aboutsummaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/compaction.c3
-rw-r--r--mm/filemap.c4
-rw-r--r--mm/highmem.c7
-rw-r--r--mm/huge_memory.c37
-rw-r--r--mm/hugetlb.c53
-rw-r--r--mm/kasan/hw_tags.c77
-rw-r--r--mm/kasan/init.c23
-rw-r--r--mm/kasan/kasan.h2
-rw-r--r--mm/memblock.c51
-rw-r--r--mm/memcontrol.c4
-rw-r--r--mm/memory-failure.c20
-rw-r--r--mm/migrate.c29
-rw-r--r--mm/page_alloc.c2
-rw-r--r--mm/slub.c11
14 files changed, 177 insertions, 146 deletions
diff --git a/mm/compaction.c b/mm/compaction.c
index e5acb9714436..190ccdaa6c19 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1342,7 +1342,7 @@ fast_isolate_freepages(struct compact_control *cc)
{
unsigned int limit = min(1U, freelist_scan_limit(cc) >> 1);
unsigned int nr_scanned = 0;
- unsigned long low_pfn, min_pfn, high_pfn = 0, highest = 0;
+ unsigned long low_pfn, min_pfn, highest = 0;
unsigned long nr_isolated = 0;
unsigned long distance;
struct page *page = NULL;
@@ -1387,6 +1387,7 @@ fast_isolate_freepages(struct compact_control *cc)
struct page *freepage;
unsigned long flags;
unsigned int order_scanned = 0;
+ unsigned long high_pfn = 0;
if (!area->nr_free)
continue;
diff --git a/mm/filemap.c b/mm/filemap.c
index 5c9d564317a5..aa0e0fb04670 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -835,6 +835,7 @@ noinline int __add_to_page_cache_locked(struct page *page,
XA_STATE(xas, &mapping->i_pages, offset);
int huge = PageHuge(page);
int error;
+ bool charged = false;
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(PageSwapBacked(page), page);
@@ -848,6 +849,7 @@ noinline int __add_to_page_cache_locked(struct page *page,
error = mem_cgroup_charge(page, current->mm, gfp);
if (error)
goto error;
+ charged = true;
}
gfp &= GFP_RECLAIM_MASK;
@@ -896,6 +898,8 @@ unlock:
if (xas_error(&xas)) {
error = xas_error(&xas);
+ if (charged)
+ mem_cgroup_uncharge(page);
goto error;
}
diff --git a/mm/highmem.c b/mm/highmem.c
index c3a9ea7875ef..874b732b120c 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -473,6 +473,11 @@ static inline void *arch_kmap_local_high_get(struct page *page)
}
#endif
+#ifndef arch_kmap_local_set_pte
+#define arch_kmap_local_set_pte(mm, vaddr, ptep, ptev) \
+ set_pte_at(mm, vaddr, ptep, ptev)
+#endif
+
/* Unmap a local mapping which was obtained by kmap_high_get() */
static inline bool kmap_high_unmap_local(unsigned long vaddr)
{
@@ -515,7 +520,7 @@ void *__kmap_local_pfn_prot(unsigned long pfn, pgprot_t prot)
vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
BUG_ON(!pte_none(*(kmap_pte - idx)));
pteval = pfn_pte(pfn, prot);
- set_pte_at(&init_mm, vaddr, kmap_pte - idx, pteval);
+ arch_kmap_local_set_pte(&init_mm, vaddr, kmap_pte - idx, pteval);
arch_kmap_local_post_map(vaddr, pteval);
current->kmap_ctrl.pteval[kmap_local_idx()] = pteval;
preempt_enable();
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 9237976abe72..91ca9b103ee5 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2202,7 +2202,7 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
{
spinlock_t *ptl;
struct mmu_notifier_range range;
- bool was_locked = false;
+ bool do_unlock_page = false;
pmd_t _pmd;
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
@@ -2218,7 +2218,6 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
VM_BUG_ON(freeze && !page);
if (page) {
VM_WARN_ON_ONCE(!PageLocked(page));
- was_locked = true;
if (page != pmd_page(*pmd))
goto out;
}
@@ -2227,19 +2226,29 @@ repeat:
if (pmd_trans_huge(*pmd)) {
if (!page) {
page = pmd_page(*pmd);
- if (unlikely(!trylock_page(page))) {
- get_page(page);
- _pmd = *pmd;
- spin_unlock(ptl);
- lock_page(page);
- spin_lock(ptl);
- if (unlikely(!pmd_same(*pmd, _pmd))) {
- unlock_page(page);
+ /*
+ * An anonymous page must be locked, to ensure that a
+ * concurrent reuse_swap_page() sees stable mapcount;
+ * but reuse_swap_page() is not used on shmem or file,
+ * and page lock must not be taken when zap_pmd_range()
+ * calls __split_huge_pmd() while i_mmap_lock is held.
+ */
+ if (PageAnon(page)) {
+ if (unlikely(!trylock_page(page))) {
+ get_page(page);
+ _pmd = *pmd;
+ spin_unlock(ptl);
+ lock_page(page);
+ spin_lock(ptl);
+ if (unlikely(!pmd_same(*pmd, _pmd))) {
+ unlock_page(page);
+ put_page(page);
+ page = NULL;
+ goto repeat;
+ }
put_page(page);
- page = NULL;
- goto repeat;
}
- put_page(page);
+ do_unlock_page = true;
}
}
if (PageMlocked(page))
@@ -2249,7 +2258,7 @@ repeat:
__split_huge_pmd_locked(vma, pmd, range.start, freeze);
out:
spin_unlock(ptl);
- if (!was_locked && page)
+ if (do_unlock_page)
unlock_page(page);
/*
* No need to double call mmu_notifier->invalidate_range() callback.
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 18f6ee317900..4bdb58ab14cb 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -79,6 +79,21 @@ DEFINE_SPINLOCK(hugetlb_lock);
static int num_fault_mutexes;
struct mutex *hugetlb_fault_mutex_table ____cacheline_aligned_in_smp;
+static inline bool PageHugeFreed(struct page *head)
+{
+ return page_private(head + 4) == -1UL;
+}
+
+static inline void SetPageHugeFreed(struct page *head)
+{
+ set_page_private(head + 4, -1UL);
+}
+
+static inline void ClearPageHugeFreed(struct page *head)
+{
+ set_page_private(head + 4, 0);
+}
+
/* Forward declaration */
static int hugetlb_acct_memory(struct hstate *h, long delta);
@@ -1028,6 +1043,7 @@ static void enqueue_huge_page(struct hstate *h, struct page *page)
list_move(&page->lru, &h->hugepage_freelists[nid]);
h->free_huge_pages++;
h->free_huge_pages_node[nid]++;
+ SetPageHugeFreed(page);
}
static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
@@ -1044,6 +1060,7 @@ static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
list_move(&page->lru, &h->hugepage_activelist);
set_page_refcounted(page);
+ ClearPageHugeFreed(page);
h->free_huge_pages--;
h->free_huge_pages_node[nid]--;
return page;
@@ -1344,12 +1361,11 @@ struct hstate *size_to_hstate(unsigned long size)
*/
bool page_huge_active(struct page *page)
{
- VM_BUG_ON_PAGE(!PageHuge(page), page);
- return PageHead(page) && PagePrivate(&page[1]);
+ return PageHeadHuge(page) && PagePrivate(&page[1]);
}
/* never called for tail page */
-static void set_page_huge_active(struct page *page)
+void set_page_huge_active(struct page *page)
{
VM_BUG_ON_PAGE(!PageHeadHuge(page), page);
SetPagePrivate(&page[1]);
@@ -1505,6 +1521,7 @@ static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
spin_lock(&hugetlb_lock);
h->nr_huge_pages++;
h->nr_huge_pages_node[nid]++;
+ ClearPageHugeFreed(page);
spin_unlock(&hugetlb_lock);
}
@@ -1755,6 +1772,7 @@ int dissolve_free_huge_page(struct page *page)
{
int rc = -EBUSY;
+retry:
/* Not to disrupt normal path by vainly holding hugetlb_lock */
if (!PageHuge(page))
return 0;
@@ -1771,6 +1789,26 @@ int dissolve_free_huge_page(struct page *page)
int nid = page_to_nid(head);
if (h->free_huge_pages - h->resv_huge_pages == 0)
goto out;
+
+ /*
+ * We should make sure that the page is already on the free list
+ * when it is dissolved.
+ */
+ if (unlikely(!PageHugeFreed(head))) {
+ spin_unlock(&hugetlb_lock);
+ cond_resched();
+
+ /*
+ * Theoretically, we should return -EBUSY when we
+ * encounter this race. In fact, we have a chance
+ * to successfully dissolve the page if we do a
+ * retry. Because the race window is quite small.
+ * If we seize this opportunity, it is an optimization
+ * for increasing the success rate of dissolving page.
+ */
+ goto retry;
+ }
+
/*
* Move PageHWPoison flag from head page to the raw error page,
* which makes any subpages rather than the error page reusable.
@@ -2009,13 +2047,16 @@ retry:
/* Free the needed pages to the hugetlb pool */
list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
+ int zeroed;
+
if ((--needed) < 0)
break;
/*
* This page is now managed by the hugetlb allocator and has
* no users -- drop the buddy allocator's reference.
*/
- VM_BUG_ON_PAGE(!put_page_testzero(page), page);
+ zeroed = put_page_testzero(page);
+ VM_BUG_ON_PAGE(!zeroed, page);
enqueue_huge_page(h, page);
}
free:
@@ -5555,9 +5596,9 @@ bool isolate_huge_page(struct page *page, struct list_head *list)
{
bool ret = true;
- VM_BUG_ON_PAGE(!PageHead(page), page);
spin_lock(&hugetlb_lock);
- if (!page_huge_active(page) || !get_page_unless_zero(page)) {
+ if (!PageHeadHuge(page) || !page_huge_active(page) ||
+ !get_page_unless_zero(page)) {
ret = false;
goto unlock;
}
diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c
index 55bd6f09c70f..e529428e7a11 100644
--- a/mm/kasan/hw_tags.c
+++ b/mm/kasan/hw_tags.c
@@ -19,11 +19,10 @@
#include "kasan.h"
-enum kasan_arg_mode {
- KASAN_ARG_MODE_DEFAULT,
- KASAN_ARG_MODE_OFF,
- KASAN_ARG_MODE_PROD,
- KASAN_ARG_MODE_FULL,
+enum kasan_arg {
+ KASAN_ARG_DEFAULT,
+ KASAN_ARG_OFF,
+ KASAN_ARG_ON,
};
enum kasan_arg_stacktrace {
@@ -38,7 +37,7 @@ enum kasan_arg_fault {
KASAN_ARG_FAULT_PANIC,
};
-static enum kasan_arg_mode kasan_arg_mode __ro_after_init;
+static enum kasan_arg kasan_arg __ro_after_init;
static enum kasan_arg_stacktrace kasan_arg_stacktrace __ro_after_init;
static enum kasan_arg_fault kasan_arg_fault __ro_after_init;
@@ -52,26 +51,24 @@ DEFINE_STATIC_KEY_FALSE(kasan_flag_stacktrace);
/* Whether panic or disable tag checking on fault. */
bool kasan_flag_panic __ro_after_init;
-/* kasan.mode=off/prod/full */
-static int __init early_kasan_mode(char *arg)
+/* kasan=off/on */
+static int __init early_kasan_flag(char *arg)
{
if (!arg)
return -EINVAL;
if (!strcmp(arg, "off"))
- kasan_arg_mode = KASAN_ARG_MODE_OFF;
- else if (!strcmp(arg, "prod"))
- kasan_arg_mode = KASAN_ARG_MODE_PROD;
- else if (!strcmp(arg, "full"))
- kasan_arg_mode = KASAN_ARG_MODE_FULL;
+ kasan_arg = KASAN_ARG_OFF;
+ else if (!strcmp(arg, "on"))
+ kasan_arg = KASAN_ARG_ON;
else
return -EINVAL;
return 0;
}
-early_param("kasan.mode", early_kasan_mode);
+early_param("kasan", early_kasan_flag);
-/* kasan.stack=off/on */
+/* kasan.stacktrace=off/on */
static int __init early_kasan_flag_stacktrace(char *arg)
{
if (!arg)
@@ -113,8 +110,8 @@ void kasan_init_hw_tags_cpu(void)
* as this function is only called for MTE-capable hardware.
*/
- /* If KASAN is disabled, do nothing. */
- if (kasan_arg_mode == KASAN_ARG_MODE_OFF)
+ /* If KASAN is disabled via command line, don't initialize it. */
+ if (kasan_arg == KASAN_ARG_OFF)
return;
hw_init_tags(KASAN_TAG_MAX);
@@ -124,43 +121,28 @@ void kasan_init_hw_tags_cpu(void)
/* kasan_init_hw_tags() is called once on boot CPU. */
void __init kasan_init_hw_tags(void)
{
- /* If hardware doesn't support MTE, do nothing. */
+ /* If hardware doesn't support MTE, don't initialize KASAN. */
if (!system_supports_mte())
return;
- /* Choose KASAN mode if kasan boot parameter is not provided. */
- if (kasan_arg_mode == KASAN_ARG_MODE_DEFAULT) {
- if (IS_ENABLED(CONFIG_DEBUG_KERNEL))
- kasan_arg_mode = KASAN_ARG_MODE_FULL;
- else
- kasan_arg_mode = KASAN_ARG_MODE_PROD;
- }
-
- /* Preset parameter values based on the mode. */
- switch (kasan_arg_mode) {
- case KASAN_ARG_MODE_DEFAULT:
- /* Shouldn't happen as per the check above. */
- WARN_ON(1);
- return;
- case KASAN_ARG_MODE_OFF:
- /* If KASAN is disabled, do nothing. */
+ /* If KASAN is disabled via command line, don't initialize it. */
+ if (kasan_arg == KASAN_ARG_OFF)
return;
- case KASAN_ARG_MODE_PROD:
- static_branch_enable(&kasan_flag_enabled);
- break;
- case KASAN_ARG_MODE_FULL:
- static_branch_enable(&kasan_flag_enabled);
- static_branch_enable(&kasan_flag_stacktrace);
- break;
- }
- /* Now, optionally override the presets. */
+ /* Enable KASAN. */
+ static_branch_enable(&kasan_flag_enabled);
switch (kasan_arg_stacktrace) {
case KASAN_ARG_STACKTRACE_DEFAULT:
+ /*
+ * Default to enabling stack trace collection for
+ * debug kernels.
+ */
+ if (IS_ENABLED(CONFIG_DEBUG_KERNEL))
+ static_branch_enable(&kasan_flag_stacktrace);
break;
case KASAN_ARG_STACKTRACE_OFF:
- static_branch_disable(&kasan_flag_stacktrace);
+ /* Do nothing, kasan_flag_stacktrace keeps its default value. */
break;
case KASAN_ARG_STACKTRACE_ON:
static_branch_enable(&kasan_flag_stacktrace);
@@ -169,11 +151,16 @@ void __init kasan_init_hw_tags(void)
switch (kasan_arg_fault) {
case KASAN_ARG_FAULT_DEFAULT:
+ /*
+ * Default to no panic on report.
+ * Do nothing, kasan_flag_panic keeps its default value.
+ */
break;
case KASAN_ARG_FAULT_REPORT:
- kasan_flag_panic = false;
+ /* Do nothing, kasan_flag_panic keeps its default value. */
break;
case KASAN_ARG_FAULT_PANIC:
+ /* Enable panic on report. */
kasan_flag_panic = true;
break;
}
diff --git a/mm/kasan/init.c b/mm/kasan/init.c
index 7ca0b92d5886..c4605ac9837b 100644
--- a/mm/kasan/init.c
+++ b/mm/kasan/init.c
@@ -373,9 +373,10 @@ static void kasan_remove_pmd_table(pmd_t *pmd, unsigned long addr,
if (kasan_pte_table(*pmd)) {
if (IS_ALIGNED(addr, PMD_SIZE) &&
- IS_ALIGNED(next, PMD_SIZE))
+ IS_ALIGNED(next, PMD_SIZE)) {
pmd_clear(pmd);
- continue;
+ continue;
+ }
}
pte = pte_offset_kernel(pmd, addr);
kasan_remove_pte_table(pte, addr, next);
@@ -398,9 +399,10 @@ static void kasan_remove_pud_table(pud_t *pud, unsigned long addr,
if (kasan_pmd_table(*pud)) {
if (IS_ALIGNED(addr, PUD_SIZE) &&
- IS_ALIGNED(next, PUD_SIZE))
+ IS_ALIGNED(next, PUD_SIZE)) {
pud_clear(pud);
- continue;
+ continue;
+ }
}
pmd = pmd_offset(pud, addr);
pmd_base = pmd_offset(pud, 0);
@@ -424,9 +426,10 @@ static void kasan_remove_p4d_table(p4d_t *p4d, unsigned long addr,
if (kasan_pud_table(*p4d)) {
if (IS_ALIGNED(addr, P4D_SIZE) &&
- IS_ALIGNED(next, P4D_SIZE))
+ IS_ALIGNED(next, P4D_SIZE)) {
p4d_clear(p4d);
- continue;
+ continue;
+ }
}
pud = pud_offset(p4d, addr);
kasan_remove_pud_table(pud, addr, next);
@@ -457,9 +460,10 @@ void kasan_remove_zero_shadow(void *start, unsigned long size)
if (kasan_p4d_table(*pgd)) {
if (IS_ALIGNED(addr, PGDIR_SIZE) &&
- IS_ALIGNED(next, PGDIR_SIZE))
+ IS_ALIGNED(next, PGDIR_SIZE)) {
pgd_clear(pgd);
- continue;
+ continue;
+ }
}
p4d = p4d_offset(pgd, addr);
@@ -482,7 +486,6 @@ int kasan_add_zero_shadow(void *start, unsigned long size)
ret = kasan_populate_early_shadow(shadow_start, shadow_end);
if (ret)
- kasan_remove_zero_shadow(shadow_start,
- size >> KASAN_SHADOW_SCALE_SHIFT);
+ kasan_remove_zero_shadow(start, size);
return ret;
}
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index cc4d9e1d49b1..8c706e7652f2 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -209,7 +209,7 @@ bool check_memory_region(unsigned long addr, size_t size, bool write,
static inline bool addr_has_metadata(const void *addr)
{
- return true;
+ return (is_vmalloc_addr(addr) || virt_addr_valid(addr));
}
#endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
diff --git a/mm/memblock.c b/mm/memblock.c
index d24bcfa88d2f..8d9b5f1e7040 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -275,14 +275,6 @@ __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end,
*
* Find @size free area aligned to @align in the specified range and node.
*
- * When allocation direction is bottom-up, the @start should be greater
- * than the end of the kernel image. Otherwise, it will be trimmed. The
- * reason is that we want the bottom-up allocation just near the kernel
- * image so it is highly likely that the allocated memory and the kernel
- * will reside in the same node.
- *
- * If bottom-up allocation failed, will try to allocate memory top-down.
- *
* Return:
* Found address on success, 0 on failure.
*/
@@ -291,8 +283,6 @@ static phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size,
phys_addr_t end, int nid,
enum memblock_flags flags)
{
- phys_addr_t kernel_end, ret;
-
/* pump up @end */
if (end == MEMBLOCK_ALLOC_ACCESSIBLE ||
end == MEMBLOCK_ALLOC_KASAN)
@@ -301,40 +291,13 @@ static phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size,
/* avoid allocating the first page */
start = max_t(phys_addr_t, start, PAGE_SIZE);
end = max(start, end);
- kernel_end = __pa_symbol(_end);
-
- /*
- * try bottom-up allocation only when bottom-up mode
- * is set and @end is above the kernel image.
- */
- if (memblock_bottom_up() && end > kernel_end) {
- phys_addr_t bottom_up_start;
-
- /* make sure we will allocate above the kernel */
- bottom_up_start = max(start, kernel_end);
- /* ok, try bottom-up allocation first */
- ret = __memblock_find_range_bottom_up(bottom_up_start, end,
- size, align, nid, flags);
- if (ret)
- return ret;
-
- /*
- * we always limit bottom-up allocation above the kernel,
- * but top-down allocation doesn't have the limit, so
- * retrying top-down allocation may succeed when bottom-up
- * allocation failed.
- *
- * bottom-up allocation is expected to be fail very rarely,
- * so we use WARN_ONCE() here to see the stack trace if
- * fail happens.
- */
- WARN_ONCE(IS_ENABLED(CONFIG_MEMORY_HOTREMOVE),
- "memblock: bottom-up allocation failed, memory hotremove may be affected\n");
- }
-
- return __memblock_find_range_top_down(start, end, size, align, nid,
- flags);
+ if (memblock_bottom_up())
+ return __memblock_find_range_bottom_up(start, end, size, align,
+ nid, flags);
+ else
+ return __memblock_find_range_top_down(start, end, size, align,
+ nid, flags);
}
/**
@@ -1427,7 +1390,7 @@ phys_addr_t __init memblock_phys_alloc_range(phys_addr_t size,
}
/**
- * memblock_phys_alloc_try_nid - allocate a memory block from specified MUMA node
+ * memblock_phys_alloc_try_nid - allocate a memory block from specified NUMA node
* @size: size of memory block to be allocated in bytes
* @align: alignment of the region and block's size
* @nid: nid of the free area to find, %NUMA_NO_NODE for any node
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 605f671203ef..e2de77b5bcc2 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3115,9 +3115,7 @@ void __memcg_kmem_uncharge(struct mem_cgroup *memcg, unsigned int nr_pages)
if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
page_counter_uncharge(&memcg->kmem, nr_pages);
- page_counter_uncharge(&memcg->memory, nr_pages);
- if (do_memsw_account())
- page_counter_uncharge(&memcg->memsw, nr_pages);
+ refill_stock(memcg, nr_pages);
}
/**
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 04d9f154a130..e9481632fcd1 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1885,6 +1885,12 @@ static int soft_offline_free_page(struct page *page)
return rc;
}
+static void put_ref_page(struct page *page)
+{
+ if (page)
+ put_page(page);
+}
+
/**
* soft_offline_page - Soft offline a page.
* @pfn: pfn to soft-offline
@@ -1910,20 +1916,26 @@ static int soft_offline_free_page(struct page *page)
int soft_offline_page(unsigned long pfn, int flags)
{
int ret;
- struct page *page;
bool try_again = true;
+ struct page *page, *ref_page = NULL;
+
+ WARN_ON_ONCE(!pfn_valid(pfn) && (flags & MF_COUNT_INCREASED));
if (!pfn_valid(pfn))
return -ENXIO;
+ if (flags & MF_COUNT_INCREASED)
+ ref_page = pfn_to_page(pfn);
+
/* Only online pages can be soft-offlined (esp., not ZONE_DEVICE). */
page = pfn_to_online_page(pfn);
- if (!page)
+ if (!page) {
+ put_ref_page(ref_page);
return -EIO;
+ }
if (PageHWPoison(page)) {
pr_info("%s: %#lx page already poisoned\n", __func__, pfn);
- if (flags & MF_COUNT_INCREASED)
- put_page(page);
+ put_ref_page(ref_page);
return 0;
}
diff --git a/mm/migrate.c b/mm/migrate.c
index ee5e612b4cd8..20ca887ea769 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -402,6 +402,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
struct zone *oldzone, *newzone;
int dirty;
int expected_count = expected_page_refs(mapping, page) + extra_count;
+ int nr = thp_nr_pages(page);
if (!mapping) {
/* Anonymous page without mapping */
@@ -437,7 +438,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
*/
newpage->index = page->index;
newpage->mapping = page->mapping;
- page_ref_add(newpage, thp_nr_pages(page)); /* add cache reference */
+ page_ref_add(newpage, nr); /* add cache reference */
if (PageSwapBacked(page)) {
__SetPageSwapBacked(newpage);
if (PageSwapCache(page)) {
@@ -459,7 +460,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
if (PageTransHuge(page)) {
int i;
- for (i = 1; i < HPAGE_PMD_NR; i++) {
+ for (i = 1; i < nr; i++) {
xas_next(&xas);
xas_store(&xas, newpage);
}
@@ -470,7 +471,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
* to one less reference.
* We know this isn't the last reference.
*/
- page_ref_unfreeze(page, expected_count - thp_nr_pages(page));
+ page_ref_unfreeze(page, expected_count - nr);
xas_unlock(&xas);
/* Leave irq disabled to prevent preemption while updating stats */
@@ -493,17 +494,17 @@ int migrate_page_move_mapping(struct address_space *mapping,
old_lruvec = mem_cgroup_lruvec(memcg, oldzone->zone_pgdat);
new_lruvec = mem_cgroup_lruvec(memcg, newzone->zone_pgdat);
- __dec_lruvec_state(old_lruvec, NR_FILE_PAGES);
- __inc_lruvec_state(new_lruvec, NR_FILE_PAGES);
+ __mod_lruvec_state(old_lruvec, NR_FILE_PAGES, -nr);
+ __mod_lruvec_state(new_lruvec, NR_FILE_PAGES, nr);
if (PageSwapBacked(page) && !PageSwapCache(page)) {
- __dec_lruvec_state(old_lruvec, NR_SHMEM);
- __inc_lruvec_state(new_lruvec, NR_SHMEM);
+ __mod_lruvec_state(old_lruvec, NR_SHMEM, -nr);
+ __mod_lruvec_state(new_lruvec, NR_SHMEM, nr);
}
if (dirty && mapping_can_writeback(mapping)) {
- __dec_node_state(oldzone->zone_pgdat, NR_FILE_DIRTY);
- __dec_zone_state(oldzone, NR_ZONE_WRITE_PENDING);
- __inc_node_state(newzone->zone_pgdat, NR_FILE_DIRTY);
- __inc_zone_state(newzone, NR_ZONE_WRITE_PENDING);
+ __mod_lruvec_state(old_lruvec, NR_FILE_DIRTY, -nr);
+ __mod_zone_page_state(oldzone, NR_ZONE_WRITE_PENDING, -nr);
+ __mod_lruvec_state(new_lruvec, NR_FILE_DIRTY, nr);
+ __mod_zone_page_state(newzone, NR_ZONE_WRITE_PENDING, nr);
}
}
local_irq_enable();
@@ -1279,6 +1280,12 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
return -ENOSYS;
}
+ if (page_count(hpage) == 1) {
+ /* page was freed from under us. So we are done. */
+ putback_active_hugepage(hpage);
+ return MIGRATEPAGE_SUCCESS;
+ }
+
new_hpage = get_new_page(hpage, private);
if (!new_hpage)
return -ENOMEM;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 027f6481ba59..519a60d5b6f7 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1207,8 +1207,10 @@ static void kernel_init_free_pages(struct page *page, int numpages)
/* s390's use of memset() could override KASAN redzones. */
kasan_disable_current();
for (i = 0; i < numpages; i++) {
+ u8 tag = page_kasan_tag(page + i);
page_kasan_tag_reset(page + i);
clear_highpage(page + i);
+ page_kasan_tag_set(page + i, tag);
}
kasan_enable_current();
}
diff --git a/mm/slub.c b/mm/slub.c
index d9e4e10683cc..7ecbbbe5bc0c 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2791,7 +2791,8 @@ static __always_inline void maybe_wipe_obj_freeptr(struct kmem_cache *s,
void *obj)
{
if (unlikely(slab_want_init_on_free(s)) && obj)
- memset((void *)((char *)obj + s->offset), 0, sizeof(void *));
+ memset((void *)((char *)kasan_reset_tag(obj) + s->offset),
+ 0, sizeof(void *));
}
/*
@@ -2883,7 +2884,7 @@ redo:
stat(s, ALLOC_FASTPATH);
}
- maybe_wipe_obj_freeptr(s, kasan_reset_tag(object));
+ maybe_wipe_obj_freeptr(s, object);
if (unlikely(slab_want_init_on_alloc(gfpflags, s)) && object)
memset(kasan_reset_tag(object), 0, s->object_size);
@@ -3329,7 +3330,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
int j;
for (j = 0; j < i; j++)
- memset(p[j], 0, s->object_size);
+ memset(kasan_reset_tag(p[j]), 0, s->object_size);
}
/* memcg and kmem_cache debug support */
@@ -5624,10 +5625,8 @@ static int sysfs_slab_add(struct kmem_cache *s)
s->kobj.kset = kset;
err = kobject_init_and_add(&s->kobj, &slab_ktype, NULL, "%s", name);
- if (err) {
- kobject_put(&s->kobj);
+ if (err)
goto out;
- }
err = sysfs_create_group(&s->kobj, &slab_attr_group);
if (err)
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-27 21:48:56 +0000