diff options
Diffstat (limited to 'lib')
| -rw-r--r-- | lib/Kconfig.debug | 8 | ||||
| -rw-r--r-- | lib/Makefile | 6 | ||||
| -rw-r--r-- | lib/buildid.c | 149 | ||||
| -rw-r--r-- | lib/cpumask.c | 16 | ||||
| -rw-r--r-- | lib/iov_iter.c | 45 | ||||
| -rw-r--r-- | lib/locking-selftest.c | 334 | ||||
| -rw-r--r-- | lib/parman.c | 1 | ||||
| -rw-r--r-- | lib/percpu-refcount.c | 12 | ||||
| -rw-r--r-- | lib/test_bpf.c | 21 | ||||
| -rw-r--r-- | lib/test_fpu.c | 6 | ||||
| -rw-r--r-- | lib/timerqueue.c | 28 | ||||
| -rw-r--r-- | lib/ubsan.c | 31 | ||||
| -rw-r--r-- | lib/ubsan.h | 6 |
13 files changed, 595 insertions, 68 deletions
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 7937265ef879..5ea0c1773b0a 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1335,6 +1335,7 @@ config LOCKDEP_SMALL config DEBUG_LOCKDEP bool "Lock dependency engine debugging" depends on DEBUG_KERNEL && LOCKDEP + select DEBUG_IRQFLAGS help If you say Y here, the lock dependency engine will do additional runtime checks to debug itself, at the price @@ -1423,6 +1424,13 @@ config TRACE_IRQFLAGS_NMI depends on TRACE_IRQFLAGS depends on TRACE_IRQFLAGS_NMI_SUPPORT +config DEBUG_IRQFLAGS + bool "Debug IRQ flag manipulation" + help + Enables checks for potentially unsafe enabling or disabling of + interrupts, such as calling raw_local_irq_restore() when interrupts + are enabled. + config STACKTRACE bool "Stack backtrace support" depends on STACKTRACE_SUPPORT diff --git a/lib/Makefile b/lib/Makefile index afeff05fa8c5..fb7d946bb8c3 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -27,16 +27,14 @@ KASAN_SANITIZE_string.o := n CFLAGS_string.o += -fno-stack-protector endif -# Used by KCSAN while enabled, avoid recursion. -KCSAN_SANITIZE_random32.o := n - lib-y := ctype.o string.o vsprintf.o cmdline.o \ rbtree.o radix-tree.o timerqueue.o xarray.o \ idr.o extable.o sha1.o irq_regs.o argv_split.o \ flex_proportions.o ratelimit.o show_mem.o \ is_single_threaded.o plist.o decompress.o kobject_uevent.o \ earlycpio.o seq_buf.o siphash.o dec_and_lock.o \ - nmi_backtrace.o nodemask.o win_minmax.o memcat_p.o + nmi_backtrace.o nodemask.o win_minmax.o memcat_p.o \ + buildid.o lib-$(CONFIG_PRINTK) += dump_stack.o lib-$(CONFIG_SMP) += cpumask.o diff --git a/lib/buildid.c b/lib/buildid.c new file mode 100644 index 000000000000..6156997c3895 --- /dev/null +++ b/lib/buildid.c @@ -0,0 +1,149 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/buildid.h> +#include <linux/elf.h> +#include <linux/pagemap.h> + +#define BUILD_ID 3 +/* + * Parse build id from the note segment. This logic can be shared between + * 32-bit and 64-bit system, because Elf32_Nhdr and Elf64_Nhdr are + * identical. + */ +static inline int parse_build_id(void *page_addr, + unsigned char *build_id, + __u32 *size, + void *note_start, + Elf32_Word note_size) +{ + Elf32_Word note_offs = 0, new_offs; + + /* check for overflow */ + if (note_start < page_addr || note_start + note_size < note_start) + return -EINVAL; + + /* only supports note that fits in the first page */ + if (note_start + note_size > page_addr + PAGE_SIZE) + return -EINVAL; + + while (note_offs + sizeof(Elf32_Nhdr) < note_size) { + Elf32_Nhdr *nhdr = (Elf32_Nhdr *)(note_start + note_offs); + + if (nhdr->n_type == BUILD_ID && + nhdr->n_namesz == sizeof("GNU") && + nhdr->n_descsz > 0 && + nhdr->n_descsz <= BUILD_ID_SIZE_MAX) { + memcpy(build_id, + note_start + note_offs + + ALIGN(sizeof("GNU"), 4) + sizeof(Elf32_Nhdr), + nhdr->n_descsz); + memset(build_id + nhdr->n_descsz, 0, + BUILD_ID_SIZE_MAX - nhdr->n_descsz); + if (size) + *size = nhdr->n_descsz; + return 0; + } + new_offs = note_offs + sizeof(Elf32_Nhdr) + + ALIGN(nhdr->n_namesz, 4) + ALIGN(nhdr->n_descsz, 4); + if (new_offs <= note_offs) /* overflow */ + break; + note_offs = new_offs; + } + return -EINVAL; +} + +/* Parse build ID from 32-bit ELF */ +static int get_build_id_32(void *page_addr, unsigned char *build_id, + __u32 *size) +{ + Elf32_Ehdr *ehdr = (Elf32_Ehdr *)page_addr; + Elf32_Phdr *phdr; + int i; + + /* only supports phdr that fits in one page */ + if (ehdr->e_phnum > + (PAGE_SIZE - sizeof(Elf32_Ehdr)) / sizeof(Elf32_Phdr)) + return -EINVAL; + + phdr = (Elf32_Phdr *)(page_addr + sizeof(Elf32_Ehdr)); + + for (i = 0; i < ehdr->e_phnum; ++i) { + if (phdr[i].p_type == PT_NOTE && + !parse_build_id(page_addr, build_id, size, + page_addr + phdr[i].p_offset, + phdr[i].p_filesz)) + return 0; + } + return -EINVAL; +} + +/* Parse build ID from 64-bit ELF */ +static int get_build_id_64(void *page_addr, unsigned char *build_id, + __u32 *size) +{ + Elf64_Ehdr *ehdr = (Elf64_Ehdr *)page_addr; + Elf64_Phdr *phdr; + int i; + + /* only supports phdr that fits in one page */ + if (ehdr->e_phnum > + (PAGE_SIZE - sizeof(Elf64_Ehdr)) / sizeof(Elf64_Phdr)) + return -EINVAL; + + phdr = (Elf64_Phdr *)(page_addr + sizeof(Elf64_Ehdr)); + + for (i = 0; i < ehdr->e_phnum; ++i) { + if (phdr[i].p_type == PT_NOTE && + !parse_build_id(page_addr, build_id, size, + page_addr + phdr[i].p_offset, + phdr[i].p_filesz)) + return 0; + } + return -EINVAL; +} + +/* + * Parse build ID of ELF file mapped to vma + * @vma: vma object + * @build_id: buffer to store build id, at least BUILD_ID_SIZE long + * @size: returns actual build id size in case of success + * + * Returns 0 on success, otherwise error (< 0). + */ +int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id, + __u32 *size) +{ + Elf32_Ehdr *ehdr; + struct page *page; + void *page_addr; + int ret; + + /* only works for page backed storage */ + if (!vma->vm_file) + return -EINVAL; + + page = find_get_page(vma->vm_file->f_mapping, 0); + if (!page) + return -EFAULT; /* page not mapped */ + + ret = -EINVAL; + page_addr = kmap_atomic(page); + ehdr = (Elf32_Ehdr *)page_addr; + + /* compare magic x7f "ELF" */ + if (memcmp(ehdr->e_ident, ELFMAG, SELFMAG) != 0) + goto out; + + /* only support executable file and shared object file */ + if (ehdr->e_type != ET_EXEC && ehdr->e_type != ET_DYN) + goto out; + + if (ehdr->e_ident[EI_CLASS] == ELFCLASS32) + ret = get_build_id_32(page_addr, build_id, size); + else if (ehdr->e_ident[EI_CLASS] == ELFCLASS64) + ret = get_build_id_64(page_addr, build_id, size); +out: + kunmap_atomic(page_addr); + put_page(page); + return ret; +} diff --git a/lib/cpumask.c b/lib/cpumask.c index 35924025097b..c3c76b833384 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -6,7 +6,6 @@ #include <linux/export.h> #include <linux/memblock.h> #include <linux/numa.h> -#include <linux/sched/isolation.h> /** * cpumask_next - get the next cpu in a cpumask @@ -206,27 +205,22 @@ void __init free_bootmem_cpumask_var(cpumask_var_t mask) */ unsigned int cpumask_local_spread(unsigned int i, int node) { - int cpu, hk_flags; - const struct cpumask *mask; + int cpu; - hk_flags = HK_FLAG_DOMAIN | HK_FLAG_MANAGED_IRQ; - mask = housekeeping_cpumask(hk_flags); /* Wrap: we always want a cpu. */ - i %= cpumask_weight(mask); + i %= num_online_cpus(); if (node == NUMA_NO_NODE) { - for_each_cpu(cpu, mask) { + for_each_cpu(cpu, cpu_online_mask) if (i-- == 0) return cpu; - } } else { /* NUMA first. */ - for_each_cpu_and(cpu, cpumask_of_node(node), mask) { + for_each_cpu_and(cpu, cpumask_of_node(node), cpu_online_mask) if (i-- == 0) return cpu; - } - for_each_cpu(cpu, mask) { + for_each_cpu(cpu, cpu_online_mask) { /* Skip NUMA nodes, done above. */ if (cpumask_test_cpu(cpu, cpumask_of_node(node))) continue; diff --git a/lib/iov_iter.c b/lib/iov_iter.c index a21e6a5792c5..d8ca336ff9cd 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -72,8 +72,6 @@ __start.bi_bvec_done = skip; \ __start.bi_idx = 0; \ for_each_bvec(__v, i->bvec, __bi, __start) { \ - if (!__v.bv_len) \ - continue; \ (void)(STEP); \ } \ } @@ -592,14 +590,15 @@ static __wsum csum_and_memcpy(void *to, const void *from, size_t len, } static size_t csum_and_copy_to_pipe_iter(const void *addr, size_t bytes, - __wsum *csum, struct iov_iter *i) + struct csum_state *csstate, + struct iov_iter *i) { struct pipe_inode_info *pipe = i->pipe; unsigned int p_mask = pipe->ring_size - 1; + __wsum sum = csstate->csum; + size_t off = csstate->off; unsigned int i_head; size_t n, r; - size_t off = 0; - __wsum sum = *csum; if (!sanity(i)) return 0; @@ -621,7 +620,8 @@ static size_t csum_and_copy_to_pipe_iter(const void *addr, size_t bytes, i_head++; } while (n); i->count -= bytes; - *csum = sum; + csstate->csum = sum; + csstate->off = off; return bytes; } @@ -1067,6 +1067,21 @@ static void pipe_advance(struct iov_iter *i, size_t size) pipe_truncate(i); } +static void iov_iter_bvec_advance(struct iov_iter *i, size_t size) +{ + struct bvec_iter bi; + + bi.bi_size = i->count; + bi.bi_bvec_done = i->iov_offset; + bi.bi_idx = 0; + bvec_iter_advance(i->bvec, &bi, size); + + i->bvec += bi.bi_idx; + i->nr_segs -= bi.bi_idx; + i->count = bi.bi_size; + i->iov_offset = bi.bi_bvec_done; +} + void iov_iter_advance(struct iov_iter *i, size_t size) { if (unlikely(iov_iter_is_pipe(i))) { @@ -1077,6 +1092,10 @@ void iov_iter_advance(struct iov_iter *i, size_t size) i->count -= size; return; } + if (iov_iter_is_bvec(i)) { + iov_iter_bvec_advance(i, size); + return; + } iterate_and_advance(i, size, v, 0, 0, 0) } EXPORT_SYMBOL(iov_iter_advance); @@ -1522,18 +1541,19 @@ bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, } EXPORT_SYMBOL(csum_and_copy_from_iter_full); -size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *csump, +size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *_csstate, struct iov_iter *i) { + struct csum_state *csstate = _csstate; const char *from = addr; - __wsum *csum = csump; __wsum sum, next; - size_t off = 0; + size_t off; if (unlikely(iov_iter_is_pipe(i))) - return csum_and_copy_to_pipe_iter(addr, bytes, csum, i); + return csum_and_copy_to_pipe_iter(addr, bytes, _csstate, i); - sum = *csum; + sum = csstate->csum; + off = csstate->off; if (unlikely(iov_iter_is_discard(i))) { WARN_ON(1); /* for now */ return 0; @@ -1561,7 +1581,8 @@ size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *csump, off += v.iov_len; }) ) - *csum = sum; + csstate->csum = sum; + csstate->off = off; return bytes; } EXPORT_SYMBOL(csum_and_copy_to_iter); diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c index 9959ea23529e..2d85abac1744 100644 --- a/lib/locking-selftest.c +++ b/lib/locking-selftest.c @@ -24,6 +24,7 @@ #include <linux/debug_locks.h> #include <linux/irqflags.h> #include <linux/rtmutex.h> +#include <linux/local_lock.h> /* * Change this to 1 if you want to see the failure printouts: @@ -51,6 +52,7 @@ __setup("debug_locks_verbose=", setup_debug_locks_verbose); #define LOCKTYPE_RWSEM 0x8 #define LOCKTYPE_WW 0x10 #define LOCKTYPE_RTMUTEX 0x20 +#define LOCKTYPE_LL 0x40 static struct ww_acquire_ctx t, t2; static struct ww_mutex o, o2, o3; @@ -64,6 +66,9 @@ static DEFINE_SPINLOCK(lock_B); static DEFINE_SPINLOCK(lock_C); static DEFINE_SPINLOCK(lock_D); +static DEFINE_RAW_SPINLOCK(raw_lock_A); +static DEFINE_RAW_SPINLOCK(raw_lock_B); + static DEFINE_RWLOCK(rwlock_A); static DEFINE_RWLOCK(rwlock_B); static DEFINE_RWLOCK(rwlock_C); @@ -133,6 +138,8 @@ static DEFINE_RT_MUTEX(rtmutex_Z2); #endif +static local_lock_t local_A = INIT_LOCAL_LOCK(local_A); + /* * non-inlined runtime initializers, to let separate locks share * the same lock-class: @@ -1306,19 +1313,23 @@ GENERATE_PERMUTATIONS_3_EVENTS(irq_read_recursion3_soft_wlock) #ifdef CONFIG_DEBUG_LOCK_ALLOC # define I_SPINLOCK(x) lockdep_reset_lock(&lock_##x.dep_map) +# define I_RAW_SPINLOCK(x) lockdep_reset_lock(&raw_lock_##x.dep_map) # define I_RWLOCK(x) lockdep_reset_lock(&rwlock_##x.dep_map) # define I_MUTEX(x) lockdep_reset_lock(&mutex_##x.dep_map) # define I_RWSEM(x) lockdep_reset_lock(&rwsem_##x.dep_map) # define I_WW(x) lockdep_reset_lock(&x.dep_map) +# define I_LOCAL_LOCK(x) lockdep_reset_lock(&local_##x.dep_map) #ifdef CONFIG_RT_MUTEXES # define I_RTMUTEX(x) lockdep_reset_lock(&rtmutex_##x.dep_map) #endif #else # define I_SPINLOCK(x) +# define I_RAW_SPINLOCK(x) # define I_RWLOCK(x) # define I_MUTEX(x) # define I_RWSEM(x) # define I_WW(x) +# define I_LOCAL_LOCK(x) #endif #ifndef I_RTMUTEX @@ -1358,9 +1369,16 @@ static void reset_locks(void) I1(A); I1(B); I1(C); I1(D); I1(X1); I1(X2); I1(Y1); I1(Y2); I1(Z1); I1(Z2); I_WW(t); I_WW(t2); I_WW(o.base); I_WW(o2.base); I_WW(o3.base); + I_RAW_SPINLOCK(A); I_RAW_SPINLOCK(B); + I_LOCAL_LOCK(A); + lockdep_reset(); + I2(A); I2(B); I2(C); I2(D); init_shared_classes(); + raw_spin_lock_init(&raw_lock_A); + raw_spin_lock_init(&raw_lock_B); + local_lock_init(&local_A); ww_mutex_init(&o, &ww_lockdep); ww_mutex_init(&o2, &ww_lockdep); ww_mutex_init(&o3, &ww_lockdep); memset(&t, 0, sizeof(t)); memset(&t2, 0, sizeof(t2)); @@ -1382,6 +1400,8 @@ static void dotest(void (*testcase_fn)(void), int expected, int lockclass_mask) WARN_ON(irqs_disabled()); + debug_locks_silent = !(debug_locks_verbose & lockclass_mask); + testcase_fn(); /* * Filter out expected failures: @@ -1402,7 +1422,7 @@ static void dotest(void (*testcase_fn)(void), int expected, int lockclass_mask) } testcase_total++; - if (debug_locks_verbose) + if (debug_locks_verbose & lockclass_mask) pr_cont(" lockclass mask: %x, debug_locks: %d, expected: %d\n", lockclass_mask, debug_locks, expected); /* @@ -2419,6 +2439,311 @@ static void fs_reclaim_tests(void) pr_cont("\n"); } +#define __guard(cleanup) __maybe_unused __attribute__((__cleanup__(cleanup))) + +static void hardirq_exit(int *_) +{ + HARDIRQ_EXIT(); +} + +#define HARDIRQ_CONTEXT(name, ...) \ + int hardirq_guard_##name __guard(hardirq_exit); \ + HARDIRQ_ENTER(); + +#define NOTTHREADED_HARDIRQ_CONTEXT(name, ...) \ + int notthreaded_hardirq_guard_##name __guard(hardirq_exit); \ + local_irq_disable(); \ + __irq_enter(); \ + WARN_ON(!in_irq()); + +static void softirq_exit(int *_) +{ + SOFTIRQ_EXIT(); +} + +#define SOFTIRQ_CONTEXT(name, ...) \ + int softirq_guard_##name __guard(softirq_exit); \ + SOFTIRQ_ENTER(); + +static void rcu_exit(int *_) +{ + rcu_read_unlock(); +} + +#define RCU_CONTEXT(name, ...) \ + int rcu_guard_##name __guard(rcu_exit); \ + rcu_read_lock(); + +static void rcu_bh_exit(int *_) +{ + rcu_read_unlock_bh(); +} + +#define RCU_BH_CONTEXT(name, ...) \ + int rcu_bh_guard_##name __guard(rcu_bh_exit); \ + rcu_read_lock_bh(); + +static void rcu_sched_exit(int *_) +{ + rcu_read_unlock_sched(); +} + +#define RCU_SCHED_CONTEXT(name, ...) \ + int rcu_sched_guard_##name __guard(rcu_sched_exit); \ + rcu_read_lock_sched(); + +static void rcu_callback_exit(int *_) +{ + rcu_lock_release(&rcu_callback_map); +} + +#define RCU_CALLBACK_CONTEXT(name, ...) \ + int rcu_callback_guard_##name __guard(rcu_callback_exit); \ + rcu_lock_acquire(&rcu_callback_map); + + +static void raw_spinlock_exit(raw_spinlock_t **lock) +{ + raw_spin_unlock(*lock); +} + +#define RAW_SPINLOCK_CONTEXT(name, lock) \ + raw_spinlock_t *raw_spinlock_guard_##name __guard(raw_spinlock_exit) = &(lock); \ + raw_spin_lock(&(lock)); + +static void spinlock_exit(spinlock_t **lock) +{ + spin_unlock(*lock); +} + +#define SPINLOCK_CONTEXT(name, lock) \ + spinlock_t *spinlock_guard_##name __guard(spinlock_exit) = &(lock); \ + spin_lock(&(lock)); + +static void mutex_exit(struct mutex **lock) +{ + mutex_unlock(*lock); +} + +#define MUTEX_CONTEXT(name, lock) \ + struct mutex *mutex_guard_##name __guard(mutex_exit) = &(lock); \ + mutex_lock(&(lock)); + +#define GENERATE_2_CONTEXT_TESTCASE(outer, outer_lock, inner, inner_lock) \ + \ +static void __maybe_unused inner##_in_##outer(void) \ +{ \ + outer##_CONTEXT(_, outer_lock); \ + { \ + inner##_CONTEXT(_, inner_lock); \ + } \ +} + +/* + * wait contexts (considering PREEMPT_RT) + * + * o: inner is allowed in outer + * x: inner is disallowed in outer + * + * \ inner | RCU | RAW_SPIN | SPIN | MUTEX + * outer \ | | | | + * ---------------+-------+----------+------+------- + * HARDIRQ | o | o | o | x + * ---------------+-------+----------+------+------- + * NOTTHREADED_IRQ| o | o | x | x + * ---------------+-------+----------+------+------- + * SOFTIRQ | o | o | o | x + * ---------------+-------+----------+------+------- + * RCU | o | o | o | x + * ---------------+-------+----------+------+------- + * RCU_BH | o | o | o | x + * ---------------+-------+----------+------+------- + * RCU_CALLBACK | o | o | o | x + * ---------------+-------+----------+------+------- + * RCU_SCHED | o | o | x | x + * ---------------+-------+----------+------+------- + * RAW_SPIN | o | o | x | x + * ---------------+-------+----------+------+------- + * SPIN | o | o | o | x + * ---------------+-------+----------+------+------- + * MUTEX | o | o | o | o + * ---------------+-------+----------+------+------- + */ + +#define GENERATE_2_CONTEXT_TESTCASE_FOR_ALL_OUTER(inner, inner_lock) \ +GENERATE_2_CONTEXT_TESTCASE(HARDIRQ, , inner, inner_lock) \ +GENERATE_2_CONTEXT_TESTCASE(NOTTHREADED_HARDIRQ, , inner, inner_lock) \ +GENERATE_2_CONTEXT_TESTCASE(SOFTIRQ, , inner, inner_lock) \ +GENERATE_2_CONTEXT_TESTCASE(RCU, , inner, inner_lock) \ +GENERATE_2_CONTEXT_TESTCASE(RCU_BH, , inner, inner_lock) \ +GENERATE_2_CONTEXT_TESTCASE(RCU_CALLBACK, , inner, inner_lock) \ +GENERATE_2_CONTEXT_TESTCASE(RCU_SCHED, , inner, inner_lock) \ +GENERATE_2_CONTEXT_TESTCASE(RAW_SPINLOCK, raw_lock_A, inner, inner_lock) \ +GENERATE_2_CONTEXT_TESTCASE(SPINLOCK, lock_A, inner, inner_lock) \ +GENERATE_2_CONTEXT_TESTCASE(MUTEX, mutex_A, inner, inner_lock) + +GENERATE_2_CONTEXT_TESTCASE_FOR_ALL_OUTER(RCU, ) +GENERATE_2_CONTEXT_TESTCASE_FOR_ALL_OUTER(RAW_SPINLOCK, raw_lock_B) +GENERATE_2_CONTEXT_TESTCASE_FOR_ALL_OUTER(SPINLOCK, lock_B) +GENERATE_2_CONTEXT_TESTCASE_FOR_ALL_OUTER(MUTEX, mutex_B) + +/* the outer context allows all kinds of preemption */ +#define DO_CONTEXT_TESTCASE_OUTER_PREEMPTIBLE(outer) \ + dotest(RCU_in_##outer, SUCCESS, LOCKTYPE_RWLOCK); \ + dotest(RAW_SPINLOCK_in_##outer, SUCCESS, LOCKTYPE_SPIN); \ + dotest(SPINLOCK_in_##outer, SUCCESS, LOCKTYPE_SPIN); \ + dotest(MUTEX_in_##outer, SUCCESS, LOCKTYPE_MUTEX); \ + +/* + * the outer context only allows the preemption introduced by spinlock_t (which + * is a sleepable lock for PREEMPT_RT) + */ +#define DO_CONTEXT_TESTCASE_OUTER_LIMITED_PREEMPTIBLE(outer) \ + dotest(RCU_in_##outer, SUCCESS, LOCKTYPE_RWLOCK); \ + dotest(RAW_SPINLOCK_in_##outer, SUCCESS, LOCKTYPE_SPIN); \ + dotest(SPINLOCK_in_##outer, SUCCESS, LOCKTYPE_SPIN); \ + dotest(MUTEX_in_##outer, FAILURE, LOCKTYPE_MUTEX); \ + +/* the outer doesn't allows any kind of preemption */ +#define DO_CONTEXT_TESTCASE_OUTER_NOT_PREEMPTIBLE(outer) \ + dotest(RCU_in_##outer, SUCCESS, LOCKTYPE_RWLOCK); \ + dotest(RAW_SPINLOCK_in_##outer, SUCCESS, LOCKTYPE_SPIN); \ + dotest(SPINLOCK_in_##outer, FAILURE, LOCKTYPE_SPIN); \ + dotest(MUTEX_in_##outer, FAILURE, LOCKTYPE_MUTEX); \ + +static void wait_context_tests(void) +{ + printk(" --------------------------------------------------------------------------\n"); + printk(" | wait context tests |\n"); + printk(" --------------------------------------------------------------------------\n"); + printk(" | rcu | raw | spin |mutex |\n"); + printk(" --------------------------------------------------------------------------\n"); + print_testname("in hardirq context"); + DO_CONTEXT_TESTCASE_OUTER_LIMITED_PREEMPTIBLE(HARDIRQ); + pr_cont("\n"); + + print_testname("in hardirq context (not threaded)"); + DO_CONTEXT_TESTCASE_OUTER_NOT_PREEMPTIBLE(NOTTHREADED_HARDIRQ); + pr_cont("\n"); + + print_testname("in softirq context"); + DO_CONTEXT_TESTCASE_OUTER_LIMITED_PREEMPTIBLE(SOFTIRQ); + pr_cont("\n"); + + print_testname("in RCU context"); + DO_CONTEXT_TESTCASE_OUTER_LIMITED_PREEMPTIBLE(RCU); + pr_cont("\n"); + + print_testname("in RCU-bh context"); + DO_CONTEXT_TESTCASE_OUTER_LIMITED_PREEMPTIBLE(RCU_BH); + pr_cont("\n"); + + print_testname("in RCU callback context"); + DO_CONTEXT_TESTCASE_OUTER_LIMITED_PREEMPTIBLE(RCU_CALLBACK); + pr_cont("\n"); + + print_testname("in RCU-sched context"); + DO_CONTEXT_TESTCASE_OUTER_NOT_PREEMPTIBLE(RCU_SCHED); + pr_cont("\n"); + + print_testname("in RAW_SPINLOCK context"); + DO_CONTEXT_TESTCASE_OUTER_NOT_PREEMPTIBLE(RAW_SPINLOCK); + pr_cont("\n"); + + print_testname("in SPINLOCK context"); + DO_CONTEXT_TESTCASE_OUTER_LIMITED_PREEMPTIBLE(SPINLOCK); + pr_cont("\n"); + + print_testname("in MUTEX context"); + DO_CONTEXT_TESTCASE_OUTER_PREEMPTIBLE(MUTEX); + pr_cont("\n"); +} + +static void local_lock_2(void) +{ + local_lock_acquire(&local_A); /* IRQ-ON */ + local_lock_release(&local_A); + + HARDIRQ_ENTER(); + spin_lock(&lock_A); /* IN-IRQ */ + spin_unlock(&lock_A); + HARDIRQ_EXIT() + + HARDIRQ_DISABLE(); + spin_lock(&lock_A); + local_lock_acquire(&local_A); /* IN-IRQ <-> IRQ-ON cycle, false */ + local_lock_release(&local_A); + spin_unlock(&lock_A); + HARDIRQ_ENABLE(); +} + +static void local_lock_3A(void) +{ + local_lock_acquire(&local_A); /* IRQ-ON */ + spin_lock(&lock_B); /* IRQ-ON */ + spin_unlock(&lock_B); + local_lock_release(&local_A); + + HARDIRQ_ENTER(); + spin_lock(&lock_A); /* IN-IRQ */ + spin_unlock(&lock_A); + HARDIRQ_EXIT() + + HARDIRQ_DISABLE(); + spin_lock(&lock_A); + local_lock_acquire(&local_A); /* IN-IRQ <-> IRQ-ON cycle only if we count local_lock(), false */ + local_lock_release(&local_A); + spin_unlock(&lock_A); + HARDIRQ_ENABLE(); +} + +static void local_lock_3B(void) +{ + local_lock_acquire(&local_A); /* IRQ-ON */ + spin_lock(&lock_B); /* IRQ-ON */ + spin_unlock(&lock_B); + local_lock_release(&local_A); + + HARDIRQ_ENTER(); + spin_lock(&lock_A); /* IN-IRQ */ + spin_unlock(&lock_A); + HARDIRQ_EXIT() + + HARDIRQ_DISABLE(); + spin_lock(&lock_A); + local_lock_acquire(&local_A); /* IN-IRQ <-> IRQ-ON cycle only if we count local_lock(), false */ + local_lock_release(&local_A); + spin_unlock(&lock_A); + HARDIRQ_ENABLE(); + + HARDIRQ_DISABLE(); + spin_lock(&lock_A); + spin_lock(&lock_B); /* IN-IRQ <-> IRQ-ON cycle, true */ + spin_unlock(&lock_B); + spin_unlock(&lock_A); + HARDIRQ_DISABLE(); + +} + +static void local_lock_tests(void) +{ + printk(" --------------------------------------------------------------------------\n"); + printk(" | local_lock tests |\n"); + printk(" ---------------------\n"); + + print_testname("local_lock inversion 2"); + dotest(local_lock_2, SUCCESS, LOCKTYPE_LL); + pr_cont("\n"); + + print_testname("local_lock inversion 3A"); + dotest(local_lock_3A, SUCCESS, LOCKTYPE_LL); + pr_cont("\n"); + + print_testname("local_lock inversion 3B"); + dotest(local_lock_3B, FAILURE, LOCKTYPE_LL); + pr_cont("\n"); +} + void locking_selftest(void) { /* @@ -2446,7 +2771,6 @@ void locking_selftest(void) printk(" --------------------------------------------------------------------------\n"); init_shared_classes(); - debug_locks_silent = !debug_locks_verbose; lockdep_set_selftest_task(current); DO_TESTCASE_6R("A-A deadlock", AA); @@ -2542,6 +2866,12 @@ void locking_selftest(void) fs_reclaim_tests(); + /* Wait context test cases that are specific for RAW_LOCK_NESTING */ + if (IS_ENABLED(CONFIG_PROVE_RAW_LOCK_NESTING)) + wait_context_tests(); + + local_lock_tests(); + if (unexpected_testcase_failures) { printk("-----------------------------------------------------------------\n"); debug_locks = 0; diff --git a/lib/parman.c b/lib/parman.c index c6e42a8db824..a11f2f667639 100644 --- a/lib/parman.c +++ b/lib/parman.c @@ -85,7 +85,6 @@ static int parman_shrink(struct parman *parman) } static bool parman_prio_used(struct parman_prio *prio) - { return !list_empty(&prio->item_list); } diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c index e59eda07305e..a1071cdefb5a 100644 --- a/lib/percpu-refcount.c +++ b/lib/percpu-refcount.c @@ -5,6 +5,7 @@ #include <linux/sched.h> #include <linux/wait.h> #include <linux/slab.h> +#include <linux/mm.h> #include <linux/percpu-refcount.h> /* @@ -168,6 +169,7 @@ static void percpu_ref_switch_to_atomic_rcu(struct rcu_head *rcu) struct percpu_ref_data, rcu); struct percpu_ref *ref = data->ref; unsigned long __percpu *percpu_count = percpu_count_ptr(ref); + static atomic_t underflows; unsigned long count = 0; int cpu; @@ -191,9 +193,13 @@ static void percpu_ref_switch_to_atomic_rcu(struct rcu_head *rcu) */ atomic_long_add((long)count - PERCPU_COUNT_BIAS, &data->count); - WARN_ONCE(atomic_long_read(&data->count) <= 0, - "percpu ref (%ps) <= 0 (%ld) after switching to atomic", - data->release, atomic_long_read(&data->count)); + if (WARN_ONCE(atomic_long_read(&data->count) <= 0, + "percpu ref (%ps) <= 0 (%ld) after switching to atomic", + data->release, atomic_long_read(&data->count)) && + atomic_inc_return(&underflows) < 4) { + pr_err("%s(): percpu_ref underflow", __func__); + mem_dump_obj(data); + } /* @ref is viewed as dead on all CPUs, send out switch confirmation */ percpu_ref_call_confirm_rcu(rcu); diff --git a/lib/test_bpf.c b/lib/test_bpf.c index ca7d635bccd9..4dc4dcbecd12 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -345,7 +345,7 @@ static int __bpf_fill_ja(struct bpf_test *self, unsigned int len, static int bpf_fill_maxinsns11(struct bpf_test *self) { - /* Hits 70 passes on x86_64, so cannot get JITed there. */ + /* Hits 70 passes on x86_64 and triggers NOPs padding. */ return __bpf_fill_ja(self, BPF_MAXINSNS, 68); } @@ -4295,13 +4295,13 @@ static struct bpf_test tests[] = { { { 0, 0xffffffff } }, .stack_depth = 40, }, - /* BPF_STX | BPF_XADD | BPF_W/DW */ + /* BPF_STX | BPF_ATOMIC | BPF_W/DW */ { "STX_XADD_W: Test: 0x12 + 0x10 = 0x22", .u.insns_int = { BPF_ALU32_IMM(BPF_MOV, R0, 0x12), BPF_ST_MEM(BPF_W, R10, -40, 0x10), - BPF_STX_XADD(BPF_W, R10, R0, -40), + BPF_ATOMIC_OP(BPF_W, BPF_ADD, R10, R0, -40), BPF_LDX_MEM(BPF_W, R0, R10, -40), BPF_EXIT_INSN(), }, @@ -4316,7 +4316,7 @@ static struct bpf_test tests[] = { BPF_ALU64_REG(BPF_MOV, R1, R10), BPF_ALU32_IMM(BPF_MOV, R0, 0x12), BPF_ST_MEM(BPF_W, R10, -40, 0x10), - BPF_STX_XADD(BPF_W, R10, R0, -40), + BPF_ATOMIC_OP(BPF_W, BPF_ADD, R10, R0, -40), BPF_ALU64_REG(BPF_MOV, R0, R10), BPF_ALU64_REG(BPF_SUB, R0, R1), BPF_EXIT_INSN(), @@ -4331,7 +4331,7 @@ static struct bpf_test tests[] = { .u.insns_int = { BPF_ALU32_IMM(BPF_MOV, R0, 0x12), BPF_ST_MEM(BPF_W, R10, -40, 0x10), - BPF_STX_XADD(BPF_W, R10, R0, -40), + BPF_ATOMIC_OP(BPF_W, BPF_ADD, R10, R0, -40), BPF_EXIT_INSN(), }, INTERNAL, @@ -4352,7 +4352,7 @@ static struct bpf_test tests[] = { .u.insns_int = { BPF_ALU32_IMM(BPF_MOV, R0, 0x12), BPF_ST_MEM(BPF_DW, R10, -40, 0x10), - BPF_STX_XADD(BPF_DW, R10, R0, -40), + BPF_ATOMIC_OP(BPF_DW, BPF_ADD, R10, R0, -40), BPF_LDX_MEM(BPF_DW, R0, R10, -40), BPF_EXIT_INSN(), }, @@ -4367,7 +4367,7 @@ static struct bpf_test tests[] = { BPF_ALU64_REG(BPF_MOV, R1, R10), BPF_ALU32_IMM(BPF_MOV, R0, 0x12), BPF_ST_MEM(BPF_DW, R10, -40, 0x10), - BPF_STX_XADD(BPF_DW, R10, R0, -40), + BPF_ATOMIC_OP(BPF_DW, BPF_ADD, R10, R0, -40), BPF_ALU64_REG(BPF_MOV, R0, R10), BPF_ALU64_REG(BPF_SUB, R0, R1), BPF_EXIT_INSN(), @@ -4382,7 +4382,7 @@ static struct bpf_test tests[] = { .u.insns_int = { BPF_ALU32_IMM(BPF_MOV, R0, 0x12), BPF_ST_MEM(BPF_DW, R10, -40, 0x10), - BPF_STX_XADD(BPF_DW, R10, R0, -40), + BPF_ATOMIC_OP(BPF_DW, BPF_ADD, R10, R0, -40), BPF_EXIT_INSN(), }, INTERNAL, @@ -5318,15 +5318,10 @@ static struct bpf_test tests[] = { { "BPF_MAXINSNS: Jump, gap, jump, ...", { }, -#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_X86) - CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL, -#else CLASSIC | FLAG_NO_DATA, -#endif { }, { { 0, 0xababcbac } }, .fill_helper = bpf_fill_maxinsns11, - .expected_errcode = -ENOTSUPP, }, { "BPF_MAXINSNS: jump over MSH", diff --git a/lib/test_fpu.c b/lib/test_fpu.c index c33764aa3eb8..e82db19fed84 100644 --- a/lib/test_fpu.c +++ b/lib/test_fpu.c @@ -63,7 +63,7 @@ static int test_fpu_get(void *data, u64 *val) return status; } -DEFINE_SIMPLE_ATTRIBUTE(test_fpu_fops, test_fpu_get, NULL, "%lld\n"); +DEFINE_DEBUGFS_ATTRIBUTE(test_fpu_fops, test_fpu_get, NULL, "%lld\n"); static struct dentry *selftest_dir; static int __init test_fpu_init(void) @@ -72,8 +72,8 @@ static int __init test_fpu_init(void) if (!selftest_dir) return -ENOMEM; - debugfs_create_file("test_fpu", 0444, selftest_dir, NULL, - &test_fpu_fops); + debugfs_create_file_unsafe("test_fpu", 0444, selftest_dir, NULL, + &test_fpu_fops); return 0; } diff --git a/lib/timerqueue.c b/lib/timerqueue.c index c52710964593..cdb9c7658478 100644 --- a/lib/timerqueue.c +++ b/lib/timerqueue.c @@ -14,6 +14,14 @@ #include <linux/rbtree.h> #include <linux/export.h> +#define __node_2_tq(_n) \ + rb_entry((_n), struct timerqueue_node, node) + +static inline bool __timerqueue_less(struct rb_node *a, const struct rb_node *b) +{ + return __node_2_tq(a)->expires < __node_2_tq(b)->expires; +} + /** * timerqueue_add - Adds timer to timerqueue. * @@ -26,28 +34,10 @@ */ bool timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node) { - struct rb_node **p = &head->rb_root.rb_root.rb_node; - struct rb_node *parent = NULL; - struct timerqueue_node *ptr; - bool leftmost = true; - /* Make sure we don't add nodes that are already added */ WARN_ON_ONCE(!RB_EMPTY_NODE(&node->node)); - while (*p) { - parent = *p; - ptr = rb_entry(parent, struct timerqueue_node, node); - if (node->expires < ptr->expires) { - p = &(*p)->rb_left; - } else { - p = &(*p)->rb_right; - leftmost = false; - } - } - rb_link_node(&node->node, parent, p); - rb_insert_color_cached(&node->node, &head->rb_root, leftmost); - - return leftmost; + return rb_add_cached(&node->node, &head->rb_root, __timerqueue_less); } EXPORT_SYMBOL_GPL(timerqueue_add); diff --git a/lib/ubsan.c b/lib/ubsan.c index 3e3352f3d0da..bec38c64d6a6 100644 --- a/lib/ubsan.c +++ b/lib/ubsan.c @@ -427,3 +427,34 @@ void __ubsan_handle_load_invalid_value(void *_data, void *val) ubsan_epilogue(); } EXPORT_SYMBOL(__ubsan_handle_load_invalid_value); + +void __ubsan_handle_alignment_assumption(void *_data, unsigned long ptr, + unsigned long align, + unsigned long offset); +void __ubsan_handle_alignment_assumption(void *_data, unsigned long ptr, + unsigned long align, + unsigned long offset) +{ + struct alignment_assumption_data *data = _data; + unsigned long real_ptr; + + if (suppress_report(&data->location)) + return; + + ubsan_prologue(&data->location, "alignment-assumption"); + + if (offset) + pr_err("assumption of %lu byte alignment (with offset of %lu byte) for pointer of type %s failed", + align, offset, data->type->type_name); + else + pr_err("assumption of %lu byte alignment for pointer of type %s failed", + align, data->type->type_name); + + real_ptr = ptr - offset; + pr_err("%saddress is %lu aligned, misalignment offset is %lu bytes", + offset ? "offset " : "", BIT(real_ptr ? __ffs(real_ptr) : 0), + real_ptr & (align - 1)); + + ubsan_epilogue(); +} +EXPORT_SYMBOL(__ubsan_handle_alignment_assumption); diff --git a/lib/ubsan.h b/lib/ubsan.h index 7b56c09473a9..9a0b71c5ff9f 100644 --- a/lib/ubsan.h +++ b/lib/ubsan.h @@ -78,6 +78,12 @@ struct invalid_value_data { struct type_descriptor *type; }; +struct alignment_assumption_data { + struct source_location location; + struct source_location assumption_location; + struct type_descriptor *type; +}; + #if defined(CONFIG_ARCH_SUPPORTS_INT128) typedef __int128 s_max; typedef unsigned __int128 u_max; |