diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-11-02 14:47:37 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-11-02 14:47:37 -0800 |
commit | b7cbaf59f62f8ab8f157698f9e31642bff525bd0 (patch) | |
tree | d7cb5995bc420fee10873f25b15f14d84f2c1bde | |
parent | 495023e4e49e4b7dee35928800bf0317276576c1 (diff) | |
parent | 3b70ae4f5c4e050bdebeeefe0c369524f37917cf (diff) | |
download | linux-b7cbaf59f62f8ab8f157698f9e31642bff525bd0.tar.bz2 |
Merge branch 'akpm' (patches from Andrew)
Merge misc fixes from Andrew Morton:
"Subsystems affected by this patch series: mm (memremap, memcg,
slab-generic, kasan, mempolicy, pagecache, oom-kill, pagemap),
kthread, signals, lib, epoll, and core-kernel"
* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
kernel/hung_task.c: make type annotations consistent
epoll: add a selftest for epoll timeout race
mm: always have io_remap_pfn_range() set pgprot_decrypted()
mm, oom: keep oom_adj under or at upper limit when printing
kthread_worker: prevent queuing delayed work from timer_fn when it is being canceled
mm/truncate.c: make __invalidate_mapping_pages() static
lib/crc32test: remove extra local_irq_disable/enable
ptrace: fix task_join_group_stop() for the case when current is traced
mm: mempolicy: fix potential pte_unmap_unlock pte error
kasan: adopt KUNIT tests to SW_TAGS mode
mm: memcg: link page counters to root if use_hierarchy is false
mm: memcontrol: correct the NR_ANON_THPS counter of hierarchical memcg
hugetlb_cgroup: fix reservation accounting
mm/mremap_pages: fix static key devmap_managed_key updates
-rw-r--r-- | fs/proc/base.c | 2 | ||||
-rw-r--r-- | include/linux/mm.h | 9 | ||||
-rw-r--r-- | include/linux/pgtable.h | 4 | ||||
-rw-r--r-- | kernel/hung_task.c | 3 | ||||
-rw-r--r-- | kernel/kthread.c | 3 | ||||
-rw-r--r-- | kernel/signal.c | 19 | ||||
-rw-r--r-- | lib/crc32test.c | 4 | ||||
-rw-r--r-- | lib/test_kasan.c | 149 | ||||
-rw-r--r-- | mm/hugetlb.c | 20 | ||||
-rw-r--r-- | mm/memcontrol.c | 25 | ||||
-rw-r--r-- | mm/mempolicy.c | 6 | ||||
-rw-r--r-- | mm/memremap.c | 39 | ||||
-rw-r--r-- | mm/truncate.c | 2 | ||||
-rw-r--r-- | tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c | 95 |
14 files changed, 275 insertions, 105 deletions
diff --git a/fs/proc/base.c b/fs/proc/base.c index 0f707003dda5..b362523a9829 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1049,6 +1049,8 @@ static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count, oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) / OOM_SCORE_ADJ_MAX; put_task_struct(task); + if (oom_adj > OOM_ADJUST_MAX) + oom_adj = OOM_ADJUST_MAX; len = snprintf(buffer, sizeof(buffer), "%d\n", oom_adj); return simple_read_from_buffer(buf, count, ppos, buffer, len); } diff --git a/include/linux/mm.h b/include/linux/mm.h index ef360fe70aaf..db6ae4d3fb4e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2759,6 +2759,15 @@ static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma, return VM_FAULT_NOPAGE; } +#ifndef io_remap_pfn_range +static inline int io_remap_pfn_range(struct vm_area_struct *vma, + unsigned long addr, unsigned long pfn, + unsigned long size, pgprot_t prot) +{ + return remap_pfn_range(vma, addr, pfn, size, pgprot_decrypted(prot)); +} +#endif + static inline vm_fault_t vmf_error(int err) { if (err == -ENOMEM) diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 38c33eabea89..71125a4676c4 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1427,10 +1427,6 @@ typedef unsigned int pgtbl_mod_mask; #endif /* !__ASSEMBLY__ */ -#ifndef io_remap_pfn_range -#define io_remap_pfn_range remap_pfn_range -#endif - #ifndef has_transparent_hugepage #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define has_transparent_hugepage() 1 diff --git a/kernel/hung_task.c b/kernel/hung_task.c index ce76f490126c..396ebaebea3f 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -225,8 +225,7 @@ static long hung_timeout_jiffies(unsigned long last_checked, * Process updating of timeout sysctl */ int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos) + void *buffer, size_t *lenp, loff_t *ppos) { int ret; diff --git a/kernel/kthread.c b/kernel/kthread.c index e29773c82b70..933a625621b8 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -897,7 +897,8 @@ void kthread_delayed_work_timer_fn(struct timer_list *t) /* Move the work from worker->delayed_work_list. */ WARN_ON_ONCE(list_empty(&work->node)); list_del_init(&work->node); - kthread_insert_work(worker, work, &worker->work_list); + if (!work->canceling) + kthread_insert_work(worker, work, &worker->work_list); raw_spin_unlock_irqrestore(&worker->lock, flags); } diff --git a/kernel/signal.c b/kernel/signal.c index a38b3edc6851..ef8f2a28d37c 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -391,16 +391,17 @@ static bool task_participate_group_stop(struct task_struct *task) void task_join_group_stop(struct task_struct *task) { + unsigned long mask = current->jobctl & JOBCTL_STOP_SIGMASK; + struct signal_struct *sig = current->signal; + + if (sig->group_stop_count) { + sig->group_stop_count++; + mask |= JOBCTL_STOP_CONSUME; + } else if (!(sig->flags & SIGNAL_STOP_STOPPED)) + return; + /* Have the new thread join an on-going signal group stop */ - unsigned long jobctl = current->jobctl; - if (jobctl & JOBCTL_STOP_PENDING) { - struct signal_struct *sig = current->signal; - unsigned long signr = jobctl & JOBCTL_STOP_SIGMASK; - unsigned long gstop = JOBCTL_STOP_PENDING | JOBCTL_STOP_CONSUME; - if (task_set_jobctl_pending(task, signr | gstop)) { - sig->group_stop_count++; - } - } + task_set_jobctl_pending(task, mask | JOBCTL_STOP_PENDING); } /* diff --git a/lib/crc32test.c b/lib/crc32test.c index 97d6a57cefcc..61ddce2cff77 100644 --- a/lib/crc32test.c +++ b/lib/crc32test.c @@ -683,7 +683,6 @@ static int __init crc32c_test(void) /* reduce OS noise */ local_irq_save(flags); - local_irq_disable(); nsec = ktime_get_ns(); for (i = 0; i < 100; i++) { @@ -694,7 +693,6 @@ static int __init crc32c_test(void) nsec = ktime_get_ns() - nsec; local_irq_restore(flags); - local_irq_enable(); pr_info("crc32c: CRC_LE_BITS = %d\n", CRC_LE_BITS); @@ -768,7 +766,6 @@ static int __init crc32_test(void) /* reduce OS noise */ local_irq_save(flags); - local_irq_disable(); nsec = ktime_get_ns(); for (i = 0; i < 100; i++) { @@ -783,7 +780,6 @@ static int __init crc32_test(void) nsec = ktime_get_ns() - nsec; local_irq_restore(flags); - local_irq_enable(); pr_info("crc32: CRC_LE_BITS = %d, CRC_BE BITS = %d\n", CRC_LE_BITS, CRC_BE_BITS); diff --git a/lib/test_kasan.c b/lib/test_kasan.c index 63c26171a791..662f862702fc 100644 --- a/lib/test_kasan.c +++ b/lib/test_kasan.c @@ -216,6 +216,12 @@ static void kmalloc_oob_16(struct kunit *test) u64 words[2]; } *ptr1, *ptr2; + /* This test is specifically crafted for the generic mode. */ + if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) { + kunit_info(test, "CONFIG_KASAN_GENERIC required\n"); + return; + } + ptr1 = kmalloc(sizeof(*ptr1) - 3, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr1); @@ -227,6 +233,23 @@ static void kmalloc_oob_16(struct kunit *test) kfree(ptr2); } +static void kmalloc_uaf_16(struct kunit *test) +{ + struct { + u64 words[2]; + } *ptr1, *ptr2; + + ptr1 = kmalloc(sizeof(*ptr1), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr1); + + ptr2 = kmalloc(sizeof(*ptr2), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr2); + kfree(ptr2); + + KUNIT_EXPECT_KASAN_FAIL(test, *ptr1 = *ptr2); + kfree(ptr1); +} + static void kmalloc_oob_memset_2(struct kunit *test) { char *ptr; @@ -429,6 +452,12 @@ static void kasan_global_oob(struct kunit *test) volatile int i = 3; char *p = &global_array[ARRAY_SIZE(global_array) + i]; + /* Only generic mode instruments globals. */ + if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) { + kunit_info(test, "CONFIG_KASAN_GENERIC required"); + return; + } + KUNIT_EXPECT_KASAN_FAIL(test, *(volatile char *)p); } @@ -467,6 +496,12 @@ static void kasan_alloca_oob_left(struct kunit *test) char alloca_array[i]; char *p = alloca_array - 1; + /* Only generic mode instruments dynamic allocas. */ + if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) { + kunit_info(test, "CONFIG_KASAN_GENERIC required"); + return; + } + if (!IS_ENABLED(CONFIG_KASAN_STACK)) { kunit_info(test, "CONFIG_KASAN_STACK is not enabled"); return; @@ -481,6 +516,12 @@ static void kasan_alloca_oob_right(struct kunit *test) char alloca_array[i]; char *p = alloca_array + i; + /* Only generic mode instruments dynamic allocas. */ + if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) { + kunit_info(test, "CONFIG_KASAN_GENERIC required"); + return; + } + if (!IS_ENABLED(CONFIG_KASAN_STACK)) { kunit_info(test, "CONFIG_KASAN_STACK is not enabled"); return; @@ -551,6 +592,9 @@ static void kasan_memchr(struct kunit *test) return; } + if (OOB_TAG_OFF) + size = round_up(size, OOB_TAG_OFF); + ptr = kmalloc(size, GFP_KERNEL | __GFP_ZERO); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); @@ -573,6 +617,9 @@ static void kasan_memcmp(struct kunit *test) return; } + if (OOB_TAG_OFF) + size = round_up(size, OOB_TAG_OFF); + ptr = kmalloc(size, GFP_KERNEL | __GFP_ZERO); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); memset(arr, 0, sizeof(arr)); @@ -619,13 +666,50 @@ static void kasan_strings(struct kunit *test) KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result = strnlen(ptr, 1)); } -static void kasan_bitops(struct kunit *test) +static void kasan_bitops_modify(struct kunit *test, int nr, void *addr) +{ + KUNIT_EXPECT_KASAN_FAIL(test, set_bit(nr, addr)); + KUNIT_EXPECT_KASAN_FAIL(test, __set_bit(nr, addr)); + KUNIT_EXPECT_KASAN_FAIL(test, clear_bit(nr, addr)); + KUNIT_EXPECT_KASAN_FAIL(test, __clear_bit(nr, addr)); + KUNIT_EXPECT_KASAN_FAIL(test, clear_bit_unlock(nr, addr)); + KUNIT_EXPECT_KASAN_FAIL(test, __clear_bit_unlock(nr, addr)); + KUNIT_EXPECT_KASAN_FAIL(test, change_bit(nr, addr)); + KUNIT_EXPECT_KASAN_FAIL(test, __change_bit(nr, addr)); +} + +static void kasan_bitops_test_and_modify(struct kunit *test, int nr, void *addr) +{ + KUNIT_EXPECT_KASAN_FAIL(test, test_and_set_bit(nr, addr)); + KUNIT_EXPECT_KASAN_FAIL(test, __test_and_set_bit(nr, addr)); + KUNIT_EXPECT_KASAN_FAIL(test, test_and_set_bit_lock(nr, addr)); + KUNIT_EXPECT_KASAN_FAIL(test, test_and_clear_bit(nr, addr)); + KUNIT_EXPECT_KASAN_FAIL(test, __test_and_clear_bit(nr, addr)); + KUNIT_EXPECT_KASAN_FAIL(test, test_and_change_bit(nr, addr)); + KUNIT_EXPECT_KASAN_FAIL(test, __test_and_change_bit(nr, addr)); + KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result = test_bit(nr, addr)); + +#if defined(clear_bit_unlock_is_negative_byte) + KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result = + clear_bit_unlock_is_negative_byte(nr, addr)); +#endif +} + +static void kasan_bitops_generic(struct kunit *test) { + long *bits; + + /* This test is specifically crafted for the generic mode. */ + if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) { + kunit_info(test, "CONFIG_KASAN_GENERIC required\n"); + return; + } + /* * Allocate 1 more byte, which causes kzalloc to round up to 16-bytes; * this way we do not actually corrupt other memory. */ - long *bits = kzalloc(sizeof(*bits) + 1, GFP_KERNEL); + bits = kzalloc(sizeof(*bits) + 1, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, bits); /* @@ -633,55 +717,34 @@ static void kasan_bitops(struct kunit *test) * below accesses are still out-of-bounds, since bitops are defined to * operate on the whole long the bit is in. */ - KUNIT_EXPECT_KASAN_FAIL(test, set_bit(BITS_PER_LONG, bits)); - - KUNIT_EXPECT_KASAN_FAIL(test, __set_bit(BITS_PER_LONG, bits)); - - KUNIT_EXPECT_KASAN_FAIL(test, clear_bit(BITS_PER_LONG, bits)); - - KUNIT_EXPECT_KASAN_FAIL(test, __clear_bit(BITS_PER_LONG, bits)); - - KUNIT_EXPECT_KASAN_FAIL(test, clear_bit_unlock(BITS_PER_LONG, bits)); - - KUNIT_EXPECT_KASAN_FAIL(test, __clear_bit_unlock(BITS_PER_LONG, bits)); - - KUNIT_EXPECT_KASAN_FAIL(test, change_bit(BITS_PER_LONG, bits)); - - KUNIT_EXPECT_KASAN_FAIL(test, __change_bit(BITS_PER_LONG, bits)); + kasan_bitops_modify(test, BITS_PER_LONG, bits); /* * Below calls try to access bit beyond allocated memory. */ - KUNIT_EXPECT_KASAN_FAIL(test, - test_and_set_bit(BITS_PER_LONG + BITS_PER_BYTE, bits)); - - KUNIT_EXPECT_KASAN_FAIL(test, - __test_and_set_bit(BITS_PER_LONG + BITS_PER_BYTE, bits)); - - KUNIT_EXPECT_KASAN_FAIL(test, - test_and_set_bit_lock(BITS_PER_LONG + BITS_PER_BYTE, bits)); + kasan_bitops_test_and_modify(test, BITS_PER_LONG + BITS_PER_BYTE, bits); - KUNIT_EXPECT_KASAN_FAIL(test, - test_and_clear_bit(BITS_PER_LONG + BITS_PER_BYTE, bits)); + kfree(bits); +} - KUNIT_EXPECT_KASAN_FAIL(test, - __test_and_clear_bit(BITS_PER_LONG + BITS_PER_BYTE, bits)); +static void kasan_bitops_tags(struct kunit *test) +{ + long *bits; - KUNIT_EXPECT_KASAN_FAIL(test, - test_and_change_bit(BITS_PER_LONG + BITS_PER_BYTE, bits)); + /* This test is specifically crafted for the tag-based mode. */ + if (IS_ENABLED(CONFIG_KASAN_GENERIC)) { + kunit_info(test, "CONFIG_KASAN_SW_TAGS required\n"); + return; + } - KUNIT_EXPECT_KASAN_FAIL(test, - __test_and_change_bit(BITS_PER_LONG + BITS_PER_BYTE, bits)); + /* Allocation size will be rounded to up granule size, which is 16. */ + bits = kzalloc(sizeof(*bits), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, bits); - KUNIT_EXPECT_KASAN_FAIL(test, - kasan_int_result = - test_bit(BITS_PER_LONG + BITS_PER_BYTE, bits)); + /* Do the accesses past the 16 allocated bytes. */ + kasan_bitops_modify(test, BITS_PER_LONG, &bits[1]); + kasan_bitops_test_and_modify(test, BITS_PER_LONG + BITS_PER_BYTE, &bits[1]); -#if defined(clear_bit_unlock_is_negative_byte) - KUNIT_EXPECT_KASAN_FAIL(test, - kasan_int_result = clear_bit_unlock_is_negative_byte( - BITS_PER_LONG + BITS_PER_BYTE, bits)); -#endif kfree(bits); } @@ -728,6 +791,7 @@ static struct kunit_case kasan_kunit_test_cases[] = { KUNIT_CASE(kmalloc_oob_krealloc_more), KUNIT_CASE(kmalloc_oob_krealloc_less), KUNIT_CASE(kmalloc_oob_16), + KUNIT_CASE(kmalloc_uaf_16), KUNIT_CASE(kmalloc_oob_in_memset), KUNIT_CASE(kmalloc_oob_memset_2), KUNIT_CASE(kmalloc_oob_memset_4), @@ -751,7 +815,8 @@ static struct kunit_case kasan_kunit_test_cases[] = { KUNIT_CASE(kasan_memchr), KUNIT_CASE(kasan_memcmp), KUNIT_CASE(kasan_strings), - KUNIT_CASE(kasan_bitops), + KUNIT_CASE(kasan_bitops_generic), + KUNIT_CASE(kasan_bitops_tags), KUNIT_CASE(kmalloc_double_kzfree), KUNIT_CASE(vmalloc_oob), {} diff --git a/mm/hugetlb.c b/mm/hugetlb.c index fe76f8fd5a73..5a620f690911 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -648,6 +648,8 @@ retry: } del += t - f; + hugetlb_cgroup_uncharge_file_region( + resv, rg, t - f); /* New entry for end of split region */ nrg->from = t; @@ -660,9 +662,6 @@ retry: /* Original entry is trimmed */ rg->to = f; - hugetlb_cgroup_uncharge_file_region( - resv, rg, nrg->to - nrg->from); - list_add(&nrg->link, &rg->link); nrg = NULL; break; @@ -678,17 +677,17 @@ retry: } if (f <= rg->from) { /* Trim beginning of region */ - del += t - rg->from; - rg->from = t; - hugetlb_cgroup_uncharge_file_region(resv, rg, t - rg->from); - } else { /* Trim end of region */ - del += rg->to - f; - rg->to = f; + del += t - rg->from; + rg->from = t; + } else { /* Trim end of region */ hugetlb_cgroup_uncharge_file_region(resv, rg, rg->to - f); + + del += rg->to - f; + rg->to = f; } } @@ -2443,6 +2442,9 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, rsv_adjust = hugepage_subpool_put_pages(spool, 1); hugetlb_acct_memory(h, -rsv_adjust); + if (deferred_reserve) + hugetlb_cgroup_uncharge_page_rsvd(hstate_index(h), + pages_per_huge_page(h), page); } return page; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 3a24e3b619f5..3dcbf24d2227 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4110,11 +4110,17 @@ static int memcg_stat_show(struct seq_file *m, void *v) (u64)memsw * PAGE_SIZE); for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) { + unsigned long nr; + if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account()) continue; + nr = memcg_page_state(memcg, memcg1_stats[i]); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (memcg1_stats[i] == NR_ANON_THPS) + nr *= HPAGE_PMD_NR; +#endif seq_printf(m, "total_%s %llu\n", memcg1_stat_names[i], - (u64)memcg_page_state(memcg, memcg1_stats[i]) * - PAGE_SIZE); + (u64)nr * PAGE_SIZE); } for (i = 0; i < ARRAY_SIZE(memcg1_events); i++) @@ -5339,17 +5345,22 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) memcg->swappiness = mem_cgroup_swappiness(parent); memcg->oom_kill_disable = parent->oom_kill_disable; } - if (parent && parent->use_hierarchy) { + if (!parent) { + page_counter_init(&memcg->memory, NULL); + page_counter_init(&memcg->swap, NULL); + page_counter_init(&memcg->kmem, NULL); + page_counter_init(&memcg->tcpmem, NULL); + } else if (parent->use_hierarchy) { memcg->use_hierarchy = true; page_counter_init(&memcg->memory, &parent->memory); page_counter_init(&memcg->swap, &parent->swap); page_counter_init(&memcg->kmem, &parent->kmem); page_counter_init(&memcg->tcpmem, &parent->tcpmem); } else { - page_counter_init(&memcg->memory, NULL); - page_counter_init(&memcg->swap, NULL); - page_counter_init(&memcg->kmem, NULL); - page_counter_init(&memcg->tcpmem, NULL); + page_counter_init(&memcg->memory, &root_mem_cgroup->memory); + page_counter_init(&memcg->swap, &root_mem_cgroup->swap); + page_counter_init(&memcg->kmem, &root_mem_cgroup->kmem); + page_counter_init(&memcg->tcpmem, &root_mem_cgroup->tcpmem); /* * Deeper hierachy with use_hierarchy == false doesn't make * much sense so let cgroup subsystem know about this diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 3fde772ef5ef..3ca4898f3f24 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -525,7 +525,7 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, unsigned long flags = qp->flags; int ret; bool has_unmovable = false; - pte_t *pte; + pte_t *pte, *mapped_pte; spinlock_t *ptl; ptl = pmd_trans_huge_lock(pmd, vma); @@ -539,7 +539,7 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, if (pmd_trans_unstable(pmd)) return 0; - pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); + mapped_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); for (; addr != end; pte++, addr += PAGE_SIZE) { if (!pte_present(*pte)) continue; @@ -571,7 +571,7 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, } else break; } - pte_unmap_unlock(pte - 1, ptl); + pte_unmap_unlock(mapped_pte, ptl); cond_resched(); if (has_unmovable) diff --git a/mm/memremap.c b/mm/memremap.c index 73a206d0f645..16b2fb482da1 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -41,28 +41,24 @@ EXPORT_SYMBOL_GPL(memremap_compat_align); DEFINE_STATIC_KEY_FALSE(devmap_managed_key); EXPORT_SYMBOL(devmap_managed_key); -static void devmap_managed_enable_put(void) +static void devmap_managed_enable_put(struct dev_pagemap *pgmap) { - static_branch_dec(&devmap_managed_key); + if (pgmap->type == MEMORY_DEVICE_PRIVATE || + pgmap->type == MEMORY_DEVICE_FS_DAX) + static_branch_dec(&devmap_managed_key); } -static int devmap_managed_enable_get(struct dev_pagemap *pgmap) +static void devmap_managed_enable_get(struct dev_pagemap *pgmap) { - if (pgmap->type == MEMORY_DEVICE_PRIVATE && - (!pgmap->ops || !pgmap->ops->page_free)) { - WARN(1, "Missing page_free method\n"); - return -EINVAL; - } - - static_branch_inc(&devmap_managed_key); - return 0; + if (pgmap->type == MEMORY_DEVICE_PRIVATE || + pgmap->type == MEMORY_DEVICE_FS_DAX) + static_branch_inc(&devmap_managed_key); } #else -static int devmap_managed_enable_get(struct dev_pagemap *pgmap) +static void devmap_managed_enable_get(struct dev_pagemap *pgmap) { - return -EINVAL; } -static void devmap_managed_enable_put(void) +static void devmap_managed_enable_put(struct dev_pagemap *pgmap) { } #endif /* CONFIG_DEV_PAGEMAP_OPS */ @@ -169,7 +165,7 @@ void memunmap_pages(struct dev_pagemap *pgmap) pageunmap_range(pgmap, i); WARN_ONCE(pgmap->altmap.alloc, "failed to free all reserved pages\n"); - devmap_managed_enable_put(); + devmap_managed_enable_put(pgmap); } EXPORT_SYMBOL_GPL(memunmap_pages); @@ -307,7 +303,6 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid) .pgprot = PAGE_KERNEL, }; const int nr_range = pgmap->nr_range; - bool need_devmap_managed = true; int error, i; if (WARN_ONCE(!nr_range, "nr_range must be specified\n")) @@ -323,6 +318,10 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid) WARN(1, "Missing migrate_to_ram method\n"); return ERR_PTR(-EINVAL); } + if (!pgmap->ops->page_free) { + WARN(1, "Missing page_free method\n"); + return ERR_PTR(-EINVAL); + } if (!pgmap->owner) { WARN(1, "Missing owner\n"); return ERR_PTR(-EINVAL); @@ -336,11 +335,9 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid) } break; case MEMORY_DEVICE_GENERIC: - need_devmap_managed = false; break; case MEMORY_DEVICE_PCI_P2PDMA: params.pgprot = pgprot_noncached(params.pgprot); - need_devmap_managed = false; break; default: WARN(1, "Invalid pgmap type %d\n", pgmap->type); @@ -364,11 +361,7 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid) } } - if (need_devmap_managed) { - error = devmap_managed_enable_get(pgmap); - if (error) - return ERR_PTR(error); - } + devmap_managed_enable_get(pgmap); /* * Clear the pgmap nr_range as it will be incremented for each diff --git a/mm/truncate.c b/mm/truncate.c index 18cec39a9f53..960edf5803ca 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -528,7 +528,7 @@ void truncate_inode_pages_final(struct address_space *mapping) } EXPORT_SYMBOL(truncate_inode_pages_final); -unsigned long __invalidate_mapping_pages(struct address_space *mapping, +static unsigned long __invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end, unsigned long *nr_pagevec) { pgoff_t indices[PAGEVEC_SIZE]; diff --git a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c index d979ff14775a..8f82f99f7748 100644 --- a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c +++ b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c @@ -3282,4 +3282,99 @@ TEST(epoll60) close(ctx.epfd); } +struct epoll61_ctx { + int epfd; + int evfd; +}; + +static void *epoll61_write_eventfd(void *ctx_) +{ + struct epoll61_ctx *ctx = ctx_; + int64_t l = 1; + + usleep(10950); + write(ctx->evfd, &l, sizeof(l)); + return NULL; +} + +static void *epoll61_epoll_with_timeout(void *ctx_) +{ + struct epoll61_ctx *ctx = ctx_; + struct epoll_event events[1]; + int n; + + n = epoll_wait(ctx->epfd, events, 1, 11); + /* + * If epoll returned the eventfd, write on the eventfd to wake up the + * blocking poller. + */ + if (n == 1) { + int64_t l = 1; + + write(ctx->evfd, &l, sizeof(l)); + } + return NULL; +} + +static void *epoll61_blocking_epoll(void *ctx_) +{ + struct epoll61_ctx *ctx = ctx_; + struct epoll_event events[1]; + + epoll_wait(ctx->epfd, events, 1, -1); + return NULL; +} + +TEST(epoll61) +{ + struct epoll61_ctx ctx; + struct epoll_event ev; + int i, r; + + ctx.epfd = epoll_create1(0); + ASSERT_GE(ctx.epfd, 0); + ctx.evfd = eventfd(0, EFD_NONBLOCK); + ASSERT_GE(ctx.evfd, 0); + + ev.events = EPOLLIN | EPOLLET | EPOLLERR | EPOLLHUP; + ev.data.ptr = NULL; + r = epoll_ctl(ctx.epfd, EPOLL_CTL_ADD, ctx.evfd, &ev); + ASSERT_EQ(r, 0); + + /* + * We are testing a race. Repeat the test case 1000 times to make it + * more likely to fail in case of a bug. + */ + for (i = 0; i < 1000; i++) { + pthread_t threads[3]; + int n; + + /* + * Start 3 threads: + * Thread 1 sleeps for 10.9ms and writes to the evenfd. + * Thread 2 calls epoll with a timeout of 11ms. + * Thread 3 calls epoll with a timeout of -1. + * + * The eventfd write by Thread 1 should either wakeup Thread 2 + * or Thread 3. If it wakes up Thread 2, Thread 2 writes on the + * eventfd to wake up Thread 3. + * + * If no events are missed, all three threads should eventually + * be joinable. + */ + ASSERT_EQ(pthread_create(&threads[0], NULL, + epoll61_write_eventfd, &ctx), 0); + ASSERT_EQ(pthread_create(&threads[1], NULL, + epoll61_epoll_with_timeout, &ctx), 0); + ASSERT_EQ(pthread_create(&threads[2], NULL, + epoll61_blocking_epoll, &ctx), 0); + + for (n = 0; n < ARRAY_SIZE(threads); ++n) + ASSERT_EQ(pthread_join(threads[n], NULL), 0); + } + + close(ctx.epfd); + close(ctx.evfd); +} + TEST_HARNESS_MAIN |