summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/filemap.c5
-rw-r--r--mm/hugetlb.c37
-rw-r--r--mm/init-mm.c2
-rw-r--r--mm/memcontrol.c4
-rw-r--r--mm/memory_hotplug.c28
-rw-r--r--mm/mempolicy.c2
-rw-r--r--mm/page_alloc.c17
-rw-r--r--mm/vmscan.c14
-rw-r--r--mm/zswap.c30
9 files changed, 109 insertions, 30 deletions
diff --git a/mm/filemap.c b/mm/filemap.c
index c46678d7d041..33be70a2ded3 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1561,6 +1561,11 @@ static ssize_t do_generic_file_read(struct file *filp, loff_t *ppos,
cond_resched();
find_page:
+ if (fatal_signal_pending(current)) {
+ error = -EINTR;
+ goto out;
+ }
+
page = find_get_page(mapping, index);
if (!page) {
page_cache_sync_readahead(mapping,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 4434cdd4cd9a..ea11123a9249 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1723,23 +1723,32 @@ free:
}
/*
- * When releasing a hugetlb pool reservation, any surplus pages that were
- * allocated to satisfy the reservation must be explicitly freed if they were
- * never used.
- * Called with hugetlb_lock held.
+ * This routine has two main purposes:
+ * 1) Decrement the reservation count (resv_huge_pages) by the value passed
+ * in unused_resv_pages. This corresponds to the prior adjustments made
+ * to the associated reservation map.
+ * 2) Free any unused surplus pages that may have been allocated to satisfy
+ * the reservation. As many as unused_resv_pages may be freed.
+ *
+ * Called with hugetlb_lock held. However, the lock could be dropped (and
+ * reacquired) during calls to cond_resched_lock. Whenever dropping the lock,
+ * we must make sure nobody else can claim pages we are in the process of
+ * freeing. Do this by ensuring resv_huge_page always is greater than the
+ * number of huge pages we plan to free when dropping the lock.
*/
static void return_unused_surplus_pages(struct hstate *h,
unsigned long unused_resv_pages)
{
unsigned long nr_pages;
- /* Uncommit the reservation */
- h->resv_huge_pages -= unused_resv_pages;
-
/* Cannot return gigantic pages currently */
if (hstate_is_gigantic(h))
- return;
+ goto out;
+ /*
+ * Part (or even all) of the reservation could have been backed
+ * by pre-allocated pages. Only free surplus pages.
+ */
nr_pages = min(unused_resv_pages, h->surplus_huge_pages);
/*
@@ -1749,12 +1758,22 @@ static void return_unused_surplus_pages(struct hstate *h,
* when the nodes with surplus pages have no free pages.
* free_pool_huge_page() will balance the the freed pages across the
* on-line nodes with memory and will handle the hstate accounting.
+ *
+ * Note that we decrement resv_huge_pages as we free the pages. If
+ * we drop the lock, resv_huge_pages will still be sufficiently large
+ * to cover subsequent pages we may free.
*/
while (nr_pages--) {
+ h->resv_huge_pages--;
+ unused_resv_pages--;
if (!free_pool_huge_page(h, &node_states[N_MEMORY], 1))
- break;
+ goto out;
cond_resched_lock(&hugetlb_lock);
}
+
+out:
+ /* Fully uncommit the reservation */
+ h->resv_huge_pages -= unused_resv_pages;
}
diff --git a/mm/init-mm.c b/mm/init-mm.c
index a56a851908d2..975e49f00f34 100644
--- a/mm/init-mm.c
+++ b/mm/init-mm.c
@@ -6,6 +6,7 @@
#include <linux/cpumask.h>
#include <linux/atomic.h>
+#include <linux/user_namespace.h>
#include <asm/pgtable.h>
#include <asm/mmu.h>
@@ -21,5 +22,6 @@ struct mm_struct init_mm = {
.mmap_sem = __RWSEM_INITIALIZER(init_mm.mmap_sem),
.page_table_lock = __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock),
.mmlist = LIST_HEAD_INIT(init_mm.mmlist),
+ .user_ns = &init_user_ns,
INIT_MM_CONTEXT(init_mm)
};
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 5d9c8a3136bc..43eefe9d834c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4496,9 +4496,9 @@ static int mem_cgroup_do_precharge(unsigned long count)
return ret;
}
- /* Try charges one by one with reclaim */
+ /* Try charges one by one with reclaim, but do not retry */
while (count--) {
- ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_NORETRY, 1);
+ ret = try_charge(mc.to, GFP_KERNEL | __GFP_NORETRY, 1);
if (ret)
return ret;
mc.precharge++;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 91f7c074e385..2ad8a8888032 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1374,17 +1374,20 @@ int is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages)
}
/*
- * Confirm all pages in a range [start, end) is belongs to the same zone.
+ * Confirm all pages in a range [start, end) belong to the same zone.
+ * When true, return its valid [start, end).
*/
-int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn)
+int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
+ unsigned long *valid_start, unsigned long *valid_end)
{
unsigned long pfn, sec_end_pfn;
+ unsigned long start, end;
struct zone *zone = NULL;
struct page *page;
int i;
- for (pfn = start_pfn, sec_end_pfn = SECTION_ALIGN_UP(start_pfn);
+ for (pfn = start_pfn, sec_end_pfn = SECTION_ALIGN_UP(start_pfn + 1);
pfn < end_pfn;
- pfn = sec_end_pfn + 1, sec_end_pfn += PAGES_PER_SECTION) {
+ pfn = sec_end_pfn, sec_end_pfn += PAGES_PER_SECTION) {
/* Make sure the memory section is present first */
if (!present_section_nr(pfn_to_section_nr(pfn)))
continue;
@@ -1400,10 +1403,20 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn)
page = pfn_to_page(pfn + i);
if (zone && page_zone(page) != zone)
return 0;
+ if (!zone)
+ start = pfn + i;
zone = page_zone(page);
+ end = pfn + MAX_ORDER_NR_PAGES;
}
}
- return 1;
+
+ if (zone) {
+ *valid_start = start;
+ *valid_end = end;
+ return 1;
+ } else {
+ return 0;
+ }
}
/*
@@ -1721,6 +1734,7 @@ static int __ref __offline_pages(unsigned long start_pfn,
long offlined_pages;
int ret, drain, retry_max, node;
unsigned long flags;
+ unsigned long valid_start, valid_end;
struct zone *zone;
struct memory_notify arg;
@@ -1731,10 +1745,10 @@ static int __ref __offline_pages(unsigned long start_pfn,
return -EINVAL;
/* This makes hotplug much easier...and readable.
we assume this for now. .*/
- if (!test_pages_in_a_zone(start_pfn, end_pfn))
+ if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end))
return -EINVAL;
- zone = page_zone(pfn_to_page(start_pfn));
+ zone = page_zone(pfn_to_page(valid_start));
node = zone_to_nid(zone);
nr_pages = end_pfn - start_pfn;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index f20eb4e8c4cc..9174ec544632 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2007,8 +2007,8 @@ retry_cpuset:
nmask = policy_nodemask(gfp, pol);
zl = policy_zonelist(gfp, pol, node);
- mpol_cond_put(pol);
page = __alloc_pages_nodemask(gfp, order, zl, nmask);
+ mpol_cond_put(pol);
out:
if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
goto retry_cpuset;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3048c5dbda16..fbed8bb17388 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5801,15 +5801,18 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
sizeof(arch_zone_lowest_possible_pfn));
memset(arch_zone_highest_possible_pfn, 0,
sizeof(arch_zone_highest_possible_pfn));
- arch_zone_lowest_possible_pfn[0] = find_min_pfn_with_active_regions();
- arch_zone_highest_possible_pfn[0] = max_zone_pfn[0];
- for (i = 1; i < MAX_NR_ZONES; i++) {
+
+ start_pfn = find_min_pfn_with_active_regions();
+
+ for (i = 0; i < MAX_NR_ZONES; i++) {
if (i == ZONE_MOVABLE)
continue;
- arch_zone_lowest_possible_pfn[i] =
- arch_zone_highest_possible_pfn[i-1];
- arch_zone_highest_possible_pfn[i] =
- max(max_zone_pfn[i], arch_zone_lowest_possible_pfn[i]);
+
+ end_pfn = max(max_zone_pfn[i], start_pfn);
+ arch_zone_lowest_possible_pfn[i] = start_pfn;
+ arch_zone_highest_possible_pfn[i] = end_pfn;
+
+ start_pfn = end_pfn;
}
arch_zone_lowest_possible_pfn[ZONE_MOVABLE] = 0;
arch_zone_highest_possible_pfn[ZONE_MOVABLE] = 0;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index d82765ba44f4..5e9e74955bd1 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -290,6 +290,7 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
int nid = shrinkctl->nid;
long batch_size = shrinker->batch ? shrinker->batch
: SHRINK_BATCH;
+ long scanned = 0, next_deferred;
long min_cache_size = batch_size;
if (current_is_kswapd())
@@ -315,7 +316,9 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
pr_err("shrink_slab: %pF negative objects to delete nr=%ld\n",
shrinker->scan_objects, total_scan);
total_scan = freeable;
- }
+ next_deferred = nr;
+ } else
+ next_deferred = total_scan;
/*
* We need to avoid excessive windup on filesystem shrinkers
@@ -372,17 +375,22 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
count_vm_events(SLABS_SCANNED, nr_to_scan);
total_scan -= nr_to_scan;
+ scanned += nr_to_scan;
cond_resched();
}
+ if (next_deferred >= scanned)
+ next_deferred -= scanned;
+ else
+ next_deferred = 0;
/*
* move the unused scan count back into the shrinker in a
* manner that handles concurrent updates. If we exhausted the
* scan, there is no need to do an update.
*/
- if (total_scan > 0)
- new_nr = atomic_long_add_return(total_scan,
+ if (next_deferred > 0)
+ new_nr = atomic_long_add_return(next_deferred,
&shrinker->nr_deferred[nid]);
else
new_nr = atomic_long_read(&shrinker->nr_deferred[nid]);
diff --git a/mm/zswap.c b/mm/zswap.c
index 340261946fda..45476f429789 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -78,7 +78,13 @@ static u64 zswap_duplicate_entry;
/* Enable/disable zswap (disabled by default) */
static bool zswap_enabled;
-module_param_named(enabled, zswap_enabled, bool, 0644);
+static int zswap_enabled_param_set(const char *,
+ const struct kernel_param *);
+static struct kernel_param_ops zswap_enabled_param_ops = {
+ .set = zswap_enabled_param_set,
+ .get = param_get_bool,
+};
+module_param_cb(enabled, &zswap_enabled_param_ops, &zswap_enabled, 0644);
/* Crypto compressor to use */
#define ZSWAP_COMPRESSOR_DEFAULT "lzo"
@@ -176,6 +182,9 @@ static atomic_t zswap_pools_count = ATOMIC_INIT(0);
/* used by param callback function */
static bool zswap_init_started;
+/* fatal error during init */
+static bool zswap_init_failed;
+
/*********************************
* helpers and fwd declarations
**********************************/
@@ -702,6 +711,11 @@ static int __zswap_param_set(const char *val, const struct kernel_param *kp,
char *s = strstrip((char *)val);
int ret;
+ if (zswap_init_failed) {
+ pr_err("can't set param, initialization failed\n");
+ return -ENODEV;
+ }
+
/* no change required */
if (!strcmp(s, *(char **)kp->arg))
return 0;
@@ -781,6 +795,17 @@ static int zswap_zpool_param_set(const char *val,
return __zswap_param_set(val, kp, NULL, zswap_compressor);
}
+static int zswap_enabled_param_set(const char *val,
+ const struct kernel_param *kp)
+{
+ if (zswap_init_failed) {
+ pr_err("can't enable, initialization failed\n");
+ return -ENODEV;
+ }
+
+ return param_set_bool(val, kp);
+}
+
/*********************************
* writeback code
**********************************/
@@ -1267,6 +1292,9 @@ pool_fail:
dstmem_fail:
zswap_entry_cache_destroy();
cache_fail:
+ /* if built-in, we aren't unloaded on failure; don't allow use */
+ zswap_init_failed = true;
+ zswap_enabled = false;
return -ENOMEM;
}
/* must be late so crypto has time to come up */
generated by cgit v1.2.3 (git 2.25.1) at 2025-12-28 08:46:25 +0000