aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
Diffstat
-rw-r--r--drivers/mtd/mtdcore.c6
-rw-r--r--fs/fs-writeback.c2
-rw-r--r--fs/inode.c16
-rw-r--r--fs/internal.h1
-rw-r--r--fs/proc/base.c5
-rw-r--r--include/linux/bug.h1
-rw-r--r--include/linux/gfp.h5
-rw-r--r--include/trace/events/gfpflags.h1
-rw-r--r--kernel/futex.c18
-rw-r--r--kernel/watchdog.c4
-rw-r--r--mm/page_alloc.c7
-rw-r--r--mm/vmscan.c37
-rw-r--r--scripts/headers_install.pl3
13 files changed, 83 insertions, 23 deletions
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 374c46dff7dd..ec794a72975d 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -1077,7 +1077,8 @@ EXPORT_SYMBOL_GPL(mtd_writev);
* until the request succeeds or until the allocation size falls below
* the system page size. This attempts to make sure it does not adversely
* impact system performance, so when allocating more than one page, we
- * ask the memory allocator to avoid re-trying.
+ * ask the memory allocator to avoid re-trying, swapping, writing back
+ * or performing I/O.
*
* Note, this function also makes sure that the allocated buffer is aligned to
* the MTD device's min. I/O unit, i.e. the "mtd->writesize" value.
@@ -1091,7 +1092,8 @@ EXPORT_SYMBOL_GPL(mtd_writev);
*/
void *mtd_kmalloc_up_to(const struct mtd_info *mtd, size_t *size)
{
- gfp_t flags = __GFP_NOWARN | __GFP_WAIT | __GFP_NORETRY;
+ gfp_t flags = __GFP_NOWARN | __GFP_WAIT |
+ __GFP_NORETRY | __GFP_NO_KSWAPD;
size_t min_alloc = max_t(size_t, mtd->writesize, PAGE_SIZE);
void *kbuf;
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 51ea267d444c..3e3422f7f0a4 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -228,6 +228,8 @@ static void requeue_io(struct inode *inode, struct bdi_writeback *wb)
static void inode_sync_complete(struct inode *inode)
{
inode->i_state &= ~I_SYNC;
+ /* If inode is clean an unused, put it into LRU now... */
+ inode_add_lru(inode);
/* Waiters must see I_SYNC cleared before being woken up */
smp_mb();
wake_up_bit(&inode->i_state, __I_SYNC);
diff --git a/fs/inode.c b/fs/inode.c
index b03c71957246..64999f144153 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -408,6 +408,19 @@ static void inode_lru_list_add(struct inode *inode)
spin_unlock(&inode->i_sb->s_inode_lru_lock);
}
+/*
+ * Add inode to LRU if needed (inode is unused and clean).
+ *
+ * Needs inode->i_lock held.
+ */
+void inode_add_lru(struct inode *inode)
+{
+ if (!(inode->i_state & (I_DIRTY | I_SYNC | I_FREEING | I_WILL_FREE)) &&
+ !atomic_read(&inode->i_count) && inode->i_sb->s_flags & MS_ACTIVE)
+ inode_lru_list_add(inode);
+}
+
+
static void inode_lru_list_del(struct inode *inode)
{
spin_lock(&inode->i_sb->s_inode_lru_lock);
@@ -1390,8 +1403,7 @@ static void iput_final(struct inode *inode)
if (!drop && (sb->s_flags & MS_ACTIVE)) {
inode->i_state |= I_REFERENCED;
- if (!(inode->i_state & (I_DIRTY|I_SYNC)))
- inode_lru_list_add(inode);
+ inode_add_lru(inode);
spin_unlock(&inode->i_lock);
return;
}
diff --git a/fs/internal.h b/fs/internal.h
index 916b7cbf3e3e..2f6af7f645eb 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -110,6 +110,7 @@ extern int open_check_o_direct(struct file *f);
* inode.c
*/
extern spinlock_t inode_sb_list_lock;
+extern void inode_add_lru(struct inode *inode);
/*
* fs-writeback.c
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 3c231adf8450..9e28356a959a 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1877,8 +1877,9 @@ static struct dentry *proc_map_files_lookup(struct inode *dir,
if (!vma)
goto out_no_vma;
- result = proc_map_files_instantiate(dir, dentry, task,
- (void *)(unsigned long)vma->vm_file->f_mode);
+ if (vma->vm_file)
+ result = proc_map_files_instantiate(dir, dentry, task,
+ (void *)(unsigned long)vma->vm_file->f_mode);
out_no_vma:
up_read(&mm->mmap_sem);
diff --git a/include/linux/bug.h b/include/linux/bug.h
index aaac4bba6f5c..b1cf40de847e 100644
--- a/include/linux/bug.h
+++ b/include/linux/bug.h
@@ -15,6 +15,7 @@ struct pt_regs;
#define BUILD_BUG_ON_NOT_POWER_OF_2(n)
#define BUILD_BUG_ON_ZERO(e) (0)
#define BUILD_BUG_ON_NULL(e) ((void*)0)
+#define BUILD_BUG_ON_INVALID(e) (0)
#define BUILD_BUG_ON(condition)
#define BUILD_BUG() (0)
#else /* __CHECKER__ */
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 02c1c9710be0..d0a79678f169 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -31,6 +31,7 @@ struct vm_area_struct;
#define ___GFP_THISNODE 0x40000u
#define ___GFP_RECLAIMABLE 0x80000u
#define ___GFP_NOTRACK 0x200000u
+#define ___GFP_NO_KSWAPD 0x400000u
#define ___GFP_OTHER_NODE 0x800000u
#define ___GFP_WRITE 0x1000000u
@@ -85,6 +86,7 @@ struct vm_area_struct;
#define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) /* Page is reclaimable */
#define __GFP_NOTRACK ((__force gfp_t)___GFP_NOTRACK) /* Don't track with kmemcheck */
+#define __GFP_NO_KSWAPD ((__force gfp_t)___GFP_NO_KSWAPD)
#define __GFP_OTHER_NODE ((__force gfp_t)___GFP_OTHER_NODE) /* On behalf of other node */
#define __GFP_WRITE ((__force gfp_t)___GFP_WRITE) /* Allocator intends to dirty page */
@@ -114,7 +116,8 @@ struct vm_area_struct;
__GFP_MOVABLE)
#define GFP_IOFS (__GFP_IO | __GFP_FS)
#define GFP_TRANSHUGE (GFP_HIGHUSER_MOVABLE | __GFP_COMP | \
- __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN)
+ __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN | \
+ __GFP_NO_KSWAPD)
#ifdef CONFIG_NUMA
#define GFP_THISNODE (__GFP_THISNODE | __GFP_NOWARN | __GFP_NORETRY)
diff --git a/include/trace/events/gfpflags.h b/include/trace/events/gfpflags.h
index 9391706e9254..d6fd8e5b14b7 100644
--- a/include/trace/events/gfpflags.h
+++ b/include/trace/events/gfpflags.h
@@ -36,6 +36,7 @@
{(unsigned long)__GFP_RECLAIMABLE, "GFP_RECLAIMABLE"}, \
{(unsigned long)__GFP_MOVABLE, "GFP_MOVABLE"}, \
{(unsigned long)__GFP_NOTRACK, "GFP_NOTRACK"}, \
+ {(unsigned long)__GFP_NO_KSWAPD, "GFP_NO_KSWAPD"}, \
{(unsigned long)__GFP_OTHER_NODE, "GFP_OTHER_NODE"} \
) : "GFP_NOWAIT"
diff --git a/kernel/futex.c b/kernel/futex.c
index 20ef219bbe9b..19eb089ca003 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -843,6 +843,9 @@ static void wake_futex(struct futex_q *q)
{
struct task_struct *p = q->task;
+ if (WARN(q->pi_state || q->rt_waiter, "refusing to wake PI futex\n"))
+ return;
+
/*
* We set q->lock_ptr = NULL _before_ we wake up the task. If
* a non-futex wake up happens on another CPU then the task
@@ -1078,6 +1081,10 @@ retry_private:
plist_for_each_entry_safe(this, next, head, list) {
if (match_futex (&this->key, &key1)) {
+ if (this->pi_state || this->rt_waiter) {
+ ret = -EINVAL;
+ goto out_unlock;
+ }
wake_futex(this);
if (++ret >= nr_wake)
break;
@@ -1090,6 +1097,10 @@ retry_private:
op_ret = 0;
plist_for_each_entry_safe(this, next, head, list) {
if (match_futex (&this->key, &key2)) {
+ if (this->pi_state || this->rt_waiter) {
+ ret = -EINVAL;
+ goto out_unlock;
+ }
wake_futex(this);
if (++op_ret >= nr_wake2)
break;
@@ -1098,6 +1109,7 @@ retry_private:
ret += op_ret;
}
+out_unlock:
double_unlock_hb(hb1, hb2);
out_put_keys:
put_futex_key(&key2);
@@ -1387,9 +1399,13 @@ retry_private:
/*
* FUTEX_WAIT_REQEUE_PI and FUTEX_CMP_REQUEUE_PI should always
* be paired with each other and no other futex ops.
+ *
+ * We should never be requeueing a futex_q with a pi_state,
+ * which is awaiting a futex_unlock_pi().
*/
if ((requeue_pi && !this->rt_waiter) ||
- (!requeue_pi && this->rt_waiter)) {
+ (!requeue_pi && this->rt_waiter) ||
+ this->pi_state) {
ret = -EINVAL;
break;
}
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 9d4c8d5a1f53..dd4b80a9f1a9 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -116,7 +116,7 @@ static unsigned long get_timestamp(int this_cpu)
return cpu_clock(this_cpu) >> 30LL; /* 2^30 ~= 10^9 */
}
-static unsigned long get_sample_period(void)
+static u64 get_sample_period(void)
{
/*
* convert watchdog_thresh from seconds to ns
@@ -125,7 +125,7 @@ static unsigned long get_sample_period(void)
* and hard thresholds) to increment before the
* hardlockup detector generates a warning
*/
- return get_softlockup_thresh() * (NSEC_PER_SEC / 5);
+ return get_softlockup_thresh() * ((u64)NSEC_PER_SEC / 5);
}
/* Commands for resetting the watchdog */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index bcb72c6e2b2d..92871579cbee 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2416,8 +2416,9 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
goto nopage;
restart:
- wake_all_kswapd(order, zonelist, high_zoneidx,
- zone_idx(preferred_zone));
+ if (!(gfp_mask & __GFP_NO_KSWAPD))
+ wake_all_kswapd(order, zonelist, high_zoneidx,
+ zone_idx(preferred_zone));
/*
* OK, we're below the kswapd watermark and have kicked background
@@ -2494,7 +2495,7 @@ rebalance:
* system then fail the allocation instead of entering direct reclaim.
*/
if ((deferred_compaction || contended_compaction) &&
- (gfp_mask & (__GFP_MOVABLE|__GFP_REPEAT)) == __GFP_MOVABLE)
+ (gfp_mask & __GFP_NO_KSWAPD))
goto nopage;
/* Try direct reclaim and then allocating */
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 48550c66f1f2..cbf84e152f04 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2207,9 +2207,12 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
* Throttle direct reclaimers if backing storage is backed by the network
* and the PFMEMALLOC reserve for the preferred node is getting dangerously
* depleted. kswapd will continue to make progress and wake the processes
- * when the low watermark is reached
+ * when the low watermark is reached.
+ *
+ * Returns true if a fatal signal was delivered during throttling. If this
+ * happens, the page allocator should not consider triggering the OOM killer.
*/
-static void throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
+static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
nodemask_t *nodemask)
{
struct zone *zone;
@@ -2224,13 +2227,20 @@ static void throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
* processes to block on log_wait_commit().
*/
if (current->flags & PF_KTHREAD)
- return;
+ goto out;
+
+ /*
+ * If a fatal signal is pending, this process should not throttle.
+ * It should return quickly so it can exit and free its memory
+ */
+ if (fatal_signal_pending(current))
+ goto out;
/* Check if the pfmemalloc reserves are ok */
first_zones_zonelist(zonelist, high_zoneidx, NULL, &zone);
pgdat = zone->zone_pgdat;
if (pfmemalloc_watermark_ok(pgdat))
- return;
+ goto out;
/* Account for the throttling */
count_vm_event(PGSCAN_DIRECT_THROTTLE);
@@ -2246,12 +2256,20 @@ static void throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
if (!(gfp_mask & __GFP_FS)) {
wait_event_interruptible_timeout(pgdat->pfmemalloc_wait,
pfmemalloc_watermark_ok(pgdat), HZ);
- return;
+
+ goto check_pending;
}
/* Throttle until kswapd wakes the process */
wait_event_killable(zone->zone_pgdat->pfmemalloc_wait,
pfmemalloc_watermark_ok(pgdat));
+
+check_pending:
+ if (fatal_signal_pending(current))
+ return true;
+
+out:
+ return false;
}
unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
@@ -2273,13 +2291,12 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
.gfp_mask = sc.gfp_mask,
};
- throttle_direct_reclaim(gfp_mask, zonelist, nodemask);
-
/*
- * Do not enter reclaim if fatal signal is pending. 1 is returned so
- * that the page allocator does not consider triggering OOM
+ * Do not enter reclaim if fatal signal was delivered while throttled.
+ * 1 is returned so that the page allocator does not OOM kill at this
+ * point.
*/
- if (fatal_signal_pending(current))
+ if (throttle_direct_reclaim(gfp_mask, zonelist, nodemask))
return 1;
trace_mm_vmscan_direct_reclaim_begin(order,
diff --git a/scripts/headers_install.pl b/scripts/headers_install.pl
index 239d22d4207b..6c353ae8a451 100644
--- a/scripts/headers_install.pl
+++ b/scripts/headers_install.pl
@@ -42,6 +42,9 @@ foreach my $filename (@files) {
$line =~ s/(^|\s)(inline)\b/$1__$2__/g;
$line =~ s/(^|\s)(asm)\b(\s|[(]|$)/$1__$2__$3/g;
$line =~ s/(^|\s|[(])(volatile)\b(\s|[(]|$)/$1__$2__$3/g;
+ $line =~ s/#ifndef _UAPI/#ifndef /;
+ $line =~ s/#define _UAPI/#define /;
+ $line =~ s!#endif /[*] _UAPI!#endif /* !;
printf {$out} "%s", $line;
}
close $out;
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.