summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/Kconfig5
-rw-r--r--mm/backing-dev.c7
-rw-r--r--mm/damon/core.c20
-rw-r--r--mm/damon/dbgfs.c35
-rw-r--r--mm/damon/vaddr-test.h79
-rw-r--r--mm/damon/vaddr.c2
-rw-r--r--mm/filemap.c2
-rw-r--r--mm/highmem.c34
-rw-r--r--mm/hugetlb.c38
-rw-r--r--mm/kfence/core.c1
-rw-r--r--mm/memcontrol.c108
-rw-r--r--mm/memory-failure.c14
-rw-r--r--mm/memory_hotplug.c1
-rw-r--r--mm/mempolicy.c3
-rw-r--r--mm/shmem.c3
-rw-r--r--mm/slab.c3
-rw-r--r--mm/slab.h2
-rw-r--r--mm/slob.c3
-rw-r--r--mm/slub.c17
-rw-r--r--mm/swap.c1
-rw-r--r--mm/swap_slots.c1
-rw-r--r--mm/util.c2
-rw-r--r--mm/vmscan.c65
23 files changed, 264 insertions, 182 deletions
diff --git a/mm/Kconfig b/mm/Kconfig
index 068ce591a13a..356f4f2c779e 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -428,7 +428,7 @@ config THP_SWAP
# UP and nommu archs use km based percpu allocator
#
config NEED_PER_CPU_KM
- depends on !SMP
+ depends on !SMP || !MMU
bool
default y
@@ -890,6 +890,9 @@ config MAPPING_DIRTY_HELPERS
config KMAP_LOCAL
bool
+config KMAP_LOCAL_NON_LINEAR_PTE_ARRAY
+ bool
+
# struct io_mapping based helper. Selected by drivers that need them
config IO_MAPPING
bool
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 1eead4761011..eae96dfe0261 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -945,6 +945,13 @@ void bdi_unregister(struct backing_dev_info *bdi)
wb_shutdown(&bdi->wb);
cgwb_bdi_unregister(bdi);
+ /*
+ * If this BDI's min ratio has been set, use bdi_set_min_ratio() to
+ * update the global bdi_min_ratio.
+ */
+ if (bdi->min_ratio)
+ bdi_set_min_ratio(bdi, 0);
+
if (bdi->dev) {
bdi_debug_unregister(bdi);
device_unregister(bdi->dev);
diff --git a/mm/damon/core.c b/mm/damon/core.c
index c381b3c525d0..e92497895202 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -282,7 +282,6 @@ int damon_set_targets(struct damon_ctx *ctx,
for (i = 0; i < nr_ids; i++) {
t = damon_new_target(ids[i]);
if (!t) {
- pr_err("Failed to alloc damon_target\n");
/* The caller should do cleanup of the ids itself */
damon_for_each_target_safe(t, next, ctx)
damon_destroy_target(t);
@@ -312,16 +311,10 @@ int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int,
unsigned long aggr_int, unsigned long primitive_upd_int,
unsigned long min_nr_reg, unsigned long max_nr_reg)
{
- if (min_nr_reg < 3) {
- pr_err("min_nr_regions (%lu) must be at least 3\n",
- min_nr_reg);
+ if (min_nr_reg < 3)
return -EINVAL;
- }
- if (min_nr_reg > max_nr_reg) {
- pr_err("invalid nr_regions. min (%lu) > max (%lu)\n",
- min_nr_reg, max_nr_reg);
+ if (min_nr_reg > max_nr_reg)
return -EINVAL;
- }
ctx->sample_interval = sample_int;
ctx->aggr_interval = aggr_int;
@@ -980,10 +973,11 @@ static unsigned long damos_wmark_wait_us(struct damos *scheme)
static void kdamond_usleep(unsigned long usecs)
{
- if (usecs > 100 * 1000)
- schedule_timeout_interruptible(usecs_to_jiffies(usecs));
+ /* See Documentation/timers/timers-howto.rst for the thresholds */
+ if (usecs > 20 * USEC_PER_MSEC)
+ schedule_timeout_idle(usecs_to_jiffies(usecs));
else
- usleep_range(usecs, usecs + 1);
+ usleep_idle_range(usecs, usecs + 1);
}
/* Returns negative error code if it's not activated but should return */
@@ -1038,7 +1032,7 @@ static int kdamond_fn(void *data)
ctx->callback.after_sampling(ctx))
done = true;
- usleep_range(ctx->sample_interval, ctx->sample_interval + 1);
+ kdamond_usleep(ctx->sample_interval);
if (ctx->primitive.check_accesses)
max_nr_accesses = ctx->primitive.check_accesses(ctx);
diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c
index eccc14b34901..ad65436756af 100644
--- a/mm/damon/dbgfs.c
+++ b/mm/damon/dbgfs.c
@@ -32,7 +32,7 @@ static char *user_input_str(const char __user *buf, size_t count, loff_t *ppos)
if (*ppos)
return ERR_PTR(-EINVAL);
- kbuf = kmalloc(count + 1, GFP_KERNEL);
+ kbuf = kmalloc(count + 1, GFP_KERNEL | __GFP_NOWARN);
if (!kbuf)
return ERR_PTR(-ENOMEM);
@@ -133,7 +133,7 @@ static ssize_t dbgfs_schemes_read(struct file *file, char __user *buf,
char *kbuf;
ssize_t len;
- kbuf = kmalloc(count, GFP_KERNEL);
+ kbuf = kmalloc(count, GFP_KERNEL | __GFP_NOWARN);
if (!kbuf)
return -ENOMEM;
@@ -210,10 +210,8 @@ static struct damos **str_to_schemes(const char *str, ssize_t len,
&wmarks.low, &parsed);
if (ret != 18)
break;
- if (!damos_action_valid(action)) {
- pr_err("wrong action %d\n", action);
+ if (!damos_action_valid(action))
goto fail;
- }
pos += parsed;
scheme = damon_new_scheme(min_sz, max_sz, min_nr_a, max_nr_a,
@@ -355,6 +353,7 @@ static ssize_t dbgfs_target_ids_write(struct file *file,
const char __user *buf, size_t count, loff_t *ppos)
{
struct damon_ctx *ctx = file->private_data;
+ struct damon_target *t, *next_t;
bool id_is_pid = true;
char *kbuf, *nrs;
unsigned long *targets;
@@ -399,8 +398,12 @@ static ssize_t dbgfs_target_ids_write(struct file *file,
goto unlock_out;
}
- /* remove targets with previously-set primitive */
- damon_set_targets(ctx, NULL, 0);
+ /* remove previously set targets */
+ damon_for_each_target_safe(t, next_t, ctx) {
+ if (targetid_is_pid(ctx))
+ put_pid((struct pid *)t->id);
+ damon_destroy_target(t);
+ }
/* Configure the context for the address space type */
if (id_is_pid)
@@ -452,7 +455,7 @@ static ssize_t dbgfs_init_regions_read(struct file *file, char __user *buf,
char *kbuf;
ssize_t len;
- kbuf = kmalloc(count, GFP_KERNEL);
+ kbuf = kmalloc(count, GFP_KERNEL | __GFP_NOWARN);
if (!kbuf)
return -ENOMEM;
@@ -578,7 +581,7 @@ static ssize_t dbgfs_kdamond_pid_read(struct file *file,
char *kbuf;
ssize_t len;
- kbuf = kmalloc(count, GFP_KERNEL);
+ kbuf = kmalloc(count, GFP_KERNEL | __GFP_NOWARN);
if (!kbuf)
return -ENOMEM;
@@ -652,10 +655,12 @@ static void dbgfs_before_terminate(struct damon_ctx *ctx)
if (!targetid_is_pid(ctx))
return;
+ mutex_lock(&ctx->kdamond_lock);
damon_for_each_target_safe(t, next, ctx) {
put_pid((struct pid *)t->id);
damon_destroy_target(t);
}
+ mutex_unlock(&ctx->kdamond_lock);
}
static struct damon_ctx *dbgfs_new_ctx(void)
@@ -877,12 +882,14 @@ static ssize_t dbgfs_monitor_on_write(struct file *file,
return -EINVAL;
}
+ mutex_lock(&damon_dbgfs_lock);
if (!strncmp(kbuf, "on", count)) {
int i;
for (i = 0; i < dbgfs_nr_ctxs; i++) {
if (damon_targets_empty(dbgfs_ctxs[i])) {
kfree(kbuf);
+ mutex_unlock(&damon_dbgfs_lock);
return -EINVAL;
}
}
@@ -892,6 +899,7 @@ static ssize_t dbgfs_monitor_on_write(struct file *file,
} else {
ret = -EINVAL;
}
+ mutex_unlock(&damon_dbgfs_lock);
if (!ret)
ret = count;
@@ -944,15 +952,16 @@ static int __init __damon_dbgfs_init(void)
static int __init damon_dbgfs_init(void)
{
- int rc;
+ int rc = -ENOMEM;
+ mutex_lock(&damon_dbgfs_lock);
dbgfs_ctxs = kmalloc(sizeof(*dbgfs_ctxs), GFP_KERNEL);
if (!dbgfs_ctxs)
- return -ENOMEM;
+ goto out;
dbgfs_ctxs[0] = dbgfs_new_ctx();
if (!dbgfs_ctxs[0]) {
kfree(dbgfs_ctxs);
- return -ENOMEM;
+ goto out;
}
dbgfs_nr_ctxs = 1;
@@ -963,6 +972,8 @@ static int __init damon_dbgfs_init(void)
pr_err("%s: dbgfs init failed\n", __func__);
}
+out:
+ mutex_unlock(&damon_dbgfs_lock);
return rc;
}
diff --git a/mm/damon/vaddr-test.h b/mm/damon/vaddr-test.h
index ecfd0b2ed222..6a1b9272ea12 100644
--- a/mm/damon/vaddr-test.h
+++ b/mm/damon/vaddr-test.h
@@ -135,7 +135,6 @@ static void damon_do_test_apply_three_regions(struct kunit *test,
struct damon_addr_range *three_regions,
unsigned long *expected, int nr_expected)
{
- struct damon_ctx *ctx = damon_new_ctx();
struct damon_target *t;
struct damon_region *r;
int i;
@@ -145,7 +144,6 @@ static void damon_do_test_apply_three_regions(struct kunit *test,
r = damon_new_region(regions[i * 2], regions[i * 2 + 1]);
damon_add_region(r, t);
}
- damon_add_target(ctx, t);
damon_va_apply_three_regions(t, three_regions);
@@ -154,8 +152,6 @@ static void damon_do_test_apply_three_regions(struct kunit *test,
KUNIT_EXPECT_EQ(test, r->ar.start, expected[i * 2]);
KUNIT_EXPECT_EQ(test, r->ar.end, expected[i * 2 + 1]);
}
-
- damon_destroy_ctx(ctx);
}
/*
@@ -252,60 +248,59 @@ static void damon_test_apply_three_regions4(struct kunit *test)
new_three_regions, expected, ARRAY_SIZE(expected));
}
-static void damon_test_split_evenly(struct kunit *test)
+static void damon_test_split_evenly_fail(struct kunit *test,
+ unsigned long start, unsigned long end, unsigned int nr_pieces)
{
- struct damon_ctx *c = damon_new_ctx();
- struct damon_target *t;
- struct damon_region *r;
- unsigned long i;
-
- KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(NULL, NULL, 5),
- -EINVAL);
-
- t = damon_new_target(42);
- r = damon_new_region(0, 100);
- KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 0), -EINVAL);
+ struct damon_target *t = damon_new_target(42);
+ struct damon_region *r = damon_new_region(start, end);
damon_add_region(r, t);
- KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 10), 0);
- KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 10u);
+ KUNIT_EXPECT_EQ(test,
+ damon_va_evenly_split_region(t, r, nr_pieces), -EINVAL);
+ KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 1u);
- i = 0;
damon_for_each_region(r, t) {
- KUNIT_EXPECT_EQ(test, r->ar.start, i++ * 10);
- KUNIT_EXPECT_EQ(test, r->ar.end, i * 10);
+ KUNIT_EXPECT_EQ(test, r->ar.start, start);
+ KUNIT_EXPECT_EQ(test, r->ar.end, end);
}
+
damon_free_target(t);
+}
+
+static void damon_test_split_evenly_succ(struct kunit *test,
+ unsigned long start, unsigned long end, unsigned int nr_pieces)
+{
+ struct damon_target *t = damon_new_target(42);
+ struct damon_region *r = damon_new_region(start, end);
+ unsigned long expected_width = (end - start) / nr_pieces;
+ unsigned long i = 0;
- t = damon_new_target(42);
- r = damon_new_region(5, 59);
damon_add_region(r, t);
- KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 5), 0);
- KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 5u);
+ KUNIT_EXPECT_EQ(test,
+ damon_va_evenly_split_region(t, r, nr_pieces), 0);
+ KUNIT_EXPECT_EQ(test, damon_nr_regions(t), nr_pieces);
- i = 0;
damon_for_each_region(r, t) {
- if (i == 4)
+ if (i == nr_pieces - 1)
break;
- KUNIT_EXPECT_EQ(test, r->ar.start, 5 + 10 * i++);
- KUNIT_EXPECT_EQ(test, r->ar.end, 5 + 10 * i);
+ KUNIT_EXPECT_EQ(test,
+ r->ar.start, start + i++ * expected_width);
+ KUNIT_EXPECT_EQ(test, r->ar.end, start + i * expected_width);
}
- KUNIT_EXPECT_EQ(test, r->ar.start, 5 + 10 * i);
- KUNIT_EXPECT_EQ(test, r->ar.end, 59ul);
+ KUNIT_EXPECT_EQ(test, r->ar.start, start + i * expected_width);
+ KUNIT_EXPECT_EQ(test, r->ar.end, end);
damon_free_target(t);
+}
- t = damon_new_target(42);
- r = damon_new_region(5, 6);
- damon_add_region(r, t);
- KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 2), -EINVAL);
- KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 1u);
+static void damon_test_split_evenly(struct kunit *test)
+{
+ KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(NULL, NULL, 5),
+ -EINVAL);
- damon_for_each_region(r, t) {
- KUNIT_EXPECT_EQ(test, r->ar.start, 5ul);
- KUNIT_EXPECT_EQ(test, r->ar.end, 6ul);
- }
- damon_free_target(t);
- damon_destroy_ctx(c);
+ damon_test_split_evenly_fail(test, 0, 100, 0);
+ damon_test_split_evenly_succ(test, 0, 100, 10);
+ damon_test_split_evenly_succ(test, 5, 59, 5);
+ damon_test_split_evenly_fail(test, 5, 6, 2);
}
static struct kunit_case damon_test_cases[] = {
diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c
index 35fe49080ee9..20a9a9d69eb1 100644
--- a/mm/damon/vaddr.c
+++ b/mm/damon/vaddr.c
@@ -13,6 +13,7 @@
#include <linux/mmu_notifier.h>
#include <linux/page_idle.h>
#include <linux/pagewalk.h>
+#include <linux/sched/mm.h>
#include "prmtv-common.h"
@@ -626,7 +627,6 @@ int damon_va_apply_scheme(struct damon_ctx *ctx, struct damon_target *t,
case DAMOS_STAT:
return 0;
default:
- pr_warn("Wrong action %d\n", scheme->action);
return -EINVAL;
}
diff --git a/mm/filemap.c b/mm/filemap.c
index daa0e23a6ee6..39c4c46c6133 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3253,8 +3253,6 @@ static struct page *next_uptodate_page(struct page *page,
goto skip;
if (!PageUptodate(page) || PageReadahead(page))
goto skip;
- if (PageHWPoison(page))
- goto skip;
if (!trylock_page(page))
goto skip;
if (page->mapping != mapping)
diff --git a/mm/highmem.c b/mm/highmem.c
index 88f65f155845..762679050c9a 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -359,7 +359,6 @@ void kunmap_high(struct page *page)
}
EXPORT_SYMBOL(kunmap_high);
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
void zero_user_segments(struct page *page, unsigned start1, unsigned end1,
unsigned start2, unsigned end2)
{
@@ -416,7 +415,6 @@ void zero_user_segments(struct page *page, unsigned start1, unsigned end1,
BUG_ON((start1 | start2 | end1 | end2) != 0);
}
EXPORT_SYMBOL(zero_user_segments);
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif /* CONFIG_HIGHMEM */
#ifdef CONFIG_KMAP_LOCAL
@@ -503,16 +501,22 @@ static inline int kmap_local_calc_idx(int idx)
static pte_t *__kmap_pte;
-static pte_t *kmap_get_pte(void)
+static pte_t *kmap_get_pte(unsigned long vaddr, int idx)
{
+ if (IS_ENABLED(CONFIG_KMAP_LOCAL_NON_LINEAR_PTE_ARRAY))
+ /*
+ * Set by the arch if __kmap_pte[-idx] does not produce
+ * the correct entry.
+ */
+ return virt_to_kpte(vaddr);
if (!__kmap_pte)
__kmap_pte = virt_to_kpte(__fix_to_virt(FIX_KMAP_BEGIN));
- return __kmap_pte;
+ return &__kmap_pte[-idx];
}
void *__kmap_local_pfn_prot(unsigned long pfn, pgprot_t prot)
{
- pte_t pteval, *kmap_pte = kmap_get_pte();
+ pte_t pteval, *kmap_pte;
unsigned long vaddr;
int idx;
@@ -524,9 +528,10 @@ void *__kmap_local_pfn_prot(unsigned long pfn, pgprot_t prot)
preempt_disable();
idx = arch_kmap_local_map_idx(kmap_local_idx_push(), pfn);
vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
- BUG_ON(!pte_none(*(kmap_pte - idx)));
+ kmap_pte = kmap_get_pte(vaddr, idx);
+ BUG_ON(!pte_none(*kmap_pte));
pteval = pfn_pte(pfn, prot);
- arch_kmap_local_set_pte(&init_mm, vaddr, kmap_pte - idx, pteval);
+ arch_kmap_local_set_pte(&init_mm, vaddr, kmap_pte, pteval);
arch_kmap_local_post_map(vaddr, pteval);
current->kmap_ctrl.pteval[kmap_local_idx()] = pteval;
preempt_enable();
@@ -559,7 +564,7 @@ EXPORT_SYMBOL(__kmap_local_page_prot);
void kunmap_local_indexed(void *vaddr)
{
unsigned long addr = (unsigned long) vaddr & PAGE_MASK;
- pte_t *kmap_pte = kmap_get_pte();
+ pte_t *kmap_pte;
int idx;
if (addr < __fix_to_virt(FIX_KMAP_END) ||
@@ -584,8 +589,9 @@ void kunmap_local_indexed(void *vaddr)
idx = arch_kmap_local_unmap_idx(kmap_local_idx(), addr);
WARN_ON_ONCE(addr != __fix_to_virt(FIX_KMAP_BEGIN + idx));
+ kmap_pte = kmap_get_pte(addr, idx);
arch_kmap_local_pre_unmap(addr);
- pte_clear(&init_mm, addr, kmap_pte - idx);
+ pte_clear(&init_mm, addr, kmap_pte);
arch_kmap_local_post_unmap(addr);
current->kmap_ctrl.pteval[kmap_local_idx()] = __pte(0);
kmap_local_idx_pop();
@@ -607,7 +613,7 @@ EXPORT_SYMBOL(kunmap_local_indexed);
void __kmap_local_sched_out(void)
{
struct task_struct *tsk = current;
- pte_t *kmap_pte = kmap_get_pte();
+ pte_t *kmap_pte;
int i;
/* Clear kmaps */
@@ -634,8 +640,9 @@ void __kmap_local_sched_out(void)
idx = arch_kmap_local_map_idx(i, pte_pfn(pteval));
addr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
+ kmap_pte = kmap_get_pte(addr, idx);
arch_kmap_local_pre_unmap(addr);
- pte_clear(&init_mm, addr, kmap_pte - idx);
+ pte_clear(&init_mm, addr, kmap_pte);
arch_kmap_local_post_unmap(addr);
}
}
@@ -643,7 +650,7 @@ void __kmap_local_sched_out(void)
void __kmap_local_sched_in(void)
{
struct task_struct *tsk = current;
- pte_t *kmap_pte = kmap_get_pte();
+ pte_t *kmap_pte;
int i;
/* Restore kmaps */
@@ -663,7 +670,8 @@ void __kmap_local_sched_in(void)
/* See comment in __kmap_local_sched_out() */
idx = arch_kmap_local_map_idx(i, pte_pfn(pteval));
addr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
- set_pte_at(&init_mm, addr, kmap_pte - idx, pteval);
+ kmap_pte = kmap_get_pte(addr, idx);
+ set_pte_at(&init_mm, addr, kmap_pte, pteval);
arch_kmap_local_post_map(addr, pteval);
}
}
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index e09159c957e3..a1baa198519a 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1037,8 +1037,10 @@ void clear_vma_resv_huge_pages(struct vm_area_struct *vma)
*/
struct resv_map *reservations = vma_resv_map(vma);
- if (reservations && is_vma_resv_set(vma, HPAGE_RESV_OWNER))
+ if (reservations && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
+ resv_map_put_hugetlb_cgroup_uncharge_info(reservations);
kref_put(&reservations->refs, resv_map_release);
+ }
reset_vma_resv_huge_pages(vma);
}
@@ -2971,7 +2973,7 @@ int __alloc_bootmem_huge_page(struct hstate *h, int nid)
struct huge_bootmem_page *m = NULL; /* initialize for clang */
int nr_nodes, node;
- if (nid >= nr_online_nodes)
+ if (nid != NUMA_NO_NODE && nid >= nr_online_nodes)
return 0;
/* do node specific alloc */
if (nid != NUMA_NO_NODE) {
@@ -4917,9 +4919,9 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma,
move_huge_pte(vma, old_addr, new_addr, src_pte);
}
- i_mmap_unlock_write(mapping);
flush_tlb_range(vma, old_end - len, old_end);
mmu_notifier_invalidate_range_end(&range);
+ i_mmap_unlock_write(mapping);
return len + old_addr - old_end;
}
@@ -4937,6 +4939,7 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct
struct hstate *h = hstate_vma(vma);
unsigned long sz = huge_page_size(h);
struct mmu_notifier_range range;
+ bool force_flush = false;
WARN_ON(!is_vm_hugetlb_page(vma));
BUG_ON(start & ~huge_page_mask(h));
@@ -4965,10 +4968,8 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct
ptl = huge_pte_lock(h, mm, ptep);
if (huge_pmd_unshare(mm, vma, &address, ptep)) {
spin_unlock(ptl);
- /*
- * We just unmapped a page of PMDs by clearing a PUD.
- * The caller's TLB flush range should cover this area.
- */
+ tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE);
+ force_flush = true;
continue;
}
@@ -5025,6 +5026,22 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct
}
mmu_notifier_invalidate_range_end(&range);
tlb_end_vma(tlb, vma);
+
+ /*
+ * If we unshared PMDs, the TLB flush was not recorded in mmu_gather. We
+ * could defer the flush until now, since by holding i_mmap_rwsem we
+ * guaranteed that the last refernece would not be dropped. But we must
+ * do the flushing before we return, as otherwise i_mmap_rwsem will be
+ * dropped and the last reference to the shared PMDs page might be
+ * dropped as well.
+ *
+ * In theory we could defer the freeing of the PMD pages as well, but
+ * huge_pmd_unshare() relies on the exact page_count for the PMD page to
+ * detect sharing, so we cannot defer the release of the page either.
+ * Instead, do flush now.
+ */
+ if (force_flush)
+ tlb_flush_mmu_tlbonly(tlb);
}
void __unmap_hugepage_range_final(struct mmu_gather *tlb,
@@ -5734,13 +5751,14 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
int ret = -ENOMEM;
struct page *page;
int writable;
- bool new_pagecache_page = false;
+ bool page_in_pagecache = false;
if (is_continue) {
ret = -EFAULT;
page = find_lock_page(mapping, idx);
if (!page)
goto out;
+ page_in_pagecache = true;
} else if (!*pagep) {
/* If a page already exists, then it's UFFDIO_COPY for
* a non-missing case. Return -EEXIST.
@@ -5828,7 +5846,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
ret = huge_add_to_page_cache(page, mapping, idx);
if (ret)
goto out_release_nounlock;
- new_pagecache_page = true;
+ page_in_pagecache = true;
}
ptl = huge_pte_lockptr(h, dst_mm, dst_pte);
@@ -5892,7 +5910,7 @@ out_release_unlock:
if (vm_shared || is_continue)
unlock_page(page);
out_release_nounlock:
- if (!new_pagecache_page)
+ if (!page_in_pagecache)
restore_reserve_on_error(h, dst_vma, dst_addr, page);
put_page(page);
goto out;
diff --git a/mm/kfence/core.c b/mm/kfence/core.c
index 09945784df9e..a19154a8d196 100644
--- a/mm/kfence/core.c
+++ b/mm/kfence/core.c
@@ -683,6 +683,7 @@ static const struct file_operations objects_fops = {
.open = open_objects,
.read = seq_read,
.llseek = seq_lseek,
+ .release = seq_release,
};
static int __init kfence_debugfs_init(void)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 781605e92015..2ed5f2a0879d 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -776,24 +776,6 @@ void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val)
rcu_read_unlock();
}
-/*
- * mod_objcg_mlstate() may be called with irq enabled, so
- * mod_memcg_lruvec_state() should be used.
- */
-static inline void mod_objcg_mlstate(struct obj_cgroup *objcg,
- struct pglist_data *pgdat,
- enum node_stat_item idx, int nr)
-{
- struct mem_cgroup *memcg;
- struct lruvec *lruvec;
-
- rcu_read_lock();
- memcg = obj_cgroup_memcg(objcg);
- lruvec = mem_cgroup_lruvec(memcg, pgdat);
- mod_memcg_lruvec_state(lruvec, idx, nr);
- rcu_read_unlock();
-}
-
/**
* __count_memcg_events - account VM events in a cgroup
* @memcg: the memory cgroup
@@ -2137,41 +2119,6 @@ static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
}
#endif
-/*
- * Most kmem_cache_alloc() calls are from user context. The irq disable/enable
- * sequence used in this case to access content from object stock is slow.
- * To optimize for user context access, there are now two object stocks for
- * task context and interrupt context access respectively.
- *
- * The task context object stock can be accessed by disabling preemption only
- * which is cheap in non-preempt kernel. The interrupt context object stock
- * can only be accessed after disabling interrupt. User context code can
- * access interrupt object stock, but not vice versa.
- */
-static inline struct obj_stock *get_obj_stock(unsigned long *pflags)
-{
- struct memcg_stock_pcp *stock;
-
- if (likely(in_task())) {
- *pflags = 0UL;
- preempt_disable();
- stock = this_cpu_ptr(&memcg_stock);
- return &stock->task_obj;
- }
-
- local_irq_save(*pflags);
- stock = this_cpu_ptr(&memcg_stock);
- return &stock->irq_obj;
-}
-
-static inline void put_obj_stock(unsigned long flags)
-{
- if (likely(in_task()))
- preempt_enable();
- else
- local_irq_restore(flags);
-}
-
/**
* consume_stock: Try to consume stocked charge on this cpu.
* @memcg: memcg to consume from.
@@ -2816,6 +2763,59 @@ retry:
*/
#define OBJCGS_CLEAR_MASK (__GFP_DMA | __GFP_RECLAIMABLE | __GFP_ACCOUNT)
+/*
+ * Most kmem_cache_alloc() calls are from user context. The irq disable/enable
+ * sequence used in this case to access content from object stock is slow.
+ * To optimize for user context access, there are now two object stocks for
+ * task context and interrupt context access respectively.
+ *
+ * The task context object stock can be accessed by disabling preemption only
+ * which is cheap in non-preempt kernel. The interrupt context object stock
+ * can only be accessed after disabling interrupt. User context code can
+ * access interrupt object stock, but not vice versa.
+ */
+static inline struct obj_stock *get_obj_stock(unsigned long *pflags)
+{
+ struct memcg_stock_pcp *stock;
+
+ if (likely(in_task())) {
+ *pflags = 0UL;
+ preempt_disable();
+ stock = this_cpu_ptr(&memcg_stock);
+ return &stock->task_obj;
+ }
+
+ local_irq_save(*pflags);
+ stock = this_cpu_ptr(&memcg_stock);
+ return &stock->irq_obj;
+}
+
+static inline void put_obj_stock(unsigned long flags)
+{
+ if (likely(in_task()))
+ preempt_enable();
+ else
+ local_irq_restore(flags);
+}
+
+/*
+ * mod_objcg_mlstate() may be called with irq enabled, so
+ * mod_memcg_lruvec_state() should be used.
+ */
+static inline void mod_objcg_mlstate(struct obj_cgroup *objcg,
+ struct pglist_data *pgdat,
+ enum node_stat_item idx, int nr)
+{
+ struct mem_cgroup *memcg;
+ struct lruvec *lruvec;
+
+ rcu_read_lock();
+ memcg = obj_cgroup_memcg(objcg);
+ lruvec = mem_cgroup_lruvec(memcg, pgdat);
+ mod_memcg_lruvec_state(lruvec, idx, nr);
+ rcu_read_unlock();
+}
+
int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
gfp_t gfp, bool new_page)
{
@@ -5558,7 +5558,7 @@ static int mem_cgroup_move_account(struct page *page,
VM_BUG_ON(from == to);
VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
- VM_BUG_ON(compound && !folio_test_multi(folio));
+ VM_BUG_ON(compound && !folio_test_large(folio));
/*
* Prevent mem_cgroup_migrate() from looking at
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 07c875fdeaf0..3a274468f193 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1470,17 +1470,12 @@ static int memory_failure_hugetlb(unsigned long pfn, int flags)
if (!(flags & MF_COUNT_INCREASED)) {
res = get_hwpoison_page(p, flags);
if (!res) {
- /*
- * Check "filter hit" and "race with other subpage."
- */
lock_page(head);
- if (PageHWPoison(head)) {
- if ((hwpoison_filter(p) && TestClearPageHWPoison(p))
- || (p != head && TestSetPageHWPoison(head))) {
+ if (hwpoison_filter(p)) {
+ if (TestClearPageHWPoison(head))
num_poisoned_pages_dec();
- unlock_page(head);
- return 0;
- }
+ unlock_page(head);
+ return 0;
}
unlock_page(head);
res = MF_FAILED;
@@ -2239,6 +2234,7 @@ retry:
} else if (ret == 0) {
if (soft_offline_free_page(page) && try_again) {
try_again = false;
+ flags &= ~MF_COUNT_INCREASED;
goto retry;
}
}
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 852041f6be41..2a9627dc784c 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -35,6 +35,7 @@
#include <linux/memblock.h>
#include <linux/compaction.h>
#include <linux/rmap.h>
+#include <linux/module.h>
#include <asm/tlbflush.h>
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 10e9c87260ed..f6248affaf38 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2140,8 +2140,7 @@ struct page *alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
* memory with both reclaim and compact as well.
*/
if (!page && (gfp & __GFP_DIRECT_RECLAIM))
- page = __alloc_pages_node(hpage_node,
- gfp, order);
+ page = __alloc_pages(gfp, order, hpage_node, nmask);
goto out;
}
diff --git a/mm/shmem.c b/mm/shmem.c
index dc038ce78700..18f93c2d68f1 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2303,6 +2303,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
INIT_LIST_HEAD(&info->swaplist);
simple_xattrs_init(&info->xattrs);
cache_no_acl(inode);
+ mapping_set_large_folios(inode->i_mapping);
switch (mode & S_IFMT) {
default:
@@ -3870,7 +3871,7 @@ static struct file_system_type shmem_fs_type = {
.parameters = shmem_fs_parameters,
#endif
.kill_sb = kill_litter_super,
- .fs_flags = FS_USERNS_MOUNT | FS_THP_SUPPORT,
+ .fs_flags = FS_USERNS_MOUNT,
};
int __init shmem_init(void)
diff --git a/mm/slab.c b/mm/slab.c
index da132a9ae6f8..ca4822f6b2b6 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3733,14 +3733,13 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp)
if (!cachep)
return;
+ trace_kmem_cache_free(_RET_IP_, objp, cachep->name);
local_irq_save(flags);
debug_check_no_locks_freed(objp, cachep->object_size);
if (!(cachep->flags & SLAB_DEBUG_OBJECTS))
debug_check_no_obj_freed(objp, cachep->object_size);
__cache_free(cachep, objp, _RET_IP_);
local_irq_restore(flags);
-
- trace_kmem_cache_free(_RET_IP_, objp, cachep->name);
}
EXPORT_SYMBOL(kmem_cache_free);
diff --git a/mm/slab.h b/mm/slab.h
index 58c01a34e5b8..56ad7eea3ddf 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -147,7 +147,7 @@ static inline slab_flags_t kmem_cache_flags(unsigned int object_size,
#define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE | SLAB_RECLAIM_ACCOUNT | \
SLAB_TEMPORARY | SLAB_ACCOUNT)
#else
-#define SLAB_CACHE_FLAGS (0)
+#define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE)
#endif
/* Common flags available with current configuration */
diff --git a/mm/slob.c b/mm/slob.c
index 74d3f6e60666..03deee1e6a94 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -666,6 +666,7 @@ static void kmem_rcu_free(struct rcu_head *head)
void kmem_cache_free(struct kmem_cache *c, void *b)
{
kmemleak_free_recursive(b, c->flags);
+ trace_kmem_cache_free(_RET_IP_, b, c->name);
if (unlikely(c->flags & SLAB_TYPESAFE_BY_RCU)) {
struct slob_rcu *slob_rcu;
slob_rcu = b + (c->size - sizeof(struct slob_rcu));
@@ -674,8 +675,6 @@ void kmem_cache_free(struct kmem_cache *c, void *b)
} else {
__kmem_cache_free(b, c->size);
}
-
- trace_kmem_cache_free(_RET_IP_, b, c->name);
}
EXPORT_SYMBOL(kmem_cache_free);
diff --git a/mm/slub.c b/mm/slub.c
index f7368bfffb7a..abe7db581d68 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3526,8 +3526,8 @@ void kmem_cache_free(struct kmem_cache *s, void *x)
s = cache_from_obj(s, x);
if (!s)
return;
- slab_free(s, virt_to_head_page(x), x, NULL, 1, _RET_IP_);
trace_kmem_cache_free(_RET_IP_, x, s->name);
+ slab_free(s, virt_to_head_page(x), x, NULL, 1, _RET_IP_);
}
EXPORT_SYMBOL(kmem_cache_free);
@@ -5081,6 +5081,7 @@ struct loc_track {
unsigned long max;
unsigned long count;
struct location *loc;
+ loff_t idx;
};
static struct dentry *slab_debugfs_root;
@@ -6052,11 +6053,11 @@ __initcall(slab_sysfs_init);
#if defined(CONFIG_SLUB_DEBUG) && defined(CONFIG_DEBUG_FS)
static int slab_debugfs_show(struct seq_file *seq, void *v)
{
-
- struct location *l;
- unsigned int idx = *(unsigned int *)v;
struct loc_track *t = seq->private;
+ struct location *l;
+ unsigned long idx;
+ idx = (unsigned long) t->idx;
if (idx < t->count) {
l = &t->loc[idx];
@@ -6105,16 +6106,18 @@ static void *slab_debugfs_next(struct seq_file *seq, void *v, loff_t *ppos)
{
struct loc_track *t = seq->private;
- v = ppos;
- ++*ppos;
+ t->idx = ++(*ppos);
if (*ppos <= t->count)
- return v;
+ return ppos;
return NULL;
}
static void *slab_debugfs_start(struct seq_file *seq, loff_t *ppos)
{
+ struct loc_track *t = seq->private;
+
+ t->idx = *ppos;
return ppos;
}
diff --git a/mm/swap.c b/mm/swap.c
index 1841c24682f8..e8c9dc6d0377 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -156,6 +156,7 @@ void put_pages_list(struct list_head *pages)
}
free_unref_page_list(pages);
+ INIT_LIST_HEAD(pages);
}
EXPORT_SYMBOL(put_pages_list);
diff --git a/mm/swap_slots.c b/mm/swap_slots.c
index 16f706c55d92..2b5531840583 100644
--- a/mm/swap_slots.c
+++ b/mm/swap_slots.c
@@ -30,6 +30,7 @@
#include <linux/swap_slots.h>
#include <linux/cpu.h>
#include <linux/cpumask.h>
+#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/mutex.h>
#include <linux/mm.h>
diff --git a/mm/util.c b/mm/util.c
index e58151a61255..741ba32a43ac 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -670,7 +670,7 @@ bool folio_mapped(struct folio *folio)
{
long i, nr;
- if (folio_test_single(folio))
+ if (!folio_test_large(folio))
return atomic_read(&folio->_mapcount) >= 0;
if (atomic_read(folio_mapcount_ptr(folio)) >= 0)
return true;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index fb9584641ac7..700434db5735 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1021,6 +1021,39 @@ static void handle_write_error(struct address_space *mapping,
unlock_page(page);
}
+static bool skip_throttle_noprogress(pg_data_t *pgdat)
+{
+ int reclaimable = 0, write_pending = 0;
+ int i;
+
+ /*
+ * If kswapd is disabled, reschedule if necessary but do not
+ * throttle as the system is likely near OOM.
+ */
+ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
+ return true;
+
+ /*
+ * If there are a lot of dirty/writeback pages then do not
+ * throttle as throttling will occur when the pages cycle
+ * towards the end of the LRU if still under writeback.
+ */
+ for (i = 0; i < MAX_NR_ZONES; i++) {
+ struct zone *zone = pgdat->node_zones + i;
+
+ if (!populated_zone(zone))
+ continue;
+
+ reclaimable += zone_reclaimable_pages(zone);
+ write_pending += zone_page_state_snapshot(zone,
+ NR_ZONE_WRITE_PENDING);
+ }
+ if (2 * write_pending <= reclaimable)
+ return true;
+
+ return false;
+}
+
void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason)
{
wait_queue_head_t *wqh = &pgdat->reclaim_wait[reason];
@@ -1056,8 +1089,16 @@ void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason)
}
break;
+ case VMSCAN_THROTTLE_CONGESTED:
+ fallthrough;
case VMSCAN_THROTTLE_NOPROGRESS:
- timeout = HZ/2;
+ if (skip_throttle_noprogress(pgdat)) {
+ cond_resched();
+ return;
+ }
+
+ timeout = 1;
+
break;
case VMSCAN_THROTTLE_ISOLATED:
timeout = HZ/50;
@@ -3321,7 +3362,7 @@ again:
if (!current_is_kswapd() && current_may_throttle() &&
!sc->hibernation_mode &&
test_bit(LRUVEC_CONGESTED, &target_lruvec->flags))
- reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK);
+ reclaim_throttle(pgdat, VMSCAN_THROTTLE_CONGESTED);
if (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed,
sc))
@@ -3386,16 +3427,16 @@ static void consider_reclaim_throttle(pg_data_t *pgdat, struct scan_control *sc)
}
/*
- * Do not throttle kswapd on NOPROGRESS as it will throttle on
- * VMSCAN_THROTTLE_WRITEBACK if there are too many pages under
- * writeback and marked for immediate reclaim at the tail of
- * the LRU.
+ * Do not throttle kswapd or cgroup reclaim on NOPROGRESS as it will
+ * throttle on VMSCAN_THROTTLE_WRITEBACK if there are too many pages
+ * under writeback and marked for immediate reclaim at the tail of the
+ * LRU.
*/
- if (current_is_kswapd())
+ if (current_is_kswapd() || cgroup_reclaim(sc))
return;
/* Throttle if making no progress at high prioities. */
- if (sc->priority < DEF_PRIORITY - 2)
+ if (sc->priority == 1 && !sc->nr_reclaimed)
reclaim_throttle(pgdat, VMSCAN_THROTTLE_NOPROGRESS);
}
@@ -3415,6 +3456,7 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
unsigned long nr_soft_scanned;
gfp_t orig_mask;
pg_data_t *last_pgdat = NULL;
+ pg_data_t *first_pgdat = NULL;
/*
* If the number of buffer_heads in the machine exceeds the maximum
@@ -3478,14 +3520,19 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
/* need some check for avoid more shrink_zone() */
}
+ if (!first_pgdat)
+ first_pgdat = zone->zone_pgdat;
+
/* See comment about same check for global reclaim above */
if (zone->zone_pgdat == last_pgdat)
continue;
last_pgdat = zone->zone_pgdat;
shrink_node(zone->zone_pgdat, sc);
- consider_reclaim_throttle(zone->zone_pgdat, sc);
}
+ if (first_pgdat)
+ consider_reclaim_throttle(first_pgdat, sc);
+
/*
* Restore to original mask to avoid the impact on the caller if we
* promoted it to __GFP_HIGHMEM.
generated by cgit (git 2.34.1) at 2024-04-19 00:52:46 +0000