summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/memcontrol.c127
-rw-r--r--mm/percpu.c83
-rw-r--r--mm/rmap.c4
3 files changed, 126 insertions, 88 deletions
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e2b98a6875c0..f99f5991d6bb 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -313,7 +313,8 @@ soft_limit_tree_from_page(struct page *page)
static void
__mem_cgroup_insert_exceeded(struct mem_cgroup *mem,
struct mem_cgroup_per_zone *mz,
- struct mem_cgroup_tree_per_zone *mctz)
+ struct mem_cgroup_tree_per_zone *mctz,
+ unsigned long long new_usage_in_excess)
{
struct rb_node **p = &mctz->rb_root.rb_node;
struct rb_node *parent = NULL;
@@ -322,7 +323,9 @@ __mem_cgroup_insert_exceeded(struct mem_cgroup *mem,
if (mz->on_tree)
return;
- mz->usage_in_excess = res_counter_soft_limit_excess(&mem->res);
+ mz->usage_in_excess = new_usage_in_excess;
+ if (!mz->usage_in_excess)
+ return;
while (*p) {
parent = *p;
mz_node = rb_entry(parent, struct mem_cgroup_per_zone,
@@ -353,16 +356,6 @@ __mem_cgroup_remove_exceeded(struct mem_cgroup *mem,
}
static void
-mem_cgroup_insert_exceeded(struct mem_cgroup *mem,
- struct mem_cgroup_per_zone *mz,
- struct mem_cgroup_tree_per_zone *mctz)
-{
- spin_lock(&mctz->lock);
- __mem_cgroup_insert_exceeded(mem, mz, mctz);
- spin_unlock(&mctz->lock);
-}
-
-static void
mem_cgroup_remove_exceeded(struct mem_cgroup *mem,
struct mem_cgroup_per_zone *mz,
struct mem_cgroup_tree_per_zone *mctz)
@@ -392,34 +385,36 @@ static bool mem_cgroup_soft_limit_check(struct mem_cgroup *mem)
static void mem_cgroup_update_tree(struct mem_cgroup *mem, struct page *page)
{
- unsigned long long prev_usage_in_excess, new_usage_in_excess;
- bool updated_tree = false;
+ unsigned long long excess;
struct mem_cgroup_per_zone *mz;
struct mem_cgroup_tree_per_zone *mctz;
-
- mz = mem_cgroup_zoneinfo(mem, page_to_nid(page), page_zonenum(page));
+ int nid = page_to_nid(page);
+ int zid = page_zonenum(page);
mctz = soft_limit_tree_from_page(page);
/*
- * We do updates in lazy mode, mem's are removed
- * lazily from the per-zone, per-node rb tree
+ * Necessary to update all ancestors when hierarchy is used.
+ * because their event counter is not touched.
*/
- prev_usage_in_excess = mz->usage_in_excess;
-
- new_usage_in_excess = res_counter_soft_limit_excess(&mem->res);
- if (prev_usage_in_excess) {
- mem_cgroup_remove_exceeded(mem, mz, mctz);
- updated_tree = true;
- }
- if (!new_usage_in_excess)
- goto done;
- mem_cgroup_insert_exceeded(mem, mz, mctz);
-
-done:
- if (updated_tree) {
- spin_lock(&mctz->lock);
- mz->usage_in_excess = new_usage_in_excess;
- spin_unlock(&mctz->lock);
+ for (; mem; mem = parent_mem_cgroup(mem)) {
+ mz = mem_cgroup_zoneinfo(mem, nid, zid);
+ excess = res_counter_soft_limit_excess(&mem->res);
+ /*
+ * We have to update the tree if mz is on RB-tree or
+ * mem is over its softlimit.
+ */
+ if (excess || mz->on_tree) {
+ spin_lock(&mctz->lock);
+ /* if on-tree, remove it */
+ if (mz->on_tree)
+ __mem_cgroup_remove_exceeded(mem, mz, mctz);
+ /*
+ * Insert again. mz->usage_in_excess will be updated.
+ * If excess is 0, no tree ops.
+ */
+ __mem_cgroup_insert_exceeded(mem, mz, mctz, excess);
+ spin_unlock(&mctz->lock);
+ }
}
}
@@ -447,9 +442,10 @@ static struct mem_cgroup_per_zone *
__mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
{
struct rb_node *rightmost = NULL;
- struct mem_cgroup_per_zone *mz = NULL;
+ struct mem_cgroup_per_zone *mz;
retry:
+ mz = NULL;
rightmost = rb_last(&mctz->rb_root);
if (!rightmost)
goto done; /* Nothing to reclaim from */
@@ -1270,9 +1266,9 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
gfp_t gfp_mask, struct mem_cgroup **memcg,
bool oom, struct page *page)
{
- struct mem_cgroup *mem, *mem_over_limit, *mem_over_soft_limit;
+ struct mem_cgroup *mem, *mem_over_limit;
int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
- struct res_counter *fail_res, *soft_fail_res = NULL;
+ struct res_counter *fail_res;
if (unlikely(test_thread_flag(TIF_MEMDIE))) {
/* Don't account this! */
@@ -1304,17 +1300,16 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
if (mem_cgroup_is_root(mem))
goto done;
- ret = res_counter_charge(&mem->res, PAGE_SIZE, &fail_res,
- &soft_fail_res);
+ ret = res_counter_charge(&mem->res, PAGE_SIZE, &fail_res);
if (likely(!ret)) {
if (!do_swap_account)
break;
ret = res_counter_charge(&mem->memsw, PAGE_SIZE,
- &fail_res, NULL);
+ &fail_res);
if (likely(!ret))
break;
/* mem+swap counter fails */
- res_counter_uncharge(&mem->res, PAGE_SIZE, NULL);
+ res_counter_uncharge(&mem->res, PAGE_SIZE);
flags |= MEM_CGROUP_RECLAIM_NOSWAP;
mem_over_limit = mem_cgroup_from_res_counter(fail_res,
memsw);
@@ -1353,16 +1348,11 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
}
}
/*
- * Insert just the ancestor, we should trickle down to the correct
- * cgroup for reclaim, since the other nodes will be below their
- * soft limit
+ * Insert ancestor (and ancestor's ancestors), to softlimit RB-tree.
+ * if they exceeds softlimit.
*/
- if (soft_fail_res) {
- mem_over_soft_limit =
- mem_cgroup_from_res_counter(soft_fail_res, res);
- if (mem_cgroup_soft_limit_check(mem_over_soft_limit))
- mem_cgroup_update_tree(mem_over_soft_limit, page);
- }
+ if (mem_cgroup_soft_limit_check(mem))
+ mem_cgroup_update_tree(mem, page);
done:
return 0;
nomem:
@@ -1437,10 +1427,9 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *mem,
if (unlikely(PageCgroupUsed(pc))) {
unlock_page_cgroup(pc);
if (!mem_cgroup_is_root(mem)) {
- res_counter_uncharge(&mem->res, PAGE_SIZE, NULL);
+ res_counter_uncharge(&mem->res, PAGE_SIZE);
if (do_swap_account)
- res_counter_uncharge(&mem->memsw, PAGE_SIZE,
- NULL);
+ res_counter_uncharge(&mem->memsw, PAGE_SIZE);
}
css_put(&mem->css);
return;
@@ -1519,7 +1508,7 @@ static int mem_cgroup_move_account(struct page_cgroup *pc,
goto out;
if (!mem_cgroup_is_root(from))
- res_counter_uncharge(&from->res, PAGE_SIZE, NULL);
+ res_counter_uncharge(&from->res, PAGE_SIZE);
mem_cgroup_charge_statistics(from, pc, false);
page = pc->page;
@@ -1539,7 +1528,7 @@ static int mem_cgroup_move_account(struct page_cgroup *pc,
}
if (do_swap_account && !mem_cgroup_is_root(from))
- res_counter_uncharge(&from->memsw, PAGE_SIZE, NULL);
+ res_counter_uncharge(&from->memsw, PAGE_SIZE);
css_put(&from->css);
css_get(&to->css);
@@ -1610,9 +1599,9 @@ uncharge:
css_put(&parent->css);
/* uncharge if move fails */
if (!mem_cgroup_is_root(parent)) {
- res_counter_uncharge(&parent->res, PAGE_SIZE, NULL);
+ res_counter_uncharge(&parent->res, PAGE_SIZE);
if (do_swap_account)
- res_counter_uncharge(&parent->memsw, PAGE_SIZE, NULL);
+ res_counter_uncharge(&parent->memsw, PAGE_SIZE);
}
return ret;
}
@@ -1803,8 +1792,7 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr,
* calling css_tryget
*/
if (!mem_cgroup_is_root(memcg))
- res_counter_uncharge(&memcg->memsw, PAGE_SIZE,
- NULL);
+ res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
mem_cgroup_swap_statistics(memcg, false);
mem_cgroup_put(memcg);
}
@@ -1831,9 +1819,9 @@ void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *mem)
if (!mem)
return;
if (!mem_cgroup_is_root(mem)) {
- res_counter_uncharge(&mem->res, PAGE_SIZE, NULL);
+ res_counter_uncharge(&mem->res, PAGE_SIZE);
if (do_swap_account)
- res_counter_uncharge(&mem->memsw, PAGE_SIZE, NULL);
+ res_counter_uncharge(&mem->memsw, PAGE_SIZE);
}
css_put(&mem->css);
}
@@ -1848,7 +1836,6 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
struct page_cgroup *pc;
struct mem_cgroup *mem = NULL;
struct mem_cgroup_per_zone *mz;
- bool soft_limit_excess = false;
if (mem_cgroup_disabled())
return NULL;
@@ -1888,10 +1875,10 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
}
if (!mem_cgroup_is_root(mem)) {
- res_counter_uncharge(&mem->res, PAGE_SIZE, &soft_limit_excess);
+ res_counter_uncharge(&mem->res, PAGE_SIZE);
if (do_swap_account &&
(ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT))
- res_counter_uncharge(&mem->memsw, PAGE_SIZE, NULL);
+ res_counter_uncharge(&mem->memsw, PAGE_SIZE);
}
if (ctype == MEM_CGROUP_CHARGE_TYPE_SWAPOUT)
mem_cgroup_swap_statistics(mem, true);
@@ -1908,7 +1895,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
mz = page_cgroup_zoneinfo(pc);
unlock_page_cgroup(pc);
- if (soft_limit_excess && mem_cgroup_soft_limit_check(mem))
+ if (mem_cgroup_soft_limit_check(mem))
mem_cgroup_update_tree(mem, page);
/* at swapout, this memcg will be accessed to record to swap */
if (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT)
@@ -1986,7 +1973,7 @@ void mem_cgroup_uncharge_swap(swp_entry_t ent)
* This memcg can be obsolete one. We avoid calling css_tryget
*/
if (!mem_cgroup_is_root(memcg))
- res_counter_uncharge(&memcg->memsw, PAGE_SIZE, NULL);
+ res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
mem_cgroup_swap_statistics(memcg, false);
mem_cgroup_put(memcg);
}
@@ -2233,6 +2220,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
unsigned long reclaimed;
int loop = 0;
struct mem_cgroup_tree_per_zone *mctz;
+ unsigned long long excess;
if (order > 0)
return 0;
@@ -2284,9 +2272,8 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
break;
} while (1);
}
- mz->usage_in_excess =
- res_counter_soft_limit_excess(&mz->mem->res);
__mem_cgroup_remove_exceeded(mz->mem, mz, mctz);
+ excess = res_counter_soft_limit_excess(&mz->mem->res);
/*
* One school of thought says that we should not add
* back the node to the tree if reclaim returns 0.
@@ -2295,8 +2282,8 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
* memory to reclaim from. Consider this as a longer
* term TODO.
*/
- if (mz->usage_in_excess)
- __mem_cgroup_insert_exceeded(mz->mem, mz, mctz);
+ /* If excess == 0, no tree ops */
+ __mem_cgroup_insert_exceeded(mz->mem, mz, mctz, excess);
spin_unlock(&mctz->lock);
css_put(&mz->mem->css);
loop++;
diff --git a/mm/percpu.c b/mm/percpu.c
index 43d8cacfdaa5..4a048abad043 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1043,7 +1043,9 @@ static struct pcpu_chunk *alloc_pcpu_chunk(void)
*/
static void *pcpu_alloc(size_t size, size_t align, bool reserved)
{
+ static int warn_limit = 10;
struct pcpu_chunk *chunk;
+ const char *err;
int slot, off;
if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE)) {
@@ -1059,11 +1061,14 @@ static void *pcpu_alloc(size_t size, size_t align, bool reserved)
if (reserved && pcpu_reserved_chunk) {
chunk = pcpu_reserved_chunk;
if (size > chunk->contig_hint ||
- pcpu_extend_area_map(chunk) < 0)
+ pcpu_extend_area_map(chunk) < 0) {
+ err = "failed to extend area map of reserved chunk";
goto fail_unlock;
+ }
off = pcpu_alloc_area(chunk, size, align);
if (off >= 0)
goto area_found;
+ err = "alloc from reserved chunk failed";
goto fail_unlock;
}
@@ -1080,6 +1085,7 @@ restart:
case 1:
goto restart; /* pcpu_lock dropped, restart */
default:
+ err = "failed to extend area map";
goto fail_unlock;
}
@@ -1093,8 +1099,10 @@ restart:
spin_unlock_irq(&pcpu_lock);
chunk = alloc_pcpu_chunk();
- if (!chunk)
+ if (!chunk) {
+ err = "failed to allocate new chunk";
goto fail_unlock_mutex;
+ }
spin_lock_irq(&pcpu_lock);
pcpu_chunk_relocate(chunk, -1);
@@ -1107,6 +1115,7 @@ area_found:
if (pcpu_populate_chunk(chunk, off, size)) {
spin_lock_irq(&pcpu_lock);
pcpu_free_area(chunk, off);
+ err = "failed to populate";
goto fail_unlock;
}
@@ -1119,6 +1128,13 @@ fail_unlock:
spin_unlock_irq(&pcpu_lock);
fail_unlock_mutex:
mutex_unlock(&pcpu_alloc_mutex);
+ if (warn_limit) {
+ pr_warning("PERCPU: allocation failed, size=%zu align=%zu, "
+ "%s\n", size, align, err);
+ dump_stack();
+ if (!--warn_limit)
+ pr_info("PERCPU: limit reached, disable warning\n");
+ }
return NULL;
}
@@ -1347,6 +1363,10 @@ struct pcpu_alloc_info * __init pcpu_build_alloc_info(
struct pcpu_alloc_info *ai;
unsigned int *cpu_map;
+ /* this function may be called multiple times */
+ memset(group_map, 0, sizeof(group_map));
+ memset(group_cnt, 0, sizeof(group_map));
+
/*
* Determine min_unit_size, alloc_size and max_upa such that
* alloc_size is multiple of atom_size and is the smallest
@@ -1574,6 +1594,7 @@ static void pcpu_dump_alloc_info(const char *lvl,
int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
void *base_addr)
{
+ static char cpus_buf[4096] __initdata;
static int smap[2], dmap[2];
size_t dyn_size = ai->dyn_size;
size_t size_sum = ai->static_size + ai->reserved_size + dyn_size;
@@ -1585,17 +1606,26 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
int *unit_map;
int group, unit, i;
+ cpumask_scnprintf(cpus_buf, sizeof(cpus_buf), cpu_possible_mask);
+
+#define PCPU_SETUP_BUG_ON(cond) do { \
+ if (unlikely(cond)) { \
+ pr_emerg("PERCPU: failed to initialize, %s", #cond); \
+ pr_emerg("PERCPU: cpu_possible_mask=%s\n", cpus_buf); \
+ pcpu_dump_alloc_info(KERN_EMERG, ai); \
+ BUG(); \
+ } \
+} while (0)
+
/* sanity checks */
BUILD_BUG_ON(ARRAY_SIZE(smap) >= PCPU_DFL_MAP_ALLOC ||
ARRAY_SIZE(dmap) >= PCPU_DFL_MAP_ALLOC);
- BUG_ON(ai->nr_groups <= 0);
- BUG_ON(!ai->static_size);
- BUG_ON(!base_addr);
- BUG_ON(ai->unit_size < size_sum);
- BUG_ON(ai->unit_size & ~PAGE_MASK);
- BUG_ON(ai->unit_size < PCPU_MIN_UNIT_SIZE);
-
- pcpu_dump_alloc_info(KERN_DEBUG, ai);
+ PCPU_SETUP_BUG_ON(ai->nr_groups <= 0);
+ PCPU_SETUP_BUG_ON(!ai->static_size);
+ PCPU_SETUP_BUG_ON(!base_addr);
+ PCPU_SETUP_BUG_ON(ai->unit_size < size_sum);
+ PCPU_SETUP_BUG_ON(ai->unit_size & ~PAGE_MASK);
+ PCPU_SETUP_BUG_ON(ai->unit_size < PCPU_MIN_UNIT_SIZE);
/* process group information and build config tables accordingly */
group_offsets = alloc_bootmem(ai->nr_groups * sizeof(group_offsets[0]));
@@ -1604,7 +1634,7 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
unit_off = alloc_bootmem(nr_cpu_ids * sizeof(unit_off[0]));
for (cpu = 0; cpu < nr_cpu_ids; cpu++)
- unit_map[cpu] = NR_CPUS;
+ unit_map[cpu] = UINT_MAX;
pcpu_first_unit_cpu = NR_CPUS;
for (group = 0, unit = 0; group < ai->nr_groups; group++, unit += i) {
@@ -1618,8 +1648,9 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
if (cpu == NR_CPUS)
continue;
- BUG_ON(cpu > nr_cpu_ids || !cpu_possible(cpu));
- BUG_ON(unit_map[cpu] != NR_CPUS);
+ PCPU_SETUP_BUG_ON(cpu > nr_cpu_ids);
+ PCPU_SETUP_BUG_ON(!cpu_possible(cpu));
+ PCPU_SETUP_BUG_ON(unit_map[cpu] != UINT_MAX);
unit_map[cpu] = unit + i;
unit_off[cpu] = gi->base_offset + i * ai->unit_size;
@@ -1632,7 +1663,11 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
pcpu_nr_units = unit;
for_each_possible_cpu(cpu)
- BUG_ON(unit_map[cpu] == NR_CPUS);
+ PCPU_SETUP_BUG_ON(unit_map[cpu] == UINT_MAX);
+
+ /* we're done parsing the input, undefine BUG macro and dump config */
+#undef PCPU_SETUP_BUG_ON
+ pcpu_dump_alloc_info(KERN_INFO, ai);
pcpu_nr_groups = ai->nr_groups;
pcpu_group_offsets = group_offsets;
@@ -1782,7 +1817,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, ssize_t dyn_size,
void *base = (void *)ULONG_MAX;
void **areas = NULL;
struct pcpu_alloc_info *ai;
- size_t size_sum, areas_size;
+ size_t size_sum, areas_size, max_distance;
int group, i, rc;
ai = pcpu_build_alloc_info(reserved_size, dyn_size, atom_size,
@@ -1832,8 +1867,24 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, ssize_t dyn_size,
}
/* base address is now known, determine group base offsets */
- for (group = 0; group < ai->nr_groups; group++)
+ max_distance = 0;
+ for (group = 0; group < ai->nr_groups; group++) {
ai->groups[group].base_offset = areas[group] - base;
+ max_distance = max(max_distance, ai->groups[group].base_offset);
+ }
+ max_distance += ai->unit_size;
+
+ /* warn if maximum distance is further than 75% of vmalloc space */
+ if (max_distance > (VMALLOC_END - VMALLOC_START) * 3 / 4) {
+ pr_warning("PERCPU: max_distance=0x%lx too large for vmalloc "
+ "space 0x%lx\n",
+ max_distance, VMALLOC_END - VMALLOC_START);
+#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
+ /* and fail if we have fallback */
+ rc = -EINVAL;
+ goto out_free;
+#endif
+ }
pr_info("PERCPU: 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,
diff --git a/mm/rmap.c b/mm/rmap.c
index 28aafe2b5306..dd43373a483f 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -242,8 +242,8 @@ vma_address(struct page *page, struct vm_area_struct *vma)
}
/*
- * At what user virtual address is page expected in vma? checking that the
- * page matches the vma: currently only used on anon pages, by unuse_vma;
+ * At what user virtual address is page expected in vma?
+ * checking that the page matches the vma.
*/
unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
{
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-19 12:40:01 +0000