summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/compaction.c29
-rw-r--r--mm/gup.c48
-rw-r--r--mm/huge_memory.c40
-rw-r--r--mm/hugetlb.c15
-rw-r--r--mm/kasan/Makefile3
-rw-r--r--mm/kasan/common.c43
-rw-r--r--mm/kasan/report.c10
-rw-r--r--mm/kmemleak.c42
-rw-r--r--mm/madvise.c2
-rw-r--r--mm/memcontrol.c20
-rw-r--r--mm/memory.c6
-rw-r--r--mm/memory_hotplug.c1
-rw-r--r--mm/mmap.c7
-rw-r--r--mm/mmu_gather.c129
-rw-r--r--mm/page_alloc.c64
-rw-r--r--mm/page_owner.c82
-rw-r--r--mm/percpu.c8
-rw-r--r--mm/shmem.c58
-rw-r--r--mm/slab.c52
-rw-r--r--mm/slub.c21
-rw-r--r--mm/swapfile.c32
-rw-r--r--mm/util.c2
-rw-r--r--mm/vmalloc.c113
-rw-r--r--mm/vmscan.c29
-rw-r--r--mm/vmstat.c5
25 files changed, 484 insertions, 377 deletions
diff --git a/mm/compaction.c b/mm/compaction.c
index f171a83707ce..3319e0872d01 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -242,6 +242,7 @@ __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source,
bool check_target)
{
struct page *page = pfn_to_online_page(pfn);
+ struct page *block_page;
struct page *end_page;
unsigned long block_pfn;
@@ -267,20 +268,26 @@ __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source,
get_pageblock_migratetype(page) != MIGRATE_MOVABLE)
return false;
+ /* Ensure the start of the pageblock or zone is online and valid */
+ block_pfn = pageblock_start_pfn(pfn);
+ block_page = pfn_to_online_page(max(block_pfn, zone->zone_start_pfn));
+ if (block_page) {
+ page = block_page;
+ pfn = block_pfn;
+ }
+
+ /* Ensure the end of the pageblock or zone is online and valid */
+ block_pfn += pageblock_nr_pages;
+ block_pfn = min(block_pfn, zone_end_pfn(zone) - 1);
+ end_page = pfn_to_online_page(block_pfn);
+ if (!end_page)
+ return false;
+
/*
* Only clear the hint if a sample indicates there is either a
* free page or an LRU page in the block. One or other condition
* is necessary for the block to be a migration source/target.
*/
- block_pfn = pageblock_start_pfn(pfn);
- pfn = max(block_pfn, zone->zone_start_pfn);
- page = pfn_to_page(pfn);
- if (zone != page_zone(page))
- return false;
- pfn = block_pfn + pageblock_nr_pages;
- pfn = min(pfn, zone_end_pfn(zone));
- end_page = pfn_to_page(pfn);
-
do {
if (pfn_valid_within(pfn)) {
if (check_source && PageLRU(page)) {
@@ -309,7 +316,7 @@ __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source,
static void __reset_isolation_suitable(struct zone *zone)
{
unsigned long migrate_pfn = zone->zone_start_pfn;
- unsigned long free_pfn = zone_end_pfn(zone);
+ unsigned long free_pfn = zone_end_pfn(zone) - 1;
unsigned long reset_migrate = free_pfn;
unsigned long reset_free = migrate_pfn;
bool source_set = false;
@@ -1363,7 +1370,7 @@ fast_isolate_freepages(struct compact_control *cc)
count_compact_events(COMPACTISOLATED, nr_isolated);
} else {
/* If isolation fails, abort the search */
- order = -1;
+ order = cc->search_order + 1;
page = NULL;
}
}
diff --git a/mm/gup.c b/mm/gup.c
index f84e22685aaa..91819b8ad9cc 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -160,8 +160,12 @@ retry:
goto retry;
}
- if (flags & FOLL_GET)
- get_page(page);
+ if (flags & FOLL_GET) {
+ if (unlikely(!try_get_page(page))) {
+ page = ERR_PTR(-ENOMEM);
+ goto out;
+ }
+ }
if (flags & FOLL_TOUCH) {
if ((flags & FOLL_WRITE) &&
!pte_dirty(pte) && !PageDirty(page))
@@ -298,7 +302,10 @@ retry_locked:
if (pmd_trans_unstable(pmd))
ret = -EBUSY;
} else {
- get_page(page);
+ if (unlikely(!try_get_page(page))) {
+ spin_unlock(ptl);
+ return ERR_PTR(-ENOMEM);
+ }
spin_unlock(ptl);
lock_page(page);
ret = split_huge_page(page);
@@ -500,7 +507,10 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address,
if (is_device_public_page(*page))
goto unmap;
}
- get_page(*page);
+ if (unlikely(!try_get_page(*page))) {
+ ret = -ENOMEM;
+ goto unmap;
+ }
out:
ret = 0;
unmap:
@@ -1545,6 +1555,20 @@ static void undo_dev_pagemap(int *nr, int nr_start, struct page **pages)
}
}
+/*
+ * Return the compund head page with ref appropriately incremented,
+ * or NULL if that failed.
+ */
+static inline struct page *try_get_compound_head(struct page *page, int refs)
+{
+ struct page *head = compound_head(page);
+ if (WARN_ON_ONCE(page_ref_count(head) < 0))
+ return NULL;
+ if (unlikely(!page_cache_add_speculative(head, refs)))
+ return NULL;
+ return head;
+}
+
#ifdef CONFIG_ARCH_HAS_PTE_SPECIAL
static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
int write, struct page **pages, int *nr)
@@ -1579,9 +1603,9 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
page = pte_page(pte);
- head = compound_head(page);
- if (!page_cache_get_speculative(head))
+ head = try_get_compound_head(page, 1);
+ if (!head)
goto pte_unmap;
if (unlikely(pte_val(pte) != pte_val(*ptep))) {
@@ -1720,8 +1744,8 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
refs++;
} while (addr += PAGE_SIZE, addr != end);
- head = compound_head(pmd_page(orig));
- if (!page_cache_add_speculative(head, refs)) {
+ head = try_get_compound_head(pmd_page(orig), refs);
+ if (!head) {
*nr -= refs;
return 0;
}
@@ -1758,8 +1782,8 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
refs++;
} while (addr += PAGE_SIZE, addr != end);
- head = compound_head(pud_page(orig));
- if (!page_cache_add_speculative(head, refs)) {
+ head = try_get_compound_head(pud_page(orig), refs);
+ if (!head) {
*nr -= refs;
return 0;
}
@@ -1795,8 +1819,8 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
refs++;
} while (addr += PAGE_SIZE, addr != end);
- head = compound_head(pgd_page(orig));
- if (!page_cache_add_speculative(head, refs)) {
+ head = try_get_compound_head(pgd_page(orig), refs);
+ if (!head) {
*nr -= refs;
return 0;
}
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 404acdcd0455..b6a34b32d8ac 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -755,6 +755,21 @@ static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
spinlock_t *ptl;
ptl = pmd_lock(mm, pmd);
+ if (!pmd_none(*pmd)) {
+ if (write) {
+ if (pmd_pfn(*pmd) != pfn_t_to_pfn(pfn)) {
+ WARN_ON_ONCE(!is_huge_zero_pmd(*pmd));
+ goto out_unlock;
+ }
+ entry = pmd_mkyoung(*pmd);
+ entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
+ if (pmdp_set_access_flags(vma, addr, pmd, entry, 1))
+ update_mmu_cache_pmd(vma, addr, pmd);
+ }
+
+ goto out_unlock;
+ }
+
entry = pmd_mkhuge(pfn_t_pmd(pfn, prot));
if (pfn_t_devmap(pfn))
entry = pmd_mkdevmap(entry);
@@ -766,11 +781,16 @@ static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
if (pgtable) {
pgtable_trans_huge_deposit(mm, pmd, pgtable);
mm_inc_nr_ptes(mm);
+ pgtable = NULL;
}
set_pmd_at(mm, addr, pmd, entry);
update_mmu_cache_pmd(vma, addr, pmd);
+
+out_unlock:
spin_unlock(ptl);
+ if (pgtable)
+ pte_free(mm, pgtable);
}
vm_fault_t vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
@@ -821,6 +841,20 @@ static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
spinlock_t *ptl;
ptl = pud_lock(mm, pud);
+ if (!pud_none(*pud)) {
+ if (write) {
+ if (pud_pfn(*pud) != pfn_t_to_pfn(pfn)) {
+ WARN_ON_ONCE(!is_huge_zero_pud(*pud));
+ goto out_unlock;
+ }
+ entry = pud_mkyoung(*pud);
+ entry = maybe_pud_mkwrite(pud_mkdirty(entry), vma);
+ if (pudp_set_access_flags(vma, addr, pud, entry, 1))
+ update_mmu_cache_pud(vma, addr, pud);
+ }
+ goto out_unlock;
+ }
+
entry = pud_mkhuge(pfn_t_pud(pfn, prot));
if (pfn_t_devmap(pfn))
entry = pud_mkdevmap(entry);
@@ -830,6 +864,8 @@ static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
}
set_pud_at(mm, addr, pud, entry);
update_mmu_cache_pud(vma, addr, pud);
+
+out_unlock:
spin_unlock(ptl);
}
@@ -1641,7 +1677,7 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
struct mm_struct *mm = tlb->mm;
bool ret = false;
- tlb_remove_check_page_size_change(tlb, HPAGE_PMD_SIZE);
+ tlb_change_page_size(tlb, HPAGE_PMD_SIZE);
ptl = pmd_trans_huge_lock(pmd, vma);
if (!ptl)
@@ -1717,7 +1753,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
pmd_t orig_pmd;
spinlock_t *ptl;
- tlb_remove_check_page_size_change(tlb, HPAGE_PMD_SIZE);
+ tlb_change_page_size(tlb, HPAGE_PMD_SIZE);
ptl = __pmd_trans_huge_lock(pmd, vma);
if (!ptl)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 97b1e0290c66..641cedfc8c0f 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3353,7 +3353,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
* This is a hugetlb vma, all the pte entries should point
* to huge page.
*/
- tlb_remove_check_page_size_change(tlb, sz);
+ tlb_change_page_size(tlb, sz);
tlb_start_vma(tlb, vma);
/*
@@ -4299,6 +4299,19 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
pfn_offset = (vaddr & ~huge_page_mask(h)) >> PAGE_SHIFT;
page = pte_page(huge_ptep_get(pte));
+
+ /*
+ * Instead of doing 'try_get_page()' below in the same_page
+ * loop, just check the count once here.
+ */
+ if (unlikely(page_count(page) <= 0)) {
+ if (pages) {
+ spin_unlock(ptl);
+ remainder = 0;
+ err = -ENOMEM;
+ break;
+ }
+ }
same_page:
if (pages) {
pages[i] = mem_map_offset(page, pfn_offset);
diff --git a/mm/kasan/Makefile b/mm/kasan/Makefile
index f06ee820d356..08b43de2383b 100644
--- a/mm/kasan/Makefile
+++ b/mm/kasan/Makefile
@@ -2,11 +2,13 @@
KASAN_SANITIZE := n
UBSAN_SANITIZE_common.o := n
UBSAN_SANITIZE_generic.o := n
+UBSAN_SANITIZE_generic_report.o := n
UBSAN_SANITIZE_tags.o := n
KCOV_INSTRUMENT := n
CFLAGS_REMOVE_common.o = $(CC_FLAGS_FTRACE)
CFLAGS_REMOVE_generic.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_generic_report.o = $(CC_FLAGS_FTRACE)
CFLAGS_REMOVE_tags.o = $(CC_FLAGS_FTRACE)
# Function splitter causes unnecessary splits in __asan_load1/__asan_store1
@@ -14,6 +16,7 @@ CFLAGS_REMOVE_tags.o = $(CC_FLAGS_FTRACE)
CFLAGS_common.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
CFLAGS_generic.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
+CFLAGS_generic_report.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
CFLAGS_tags.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
obj-$(CONFIG_KASAN) := common.o init.o report.o
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index 80bbe62b16cd..36afcf64e016 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -36,6 +36,7 @@
#include <linux/types.h>
#include <linux/vmalloc.h>
#include <linux/bug.h>
+#include <linux/uaccess.h>
#include "kasan.h"
#include "../slab.h"
@@ -48,37 +49,28 @@ static inline int in_irqentry_text(unsigned long ptr)
ptr < (unsigned long)&__softirqentry_text_end);
}
-static inline void filter_irq_stacks(struct stack_trace *trace)
+static inline unsigned int filter_irq_stacks(unsigned long *entries,
+ unsigned int nr_entries)
{
- int i;
+ unsigned int i;
- if (!trace->nr_entries)
- return;
- for (i = 0; i < trace->nr_entries; i++)
- if (in_irqentry_text(trace->entries[i])) {
+ for (i = 0; i < nr_entries; i++) {
+ if (in_irqentry_text(entries[i])) {
/* Include the irqentry function into the stack. */
- trace->nr_entries = i + 1;
- break;
+ return i + 1;
}
+ }
+ return nr_entries;
}
static inline depot_stack_handle_t save_stack(gfp_t flags)
{
unsigned long entries[KASAN_STACK_DEPTH];
- struct stack_trace trace = {
- .nr_entries = 0,
- .entries = entries,
- .max_entries = KASAN_STACK_DEPTH,
- .skip = 0
- };
+ unsigned int nr_entries;
- save_stack_trace(&trace);
- filter_irq_stacks(&trace);
- if (trace.nr_entries != 0 &&
- trace.entries[trace.nr_entries-1] == ULONG_MAX)
- trace.nr_entries--;
-
- return depot_save_stack(&trace, flags);
+ nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 0);
+ nr_entries = filter_irq_stacks(entries, nr_entries);
+ return stack_depot_save(entries, nr_entries, flags);
}
static inline void set_track(struct kasan_track *track, gfp_t flags)
@@ -614,6 +606,15 @@ void kasan_free_shadow(const struct vm_struct *vm)
vfree(kasan_mem_to_shadow(vm->addr));
}
+extern void __kasan_report(unsigned long addr, size_t size, bool is_write, unsigned long ip);
+
+void kasan_report(unsigned long addr, size_t size, bool is_write, unsigned long ip)
+{
+ unsigned long flags = user_access_save();
+ __kasan_report(addr, size, is_write, ip);
+ user_access_restore(flags);
+}
+
#ifdef CONFIG_MEMORY_HOTPLUG
static bool shadow_mapped(unsigned long addr)
{
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index ca9418fe9232..03a443579386 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -100,10 +100,11 @@ static void print_track(struct kasan_track *track, const char *prefix)
{
pr_err("%s by task %u:\n", prefix, track->pid);
if (track->stack) {
- struct stack_trace trace;
+ unsigned long *entries;
+ unsigned int nr_entries;
- depot_fetch_stack(track->stack, &trace);
- print_stack_trace(&trace, 0);
+ nr_entries = stack_depot_fetch(track->stack, &entries);
+ stack_trace_print(entries, nr_entries, 0);
} else {
pr_err("(stack is not available)\n");
}
@@ -281,8 +282,7 @@ void kasan_report_invalid_free(void *object, unsigned long ip)
end_report(&flags);
}
-void kasan_report(unsigned long addr, size_t size,
- bool is_write, unsigned long ip)
+void __kasan_report(unsigned long addr, size_t size, bool is_write, unsigned long ip)
{
struct kasan_access_info info;
void *tagged_addr;
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 707fa5579f66..e57bf810f798 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -410,11 +410,6 @@ static void print_unreferenced(struct seq_file *seq,
*/
static void dump_object_info(struct kmemleak_object *object)
{
- struct stack_trace trace;
-
- trace.nr_entries = object->trace_len;
- trace.entries = object->trace;
-
pr_notice("Object 0x%08lx (size %zu):\n",
object->pointer, object->size);
pr_notice(" comm \"%s\", pid %d, jiffies %lu\n",
@@ -424,7 +419,7 @@ static void dump_object_info(struct kmemleak_object *object)
pr_notice(" flags = 0x%x\n", object->flags);
pr_notice(" checksum = %u\n", object->checksum);
pr_notice(" backtrace:\n");
- print_stack_trace(&trace, 4);
+ stack_trace_print(object->trace, object->trace_len, 4);
}
/*
@@ -553,15 +548,7 @@ static struct kmemleak_object *find_and_remove_object(unsigned long ptr, int ali
*/
static int __save_stack_trace(unsigned long *trace)
{
- struct stack_trace stack_trace;
-
- stack_trace.max_entries = MAX_TRACE;
- stack_trace.nr_entries = 0;
- stack_trace.entries = trace;
- stack_trace.skip = 2;
- save_stack_trace(&stack_trace);
-
- return stack_trace.nr_entries;
+ return stack_trace_save(trace, MAX_TRACE, 2);
}
/*
@@ -1401,6 +1388,7 @@ static void scan_block(void *_start, void *_end,
/*
* Scan a large memory block in MAX_SCAN_SIZE chunks to reduce the latency.
*/
+#ifdef CONFIG_SMP
static void scan_large_block(void *start, void *end)
{
void *next;
@@ -1412,6 +1400,7 @@ static void scan_large_block(void *start, void *end)
cond_resched();
}
}
+#endif
/*
* Scan a memory block corresponding to a kmemleak_object. A condition is
@@ -1529,11 +1518,6 @@ static void kmemleak_scan(void)
}
rcu_read_unlock();
- /* data/bss scanning */
- scan_large_block(_sdata, _edata);
- scan_large_block(__bss_start, __bss_stop);
- scan_large_block(__start_ro_after_init, __end_ro_after_init);
-
#ifdef CONFIG_SMP
/* per-cpu sections scanning */
for_each_possible_cpu(i)
@@ -2024,13 +2008,8 @@ early_param("kmemleak", kmemleak_boot_config);
static void __init print_log_trace(struct early_log *log)
{
- struct stack_trace trace;
-
- trace.nr_entries = log->trace_len;
- trace.entries = log->trace;
-
pr_notice("Early log backtrace:\n");
- print_stack_trace(&trace, 2);
+ stack_trace_print(log->trace, log->trace_len, 2);
}
/*
@@ -2071,6 +2050,17 @@ void __init kmemleak_init(void)
}
local_irq_restore(flags);
+ /* register the data/bss sections */
+ create_object((unsigned long)_sdata, _edata - _sdata,
+ KMEMLEAK_GREY, GFP_ATOMIC);
+ create_object((unsigned long)__bss_start, __bss_stop - __bss_start,
+ KMEMLEAK_GREY, GFP_ATOMIC);
+ /* only register .data..ro_after_init if not within .data */
+ if (__start_ro_after_init < _sdata || __end_ro_after_init > _edata)
+ create_object((unsigned long)__start_ro_after_init,
+ __end_ro_after_init - __start_ro_after_init,
+ KMEMLEAK_GREY, GFP_ATOMIC);
+
/*
* This is the point where tracking allocations is safe. Automatic
* scanning is started during the late initcall. Add the early logged
diff --git a/mm/madvise.c b/mm/madvise.c
index 21a7881a2db4..bb3a4554d5d5 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -328,7 +328,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
if (pmd_trans_unstable(pmd))
return 0;
- tlb_remove_check_page_size_change(tlb, PAGE_SIZE);
+ tlb_change_page_size(tlb, PAGE_SIZE);
orig_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
flush_tlb_batched_pending(mm);
arch_enter_lazy_mmu_mode();
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 532e0e2a4817..81a0d3914ec9 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3882,6 +3882,22 @@ struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb)
return &memcg->cgwb_domain;
}
+/*
+ * idx can be of type enum memcg_stat_item or node_stat_item.
+ * Keep in sync with memcg_exact_page().
+ */
+static unsigned long memcg_exact_page_state(struct mem_cgroup *memcg, int idx)
+{
+ long x = atomic_long_read(&memcg->stat[idx]);
+ int cpu;
+
+ for_each_online_cpu(cpu)
+ x += per_cpu_ptr(memcg->stat_cpu, cpu)->count[idx];
+ if (x < 0)
+ x = 0;
+ return x;
+}
+
/**
* mem_cgroup_wb_stats - retrieve writeback related stats from its memcg
* @wb: bdi_writeback in question
@@ -3907,10 +3923,10 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css);
struct mem_cgroup *parent;
- *pdirty = memcg_page_state(memcg, NR_FILE_DIRTY);
+ *pdirty = memcg_exact_page_state(memcg, NR_FILE_DIRTY);
/* this should eventually include NR_UNSTABLE_NFS */
- *pwriteback = memcg_page_state(memcg, NR_WRITEBACK);
+ *pwriteback = memcg_exact_page_state(memcg, NR_WRITEBACK);
*pfilepages = mem_cgroup_nr_lru_pages(memcg, (1 << LRU_INACTIVE_FILE) |
(1 << LRU_ACTIVE_FILE));
*pheadroom = PAGE_COUNTER_MAX;
diff --git a/mm/memory.c b/mm/memory.c
index ab650c21bccd..36aac6844662 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -356,7 +356,7 @@ void free_pgd_range(struct mmu_gather *tlb,
* We add page table cache pages with PAGE_SIZE,
* (see pte_free_tlb()), flush the tlb if we need
*/
- tlb_remove_check_page_size_change(tlb, PAGE_SIZE);
+ tlb_change_page_size(tlb, PAGE_SIZE);
pgd = pgd_offset(tlb->mm, addr);
do {
next = pgd_addr_end(addr, end);
@@ -1046,7 +1046,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
pte_t *pte;
swp_entry_t entry;
- tlb_remove_check_page_size_change(tlb, PAGE_SIZE);
+ tlb_change_page_size(tlb, PAGE_SIZE);
again:
init_rss_vec(rss);
start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
@@ -1155,7 +1155,7 @@ again:
*/
if (force_flush) {
force_flush = 0;
- tlb_flush_mmu_free(tlb);
+ tlb_flush_mmu(tlb);
if (addr != end)
goto again;
}
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 0082d699be94..b236069ff0d8 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -874,6 +874,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ
*/
mem = find_memory_block(__pfn_to_section(pfn));
nid = mem->nid;
+ put_device(&mem->dev);
/* associate pfn range with the zone */
zone = move_pfn_range(online_type, nid, pfn, nr_pages);
diff --git a/mm/mmap.c b/mm/mmap.c
index 41eb48d9b527..bd7b9f293b39 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -45,6 +45,7 @@
#include <linux/moduleparam.h>
#include <linux/pkeys.h>
#include <linux/oom.h>
+#include <linux/sched/mm.h>
#include <linux/uaccess.h>
#include <asm/cacheflush.h>
@@ -2525,7 +2526,8 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr)
vma = find_vma_prev(mm, addr, &prev);
if (vma && (vma->vm_start <= addr))
return vma;
- if (!prev || expand_stack(prev, addr))
+ /* don't alter vm_end if the coredump is running */
+ if (!prev || !mmget_still_valid(mm) || expand_stack(prev, addr))
return NULL;
if (prev->vm_flags & VM_LOCKED)
populate_vma_page_range(prev, addr, prev->vm_end, NULL);
@@ -2551,6 +2553,9 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr)
return vma;
if (!(vma->vm_flags & VM_GROWSDOWN))
return NULL;
+ /* don't alter vm_start if the coredump is running */
+ if (!mmget_still_valid(mm))
+ return NULL;
start = vma->vm_start;
if (expand_stack(vma, addr))
return NULL;
diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c
index f2f03c655807..99740e1dd273 100644
--- a/mm/mmu_gather.c
+++ b/mm/mmu_gather.c
@@ -11,7 +11,7 @@
#include <asm/pgalloc.h>
#include <asm/tlb.h>
-#ifdef HAVE_GENERIC_MMU_GATHER
+#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
static bool tlb_next_batch(struct mmu_gather *tlb)
{
@@ -41,35 +41,10 @@ static bool tlb_next_batch(struct mmu_gather *tlb)
return true;
}
-void arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
- unsigned long start, unsigned long end)
-{
- tlb->mm = mm;
-
- /* Is it from 0 to ~0? */
- tlb->fullmm = !(start | (end+1));
- tlb->need_flush_all = 0;
- tlb->local.next = NULL;
- tlb->local.nr = 0;
- tlb->local.max = ARRAY_SIZE(tlb->__pages);
- tlb->active = &tlb->local;
- tlb->batch_count = 0;
-
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
- tlb->batch = NULL;
-#endif
- tlb->page_size = 0;
-
- __tlb_reset_range(tlb);
-}
-
-void tlb_flush_mmu_free(struct mmu_gather *tlb)
+static void tlb_batch_pages_flush(struct mmu_gather *tlb)
{
struct mmu_gather_batch *batch;
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
- tlb_table_flush(tlb);
-#endif
for (batch = &tlb->local; batch && batch->nr; batch = batch->next) {
free_pages_and_swap_cache(batch->pages, batch->nr);
batch->nr = 0;
@@ -77,31 +52,10 @@ void tlb_flush_mmu_free(struct mmu_gather *tlb)
tlb->active = &tlb->local;
}
-void tlb_flush_mmu(struct mmu_gather *tlb)
-{
- tlb_flush_mmu_tlbonly(tlb);
- tlb_flush_mmu_free(tlb);
-}
-
-/* tlb_finish_mmu
- * Called at the end of the shootdown operation to free up any resources
- * that were required.
- */
-void arch_tlb_finish_mmu(struct mmu_gather *tlb,
- unsigned long start, unsigned long end, bool force)
+static void tlb_batch_list_free(struct mmu_gather *tlb)
{
struct mmu_gather_batch *batch, *next;
- if (force) {
- __tlb_reset_range(tlb);
- __tlb_adjust_range(tlb, start, end - start);
- }
-
- tlb_flush_mmu(tlb);
-
- /* keep the page table cache within bounds */
- check_pgt_cache();
-
for (batch = tlb->local.next; batch; batch = next) {
next = batch->next;
free_pages((unsigned long)batch, 0);
@@ -109,19 +63,15 @@ void arch_tlb_finish_mmu(struct mmu_gather *tlb,
tlb->local.next = NULL;
}
-/* __tlb_remove_page
- * Must perform the equivalent to __free_pte(pte_get_and_clear(ptep)), while
- * handling the additional races in SMP caused by other CPUs caching valid
- * mappings in their TLBs. Returns the number of free page slots left.
- * When out of page slots we must call tlb_flush_mmu().
- *returns true if the caller should flush.
- */
bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size)
{
struct mmu_gather_batch *batch;
VM_BUG_ON(!tlb->end);
+
+#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
VM_WARN_ON(tlb->page_size != page_size);
+#endif
batch = tlb->active;
/*
@@ -139,7 +89,7 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_
return false;
}
-#endif /* HAVE_GENERIC_MMU_GATHER */
+#endif /* HAVE_MMU_GATHER_NO_GATHER */
#ifdef CONFIG_HAVE_RCU_TABLE_FREE
@@ -152,7 +102,7 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_
*/
static inline void tlb_table_invalidate(struct mmu_gather *tlb)
{
-#ifdef CONFIG_HAVE_RCU_TABLE_INVALIDATE
+#ifndef CONFIG_HAVE_RCU_TABLE_NO_INVALIDATE
/*
* Invalidate page-table caches used by hardware walkers. Then we still
* need to RCU-sched wait while freeing the pages because software
@@ -193,7 +143,7 @@ static void tlb_remove_table_rcu(struct rcu_head *head)
free_page((unsigned long)batch);
}
-void tlb_table_flush(struct mmu_gather *tlb)
+static void tlb_table_flush(struct mmu_gather *tlb)
{
struct mmu_table_batch **batch = &tlb->batch;
@@ -225,6 +175,22 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table)
#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
+static void tlb_flush_mmu_free(struct mmu_gather *tlb)
+{
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+ tlb_table_flush(tlb);
+#endif
+#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
+ tlb_batch_pages_flush(tlb);
+#endif
+}
+
+void tlb_flush_mmu(struct mmu_gather *tlb)
+{
+ tlb_flush_mmu_tlbonly(tlb);
+ tlb_flush_mmu_free(tlb);
+}
+
/**
* tlb_gather_mmu - initialize an mmu_gather structure for page-table tear-down
* @tlb: the mmu_gather structure to initialize
@@ -240,10 +206,40 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table)
void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
unsigned long start, unsigned long end)
{
- arch_tlb_gather_mmu(tlb, mm, start, end);
+ tlb->mm = mm;
+
+ /* Is it from 0 to ~0? */
+ tlb->fullmm = !(start | (end+1));
+
+#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
+ tlb->need_flush_all = 0;
+ tlb->local.next = NULL;
+ tlb->local.nr = 0;
+ tlb->local.max = ARRAY_SIZE(tlb->__pages);
+ tlb->active = &tlb->local;
+ tlb->batch_count = 0;
+#endif
+
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+ tlb->batch = NULL;
+#endif
+#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
+ tlb->page_size = 0;
+#endif
+
+ __tlb_reset_range(tlb);
inc_tlb_flush_pending(tlb->mm);
}
+/**
+ * tlb_finish_mmu - finish an mmu_gather structure
+ * @tlb: the mmu_gather structure to finish
+ * @start: start of the region that will be removed from the page-table
+ * @end: end of the region that will be removed from the page-table
+ *
+ * Called at the end of the shootdown operation to free up any resources that
+ * were required.
+ */
void tlb_finish_mmu(struct mmu_gather *tlb,
unsigned long start, unsigned long end)
{
@@ -254,8 +250,17 @@ void tlb_finish_mmu(struct mmu_gather *tlb,
* the TLB by observing pte_none|!pte_dirty, for example so flush TLB
* forcefully if we detect parallel PTE batching threads.
*/
- bool force = mm_tlb_flush_nested(tlb->mm);
+ if (mm_tlb_flush_nested(tlb->mm)) {
+ __tlb_reset_range(tlb);
+ __tlb_adjust_range(tlb, start, end - start);
+ }
- arch_tlb_finish_mmu(tlb, start, end, force);
+ tlb_flush_mmu(tlb);
+
+ /* keep the page table cache within bounds */
+ check_pgt_cache();
+#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
+ tlb_batch_list_free(tlb);
+#endif
dec_tlb_flush_pending(tlb->mm);
}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d96ca5bc555b..59661106da16 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -266,7 +266,20 @@ compound_page_dtor * const compound_page_dtors[] = {
int min_free_kbytes = 1024;
int user_min_free_kbytes = -1;
+#ifdef CONFIG_DISCONTIGMEM
+/*
+ * DiscontigMem defines memory ranges as separate pg_data_t even if the ranges
+ * are not on separate NUMA nodes. Functionally this works but with
+ * watermark_boost_factor, it can reclaim prematurely as the ranges can be
+ * quite small. By default, do not boost watermarks on discontigmem as in
+ * many cases very high-order allocations like THP are likely to be
+ * unsupported and the premature reclaim offsets the advantage of long-term
+ * fragmentation avoidance.
+ */
+int watermark_boost_factor __read_mostly;
+#else
int watermark_boost_factor __read_mostly = 15000;
+#endif
int watermark_scale_factor = 10;
static unsigned long nr_kernel_pages __initdata;
@@ -1131,7 +1144,9 @@ static __always_inline bool free_pages_prepare(struct page *page,
}
arch_free_page(page, order);
kernel_poison_pages(page, 1 << order, 0);
- kernel_map_pages(page, 1 << order, 0);
+ if (debug_pagealloc_enabled())
+ kernel_map_pages(page, 1 << order, 0);
+
kasan_free_nondeferred_pages(page, order);
return true;
@@ -2001,7 +2016,8 @@ inline void post_alloc_hook(struct page *page, unsigned int order,
set_page_refcounted(page);
arch_alloc_page(page, order);
- kernel_map_pages(page, 1 << order, 1);
+ if (debug_pagealloc_enabled())
+ kernel_map_pages(page, 1 << order, 1);
kasan_alloc_pages(page, order);
kernel_poison_pages(page, 1 << order, 1);
set_page_owner(page, order, gfp_flags);
@@ -3419,8 +3435,11 @@ alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask)
alloc_flags |= ALLOC_KSWAPD;
#ifdef CONFIG_ZONE_DMA32
+ if (!zone)
+ return alloc_flags;
+
if (zone_idx(zone) != ZONE_NORMAL)
- goto out;
+ return alloc_flags;
/*
* If ZONE_DMA32 exists, assume it is the one after ZONE_NORMAL and
@@ -3429,9 +3448,9 @@ alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask)
*/
BUILD_BUG_ON(ZONE_NORMAL - ZONE_DMA32 != 1);
if (nr_online_nodes > 1 && !populated_zone(--zone))
- goto out;
+ return alloc_flags;
-out:
+ alloc_flags |= ALLOC_NOFRAGMENT;
#endif /* CONFIG_ZONE_DMA32 */
return alloc_flags;
}
@@ -3773,11 +3792,6 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
memalloc_noreclaim_restore(noreclaim_flag);
psi_memstall_leave(&pflags);
- if (*compact_result <= COMPACT_INACTIVE) {
- WARN_ON_ONCE(page);
- return NULL;
- }
-
/*
* At least in one zone compaction wasn't deferred or skipped, so let's
* count a compaction stall
@@ -8005,7 +8019,10 @@ void *__init alloc_large_system_hash(const char *tablename,
bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
int migratetype, int flags)
{
- unsigned long pfn, iter, found;
+ unsigned long found;
+ unsigned long iter = 0;
+ unsigned long pfn = page_to_pfn(page);
+ const char *reason = "unmovable page";
/*
* TODO we could make this much more efficient by not checking every
@@ -8015,17 +8032,20 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
* can still lead to having bootmem allocations in zone_movable.
*/
- /*
- * CMA allocations (alloc_contig_range) really need to mark isolate
- * CMA pageblocks even when they are not movable in fact so consider
- * them movable here.
- */
- if (is_migrate_cma(migratetype) &&
- is_migrate_cma(get_pageblock_migratetype(page)))
- return false;
+ if (is_migrate_cma_page(page)) {
+ /*
+ * CMA allocations (alloc_contig_range) really need to mark
+ * isolate CMA pageblocks even when they are not movable in fact
+ * so consider them movable here.
+ */
+ if (is_migrate_cma(migratetype))
+ return false;
+
+ reason = "CMA page";
+ goto unmovable;
+ }
- pfn = page_to_pfn(page);
- for (found = 0, iter = 0; iter < pageblock_nr_pages; iter++) {
+ for (found = 0; iter < pageblock_nr_pages; iter++) {
unsigned long check = pfn + iter;
if (!pfn_valid_within(check))
@@ -8105,7 +8125,7 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
unmovable:
WARN_ON_ONCE(zone_idx(zone) == ZONE_MOVABLE);
if (flags & REPORT_FAILURE)
- dump_page(pfn_to_page(pfn+iter), "unmovable page");
+ dump_page(pfn_to_page(pfn + iter), reason);
return true;
}
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 925b6f44a444..addcbb2ae4e4 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -58,15 +58,10 @@ static bool need_page_owner(void)
static __always_inline depot_stack_handle_t create_dummy_stack(void)
{
unsigned long entries[4];
- struct stack_trace dummy;
+ unsigned int nr_entries;
- dummy.nr_entries = 0;
- dummy.max_entries = ARRAY_SIZE(entries);
- dummy.entries = &entries[0];
- dummy.skip = 0;
-
- save_stack_trace(&dummy);
- return depot_save_stack(&dummy, GFP_KERNEL);
+ nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 0);
+ return stack_depot_save(entries, nr_entries, GFP_KERNEL);
}
static noinline void register_dummy_stack(void)
@@ -120,49 +115,39 @@ void __reset_page_owner(struct page *page, unsigned int order)
}
}
-static inline bool check_recursive_alloc(struct stack_trace *trace,
- unsigned long ip)
+static inline bool check_recursive_alloc(unsigned long *entries,
+ unsigned int nr_entries,
+ unsigned long ip)
{
- int i;
-
- if (!trace->nr_entries)
- return false;
+ unsigned int i;
- for (i = 0; i < trace->nr_entries; i++) {
- if (trace->entries[i] == ip)
+ for (i = 0; i < nr_entries; i++) {
+ if (entries[i] == ip)
return true;
}
-
return false;
}
static noinline depot_stack_handle_t save_stack(gfp_t flags)
{
unsigned long entries[PAGE_OWNER_STACK_DEPTH];
- struct stack_trace trace = {
- .nr_entries = 0,
- .entries = entries,
- .max_entries = PAGE_OWNER_STACK_DEPTH,
- .skip = 2
- };
depot_stack_handle_t handle;
+ unsigned int nr_entries;
- save_stack_trace(&trace);
- if (trace.nr_entries != 0 &&
- trace.entries[trace.nr_entries-1] == ULONG_MAX)
- trace.nr_entries--;
+ nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 2);
/*
- * We need to check recursion here because our request to stackdepot
- * could trigger memory allocation to save new entry. New memory
- * allocation would reach here and call depot_save_stack() again
- * if we don't catch it. There is still not enough memory in stackdepot
- * so it would try to allocate memory again and loop forever.
+ * We need to check recursion here because our request to
+ * stackdepot could trigger memory allocation to save new
+ * entry. New memory allocation would reach here and call
+ * stack_depot_save_entries() again if we don't catch it. There is
+ * still not enough memory in stackdepot so it would try to
+ * allocate memory again and loop forever.
*/
- if (check_recursive_alloc(&trace, _RET_IP_))
+ if (check_recursive_alloc(entries, nr_entries, _RET_IP_))
return dummy_handle;
- handle = depot_save_stack(&trace, flags);
+ handle = stack_depot_save(entries, nr_entries, flags);
if (!handle)
handle = failure_handle;
@@ -340,16 +325,10 @@ print_page_owner(char __user *buf, size_t count, unsigned long pfn,
struct page *page, struct page_owner *page_owner,
depot_stack_handle_t handle)
{
- int ret;
- int pageblock_mt, page_mt;
+ int ret, pageblock_mt, page_mt;
+ unsigned long *entries;
+ unsigned int nr_entries;
char *kbuf;
- unsigned long entries[PAGE_OWNER_STACK_DEPTH];
- struct stack_trace trace = {
- .nr_entries = 0,
- .entries = entries,
- .max_entries = PAGE_OWNER_STACK_DEPTH,
- .skip = 0
- };
count = min_t(size_t, count, PAGE_SIZE);
kbuf = kmalloc(count, GFP_KERNEL);
@@ -378,8 +357,8 @@ print_page_owner(char __user *buf, size_t count, unsigned long pfn,
if (ret >= count)
goto err;
- depot_fetch_stack(handle, &trace);
- ret += snprint_stack_trace(kbuf + ret, count - ret, &trace, 0);
+ nr_entries = stack_depot_fetch(handle, &entries);
+ ret += stack_trace_snprint(kbuf + ret, count - ret, entries, nr_entries, 0);
if (ret >= count)
goto err;
@@ -410,14 +389,9 @@ void __dump_page_owner(struct page *page)
{
struct page_ext *page_ext = lookup_page_ext(page);
struct page_owner *page_owner;
- unsigned long entries[PAGE_OWNER_STACK_DEPTH];
- struct stack_trace trace = {
- .nr_entries = 0,
- .entries = entries,
- .max_entries = PAGE_OWNER_STACK_DEPTH,
- .skip = 0
- };
depot_stack_handle_t handle;
+ unsigned long *entries;
+ unsigned int nr_entries;
gfp_t gfp_mask;
int mt;
@@ -441,10 +415,10 @@ void __dump_page_owner(struct page *page)
return;
}
- depot_fetch_stack(handle, &trace);
+ nr_entries = stack_depot_fetch(handle, &entries);
pr_alert("page allocated via order %u, migratetype %s, gfp_mask %#x(%pGg)\n",
page_owner->order, migratetype_names[mt], gfp_mask, &gfp_mask);
- print_stack_trace(&trace, 0);
+ stack_trace_print(entries, nr_entries, 0);
if (page_owner->last_migrate_reason != -1)
pr_alert("page has been migrated, last migrate reason: %s\n",
diff --git a/mm/percpu.c b/mm/percpu.c
index 2e6fc8d552c9..68dd2e7e73b5 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -2567,8 +2567,8 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
ai->groups[group].base_offset = areas[group] - base;
}
- pr_info("Embedded %zu pages/cpu @%p s%zu r%zu d%zu u%zu\n",
- PFN_DOWN(size_sum), base, ai->static_size, ai->reserved_size,
+ pr_info("Embedded %zu pages/cpu s%zu r%zu d%zu u%zu\n",
+ PFN_DOWN(size_sum), ai->static_size, ai->reserved_size,
ai->dyn_size, ai->unit_size);
rc = pcpu_setup_first_chunk(ai, base);
@@ -2692,8 +2692,8 @@ int __init pcpu_page_first_chunk(size_t reserved_size,
}
/* we're ready, commit */
- pr_info("%d %s pages/cpu @%p s%zu r%zu d%zu\n",
- unit_pages, psize_str, vm.addr, ai->static_size,
+ pr_info("%d %s pages/cpu s%zu r%zu d%zu\n",
+ unit_pages, psize_str, ai->static_size,
ai->reserved_size, ai->dyn_size);
rc = pcpu_setup_first_chunk(ai, vm.addr);
diff --git a/mm/shmem.c b/mm/shmem.c
index b3db3779a30a..2275a0ff7c30 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1081,9 +1081,14 @@ static void shmem_evict_inode(struct inode *inode)
}
spin_unlock(&sbinfo->shrinklist_lock);
}
- if (!list_empty(&info->swaplist)) {
+ while (!list_empty(&info->swaplist)) {
+ /* Wait while shmem_unuse() is scanning this inode... */
+ wait_var_event(&info->stop_eviction,
+ !atomic_read(&info->stop_eviction));
mutex_lock(&shmem_swaplist_mutex);
- list_del_init(&info->swaplist);
+ /* ...but beware of the race if we peeked too early */
+ if (!atomic_read(&info->stop_eviction))
+ list_del_init(&info->swaplist);
mutex_unlock(&shmem_swaplist_mutex);
}
}
@@ -1099,10 +1104,11 @@ extern struct swap_info_struct *swap_info[];
static int shmem_find_swap_entries(struct address_space *mapping,
pgoff_t start, unsigned int nr_entries,
struct page **entries, pgoff_t *indices,
- bool frontswap)
+ unsigned int type, bool frontswap)
{
XA_STATE(xas, &mapping->i_pages, start);
struct page *page;
+ swp_entry_t entry;
unsigned int ret = 0;
if (!nr_entries)
@@ -1116,13 +1122,12 @@ static int shmem_find_swap_entries(struct address_space *mapping,
if (!xa_is_value(page))
continue;
- if (frontswap) {
- swp_entry_t entry = radix_to_swp_entry(page);
-
- if (!frontswap_test(swap_info[swp_type(entry)],
- swp_offset(entry)))
- continue;
- }
+ entry = radix_to_swp_entry(page);
+ if (swp_type(entry) != type)
+ continue;
+ if (frontswap &&
+ !frontswap_test(swap_info[type], swp_offset(entry)))
+ continue;
indices[ret] = xas.xa_index;
entries[ret] = page;
@@ -1194,7 +1199,7 @@ static int shmem_unuse_inode(struct inode *inode, unsigned int type,
pvec.nr = shmem_find_swap_entries(mapping, start, nr_entries,
pvec.pages, indices,
- frontswap);
+ type, frontswap);
if (pvec.nr == 0) {
ret = 0;
break;
@@ -1227,36 +1232,27 @@ int shmem_unuse(unsigned int type, bool frontswap,
unsigned long *fs_pages_to_unuse)
{
struct shmem_inode_info *info, *next;
- struct inode *inode;
- struct inode *prev_inode = NULL;
int error = 0;
if (list_empty(&shmem_swaplist))
return 0;
mutex_lock(&shmem_swaplist_mutex);
-
- /*
- * The extra refcount on the inode is necessary to safely dereference
- * p->next after re-acquiring the lock. New shmem inodes with swap
- * get added to the end of the list and we will scan them all.
- */
list_for_each_entry_safe(info, next, &shmem_swaplist, swaplist) {
if (!info->swapped) {
list_del_init(&info->swaplist);
continue;
}
-
- inode = igrab(&info->vfs_inode);
- if (!inode)
- continue;
-
+ /*
+ * Drop the swaplist mutex while searching the inode for swap;
+ * but before doing so, make sure shmem_evict_inode() will not
+ * remove placeholder inode from swaplist, nor let it be freed
+ * (igrab() would protect from unlink, but not from unmount).
+ */
+ atomic_inc(&info->stop_eviction);
mutex_unlock(&shmem_swaplist_mutex);
- if (prev_inode)
- iput(prev_inode);
- prev_inode = inode;
- error = shmem_unuse_inode(inode, type, frontswap,
+ error = shmem_unuse_inode(&info->vfs_inode, type, frontswap,
fs_pages_to_unuse);
cond_resched();
@@ -1264,14 +1260,13 @@ int shmem_unuse(unsigned int type, bool frontswap,
next = list_next_entry(info, swaplist);
if (!info->swapped)
list_del_init(&info->swaplist);
+ if (atomic_dec_and_test(&info->stop_eviction))
+ wake_up_var(&info->stop_eviction);
if (error)
break;
}
mutex_unlock(&shmem_swaplist_mutex);
- if (prev_inode)
- iput(prev_inode);
-
return error;
}
@@ -2238,6 +2233,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
info = SHMEM_I(inode);
memset(info, 0, (char *)inode - (char *)info);
spin_lock_init(&info->lock);
+ atomic_set(&info->stop_eviction, 0);
info->seals = F_SEAL_SEAL;
info->flags = flags & VM_NORESERVE;
INIT_LIST_HEAD(&info->shrinklist);
diff --git a/mm/slab.c b/mm/slab.c
index 329bfe67f2ca..284ab737faee 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1467,53 +1467,17 @@ static bool is_debug_pagealloc_cache(struct kmem_cache *cachep)
}
#ifdef CONFIG_DEBUG_PAGEALLOC
-static void store_stackinfo(struct kmem_cache *cachep, unsigned long *addr,
- unsigned long caller)
-{
- int size = cachep->object_size;
-
- addr = (unsigned long *)&((char *)addr)[obj_offset(cachep)];
-
- if (size < 5 * sizeof(unsigned long))
- return;
-
- *addr++ = 0x12345678;
- *addr++ = caller;
- *addr++ = smp_processor_id();
- size -= 3 * sizeof(unsigned long);
- {
- unsigned long *sptr = &caller;
- unsigned long svalue;
-
- while (!kstack_end(sptr)) {
- svalue = *sptr++;
- if (kernel_text_address(svalue)) {
- *addr++ = svalue;
- size -= sizeof(unsigned long);
- if (size <= sizeof(unsigned long))
- break;
- }
- }
-
- }
- *addr++ = 0x87654321;
-}
-
-static void slab_kernel_map(struct kmem_cache *cachep, void *objp,
- int map, unsigned long caller)
+static void slab_kernel_map(struct kmem_cache *cachep, void *objp, int map)
{
if (!is_debug_pagealloc_cache(cachep))
return;
- if (caller)
- store_stackinfo(cachep, objp, caller);
-
kernel_map_pages(virt_to_page(objp), cachep->size / PAGE_SIZE, map);
}
#else
static inline void slab_kernel_map(struct kmem_cache *cachep, void *objp,
- int map, unsigned long caller) {}
+ int map) {}
#endif
@@ -1661,7 +1625,7 @@ static void slab_destroy_debugcheck(struct kmem_cache *cachep,
if (cachep->flags & SLAB_POISON) {
check_poison_obj(cachep, objp);
- slab_kernel_map(cachep, objp, 1, 0);
+ slab_kernel_map(cachep, objp, 1);
}
if (cachep->flags & SLAB_RED_ZONE) {
if (*dbg_redzone1(cachep, objp) != RED_INACTIVE)
@@ -2374,7 +2338,6 @@ static void *alloc_slabmgmt(struct kmem_cache *cachep,
/* Slab management obj is off-slab. */
freelist = kmem_cache_alloc_node(cachep->freelist_cache,
local_flags, nodeid);
- freelist = kasan_reset_tag(freelist);
if (!freelist)
return NULL;
} else {
@@ -2434,7 +2397,7 @@ static void cache_init_objs_debug(struct kmem_cache *cachep, struct page *page)
/* need to poison the objs? */
if (cachep->flags & SLAB_POISON) {
poison_obj(cachep, objp, POISON_FREE);
- slab_kernel_map(cachep, objp, 0, 0);
+ slab_kernel_map(cachep, objp, 0);
}
}
#endif
@@ -2813,7 +2776,7 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
if (cachep->flags & SLAB_POISON) {
poison_obj(cachep, objp, POISON_FREE);
- slab_kernel_map(cachep, objp, 0, caller);
+ slab_kernel_map(cachep, objp, 0);
}
return objp;
}
@@ -3077,7 +3040,7 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
return objp;
if (cachep->flags & SLAB_POISON) {
check_poison_obj(cachep, objp);
- slab_kernel_map(cachep, objp, 1, 0);
+ slab_kernel_map(cachep, objp, 1);
poison_obj(cachep, objp, POISON_INUSE);
}
if (cachep->flags & SLAB_STORE_USER)
@@ -4308,7 +4271,8 @@ static void show_symbol(struct seq_file *m, unsigned long address)
static int leaks_show(struct seq_file *m, void *p)
{
- struct kmem_cache *cachep = list_entry(p, struct kmem_cache, list);
+ struct kmem_cache *cachep = list_entry(p, struct kmem_cache,
+ root_caches_node);
struct page *page;
struct kmem_cache_node *n;
const char *name;
diff --git a/mm/slub.c b/mm/slub.c
index d30ede89f4a6..6b28cd2b5a58 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -552,31 +552,22 @@ static void set_track(struct kmem_cache *s, void *object,
if (addr) {
#ifdef CONFIG_STACKTRACE
- struct stack_trace trace;
- int i;
+ unsigned int nr_entries;
- trace.nr_entries = 0;
- trace.max_entries = TRACK_ADDRS_COUNT;
- trace.entries = p->addrs;
- trace.skip = 3;
metadata_access_enable();
- save_stack_trace(&trace);
+ nr_entries = stack_trace_save(p->addrs, TRACK_ADDRS_COUNT, 3);
metadata_access_disable();
- /* See rant in lockdep.c */
- if (trace.nr_entries != 0 &&
- trace.entries[trace.nr_entries - 1] == ULONG_MAX)
- trace.nr_entries--;
-
- for (i = trace.nr_entries; i < TRACK_ADDRS_COUNT; i++)
- p->addrs[i] = 0;
+ if (nr_entries < TRACK_ADDRS_COUNT)
+ p->addrs[nr_entries] = 0;
#endif
p->addr = addr;
p->cpu = smp_processor_id();
p->pid = current->pid;
p->when = jiffies;
- } else
+ } else {
memset(p, 0, sizeof(struct track));
+ }
}
static void init_tracking(struct kmem_cache *s, void *object)
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 2b8d9c3fbb47..cf63b5f01adf 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2023,7 +2023,6 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si,
* If the boolean frontswap is true, only unuse pages_to_unuse pages;
* pages_to_unuse==0 means all pages; ignored if frontswap is false
*/
-#define SWAP_UNUSE_MAX_TRIES 3
int try_to_unuse(unsigned int type, bool frontswap,
unsigned long pages_to_unuse)
{
@@ -2035,7 +2034,6 @@ int try_to_unuse(unsigned int type, bool frontswap,
struct page *page;
swp_entry_t entry;
unsigned int i;
- int retries = 0;
if (!si->inuse_pages)
return 0;
@@ -2053,11 +2051,9 @@ retry:
spin_lock(&mmlist_lock);
p = &init_mm.mmlist;
- while ((p = p->next) != &init_mm.mmlist) {
- if (signal_pending(current)) {
- retval = -EINTR;
- break;
- }
+ while (si->inuse_pages &&
+ !signal_pending(current) &&
+ (p = p->next) != &init_mm.mmlist) {
mm = list_entry(p, struct mm_struct, mmlist);
if (!mmget_not_zero(mm))
@@ -2084,7 +2080,9 @@ retry:
mmput(prev_mm);
i = 0;
- while ((i = find_next_to_unuse(si, i, frontswap)) != 0) {
+ while (si->inuse_pages &&
+ !signal_pending(current) &&
+ (i = find_next_to_unuse(si, i, frontswap)) != 0) {
entry = swp_entry(type, i);
page = find_get_page(swap_address_space(entry), i);
@@ -2117,14 +2115,18 @@ retry:
* If yes, we would need to do retry the unuse logic again.
* Under global memory pressure, swap entries can be reinserted back
* into process space after the mmlist loop above passes over them.
- * Its not worth continuosuly retrying to unuse the swap in this case.
- * So we try SWAP_UNUSE_MAX_TRIES times.
+ *
+ * Limit the number of retries? No: when mmget_not_zero() above fails,
+ * that mm is likely to be freeing swap from exit_mmap(), which proceeds
+ * at its own independent pace; and even shmem_writepage() could have
+ * been preempted after get_swap_page(), temporarily hiding that swap.
+ * It's easy and robust (though cpu-intensive) just to keep retrying.
*/
- if (++retries >= SWAP_UNUSE_MAX_TRIES)
- retval = -EBUSY;
- else if (si->inuse_pages)
- goto retry;
-
+ if (si->inuse_pages) {
+ if (!signal_pending(current))
+ goto retry;
+ retval = -EINTR;
+ }
out:
return (retval == FRONTSWAP_PAGES_UNUSED) ? 0 : retval;
}
diff --git a/mm/util.c b/mm/util.c
index d559bde497a9..43a2984bccaa 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -204,7 +204,7 @@ EXPORT_SYMBOL(vmemdup_user);
* @s: The string to duplicate
* @n: Maximum number of bytes to copy, including the trailing NUL.
*
- * Return: newly allocated copy of @s or %NULL in case of error
+ * Return: newly allocated copy of @s or an ERR_PTR() in case of error
*/
char *strndup_user(const char __user *s, long n)
{
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index e86ba6e74b50..e5e9e1fcac01 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -18,6 +18,7 @@
#include <linux/interrupt.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
+#include <linux/set_memory.h>
#include <linux/debugobjects.h>
#include <linux/kallsyms.h>
#include <linux/list.h>
@@ -1059,24 +1060,9 @@ static void vb_free(const void *addr, unsigned long size)
spin_unlock(&vb->lock);
}
-/**
- * vm_unmap_aliases - unmap outstanding lazy aliases in the vmap layer
- *
- * The vmap/vmalloc layer lazily flushes kernel virtual mappings primarily
- * to amortize TLB flushing overheads. What this means is that any page you
- * have now, may, in a former life, have been mapped into kernel virtual
- * address by the vmap layer and so there might be some CPUs with TLB entries
- * still referencing that page (additional to the regular 1:1 kernel mapping).
- *
- * vm_unmap_aliases flushes all such lazy mappings. After it returns, we can
- * be sure that none of the pages we have control over will have any aliases
- * from the vmap layer.
- */
-void vm_unmap_aliases(void)
+static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush)
{
- unsigned long start = ULONG_MAX, end = 0;
int cpu;
- int flush = 0;
if (unlikely(!vmap_initialized))
return;
@@ -1113,6 +1099,27 @@ void vm_unmap_aliases(void)
flush_tlb_kernel_range(start, end);
mutex_unlock(&vmap_purge_lock);
}
+
+/**
+ * vm_unmap_aliases - unmap outstanding lazy aliases in the vmap layer
+ *
+ * The vmap/vmalloc layer lazily flushes kernel virtual mappings primarily
+ * to amortize TLB flushing overheads. What this means is that any page you
+ * have now, may, in a former life, have been mapped into kernel virtual
+ * address by the vmap layer and so there might be some CPUs with TLB entries
+ * still referencing that page (additional to the regular 1:1 kernel mapping).
+ *
+ * vm_unmap_aliases flushes all such lazy mappings. After it returns, we can
+ * be sure that none of the pages we have control over will have any aliases
+ * from the vmap layer.
+ */
+void vm_unmap_aliases(void)
+{
+ unsigned long start = ULONG_MAX, end = 0;
+ int flush = 0;
+
+ _vm_unmap_aliases(start, end, flush);
+}
EXPORT_SYMBOL_GPL(vm_unmap_aliases);
/**
@@ -1505,6 +1512,72 @@ struct vm_struct *remove_vm_area(const void *addr)
return NULL;
}
+static inline void set_area_direct_map(const struct vm_struct *area,
+ int (*set_direct_map)(struct page *page))
+{
+ int i;
+
+ for (i = 0; i < area->nr_pages; i++)
+ if (page_address(area->pages[i]))
+ set_direct_map(area->pages[i]);
+}
+
+/* Handle removing and resetting vm mappings related to the vm_struct. */
+static void vm_remove_mappings(struct vm_struct *area, int deallocate_pages)
+{
+ unsigned long addr = (unsigned long)area->addr;
+ unsigned long start = ULONG_MAX, end = 0;
+ int flush_reset = area->flags & VM_FLUSH_RESET_PERMS;
+ int i;
+
+ /*
+ * The below block can be removed when all architectures that have
+ * direct map permissions also have set_direct_map_() implementations.
+ * This is concerned with resetting the direct map any an vm alias with
+ * execute permissions, without leaving a RW+X window.
+ */
+ if (flush_reset && !IS_ENABLED(CONFIG_ARCH_HAS_SET_DIRECT_MAP)) {
+ set_memory_nx(addr, area->nr_pages);
+ set_memory_rw(addr, area->nr_pages);
+ }
+
+ remove_vm_area(area->addr);
+
+ /* If this is not VM_FLUSH_RESET_PERMS memory, no need for the below. */
+ if (!flush_reset)
+ return;
+
+ /*
+ * If not deallocating pages, just do the flush of the VM area and
+ * return.
+ */
+ if (!deallocate_pages) {
+ vm_unmap_aliases();
+ return;
+ }
+
+ /*
+ * If execution gets here, flush the vm mapping and reset the direct
+ * map. Find the start and end range of the direct mappings to make sure
+ * the vm_unmap_aliases() flush includes the direct map.
+ */
+ for (i = 0; i < area->nr_pages; i++) {
+ if (page_address(area->pages[i])) {
+ start = min(addr, start);
+ end = max(addr, end);
+ }
+ }
+
+ /*
+ * Set direct map to something invalid so that it won't be cached if
+ * there are any accesses after the TLB flush, then flush the TLB and
+ * reset the direct map permissions to the default.
+ */
+ set_area_direct_map(area, set_direct_map_invalid_noflush);
+ _vm_unmap_aliases(start, end, 1);
+ set_area_direct_map(area, set_direct_map_default_noflush);
+}
+
static void __vunmap(const void *addr, int deallocate_pages)
{
struct vm_struct *area;
@@ -1526,7 +1599,8 @@ static void __vunmap(const void *addr, int deallocate_pages)
debug_check_no_locks_freed(area->addr, get_vm_area_size(area));
debug_check_no_obj_freed(area->addr, get_vm_area_size(area));
- remove_vm_area(addr);
+ vm_remove_mappings(area, deallocate_pages);
+
if (deallocate_pages) {
int i;
@@ -1961,8 +2035,9 @@ EXPORT_SYMBOL(vzalloc_node);
*/
void *vmalloc_exec(unsigned long size)
{
- return __vmalloc_node(size, 1, GFP_KERNEL, PAGE_KERNEL_EXEC,
- NUMA_NO_NODE, __builtin_return_address(0));
+ return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END,
+ GFP_KERNEL, PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS,
+ NUMA_NO_NODE, __builtin_return_address(0));
}
#if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index a5ad0b35ab8e..a815f73ee4d5 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2176,7 +2176,6 @@ static void shrink_active_list(unsigned long nr_to_scan,
* 10TB 320 32GB
*/
static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
- struct mem_cgroup *memcg,
struct scan_control *sc, bool actual_reclaim)
{
enum lru_list active_lru = file * LRU_FILE + LRU_ACTIVE;
@@ -2197,16 +2196,12 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
inactive = lruvec_lru_size(lruvec, inactive_lru, sc->reclaim_idx);
active = lruvec_lru_size(lruvec, active_lru, sc->reclaim_idx);
- if (memcg)
- refaults = memcg_page_state(memcg, WORKINGSET_ACTIVATE);
- else
- refaults = node_page_state(pgdat, WORKINGSET_ACTIVATE);
-
/*
* When refaults are being observed, it means a new workingset
* is being established. Disable active list protection to get
* rid of the stale workingset quickly.
*/
+ refaults = lruvec_page_state(lruvec, WORKINGSET_ACTIVATE);
if (file && actual_reclaim && lruvec->refaults != refaults) {
inactive_ratio = 0;
} else {
@@ -2227,12 +2222,10 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
}
static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
- struct lruvec *lruvec, struct mem_cgroup *memcg,
- struct scan_control *sc)
+ struct lruvec *lruvec, struct scan_control *sc)
{
if (is_active_lru(lru)) {
- if (inactive_list_is_low(lruvec, is_file_lru(lru),
- memcg, sc, true))
+ if (inactive_list_is_low(lruvec, is_file_lru(lru), sc, true))
shrink_active_list(nr_to_scan, lruvec, sc, lru);
return 0;
}
@@ -2332,7 +2325,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
* anonymous pages on the LRU in eligible zones.
* Otherwise, the small LRU gets thrashed.
*/
- if (!inactive_list_is_low(lruvec, false, memcg, sc, false) &&
+ if (!inactive_list_is_low(lruvec, false, sc, false) &&
lruvec_lru_size(lruvec, LRU_INACTIVE_ANON, sc->reclaim_idx)
>> sc->priority) {
scan_balance = SCAN_ANON;
@@ -2350,7 +2343,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
* lruvec even if it has plenty of old anonymous pages unless the
* system is under heavy pressure.
*/
- if (!inactive_list_is_low(lruvec, true, memcg, sc, false) &&
+ if (!inactive_list_is_low(lruvec, true, sc, false) &&
lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, sc->reclaim_idx) >> sc->priority) {
scan_balance = SCAN_FILE;
goto out;
@@ -2503,7 +2496,7 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc
nr[lru] -= nr_to_scan;
nr_reclaimed += shrink_list(lru, nr_to_scan,
- lruvec, memcg, sc);
+ lruvec, sc);
}
}
@@ -2570,7 +2563,7 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc
* Even if we did not try to evict anon pages at all, we want to
* rebalance the anon lru active/inactive ratio.
*/
- if (inactive_list_is_low(lruvec, false, memcg, sc, true))
+ if (inactive_list_is_low(lruvec, false, sc, true))
shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
sc, LRU_ACTIVE_ANON);
}
@@ -2969,12 +2962,8 @@ static void snapshot_refaults(struct mem_cgroup *root_memcg, pg_data_t *pgdat)
unsigned long refaults;
struct lruvec *lruvec;
- if (memcg)
- refaults = memcg_page_state(memcg, WORKINGSET_ACTIVATE);
- else
- refaults = node_page_state(pgdat, WORKINGSET_ACTIVATE);
-
lruvec = mem_cgroup_lruvec(pgdat, memcg);
+ refaults = lruvec_page_state(lruvec, WORKINGSET_ACTIVATE);
lruvec->refaults = refaults;
} while ((memcg = mem_cgroup_iter(root_memcg, memcg, NULL)));
}
@@ -3339,7 +3328,7 @@ static void age_active_anon(struct pglist_data *pgdat,
do {
struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg);
- if (inactive_list_is_low(lruvec, false, memcg, sc, true))
+ if (inactive_list_is_low(lruvec, false, sc, true))
shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
sc, LRU_ACTIVE_ANON);
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 36b56f858f0f..a7d493366a65 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1274,13 +1274,8 @@ const char * const vmstat_text[] = {
#endif
#endif /* CONFIG_MEMORY_BALLOON */
#ifdef CONFIG_DEBUG_TLBFLUSH
-#ifdef CONFIG_SMP
"nr_tlb_remote_flush",
"nr_tlb_remote_flush_received",
-#else
- "", /* nr_tlb_remote_flush */
- "", /* nr_tlb_remote_flush_received */
-#endif /* CONFIG_SMP */
"nr_tlb_local_flush_all",
"nr_tlb_local_flush_one",
#endif /* CONFIG_DEBUG_TLBFLUSH */
generated by cgit v1.2.3 (git 2.39.0) at 2024-12-29 01:01:02 +0300