aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/btf.c58
-rw-r--r--kernel/bpf/core.c49
-rw-r--r--kernel/bpf/devmap.c3
-rw-r--r--kernel/bpf/helpers.c2
-rw-r--r--kernel/bpf/queue_stack_maps.c2
-rw-r--r--kernel/bpf/verifier.c13
-rw-r--r--kernel/cgroup/cgroup.c45
-rw-r--r--kernel/debug/kdb/kdb_main.c7
-rw-r--r--kernel/delayacct.c15
-rw-r--r--kernel/dma/direct.c2
-rw-r--r--kernel/dma/swiotlb.c326
-rw-r--r--kernel/fork.c59
-rw-r--r--kernel/kallsyms.c4
-rw-r--r--kernel/memremap.c98
-rw-r--r--kernel/sched/Makefile1
-rw-r--r--kernel/sched/core.c16
-rw-r--r--kernel/sched/loadavg.c139
-rw-r--r--kernel/sched/psi.c759
-rw-r--r--kernel/sched/sched.h178
-rw-r--r--kernel/sched/stats.h86
20 files changed, 1299 insertions, 563 deletions
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 378cef70341c..ee4c82667d65 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -2067,56 +2067,47 @@ static int btf_check_sec_info(struct btf_verifier_env *env,
return 0;
}
-static int btf_parse_hdr(struct btf_verifier_env *env, void __user *btf_data,
- u32 btf_data_size)
+static int btf_parse_hdr(struct btf_verifier_env *env)
{
+ u32 hdr_len, hdr_copy, btf_data_size;
const struct btf_header *hdr;
- u32 hdr_len, hdr_copy;
- /*
- * Minimal part of the "struct btf_header" that
- * contains the hdr_len.
- */
- struct btf_min_header {
- u16 magic;
- u8 version;
- u8 flags;
- u32 hdr_len;
- } __user *min_hdr;
struct btf *btf;
int err;
btf = env->btf;
- min_hdr = btf_data;
+ btf_data_size = btf->data_size;
- if (btf_data_size < sizeof(*min_hdr)) {
+ if (btf_data_size <
+ offsetof(struct btf_header, hdr_len) + sizeof(hdr->hdr_len)) {
btf_verifier_log(env, "hdr_len not found");
return -EINVAL;
}
- if (get_user(hdr_len, &min_hdr->hdr_len))
- return -EFAULT;
-
+ hdr = btf->data;
+ hdr_len = hdr->hdr_len;
if (btf_data_size < hdr_len) {
btf_verifier_log(env, "btf_header not found");
return -EINVAL;
}
- err = bpf_check_uarg_tail_zero(btf_data, sizeof(btf->hdr), hdr_len);
- if (err) {
- if (err == -E2BIG)
- btf_verifier_log(env, "Unsupported btf_header");
- return err;
+ /* Ensure the unsupported header fields are zero */
+ if (hdr_len > sizeof(btf->hdr)) {
+ u8 *expected_zero = btf->data + sizeof(btf->hdr);
+ u8 *end = btf->data + hdr_len;
+
+ for (; expected_zero < end; expected_zero++) {
+ if (*expected_zero) {
+ btf_verifier_log(env, "Unsupported btf_header");
+ return -E2BIG;
+ }
+ }
}
hdr_copy = min_t(u32, hdr_len, sizeof(btf->hdr));
- if (copy_from_user(&btf->hdr, btf_data, hdr_copy))
- return -EFAULT;
+ memcpy(&btf->hdr, btf->data, hdr_copy);
hdr = &btf->hdr;
- if (hdr->hdr_len != hdr_len)
- return -EINVAL;
-
btf_verifier_log_hdr(env, btf_data_size);
if (hdr->magic != BTF_MAGIC) {
@@ -2186,10 +2177,6 @@ static struct btf *btf_parse(void __user *btf_data, u32 btf_data_size,
}
env->btf = btf;
- err = btf_parse_hdr(env, btf_data, btf_data_size);
- if (err)
- goto errout;
-
data = kvmalloc(btf_data_size, GFP_KERNEL | __GFP_NOWARN);
if (!data) {
err = -ENOMEM;
@@ -2198,13 +2185,18 @@ static struct btf *btf_parse(void __user *btf_data, u32 btf_data_size,
btf->data = data;
btf->data_size = btf_data_size;
- btf->nohdr_data = btf->data + btf->hdr.hdr_len;
if (copy_from_user(data, btf_data, btf_data_size)) {
err = -EFAULT;
goto errout;
}
+ err = btf_parse_hdr(env);
+ if (err)
+ goto errout;
+
+ btf->nohdr_data = btf->data + btf->hdr.hdr_len;
+
err = btf_parse_str_sec(env);
if (err)
goto errout;
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 7c7eeea8cffc..6377225b2082 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -365,10 +365,13 @@ void bpf_prog_kallsyms_del_all(struct bpf_prog *fp)
}
#ifdef CONFIG_BPF_JIT
+# define BPF_JIT_LIMIT_DEFAULT (PAGE_SIZE * 40000)
+
/* All BPF JIT sysctl knobs here. */
int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_ALWAYS_ON);
int bpf_jit_harden __read_mostly;
int bpf_jit_kallsyms __read_mostly;
+int bpf_jit_limit __read_mostly = BPF_JIT_LIMIT_DEFAULT;
static __always_inline void
bpf_get_prog_addr_region(const struct bpf_prog *prog,
@@ -577,27 +580,64 @@ int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
return ret;
}
+static atomic_long_t bpf_jit_current;
+
+#if defined(MODULES_VADDR)
+static int __init bpf_jit_charge_init(void)
+{
+ /* Only used as heuristic here to derive limit. */
+ bpf_jit_limit = min_t(u64, round_up((MODULES_END - MODULES_VADDR) >> 2,
+ PAGE_SIZE), INT_MAX);
+ return 0;
+}
+pure_initcall(bpf_jit_charge_init);
+#endif
+
+static int bpf_jit_charge_modmem(u32 pages)
+{
+ if (atomic_long_add_return(pages, &bpf_jit_current) >
+ (bpf_jit_limit >> PAGE_SHIFT)) {
+ if (!capable(CAP_SYS_ADMIN)) {
+ atomic_long_sub(pages, &bpf_jit_current);
+ return -EPERM;
+ }
+ }
+
+ return 0;
+}
+
+static void bpf_jit_uncharge_modmem(u32 pages)
+{
+ atomic_long_sub(pages, &bpf_jit_current);
+}
+
struct bpf_binary_header *
bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
unsigned int alignment,
bpf_jit_fill_hole_t bpf_fill_ill_insns)
{
struct bpf_binary_header *hdr;
- unsigned int size, hole, start;
+ u32 size, hole, start, pages;
/* Most of BPF filters are really small, but if some of them
* fill a page, allow at least 128 extra bytes to insert a
* random section of illegal instructions.
*/
size = round_up(proglen + sizeof(*hdr) + 128, PAGE_SIZE);
+ pages = size / PAGE_SIZE;
+
+ if (bpf_jit_charge_modmem(pages))
+ return NULL;
hdr = module_alloc(size);
- if (hdr == NULL)
+ if (!hdr) {
+ bpf_jit_uncharge_modmem(pages);
return NULL;
+ }
/* Fill space with illegal/arch-dep instructions. */
bpf_fill_ill_insns(hdr, size);
- hdr->pages = size / PAGE_SIZE;
+ hdr->pages = pages;
hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)),
PAGE_SIZE - sizeof(*hdr));
start = (get_random_int() % hole) & ~(alignment - 1);
@@ -610,7 +650,10 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
void bpf_jit_binary_free(struct bpf_binary_header *hdr)
{
+ u32 pages = hdr->pages;
+
module_memfree(hdr);
+ bpf_jit_uncharge_modmem(pages);
}
/* This symbol is only overridden by archs that have different
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 141710b82a6c..191b79948424 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -512,8 +512,7 @@ static int dev_map_notification(struct notifier_block *notifier,
struct bpf_dtab_netdev *dev, *odev;
dev = READ_ONCE(dtab->netdev_map[i]);
- if (!dev ||
- dev->dev->ifindex != netdev->ifindex)
+ if (!dev || netdev != dev->dev)
continue;
odev = cmpxchg(&dtab->netdev_map[i], dev, NULL);
if (dev == odev)
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index ab0d5e3f9892..a74972b07e74 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -99,7 +99,6 @@ BPF_CALL_2(bpf_map_pop_elem, struct bpf_map *, map, void *, value)
const struct bpf_func_proto bpf_map_pop_elem_proto = {
.func = bpf_map_pop_elem,
.gpl_only = false,
- .pkt_access = true,
.ret_type = RET_INTEGER,
.arg1_type = ARG_CONST_MAP_PTR,
.arg2_type = ARG_PTR_TO_UNINIT_MAP_VALUE,
@@ -113,7 +112,6 @@ BPF_CALL_2(bpf_map_peek_elem, struct bpf_map *, map, void *, value)
const struct bpf_func_proto bpf_map_peek_elem_proto = {
.func = bpf_map_pop_elem,
.gpl_only = false,
- .pkt_access = true,
.ret_type = RET_INTEGER,
.arg1_type = ARG_CONST_MAP_PTR,
.arg2_type = ARG_PTR_TO_UNINIT_MAP_VALUE,
diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c
index 12a93fb37449..8bbd72d3a121 100644
--- a/kernel/bpf/queue_stack_maps.c
+++ b/kernel/bpf/queue_stack_maps.c
@@ -122,6 +122,7 @@ static int __queue_map_get(struct bpf_map *map, void *value, bool delete)
raw_spin_lock_irqsave(&qs->lock, flags);
if (queue_stack_map_is_empty(qs)) {
+ memset(value, 0, qs->map.value_size);
err = -ENOENT;
goto out;
}
@@ -151,6 +152,7 @@ static int __stack_map_get(struct bpf_map *map, void *value, bool delete)
raw_spin_lock_irqsave(&qs->lock, flags);
if (queue_stack_map_is_empty(qs)) {
+ memset(value, 0, qs->map.value_size);
err = -ENOENT;
goto out;
}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 98fa0be35370..171a2c88e77d 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1387,21 +1387,24 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
enum bpf_access_type t)
{
switch (env->prog->type) {
+ /* Program types only with direct read access go here! */
case BPF_PROG_TYPE_LWT_IN:
case BPF_PROG_TYPE_LWT_OUT:
case BPF_PROG_TYPE_LWT_SEG6LOCAL:
case BPF_PROG_TYPE_SK_REUSEPORT:
- /* dst_input() and dst_output() can't write for now */
+ case BPF_PROG_TYPE_FLOW_DISSECTOR:
+ case BPF_PROG_TYPE_CGROUP_SKB:
if (t == BPF_WRITE)
return false;
/* fallthrough */
+
+ /* Program types with direct read + write access go here! */
case BPF_PROG_TYPE_SCHED_CLS:
case BPF_PROG_TYPE_SCHED_ACT:
case BPF_PROG_TYPE_XDP:
case BPF_PROG_TYPE_LWT_XMIT:
case BPF_PROG_TYPE_SK_SKB:
case BPF_PROG_TYPE_SK_MSG:
- case BPF_PROG_TYPE_FLOW_DISSECTOR:
if (meta)
return meta->pkt_access;
@@ -5706,7 +5709,11 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
bool is_narrower_load;
u32 target_size;
- if (ops->gen_prologue) {
+ if (ops->gen_prologue || env->seen_direct_write) {
+ if (!ops->gen_prologue) {
+ verbose(env, "bpf verifier is misconfigured\n");
+ return -EINVAL;
+ }
cnt = ops->gen_prologue(insn_buf, env->seen_direct_write,
env->prog);
if (cnt >= ARRAY_SIZE(insn_buf)) {
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 4c1cf0969a80..8b79318810ad 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -55,6 +55,7 @@
#include <linux/nsproxy.h>
#include <linux/file.h>
#include <linux/sched/cputime.h>
+#include <linux/psi.h>
#include <net/sock.h>
#define CREATE_TRACE_POINTS
@@ -862,7 +863,7 @@ static void css_set_move_task(struct task_struct *task,
*/
WARN_ON_ONCE(task->flags & PF_EXITING);
- rcu_assign_pointer(task->cgroups, to_cset);
+ cgroup_move_task(task, to_cset);
list_add_tail(&task->cg_list, use_mg_tasks ? &to_cset->mg_tasks :
&to_cset->tasks);
}
@@ -3446,6 +3447,21 @@ static int cpu_stat_show(struct seq_file *seq, void *v)
return ret;
}
+#ifdef CONFIG_PSI
+static int cgroup_io_pressure_show(struct seq_file *seq, void *v)
+{
+ return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_IO);
+}
+static int cgroup_memory_pressure_show(struct seq_file *seq, void *v)
+{
+ return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_MEM);
+}
+static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v)
+{
+ return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_CPU);
+}
+#endif
+
static int cgroup_file_open(struct kernfs_open_file *of)
{
struct cftype *cft = of->kn->priv;
@@ -4576,6 +4592,23 @@ static struct cftype cgroup_base_files[] = {
.flags = CFTYPE_NOT_ON_ROOT,
.seq_show = cpu_stat_show,
},
+#ifdef CONFIG_PSI
+ {
+ .name = "io.pressure",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = cgroup_io_pressure_show,
+ },
+ {
+ .name = "memory.pressure",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = cgroup_memory_pressure_show,
+ },
+ {
+ .name = "cpu.pressure",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = cgroup_cpu_pressure_show,
+ },
+#endif
{ } /* terminate */
};
@@ -4636,6 +4669,7 @@ static void css_free_rwork_fn(struct work_struct *work)
*/
cgroup_put(cgroup_parent(cgrp));
kernfs_put(cgrp->kn);
+ psi_cgroup_free(cgrp);
if (cgroup_on_dfl(cgrp))
cgroup_rstat_exit(cgrp);
kfree(cgrp);
@@ -4892,10 +4926,15 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
cgrp->self.parent = &parent->self;
cgrp->root = root;
cgrp->level = level;
- ret = cgroup_bpf_inherit(cgrp);
+
+ ret = psi_cgroup_alloc(cgrp);
if (ret)
goto out_idr_free;
+ ret = cgroup_bpf_inherit(cgrp);
+ if (ret)
+ goto out_psi_free;
+
for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) {
cgrp->ancestor_ids[tcgrp->level] = tcgrp->id;
@@ -4933,6 +4972,8 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
return cgrp;
+out_psi_free:
+ psi_cgroup_free(cgrp);
out_idr_free:
cgroup_idr_remove(&root->cgroup_idr, cgrp->id);
out_stat_exit:
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 2ddfce8f1e8f..bb4fe4e1a601 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -2556,16 +2556,11 @@ static int kdb_summary(int argc, const char **argv)
}
kdb_printf("%02ld:%02ld\n", val.uptime/(60*60), (val.uptime/60)%60);
- /* lifted from fs/proc/proc_misc.c::loadavg_read_proc() */
-
-#define LOAD_INT(x) ((x) >> FSHIFT)
-#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
kdb_printf("load avg %ld.%02ld %ld.%02ld %ld.%02ld\n",
LOAD_INT(val.loads[0]), LOAD_FRAC(val.loads[0]),
LOAD_INT(val.loads[1]), LOAD_FRAC(val.loads[1]),
LOAD_INT(val.loads[2]), LOAD_FRAC(val.loads[2]));
-#undef LOAD_INT
-#undef LOAD_FRAC
+
/* Display in kilobytes */
#define K(x) ((x) << (PAGE_SHIFT - 10))
kdb_printf("\nMemTotal: %8lu kB\nMemFree: %8lu kB\n"
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index ca8ac2824f0b..2a12b988c717 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -135,9 +135,12 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
d->swapin_delay_total = (tmp < d->swapin_delay_total) ? 0 : tmp;
tmp = d->freepages_delay_total + tsk->delays->freepages_delay;
d->freepages_delay_total = (tmp < d->freepages_delay_total) ? 0 : tmp;
+ tmp = d->thrashing_delay_total + tsk->delays->thrashing_delay;
+ d->thrashing_delay_total = (tmp < d->thrashing_delay_total) ? 0 : tmp;
d->blkio_count += tsk->delays->blkio_count;
d->swapin_count += tsk->delays->swapin_count;
d->freepages_count += tsk->delays->freepages_count;
+ d->thrashing_count += tsk->delays->thrashing_count;
raw_spin_unlock_irqrestore(&tsk->delays->lock, flags);
return 0;
@@ -169,3 +172,15 @@ void __delayacct_freepages_end(void)
&current->delays->freepages_count);
}
+void __delayacct_thrashing_start(void)
+{
+ current->delays->thrashing_start = ktime_get_ns();
+}
+
+void __delayacct_thrashing_end(void)
+{
+ delayacct_end(&current->delays->lock,
+ &current->delays->thrashing_start,
+ &current->delays->thrashing_delay,
+ &current->delays->thrashing_count);
+}
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 87a6bc2a96c0..f14c376937e5 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -14,8 +14,6 @@
#include <linux/pfn.h>
#include <linux/set_memory.h>
-#define DIRECT_MAPPING_ERROR 0
-
/*
* Most architectures use ZONE_DMA for the first 16 Megabytes, but
* some use it for entirely different regions:
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 4f8a6dbf0b60..ebecaf255ea2 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -21,6 +21,7 @@
#include <linux/cache.h>
#include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
#include <linux/mm.h>
#include <linux/export.h>
#include <linux/spinlock.h>
@@ -73,13 +74,6 @@ static phys_addr_t io_tlb_start, io_tlb_end;
static unsigned long io_tlb_nslabs;
/*
- * When the IOMMU overflows we return a fallback buffer. This sets the size.
- */
-static unsigned long io_tlb_overflow = 32*1024;
-
-static phys_addr_t io_tlb_overflow_buffer;
-
-/*
* This is a free list describing the number of free entries available from
* each index
*/
@@ -126,7 +120,6 @@ setup_io_tlb_npages(char *str)
return 0;
}
early_param("swiotlb", setup_io_tlb_npages);
-/* make io_tlb_overflow tunable too? */
unsigned long swiotlb_nr_tbl(void)
{
@@ -194,16 +187,10 @@ void __init swiotlb_update_mem_attributes(void)
bytes = PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT);
set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT);
memset(vaddr, 0, bytes);
-
- vaddr = phys_to_virt(io_tlb_overflow_buffer);
- bytes = PAGE_ALIGN(io_tlb_overflow);
- set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT);
- memset(vaddr, 0, bytes);
}
int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
{
- void *v_overflow_buffer;
unsigned long i, bytes;
bytes = nslabs << IO_TLB_SHIFT;
@@ -213,17 +200,6 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
io_tlb_end = io_tlb_start + bytes;
/*
- * Get the overflow emergency buffer
- */
- v_overflow_buffer = memblock_virt_alloc_low_nopanic(
- PAGE_ALIGN(io_tlb_overflow),
- PAGE_SIZE);
- if (!v_overflow_buffer)
- return -ENOMEM;
-
- io_tlb_overflow_buffer = __pa(v_overflow_buffer);
-
- /*
* Allocate and initialize the free list array. This array is used
* to find contiguous free memory regions of size up to IO_TLB_SEGSIZE
* between io_tlb_start and io_tlb_end.
@@ -330,7 +306,6 @@ int
swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
{
unsigned long i, bytes;
- unsigned char *v_overflow_buffer;
bytes = nslabs << IO_TLB_SHIFT;
@@ -342,19 +317,6 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
memset(tlb, 0, bytes);
/*
- * Get the overflow emergency buffer
- */
- v_overflow_buffer = (void *)__get_free_pages(GFP_DMA,
- get_order(io_tlb_overflow));
- if (!v_overflow_buffer)
- goto cleanup2;
-
- set_memory_decrypted((unsigned long)v_overflow_buffer,
- io_tlb_overflow >> PAGE_SHIFT);
- memset(v_overflow_buffer, 0, io_tlb_overflow);
- io_tlb_overflow_buffer = virt_to_phys(v_overflow_buffer);
-
- /*
* Allocate and initialize the free list array. This array is used
* to find contiguous free memory regions of size up to IO_TLB_SEGSIZE
* between io_tlb_start and io_tlb_end.
@@ -390,10 +352,6 @@ cleanup4:
sizeof(int)));
io_tlb_list = NULL;
cleanup3:
- free_pages((unsigned long)v_overflow_buffer,
- get_order(io_tlb_overflow));
- io_tlb_overflow_buffer = 0;
-cleanup2:
io_tlb_end = 0;
io_tlb_start = 0;
io_tlb_nslabs = 0;
@@ -407,8 +365,6 @@ void __init swiotlb_exit(void)
return;
if (late_alloc) {
- free_pages((unsigned long)phys_to_virt(io_tlb_overflow_buffer),
- get_order(io_tlb_overflow));
free_pages((unsigned long)io_tlb_orig_addr,
get_order(io_tlb_nslabs * sizeof(phys_addr_t)));
free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs *
@@ -416,8 +372,6 @@ void __init swiotlb_exit(void)
free_pages((unsigned long)phys_to_virt(io_tlb_start),
get_order(io_tlb_nslabs << IO_TLB_SHIFT));
} else {
- memblock_free_late(io_tlb_overflow_buffer,
- PAGE_ALIGN(io_tlb_overflow));
memblock_free_late(__pa(io_tlb_orig_addr),
PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t)));
memblock_free_late(__pa(io_tlb_list),
@@ -429,7 +383,7 @@ void __init swiotlb_exit(void)
max_segment = 0;
}
-int is_swiotlb_buffer(phys_addr_t paddr)
+static int is_swiotlb_buffer(phys_addr_t paddr)
{
return paddr >= io_tlb_start && paddr < io_tlb_end;
}
@@ -591,26 +545,6 @@ found:
}
/*
- * Allocates bounce buffer and returns its physical address.
- */
-static phys_addr_t
-map_single(struct device *hwdev, phys_addr_t phys, size_t size,
- enum dma_data_direction dir, unsigned long attrs)
-{
- dma_addr_t start_dma_addr;
-
- if (swiotlb_force == SWIOTLB_NO_FORCE) {
- dev_warn_ratelimited(hwdev, "Cannot do DMA to address %pa\n",
- &phys);
- return SWIOTLB_MAP_ERROR;
- }
-
- start_dma_addr = __phys_to_dma(hwdev, io_tlb_start);
- return swiotlb_tbl_map_single(hwdev, start_dma_addr, phys, size,
- dir, attrs);
-}
-
-/*
* tlb_addr is the physical address of the bounce buffer to unmap.
*/
void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
@@ -689,104 +623,32 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr,
}
}
-static inline bool dma_coherent_ok(struct device *dev, dma_addr_t addr,
- size_t size)
-{
- u64 mask = DMA_BIT_MASK(32);
-
- if (dev && dev->coherent_dma_mask)
- mask = dev->coherent_dma_mask;
- return addr + size - 1 <= mask;
-}
-
-static void *
-swiotlb_alloc_buffer(struct device *dev, size_t size, dma_addr_t *dma_handle,
- unsigned long attrs)
+static dma_addr_t swiotlb_bounce_page(struct device *dev, phys_addr_t *phys,
+ size_t size, enum dma_data_direction dir, unsigned long attrs)
{
- phys_addr_t phys_addr;
-
- if (swiotlb_force == SWIOTLB_NO_FORCE)
- goto out_warn;
-
- phys_addr = swiotlb_tbl_map_single(dev,
- __phys_to_dma(dev, io_tlb_start),
- 0, size, DMA_FROM_DEVICE, attrs);
- if (phys_addr == SWIOTLB_MAP_ERROR)
- goto out_warn;
-
- *dma_handle = __phys_to_dma(dev, phys_addr);
- if (!dma_coherent_ok(dev, *dma_handle, size))
- goto out_unmap;
-
- memset(phys_to_virt(phys_addr), 0, size);
- return phys_to_virt(phys_addr);
+ dma_addr_t dma_addr;
-out_unmap:
- dev_warn(dev, "hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n",
- (unsigned long long)dev->coherent_dma_mask,
- (unsigned long long)*dma_handle);
-
- /*
- * DMA_TO_DEVICE to avoid memcpy in unmap_single.
- * DMA_ATTR_SKIP_CPU_SYNC is optional.
- */
- swiotlb_tbl_unmap_single(dev, phys_addr, size, DMA_TO_DEVICE,
- DMA_ATTR_SKIP_CPU_SYNC);
-out_warn:
- if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) {
- dev_warn(dev,
- "swiotlb: coherent allocation failed, size=%zu\n",
- size);
- dump_stack();
+ if (unlikely(swiotlb_force == SWIOTLB_NO_FORCE)) {
+ dev_warn_ratelimited(dev,
+ "Cannot do DMA to address %pa\n", phys);
+ return DIRECT_MAPPING_ERROR;
}
- return NULL;
-}
-
-static bool swiotlb_free_buffer(struct device *dev, size_t size,
- dma_addr_t dma_addr)
-{
- phys_addr_t phys_addr = dma_to_phys(dev, dma_addr);
- WARN_ON_ONCE(irqs_disabled());
-
- if (!is_swiotlb_buffer(phys_addr))
- return false;
-
- /*
- * DMA_TO_DEVICE to avoid memcpy in swiotlb_tbl_unmap_single.
- * DMA_ATTR_SKIP_CPU_SYNC is optional.
- */
- swiotlb_tbl_unmap_single(dev, phys_addr, size, DMA_TO_DEVICE,
- DMA_ATTR_SKIP_CPU_SYNC);
- return true;
-}
-
-static void
-swiotlb_full(struct device *dev, size_t size, enum dma_data_direction dir,
- int do_panic)
-{
- if (swiotlb_force == SWIOTLB_NO_FORCE)
- return;
-
- /*
- * Ran out of IOMMU space for this operation. This is very bad.
- * Unfortunately the drivers cannot handle this operation properly.
- * unless they check for dma_mapping_error (most don't)
- * When the mapping is small enough return a static buffer to limit
- * the damage, or panic when the transfer is too big.
- */
- dev_err_ratelimited(dev, "DMA: Out of SW-IOMMU space for %zu bytes\n",
- size);
+ /* Oh well, have to allocate and map a bounce buffer. */
+ *phys = swiotlb_tbl_map_single(dev, __phys_to_dma(dev, io_tlb_start),
+ *phys, size, dir, attrs);
+ if (*phys == SWIOTLB_MAP_ERROR)
+ return DIRECT_MAPPING_ERROR;
- if (size <= io_tlb_overflow || !do_panic)
- return;
+ /* Ensure that the address returned is DMA'ble */
+ dma_addr = __phys_to_dma(dev, *phys);
+ if (unlikely(!dma_capable(dev, dma_addr, size))) {
+ swiotlb_tbl_unmap_single(dev, *phys, size, dir,
+ attrs | DMA_ATTR_SKIP_CPU_SYNC);
+ return DIRECT_MAPPING_ERROR;
+ }
- if (dir == DMA_BIDIRECTIONAL)
- panic("DMA: Random memory could be DMA accessed\n");
- if (dir == DMA_FROM_DEVICE)
- panic("DMA: Random memory could be DMA written\n");
- if (dir == DMA_TO_DEVICE)
- panic("DMA: Random memory could be DMA read\n");
+ return dma_addr;
}
/*
@@ -801,7 +663,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
enum dma_data_direction dir,
unsigned long attrs)
{
- phys_addr_t map, phys = page_to_phys(page) + offset;
+ phys_addr_t phys = page_to_phys(page) + offset;
dma_addr_t dev_addr = phys_to_dma(dev, phys);
BUG_ON(dir == DMA_NONE);
@@ -810,28 +672,17 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
* we can safely return the device addr and not worry about bounce
* buffering it.
*/
- if (dma_capable(dev, dev_addr, size) && swiotlb_force != SWIOTLB_FORCE)
- return dev_addr;
-
- trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force);
-
- /* Oh well, have to allocate and map a bounce buffer. */
- map = map_single(dev, phys, size, dir, attrs);
- if (map == SWIOTLB_MAP_ERROR) {
- swiotlb_full(dev, size, dir, 1);
- return __phys_to_dma(dev, io_tlb_overflow_buffer);
+ if (!dma_capable(dev, dev_addr, size) ||
+ swiotlb_force == SWIOTLB_FORCE) {
+ trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force);
+ dev_addr = swiotlb_bounce_page(dev, &phys, size, dir, attrs);
}
- dev_addr = __phys_to_dma(dev, map);
+ if (!dev_is_dma_coherent(dev) &&
+ (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
+ arch_sync_dma_for_device(dev, phys, size, dir);
- /* Ensure that the address returned is DMA'ble */
- if (dma_capable(dev, dev_addr, size))
- return dev_addr;
-
- attrs |= DMA_ATTR_SKIP_CPU_SYNC;
- swiotlb_tbl_unmap_single(dev, map, size, dir, attrs);
-
- return __phys_to_dma(dev, io_tlb_overflow_buffer);
+ return dev_addr;
}
/*
@@ -842,14 +693,18 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
* After this call, reads by the cpu to the buffer are guaranteed to see
* whatever the device wrote there.
*/
-static void unmap_single(struct device *hwdev, dma_addr_t dev_addr,
- size_t size, enum dma_data_direction dir,
- unsigned long attrs)
+void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
+ size_t size, enum dma_data_direction dir,
+ unsigned long attrs)
{
phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
BUG_ON(dir == DMA_NONE);
+ if (!dev_is_dma_coherent(hwdev) &&
+ (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
+ arch_sync_dma_for_cpu(hwdev, paddr, size, dir);
+
if (is_swiotlb_buffer(paddr)) {
swiotlb_tbl_unmap_single(hwdev, paddr, size, dir, attrs);
return;
@@ -867,13 +722,6 @@ static void unmap_single(struct device *hwdev, dma_addr_t dev_addr,
dma_mark_clean(phys_to_virt(paddr), size);
}
-void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
- size_t size, enum dma_data_direction dir,
- unsigned long attrs)
-{
- unmap_single(hwdev, dev_addr, size, dir, attrs);
-}
-
/*
* Make physical memory consistent for a single streaming mode DMA translation
* after a transfer.
@@ -893,15 +741,17 @@ swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
BUG_ON(dir == DMA_NONE);
- if (is_swiotlb_buffer(paddr)) {
+ if (!dev_is_dma_coherent(hwdev) && target == SYNC_FOR_CPU)
+ arch_sync_dma_for_cpu(hwdev, paddr, size, dir);
+
+ if (is_swiotlb_buffer(paddr))
swiotlb_tbl_sync_single(hwdev, paddr, size, dir, target);
- return;
- }
- if (dir != DMA_FROM_DEVICE)
- return;
+ if (!dev_is_dma_coherent(hwdev) && target == SYNC_FOR_DEVICE)
+ arch_sync_dma_for_device(hwdev, paddr, size, dir);
- dma_mark_clean(phys_to_virt(paddr), size);
+ if (!is_swiotlb_buffer(paddr) && dir == DMA_FROM_DEVICE)
+ dma_mark_clean(phys_to_virt(paddr), size);
}
void
@@ -925,48 +775,31 @@ swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr,
* appropriate dma address and length. They are obtained via
* sg_dma_{address,length}(SG).
*
- * NOTE: An implementation may be able to use a smaller number of
- * DMA address/length pairs than there are SG table elements.
- * (for example via virtual mapping capabilities)
- * The routine returns the number of addr/length pairs actually
- * used, at most nents.
- *
* Device ownership issues as mentioned above for swiotlb_map_page are the
* same here.
*/
int
-swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
+swiotlb_map_sg_attrs(struct device *dev, struct scatterlist *sgl, int nelems,
enum dma_data_direction dir, unsigned long attrs)
{
struct scatterlist *sg;
int i;
- BUG_ON(dir == DMA_NONE);
-
for_each_sg(sgl, sg, nelems, i) {
- phys_addr_t paddr = sg_phys(sg);
- dma_addr_t dev_addr = phys_to_dma(hwdev, paddr);
-
- if (swiotlb_force == SWIOTLB_FORCE ||
- !dma_capable(hwdev, dev_addr, sg->length)) {
- phys_addr_t map = map_single(hwdev, sg_phys(sg),
- sg->length, dir, attrs);
- if (map == SWIOTLB_MAP_ERROR) {
- /* Don't panic here, we expect map_sg users
- to do proper error handling. */
- swiotlb_full(hwdev, sg->length, dir, 0);
- attrs |= DMA_ATTR_SKIP_CPU_SYNC;
- swiotlb_unmap_sg_attrs(hwdev, sgl, i, dir,
- attrs);
- sg_dma_len(sgl) = 0;
- return 0;
- }
- sg->dma_address = __phys_to_dma(hwdev, map);
- } else
- sg->dma_address = dev_addr;
+ sg->dma_address = swiotlb_map_page(dev, sg_page(sg), sg->offset,
+ sg->length, dir, attrs);
+ if (sg->dma_address == DIRECT_MAPPING_ERROR)
+ goto out_error;
sg_dma_len(sg) = sg->length;
}
+
return nelems;
+
+out_error:
+ swiotlb_unmap_sg_attrs(dev, sgl, i, dir,
+ attrs | DMA_ATTR_SKIP_CPU_SYNC);
+ sg_dma_len(sgl) = 0;
+ return 0;
}
/*
@@ -984,7 +817,7 @@ swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
BUG_ON(dir == DMA_NONE);
for_each_sg(sgl, sg, nelems, i)
- unmap_single(hwdev, sg->dma_address, sg_dma_len(sg), dir,
+ swiotlb_unmap_page(hwdev, sg->dma_address, sg_dma_len(sg), dir,
attrs);
}
@@ -1022,12 +855,6 @@ swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE);
}
-int
-swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
-{
- return (dma_addr == __phys_to_dma(hwdev, io_tlb_overflow_buffer));
-}
-
/*
* Return whether the given device DMA address mask can be supported
* properly. For example, if your device can only drive the low 24-bits
@@ -1040,39 +867,10 @@ swiotlb_dma_supported(struct device *hwdev, u64 mask)
return __phys_to_dma(hwdev, io_tlb_end - 1) <= mask;
}
-void *swiotlb_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
- gfp_t gfp, unsigned long attrs)
-{
- void *vaddr;
-
- /* temporary workaround: */
- if (gfp & __GFP_NOWARN)
- attrs |= DMA_ATTR_NO_WARN;
-
- /*
- * Don't print a warning when the first allocation attempt fails.
- * swiotlb_alloc_coherent() will print a warning when the DMA memory
- * allocation ultimately failed.
- */
- gfp |= __GFP_NOWARN;
-
- vaddr = dma_direct_alloc(dev, size, dma_handle, gfp, attrs);
- if (!vaddr)
- vaddr = swiotlb_alloc_buffer(dev, size, dma_handle, attrs);
- return vaddr;
-}
-
-void swiotlb_free(struct device *dev, size_t size, void *vaddr,
- dma_addr_t dma_addr, unsigned long attrs)
-{
- if (!swiotlb_free_buffer(dev, size, dma_addr))
- dma_direct_free(dev, size, vaddr, dma_addr, attrs);
-}
-
const struct dma_map_ops swiotlb_dma_ops = {
- .mapping_error = swiotlb_dma_mapping_error,
- .alloc = swiotlb_alloc,
- .free = swiotlb_free,
+ .mapping_error = dma_direct_mapping_error,
+ .alloc = dma_direct_alloc,
+ .free = dma_direct_free,
.sync_single_for_cpu = swiotlb_sync_single_for_cpu,
.sync_single_for_device = swiotlb_sync_single_for_device,
.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
diff --git a/kernel/fork.c b/kernel/fork.c
index f0b58479534f..8f82a3bdcb8f 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -223,9 +223,14 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
return s->addr;
}
+ /*
+ * Allocated stacks are cached and later reused by new threads,
+ * so memcg accounting is performed manually on assigning/releasing
+ * stacks to tasks. Drop __GFP_ACCOUNT.
+ */
stack = __vmalloc_node_range(THREAD_SIZE, THREAD_ALIGN,
VMALLOC_START, VMALLOC_END,
- THREADINFO_GFP,
+ THREADINFO_GFP & ~__GFP_ACCOUNT,
PAGE_KERNEL,
0, node, __builtin_return_address(0));
@@ -248,9 +253,19 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
static inline void free_thread_stack(struct task_struct *tsk)
{
#ifdef CONFIG_VMAP_STACK
- if (task_stack_vm_area(tsk)) {
+ struct vm_struct *vm = task_stack_vm_area(tsk);
+
+ if (vm) {
int i;
+ for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
+ mod_memcg_page_state(vm->pages[i],
+ MEMCG_KERNEL_STACK_KB,
+ -(int)(PAGE_SIZE / 1024));
+
+ memcg_kmem_uncharge(vm->pages[i], 0);
+ }
+
for (i = 0; i < NR_CACHED_STACKS; i++) {
if (this_cpu_cmpxchg(cached_stacks[i],
NULL, tsk->stack_vm_area) != NULL)
@@ -351,10 +366,6 @@ static void account_kernel_stack(struct task_struct *tsk, int account)
NR_KERNEL_STACK_KB,
PAGE_SIZE / 1024 * account);
}
-
- /* All stack pages belong to the same memcg. */
- mod_memcg_page_state(vm->pages[0], MEMCG_KERNEL_STACK_KB,
- account * (THREAD_SIZE / 1024));
} else {
/*
* All stack pages are in the same zone and belong to the
@@ -370,6 +381,35 @@ static void account_kernel_stack(struct task_struct *tsk, int account)
}
}
+static int memcg_charge_kernel_stack(struct task_struct *tsk)
+{
+#ifdef CONFIG_VMAP_STACK
+ struct vm_struct *vm = task_stack_vm_area(tsk);
+ int ret;
+
+ if (vm) {
+ int i;
+
+ for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
+ /*
+ * If memcg_kmem_charge() fails, page->mem_cgroup
+ * pointer is NULL, and both memcg_kmem_uncharge()
+ * and mod_memcg_page_state() in free_thread_stack()
+ * will ignore this page. So it's safe.
+ */
+ ret = memcg_kmem_charge(vm->pages[i], GFP_KERNEL, 0);
+ if (ret)
+ return ret;
+
+ mod_memcg_page_state(vm->pages[i],
+ MEMCG_KERNEL_STACK_KB,
+ PAGE_SIZE / 1024);
+ }
+ }
+#endif
+ return 0;
+}
+
static void release_task_stack(struct task_struct *tsk)
{
if (WARN_ON(tsk->state != TASK_DEAD))
@@ -807,6 +847,9 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
if (!stack)
goto free_tsk;
+ if (memcg_charge_kernel_stack(tsk))
+ goto free_stack;
+
stack_vm_area = task_stack_vm_area(tsk);
err = arch_dup_task_struct(tsk, orig);
@@ -1779,6 +1822,10 @@ static __latent_entropy struct task_struct *copy_process(
p->default_timer_slack_ns = current->timer_slack_ns;
+#ifdef CONFIG_PSI
+ p->psi_flags = 0;
+#endif
+
task_io_accounting_init(&p->ioac);
acct_clear_integrals(p);
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 02a0b01380d8..f3a04994e063 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -37,7 +37,7 @@ extern const u8 kallsyms_names[] __weak;
* Tell the compiler that the count isn't in the small data section if the arch
* has one (eg: FRV).
*/
-extern const unsigned long kallsyms_num_syms
+extern const unsigned int kallsyms_num_syms
__attribute__((weak, section(".rodata")));
extern const unsigned long kallsyms_relative_base
@@ -46,7 +46,7 @@ __attribute__((weak, section(".rodata")));
extern const u8 kallsyms_token_table[] __weak;
extern const u16 kallsyms_token_index[] __weak;
-extern const unsigned long kallsyms_markers[] __weak;
+extern const unsigned int kallsyms_markers[] __weak;
/*
* Expand a compressed symbol data into the resulting uncompressed string,
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 5b8600d39931..9eced2cc9f94 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -1,47 +1,21 @@
/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright(c) 2015 Intel Corporation. All rights reserved. */
-#include <linux/radix-tree.h>
#include <linux/device.h>
-#include <linux/types.h>
-#include <linux/pfn_t.h>
#include <linux/io.h>
#include <linux/kasan.h>
-#include <linux/mm.h>
#include <linux/memory_hotplug.h>
+#include <linux/mm.h>
+#include <linux/pfn_t.h>
#include <linux/swap.h>
#include <linux/swapops.h>
+#include <linux/types.h>
#include <linux/wait_bit.h>
+#include <linux/xarray.h>
-static DEFINE_MUTEX(pgmap_lock);
-static RADIX_TREE(pgmap_radix, GFP_KERNEL);
+static DEFINE_XARRAY(pgmap_array);
#define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1)
#define SECTION_SIZE (1UL << PA_SECTION_SHIFT)
-static unsigned long order_at(struct resource *res, unsigned long pgoff)
-{
- unsigned long phys_pgoff = PHYS_PFN(res->start) + pgoff;
- unsigned long nr_pages, mask;
-
- nr_pages = PHYS_PFN(resource_size(res));
- if (nr_pages == pgoff)
- return ULONG_MAX;
-
- /*
- * What is the largest aligned power-of-2 range available from
- * this resource pgoff to the end of the resource range,
- * considering the alignment of the current pgoff?
- */
- mask = phys_pgoff | rounddown_pow_of_two(nr_pages - pgoff);
- if (!mask)
- return ULONG_MAX;
-
- return find_first_bit(&mask, BITS_PER_LONG);
-}
-
-#define foreach_order_pgoff(res, order, pgoff) \
- for (pgoff = 0, order = order_at((res), pgoff); order < ULONG_MAX; \
- pgoff += 1UL << order, order = order_at((res), pgoff))
-
#if IS_ENABLED(CONFIG_DEVICE_PRIVATE)
vm_fault_t device_private_entry_fault(struct vm_area_struct *vma,
unsigned long addr,
@@ -70,18 +44,10 @@ vm_fault_t device_private_entry_fault(struct vm_area_struct *vma,
EXPORT_SYMBOL(device_private_entry_fault);
#endif /* CONFIG_DEVICE_PRIVATE */
-static void pgmap_radix_release(struct resource *res, unsigned long end_pgoff)
+static void pgmap_array_delete(struct resource *res)
{
- unsigned long pgoff, order;
-
- mutex_lock(&pgmap_lock);
- foreach_order_pgoff(res, order, pgoff) {
- if (pgoff >= end_pgoff)
- break;
- radix_tree_delete(&pgmap_radix, PHYS_PFN(res->start) + pgoff);
- }
- mutex_unlock(&pgmap_lock);
-
+ xa_store_range(&pgmap_array, PHYS_PFN(res->start), PHYS_PFN(res->end),
+ NULL, GFP_KERNEL);
synchronize_rcu();
}
@@ -142,7 +108,7 @@ static void devm_memremap_pages_release(void *data)
mem_hotplug_done();
untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
- pgmap_radix_release(res, -1);
+ pgmap_array_delete(res);
dev_WARN_ONCE(dev, pgmap->altmap.alloc,
"%s: failed to free all reserved pages\n", __func__);
}
@@ -175,10 +141,9 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
struct vmem_altmap *altmap = pgmap->altmap_valid ?
&pgmap->altmap : NULL;
struct resource *res = &pgmap->res;
- unsigned long pfn, pgoff, order;
+ struct dev_pagemap *conflict_pgmap;
pgprot_t pgprot = PAGE_KERNEL;
int error, nid, is_ram;
- struct dev_pagemap *conflict_pgmap;
align_start = res->start & ~(SECTION_SIZE - 1);
align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
@@ -216,20 +181,10 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
pgmap->dev = dev;
- mutex_lock(&pgmap_lock);
- error = 0;
-
- foreach_order_pgoff(res, order, pgoff) {
- error = __radix_tree_insert(&pgmap_radix,
- PHYS_PFN(res->start) + pgoff, order, pgmap);
- if (error) {
- dev_err(dev, "%s: failed: %d\n", __func__, error);
- break;
- }
- }
- mutex_unlock(&pgmap_lock);
+ error = xa_err(xa_store_range(&pgmap_array, PHYS_PFN(res->start),
+ PHYS_PFN(res->end), pgmap, GFP_KERNEL));
if (error)
- goto err_radix;
+ goto err_array;
nid = dev_to_node(dev);
if (nid < 0)
@@ -256,19 +211,14 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
if (error)
goto err_add_memory;
- for_each_device_pfn(pfn, pgmap) {
- struct page *page = pfn_to_page(pfn);
-
- /*
- * ZONE_DEVICE pages union ->lru with a ->pgmap back
- * pointer. It is a bug if a ZONE_DEVICE page is ever
- * freed or placed on a driver-private list. Seed the
- * storage with LIST_POISON* values.
- */
- list_del(&page->lru);
- page->pgmap = pgmap;
- percpu_ref_get(pgmap->ref);
- }
+ /*
+ * Initialization of the pages has been deferred until now in order
+ * to allow us to do the work while not holding the hotplug lock.
+ */
+ memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
+ align_start >> PAGE_SHIFT,
+ align_size >> PAGE_SHIFT, pgmap);
+ percpu_ref_get_many(pgmap->ref, pfn_end(pgmap) - pfn_first(pgmap));
devm_add_action(dev, devm_memremap_pages_release, pgmap);
@@ -279,8 +229,8 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
err_kasan:
untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
err_pfn_remap:
- err_radix:
- pgmap_radix_release(res, pgoff);
+ pgmap_array_delete(res);
+ err_array:
return ERR_PTR(error);
}
EXPORT_SYMBOL(devm_memremap_pages);
@@ -320,7 +270,7 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
/* fall back to slow path lookup */
rcu_read_lock();
- pgmap = radix_tree_lookup(&pgmap_radix, PHYS_PFN(phys));
+ pgmap = xa_load(&pgmap_array, PHYS_PFN(phys));
if (pgmap && !percpu_ref_tryget_live(pgmap->ref))
pgmap = NULL;
rcu_read_unlock();
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 7fe183404c38..21fb5a5662b5 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -29,3 +29,4 @@ obj-$(CONFIG_CPU_FREQ) += cpufreq.o
obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o
obj-$(CONFIG_MEMBARRIER) += membarrier.o
obj-$(CONFIG_CPU_ISOLATION) += isolation.o
+obj-$(CONFIG_PSI) += psi.o
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2e696b03e99d..fd2fce8a001b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -722,8 +722,10 @@ static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
if (!(flags & ENQUEUE_NOCLOCK))
update_rq_clock(rq);
- if (!(flags & ENQUEUE_RESTORE))
+ if (!(flags & ENQUEUE_RESTORE)) {
sched_info_queued(rq, p);
+ psi_enqueue(p, flags & ENQUEUE_WAKEUP);
+ }
p->sched_class->enqueue_task(rq, p, flags);
}
@@ -733,8 +735,10 @@ static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
if (!(flags & DEQUEUE_NOCLOCK))
update_rq_clock(rq);
- if (!(flags & DEQUEUE_SAVE))
+ if (!(flags & DEQUEUE_SAVE)) {
sched_info_dequeued(rq, p);
+ psi_dequeue(p, flags & DEQUEUE_SLEEP);
+ }
p->sched_class->dequeue_task(rq, p, flags);
}
@@ -2037,6 +2041,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags);
if (task_cpu(p) != cpu) {
wake_flags |= WF_MIGRATED;
+ psi_ttwu_dequeue(p);
set_task_cpu(p, cpu);
}
@@ -3051,6 +3056,7 @@ void scheduler_tick(void)
curr->sched_class->task_tick(rq, curr, 0);
cpu_load_update_active(rq);
calc_global_load_tick(rq);
+ psi_task_tick(rq);
rq_unlock(rq, &rf);
@@ -4933,9 +4939,7 @@ static void do_sched_yield(void)
struct rq_flags rf;
struct rq *rq;
- local_irq_disable();
- rq = this_rq();
- rq_lock(rq, &rf);
+ rq = this_rq_lock_irq(&rf);
schedstat_inc(rq->yld_count);
current->sched_class->yield_task(rq);
@@ -6069,6 +6073,8 @@ void __init sched_init(void)
init_schedstats();
+ psi_init();
+
scheduler_running = 1;
}
diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c
index a171c1258109..28a516575c18 100644
--- a/kernel/sched/loadavg.c
+++ b/kernel/sched/loadavg.c
@@ -91,19 +91,73 @@ long calc_load_fold_active(struct rq *this_rq, long adjust)
return delta;
}
-/*
- * a1 = a0 * e + a * (1 - e)
+/**
+ * fixed_power_int - compute: x^n, in O(log n) time
+ *
+ * @x: base of the power
+ * @frac_bits: fractional bits of @x
+ * @n: power to raise @x to.
+ *
+ * By exploiting the relation between the definition of the natural power
+ * function: x^n := x*x*...*x (x multiplied by itself for n times), and
+ * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i,
+ * (where: n_i \elem {0, 1}, the binary vector representing n),
+ * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is
+ * of course trivially computable in O(log_2 n), the length of our binary
+ * vector.
*/
static unsigned long
-calc_load(unsigned long load, unsigned long exp, unsigned long active)
+fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n)
{
- unsigned long newload;
+ unsigned long result = 1UL << frac_bits;
+
+ if (n) {
+ for (;;) {
+ if (n & 1) {
+ result *= x;
+ result += 1UL << (frac_bits - 1);
+ result >>= frac_bits;
+ }
+ n >>= 1;
+ if (!n)
+ break;
+ x *= x;
+ x += 1UL << (frac_bits - 1);
+ x >>= frac_bits;
+ }
+ }
- newload = load * exp + active * (FIXED_1 - exp);
- if (active >= load)
- newload += FIXED_1-1;
+ return result;
+}
- return newload / FIXED_1;
+/*
+ * a1 = a0 * e + a * (1 - e)
+ *
+ * a2 = a1 * e + a * (1 - e)
+ * = (a0 * e + a * (1 - e)) * e + a * (1 - e)
+ * = a0 * e^2 + a * (1 - e) * (1 + e)
+ *
+ * a3 = a2 * e + a * (1 - e)
+ * = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e)
+ * = a0 * e^3 + a * (1 - e) * (1 + e + e^2)
+ *
+ * ...
+ *
+ * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1]
+ * = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e)
+ * = a0 * e^n + a * (1 - e^n)
+ *
+ * [1] application of the geometric series:
+ *
+ * n 1 - x^(n+1)
+ * S_n := \Sum x^i = -------------
+ * i=0 1 - x
+ */
+unsigned long
+calc_load_n(unsigned long load, unsigned long exp,
+ unsigned long active, unsigned int n)
+{
+ return calc_load(load, fixed_power_int(exp, FSHIFT, n), active);
}
#ifdef CONFIG_NO_HZ_COMMON
@@ -225,75 +279,6 @@ static long calc_load_nohz_fold(void)
return delta;
}
-/**
- * fixed_power_int - compute: x^n, in O(log n) time
- *
- * @x: base of the power
- * @frac_bits: fractional bits of @x
- * @n: power to raise @x to.
- *
- * By exploiting the relation between the definition of the natural power
- * function: x^n := x*x*...*x (x multiplied by itself for n times), and
- * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i,
- * (where: n_i \elem {0, 1}, the binary vector representing n),
- * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is
- * of course trivially computable in O(log_2 n), the length of our binary
- * vector.
- */
-static unsigned long
-fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n)
-{
- unsigned long result = 1UL << frac_bits;
-
- if (n) {
- for (;;) {
- if (n & 1) {
- result *= x;
- result += 1UL << (frac_bits - 1);
- result >>= frac_bits;
- }
- n >>= 1;
- if (!n)
- break;
- x *= x;
- x += 1UL << (frac_bits - 1);
- x >>= frac_bits;
- }
- }
-
- return result;
-}
-
-/*
- * a1 = a0 * e + a * (1 - e)
- *
- * a2 = a1 * e + a * (1 - e)
- * = (a0 * e + a * (1 - e)) * e + a * (1 - e)
- * = a0 * e^2 + a * (1 - e) * (1 + e)
- *
- * a3 = a2 * e + a * (1 - e)
- * = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e)
- * = a0 * e^3 + a * (1 - e) * (1 + e + e^2)
- *
- * ...
- *
- * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1]
- * = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e)
- * = a0 * e^n + a * (1 - e^n)
- *
- * [1] application of the geometric series:
- *
- * n 1 - x^(n+1)
- * S_n := \Sum x^i = -------------
- * i=0 1 - x
- */
-static unsigned long
-calc_load_n(unsigned long load, unsigned long exp,
- unsigned long active, unsigned int n)
-{
- return calc_load(load, fixed_power_int(exp, FSHIFT, n), active);
-}
-
/*
* NO_HZ can leave us missing all per-CPU ticks calling
* calc_load_fold_active(), but since a NO_HZ CPU folds its delta into
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
new file mode 100644
index 000000000000..7cdecfc010af
--- /dev/null
+++ b/kernel/sched/psi.c
@@ -0,0 +1,759 @@
+/*
+ * Pressure stall information for CPU, memory and IO
+ *
+ * Copyright (c) 2018 Facebook, Inc.
+ * Author: Johannes Weiner <hannes@cmpxchg.org>
+ *
+ * When CPU, memory and IO are contended, tasks experience delays that
+ * reduce throughput and introduce latencies into the workload. Memory
+ * and IO contention, in addition, can cause a full loss of forward
+ * progress in which the CPU goes idle.
+ *
+ * This code aggregates individual task delays into resource pressure
+ * metrics that indicate problems with both workload health and
+ * resource utilization.
+ *
+ * Model
+ *
+ * The time in which a task can execute on a CPU is our baseline for
+ * productivity. Pressure expresses the amount of time in which this
+ * potential cannot be realized due to resource contention.
+ *
+ * This concept of productivity has two components: the workload and
+ * the CPU. To measure the impact of pressure on both, we define two
+ * contention states for a resource: SOME and FULL.
+ *
+ * In the SOME state of a given resource, one or more tasks are
+ * delayed on that resource. This affects the workload's ability to
+ * perform work, but the CPU may still be executing other tasks.
+ *
+ * In the FULL state of a given resource, all non-idle tasks are
+ * delayed on that resource such that nobody is advancing and the CPU
+ * goes idle. This leaves both workload and CPU unproductive.
+ *
+ * (Naturally, the FULL state doesn't exist for the CPU resource.)
+ *
+ * SOME = nr_delayed_tasks != 0
+ * FULL = nr_delayed_tasks != 0 && nr_running_tasks == 0
+ *
+ * The percentage of wallclock time spent in those compound stall
+ * states gives pressure numbers between 0 and 100 for each resource,
+ * where the SOME percentage indicates workload slowdowns and the FULL
+ * percentage indicates reduced CPU utilization:
+ *
+ * %SOME = time(SOME) / period
+ * %FULL = time(FULL) / period
+ *
+ * Multiple CPUs
+ *
+ * The more tasks and available CPUs there are, the more work can be
+ * performed concurrently. This means that the potential that can go
+ * unrealized due to resource contention *also* scales with non-idle
+ * tasks and CPUs.
+ *
+ * Consider a scenario where 257 number crunching tasks are trying to
+ * run concurrently on 256 CPUs. If we simply aggregated the task
+ * states, we would have to conclude a CPU SOME pressure number of
+ * 100%, since *somebody* is waiting on a runqueue at all
+ * times. However, that is clearly not the amount of contention the
+ * workload is experiencing: only one out of 256 possible exceution
+ * threads will be contended at any given time, or about 0.4%.
+ *
+ * Conversely, consider a scenario of 4 tasks and 4 CPUs where at any
+ * given time *one* of the tasks is delayed due to a lack of memory.
+ * Again, looking purely at the task state would yield a memory FULL
+ * pressure number of 0%, since *somebody* is always making forward
+ * progress. But again this wouldn't capture the amount of execution
+ * potential lost, which is 1 out of 4 CPUs, or 25%.
+ *
+ * To calculate wasted potential (pressure) with multiple processors,
+ * we have to base our calculation on the number of non-idle tasks in
+ * conjunction with the number of available CPUs, which is the number
+ * of potential execution threads. SOME becomes then the proportion of
+ * delayed tasks to possibe threads, and FULL is the share of possible
+ * threads that are unproductive due to delays:
+ *
+ * threads = min(nr_nonidle_tasks, nr_cpus)
+ * SOME = min(nr_delayed_tasks / threads, 1)
+ * FULL = (threads - min(nr_running_tasks, threads)) / threads
+ *
+ * For the 257 number crunchers on 256 CPUs, this yields:
+ *
+ * threads = min(257, 256)
+ * SOME = min(1 / 256, 1) = 0.4%
+ * FULL = (256 - min(257, 256)) / 256 = 0%
+ *
+ * For the 1 out of 4 memory-delayed tasks, this yields:
+ *
+ * threads = min(4, 4)
+ * SOME = min(1 / 4, 1) = 25%
+ * FULL = (4 - min(3, 4)) / 4 = 25%
+ *
+ * [ Substitute nr_cpus with 1, and you can see that it's a natural
+ * extension of the single-CPU model. ]
+ *
+ * Implementation
+ *
+ * To assess the precise time spent in each such state, we would have
+ * to freeze the system on task changes and start/stop the state
+ * clocks accordingly. Obviously that doesn't scale in practice.
+ *
+ * Because the scheduler aims to distribute the compute load evenly
+ * among the available CPUs, we can track task state locally to each
+ * CPU and, at much lower frequency, extrapolate the global state for
+ * the cumulative stall times and the running averages.
+ *
+ * For each runqueue, we track:
+ *
+ * tSOME[cpu] = time(nr_delayed_tasks[cpu] != 0)
+ * tFULL[cpu] = time(nr_delayed_tasks[cpu] && !nr_running_tasks[cpu])
+ * tNONIDLE[cpu] = time(nr_nonidle_tasks[cpu] != 0)
+ *
+ * and then periodically aggregate:
+ *
+ * tNONIDLE = sum(tNONIDLE[i])
+ *
+ * tSOME = sum(tSOME[i] * tNONIDLE[i]) / tNONIDLE
+ * tFULL = sum(tFULL[i] * tNONIDLE[i]) / tNONIDLE
+ *
+ * %SOME = tSOME / period
+ * %FULL = tFULL / period
+ *
+ * This gives us an approximation of pressure that is practical
+ * cost-wise, yet way more sensitive and accurate than periodic
+ * sampling of the aggregate task states would be.
+ */
+
+#include <linux/sched/loadavg.h>
+#include <linux/seq_file.h>
+#include <linux/proc_fs.h>
+#include <linux/seqlock.h>
+#include <linux/cgroup.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/psi.h>
+#include "sched.h"
+
+static int psi_bug __read_mostly;
+
+bool psi_disabled __read_mostly;
+core_param(psi_disabled, psi_disabled, bool, 0644);
+
+/* Running averages - we need to be higher-res than loadavg */
+#define PSI_FREQ (2*HZ+1) /* 2 sec intervals */
+#define EXP_10s 1677 /* 1/exp(2s/10s) as fixed-point */
+#define EXP_60s 1981 /* 1/exp(2s/60s) */
+#define EXP_300s 2034 /* 1/exp(2s/300s) */
+
+/* Sampling frequency in nanoseconds */
+static u64 psi_period __read_mostly;
+
+/* System-level pressure and stall tracking */
+static DEFINE_PER_CPU(struct psi_group_cpu, system_group_pcpu);
+static struct psi_group psi_system = {
+ .pcpu = &system_group_pcpu,
+};
+
+static void psi_update_work(struct work_struct *work);
+
+static void group_init(struct psi_group *group)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu)
+ seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq);
+ group->next_update = sched_clock() + psi_period;
+ INIT_DELAYED_WORK(&group->clock_work, psi_update_work);
+ mutex_init(&group->stat_lock);
+}
+
+void __init psi_init(void)
+{
+ if (psi_disabled)
+ return;
+
+ psi_period = jiffies_to_nsecs(PSI_FREQ);
+ group_init(&psi_system);
+}
+
+static bool test_state(unsigned int *tasks, enum psi_states state)
+{
+ switch (state) {
+ case PSI_IO_SOME:
+ return tasks[NR_IOWAIT];
+ case PSI_IO_FULL:
+ return tasks[NR_IOWAIT] && !tasks[NR_RUNNING];
+ case PSI_MEM_SOME:
+ return tasks[NR_MEMSTALL];
+ case PSI_MEM_FULL:
+ return tasks[NR_MEMSTALL] && !tasks[NR_RUNNING];
+ case PSI_CPU_SOME:
+ return tasks[NR_RUNNING] > 1;
+ case PSI_NONIDLE:
+ return tasks[NR_IOWAIT] || tasks[NR_MEMSTALL] ||
+ tasks[NR_RUNNING];
+ default:
+ return false;
+ }
+}
+
+static void get_recent_times(struct psi_group *group, int cpu, u32 *times)
+{
+ struct psi_group_cpu *groupc = per_cpu_ptr(group->pcpu, cpu);
+ unsigned int tasks[NR_PSI_TASK_COUNTS];
+ u64 now, state_start;
+ unsigned int seq;
+ int s;
+
+ /* Snapshot a coherent view of the CPU state */
+ do {
+ seq = read_seqcount_begin(&groupc->seq);
+ now = cpu_clock(cpu);
+ memcpy(times, groupc->times, sizeof(groupc->times));
+ memcpy(tasks, groupc->tasks, sizeof(groupc->tasks));
+ state_start = groupc->state_start;
+ } while (read_seqcount_retry(&groupc->seq, seq));
+
+ /* Calculate state time deltas against the previous snapshot */
+ for (s = 0; s < NR_PSI_STATES; s++) {
+ u32 delta;
+ /*
+ * In addition to already concluded states, we also
+ * incorporate currently active states on the CPU,
+ * since states may last for many sampling periods.
+ *
+ * This way we keep our delta sampling buckets small
+ * (u32) and our reported pressure close to what's
+ * actually happening.
+ */
+ if (test_state(tasks, s))
+ times[s] += now - state_start;
+
+ delta = times[s] - groupc->times_prev[s];
+ groupc->times_prev[s] = times[s];
+
+ times[s] = delta;
+ }
+}
+
+static void calc_avgs(unsigned long avg[3], int missed_periods,
+ u64 time, u64 period)
+{
+ unsigned long pct;
+
+ /* Fill in zeroes for periods of no activity */
+ if (missed_periods) {
+ avg[0] = calc_load_n(avg[0], EXP_10s, 0, missed_periods);
+ avg[1] = calc_load_n(avg[1], EXP_60s, 0, missed_periods);
+ avg[2] = calc_load_n(avg[2], EXP_300s, 0, missed_periods);
+ }
+
+ /* Sample the most recent active period */
+ pct = div_u64(time * 100, period);
+ pct *= FIXED_1;
+ avg[0] = calc_load(avg[0], EXP_10s, pct);
+ avg[1] = calc_load(avg[1], EXP_60s, pct);
+ avg[2] = calc_load(avg[2], EXP_300s, pct);
+}
+
+static bool update_stats(struct psi_group *group)
+{
+ u64 deltas[NR_PSI_STATES - 1] = { 0, };
+ unsigned long missed_periods = 0;
+ unsigned long nonidle_total = 0;
+ u64 now, expires, period;
+ int cpu;
+ int s;
+
+ mutex_lock(&group->stat_lock);
+
+ /*
+ * Collect the per-cpu time buckets and average them into a
+ * single time sample that is normalized to wallclock time.
+ *
+ * For averaging, each CPU is weighted by its non-idle time in
+ * the sampling period. This eliminates artifacts from uneven
+ * loading, or even entirely idle CPUs.
+ */
+ for_each_possible_cpu(cpu) {
+ u32 times[NR_PSI_STATES];
+ u32 nonidle;
+
+ get_recent_times(group, cpu, times);
+
+ nonidle = nsecs_to_jiffies(times[PSI_NONIDLE]);
+ nonidle_total += nonidle;
+
+ for (s = 0; s < PSI_NONIDLE; s++)
+ deltas[s] += (u64)times[s] * nonidle;
+ }
+
+ /*
+ * Integrate the sample into the running statistics that are
+ * reported to userspace: the cumulative stall times and the
+ * decaying averages.
+ *
+ * Pressure percentages are sampled at PSI_FREQ. We might be
+ * called more often when the user polls more frequently than
+ * that; we might be called less often when there is no task
+ * activity, thus no data, and clock ticks are sporadic. The
+ * below handles both.
+ */
+
+ /* total= */
+ for (s = 0; s < NR_PSI_STATES - 1; s++)
+ group->total[s] += div_u64(deltas[s], max(nonidle_total, 1UL));
+
+ /* avgX= */
+ now = sched_clock();
+ expires = group->next_update;
+ if (now < expires)
+ goto out;
+ if (now - expires > psi_period)
+ missed_periods = div_u64(now - expires, psi_period);
+
+ /*
+ * The periodic clock tick can get delayed for various
+ * reasons, especially on loaded systems. To avoid clock
+ * drift, we schedule the clock in fixed psi_period intervals.
+ * But the deltas we sample out of the per-cpu buckets above
+ * are based on the actual time elapsing between clock ticks.
+ */
+ group->next_update = expires + ((1 + missed_periods) * psi_period);
+ period = now - (group->last_update + (missed_periods * psi_period));
+ group->last_update = now;
+
+ for (s = 0; s < NR_PSI_STATES - 1; s++) {
+ u32 sample;
+
+ sample = group->total[s] - group->total_prev[s];
+ /*
+ * Due to the lockless sampling of the time buckets,
+ * recorded time deltas can slip into the next period,
+ * which under full pressure can result in samples in
+ * excess of the period length.
+ *
+ * We don't want to report non-sensical pressures in
+ * excess of 100%, nor do we want to drop such events
+ * on the floor. Instead we punt any overage into the
+ * future until pressure subsides. By doing this we
+ * don't underreport the occurring pressure curve, we
+ * just report it delayed by one period length.
+ *
+ * The error isn't cumulative. As soon as another
+ * delta slips from a period P to P+1, by definition
+ * it frees up its time T in P.
+ */
+ if (sample > period)
+ sample = period;
+ group->total_prev[s] += sample;
+ calc_avgs(group->avg[s], missed_periods, sample, period);
+ }
+out:
+ mutex_unlock(&group->stat_lock);
+ return nonidle_total;
+}
+
+static void psi_update_work(struct work_struct *work)
+{
+ struct delayed_work *dwork;
+ struct psi_group *group;
+ bool nonidle;
+
+ dwork = to_delayed_work(work);
+ group = container_of(dwork, struct psi_group, clock_work);
+
+ /*
+ * If there is task activity, periodically fold the per-cpu
+ * times and feed samples into the running averages. If things
+ * are idle and there is no data to process, stop the clock.
+ * Once restarted, we'll catch up the running averages in one
+ * go - see calc_avgs() and missed_periods.
+ */
+
+ nonidle = update_stats(group);
+
+ if (nonidle) {
+ unsigned long delay = 0;
+ u64 now;
+
+ now = sched_clock();
+ if (group->next_update > now)
+ delay = nsecs_to_jiffies(group->next_update - now) + 1;
+ schedule_delayed_work(dwork, delay);
+ }
+}
+
+static void record_times(struct psi_group_cpu *groupc, int cpu,
+ bool memstall_tick)
+{
+ u32 delta;
+ u64 now;
+
+ now = cpu_clock(cpu);
+ delta = now - groupc->state_start;
+ groupc->state_start = now;
+
+ if (test_state(groupc->tasks, PSI_IO_SOME)) {
+ groupc->times[PSI_IO_SOME] += delta;
+ if (test_state(groupc->tasks, PSI_IO_FULL))
+ groupc->times[PSI_IO_FULL] += delta;
+ }
+
+ if (test_state(groupc->tasks, PSI_MEM_SOME)) {
+ groupc->times[PSI_MEM_SOME] += delta;
+ if (test_state(groupc->tasks, PSI_MEM_FULL))
+ groupc->times[PSI_MEM_FULL] += delta;
+ else if (memstall_tick) {
+ u32 sample;
+ /*
+ * Since we care about lost potential, a
+ * memstall is FULL when there are no other
+ * working tasks, but also when the CPU is
+ * actively reclaiming and nothing productive
+ * could run even if it were runnable.
+ *
+ * When the timer tick sees a reclaiming CPU,
+ * regardless of runnable tasks, sample a FULL
+ * tick (or less if it hasn't been a full tick
+ * since the last state change).
+ */
+ sample = min(delta, (u32)jiffies_to_nsecs(1));
+ groupc->times[PSI_MEM_FULL] += sample;
+ }
+ }
+
+ if (test_state(groupc->tasks, PSI_CPU_SOME))
+ groupc->times[PSI_CPU_SOME] += delta;
+
+ if (test_state(groupc->tasks, PSI_NONIDLE))
+ groupc->times[PSI_NONIDLE] += delta;
+}
+
+static void psi_group_change(struct psi_group *group, int cpu,
+ unsigned int clear, unsigned int set)
+{
+ struct psi_group_cpu *groupc;
+ unsigned int t, m;
+
+ groupc = per_cpu_ptr(group->pcpu, cpu);
+
+ /*
+ * First we assess the aggregate resource states this CPU's
+ * tasks have been in since the last change, and account any
+ * SOME and FULL time these may have resulted in.
+ *
+ * Then we update the task counts according to the state
+ * change requested through the @clear and @set bits.
+ */
+ write_seqcount_begin(&groupc->seq);
+
+ record_times(groupc, cpu, false);
+
+ for (t = 0, m = clear; m; m &= ~(1 << t), t++) {
+ if (!(m & (1 << t)))
+ continue;
+ if (groupc->tasks[t] == 0 && !psi_bug) {
+ printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u] clear=%x set=%x\n",
+ cpu, t, groupc->tasks[0],
+ groupc->tasks[1], groupc->tasks[2],
+ clear, set);
+ psi_bug = 1;
+ }
+ groupc->tasks[t]--;
+ }
+
+ for (t = 0; set; set &= ~(1 << t), t++)
+ if (set & (1 << t))
+ groupc->tasks[t]++;
+
+ write_seqcount_end(&groupc->seq);
+
+ if (!delayed_work_pending(&group->clock_work))
+ schedule_delayed_work(&group->clock_work, PSI_FREQ);
+}
+
+static struct psi_group *iterate_groups(struct task_struct *task, void **iter)
+{
+#ifdef CONFIG_CGROUPS
+ struct cgroup *cgroup = NULL;
+
+ if (!*iter)
+ cgroup = task->cgroups->dfl_cgrp;
+ else if (*iter == &psi_system)
+ return NULL;
+ else
+ cgroup = cgroup_parent(*iter);
+
+ if (cgroup && cgroup_parent(cgroup)) {
+ *iter = cgroup;
+ return cgroup_psi(cgroup);
+ }
+#else
+ if (*iter)
+ return NULL;
+#endif
+ *iter = &psi_system;
+ return &psi_system;
+}
+
+void psi_task_change(struct task_struct *task, int clear, int set)
+{
+ int cpu = task_cpu(task);
+ struct psi_group *group;
+ void *iter = NULL;
+
+ if (!task->pid)
+ return;
+
+ if (((task->psi_flags & set) ||
+ (task->psi_flags & clear) != clear) &&
+ !psi_bug) {
+ printk_deferred(KERN_ERR "psi: inconsistent task state! task=%d:%s cpu=%d psi_flags=%x clear=%x set=%x\n",
+ task->pid, task->comm, cpu,
+ task->psi_flags, clear, set);
+ psi_bug = 1;
+ }
+
+ task->psi_flags &= ~clear;
+ task->psi_flags |= set;
+
+ while ((group = iterate_groups(task, &iter)))
+ psi_group_change(group, cpu, clear, set);
+}
+
+void psi_memstall_tick(struct task_struct *task, int cpu)
+{
+ struct psi_group *group;
+ void *iter = NULL;
+
+ while ((group = iterate_groups(task, &iter))) {
+ struct psi_group_cpu *groupc;
+
+ groupc = per_cpu_ptr(group->pcpu, cpu);
+ write_seqcount_begin(&groupc->seq);
+ record_times(groupc, cpu, true);
+ write_seqcount_end(&groupc->seq);
+ }
+}
+
+/**
+ * psi_memstall_enter - mark the beginning of a memory stall section
+ * @flags: flags to handle nested sections
+ *
+ * Marks the calling task as being stalled due to a lack of memory,
+ * such as waiting for a refault or performing reclaim.
+ */
+void psi_memstall_enter(unsigned long *flags)
+{
+ struct rq_flags rf;
+ struct rq *rq;
+
+ if (psi_disabled)
+ return;
+
+ *flags = current->flags & PF_MEMSTALL;
+ if (*flags)
+ return;
+ /*
+ * PF_MEMSTALL setting & accounting needs to be atomic wrt
+ * changes to the task's scheduling state, otherwise we can
+ * race with CPU migration.
+ */
+ rq = this_rq_lock_irq(&rf);
+
+ current->flags |= PF_MEMSTALL;
+ psi_task_change(current, 0, TSK_MEMSTALL);
+
+ rq_unlock_irq(rq, &rf);
+}
+
+/**
+ * psi_memstall_leave - mark the end of an memory stall section
+ * @flags: flags to handle nested memdelay sections
+ *
+ * Marks the calling task as no longer stalled due to lack of memory.
+ */
+void psi_memstall_leave(unsigned long *flags)
+{
+ struct rq_flags rf;
+ struct rq *rq;
+
+ if (psi_disabled)
+ return;
+
+ if (*flags)
+ return;
+ /*
+ * PF_MEMSTALL clearing & accounting needs to be atomic wrt
+ * changes to the task's scheduling state, otherwise we could
+ * race with CPU migration.
+ */
+ rq = this_rq_lock_irq(&rf);
+
+ current->flags &= ~PF_MEMSTALL;
+ psi_task_change(current, TSK_MEMSTALL, 0);
+
+ rq_unlock_irq(rq, &rf);
+}
+
+#ifdef CONFIG_CGROUPS
+int psi_cgroup_alloc(struct cgroup *cgroup)
+{
+ if (psi_disabled)
+ return 0;
+
+ cgroup->psi.pcpu = alloc_percpu(struct psi_group_cpu);
+ if (!cgroup->psi.pcpu)
+ return -ENOMEM;
+ group_init(&cgroup->psi);
+ return 0;
+}
+
+void psi_cgroup_free(struct cgroup *cgroup)
+{
+ if (psi_disabled)
+ return;
+
+ cancel_delayed_work_sync(&cgroup->psi.clock_work);
+ free_percpu(cgroup->psi.pcpu);
+}
+
+/**
+ * cgroup_move_task - move task to a different cgroup
+ * @task: the task
+ * @to: the target css_set
+ *
+ * Move task to a new cgroup and safely migrate its associated stall
+ * state between the different groups.
+ *
+ * This function acquires the task's rq lock to lock out concurrent
+ * changes to the task's scheduling state and - in case the task is
+ * running - concurrent changes to its stall state.
+ */
+void cgroup_move_task(struct task_struct *task, struct css_set *to)
+{
+ bool move_psi = !psi_disabled;
+ unsigned int task_flags = 0;
+ struct rq_flags rf;
+ struct rq *rq;
+
+ if (move_psi) {
+ rq = task_rq_lock(task, &rf);
+
+ if (task_on_rq_queued(task))
+ task_flags = TSK_RUNNING;
+ else if (task->in_iowait)
+ task_flags = TSK_IOWAIT;
+
+ if (task->flags & PF_MEMSTALL)
+ task_flags |= TSK_MEMSTALL;
+
+ if (task_flags)
+ psi_task_change(task, task_flags, 0);
+ }
+
+ /*
+ * Lame to do this here, but the scheduler cannot be locked
+ * from the outside, so we move cgroups from inside sched/.
+ */
+ rcu_assign_pointer(task->cgroups, to);
+
+ if (move_psi) {
+ if (task_flags)
+ psi_task_change(task, 0, task_flags);
+
+ task_rq_unlock(rq, task, &rf);
+ }
+}
+#endif /* CONFIG_CGROUPS */
+
+int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res)
+{
+ int full;
+
+ if (psi_disabled)
+ return -EOPNOTSUPP;
+
+ update_stats(group);
+
+ for (full = 0; full < 2 - (res == PSI_CPU); full++) {
+ unsigned long avg[3];
+ u64 total;
+ int w;
+
+ for (w = 0; w < 3; w++)
+ avg[w] = group->avg[res * 2 + full][w];
+ total = div_u64(group->total[res * 2 + full], NSEC_PER_USEC);
+
+ seq_printf(m, "%s avg10=%lu.%02lu avg60=%lu.%02lu avg300=%lu.%02lu total=%llu\n",
+ full ? "full" : "some",
+ LOAD_INT(avg[0]), LOAD_FRAC(avg[0]),
+ LOAD_INT(avg[1]), LOAD_FRAC(avg[1]),
+ LOAD_INT(avg[2]), LOAD_FRAC(avg[2]),
+ total);
+ }
+
+ return 0;
+}
+
+static int psi_io_show(struct seq_file *m, void *v)
+{
+ return psi_show(m, &psi_system, PSI_IO);
+}
+
+static int psi_memory_show(struct seq_file *m, void *v)
+{
+ return psi_show(m, &psi_system, PSI_MEM);
+}
+
+static int psi_cpu_show(struct seq_file *m, void *v)
+{
+ return psi_show(m, &psi_system, PSI_CPU);
+}
+
+static int psi_io_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, psi_io_show, NULL);
+}
+
+static int psi_memory_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, psi_memory_show, NULL);
+}
+
+static int psi_cpu_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, psi_cpu_show, NULL);
+}
+
+static const struct file_operations psi_io_fops = {
+ .open = psi_io_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static const struct file_operations psi_memory_fops = {
+ .open = psi_memory_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static const struct file_operations psi_cpu_fops = {
+ .open = psi_cpu_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static int __init psi_proc_init(void)
+{
+ proc_mkdir("pressure", NULL);
+ proc_create("pressure/io", 0, NULL, &psi_io_fops);
+ proc_create("pressure/memory", 0, NULL, &psi_memory_fops);
+ proc_create("pressure/cpu", 0, NULL, &psi_cpu_fops);
+ return 0;
+}
+module_init(psi_proc_init);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b8c007713b3b..618577fc9aa8 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -54,6 +54,7 @@
#include <linux/proc_fs.h>
#include <linux/prefetch.h>
#include <linux/profile.h>
+#include <linux/psi.h>
#include <linux/rcupdate_wait.h>
#include <linux/security.h>
#include <linux/stop_machine.h>
@@ -319,6 +320,7 @@ extern bool dl_cpu_busy(unsigned int cpu);
#ifdef CONFIG_CGROUP_SCHED
#include <linux/cgroup.h>
+#include <linux/psi.h>
struct cfs_rq;
struct rt_rq;
@@ -957,6 +959,8 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
#define cpu_curr(cpu) (cpu_rq(cpu)->curr)
#define raw_rq() raw_cpu_ptr(&runqueues)
+extern void update_rq_clock(struct rq *rq);
+
static inline u64 __rq_clock_broken(struct rq *rq)
{
return READ_ONCE(rq->clock);
@@ -1075,6 +1079,98 @@ static inline void rq_repin_lock(struct rq *rq, struct rq_flags *rf)
#endif
}
+struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
+ __acquires(rq->lock);
+
+struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
+ __acquires(p->pi_lock)
+ __acquires(rq->lock);
+
+static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf)
+ __releases(rq->lock)
+{
+ rq_unpin_lock(rq, rf);
+ raw_spin_unlock(&rq->lock);
+}
+
+static inline void
+task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
+ __releases(rq->lock)
+ __releases(p->pi_lock)
+{
+ rq_unpin_lock(rq, rf);
+ raw_spin_unlock(&rq->lock);
+ raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
+}
+
+static inline void
+rq_lock_irqsave(struct rq *rq, struct rq_flags *rf)
+ __acquires(rq->lock)
+{
+ raw_spin_lock_irqsave(&rq->lock, rf->flags);
+ rq_pin_lock(rq, rf);
+}
+
+static inline void
+rq_lock_irq(struct rq *rq, struct rq_flags *rf)
+ __acquires(rq->lock)
+{
+ raw_spin_lock_irq(&rq->lock);
+ rq_pin_lock(rq, rf);
+}
+
+static inline void
+rq_lock(struct rq *rq, struct rq_flags *rf)
+ __acquires(rq->lock)
+{
+ raw_spin_lock(&rq->lock);
+ rq_pin_lock(rq, rf);
+}
+
+static inline void
+rq_relock(struct rq *rq, struct rq_flags *rf)
+ __acquires(rq->lock)
+{
+ raw_spin_lock(&rq->lock);
+ rq_repin_lock(rq, rf);
+}
+
+static inline void
+rq_unlock_irqrestore(struct rq *rq, struct rq_flags *rf)
+ __releases(rq->lock)
+{
+ rq_unpin_lock(rq, rf);
+ raw_spin_unlock_irqrestore(&rq->lock, rf->flags);
+}
+
+static inline void
+rq_unlock_irq(struct rq *rq, struct rq_flags *rf)
+ __releases(rq->lock)
+{
+ rq_unpin_lock(rq, rf);
+ raw_spin_unlock_irq(&rq->lock);
+}
+
+static inline void
+rq_unlock(struct rq *rq, struct rq_flags *rf)
+ __releases(rq->lock)
+{
+ rq_unpin_lock(rq, rf);
+ raw_spin_unlock(&rq->lock);
+}
+
+static inline struct rq *
+this_rq_lock_irq(struct rq_flags *rf)
+ __acquires(rq->lock)
+{
+ struct rq *rq;
+
+ local_irq_disable();
+ rq = this_rq();
+ rq_lock(rq, rf);
+ return rq;
+}
+
#ifdef CONFIG_NUMA
enum numa_topology_type {
NUMA_DIRECT,
@@ -1717,8 +1813,6 @@ static inline void sub_nr_running(struct rq *rq, unsigned count)
sched_update_tick_dependency(rq);
}
-extern void update_rq_clock(struct rq *rq);
-
extern void activate_task(struct rq *rq, struct task_struct *p, int flags);
extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags);
@@ -1783,86 +1877,6 @@ unsigned long arch_scale_cpu_capacity(void __always_unused *sd, int cpu)
#endif
#endif
-struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
- __acquires(rq->lock);
-
-struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
- __acquires(p->pi_lock)
- __acquires(rq->lock);
-
-static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf)
- __releases(rq->lock)
-{
- rq_unpin_lock(rq, rf);
- raw_spin_unlock(&rq->lock);
-}
-
-static inline void
-task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
- __releases(rq->lock)
- __releases(p->pi_lock)
-{
- rq_unpin_lock(rq, rf);
- raw_spin_unlock(&rq->lock);
- raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
-}
-
-static inline void
-rq_lock_irqsave(struct rq *rq, struct rq_flags *rf)
- __acquires(rq->lock)
-{
- raw_spin_lock_irqsave(&rq->lock, rf->flags);
- rq_pin_lock(rq, rf);
-}
-
-static inline void
-rq_lock_irq(struct rq *rq, struct rq_flags *rf)
- __acquires(rq->lock)
-{
- raw_spin_lock_irq(&rq->lock);
- rq_pin_lock(rq, rf);
-}
-
-static inline void
-rq_lock(struct rq *rq, struct rq_flags *rf)
- __acquires(rq->lock)
-{
- raw_spin_lock(&rq->lock);
- rq_pin_lock(rq, rf);
-}
-
-static inline void
-rq_relock(struct rq *rq, struct rq_flags *rf)
- __acquires(rq->lock)
-{
- raw_spin_lock(&rq->lock);
- rq_repin_lock(rq, rf);
-}
-
-static inline void
-rq_unlock_irqrestore(struct rq *rq, struct rq_flags *rf)
- __releases(rq->lock)
-{
- rq_unpin_lock(rq, rf);
- raw_spin_unlock_irqrestore(&rq->lock, rf->flags);
-}
-
-static inline void
-rq_unlock_irq(struct rq *rq, struct rq_flags *rf)
- __releases(rq->lock)
-{
- rq_unpin_lock(rq, rf);
- raw_spin_unlock_irq(&rq->lock);
-}
-
-static inline void
-rq_unlock(struct rq *rq, struct rq_flags *rf)
- __releases(rq->lock)
-{
- rq_unpin_lock(rq, rf);
- raw_spin_unlock(&rq->lock);
-}
-
#ifdef CONFIG_SMP
#ifdef CONFIG_PREEMPT
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 8aea199a39b4..4904c4677000 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -55,6 +55,92 @@ static inline void rq_sched_info_depart (struct rq *rq, unsigned long long delt
# define schedstat_val_or_zero(var) 0
#endif /* CONFIG_SCHEDSTATS */
+#ifdef CONFIG_PSI
+/*
+ * PSI tracks state that persists across sleeps, such as iowaits and
+ * memory stalls. As a result, it has to distinguish between sleeps,
+ * where a task's runnable state changes, and requeues, where a task
+ * and its state are being moved between CPUs and runqueues.
+ */
+static inline void psi_enqueue(struct task_struct *p, bool wakeup)
+{
+ int clear = 0, set = TSK_RUNNING;
+
+ if (psi_disabled)
+ return;
+
+ if (!wakeup || p->sched_psi_wake_requeue) {
+ if (p->flags & PF_MEMSTALL)
+ set |= TSK_MEMSTALL;
+ if (p->sched_psi_wake_requeue)
+ p->sched_psi_wake_requeue = 0;
+ } else {
+ if (p->in_iowait)
+ clear |= TSK_IOWAIT;
+ }
+
+ psi_task_change(p, clear, set);
+}
+
+static inline void psi_dequeue(struct task_struct *p, bool sleep)
+{
+ int clear = TSK_RUNNING, set = 0;
+
+ if (psi_disabled)
+ return;
+
+ if (!sleep) {
+ if (p->flags & PF_MEMSTALL)
+ clear |= TSK_MEMSTALL;
+ } else {
+ if (p->in_iowait)
+ set |= TSK_IOWAIT;
+ }
+
+ psi_task_change(p, clear, set);
+}
+
+static inline void psi_ttwu_dequeue(struct task_struct *p)
+{
+ if (psi_disabled)
+ return;
+ /*
+ * Is the task being migrated during a wakeup? Make sure to
+ * deregister its sleep-persistent psi states from the old
+ * queue, and let psi_enqueue() know it has to requeue.
+ */
+ if (unlikely(p->in_iowait || (p->flags & PF_MEMSTALL))) {
+ struct rq_flags rf;
+ struct rq *rq;
+ int clear = 0;
+
+ if (p->in_iowait)
+ clear |= TSK_IOWAIT;
+ if (p->flags & PF_MEMSTALL)
+ clear |= TSK_MEMSTALL;
+
+ rq = __task_rq_lock(p, &rf);
+ psi_task_change(p, clear, 0);
+ p->sched_psi_wake_requeue = 1;
+ __task_rq_unlock(rq, &rf);
+ }
+}
+
+static inline void psi_task_tick(struct rq *rq)
+{
+ if (psi_disabled)
+ return;
+
+ if (unlikely(rq->curr->flags & PF_MEMSTALL))
+ psi_memstall_tick(rq->curr, cpu_of(rq));
+}
+#else /* CONFIG_PSI */
+static inline void psi_enqueue(struct task_struct *p, bool wakeup) {}
+static inline void psi_dequeue(struct task_struct *p, bool sleep) {}
+static inline void psi_ttwu_dequeue(struct task_struct *p) {}
+static inline void psi_task_tick(struct rq *rq) {}
+#endif /* CONFIG_PSI */
+
#ifdef CONFIG_SCHED_INFO
static inline void sched_info_reset_dequeued(struct task_struct *t)
{
Powered by cgit, Gruvboxed by Blaster4385.