Merge commit 'cf6cbd9fb3ecd1f848b38c910a9d09af148b766f' into patch_branch
Change-Id: I0e6a0be65fb5289e2f68bee5200e9872a76551a2
diff --git a/chromeos/config/arm64/chromiumos-arm64.flavour.config b/chromeos/config/arm64/chromiumos-arm64.flavour.config
index 2da699e..137651a 100644
--- a/chromeos/config/arm64/chromiumos-arm64.flavour.config
+++ b/chromeos/config/arm64/chromiumos-arm64.flavour.config
@@ -268,7 +268,6 @@
# CONFIG_IOMMU_IO_PGTABLE_ARMV7S_SELFTEST is not set
CONFIG_IOMMU_IO_PGTABLE_LPAE=y
# CONFIG_IOMMU_IO_PGTABLE_LPAE_SELFTEST is not set
-# CONFIG_ION is not set
# CONFIG_IPQ_GCC_4019 is not set
# CONFIG_IPQ_GCC_806X is not set
# CONFIG_IPQ_GCC_8074 is not set
diff --git a/chromeos/config/arm64/chromiumos-mediatek.flavour.config b/chromeos/config/arm64/chromiumos-mediatek.flavour.config
index f6fbcdb..a76f862 100644
--- a/chromeos/config/arm64/chromiumos-mediatek.flavour.config
+++ b/chromeos/config/arm64/chromiumos-mediatek.flavour.config
@@ -51,10 +51,6 @@
CONFIG_IOMMU_IO_PGTABLE_ARMV7S=y
# CONFIG_IOMMU_IO_PGTABLE_ARMV7S_SELFTEST is not set
# CONFIG_IOMMU_IO_PGTABLE_LPAE is not set
-CONFIG_ION=y
-# CONFIG_ION_CARVEOUT_HEAP is not set
-# CONFIG_ION_CHUNK_HEAP is not set
-# CONFIG_ION_SYSTEM_HEAP is not set
# CONFIG_MALI_DEVFREQ is not set
# CONFIG_MALI_DMA_FENCE is not set
# CONFIG_MALI_EXPERT is not set
diff --git a/chromeos/config/arm64/chromiumos-qualcomm.flavour.config b/chromeos/config/arm64/chromiumos-qualcomm.flavour.config
index d319664..0d1a72e 100644
--- a/chromeos/config/arm64/chromiumos-qualcomm.flavour.config
+++ b/chromeos/config/arm64/chromiumos-qualcomm.flavour.config
@@ -90,7 +90,6 @@
# CONFIG_IOMMU_IO_PGTABLE_ARMV7S is not set
CONFIG_IOMMU_IO_PGTABLE_LPAE=y
# CONFIG_IOMMU_IO_PGTABLE_LPAE_SELFTEST is not set
-# CONFIG_ION is not set
# CONFIG_IPQ_GCC_4019 is not set
# CONFIG_IPQ_GCC_806X is not set
# CONFIG_IPQ_GCC_8074 is not set
diff --git a/chromeos/config/arm64/chromiumos-rockchip64.flavour.config b/chromeos/config/arm64/chromiumos-rockchip64.flavour.config
index 82883e26..c5e3c33 100644
--- a/chromeos/config/arm64/chromiumos-rockchip64.flavour.config
+++ b/chromeos/config/arm64/chromiumos-rockchip64.flavour.config
@@ -184,10 +184,6 @@
# CONFIG_INPUT_RK805_PWRKEY is not set
# CONFIG_IOMMU_IO_PGTABLE_ARMV7S is not set
# CONFIG_IOMMU_IO_PGTABLE_LPAE is not set
-CONFIG_ION=y
-# CONFIG_ION_CARVEOUT_HEAP is not set
-# CONFIG_ION_CHUNK_HEAP is not set
-# CONFIG_ION_SYSTEM_HEAP is not set
# CONFIG_IPW2100 is not set
# CONFIG_IPW2200 is not set
# CONFIG_IWL3945 is not set
diff --git a/chromeos/config/armel/common.config b/chromeos/config/armel/common.config
index f783c74..f358268 100644
--- a/chromeos/config/armel/common.config
+++ b/chromeos/config/armel/common.config
@@ -380,10 +380,6 @@
CONFIG_IOMMU_API=y
# CONFIG_IOMMU_IO_PGTABLE_ARMV7S is not set
# CONFIG_IOMMU_IO_PGTABLE_LPAE is not set
-CONFIG_ION=y
-# CONFIG_ION_CARVEOUT_HEAP is not set
-# CONFIG_ION_CHUNK_HEAP is not set
-# CONFIG_ION_SYSTEM_HEAP is not set
# CONFIG_JFFS2_FS is not set
# CONFIG_KALLSYMS_ABSOLUTE_PERCPU is not set
CONFIG_KERNEL_GZIP=y
diff --git a/chromeos/config/base.config b/chromeos/config/base.config
index d614297..3dd9c96 100644
--- a/chromeos/config/base.config
+++ b/chromeos/config/base.config
@@ -1162,6 +1162,7 @@
# CONFIG_INV_MPU6050_SPI is not set
CONFIG_IOMMU_HELPER=y
CONFIG_IOMMU_SUPPORT=y
+# CONFIG_ION is not set
# CONFIG_IOSCHED_BFQ is not set
CONFIG_IOSCHED_CFQ=y
CONFIG_IOSCHED_DEADLINE=y
diff --git a/chromeos/config/x86_64/common.config b/chromeos/config/x86_64/common.config
index 905dc52..ca5fe0327 100644
--- a/chromeos/config/x86_64/common.config
+++ b/chromeos/config/x86_64/common.config
@@ -636,10 +636,6 @@
CONFIG_INTERVAL_TREE=y
# CONFIG_IOMMU_DEBUG is not set
# CONFIG_IOMMU_STRESS is not set
-CONFIG_ION=y
-# CONFIG_ION_CARVEOUT_HEAP is not set
-# CONFIG_ION_CHUNK_HEAP is not set
-# CONFIG_ION_SYSTEM_HEAP is not set
CONFIG_IOSF_MBI=y
# CONFIG_IOSF_MBI_DEBUG is not set
# CONFIG_IO_DELAY_0X80 is not set
diff --git a/drivers/crypto/ccp/sp-platform.c b/drivers/crypto/ccp/sp-platform.c
index 71734f2..b75dc7db 100644
--- a/drivers/crypto/ccp/sp-platform.c
+++ b/drivers/crypto/ccp/sp-platform.c
@@ -33,8 +33,31 @@
unsigned int irq_count;
};
-static const struct acpi_device_id sp_acpi_match[];
-static const struct of_device_id sp_of_match[];
+static const struct sp_dev_vdata dev_vdata[] = {
+ {
+ .bar = 0,
+#ifdef CONFIG_CRYPTO_DEV_SP_CCP
+ .ccp_vdata = &ccpv3_platform,
+#endif
+ },
+};
+
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id sp_acpi_match[] = {
+ { "AMDI0C00", (kernel_ulong_t)&dev_vdata[0] },
+ { },
+};
+MODULE_DEVICE_TABLE(acpi, sp_acpi_match);
+#endif
+
+#ifdef CONFIG_OF
+static const struct of_device_id sp_of_match[] = {
+ { .compatible = "amd,ccp-seattle-v1a",
+ .data = (const void *)&dev_vdata[0] },
+ { },
+};
+MODULE_DEVICE_TABLE(of, sp_of_match);
+#endif
static struct sp_dev_vdata *sp_get_of_version(struct platform_device *pdev)
{
@@ -201,32 +224,6 @@
}
#endif
-static const struct sp_dev_vdata dev_vdata[] = {
- {
- .bar = 0,
-#ifdef CONFIG_CRYPTO_DEV_SP_CCP
- .ccp_vdata = &ccpv3_platform,
-#endif
- },
-};
-
-#ifdef CONFIG_ACPI
-static const struct acpi_device_id sp_acpi_match[] = {
- { "AMDI0C00", (kernel_ulong_t)&dev_vdata[0] },
- { },
-};
-MODULE_DEVICE_TABLE(acpi, sp_acpi_match);
-#endif
-
-#ifdef CONFIG_OF
-static const struct of_device_id sp_of_match[] = {
- { .compatible = "amd,ccp-seattle-v1a",
- .data = (const void *)&dev_vdata[0] },
- { },
-};
-MODULE_DEVICE_TABLE(of, sp_of_match);
-#endif
-
static struct platform_driver sp_platform_driver = {
.driver = {
.name = "ccp",
diff --git a/drivers/platform/x86/intel_pmc_core.c b/drivers/platform/x86/intel_pmc_core.c
index f20a753..e19e1c5 100644
--- a/drivers/platform/x86/intel_pmc_core.c
+++ b/drivers/platform/x86/intel_pmc_core.c
@@ -141,9 +141,9 @@
writel(val, pmcdev->regbase + reg_offset);
}
-static inline u32 pmc_core_adjust_slp_s0_step(u32 value)
+static inline u64 pmc_core_adjust_slp_s0_step(u32 value)
{
- return value * SPT_PMC_SLP_S0_RES_COUNTER_STEP;
+ return (u64)value * SPT_PMC_SLP_S0_RES_COUNTER_STEP;
}
/**
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 69966c4..6503a9c 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -48,13 +48,12 @@
MEMCG_NR_STAT,
};
-/* Cgroup-specific events, on top of universal VM events */
-enum memcg_event_item {
- MEMCG_LOW = NR_VM_EVENT_ITEMS,
+enum memcg_memory_event {
+ MEMCG_LOW,
MEMCG_HIGH,
MEMCG_MAX,
MEMCG_OOM,
- MEMCG_NR_EVENTS,
+ MEMCG_NR_MEMORY_EVENTS,
};
struct mem_cgroup_reclaim_cookie {
@@ -88,7 +87,7 @@
struct mem_cgroup_stat_cpu {
long count[MEMCG_NR_STAT];
- unsigned long events[MEMCG_NR_EVENTS];
+ unsigned long events[NR_VM_EVENT_ITEMS];
unsigned long nr_page_events;
unsigned long targets[MEM_CGROUP_NTARGETS];
};
@@ -108,7 +107,10 @@
*/
struct mem_cgroup_per_node {
struct lruvec lruvec;
- struct lruvec_stat __percpu *lruvec_stat;
+
+ struct lruvec_stat __percpu *lruvec_stat_cpu;
+ atomic_long_t lruvec_stat[NR_VM_NODE_STAT_ITEMS];
+
unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
struct mem_cgroup_reclaim_iter iter[DEF_PRIORITY + 1];
@@ -199,7 +201,8 @@
/* OOM-Killer disable */
int oom_kill_disable;
- /* handle for "memory.events" */
+ /* memory.events */
+ atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS];
struct cgroup_file events_file;
/* protect arrays of thresholds */
@@ -227,10 +230,11 @@
spinlock_t move_lock;
struct task_struct *move_lock_task;
unsigned long move_lock_flags;
- /*
- * percpu counter.
- */
- struct mem_cgroup_stat_cpu __percpu *stat;
+
+ /* memory.stat */
+ struct mem_cgroup_stat_cpu __percpu *stat_cpu;
+ atomic_long_t stat[MEMCG_NR_STAT];
+ atomic_long_t events[NR_VM_EVENT_ITEMS];
unsigned long socket_pressure;
@@ -265,6 +269,12 @@
/* WARNING: nodeinfo must be the last member here */
};
+/*
+ * size of first charge trial. "32" comes from vmscan.c's magic value.
+ * TODO: maybe necessary to use big numbers in big irons.
+ */
+#define MEMCG_CHARGE_BATCH 32U
+
extern struct mem_cgroup *root_mem_cgroup;
static inline bool mem_cgroup_disabled(void)
@@ -272,13 +282,6 @@
return !cgroup_subsys_enabled(memory_cgrp_subsys);
}
-static inline void mem_cgroup_event(struct mem_cgroup *memcg,
- enum memcg_event_item event)
-{
- this_cpu_inc(memcg->stat->events[event]);
- cgroup_file_notify(&memcg->events_file);
-}
-
bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg);
int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
@@ -492,32 +495,40 @@
static inline unsigned long memcg_page_state(struct mem_cgroup *memcg,
int idx)
{
- long val = 0;
- int cpu;
-
- for_each_possible_cpu(cpu)
- val += per_cpu(memcg->stat->count[idx], cpu);
-
- if (val < 0)
- val = 0;
-
- return val;
+ long x = atomic_long_read(&memcg->stat[idx]);
+#ifdef CONFIG_SMP
+ if (x < 0)
+ x = 0;
+#endif
+ return x;
}
/* idx can be of type enum memcg_stat_item or node_stat_item */
static inline void __mod_memcg_state(struct mem_cgroup *memcg,
int idx, int val)
{
- if (!mem_cgroup_disabled())
- __this_cpu_add(memcg->stat->count[idx], val);
+ long x;
+
+ if (mem_cgroup_disabled())
+ return;
+
+ x = val + __this_cpu_read(memcg->stat_cpu->count[idx]);
+ if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
+ atomic_long_add(x, &memcg->stat[idx]);
+ x = 0;
+ }
+ __this_cpu_write(memcg->stat_cpu->count[idx], x);
}
/* idx can be of type enum memcg_stat_item or node_stat_item */
static inline void mod_memcg_state(struct mem_cgroup *memcg,
int idx, int val)
{
- if (!mem_cgroup_disabled())
- this_cpu_add(memcg->stat->count[idx], val);
+ unsigned long flags;
+
+ local_irq_save(flags);
+ __mod_memcg_state(memcg, idx, val);
+ local_irq_restore(flags);
}
/**
@@ -555,89 +566,116 @@
enum node_stat_item idx)
{
struct mem_cgroup_per_node *pn;
- long val = 0;
- int cpu;
+ long x;
if (mem_cgroup_disabled())
return node_page_state(lruvec_pgdat(lruvec), idx);
pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
- for_each_possible_cpu(cpu)
- val += per_cpu(pn->lruvec_stat->count[idx], cpu);
-
- if (val < 0)
- val = 0;
-
- return val;
+ x = atomic_long_read(&pn->lruvec_stat[idx]);
+#ifdef CONFIG_SMP
+ if (x < 0)
+ x = 0;
+#endif
+ return x;
}
static inline void __mod_lruvec_state(struct lruvec *lruvec,
enum node_stat_item idx, int val)
{
struct mem_cgroup_per_node *pn;
+ long x;
+ /* Update node */
__mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
+
if (mem_cgroup_disabled())
return;
+
pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
+
+ /* Update memcg */
__mod_memcg_state(pn->memcg, idx, val);
- __this_cpu_add(pn->lruvec_stat->count[idx], val);
+
+ /* Update lruvec */
+ x = val + __this_cpu_read(pn->lruvec_stat_cpu->count[idx]);
+ if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
+ atomic_long_add(x, &pn->lruvec_stat[idx]);
+ x = 0;
+ }
+ __this_cpu_write(pn->lruvec_stat_cpu->count[idx], x);
}
static inline void mod_lruvec_state(struct lruvec *lruvec,
enum node_stat_item idx, int val)
{
- struct mem_cgroup_per_node *pn;
+ unsigned long flags;
- mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
- if (mem_cgroup_disabled())
- return;
- pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
- mod_memcg_state(pn->memcg, idx, val);
- this_cpu_add(pn->lruvec_stat->count[idx], val);
+ local_irq_save(flags);
+ __mod_lruvec_state(lruvec, idx, val);
+ local_irq_restore(flags);
}
static inline void __mod_lruvec_page_state(struct page *page,
enum node_stat_item idx, int val)
{
- struct mem_cgroup_per_node *pn;
+ pg_data_t *pgdat = page_pgdat(page);
+ struct lruvec *lruvec;
- __mod_node_page_state(page_pgdat(page), idx, val);
- if (mem_cgroup_disabled() || !page->mem_cgroup)
+ /* Untracked pages have no memcg, no lruvec. Update only the node */
+ if (!page->mem_cgroup) {
+ __mod_node_page_state(pgdat, idx, val);
return;
- __mod_memcg_state(page->mem_cgroup, idx, val);
- pn = page->mem_cgroup->nodeinfo[page_to_nid(page)];
- __this_cpu_add(pn->lruvec_stat->count[idx], val);
+ }
+
+ lruvec = mem_cgroup_lruvec(pgdat, page->mem_cgroup);
+ __mod_lruvec_state(lruvec, idx, val);
}
static inline void mod_lruvec_page_state(struct page *page,
enum node_stat_item idx, int val)
{
- struct mem_cgroup_per_node *pn;
+ unsigned long flags;
- mod_node_page_state(page_pgdat(page), idx, val);
- if (mem_cgroup_disabled() || !page->mem_cgroup)
- return;
- mod_memcg_state(page->mem_cgroup, idx, val);
- pn = page->mem_cgroup->nodeinfo[page_to_nid(page)];
- this_cpu_add(pn->lruvec_stat->count[idx], val);
+ local_irq_save(flags);
+ __mod_lruvec_page_state(page, idx, val);
+ local_irq_restore(flags);
}
unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
gfp_t gfp_mask,
unsigned long *total_scanned);
+static inline void __count_memcg_events(struct mem_cgroup *memcg,
+ enum vm_event_item idx,
+ unsigned long count)
+{
+ unsigned long x;
+
+ if (mem_cgroup_disabled())
+ return;
+
+ x = count + __this_cpu_read(memcg->stat_cpu->events[idx]);
+ if (unlikely(x > MEMCG_CHARGE_BATCH)) {
+ atomic_long_add(x, &memcg->events[idx]);
+ x = 0;
+ }
+ __this_cpu_write(memcg->stat_cpu->events[idx], x);
+}
+
static inline void count_memcg_events(struct mem_cgroup *memcg,
enum vm_event_item idx,
unsigned long count)
{
- if (!mem_cgroup_disabled())
- this_cpu_add(memcg->stat->events[idx], count);
+ unsigned long flags;
+
+ local_irq_save(flags);
+ __count_memcg_events(memcg, idx, count);
+ local_irq_restore(flags);
}
-/* idx can be of type enum memcg_stat_item or node_stat_item */
static inline void count_memcg_page_event(struct page *page,
- int idx)
+ enum vm_event_item idx)
{
if (page->mem_cgroup)
count_memcg_events(page->mem_cgroup, idx, 1);
@@ -654,12 +692,20 @@
rcu_read_lock();
memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
if (likely(memcg)) {
- this_cpu_inc(memcg->stat->events[idx]);
+ count_memcg_events(memcg, idx, 1);
if (idx == OOM_KILL)
cgroup_file_notify(&memcg->events_file);
}
rcu_read_unlock();
}
+
+static inline void memcg_memory_event(struct mem_cgroup *memcg,
+ enum memcg_memory_event event)
+{
+ atomic_long_inc(&memcg->memory_events[event]);
+ cgroup_file_notify(&memcg->events_file);
+}
+
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
void mem_cgroup_split_huge_fixup(struct page *head);
#endif
@@ -676,8 +722,8 @@
return true;
}
-static inline void mem_cgroup_event(struct mem_cgroup *memcg,
- enum memcg_event_item event)
+static inline void memcg_memory_event(struct mem_cgroup *memcg,
+ enum memcg_memory_event event)
{
}
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6a9a7e1..65eddf0 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -542,39 +542,10 @@
return mz;
}
-/*
- * Return page count for single (non recursive) @memcg.
- *
- * Implementation Note: reading percpu statistics for memcg.
- *
- * Both of vmstat[] and percpu_counter has threshold and do periodic
- * synchronization to implement "quick" read. There are trade-off between
- * reading cost and precision of value. Then, we may have a chance to implement
- * a periodic synchronization of counter in memcg's counter.
- *
- * But this _read() function is used for user interface now. The user accounts
- * memory usage by memory cgroup and he _always_ requires exact value because
- * he accounts memory. Even if we provide quick-and-fuzzy read, we always
- * have to visit all online cpus and make sum. So, for now, unnecessary
- * synchronization is not implemented. (just implemented for cpu hotplug)
- *
- * If there are kernel internal actions which can make use of some not-exact
- * value, and reading all cpu value can be performance bottleneck in some
- * common workload, threshold and synchronization as vmstat[] should be
- * implemented.
- *
- * The parameter idx can be of type enum memcg_event_item or vm_event_item.
- */
-
static unsigned long memcg_sum_events(struct mem_cgroup *memcg,
int event)
{
- unsigned long val = 0;
- int cpu;
-
- for_each_possible_cpu(cpu)
- val += per_cpu(memcg->stat->events[event], cpu);
- return val;
+ return atomic_long_read(&memcg->events[event]);
}
static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
@@ -586,27 +557,27 @@
* counted as CACHE even if it's on ANON LRU.
*/
if (PageAnon(page))
- __this_cpu_add(memcg->stat->count[MEMCG_RSS], nr_pages);
+ __mod_memcg_state(memcg, MEMCG_RSS, nr_pages);
else {
- __this_cpu_add(memcg->stat->count[MEMCG_CACHE], nr_pages);
+ __mod_memcg_state(memcg, MEMCG_CACHE, nr_pages);
if (PageSwapBacked(page))
- __this_cpu_add(memcg->stat->count[NR_SHMEM], nr_pages);
+ __mod_memcg_state(memcg, NR_SHMEM, nr_pages);
}
if (compound) {
VM_BUG_ON_PAGE(!PageTransHuge(page), page);
- __this_cpu_add(memcg->stat->count[MEMCG_RSS_HUGE], nr_pages);
+ __mod_memcg_state(memcg, MEMCG_RSS_HUGE, nr_pages);
}
/* pagein of a big page is an event. So, ignore page size */
if (nr_pages > 0)
- __this_cpu_inc(memcg->stat->events[PGPGIN]);
+ __count_memcg_events(memcg, PGPGIN, 1);
else {
- __this_cpu_inc(memcg->stat->events[PGPGOUT]);
+ __count_memcg_events(memcg, PGPGOUT, 1);
nr_pages = -nr_pages; /* for event */
}
- __this_cpu_add(memcg->stat->nr_page_events, nr_pages);
+ __this_cpu_add(memcg->stat_cpu->nr_page_events, nr_pages);
}
unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
@@ -642,8 +613,8 @@
{
unsigned long val, next;
- val = __this_cpu_read(memcg->stat->nr_page_events);
- next = __this_cpu_read(memcg->stat->targets[target]);
+ val = __this_cpu_read(memcg->stat_cpu->nr_page_events);
+ next = __this_cpu_read(memcg->stat_cpu->targets[target]);
/* from time_after() in jiffies.h */
if ((long)(next - val) < 0) {
switch (target) {
@@ -659,7 +630,7 @@
default:
break;
}
- __this_cpu_write(memcg->stat->targets[target], next);
+ __this_cpu_write(memcg->stat_cpu->targets[target], next);
return true;
}
return false;
@@ -1707,11 +1678,6 @@
}
EXPORT_SYMBOL(unlock_page_memcg);
-/*
- * size of first charge trial. "32" comes from vmscan.c's magic value.
- * TODO: maybe necessary to use big numbers in big irons.
- */
-#define CHARGE_BATCH 32U
struct memcg_stock_pcp {
struct mem_cgroup *cached; /* this never be root cgroup */
unsigned int nr_pages;
@@ -1739,7 +1705,7 @@
unsigned long flags;
bool ret = false;
- if (nr_pages > CHARGE_BATCH)
+ if (nr_pages > MEMCG_CHARGE_BATCH)
return ret;
local_irq_save(flags);
@@ -1808,7 +1774,7 @@
}
stock->nr_pages += nr_pages;
- if (stock->nr_pages > CHARGE_BATCH)
+ if (stock->nr_pages > MEMCG_CHARGE_BATCH)
drain_stock(stock);
local_irq_restore(flags);
@@ -1858,9 +1824,44 @@
static int memcg_hotplug_cpu_dead(unsigned int cpu)
{
struct memcg_stock_pcp *stock;
+ struct mem_cgroup *memcg;
stock = &per_cpu(memcg_stock, cpu);
drain_stock(stock);
+
+ for_each_mem_cgroup(memcg) {
+ int i;
+
+ for (i = 0; i < MEMCG_NR_STAT; i++) {
+ int nid;
+ long x;
+
+ x = this_cpu_xchg(memcg->stat_cpu->count[i], 0);
+ if (x)
+ atomic_long_add(x, &memcg->stat[i]);
+
+ if (i >= NR_VM_NODE_STAT_ITEMS)
+ continue;
+
+ for_each_node(nid) {
+ struct mem_cgroup_per_node *pn;
+
+ pn = mem_cgroup_nodeinfo(memcg, nid);
+ x = this_cpu_xchg(pn->lruvec_stat_cpu->count[i], 0);
+ if (x)
+ atomic_long_add(x, &pn->lruvec_stat[i]);
+ }
+ }
+
+ for (i = 0; i < NR_VM_EVENT_ITEMS; i++) {
+ long x;
+
+ x = this_cpu_xchg(memcg->stat_cpu->events[i], 0);
+ if (x)
+ atomic_long_add(x, &memcg->events[i]);
+ }
+ }
+
return 0;
}
@@ -1871,7 +1872,7 @@
do {
if (page_counter_read(&memcg->memory) <= memcg->high)
continue;
- mem_cgroup_event(memcg, MEMCG_HIGH);
+ memcg_memory_event(memcg, MEMCG_HIGH);
try_to_free_mem_cgroup_pages(memcg, nr_pages, gfp_mask, true);
} while ((memcg = parent_mem_cgroup(memcg)));
}
@@ -1881,7 +1882,7 @@
struct mem_cgroup *memcg;
memcg = container_of(work, struct mem_cgroup, high_work);
- reclaim_high(memcg, CHARGE_BATCH, GFP_KERNEL);
+ reclaim_high(memcg, MEMCG_CHARGE_BATCH, GFP_KERNEL);
}
/*
@@ -1905,7 +1906,7 @@
static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
unsigned int nr_pages)
{
- unsigned int batch = max(CHARGE_BATCH, nr_pages);
+ unsigned int batch = max(MEMCG_CHARGE_BATCH, nr_pages);
int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
struct mem_cgroup *mem_over_limit;
struct page_counter *counter;
@@ -1962,7 +1963,7 @@
if (!gfpflags_allow_blocking(gfp_mask))
goto nomem;
- mem_cgroup_event(mem_over_limit, MEMCG_MAX);
+ memcg_memory_event(mem_over_limit, MEMCG_MAX);
nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages,
gfp_mask, may_swap);
@@ -2005,7 +2006,7 @@
if (fatal_signal_pending(current))
goto force;
- mem_cgroup_event(mem_over_limit, MEMCG_OOM);
+ memcg_memory_event(mem_over_limit, MEMCG_OOM);
mem_cgroup_oom(mem_over_limit, gfp_mask,
get_order(nr_pages * PAGE_SIZE));
@@ -2415,18 +2416,11 @@
for (i = 1; i < HPAGE_PMD_NR; i++)
head[i].mem_cgroup = head->mem_cgroup;
- __this_cpu_sub(head->mem_cgroup->stat->count[MEMCG_RSS_HUGE],
- HPAGE_PMD_NR);
+ __mod_memcg_state(head->mem_cgroup, MEMCG_RSS_HUGE, -HPAGE_PMD_NR);
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#ifdef CONFIG_MEMCG_SWAP
-static void mem_cgroup_swap_statistics(struct mem_cgroup *memcg,
- int nr_entries)
-{
- this_cpu_add(memcg->stat->count[MEMCG_SWAP], nr_entries);
-}
-
/**
* mem_cgroup_move_swap_account - move swap charge and swap_cgroup's record.
* @entry: swap entry to be moved
@@ -2450,8 +2444,8 @@
new_id = mem_cgroup_id(to);
if (swap_cgroup_cmpxchg(entry, old_id, new_id) == old_id) {
- mem_cgroup_swap_statistics(from, -1);
- mem_cgroup_swap_statistics(to, 1);
+ mod_memcg_state(from, MEMCG_SWAP, -1);
+ mod_memcg_state(to, MEMCG_SWAP, 1);
return 0;
}
return -EINVAL;
@@ -2767,10 +2761,10 @@
struct mem_cgroup *iter;
int i;
- memset(events, 0, sizeof(*events) * MEMCG_NR_EVENTS);
+ memset(events, 0, sizeof(*events) * NR_VM_EVENT_ITEMS);
for_each_mem_cgroup_tree(iter, memcg) {
- for (i = 0; i < MEMCG_NR_EVENTS; i++)
+ for (i = 0; i < NR_VM_EVENT_ITEMS; i++)
events[i] += memcg_sum_events(iter, i);
}
}
@@ -4175,8 +4169,8 @@
if (!pn)
return 1;
- pn->lruvec_stat = alloc_percpu(struct lruvec_stat);
- if (!pn->lruvec_stat) {
+ pn->lruvec_stat_cpu = alloc_percpu(struct lruvec_stat);
+ if (!pn->lruvec_stat_cpu) {
kfree(pn);
return 1;
}
@@ -4197,7 +4191,7 @@
if (!pn)
return;
- free_percpu(pn->lruvec_stat);
+ free_percpu(pn->lruvec_stat_cpu);
kfree(pn);
}
@@ -4207,7 +4201,7 @@
for_each_node(node)
free_mem_cgroup_per_node_info(memcg, node);
- free_percpu(memcg->stat);
+ free_percpu(memcg->stat_cpu);
kfree(memcg);
}
@@ -4236,8 +4230,8 @@
if (memcg->id.id < 0)
goto fail;
- memcg->stat = alloc_percpu(struct mem_cgroup_stat_cpu);
- if (!memcg->stat)
+ memcg->stat_cpu = alloc_percpu(struct mem_cgroup_stat_cpu);
+ if (!memcg->stat_cpu)
goto fail;
for_each_node(node)
@@ -4594,8 +4588,8 @@
spin_lock_irqsave(&from->move_lock, flags);
if (!anon && page_mapped(page)) {
- __this_cpu_sub(from->stat->count[NR_FILE_MAPPED], nr_pages);
- __this_cpu_add(to->stat->count[NR_FILE_MAPPED], nr_pages);
+ __mod_memcg_state(from, NR_FILE_MAPPED, -nr_pages);
+ __mod_memcg_state(to, NR_FILE_MAPPED, nr_pages);
}
/*
@@ -4607,16 +4601,14 @@
struct address_space *mapping = page_mapping(page);
if (mapping_cap_account_dirty(mapping)) {
- __this_cpu_sub(from->stat->count[NR_FILE_DIRTY],
- nr_pages);
- __this_cpu_add(to->stat->count[NR_FILE_DIRTY],
- nr_pages);
+ __mod_memcg_state(from, NR_FILE_DIRTY, -nr_pages);
+ __mod_memcg_state(to, NR_FILE_DIRTY, nr_pages);
}
}
if (PageWriteback(page)) {
- __this_cpu_sub(from->stat->count[NR_WRITEBACK], nr_pages);
- __this_cpu_add(to->stat->count[NR_WRITEBACK], nr_pages);
+ __mod_memcg_state(from, NR_WRITEBACK, -nr_pages);
+ __mod_memcg_state(to, NR_WRITEBACK, nr_pages);
}
/*
@@ -5269,7 +5261,7 @@
continue;
}
- mem_cgroup_event(memcg, MEMCG_OOM);
+ memcg_memory_event(memcg, MEMCG_OOM);
if (!mem_cgroup_out_of_memory(memcg, GFP_KERNEL, 0))
break;
}
@@ -5282,10 +5274,14 @@
{
struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
- seq_printf(m, "low %lu\n", memcg_sum_events(memcg, MEMCG_LOW));
- seq_printf(m, "high %lu\n", memcg_sum_events(memcg, MEMCG_HIGH));
- seq_printf(m, "max %lu\n", memcg_sum_events(memcg, MEMCG_MAX));
- seq_printf(m, "oom %lu\n", memcg_sum_events(memcg, MEMCG_OOM));
+ seq_printf(m, "low %lu\n",
+ atomic_long_read(&memcg->memory_events[MEMCG_LOW]));
+ seq_printf(m, "high %lu\n",
+ atomic_long_read(&memcg->memory_events[MEMCG_HIGH]));
+ seq_printf(m, "max %lu\n",
+ atomic_long_read(&memcg->memory_events[MEMCG_MAX]));
+ seq_printf(m, "oom %lu\n",
+ atomic_long_read(&memcg->memory_events[MEMCG_OOM]));
seq_printf(m, "oom_kill %lu\n", memcg_sum_events(memcg, OOM_KILL));
return 0;
@@ -5295,7 +5291,7 @@
{
struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
unsigned long stat[MEMCG_NR_STAT];
- unsigned long events[MEMCG_NR_EVENTS];
+ unsigned long events[NR_VM_EVENT_ITEMS];
int i;
/*
@@ -5652,12 +5648,12 @@
}
local_irq_save(flags);
- __this_cpu_sub(ug->memcg->stat->count[MEMCG_RSS], ug->nr_anon);
- __this_cpu_sub(ug->memcg->stat->count[MEMCG_CACHE], ug->nr_file);
- __this_cpu_sub(ug->memcg->stat->count[MEMCG_RSS_HUGE], ug->nr_huge);
- __this_cpu_sub(ug->memcg->stat->count[NR_SHMEM], ug->nr_shmem);
- __this_cpu_add(ug->memcg->stat->events[PGPGOUT], ug->pgpgout);
- __this_cpu_add(ug->memcg->stat->nr_page_events, nr_pages);
+ __mod_memcg_state(ug->memcg, MEMCG_RSS, -ug->nr_anon);
+ __mod_memcg_state(ug->memcg, MEMCG_CACHE, -ug->nr_file);
+ __mod_memcg_state(ug->memcg, MEMCG_RSS_HUGE, -ug->nr_huge);
+ __mod_memcg_state(ug->memcg, NR_SHMEM, -ug->nr_shmem);
+ __count_memcg_events(ug->memcg, PGPGOUT, ug->pgpgout);
+ __this_cpu_add(ug->memcg->stat_cpu->nr_page_events, nr_pages);
memcg_check_events(ug->memcg, ug->dummy_page);
local_irq_restore(flags);
@@ -5898,7 +5894,7 @@
if (in_softirq())
gfp_mask = GFP_NOWAIT;
- this_cpu_add(memcg->stat->count[MEMCG_SOCK], nr_pages);
+ mod_memcg_state(memcg, MEMCG_SOCK, nr_pages);
if (try_charge(memcg, gfp_mask, nr_pages) == 0)
return true;
@@ -5919,7 +5915,7 @@
return;
}
- this_cpu_sub(memcg->stat->count[MEMCG_SOCK], nr_pages);
+ mod_memcg_state(memcg, MEMCG_SOCK, -nr_pages);
refill_stock(memcg, nr_pages);
}
@@ -6043,7 +6039,7 @@
oldid = swap_cgroup_record(entry, mem_cgroup_id(swap_memcg),
nr_entries);
VM_BUG_ON_PAGE(oldid, page);
- mem_cgroup_swap_statistics(swap_memcg, nr_entries);
+ mod_memcg_state(swap_memcg, MEMCG_SWAP, nr_entries);
page->mem_cgroup = NULL;
@@ -6109,7 +6105,7 @@
mem_cgroup_id_get_many(memcg, nr_pages - 1);
oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg), nr_pages);
VM_BUG_ON_PAGE(oldid, page);
- mem_cgroup_swap_statistics(memcg, nr_pages);
+ mod_memcg_state(memcg, MEMCG_SWAP, nr_pages);
return 0;
}
@@ -6137,7 +6133,7 @@
else
page_counter_uncharge(&memcg->memsw, nr_pages);
}
- mem_cgroup_swap_statistics(memcg, -nr_pages);
+ mod_memcg_state(memcg, MEMCG_SWAP, -nr_pages);
mem_cgroup_id_put_many(memcg, nr_pages);
}
rcu_read_unlock();
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e3e71361..8ee1659 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2662,7 +2662,7 @@
sc->memcg_low_skipped = 1;
continue;
}
- mem_cgroup_event(memcg, MEMCG_LOW);
+ memcg_memory_event(memcg, MEMCG_LOW);
}
reclaimed = sc->nr_reclaimed;
diff --git a/security/container/monitor.c b/security/container/monitor.c
index ef44e1e..73f986b 100644
--- a/security/container/monitor.c
+++ b/security/container/monitor.c
@@ -22,6 +22,12 @@
/* protects csm_host_port and csm_vsocket. */
DECLARE_RWSEM(csm_rwsem_vsocket);
+/* queue used for poll wait on config changes. */
+static DECLARE_WAIT_QUEUE_HEAD(config_wait);
+
+/* increase each time a new configuration is applied. */
+static unsigned long config_version;
+
/*
* Is monitoring enabled? Defaults to disabled.
* These variables might be used without locking csm_rwsem_config to check if an
@@ -38,6 +44,7 @@
static struct dentry *csm_dir;
static struct dentry *csm_enabled_file;
static struct dentry *csm_container_file;
+static struct dentry *csm_config_vers_file;
/* Option to disable the CSM LSM at boot. */
static bool cmdline_boot_disabled;
@@ -74,6 +81,9 @@
csm_execute_config.envp_allowlist = econf->envp_allowlist.arg;
econf->envp_allowlist.arg = NULL;
}
+
+ config_version++;
+ wake_up(&config_wait);
}
int csm_update_config_from_buffer(void *data, size_t size)
@@ -196,6 +206,39 @@
.write = csm_enabled_write,
};
+static int csm_config_version_open(struct inode *inode, struct file *file)
+{
+ /* private_data is used to keep the latest config version read. */
+ file->private_data = (void*)-1;
+ return 0;
+}
+
+static ssize_t csm_config_version_read(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ unsigned long version = config_version;
+ file->private_data = (void*)version;
+ return simple_read_from_buffer(buf, count, ppos, &version,
+ sizeof(version));
+}
+
+static __poll_t csm_config_version_poll(struct file *file,
+ struct poll_table_struct *poll_tab)
+{
+ if ((unsigned long)file->private_data != config_version)
+ return EPOLLIN;
+ poll_wait(file, &config_wait, poll_tab);
+ if ((unsigned long)file->private_data != config_version)
+ return EPOLLIN;
+ return 0;
+}
+
+static const struct file_operations csm_config_version_fops = {
+ .open = csm_config_version_open,
+ .read = csm_config_version_read,
+ .poll = csm_config_version_poll,
+};
+
static void set_container_decode_callbacks(schema_Container *container)
{
container->pod_namespace.funcs.decode = pb_decode_string_field;
@@ -378,13 +421,21 @@
goto error_rm_enabled;
}
+ csm_config_vers_file = securityfs_create_file("config_version", 0200,
+ csm_dir, NULL,
+ &csm_config_version_fops);
+ if (IS_ERR(csm_config_vers_file)) {
+ err = PTR_ERR(csm_config_vers_file);
+ goto error_rm_container;
+ }
+
#ifdef CONFIG_SECURITY_CONTAINER_MONITOR_DEBUG_CONFIG
csm_config_file = securityfs_create_file("config", 0200, csm_dir,
NULL, &csm_config_fops);
if (IS_ERR(csm_config_file)) {
err = PTR_ERR(csm_config_file);
- securityfs_remove(csm_container_file);
- goto error_rm_enabled;
+ securityfs_remove(csm_config_vers_file);
+ goto error_rm_container;
}
#endif /* CONFIG_SECURITY_CONTAINER_MONITOR_DEBUG_CONFIG */
@@ -394,6 +445,8 @@
pr_debug("registered hooks\n");
return 0;
+error_rm_container:
+ securityfs_remove(csm_container_file);
error_rm_enabled:
securityfs_remove(csm_enabled_file);
error_rmdir: