aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/core.c8
-rw-r--r--kernel/bpf/helpers.c12
-rw-r--r--kernel/cgroup/cgroup.c37
-rw-r--r--kernel/events/core.c45
-rw-r--r--kernel/exit.c2
-rw-r--r--kernel/kexec_file.c11
-rw-r--r--kernel/module/internal.h13
-rw-r--r--kernel/module/kallsyms.c35
-rw-r--r--kernel/module/main.c9
-rw-r--r--kernel/power/user.c13
-rw-r--r--kernel/printk/printk.c13
-rw-r--r--kernel/rcu/srcutree.c98
-rw-r--r--kernel/sched/deadline.c5
-rw-r--r--kernel/sysctl.c57
-rw-r--r--kernel/time/posix-timers.c19
-rw-r--r--kernel/trace/Kconfig3
-rw-r--r--kernel/trace/trace.c11
-rw-r--r--kernel/trace/trace_events_hist.c2
-rw-r--r--kernel/watch_queue.c53
19 files changed, 306 insertions, 140 deletions
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 5f6f3f829b36..e7961508a47d 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -68,11 +68,13 @@ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns
{
u8 *ptr = NULL;
- if (k >= SKF_NET_OFF)
+ if (k >= SKF_NET_OFF) {
ptr = skb_network_header(skb) + k - SKF_NET_OFF;
- else if (k >= SKF_LL_OFF)
+ } else if (k >= SKF_LL_OFF) {
+ if (unlikely(!skb_mac_header_was_set(skb)))
+ return NULL;
ptr = skb_mac_header(skb) + k - SKF_LL_OFF;
-
+ }
if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb))
return ptr;
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 225806a02efb..bb1254f07667 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1497,11 +1497,12 @@ const struct bpf_func_proto bpf_dynptr_from_mem_proto = {
.arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL | MEM_UNINIT,
};
-BPF_CALL_4(bpf_dynptr_read, void *, dst, u32, len, struct bpf_dynptr_kern *, src, u32, offset)
+BPF_CALL_5(bpf_dynptr_read, void *, dst, u32, len, struct bpf_dynptr_kern *, src,
+ u32, offset, u64, flags)
{
int err;
- if (!src->data)
+ if (!src->data || flags)
return -EINVAL;
err = bpf_dynptr_check_off_len(src, offset, len);
@@ -1521,13 +1522,15 @@ const struct bpf_func_proto bpf_dynptr_read_proto = {
.arg2_type = ARG_CONST_SIZE_OR_ZERO,
.arg3_type = ARG_PTR_TO_DYNPTR,
.arg4_type = ARG_ANYTHING,
+ .arg5_type = ARG_ANYTHING,
};
-BPF_CALL_4(bpf_dynptr_write, struct bpf_dynptr_kern *, dst, u32, offset, void *, src, u32, len)
+BPF_CALL_5(bpf_dynptr_write, struct bpf_dynptr_kern *, dst, u32, offset, void *, src,
+ u32, len, u64, flags)
{
int err;
- if (!dst->data || bpf_dynptr_is_rdonly(dst))
+ if (!dst->data || flags || bpf_dynptr_is_rdonly(dst))
return -EINVAL;
err = bpf_dynptr_check_off_len(dst, offset, len);
@@ -1547,6 +1550,7 @@ const struct bpf_func_proto bpf_dynptr_write_proto = {
.arg2_type = ARG_ANYTHING,
.arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg4_type = ARG_CONST_SIZE_OR_ZERO,
+ .arg5_type = ARG_ANYTHING,
};
BPF_CALL_3(bpf_dynptr_data, struct bpf_dynptr_kern *, ptr, u32, offset, u32, len)
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 1779ccddb734..13c8e91d7862 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -765,7 +765,8 @@ struct css_set init_css_set = {
.task_iters = LIST_HEAD_INIT(init_css_set.task_iters),
.threaded_csets = LIST_HEAD_INIT(init_css_set.threaded_csets),
.cgrp_links = LIST_HEAD_INIT(init_css_set.cgrp_links),
- .mg_preload_node = LIST_HEAD_INIT(init_css_set.mg_preload_node),
+ .mg_src_preload_node = LIST_HEAD_INIT(init_css_set.mg_src_preload_node),
+ .mg_dst_preload_node = LIST_HEAD_INIT(init_css_set.mg_dst_preload_node),
.mg_node = LIST_HEAD_INIT(init_css_set.mg_node),
/*
@@ -1240,7 +1241,8 @@ static struct css_set *find_css_set(struct css_set *old_cset,
INIT_LIST_HEAD(&cset->threaded_csets);
INIT_HLIST_NODE(&cset->hlist);
INIT_LIST_HEAD(&cset->cgrp_links);
- INIT_LIST_HEAD(&cset->mg_preload_node);
+ INIT_LIST_HEAD(&cset->mg_src_preload_node);
+ INIT_LIST_HEAD(&cset->mg_dst_preload_node);
INIT_LIST_HEAD(&cset->mg_node);
/* Copy the set of subsystem state objects generated in
@@ -2597,21 +2599,27 @@ int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp)
*/
void cgroup_migrate_finish(struct cgroup_mgctx *mgctx)
{
- LIST_HEAD(preloaded);
struct css_set *cset, *tmp_cset;
lockdep_assert_held(&cgroup_mutex);
spin_lock_irq(&css_set_lock);
- list_splice_tail_init(&mgctx->preloaded_src_csets, &preloaded);
- list_splice_tail_init(&mgctx->preloaded_dst_csets, &preloaded);
+ list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_src_csets,
+ mg_src_preload_node) {
+ cset->mg_src_cgrp = NULL;
+ cset->mg_dst_cgrp = NULL;
+ cset->mg_dst_cset = NULL;
+ list_del_init(&cset->mg_src_preload_node);
+ put_css_set_locked(cset);
+ }
- list_for_each_entry_safe(cset, tmp_cset, &preloaded, mg_preload_node) {
+ list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_dst_csets,
+ mg_dst_preload_node) {
cset->mg_src_cgrp = NULL;
cset->mg_dst_cgrp = NULL;
cset->mg_dst_cset = NULL;
- list_del_init(&cset->mg_preload_node);
+ list_del_init(&cset->mg_dst_preload_node);
put_css_set_locked(cset);
}
@@ -2651,7 +2659,7 @@ void cgroup_migrate_add_src(struct css_set *src_cset,
if (src_cset->dead)
return;
- if (!list_empty(&src_cset->mg_preload_node))
+ if (!list_empty(&src_cset->mg_src_preload_node))
return;
src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root);
@@ -2664,7 +2672,7 @@ void cgroup_migrate_add_src(struct css_set *src_cset,
src_cset->mg_src_cgrp = src_cgrp;
src_cset->mg_dst_cgrp = dst_cgrp;
get_css_set(src_cset);
- list_add_tail(&src_cset->mg_preload_node, &mgctx->preloaded_src_csets);
+ list_add_tail(&src_cset->mg_src_preload_node, &mgctx->preloaded_src_csets);
}
/**
@@ -2689,7 +2697,7 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx)
/* look up the dst cset for each src cset and link it to src */
list_for_each_entry_safe(src_cset, tmp_cset, &mgctx->preloaded_src_csets,
- mg_preload_node) {
+ mg_src_preload_node) {
struct css_set *dst_cset;
struct cgroup_subsys *ss;
int ssid;
@@ -2708,7 +2716,7 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx)
if (src_cset == dst_cset) {
src_cset->mg_src_cgrp = NULL;
src_cset->mg_dst_cgrp = NULL;
- list_del_init(&src_cset->mg_preload_node);
+ list_del_init(&src_cset->mg_src_preload_node);
put_css_set(src_cset);
put_css_set(dst_cset);
continue;
@@ -2716,8 +2724,8 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx)
src_cset->mg_dst_cset = dst_cset;
- if (list_empty(&dst_cset->mg_preload_node))
- list_add_tail(&dst_cset->mg_preload_node,
+ if (list_empty(&dst_cset->mg_dst_preload_node))
+ list_add_tail(&dst_cset->mg_dst_preload_node,
&mgctx->preloaded_dst_csets);
else
put_css_set(dst_cset);
@@ -2963,7 +2971,8 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
goto out_finish;
spin_lock_irq(&css_set_lock);
- list_for_each_entry(src_cset, &mgctx.preloaded_src_csets, mg_preload_node) {
+ list_for_each_entry(src_cset, &mgctx.preloaded_src_csets,
+ mg_src_preload_node) {
struct task_struct *task, *ntask;
/* all tasks in src_csets need to be migrated */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 80782cddb1da..d2b354991bf5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6253,10 +6253,10 @@ again:
if (!atomic_inc_not_zero(&event->rb->mmap_count)) {
/*
- * Raced against perf_mmap_close() through
- * perf_event_set_output(). Try again, hope for better
- * luck.
+ * Raced against perf_mmap_close(); remove the
+ * event and try again.
*/
+ ring_buffer_attach(event, NULL);
mutex_unlock(&event->mmap_mutex);
goto again;
}
@@ -11825,14 +11825,25 @@ err_size:
goto out;
}
+static void mutex_lock_double(struct mutex *a, struct mutex *b)
+{
+ if (b < a)
+ swap(a, b);
+
+ mutex_lock(a);
+ mutex_lock_nested(b, SINGLE_DEPTH_NESTING);
+}
+
static int
perf_event_set_output(struct perf_event *event, struct perf_event *output_event)
{
struct perf_buffer *rb = NULL;
int ret = -EINVAL;
- if (!output_event)
+ if (!output_event) {
+ mutex_lock(&event->mmap_mutex);
goto set;
+ }
/* don't allow circular references */
if (event == output_event)
@@ -11870,8 +11881,15 @@ perf_event_set_output(struct perf_event *event, struct perf_event *output_event)
event->pmu != output_event->pmu)
goto out;
+ /*
+ * Hold both mmap_mutex to serialize against perf_mmap_close(). Since
+ * output_event is already on rb->event_list, and the list iteration
+ * restarts after every removal, it is guaranteed this new event is
+ * observed *OR* if output_event is already removed, it's guaranteed we
+ * observe !rb->mmap_count.
+ */
+ mutex_lock_double(&event->mmap_mutex, &output_event->mmap_mutex);
set:
- mutex_lock(&event->mmap_mutex);
/* Can't redirect output if we've got an active mmap() */
if (atomic_read(&event->mmap_count))
goto unlock;
@@ -11881,6 +11899,12 @@ set:
rb = ring_buffer_get(output_event);
if (!rb)
goto unlock;
+
+ /* did we race against perf_mmap_close() */
+ if (!atomic_read(&rb->mmap_count)) {
+ ring_buffer_put(rb);
+ goto unlock;
+ }
}
ring_buffer_attach(event, rb);
@@ -11888,20 +11912,13 @@ set:
ret = 0;
unlock:
mutex_unlock(&event->mmap_mutex);
+ if (output_event)
+ mutex_unlock(&output_event->mmap_mutex);
out:
return ret;
}
-static void mutex_lock_double(struct mutex *a, struct mutex *b)
-{
- if (b < a)
- swap(a, b);
-
- mutex_lock(a);
- mutex_lock_nested(b, SINGLE_DEPTH_NESTING);
-}
-
static int perf_event_set_clock(struct perf_event *event, clockid_t clk_id)
{
bool nmi_safe = false;
diff --git a/kernel/exit.c b/kernel/exit.c
index f072959fcab7..64c938ce36fe 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -766,7 +766,7 @@ void __noreturn do_exit(long code)
#ifdef CONFIG_POSIX_TIMERS
hrtimer_cancel(&tsk->signal->real_timer);
- exit_itimers(tsk->signal);
+ exit_itimers(tsk);
#endif
if (tsk->mm)
setmax_mm_hiwater_rss(&tsk->signal->maxrss, tsk->mm);
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index 145321a5e798..f9261c07b048 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -29,6 +29,15 @@
#include <linux/vmalloc.h>
#include "kexec_internal.h"
+#ifdef CONFIG_KEXEC_SIG
+static bool sig_enforce = IS_ENABLED(CONFIG_KEXEC_SIG_FORCE);
+
+void set_kexec_sig_enforced(void)
+{
+ sig_enforce = true;
+}
+#endif
+
static int kexec_calculate_store_digests(struct kimage *image);
/*
@@ -159,7 +168,7 @@ kimage_validate_signature(struct kimage *image)
image->kernel_buf_len);
if (ret) {
- if (IS_ENABLED(CONFIG_KEXEC_SIG_FORCE)) {
+ if (sig_enforce) {
pr_notice("Enforced kernel signature verification failed (%d).\n", ret);
return ret;
}
diff --git a/kernel/module/internal.h b/kernel/module/internal.h
index bc5507ab8450..ec104c2950c3 100644
--- a/kernel/module/internal.h
+++ b/kernel/module/internal.h
@@ -11,6 +11,7 @@
#include <linux/mutex.h>
#include <linux/rculist.h>
#include <linux/rcupdate.h>
+#include <linux/mm.h>
#ifndef ARCH_SHF_SMALL
#define ARCH_SHF_SMALL 0
@@ -30,11 +31,13 @@
* to ensure complete separation of code and data, but
* only when CONFIG_STRICT_MODULE_RWX=y
*/
-#ifdef CONFIG_STRICT_MODULE_RWX
-# define strict_align(X) PAGE_ALIGN(X)
-#else
-# define strict_align(X) (X)
-#endif
+static inline unsigned int strict_align(unsigned int size)
+{
+ if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
+ return PAGE_ALIGN(size);
+ else
+ return size;
+}
extern struct mutex module_mutex;
extern struct list_head modules;
diff --git a/kernel/module/kallsyms.c b/kernel/module/kallsyms.c
index 3e11523bc6f6..77e75bead569 100644
--- a/kernel/module/kallsyms.c
+++ b/kernel/module/kallsyms.c
@@ -137,6 +137,7 @@ void layout_symtab(struct module *mod, struct load_info *info)
info->symoffs = ALIGN(mod->data_layout.size, symsect->sh_addralign ?: 1);
info->stroffs = mod->data_layout.size = info->symoffs + ndst * sizeof(Elf_Sym);
mod->data_layout.size += strtab_size;
+ /* Note add_kallsyms() computes strtab_size as core_typeoffs - stroffs */
info->core_typeoffs = mod->data_layout.size;
mod->data_layout.size += ndst * sizeof(char);
mod->data_layout.size = strict_align(mod->data_layout.size);
@@ -169,19 +170,20 @@ void add_kallsyms(struct module *mod, const struct load_info *info)
Elf_Sym *dst;
char *s;
Elf_Shdr *symsec = &info->sechdrs[info->index.sym];
+ unsigned long strtab_size;
/* Set up to point into init section. */
mod->kallsyms = (void __rcu *)mod->init_layout.base +
info->mod_kallsyms_init_off;
- preempt_disable();
+ rcu_read_lock();
/* The following is safe since this pointer cannot change */
- rcu_dereference_sched(mod->kallsyms)->symtab = (void *)symsec->sh_addr;
- rcu_dereference_sched(mod->kallsyms)->num_symtab = symsec->sh_size / sizeof(Elf_Sym);
+ rcu_dereference(mod->kallsyms)->symtab = (void *)symsec->sh_addr;
+ rcu_dereference(mod->kallsyms)->num_symtab = symsec->sh_size / sizeof(Elf_Sym);
/* Make sure we get permanent strtab: don't use info->strtab. */
- rcu_dereference_sched(mod->kallsyms)->strtab =
+ rcu_dereference(mod->kallsyms)->strtab =
(void *)info->sechdrs[info->index.str].sh_addr;
- rcu_dereference_sched(mod->kallsyms)->typetab = mod->init_layout.base + info->init_typeoffs;
+ rcu_dereference(mod->kallsyms)->typetab = mod->init_layout.base + info->init_typeoffs;
/*
* Now populate the cut down core kallsyms for after init
@@ -190,22 +192,29 @@ void add_kallsyms(struct module *mod, const struct load_info *info)
mod->core_kallsyms.symtab = dst = mod->data_layout.base + info->symoffs;
mod->core_kallsyms.strtab = s = mod->data_layout.base + info->stroffs;
mod->core_kallsyms.typetab = mod->data_layout.base + info->core_typeoffs;
- src = rcu_dereference_sched(mod->kallsyms)->symtab;
- for (ndst = i = 0; i < rcu_dereference_sched(mod->kallsyms)->num_symtab; i++) {
- rcu_dereference_sched(mod->kallsyms)->typetab[i] = elf_type(src + i, info);
+ strtab_size = info->core_typeoffs - info->stroffs;
+ src = rcu_dereference(mod->kallsyms)->symtab;
+ for (ndst = i = 0; i < rcu_dereference(mod->kallsyms)->num_symtab; i++) {
+ rcu_dereference(mod->kallsyms)->typetab[i] = elf_type(src + i, info);
if (i == 0 || is_livepatch_module(mod) ||
is_core_symbol(src + i, info->sechdrs, info->hdr->e_shnum,
info->index.pcpu)) {
+ ssize_t ret;
+
mod->core_kallsyms.typetab[ndst] =
- rcu_dereference_sched(mod->kallsyms)->typetab[i];
+ rcu_dereference(mod->kallsyms)->typetab[i];
dst[ndst] = src[i];
dst[ndst++].st_name = s - mod->core_kallsyms.strtab;
- s += strscpy(s,
- &rcu_dereference_sched(mod->kallsyms)->strtab[src[i].st_name],
- KSYM_NAME_LEN) + 1;
+ ret = strscpy(s,
+ &rcu_dereference(mod->kallsyms)->strtab[src[i].st_name],
+ strtab_size);
+ if (ret < 0)
+ break;
+ s += ret + 1;
+ strtab_size -= ret + 1;
}
}
- preempt_enable();
+ rcu_read_unlock();
mod->core_kallsyms.num_symtab = ndst;
}
diff --git a/kernel/module/main.c b/kernel/module/main.c
index fed58d30725d..0548151dd933 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -2939,24 +2939,25 @@ static void cfi_init(struct module *mod)
{
#ifdef CONFIG_CFI_CLANG
initcall_t *init;
+#ifdef CONFIG_MODULE_UNLOAD
exitcall_t *exit;
+#endif
rcu_read_lock_sched();
mod->cfi_check = (cfi_check_fn)
find_kallsyms_symbol_value(mod, "__cfi_check");
init = (initcall_t *)
find_kallsyms_symbol_value(mod, "__cfi_jt_init_module");
- exit = (exitcall_t *)
- find_kallsyms_symbol_value(mod, "__cfi_jt_cleanup_module");
- rcu_read_unlock_sched();
-
/* Fix init/exit functions to point to the CFI jump table */
if (init)
mod->init = *init;
#ifdef CONFIG_MODULE_UNLOAD
+ exit = (exitcall_t *)
+ find_kallsyms_symbol_value(mod, "__cfi_jt_cleanup_module");
if (exit)
mod->exit = *exit;
#endif
+ rcu_read_unlock_sched();
cfi_module_add(mod, mod_tree.addr_min);
#endif
diff --git a/kernel/power/user.c b/kernel/power/user.c
index ad241b4ff64c..d43c2aa583b2 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -26,6 +26,7 @@
#include "power.h"
+static bool need_wait;
static struct snapshot_data {
struct snapshot_handle handle;
@@ -78,7 +79,7 @@ static int snapshot_open(struct inode *inode, struct file *filp)
* Resuming. We may need to wait for the image device to
* appear.
*/
- wait_for_device_probe();
+ need_wait = true;
data->swap = -1;
data->mode = O_WRONLY;
@@ -168,6 +169,11 @@ static ssize_t snapshot_write(struct file *filp, const char __user *buf,
ssize_t res;
loff_t pg_offp = *offp & ~PAGE_MASK;
+ if (need_wait) {
+ wait_for_device_probe();
+ need_wait = false;
+ }
+
lock_system_sleep();
data = filp->private_data;
@@ -244,6 +250,11 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
loff_t size;
sector_t offset;
+ if (need_wait) {
+ wait_for_device_probe();
+ need_wait = false;
+ }
+
if (_IOC_TYPE(cmd) != SNAPSHOT_IOC_MAGIC)
return -ENOTTY;
if (_IOC_NR(cmd) > SNAPSHOT_IOC_MAXNR)
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index b49c6ff6dca0..a1a81fd9889b 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -3380,6 +3380,7 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre
diff = 0;
console_lock();
+
for_each_console(c) {
if (con && con != c)
continue;
@@ -3389,11 +3390,19 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre
if (printk_seq < seq)
diff += seq - printk_seq;
}
- console_unlock();
- if (diff != last_diff && reset_on_progress)
+ /*
+ * If consoles are suspended, it cannot be expected that they
+ * make forward progress, so timeout immediately. @diff is
+ * still used to return a valid flush status.
+ */
+ if (console_suspended)
+ remaining = 0;
+ else if (diff != last_diff && reset_on_progress)
remaining = timeout_ms;
+ console_unlock();
+
if (diff == 0 || remaining == 0)
break;
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 50ba70f019de..1c304fec89c0 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -511,10 +511,52 @@ static bool srcu_readers_active(struct srcu_struct *ssp)
return sum;
}
-#define SRCU_INTERVAL 1 // Base delay if no expedited GPs pending.
-#define SRCU_MAX_INTERVAL 10 // Maximum incremental delay from slow readers.
-#define SRCU_MAX_NODELAY_PHASE 1 // Maximum per-GP-phase consecutive no-delay instances.
-#define SRCU_MAX_NODELAY 100 // Maximum consecutive no-delay instances.
+/*
+ * We use an adaptive strategy for synchronize_srcu() and especially for
+ * synchronize_srcu_expedited(). We spin for a fixed time period
+ * (defined below, boot time configurable) to allow SRCU readers to exit
+ * their read-side critical sections. If there are still some readers
+ * after one jiffy, we repeatedly block for one jiffy time periods.
+ * The blocking time is increased as the grace-period age increases,
+ * with max blocking time capped at 10 jiffies.
+ */
+#define SRCU_DEFAULT_RETRY_CHECK_DELAY 5
+
+static ulong srcu_retry_check_delay = SRCU_DEFAULT_RETRY_CHECK_DELAY;
+module_param(srcu_retry_check_delay, ulong, 0444);
+
+#define SRCU_INTERVAL 1 // Base delay if no expedited GPs pending.
+#define SRCU_MAX_INTERVAL 10 // Maximum incremental delay from slow readers.
+
+#define SRCU_DEFAULT_MAX_NODELAY_PHASE_LO 3UL // Lowmark on default per-GP-phase
+ // no-delay instances.
+#define SRCU_DEFAULT_MAX_NODELAY_PHASE_HI 1000UL // Highmark on default per-GP-phase
+ // no-delay instances.
+
+#define SRCU_UL_CLAMP_LO(val, low) ((val) > (low) ? (val) : (low))
+#define SRCU_UL_CLAMP_HI(val, high) ((val) < (high) ? (val) : (high))
+#define SRCU_UL_CLAMP(val, low, high) SRCU_UL_CLAMP_HI(SRCU_UL_CLAMP_LO((val), (low)), (high))
+// per-GP-phase no-delay instances adjusted to allow non-sleeping poll upto
+// one jiffies time duration. Mult by 2 is done to factor in the srcu_get_delay()
+// called from process_srcu().
+#define SRCU_DEFAULT_MAX_NODELAY_PHASE_ADJUSTED \
+ (2UL * USEC_PER_SEC / HZ / SRCU_DEFAULT_RETRY_CHECK_DELAY)
+
+// Maximum per-GP-phase consecutive no-delay instances.
+#define SRCU_DEFAULT_MAX_NODELAY_PHASE \
+ SRCU_UL_CLAMP(SRCU_DEFAULT_MAX_NODELAY_PHASE_ADJUSTED, \
+ SRCU_DEFAULT_MAX_NODELAY_PHASE_LO, \
+ SRCU_DEFAULT_MAX_NODELAY_PHASE_HI)
+
+static ulong srcu_max_nodelay_phase = SRCU_DEFAULT_MAX_NODELAY_PHASE;
+module_param(srcu_max_nodelay_phase, ulong, 0444);
+
+// Maximum consecutive no-delay instances.
+#define SRCU_DEFAULT_MAX_NODELAY (SRCU_DEFAULT_MAX_NODELAY_PHASE > 100 ? \
+ SRCU_DEFAULT_MAX_NODELAY_PHASE : 100)
+
+static ulong srcu_max_nodelay = SRCU_DEFAULT_MAX_NODELAY;
+module_param(srcu_max_nodelay, ulong, 0444);
/*
* Return grace-period delay, zero if there are expedited grace
@@ -522,16 +564,22 @@ static bool srcu_readers_active(struct srcu_struct *ssp)
*/
static unsigned long srcu_get_delay(struct srcu_struct *ssp)
{
+ unsigned long gpstart;
+ unsigned long j;
unsigned long jbase = SRCU_INTERVAL;
if (ULONG_CMP_LT(READ_ONCE(ssp->srcu_gp_seq), READ_ONCE(ssp->srcu_gp_seq_needed_exp)))
jbase = 0;
- if (rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)))
- jbase += jiffies - READ_ONCE(ssp->srcu_gp_start);
- if (!jbase) {
- WRITE_ONCE(ssp->srcu_n_exp_nodelay, READ_ONCE(ssp->srcu_n_exp_nodelay) + 1);
- if (READ_ONCE(ssp->srcu_n_exp_nodelay) > SRCU_MAX_NODELAY_PHASE)
- jbase = 1;
+ if (rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq))) {
+ j = jiffies - 1;
+ gpstart = READ_ONCE(ssp->srcu_gp_start);
+ if (time_after(j, gpstart))
+ jbase += j - gpstart;
+ if (!jbase) {
+ WRITE_ONCE(ssp->srcu_n_exp_nodelay, READ_ONCE(ssp->srcu_n_exp_nodelay) + 1);
+ if (READ_ONCE(ssp->srcu_n_exp_nodelay) > srcu_max_nodelay_phase)
+ jbase = 1;
+ }
}
return jbase > SRCU_MAX_INTERVAL ? SRCU_MAX_INTERVAL : jbase;
}
@@ -607,15 +655,6 @@ void __srcu_read_unlock(struct srcu_struct *ssp, int idx)
EXPORT_SYMBOL_GPL(__srcu_read_unlock);
/*
- * We use an adaptive strategy for synchronize_srcu() and especially for
- * synchronize_srcu_expedited(). We spin for a fixed time period
- * (defined below) to allow SRCU readers to exit their read-side critical
- * sections. If there are still some readers after a few microseconds,
- * we repeatedly block for 1-millisecond time periods.
- */
-#define SRCU_RETRY_CHECK_DELAY 5
-
-/*
* Start an SRCU grace period.
*/
static void srcu_gp_start(struct srcu_struct *ssp)
@@ -700,7 +739,7 @@ static void srcu_schedule_cbs_snp(struct srcu_struct *ssp, struct srcu_node *snp
*/
static void srcu_gp_end(struct srcu_struct *ssp)
{
- unsigned long cbdelay;
+ unsigned long cbdelay = 1;
bool cbs;
bool last_lvl;
int cpu;
@@ -720,7 +759,9 @@ static void srcu_gp_end(struct srcu_struct *ssp)
spin_lock_irq_rcu_node(ssp);
idx = rcu_seq_state(ssp->srcu_gp_seq);
WARN_ON_ONCE(idx != SRCU_STATE_SCAN2);
- cbdelay = !!srcu_get_delay(ssp);
+ if (ULONG_CMP_LT(READ_ONCE(ssp->srcu_gp_seq), READ_ONCE(ssp->srcu_gp_seq_needed_exp)))
+ cbdelay = 0;
+
WRITE_ONCE(ssp->srcu_last_gp_end, ktime_get_mono_fast_ns());
rcu_seq_end(&ssp->srcu_gp_seq);
gpseq = rcu_seq_current(&ssp->srcu_gp_seq);
@@ -921,12 +962,16 @@ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp,
*/
static bool try_check_zero(struct srcu_struct *ssp, int idx, int trycount)
{
+ unsigned long curdelay;
+
+ curdelay = !srcu_get_delay(ssp);
+
for (;;) {
if (srcu_readers_active_idx_check(ssp, idx))
return true;
- if (--trycount + !srcu_get_delay(ssp) <= 0)
+ if ((--trycount + curdelay) <= 0)
return false;
- udelay(SRCU_RETRY_CHECK_DELAY);
+ udelay(srcu_retry_check_delay);
}
}
@@ -1582,7 +1627,7 @@ static void process_srcu(struct work_struct *work)
j = jiffies;
if (READ_ONCE(ssp->reschedule_jiffies) == j) {
WRITE_ONCE(ssp->reschedule_count, READ_ONCE(ssp->reschedule_count) + 1);
- if (READ_ONCE(ssp->reschedule_count) > SRCU_MAX_NODELAY)
+ if (READ_ONCE(ssp->reschedule_count) > srcu_max_nodelay)
curdelay = 1;
} else {
WRITE_ONCE(ssp->reschedule_count, 1);
@@ -1674,6 +1719,11 @@ static int __init srcu_bootup_announce(void)
pr_info("Hierarchical SRCU implementation.\n");
if (exp_holdoff != DEFAULT_SRCU_EXP_HOLDOFF)
pr_info("\tNon-default auto-expedite holdoff of %lu ns.\n", exp_holdoff);
+ if (srcu_retry_check_delay != SRCU_DEFAULT_RETRY_CHECK_DELAY)
+ pr_info("\tNon-default retry check delay of %lu us.\n", srcu_retry_check_delay);
+ if (srcu_max_nodelay != SRCU_DEFAULT_MAX_NODELAY)
+ pr_info("\tNon-default max no-delay of %lu.\n", srcu_max_nodelay);
+ pr_info("\tMax phase no-delay instances is %lu.\n", srcu_max_nodelay_phase);
return 0;
}
early_initcall(srcu_bootup_announce);
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index b5152961b743..7bf561262cb8 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1701,7 +1701,10 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
* the throttle.
*/
p->dl.dl_throttled = 0;
- BUG_ON(!is_dl_boosted(&p->dl) || flags != ENQUEUE_REPLENISH);
+ if (!(flags & ENQUEUE_REPLENISH))
+ printk_deferred_once("sched: DL de-boosted task PID %d: REPLENISH flag missing\n",
+ task_pid_nr(p));
+
return;
}
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index e52b6e372c60..35d034219513 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -446,14 +446,14 @@ static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp,
if (*negp) {
if (*lvalp > (unsigned long) INT_MAX + 1)
return -EINVAL;
- *valp = -*lvalp;
+ WRITE_ONCE(*valp, -*lvalp);
} else {
if (*lvalp > (unsigned long) INT_MAX)
return -EINVAL;
- *valp = *lvalp;
+ WRITE_ONCE(*valp, *lvalp);
}
} else {
- int val = *valp;
+ int val = READ_ONCE(*valp);
if (val < 0) {
*negp = true;
*lvalp = -(unsigned long)val;
@@ -472,9 +472,9 @@ static int do_proc_douintvec_conv(unsigned long *lvalp,
if (write) {
if (*lvalp > UINT_MAX)
return -EINVAL;
- *valp = *lvalp;
+ WRITE_ONCE(*valp, *lvalp);
} else {
- unsigned int val = *valp;
+ unsigned int val = READ_ONCE(*valp);
*lvalp = (unsigned long)val;
}
return 0;
@@ -857,7 +857,7 @@ static int do_proc_dointvec_minmax_conv(bool *negp, unsigned long *lvalp,
if ((param->min && *param->min > tmp) ||
(param->max && *param->max < tmp))
return -EINVAL;
- *valp = tmp;
+ WRITE_ONCE(*valp, tmp);
}
return 0;
@@ -923,7 +923,7 @@ static int do_proc_douintvec_minmax_conv(unsigned long *lvalp,
(param->max && *param->max < tmp))
return -ERANGE;
- *valp = tmp;
+ WRITE_ONCE(*valp, tmp);
}
return 0;
@@ -1007,13 +1007,13 @@ int proc_dou8vec_minmax(struct ctl_table *table, int write,
tmp.maxlen = sizeof(val);
tmp.data = &val;
- val = *data;
+ val = READ_ONCE(*data);
res = do_proc_douintvec(&tmp, write, buffer, lenp, ppos,
do_proc_douintvec_minmax_conv, &param);
if (res)
return res;
if (write)
- *data = val;
+ WRITE_ONCE(*data, val);
return 0;
}
EXPORT_SYMBOL_GPL(proc_dou8vec_minmax);
@@ -1090,9 +1090,9 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table,
err = -EINVAL;
break;
}
- *i = val;
+ WRITE_ONCE(*i, val);
} else {
- val = convdiv * (*i) / convmul;
+ val = convdiv * READ_ONCE(*i) / convmul;
if (!first)
proc_put_char(&buffer, &left, '\t');
proc_put_long(&buffer, &left, val, false);
@@ -1173,9 +1173,12 @@ static int do_proc_dointvec_jiffies_conv(bool *negp, unsigned long *lvalp,
if (write) {
if (*lvalp > INT_MAX / HZ)
return 1;
- *valp = *negp ? -(*lvalp*HZ) : (*lvalp*HZ);
+ if (*negp)
+ WRITE_ONCE(*valp, -*lvalp * HZ);
+ else
+ WRITE_ONCE(*valp, *lvalp * HZ);
} else {
- int val = *valp;
+ int val = READ_ONCE(*valp);
unsigned long lval;
if (val < 0) {
*negp = true;
@@ -1221,9 +1224,9 @@ static int do_proc_dointvec_ms_jiffies_conv(bool *negp, unsigned long *lvalp,
if (jif > INT_MAX)
return 1;
- *valp = (int)jif;
+ WRITE_ONCE(*valp, (int)jif);
} else {
- int val = *valp;
+ int val = READ_ONCE(*valp);
unsigned long lval;
if (val < 0) {
*negp = true;
@@ -1291,8 +1294,8 @@ int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write,
* @ppos: the current position in the file
*
* Reads/writes up to table->maxlen/sizeof(unsigned int) integer
- * values from/to the user buffer, treated as an ASCII string.
- * The values read are assumed to be in 1/1000 seconds, and
+ * values from/to the user buffer, treated as an ASCII string.
+ * The values read are assumed to be in 1/1000 seconds, and
* are converted into jiffies.
*
* Returns 0 on success.
@@ -2091,6 +2094,17 @@ static struct ctl_table vm_table[] = {
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_TWO_HUNDRED,
},
+#ifdef CONFIG_NUMA
+ {
+ .procname = "numa_stat",
+ .data = &sysctl_vm_numa_stat,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = sysctl_vm_numa_stat_handler,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE,
+ },
+#endif
#ifdef CONFIG_HUGETLB_PAGE
{
.procname = "nr_hugepages",
@@ -2107,15 +2121,6 @@ static struct ctl_table vm_table[] = {
.mode = 0644,
.proc_handler = &hugetlb_mempolicy_sysctl_handler,
},
- {
- .procname = "numa_stat",
- .data = &sysctl_vm_numa_stat,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = sysctl_vm_numa_stat_handler,
- .extra1 = SYSCTL_ZERO,
- .extra2 = SYSCTL_ONE,
- },
#endif
{
.procname = "hugetlb_shm_group",
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 1cd10b102c51..5dead89308b7 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -1051,15 +1051,24 @@ retry_delete:
}
/*
- * This is called by do_exit or de_thread, only when there are no more
- * references to the shared signal_struct.
+ * This is called by do_exit or de_thread, only when nobody else can
+ * modify the signal->posix_timers list. Yet we need sighand->siglock
+ * to prevent the race with /proc/pid/timers.
*/
-void exit_itimers(struct signal_struct *sig)
+void exit_itimers(struct task_struct *tsk)
{
+ struct list_head timers;
struct k_itimer *tmr;
- while (!list_empty(&sig->posix_timers)) {
- tmr = list_entry(sig->posix_timers.next, struct k_itimer, list);
+ if (list_empty(&tsk->signal->posix_timers))
+ return;
+
+ spin_lock_irq(&tsk->sighand->siglock);
+ list_replace_init(&tsk->signal->posix_timers, &timers);
+ spin_unlock_irq(&tsk->sighand->siglock);
+
+ while (!list_empty(&timers)) {
+ tmr = list_first_entry(&timers, struct k_itimer, list);
itimer_delete(tmr);
}
}
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index debbbb083286..ccd6a5ade3e9 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -194,7 +194,8 @@ config FUNCTION_TRACER
sequence is then dynamically patched into a tracer call when
tracing is enabled by the administrator. If it's runtime disabled
(the bootup default), then the overhead of the instructions is very
- small and not measurable even in micro-benchmarks.
+ small and not measurable even in micro-benchmarks (at least on
+ x86, but may have impact on other architectures).
config FUNCTION_GRAPH_TRACER
bool "Kernel Function Graph Tracer"
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index a8cfac0611bc..b8dd54627075 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -9864,6 +9864,12 @@ void trace_init_global_iter(struct trace_iterator *iter)
/* Output in nanoseconds only if we are using a clock in nanoseconds. */
if (trace_clocks[iter->tr->clock_id].in_ns)
iter->iter_flags |= TRACE_FILE_TIME_IN_NS;
+
+ /* Can not use kmalloc for iter.temp and iter.fmt */
+ iter->temp = static_temp_buf;
+ iter->temp_size = STATIC_TEMP_BUF_SIZE;
+ iter->fmt = static_fmt_buf;
+ iter->fmt_size = STATIC_FMT_BUF_SIZE;
}
void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
@@ -9896,11 +9902,6 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
/* Simulate the iterator */
trace_init_global_iter(&iter);
- /* Can not use kmalloc for iter.temp and iter.fmt */
- iter.temp = static_temp_buf;
- iter.temp_size = STATIC_TEMP_BUF_SIZE;
- iter.fmt = static_fmt_buf;
- iter.fmt_size = STATIC_FMT_BUF_SIZE;
for_each_tracing_cpu(cpu) {
atomic_inc(&per_cpu_ptr(iter.array_buffer->data, cpu)->disabled);
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 48e82e141d54..e87a46794079 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -4430,6 +4430,8 @@ static int parse_var_defs(struct hist_trigger_data *hist_data)
s = kstrdup(field_str, GFP_KERNEL);
if (!s) {
+ kfree(hist_data->attrs->var_defs.name[n_vars]);
+ hist_data->attrs->var_defs.name[n_vars] = NULL;
ret = -ENOMEM;
goto free;
}
diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c
index 230038d4f908..bb9962b33f95 100644
--- a/kernel/watch_queue.c
+++ b/kernel/watch_queue.c
@@ -34,6 +34,27 @@ MODULE_LICENSE("GPL");
#define WATCH_QUEUE_NOTE_SIZE 128
#define WATCH_QUEUE_NOTES_PER_PAGE (PAGE_SIZE / WATCH_QUEUE_NOTE_SIZE)
+/*
+ * This must be called under the RCU read-lock, which makes
+ * sure that the wqueue still exists. It can then take the lock,
+ * and check that the wqueue hasn't been destroyed, which in
+ * turn makes sure that the notification pipe still exists.
+ */
+static inline bool lock_wqueue(struct watch_queue *wqueue)
+{
+ spin_lock_bh(&wqueue->lock);
+ if (unlikely(wqueue->defunct)) {
+ spin_unlock_bh(&wqueue->lock);
+ return false;
+ }
+ return true;
+}
+
+static inline void unlock_wqueue(struct watch_queue *wqueue)
+{
+ spin_unlock_bh(&wqueue->lock);
+}
+
static void watch_queue_pipe_buf_release(struct pipe_inode_info *pipe,
struct pipe_buffer *buf)
{
@@ -69,6 +90,10 @@ static const struct pipe_buf_operations watch_queue_pipe_buf_ops = {
/*
* Post a notification to a watch queue.
+ *
+ * Must be called with the RCU lock for reading, and the
+ * watch_queue lock held, which guarantees that the pipe
+ * hasn't been released.
*/
static bool post_one_notification(struct watch_queue *wqueue,
struct watch_notification *n)
@@ -85,9 +110,6 @@ static bool post_one_notification(struct watch_queue *wqueue,
spin_lock_irq(&pipe->rd_wait.lock);
- if (wqueue->defunct)
- goto out;
-
mask = pipe->ring_size - 1;
head = pipe->head;
tail = pipe->tail;
@@ -203,7 +225,10 @@ void __post_watch_notification(struct watch_list *wlist,
if (security_post_notification(watch->cred, cred, n) < 0)
continue;
- post_one_notification(wqueue, n);
+ if (lock_wqueue(wqueue)) {
+ post_one_notification(wqueue, n);
+ unlock_wqueue(wqueue);
+ }
}
rcu_read_unlock();
@@ -462,11 +487,12 @@ int add_watch_to_object(struct watch *watch, struct watch_list *wlist)
return -EAGAIN;
}
- spin_lock_bh(&wqueue->lock);
- kref_get(&wqueue->usage);
- kref_get(&watch->usage);
- hlist_add_head(&watch->queue_node, &wqueue->watches);
- spin_unlock_bh(&wqueue->lock);
+ if (lock_wqueue(wqueue)) {
+ kref_get(&wqueue->usage);
+ kref_get(&watch->usage);
+ hlist_add_head(&watch->queue_node, &wqueue->watches);
+ unlock_wqueue(wqueue);
+ }
hlist_add_head(&watch->list_node, &wlist->watchers);
return 0;
@@ -520,20 +546,15 @@ found:
wqueue = rcu_dereference(watch->queue);
- /* We don't need the watch list lock for the next bit as RCU is
- * protecting *wqueue from deallocation.
- */
- if (wqueue) {
+ if (lock_wqueue(wqueue)) {
post_one_notification(wqueue, &n.watch);
- spin_lock_bh(&wqueue->lock);
-
if (!hlist_unhashed(&watch->queue_node)) {
hlist_del_init_rcu(&watch->queue_node);
put_watch(watch);
}
- spin_unlock_bh(&wqueue->lock);
+ unlock_wqueue(wqueue);
}
if (wlist->release_watch) {
Copyright © 1990 – 2022 jet tsang zeon-git.
All Rights Reverse Engineered.