indicate a swich to EL2 is needed. + * @el2_switch: Flag to indicate a switch to EL2 is needed. * @entry: Location to jump to for soft reset. - * arg0: First argument passed to @entry. - * arg1: Second argument passed to @entry. - * arg2: Third argument passed to @entry. + * arg0: First argument passed to @entry. (relocation list) + * arg1: Second argument passed to @entry.(physical kernel entry) + * arg2: Third argument passed to @entry. (physical dtb address) * * Put the CPU into the same state as it would be if it had been reset, and * branch to what would be the reset vector. It must be executed with the diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 34bd0790d..5edfb9cfd 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -31,6 +31,7 @@ #include <asm/cache.h> #include <asm/cputype.h> #include <asm/elf.h> +#include <asm/image.h> #include <asm/kernel-pgtable.h> #include <asm/kvm_arm.h> #include <asm/memory.h> @@ -91,7 +92,7 @@ _head: .quad 0 // reserved .quad 0 // reserved .quad 0 // reserved - .ascii "ARM\x64" // Magic number + .ascii ARM64_IMAGE_MAGIC // Magic number #ifdef CONFIG_EFI .long pe_header - _head // Offset to the PE header. diff --git a/arch/arm64/kernel/image.h b/arch/arm64/kernel/image.h index eff6a564a..b22e8ad07 100644 --- a/arch/arm64/kernel/image.h +++ b/arch/arm64/kernel/image.h @@ -15,13 +15,15 @@ * You should have received a copy of the GNU General Public License * along with this program. If not, see <http://www.gnu.org/licenses/>. */ -#ifndef __ASM_IMAGE_H -#define __ASM_IMAGE_H +#ifndef __ARM64_KERNEL_IMAGE_H +#define __ARM64_KERNEL_IMAGE_H #ifndef LINKER_SCRIPT #error This file should only be included in vmlinux.lds.S #endif +#include <asm/image.h> + /* * There aren't any ELF relocations we can use to endian-swap values known only * at link time (e.g. the subtraction of two symbol addresses), so we must get @@ -47,19 +49,22 @@ sym##_lo32 = DATA_LE32((data) & 0xffffffff); \ sym##_hi32 = DATA_LE32((data) >> 32) +#define __HEAD_FLAG(field) (__HEAD_FLAG_##field << \ + ARM64_IMAGE_FLAG_##field##_SHIFT) + #ifdef CONFIG_CPU_BIG_ENDIAN -#define __HEAD_FLAG_BE 1 +#define __HEAD_FLAG_BE ARM64_IMAGE_FLAG_BE #else -#define __HEAD_FLAG_BE 0 +#define __HEAD_FLAG_BE ARM64_IMAGE_FLAG_LE #endif #define __HEAD_FLAG_PAGE_SIZE ((PAGE_SHIFT - 10) / 2) #define __HEAD_FLAG_PHYS_BASE 1 -#define __HEAD_FLAGS ((__HEAD_FLAG_BE << 0) | \ - (__HEAD_FLAG_PAGE_SIZE << 1) | \ - (__HEAD_FLAG_PHYS_BASE << 3)) +#define __HEAD_FLAGS (__HEAD_FLAG(BE) | \ + __HEAD_FLAG(PAGE_SIZE) | \ + __HEAD_FLAG(PHYS_BASE)) /* * These will output as part of the Image header, which should be little-endian @@ -113,4 +118,4 @@ __efistub_screen_info = screen_info; #endif -#endif /* __ASM_IMAGE_H */ +#endif /* __ARM64_KERNEL_IMAGE_H */ diff --git a/arch/arm64/kernel/kexec_image.c b/arch/arm64/kernel/kexec_image.c new file mode 100644 index 000000000..1ad1d5f8f --- /dev/null +++ b/arch/arm64/kernel/kexec_image.c @@ -0,0 +1,126 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Kexec image loader + + * Copyright (C) 2018 Linaro Limited + * Author: AKASHI Takahiro <takahiro.akashi(a)linaro.org> + */ + +#define pr_fmt(fmt) "kexec_file(Image): " fmt + +#include <linux/err.h> +#include <linux/errno.h> +#include <linux/kernel.h> +#include <linux/kexec.h> +#include <linux/pe.h> +#include <linux/string.h> +#include <linux/verification.h> +#include <asm/byteorder.h> +#include <asm/cpufeature.h> +#include <asm/image.h> +#include <asm/memory.h> + +static int image_probe(const char *kernel_buf, unsigned long kernel_len) +{ + const struct arm64_image_header *h = + (const struct arm64_image_header *)(kernel_buf); + + if (!h || (kernel_len < sizeof(*h))) + return -EINVAL; + + if (memcmp(&h->magic, ARM64_IMAGE_MAGIC, sizeof(h->magic))) + return -EINVAL; + + return 0; +} + +static void *image_load(struct kimage *image, + char *kernel, unsigned long kernel_len, + char *initrd, unsigned long initrd_len, + char *cmdline, unsigned long cmdline_len) +{ + struct arm64_image_header *h; + u64 flags, value; + bool be_image, be_kernel; + struct kexec_buf kbuf; + unsigned long text_offset; + struct kexec_segment *kernel_segment; + int ret; + + /* + * We require a kernel with an unambiguous Image header. Per + * Documentation/booting.txt, this is the case when image_size + * is non-zero (practically speaking, since v3.17). + */ + h = (struct arm64_image_header *)kernel; + if (!h->image_size) + return ERR_PTR(-EINVAL); + + /* Check cpu features */ + flags = le64_to_cpu(h->flags); + be_image = arm64_image_flag_field(flags, ARM64_IMAGE_FLAG_BE); + be_kernel = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN); + if ((be_image != be_kernel) && !system_supports_mixed_endian()) + return ERR_PTR(-EINVAL); + + value = arm64_image_flag_field(flags, ARM64_IMAGE_FLAG_PAGE_SIZE); + if (((value == ARM64_IMAGE_FLAG_PAGE_SIZE_4K) && + !system_supports_4kb_granule()) || + ((value == ARM64_IMAGE_FLAG_PAGE_SIZE_64K) && + !system_supports_64kb_granule()) || + ((value == ARM64_IMAGE_FLAG_PAGE_SIZE_16K) && + !system_supports_16kb_granule())) + return ERR_PTR(-EINVAL); + + /* Load the kernel */ + kbuf.image = image; + kbuf.buf_min = 0; + kbuf.buf_max = ULONG_MAX; + kbuf.top_down = false; + + kbuf.buffer = kernel; + kbuf.bufsz = kernel_len; + kbuf.mem = 0; + kbuf.memsz = le64_to_cpu(h->image_size); + text_offset = le64_to_cpu(h->text_offset); + kbuf.buf_align = MIN_KIMG_ALIGN; + + /* Adjust kernel segment with TEXT_OFFSET */ + kbuf.memsz += text_offset; + + ret = kexec_add_buffer(&kbuf); + if (ret) + return ERR_PTR(ret); + + kernel_segment = &image->segment[image->nr_segments - 1]; + kernel_segment->mem += text_offset; + kernel_segment->memsz -= text_offset; + image->start = kernel_segment->mem; + + pr_debug("Loaded kernel at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + kernel_segment->mem, kbuf.bufsz, + kernel_segment->memsz); + + /* Load additional data */ + ret = load_other_segments(image, + kernel_segment->mem, kernel_segment->memsz, + initrd, initrd_len, cmdline); + + return ERR_PTR(ret); +} + +#ifdef CONFIG_KEXEC_IMAGE_VERIFY_SIG +static int image_verify_sig(const char *kernel, unsigned long kernel_len) +{ + return verify_pefile_signature(kernel, kernel_len, NULL, + VERIFYING_KEXEC_PE_SIGNATURE); +} +#endif + +const struct kexec_file_ops kexec_image_ops = { + .probe = image_probe, + .load = image_load, +#ifdef CONFIG_KEXEC_IMAGE_VERIFY_SIG + .verify_sig = image_verify_sig, +#endif +}; diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c index b41d6d482..213d0053e 100644 --- a/arch/arm64/kernel/machine_kexec.c +++ b/arch/arm64/kernel/machine_kexec.c @@ -214,9 +214,17 @@ void machine_kexec(struct kimage *kimage) * uses physical addressing to relocate the new image to its final * position and transfers control to the image entry point when the * relocation is complete. + * In kexec case, kimage->start points to purgatory assuming that + * kernel entry and dtb address are embedded in purgatory by + * userspace (kexec-tools). + * In kexec_file case, the kernel starts directly without purgatory. */ - - cpu_soft_restart(reboot_code_buffer_phys, kimage->head, kimage->start, 0); + cpu_soft_restart(reboot_code_buffer_phys, kimage->head, kimage->start, +#ifdef CONFIG_KEXEC_FILE + kimage->arch.dtb_mem); +#else + 0); +#endif BUG(); /* Should never get here. */ } diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c new file mode 100644 index 000000000..ec3b72dc0 --- /dev/null +++ b/arch/arm64/kernel/machine_kexec_file.c @@ -0,0 +1,342 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * kexec_file for arm64 + * + * Copyright (C) 2018 Linaro Limited + * Author: AKASHI Takahiro <takahiro.akashi(a)linaro.org> + * + * Most code is derived from arm64 port of kexec-tools + */ + +#define pr_fmt(fmt) "kexec_file: " fmt + +#include <linux/ioport.h> +#include <linux/kernel.h> +#include <linux/kexec.h> +#include <linux/libfdt.h> +#include <linux/memblock.h> +#include <linux/of_fdt.h> +#include <linux/random.h> +#include <linux/slab.h> +#include <linux/string.h> +#include <linux/types.h> +#include <linux/vmalloc.h> +#include <asm/byteorder.h> + +/* relevant device tree properties */ +#define FDT_PROP_KEXEC_ELFHDR "linux,elfcorehdr" +#define FDT_PROP_MEM_RANGE "linux,usable-memory-range" +#define FDT_PROP_INITRD_START "linux,initrd-start" +#define FDT_PROP_INITRD_END "linux,initrd-end" +#define FDT_PROP_BOOTARGS "bootargs" +#define FDT_PROP_KASLR_SEED "kaslr-seed" +#define FDT_PROP_RNG_SEED "rng-seed" +#define RNG_SEED_SIZE 128 + +const struct kexec_file_ops * const kexec_file_loaders[] = { + &kexec_image_ops, + NULL +}; + +int arch_kimage_file_post_load_cleanup(struct kimage *image) +{ + vfree(image->arch.dtb); + image->arch.dtb = NULL; + + vfree(image->arch.elf_headers); + image->arch.elf_headers = NULL; + image->arch.elf_headers_sz = 0; + + return kexec_image_post_load_cleanup_default(image); +} + +static int setup_dtb(struct kimage *image, + unsigned long initrd_load_addr, unsigned long initrd_len, + char *cmdline, void *dtb) +{ + int off, ret; + + ret = fdt_path_offset(dtb, "/chosen"); + if (ret < 0) + goto out; + + off = ret; + + ret = fdt_delprop(dtb, off, FDT_PROP_KEXEC_ELFHDR); + if (ret && ret != -FDT_ERR_NOTFOUND) + goto out; + ret = fdt_delprop(dtb, off, FDT_PROP_MEM_RANGE); + if (ret && ret != -FDT_ERR_NOTFOUND) + goto out; + + if (image->type == KEXEC_TYPE_CRASH) { + /* add linux,elfcorehdr */ + ret = fdt_appendprop_addrrange(dtb, 0, off, + FDT_PROP_KEXEC_ELFHDR, + image->arch.elf_headers_mem, + image->arch.elf_headers_sz); + if (ret) + return (ret == -FDT_ERR_NOSPACE ? -ENOMEM : -EINVAL); + + /* add linux,usable-memory-range */ + ret = fdt_appendprop_addrrange(dtb, 0, off, + FDT_PROP_MEM_RANGE, + crashk_res.start, + crashk_res.end - crashk_res.start + 1); + if (ret) + return (ret == -FDT_ERR_NOSPACE ? -ENOMEM : -EINVAL); + } + + /* add bootargs */ + if (cmdline) { + ret = fdt_setprop_string(dtb, off, FDT_PROP_BOOTARGS, cmdline); + if (ret) + goto out; + } else { + ret = fdt_delprop(dtb, off, FDT_PROP_BOOTARGS); + if (ret && (ret != -FDT_ERR_NOTFOUND)) + goto out; + } + + /* add initrd-* */ + if (initrd_load_addr) { + ret = fdt_setprop_u64(dtb, off, FDT_PROP_INITRD_START, + initrd_load_addr); + if (ret) + goto out; + + ret = fdt_setprop_u64(dtb, off, FDT_PROP_INITRD_END, + initrd_load_addr + initrd_len); + if (ret) + goto out; + } else { + ret = fdt_delprop(dtb, off, FDT_PROP_INITRD_START); + if (ret && (ret != -FDT_ERR_NOTFOUND)) + goto out; + + ret = fdt_delprop(dtb, off, FDT_PROP_INITRD_END); + if (ret && (ret != -FDT_ERR_NOTFOUND)) + goto out; + } + + /* add kaslr-seed */ + ret = fdt_delprop(dtb, off, FDT_PROP_KASLR_SEED); + if (ret && (ret != -FDT_ERR_NOTFOUND)) + goto out; + + if (rng_is_initialized()) { + u64 seed = get_random_u64(); + ret = fdt_setprop_u64(dtb, off, FDT_PROP_KASLR_SEED, seed); + if (ret) + goto out; + } else { + pr_notice("RNG is not initialised: omitting \"%s\" property\n", + FDT_PROP_KASLR_SEED); + } + + /* add rng-seed */ + if (rng_is_initialized()) { + u8 rng_seed[RNG_SEED_SIZE]; + get_random_bytes(rng_seed, RNG_SEED_SIZE); + ret = fdt_setprop(dtb, off, FDT_PROP_RNG_SEED, rng_seed, + RNG_SEED_SIZE); + if (ret) + goto out; + } else { + pr_notice("RNG is not initialised: omitting \"%s\" property\n", + FDT_PROP_RNG_SEED); + } + +out: + if (ret) + return (ret == -FDT_ERR_NOSPACE) ? -ENOMEM : -EINVAL; + + return 0; +} + +/* + * More space needed so that we can add initrd, bootargs, kaslr-seed, + * rng-seed, userable-memory-range and elfcorehdr. + */ +#define DTB_EXTRA_SPACE 0x1000 + +static int create_dtb(struct kimage *image, + unsigned long initrd_load_addr, unsigned long initrd_len, + char *cmdline, void **dtb) +{ + void *buf; + size_t buf_size; + size_t cmdline_len; + int ret; + + cmdline_len = cmdline ? strlen(cmdline) : 0; + buf_size = fdt_totalsize(initial_boot_params) + + cmdline_len + DTB_EXTRA_SPACE; + + for (;;) { + buf = vmalloc(buf_size); + if (!buf) + return -ENOMEM; + + /* duplicate a device tree blob */ + ret = fdt_open_into(initial_boot_params, buf, buf_size); + if (ret) { + vfree(buf); + return -EINVAL; + } + + ret = setup_dtb(image, initrd_load_addr, initrd_len, + cmdline, buf); + if (ret) { + vfree(buf); + if (ret == -ENOMEM) { + /* unlikely, but just in case */ + buf_size += DTB_EXTRA_SPACE; + continue; + } else { + return ret; + } + } + + /* trim it */ + fdt_pack(buf); + *dtb = buf; + + return 0; + } +} + +static int prepare_elf_headers(void **addr, unsigned long *sz) +{ + struct crash_mem *cmem; + unsigned int nr_ranges; + int ret; + u64 i; + phys_addr_t start, end; + + nr_ranges = 1; /* for exclusion of crashkernel region */ + for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE, + MEMBLOCK_NONE, &start, &end, NULL) + nr_ranges++; + + cmem = kmalloc(sizeof(struct crash_mem) + + sizeof(struct crash_mem_range) * nr_ranges, GFP_KERNEL); + if (!cmem) + return -ENOMEM; + + cmem->max_nr_ranges = nr_ranges; + cmem->nr_ranges = 0; + for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE, + MEMBLOCK_NONE, &start, &end, NULL) { + cmem->ranges[cmem->nr_ranges].start = start; + cmem->ranges[cmem->nr_ranges].end = end - 1; + cmem->nr_ranges++; + } + + /* Exclude crashkernel region */ + ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end); + + if (!ret) + ret = crash_prepare_elf64_headers(cmem, true, addr, sz); + + kfree(cmem); + return ret; +} + +int load_other_segments(struct kimage *image, + unsigned long kernel_load_addr, + unsigned long kernel_size, + char *initrd, unsigned long initrd_len, + char *cmdline) +{ + struct kexec_buf kbuf; + void *headers, *dtb = NULL; + unsigned long headers_sz, initrd_load_addr = 0, dtb_len; + int ret = 0; + + kbuf.image = image; + /* not allocate anything below the kernel */ + kbuf.buf_min = kernel_load_addr + kernel_size; + + /* load elf core header */ + if (image->type == KEXEC_TYPE_CRASH) { + ret = prepare_elf_headers(&headers, &headers_sz); + if (ret) { + pr_err("Preparing elf core header failed\n"); + goto out_err; + } + + kbuf.buffer = headers; + kbuf.bufsz = headers_sz; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + kbuf.memsz = headers_sz; + kbuf.buf_align = SZ_64K; /* largest supported page size */ + kbuf.buf_max = ULONG_MAX; + kbuf.top_down = true; + + ret = kexec_add_buffer(&kbuf); + if (ret) { + vfree(headers); + goto out_err; + } + image->arch.elf_headers = headers; + image->arch.elf_headers_mem = kbuf.mem; + image->arch.elf_headers_sz = headers_sz; + + pr_debug("Loaded elf core header at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + image->arch.elf_headers_mem, headers_sz, headers_sz); + } + + /* load initrd */ + if (initrd) { + kbuf.buffer = initrd; + kbuf.bufsz = initrd_len; + kbuf.mem = 0; + kbuf.memsz = initrd_len; + kbuf.buf_align = 0; + /* within 1GB-aligned window of up to 32GB in size */ + kbuf.buf_max = round_down(kernel_load_addr, SZ_1G) + + (unsigned long)SZ_1G * 32; + kbuf.top_down = false; + + ret = kexec_add_buffer(&kbuf); + if (ret) + goto out_err; + initrd_load_addr = kbuf.mem; + + pr_debug("Loaded initrd at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + initrd_load_addr, initrd_len, initrd_len); + } + + /* load dtb */ + ret = create_dtb(image, initrd_load_addr, initrd_len, cmdline, &dtb); + if (ret) { + pr_err("Preparing for new dtb failed\n"); + goto out_err; + } + + dtb_len = fdt_totalsize(dtb); + kbuf.buffer = dtb; + kbuf.bufsz = dtb_len; + kbuf.mem = 0; + kbuf.memsz = dtb_len; + /* not across 2MB boundary */ + kbuf.buf_align = SZ_2M; + kbuf.buf_max = ULONG_MAX; + kbuf.top_down = true; + + ret = kexec_add_buffer(&kbuf); + if (ret) + goto out_err; + image->arch.dtb = dtb; + image->arch.dtb_mem = kbuf.mem; + + pr_debug("Loaded dtb at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + kbuf.mem, dtb_len, dtb_len); + + return 0; + +out_err: + vfree(dtb); + return ret; +} diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S index f407e422a..95fd94209 100644 --- a/arch/arm64/kernel/relocate_kernel.S +++ b/arch/arm64/kernel/relocate_kernel.S @@ -32,6 +32,7 @@ ENTRY(arm64_relocate_new_kernel) /* Setup the list loop variables. */ + mov x18, x2 /* x18 = dtb address */ mov x17, x1 /* x17 = kimage_start */ mov x16, x0 /* x16 = kimage_head */ raw_dcache_line_size x15, x0 /* x15 = dcache line size */ @@ -107,7 +108,7 @@ ENTRY(arm64_relocate_new_kernel) isb /* Start new image. */ - mov x0, xzr + mov x0, x18 mov x1, xzr mov x2, xzr mov x3, xzr diff --git a/arch/powerpc/kernel/machine_kexec_file_64.c b/arch/powerpc/kernel/machine_kexec_file_64.c index c77e95e9b..0d20c7ad4 100644 --- a/arch/powerpc/kernel/machine_kexec_file_64.c +++ b/arch/powerpc/kernel/machine_kexec_file_64.c @@ -24,7 +24,6 @@ #include <linux/slab.h> #include <linux/kexec.h> -#include <linux/memblock.h> #include <linux/of_fdt.h> #include <linux/libfdt.h> #include <asm/ima.h> @@ -46,59 +45,6 @@ int arch_kexec_kernel_image_probe(struct kimage *image, void *buf, return kexec_image_probe_default(image, buf, buf_len); } -/** - * arch_kexec_walk_mem - call func(data) for each unreserved memory block - * @kbuf: Context info for the search. Also passed to @func. - * @func: Function to call for each memory block. - * - * This function is used by kexec_add_buffer and kexec_locate_mem_hole - * to find unreserved memory to load kexec segments into. - * - * Return: The memory walk will stop when func returns a non-zero value - * and that value will be returned. If all free regions are visited without - * func returning non-zero, then zero will be returned. - */ -int arch_kexec_walk_mem(struct kexec_buf *kbuf, - int (*func)(struct resource *, void *)) -{ - int ret = 0; - u64 i; - phys_addr_t mstart, mend; - struct resource res = { }; - - if (kbuf->top_down) { - for_each_free_mem_range_reverse(i, NUMA_NO_NODE, 0, - &mstart, &mend, NULL) { - /* - * In memblock, end points to the first byte after the - * range while in kexec, end points to the last byte - * in the range. - */ - res.start = mstart; - res.end = mend - 1; - ret = func(&res, kbuf); - if (ret) - break; - } - } else { - for_each_free_mem_range(i, NUMA_NO_NODE, 0, &mstart, &mend, - NULL) { - /* - * In memblock, end points to the first byte after the - * range while in kexec, end points to the last byte - * in the range. - */ - res.start = mstart; - res.end = mend - 1; - ret = func(&res, kbuf); - if (ret) - break; - } - } - - return ret; -} - /** * setup_purgatory - initialize the purgatory's global variables * @image: kexec image. diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c index f413f57f8..32023b4f9 100644 --- a/arch/s390/kernel/machine_kexec_file.c +++ b/arch/s390/kernel/machine_kexec_file.c @@ -134,16 +134,6 @@ int kexec_file_add_initrd(struct kimage *image, struct s390_load_data *data, return ret; } -/* - * The kernel is loaded to a fixed location. Turn off kexec_locate_mem_hole - * and provide kbuf->mem by hand. - */ -int arch_kexec_walk_mem(struct kexec_buf *kbuf, - int (*func)(struct resource *, void *)) -{ - return 1; -} - int arch_kexec_apply_relocations_add(struct purgatory_info *pi, Elf_Shdr *section, const Elf_Shdr *relsec, diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index 70caa60b4..8977de5ad 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -535,9 +535,17 @@ static int bzImage64_cleanup(void *loader_data) #ifdef CONFIG_KEXEC_BZIMAGE_VERIFY_SIG static int bzImage64_verify_sig(const char *kernel, unsigned long kernel_len) { - return verify_pefile_signature(kernel, kernel_len, - VERIFY_USE_SECONDARY_KEYRING, - VERIFYING_KEXEC_PE_SIGNATURE); + int ret; + + ret = verify_pefile_signature(kernel, kernel_len, + VERIFY_USE_SECONDARY_KEYRING, + VERIFYING_KEXEC_PE_SIGNATURE); + if (ret == -ENOKEY && IS_ENABLED(CONFIG_INTEGRITY_PLATFORM_KEYRING)) { + ret = verify_pefile_signature(kernel, kernel_len, + VERIFY_USE_PLATFORM_KEYRING, + VERIFYING_KEXEC_PE_SIGNATURE); + } + return ret; } #endif diff --git a/certs/system_keyring.c b/certs/system_keyring.c index 817287175..c05c29ae4 100644 --- a/certs/system_keyring.c +++ b/certs/system_keyring.c @@ -24,6 +24,9 @@ static struct key *builtin_trusted_keys; #ifdef CONFIG_SECONDARY_TRUSTED_KEYRING static struct key *secondary_trusted_keys; #endif +#ifdef CONFIG_INTEGRITY_PLATFORM_KEYRING +static struct key *platform_trusted_keys; +#endif extern __initconst const u8 system_certificate_list[]; extern __initconst const unsigned long system_certificate_list_size; @@ -237,11 +240,22 @@ int verify_pkcs7_signature(const void *data, size_t len, #else trusted_keys = builtin_trusted_keys; #endif + } else if (trusted_keys == VERIFY_USE_PLATFORM_KEYRING) { +#ifdef CONFIG_INTEGRITY_PLATFORM_KEYRING + trusted_keys = platform_trusted_keys; +#else + trusted_keys = NULL; +#endif + if (!trusted_keys) { + ret = -ENOKEY; + pr_devel("PKCS#7 platform keyring is not available\n"); + goto error; + } } ret = pkcs7_validate_trust(pkcs7, trusted_keys); if (ret < 0) { if (ret == -ENOKEY) - pr_err("PKCS#7 signature not signed with a trusted key\n"); + pr_devel("PKCS#7 signature not signed with a trusted key\n"); goto error; } @@ -266,3 +280,10 @@ int verify_pkcs7_signature(const void *data, size_t len, EXPORT_SYMBOL_GPL(verify_pkcs7_signature); #endif /* CONFIG_SYSTEM_DATA_VERIFICATION */ + +#ifdef CONFIG_INTEGRITY_PLATFORM_KEYRING +void __init set_platform_trusted_keys(struct key *keyring) +{ + platform_trusted_keys = keyring; +} +#endif diff --git a/include/keys/system_keyring.h b/include/keys/system_keyring.h index 359c2f936..42a93eda3 100644 --- a/include/keys/system_keyring.h +++ b/include/keys/system_keyring.h @@ -61,5 +61,13 @@ static inline struct key *get_ima_blacklist_keyring(void) } #endif /* CONFIG_IMA_BLACKLIST_KEYRING */ +#if defined(CONFIG_INTEGRITY_PLATFORM_KEYRING) && \ + defined(CONFIG_SYSTEM_TRUSTED_KEYRING) +extern void __init set_platform_trusted_keys(struct key *keyring); +#else +static inline void set_platform_trusted_keys(struct key *keyring) +{ +} +#endif #endif /* _KEYS_SYSTEM_KEYRING_H */ diff --git a/include/linux/efi.h b/include/linux/efi.h index 34c255c2a..b8a6df5df 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -676,6 +676,10 @@ void efi_native_runtime_setup(void); #define EFI_IMAGE_SECURITY_DATABASE_GUID EFI_GUID(0xd719b2cb, 0x3d3a, 0x4596, 0xa3, 0xbc, 0xda, 0xd0, 0x0e, 0x67, 0x65, 0x6f) #define EFI_SHIM_LOCK_GUID EFI_GUID(0x605dab50, 0xe046, 0x4300, 0xab, 0xb6, 0x3d, 0xd8, 0x10, 0xdd, 0x8b, 0x23) +#define EFI_CERT_SHA256_GUID EFI_GUID(0xc1c41626, 0x504c, 0x4092, 0xac, 0xa9, 0x41, 0xf9, 0x36, 0x93, 0x43, 0x28) +#define EFI_CERT_X509_GUID EFI_GUID(0xa5c059a1, 0x94e4, 0x4aa7, 0x87, 0xb5, 0xab, 0x15, 0x5c, 0x2b, 0xf0, 0x72) +#define EFI_CERT_X509_SHA256_GUID EFI_GUID(0x3bd2a492, 0x96c0, 0x4079, 0xb4, 0x20, 0xfc, 0xf9, 0x8e, 0xf1, 0x03, 0xed) + /* * This GUID is used to pass to the kernel proper the struct screen_info * structure that was populated by the stub based on the GOP protocol instance @@ -947,6 +951,27 @@ typedef struct { efi_memory_desc_t entry[0]; } efi_memory_attributes_table_t; +typedef struct { + efi_guid_t signature_owner; + u8 signature_data[]; +} efi_signature_data_t; + +typedef struct { + efi_guid_t signature_type; + u32 signature_list_size; + u32 signature_header_size; + u32 signature_size; + u8 signature_header[]; + /* efi_signature_data_t signatures[][] */ +} efi_signature_list_t; + +typedef u8 efi_sha256_hash_t[32]; + +typedef struct { + efi_sha256_hash_t to_be_signed_hash; + efi_time_t time_of_revocation; +} efi_cert_x509_sha256_t; + /* * All runtime access to EFI goes through this structure: */ @@ -1129,6 +1154,15 @@ extern int efi_memattr_apply_permissions(struct mm_struct *mm, char * __init efi_md_typeattr_format(char *buf, size_t size, const efi_memory_desc_t *md); + +typedef void (*efi_element_handler_t)(const char *source, + const void *element_data, + size_t element_size); +extern int __init parse_efi_signature_list( + const char *source, + const void *data, size_t size, + efi_element_handler_t (*get_handler_for_guid)(const efi_guid_t *)); + /** * efi_range_is_wc - check the WC bit on an address range * @start: starting kvirt address diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 98cf0fb09..542a15c91 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -147,6 +147,19 @@ extern const struct kexec_file_ops * const kexec_file_loaders[]; int kexec_image_probe_default(struct kimage *image, void *buf, unsigned long buf_len); +int kexec_image_post_load_cleanup_default(struct kimage *image); + +int wrap_kexec_file_load(int kernel_fd, int initrd_fd, + unsigned long cmdline_len, const char __user *cmdline_ptr, + unsigned long flags); + +/* + * If kexec_buf.mem is set to this value, kexec_locate_mem_hole() + * will try to allocate free memory. Arch may overwrite it. + */ +#ifndef KEXEC_BUF_MEM_UNKNOWN +#define KEXEC_BUF_MEM_UNKNOWN 0 +#endif /** * struct kexec_buf - parameters for finding a place for a buffer in memory @@ -187,8 +200,6 @@ int __weak arch_kexec_apply_relocations(struct purgatory_info *pi, const Elf_Shdr *relsec, const Elf_Shdr *symtab); -int __weak arch_kexec_walk_mem(struct kexec_buf *kbuf, - int (*func)(struct resource *, void *)); extern int kexec_add_buffer(struct kexec_buf *kbuf); int kexec_locate_mem_hole(struct kexec_buf *kbuf); diff --git a/include/linux/pe.h b/include/linux/pe.h index 143ce75be..3482b18a4 100644 --- a/include/linux/pe.h +++ b/include/linux/pe.h @@ -166,7 +166,7 @@ struct mz_hdr { uint16_t oem_info; /* oem specific */ uint16_t reserved1[10]; /* reserved */ uint32_t peaddr; /* address of pe header */ - char message[64]; /* message to print */ + char message[]; /* message to print */ }; struct mz_reloc { diff --git a/include/linux/verification.h b/include/linux/verification.h index cfa4730d6..018fb5f13 100644 --- a/include/linux/verification.h +++ b/include/linux/verification.h @@ -17,6 +17,7 @@ * should be used. */ #define VERIFY_USE_SECONDARY_KEYRING ((struct key *)1UL) +#define VERIFY_USE_PLATFORM_KEYRING ((struct key *)2UL) /* * The use to which an asymmetric key is being put. diff --git a/include/uapi/linux/kexec.h b/include/uapi/linux/kexec.h index ca3cebebd..9385ecba2 100644 --- a/include/uapi/linux/kexec.h +++ b/include/uapi/linux/kexec.h @@ -25,6 +25,7 @@ #define KEXEC_FILE_UNLOAD 0x00000001 #define KEXEC_FILE_ON_CRASH 0x00000002 #define KEXEC_FILE_NO_INITRAMFS 0x00000004 +#define KEXEC_FILE_LOAD_WRAP 0x100000000 /* These values match the ELF architecture values. * Unless there is a good reason that should continue to be the case. diff --git a/kernel/kexec.c b/kernel/kexec.c index 47dfad722..d44a55202 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -238,6 +238,16 @@ SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments, { int result; + if (flags & KEXEC_FILE_LOAD_WRAP) { + int kernel_fd, initrd_fd; + + kernel_fd = entry >> 32; + initrd_fd = entry & 0x00000000ffffffff; + flags &= ~KEXEC_FILE_LOAD_WRAP; + return wrap_kexec_file_load(kernel_fd, initrd_fd, nr_segments, + (char __user *)segments, flags); + } + result = kexec_load_check(nr_segments, flags); if (result) return result; diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index 04f99368b..2a25db8dd 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -16,6 +16,7 @@ #include <linux/file.h> #include <linux/slab.h> #include <linux/kexec.h> +#include <linux/memblock.h> #include <linux/mutex.h> #include <linux/list.h> #include <linux/fs.h> @@ -78,7 +79,7 @@ void * __weak arch_kexec_kernel_image_load(struct kimage *image) return kexec_image_load_default(image); } -static int kexec_image_post_load_cleanup_default(struct kimage *image) +int kexec_image_post_load_cleanup_default(struct kimage *image) { if (!image->fops || !image->fops->cleanup) return 0; @@ -407,6 +408,96 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, return ret; } +int wrap_kexec_file_load(int kernel_fd, int initrd_fd, + unsigned long cmdline_len, const char __user *cmdline_ptr, + unsigned long flags) +{ + int ret = 0, i; + struct kimage **dest_image, *image; + + /* We only trust the superuser with rebooting the system. */ + if (!capable(CAP_SYS_BOOT) || kexec_load_disabled) + return -EPERM; + + /* Make sure we have a legal set of flags */ + if (flags != (flags & KEXEC_FILE_FLAGS)) + return -EINVAL; + + image = NULL; + + if (!mutex_trylock(&kexec_mutex)) + return -EBUSY; + + dest_image = &kexec_image; + if (flags & KEXEC_FILE_ON_CRASH) { + dest_image = &kexec_crash_image; + if (kexec_crash_image) + arch_kexec_unprotect_crashkres(); + } + + if (flags & KEXEC_FILE_UNLOAD) + goto exchange; + + /* + * In case of crash, new kernel gets loaded in reserved region. It is + * same memory where old crash kernel might be loaded. Free any + * current crash dump kernel before we corrupt it. + */ + if (flags & KEXEC_FILE_ON_CRASH) + kimage_free(xchg(&kexec_crash_image, NULL)); + + ret = kimage_file_alloc_init(&image, kernel_fd, initrd_fd, cmdline_ptr, + cmdline_len, flags); + if (ret) + goto out; + + ret = machine_kexec_prepare(image); + if (ret) + goto out; + + /* + * Some architecture(like S390) may touch the crash memory before + * machine_kexec_prepare(), we must copy vmcoreinfo data after it. + */ + ret = kimage_crash_copy_vmcoreinfo(image); + if (ret) + goto out; + + ret = kexec_calculate_store_digests(image); + if (ret) + goto out; + + for (i = 0; i < image->nr_segments; i++) { + struct kexec_segment *ksegment; + + ksegment = &image->segment[i]; + pr_debug("Loading segment %d: buf=0x%p bufsz=0x%zx mem=0x%lx memsz=0x%zx\n", + i, ksegment->buf, ksegment->bufsz, ksegment->mem, + ksegment->memsz); + + ret = kimage_load_segment(image, &image->segment[i]); + if (ret) + goto out; + } + + kimage_terminate(image); + + /* + * Free up any temporary buffers allocated which are not needed + * after image has been loaded + */ + kimage_file_post_load_cleanup(image); +exchange: + image = xchg(dest_image, image); +out: + if ((flags & KEXEC_FILE_ON_CRASH) && kexec_crash_image) + arch_kexec_protect_crashkres(); + + mutex_unlock(&kexec_mutex); + kimage_free(image); + return ret; +} + static int locate_mem_hole_top_down(unsigned long start, unsigned long end, struct kexec_buf *kbuf) { @@ -501,8 +592,60 @@ static int locate_mem_hole_callback(struct resource *res, void *arg) return locate_mem_hole_bottom_up(start, end, kbuf); } +#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK +static int kexec_walk_memblock(struct kexec_buf *kbuf, + int (*func)(struct resource *, void *)) +{ + return 0; +} +#else +static int kexec_walk_memblock(struct kexec_buf *kbuf, + int (*func)(struct resource *, void *)) +{ + int ret = 0; + u64 i; + phys_addr_t mstart, mend; + struct resource res = { }; + + if (kbuf->image->type == KEXEC_TYPE_CRASH) + return func(&crashk_res, kbuf); + + if (kbuf->top_down) { + for_each_free_mem_range_reverse(i, NUMA_NO_NODE, MEMBLOCK_NONE, + &mstart, &mend, NULL) { + /* + * In memblock, end points to the first byte after the + * range while in kexec, end points to the last byte + * in the range. + */ + res.start = mstart; + res.end = mend - 1; + ret = func(&res, kbuf); + if (ret) + break; + } + } else { + for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, + &mstart, &mend, NULL) { + /* + * In memblock, end points to the first byte after the + * range while in kexec, end points to the last byte + * in the range. + */ + res.start = mstart; + res.end = mend - 1; + ret = func(&res, kbuf); + if (ret) + break; + } + } + + return ret; +} +#endif + /** - * arch_kexec_walk_mem - call func(data) on free memory regions + * kexec_walk_resources - call func(data) on free memory regions * @kbuf: Context info for the search. Also passed to @func. * @func: Function to call for each memory region. * @@ -510,8 +653,8 @@ static int locate_mem_hole_callback(struct resource *res, void *arg) * and that value will be returned. If all free regions are visited without * func returning non-zero, then zero will be returned. */ -int __weak arch_kexec_walk_mem(struct kexec_buf *kbuf, - int (*func)(struct resource *, void *)) +static int kexec_walk_resources(struct kexec_buf *kbuf, + int (*func)(struct resource *, void *)) { if (kbuf->image->type == KEXEC_TYPE_CRASH) return walk_iomem_res_desc(crashk_res.desc, @@ -534,7 +677,14 @@ int kexec_locate_mem_hole(struct kexec_buf *kbuf) { int ret; - ret = arch_kexec_walk_mem(kbuf, locate_mem_hole_callback); + /* Arch knows where to place */ + if (kbuf->mem != KEXEC_BUF_MEM_UNKNOWN) + return 0; + + if (IS_ENABLED(CONFIG_ARCH_DISCARD_MEMBLOCK)) + ret = kexec_walk_resources(kbuf, locate_mem_hole_callback); + else + ret = kexec_walk_memblock(kbuf, locate_mem_hole_callback); return ret == 1 ? 0 : -EADDRNOTAVAIL; } diff --git a/lib/Makefile b/lib/Makefile index 01f8051b4..455797430 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -213,7 +213,7 @@ KASAN_SANITIZE_stackdepot.o := n KCOV_INSTRUMENT_stackdepot.o := n libfdt_files = fdt.o fdt_ro.o fdt_wip.o fdt_rw.o fdt_sw.o fdt_strerror.o \ - fdt_empty_tree.o + fdt_empty_tree.o fdt_addresses.o $(foreach file, $(libfdt_files), \ $(eval CFLAGS_$(file) = -I$(src)/../scripts/dtc/libfdt)) lib-$(CONFIG_LIBFDT) += $(libfdt_files) diff --git a/lib/fdt_addresses.c b/lib/fdt_addresses.c new file mode 100644 index 000000000..23610bcf3 --- /dev/null +++ b/lib/fdt_addresses.c @@ -0,0 +1,2 @@ +#include <linux/libfdt_env.h> +#include "../scripts/dtc/libfdt/fdt_addresses.c" diff --git a/scripts/dtc/libfdt/fdt_addresses.c b/scripts/dtc/libfdt/fdt_addresses.c index eff4dbcc7..8211d00ba 100644 --- a/scripts/dtc/libfdt/fdt_addresses.c +++ b/scripts/dtc/libfdt/fdt_addresses.c @@ -94,3 +94,50 @@ int fdt_size_cells(const void *fdt, int nodeoffset) return val; } + +/* This function assumes that [address|size]_cells is 1 or 2 */ +int fdt_appendprop_addrrange(void *fdt, int parent, int nodeoffset, + const char *name, uint64_t addr, uint64_t size) +{ + int addr_cells, size_cells, ret; + uint8_t data[sizeof(fdt64_t) * 2], *prop; + + ret = fdt_address_cells(fdt, parent); + if (ret < 0) + return ret; + addr_cells = ret; + + ret = fdt_size_cells(fdt, parent); + if (ret < 0) + return ret; + size_cells = ret; + + /* check validity of address */ + prop = data; + if (addr_cells == 1) { + if ((addr > UINT32_MAX) || ((UINT32_MAX + 1 - addr) < size)) + return -FDT_ERR_BADVALUE; + + fdt32_st(prop, (uint32_t)addr); + } else if (addr_cells == 2) { + fdt64_st(prop, addr); + } else { + return -FDT_ERR_BADNCELLS; + } + + /* check validity of size */ + prop += addr_cells * sizeof(fdt32_t); + if (size_cells == 1) { + if (size > UINT32_MAX) + return -FDT_ERR_BADVALUE; + + fdt32_st(prop, (uint32_t)size); + } else if (size_cells == 2) { + fdt64_st(prop, size); + } else { + return -FDT_ERR_BADNCELLS; + } + + return fdt_appendprop(fdt, nodeoffset, name, data, + (addr_cells + size_cells) * sizeof(fdt32_t)); +} diff --git a/scripts/dtc/libfdt/libfdt.h b/scripts/dtc/libfdt/libfdt.h index 1e27780e1..da72b54c4 100644 --- a/scripts/dtc/libfdt/libfdt.h +++ b/scripts/dtc/libfdt/libfdt.h @@ -153,6 +153,30 @@ static inline void *fdt_offset_ptr_w(void *fdt, int offset, int checklen) uint32_t fdt_next_tag(const void *fdt, int offset, int *nextoffset); +static inline void fdt32_st(void *property, uint32_t value) +{ + uint8_t *bp = property; + + bp[0] = value >> 24; + bp[1] = (value >> 16) & 0xff; + bp[2] = (value >> 8) & 0xff; + bp[3] = value & 0xff; +} + +static inline void fdt64_st(void *property, uint64_t value) +{ + uint8_t *bp = property; + + bp[0] = value >> 56; + bp[1] = (value >> 48) & 0xff; + bp[2] = (value >> 40) & 0xff; + bp[3] = (value >> 32) & 0xff; + bp[4] = (value >> 24) & 0xff; + bp[5] = (value >> 16) & 0xff; + bp[6] = (value >> 8) & 0xff; + bp[7] = value & 0xff; +} + /**********************************************************************/ /* Traversal functions */ /**********************************************************************/ @@ -1765,6 +1789,43 @@ static inline int fdt_appendprop_cell(void *fdt, int nodeoffset, #define fdt_appendprop_string(fdt, nodeoffset, name, str) \ fdt_appendprop((fdt), (nodeoffset), (name), (str), strlen(str)+1) +/** + * fdt_appendprop_addrrange - append a address range property + * @fdt: pointer to the device tree blob + * @parent: offset of the parent node + * @nodeoffset: offset of the node to add a property at + * @name: name of property + * @addr: start address of a given range + * @size: size of a given range + * + * fdt_appendprop_addrrange() appends an address range value (start + * address and size) to the value of the named property in the given + * node, or creates a new property with that value if it does not + * already exist. + * If "name" is not specified, a default "reg" is used. + * Cell sizes are determined by parent's #address-cells and #size-cells. + * + * This function may insert data into the blob, and will therefore + * change the offsets of some existing nodes. + * + * returns: + * 0, on success + * -FDT_ERR_BADLAYOUT, + * -FDT_ERR_BADMAGIC, + * -FDT_ERR_BADNCELLS, if the node has a badly formatted or invalid + * #address-cells property + * -FDT_ERR_BADOFFSET, nodeoffset did not point to FDT_BEGIN_NODE tag + * -FDT_ERR_BADSTATE, + * -FDT_ERR_BADSTRUCTURE, + * -FDT_ERR_BADVERSION, + * -FDT_ERR_BADVALUE, addr or size doesn't fit to respective cells size + * -FDT_ERR_NOSPACE, there is insufficient free space in the blob to + * contain a new property + * -FDT_ERR_TRUNCATED, standard meanings + */ +int fdt_appendprop_addrrange(void *fdt, int parent, int nodeoffset, + const char *name, uint64_t addr, uint64_t size); + /** * fdt_delprop - delete a property * @fdt: pointer to the device tree blob diff --git a/security/integrity/Kconfig b/security/integrity/Kconfig index da9565891..4b4d2aeef 100644 --- a/security/integrity/Kconfig +++ b/security/integrity/Kconfig @@ -51,6 +51,17 @@ config INTEGRITY_TRUSTED_KEYRING .evm keyrings be signed by a key on the system trusted keyring. +config INTEGRITY_PLATFORM_KEYRING + bool "Provide keyring for platform/firmware trusted keys" + depends on INTEGRITY_ASYMMETRIC_KEYS + depends on SYSTEM_BLACKLIST_KEYRING + depends on EFI + help + Provide a separate, distinct keyring for platform trusted keys, which + the kernel automatically populates during initialization from values + provided by the platform for verifying the kexec'ed kerned image + and, possibly, the initramfs signature. + config INTEGRITY_AUDIT bool "Enables integrity auditing support " depends on AUDIT diff --git a/security/integrity/Makefile b/security/integrity/Makefile index 04d6e462b..86df9aba8 100644 --- a/security/integrity/Makefile +++ b/security/integrity/Makefile @@ -9,6 +9,11 @@ integrity-y := iint.o integrity-$(CONFIG_INTEGRITY_AUDIT) += integrity_audit.o integrity-$(CONFIG_INTEGRITY_SIGNATURE) += digsig.o integrity-$(CONFIG_INTEGRITY_ASYMMETRIC_KEYS) += digsig_asymmetric.o +integrity-$(CONFIG_INTEGRITY_PLATFORM_KEYRING) += platform_certs/platform_keyring.o \ + platform_certs/efi_parser.o \ + platform_certs/load_uefi.o +obj-$(CONFIG_LOAD_UEFI_KEYS) += platform_certs/load_uefi.o +$(obj)/load_uefi.o: KBUILD_CFLAGS += -fshort-wchar subdir-$(CONFIG_IMA) += ima obj-$(CONFIG_IMA) += ima/ diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c index 9bb0a7f28..c585ca8db 100644 --- a/security/integrity/digsig.c +++ b/security/integrity/digsig.c @@ -35,6 +35,7 @@ static const char *keyring_name[INTEGRITY_KEYRING_MAX] = { ".ima", #endif "_module", + ".platform", }; #ifdef CONFIG_INTEGRITY_TRUSTED_KEYRING @@ -79,12 +80,42 @@ int integrity_digsig_verify(const unsigned int id, const char *sig, int siglen, return -EOPNOTSUPP; } -int __init integrity_init_keyring(const unsigned int id) +static int __init __integrity_init_keyring(const unsigned int id, + key_perm_t perm, + struct key_restriction *restriction) { const struct cred *cred = current_cred(); - struct key_restriction *restriction; int err = 0; + keyring[id] = keyring_alloc(keyring_name[id], KUIDT_INIT(0), + KGIDT_INIT(0), cred, perm, + KEY_ALLOC_NOT_IN_QUOTA, restriction, NULL); + if (IS_ERR(keyring[id])) { + err = PTR_ERR(keyring[id]); + pr_info("Can't allocate %s keyring (%d)\n", + keyring_name[id], err); + keyring[id] = NULL; + } else { + if (id == INTEGRITY_KEYRING_PLATFORM) + set_platform_trusted_keys(keyring[id]); + } + + return err; +} + +int __init integrity_init_keyring(const unsigned int id) +{ + struct key_restriction *restriction; + key_perm_t perm; + + perm = (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW + | KEY_USR_READ | KEY_USR_SEARCH; + + if (id == INTEGRITY_KEYRING_PLATFORM) { + restriction = NULL; + goto out; + } + if (!init_keyring) return 0; @@ -93,32 +124,43 @@ int __init integrity_init_keyring(const unsigned int id) return -ENOMEM; restriction->check = restrict_link_to_ima; + perm |= KEY_USR_WRITE; - keyring[id] = keyring_alloc(keyring_name[id], KUIDT_INIT(0), - KGIDT_INIT(0), cred, - ((KEY_POS_ALL & ~KEY_POS_SETATTR) | - KEY_USR_VIEW | KEY_USR_READ | - KEY_USR_WRITE | KEY_USR_SEARCH), - KEY_ALLOC_NOT_IN_QUOTA, - restriction, NULL); - if (IS_ERR(keyring[id])) { - err = PTR_ERR(keyring[id]); - pr_info("Can't allocate %s keyring (%d)\n", - keyring_name[id], err); - keyring[id] = NULL; +out: + return __integrity_init_keyring(id, perm, restriction); +} + +int __init integrity_add_key(const unsigned int id, const void *data, + off_t size, key_perm_t perm) +{ + key_ref_t key; + int rc = 0; + + if (!keyring[id]) + return -EINVAL; + + key = key_create_or_update(make_key_ref(keyring[id], 1), "asymmetric", + NULL, data, size, perm, + KEY_ALLOC_NOT_IN_QUOTA); + if (IS_ERR(key)) { + rc = PTR_ERR(key); + pr_err("Problem loading X.509 certificate %d\n", rc); + } else { + pr_notice("Loaded X.509 cert '%s'\n", + key_ref_to_ptr(key)->description); + key_ref_put(key); } - return err; + + return rc; + } int __init integrity_load_x509(const unsigned int id, const char *path) { - key_ref_t key; void *data; loff_t size; int rc; - - if (!keyring[id]) - return -EINVAL; + key_perm_t perm; rc = kernel_read_file_from_path(path, &data, &size, 0, READING_X509_CERTIFICATE); @@ -127,23 +169,21 @@ int __init integrity_load_x509(const unsigned int id, const char *path) return rc; } - key = key_create_or_update(make_key_ref(keyring[id], 1), - "asymmetric", - NULL, - data, - size, - ((KEY_POS_ALL & ~KEY_POS_SETATTR) | - KEY_USR_VIEW | KEY_USR_READ), - KEY_ALLOC_NOT_IN_QUOTA); - if (IS_ERR(key)) { - rc = PTR_ERR(key); - pr_err("Problem loading X.509 certificate (%d): %s\n", - rc, path); - } else { - pr_notice("Loaded X.509 cert '%s': %s\n", - key_ref_to_ptr(key)->description, path); - key_ref_put(key); - } + perm = (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW | KEY_USR_READ; + + pr_info("Loading X.509 certificate: %s\n", path); + rc = integrity_add_key(id, (const void *)data, size, perm); + vfree(data); - return 0; + return rc; +} + +int __init integrity_load_cert(const unsigned int id, const char *source, + const void *data, size_t len, key_perm_t perm) +{ + if (!data) + return -EINVAL; + + pr_info("Loading X.509 certificate: %s\n", source); + return integrity_add_key(id, data, len, perm); } diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c index 08aabf763..ad285f17d 100644 --- a/security/integrity/ima/ima_appraise.c +++ b/security/integrity/ima/ima_appraise.c @@ -294,12 +294,22 @@ int ima_appraise_measurement(enum ima_hooks func, case EVM_IMA_XATTR_DIGSIG: set_bit(IMA_DIGSIG, &iint->atomic_flags); rc = integrity_digsig_verify(INTEGRITY_KEYRING_IMA, - (const char *)xattr_value, rc, + (const char *)xattr_value, + xattr_len, iint->ima_hash->digest, iint->ima_hash->length); if (rc == -EOPNOTSUPP) { status = INTEGRITY_UNKNOWN; - } else if (rc) { + break; + } + if (IS_ENABLED(CONFIG_INTEGRITY_PLATFORM_KEYRING) && rc && + func == KEXEC_KERNEL_CHECK) + rc = integrity_digsig_verify(INTEGRITY_KEYRING_PLATFORM, + (const char *)xattr_value, + xattr_len, + iint->ima_hash->digest, + iint->ima_hash->length); + if (rc) { cause = "invalid-signature"; status = INTEGRITY_FAIL; } else { diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h index 0ec551223..0750bab0d 100644 --- a/security/integrity/integrity.h +++ b/security/integrity/integrity.h @@ -142,7 +142,8 @@ int integrity_kernel_read(struct file *file, loff_t offset, #define INTEGRITY_KEYRING_EVM 0 #define INTEGRITY_KEYRING_IMA 1 #define INTEGRITY_KEYRING_MODULE 2 -#define INTEGRITY_KEYRING_MAX 3 +#define INTEGRITY_KEYRING_PLATFORM 3 +#define INTEGRITY_KEYRING_MAX 4 extern struct dentry *integrity_dir; @@ -153,6 +154,8 @@ int integrity_digsig_verify(const unsigned int id, const char *sig, int siglen, int __init integrity_init_keyring(const unsigned int id); int __init integrity_load_x509(const unsigned int id, const char *path); +int __init integrity_load_cert(const unsigned int id, const char *source, + const void *data, size_t len, key_perm_t perm); #else static inline int integrity_digsig_verify(const unsigned int id, @@ -166,6 +169,14 @@ static inline int integrity_init_keyring(const unsigned int id) { return 0; } + +static inline int __init integrity_load_cert(const unsigned int id, + const char *source, + const void *data, size_t len, + key_perm_t perm) +{ + return 0; +} #endif /* CONFIG_INTEGRITY_SIGNATURE */ #ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS @@ -222,3 +233,13 @@ integrity_audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type) } #endif + +#ifdef CONFIG_INTEGRITY_PLATFORM_KEYRING +void __init add_to_platform_keyring(const char *source, const void *data, + size_t len); +#else +static inline void __init add_to_platform_keyring(const char *source, + const void *data, size_t len) +{ +} +#endif diff --git a/security/integrity/platform_certs/efi_parser.c b/security/integrity/platform_certs/efi_parser.c new file mode 100644 index 000000000..18f01f36f --- /dev/null +++ b/security/integrity/platform_certs/efi_parser.c @@ -0,0 +1,108 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* EFI signature/key/certificate list parser + * + * Copyright (C) 2012, 2016 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells(a)redhat.com) + */ + +#define pr_fmt(fmt) "EFI: "fmt +#include <linux/module.h> +#include <linux/printk.h> +#include <linux/err.h> +#include <linux/efi.h> + +/** + * parse_efi_signature_list - Parse an EFI signature list for certificates + * @source: The source of the key + * @data: The data blob to parse + * @size: The size of the data blob + * @get_handler_for_guid: Get the handler func for the sig type (or NULL) + * + * Parse an EFI signature list looking for elements of interest. A list is + * made up of a series of sublists, where all the elements in a sublist are of + * the same type, but sublists can be of different types. + * + * For each sublist encountered, the @get_handler_for_guid function is called + * with the type specifier GUID and returns either a pointer to a function to + * handle elements of that type or NULL if the type is not of interest. + * + * If the sublist is of interest, each element is passed to the handler + * function in turn. + * + * Error EBADMSG is returned if the list doesn't parse correctly and 0 is + * returned if the list was parsed correctly. No error can be returned from + * the @get_handler_for_guid function or the element handler function it + * returns. + */ +int __init parse_efi_signature_list( + const char *source, + const void *data, size_t size, + efi_element_handler_t (*get_handler_for_guid)(const efi_guid_t *)) +{ + efi_element_handler_t handler; + unsigned int offs = 0; + + pr_devel("-->%s(,%zu)\n", __func__, size); + + while (size > 0) { + const efi_signature_data_t *elem; + efi_signature_list_t list; + size_t lsize, esize, hsize, elsize; + + if (size < sizeof(list)) + return -EBADMSG; + + memcpy(&list, data, sizeof(list)); + pr_devel("LIST[%04x] guid=%pUl ls=%x hs=%x ss=%x\n", + offs, + list.signature_type.b, list.signature_list_size, + list.signature_header_size, list.signature_size); + + lsize = list.signature_list_size; + hsize = list.signature_header_size; + esize = list.signature_size; + elsize = lsize - sizeof(list) - hsize; + + if (lsize > size) { + pr_devel("<--%s() = -EBADMSG [overrun @%x]\n", + __func__, offs); + return -EBADMSG; + } + + if (lsize < sizeof(list) || + lsize - sizeof(list) < hsize || + esize < sizeof(*elem) || + elsize < esize || + elsize % esize != 0) { + pr_devel("- bad size combo @%x\n", offs); + return -EBADMSG; + } + + handler = get_handler_for_guid(&list.signature_type); + if (!handler) { + data += lsize; + size -= lsize; + offs += lsize; + continue; + } + + data += sizeof(list) + hsize; + size -= sizeof(list) + hsize; + offs += sizeof(list) + hsize; + + for (; elsize > 0; elsize -= esize) { + elem = data; + + pr_devel("ELEM[%04x]\n", offs); + handler(source, + &elem->signature_data, + esize - sizeof(*elem)); + + data += esize; + size -= esize; + offs += esize; + } + } + + return 0; +} diff --git a/security/integrity/platform_certs/load_uefi.c b/security/integrity/platform_certs/load_uefi.c new file mode 100644 index 000000000..81b19c528 --- /dev/null +++ b/security/integrity/platform_certs/load_uefi.c @@ -0,0 +1,194 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/cred.h> +#include <linux/err.h> +#include <linux/efi.h> +#include <linux/slab.h> +#include <keys/asymmetric-type.h> +#include <keys/system_keyring.h> +#include "../integrity.h" + +static efi_guid_t efi_cert_x509_guid __initdata = EFI_CERT_X509_GUID; +static efi_guid_t efi_cert_x509_sha256_guid __initdata = + EFI_CERT_X509_SHA256_GUID; +static efi_guid_t efi_cert_sha256_guid __initdata = EFI_CERT_SHA256_GUID; + +/* + * Look to see if a UEFI variable called MokIgnoreDB exists and return true if + * it does. + * + * This UEFI variable is set by the shim if a user tells the shim to not use + * the certs/hashes in the UEFI db variable for verification purposes. If it + * is set, we should ignore the db variable also and the true return indicates + * this. + */ +static __init bool uefi_check_ignore_db(void) +{ + efi_status_t status; + unsigned int db = 0; + unsigned long size = sizeof(db); + efi_guid_t guid = EFI_SHIM_LOCK_GUID; + + status = efi.get_variable(L"MokIgnoreDB", &guid, NULL, &size, &db); + return status == EFI_SUCCESS; +} + +/* + * Get a certificate list blob from the named EFI variable. + */ +static __init void *get_cert_list(efi_char16_t *name, efi_guid_t *guid, + unsigned long *size) +{ + efi_status_t status; + unsigned long lsize = 4; + unsigned long tmpdb[4]; + void *db; + + status = efi.get_variable(name, guid, NULL, &lsize, &tmpdb); + if (status != EFI_BUFFER_TOO_SMALL) { + pr_err("Couldn't get size: 0x%lx\n", status); + return NULL; + } + + db = kmalloc(lsize, GFP_KERNEL); + if (!db) + return NULL; + + status = efi.get_variable(name, guid, NULL, &lsize, db); + if (status != EFI_SUCCESS) { + kfree(db); + pr_err("Error reading db var: 0x%lx\n", status); + return NULL; + } + + *size = lsize; + return db; +} + +/* + * Blacklist a hash. + */ +static __init void uefi_blacklist_hash(const char *source, const void *data, + size_t len, const char *type, + size_t type_len) +{ + char *hash, *p; + + hash = kmalloc(type_len + len * 2 + 1, GFP_KERNEL); + if (!hash) + return; + p = memcpy(hash, type, type_len); + p += type_len; + bin2hex(p, data, len); + p += len * 2; + *p = 0; + + mark_hash_blacklisted(hash); + kfree(hash); +} + +/* + * Blacklist an X509 TBS hash. + */ +static __init void uefi_blacklist_x509_tbs(const char *source, + const void *data, size_t len) +{ + uefi_blacklist_hash(source, data, len, "tbs:", 4); +} + +/* + * Blacklist the hash of an executable. + */ +static __init void uefi_blacklist_binary(const char *source, + const void *data, size_t len) +{ + uefi_blacklist_hash(source, data, len, "bin:", 4); +} + +/* + * Return the appropriate handler for particular signature list types found in + * the UEFI db and MokListRT tables. + */ +static __init efi_element_handler_t get_handler_for_db(const efi_guid_t * + sig_type) +{ + if (efi_guidcmp(*sig_type, efi_cert_x509_guid) == 0) + return add_to_platform_keyring; + return 0; +} + +/* + * Return the appropriate handler for particular signature list types found in + * the UEFI dbx and MokListXRT tables. + */ +static __init efi_element_handler_t get_handler_for_dbx(const efi_guid_t * + sig_type) +{ + if (efi_guidcmp(*sig_type, efi_cert_x509_sha256_guid) == 0) + return uefi_blacklist_x509_tbs; + if (efi_guidcmp(*sig_type, efi_cert_sha256_guid) == 0) + return uefi_blacklist_binary; + return 0; +} + +/* + * Load the certs contained in the UEFI databases into the platform trusted + * keyring and the UEFI blacklisted X.509 cert SHA256 hashes into the blacklist + * keyring. + */ +static int __init load_uefi_certs(void) +{ + efi_guid_t secure_var = EFI_IMAGE_SECURITY_DATABASE_GUID; + efi_guid_t mok_var = EFI_SHIM_LOCK_GUID; + void *db = NULL, *dbx = NULL, *mok = NULL; + unsigned long dbsize = 0, dbxsize = 0, moksize = 0; + int rc = 0; + + if (!efi.get_variable) + return false; + + /* Get db, MokListRT, and dbx. They might not exist, so it isn't + * an error if we can't get them. + */ + if (!uefi_check_ignore_db()) { + db = get_cert_list(L"db", &secure_var, &dbsize); + if (!db) { + pr_err("MODSIGN: Couldn't get UEFI db list\n"); + } else { + rc = parse_efi_signature_list("UEFI:db", + db, dbsize, get_handler_for_db); + if (rc) + pr_err("Couldn't parse db signatures: %d\n", + rc); + kfree(db); + } + } + + mok = get_cert_list(L"MokListRT", &mok_var, &moksize); + if (!mok) { + pr_info("Couldn't get UEFI MokListRT\n"); + } else { + rc = parse_efi_signature_list("UEFI:MokListRT", + mok, moksize, get_handler_for_db); + if (rc) + pr_err("Couldn't parse MokListRT signatures: %d\n", rc); + kfree(mok); + } + + dbx = get_cert_list(L"dbx", &secure_var, &dbxsize); + if (!dbx) { + pr_info("Couldn't get UEFI dbx list\n"); + } else { + rc = parse_efi_signature_list("UEFI:dbx", + dbx, dbxsize, + get_handler_for_dbx); + if (rc) + pr_err("Couldn't parse dbx signatures: %d\n", rc); + kfree(dbx); + } + + return rc; +} +late_initcall(load_uefi_certs); diff --git a/security/integrity/platform_certs/platform_keyring.c b/security/integrity/platform_certs/platform_keyring.c new file mode 100644 index 000000000..bcafd7387 --- /dev/null +++ b/security/integrity/platform_certs/platform_keyring.c @@ -0,0 +1,58 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Platform keyring for firmware/platform keys + * + * Copyright IBM Corporation, 2018 + * Author(s): Nayna Jain <nayna(a)linux.ibm.com> + */ + +#include <linux/export.h> +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/cred.h> +#include <linux/err.h> +#include <linux/slab.h> +#include "../integrity.h" + +/** + * add_to_platform_keyring - Add to platform keyring without validation. + * @source: Source of key + * @data: The blob holding the key + * @len: The length of the data blob + * + * Add a key to the platform keyring without checking its trust chain. This + * is available only during kernel initialisation. + */ +void __init add_to_platform_keyring(const char *source, const void *data, + size_t len) +{ + key_perm_t perm; + int rc; + + perm = (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW; + + rc = integrity_load_cert(INTEGRITY_KEYRING_PLATFORM, source, data, len, + perm); + if (rc) + pr_info("Error adding keys to platform keyring %s\n", source); +} + +/* + * Create the trusted keyrings. + */ +static __init int platform_keyring_init(void) +{ + int rc; + + rc = integrity_init_keyring(INTEGRITY_KEYRING_PLATFORM); + if (rc) + return rc; + + pr_notice("Platform Keyring initialized\n"); + return 0; +} + +/* + * Must be initialised before we try and load the keys into the keyring. + */ +device_initcall(platform_keyring_init); -- 2.27.0

1 0

[PATCH openEuler-1.0-LTS 0/5] drm/hisilicon: Fix hibmc did not get edid
by Gou Hao 18 Sep '21

18 Sep '21

From: gouhao <gouhao(a)uniontech.com> Fix hibmc did not get edid. issue: https://gitee.com/openeuler/kernel/issues/I469VQ gouhao (5): drm-Split-out-drm_probe_helper.h drm-Add-ddc-link-in-sysfs-created-by-drm_connector drm-Add-drm_connector_init-variant-with-ddc drm/hisilicon: Support i2c driver algorithms for bit-shift adapters drm/hisilicon: Features to support reading resolutions from EDID drivers/gpu/drm/drm_connector.c | 35 +++++++ drivers/gpu/drm/drm_sysfs.c | 8 ++ drivers/gpu/drm/hisilicon/hibmc/Makefile | 3 +- .../gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h | 26 +++++ .../gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c | 99 +++++++++++++++++++ .../gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c | 55 ++++++++--- include/drm/drm_connector.h | 18 ++++ include/drm/drm_probe_helper.h | 27 +++++ 8 files changed, 256 insertions(+), 15 deletions(-) create mode 100644 drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c create mode 100644 include/drm/drm_probe_helper.h -- 2.20.1

2 6

[PATCH openEuler-1.0-LTS 1/3] block: check if a profile is actually registered in blk_integrity_unregister
by Yang Yingliang 17 Sep '21

17 Sep '21

From: Christoph Hellwig <hch(a)lst.de> mainline inclusion from mainline-v5.15 commit 783a40a1b3ac7f3714d2776fa8ac8cce3535e4f6 category: bugfix bugzilla: 181328 CVE: NA ----------------------------------------------- While clearing the profile itself is harmless, we really should not clear the stable writes flag if it wasn't set due to a registered integrity profile. Reported-by: Lihong Kou <koulihong(a)huawei.com> Signed-off-by: Christoph Hellwig <hch(a)lst.de> Reviewed-by: Sagi Grimberg <sagi(a)grimberg.me> Link: https://lore.kernel.org/r/20210914070657.87677-2-hch@lst.de Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- block/blk-integrity.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/block/blk-integrity.c b/block/blk-integrity.c index 6121611e13164..0638f4868f705 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -431,8 +431,13 @@ EXPORT_SYMBOL(blk_integrity_register); */ void blk_integrity_unregister(struct gendisk *disk) { + struct blk_integrity *bi = &disk->queue->integrity; + + if (!bi->profile) + return; + disk->queue->backing_dev_info->capabilities &= ~BDI_CAP_STABLE_WRITES; - memset(&disk->queue->integrity, 0, sizeof(struct blk_integrity)); + memset(bi, 0, sizeof(*bi)); } EXPORT_SYMBOL(blk_integrity_unregister); -- 2.25.1

1 2

[PATCH kernel-4.19 1/3] block: check if a profile is actually registered in blk_integrity_unregister
by Yang Yingliang 17 Sep '21

17 Sep '21

From: Christoph Hellwig <hch(a)lst.de> mainline inclusion from block-5.15 commit 783a40a1b3ac7f3714d2776fa8ac8cce3535e4f6 category: bugfix bugzilla: 181328 CVE: NA ----------------------------------------------- While clearing the profile itself is harmless, we really should not clear the stable writes flag if it wasn't set due to a registered integrity profile. Reported-by: Lihong Kou <koulihong(a)huawei.com> Signed-off-by: Christoph Hellwig <hch(a)lst.de> Reviewed-by: Sagi Grimberg <sagi(a)grimberg.me> Link: https://lore.kernel.org/r/20210914070657.87677-2-hch@lst.de Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- block/blk-integrity.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/block/blk-integrity.c b/block/blk-integrity.c index 6121611e13164..0638f4868f705 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -431,8 +431,13 @@ EXPORT_SYMBOL(blk_integrity_register); */ void blk_integrity_unregister(struct gendisk *disk) { + struct blk_integrity *bi = &disk->queue->integrity; + + if (!bi->profile) + return; + disk->queue->backing_dev_info->capabilities &= ~BDI_CAP_STABLE_WRITES; - memset(&disk->queue->integrity, 0, sizeof(struct blk_integrity)); + memset(bi, 0, sizeof(*bi)); } EXPORT_SYMBOL(blk_integrity_unregister); -- 2.25.1

1 2

[PATCH openEuler-1.0-LTS 01/11] Revert "nbd: use blk_mq_queue_tag_inflight_iter()"
by Yang Yingliang 17 Sep '21

17 Sep '21

From: Yu Kuai <yukuai3(a)huawei.com> hulk inclusion category: bugfix bugzilla: 34280, https://gitee.com/openeuler/kernel/issues/I4AKY4 CVE: NA ----------------------------------------------- This reverts commit a139227441d1a01bfce70e591dd6b17e126561fa. Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/block/nbd.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index a82a5dc845c6f..6a72c07ce3cba 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -763,8 +763,7 @@ static void recv_work(struct work_struct *work) kfree(args); } -static void nbd_clear_req(struct blk_mq_hw_ctx *hctx, - struct request *req, void *data, bool reserved) +static void nbd_clear_req(struct request *req, void *data, bool reserved) { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req); @@ -778,7 +777,7 @@ static void nbd_clear_req(struct blk_mq_hw_ctx *hctx, static void nbd_clear_que(struct nbd_device *nbd) { blk_mq_quiesce_queue(nbd->disk->queue); - blk_mq_queue_tag_inflight_iter(nbd->disk->queue, nbd_clear_req, NULL); + blk_mq_tagset_busy_iter(&nbd->tag_set, nbd_clear_req, NULL); blk_mq_unquiesce_queue(nbd->disk->queue); dev_dbg(disk_to_dev(nbd->disk), "queue cleared\n"); } -- 2.25.1

1 10

2024

2023

2022

2021

2020

2019

Kernel