aboutsummaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/Kconfig9
-rw-r--r--mm/Makefile4
-rw-r--r--mm/huge_memory.c11
-rw-r--r--mm/hugetlb.c1
-rw-r--r--mm/kasan/quarantine.c7
-rw-r--r--mm/memcontrol.c82
-rw-r--r--mm/memory_hotplug.c2
-rw-r--r--mm/mempolicy.c17
-rw-r--r--mm/oom_kill.c2
-rw-r--r--mm/page_alloc.c121
-rw-r--r--mm/readahead.c9
-rw-r--r--mm/rmap.c7
-rw-r--r--mm/shmem.c4
-rw-r--r--mm/slab.c30
-rw-r--r--mm/slub.c46
-rw-r--r--mm/usercopy.c277
-rw-r--r--mm/vmscan.c22
17 files changed, 535 insertions, 116 deletions
diff --git a/mm/Kconfig b/mm/Kconfig
index 78a23c5c302d..be0ee11fa0d9 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -262,7 +262,14 @@ config COMPACTION
select MIGRATION
depends on MMU
help
- Allows the compaction of memory for the allocation of huge pages.
+ Compaction is the only memory management component to form
+ high order (larger physically contiguous) memory blocks
+ reliably. The page allocator relies on compaction heavily and
+ the lack of the feature can lead to unexpected OOM killer
+ invocations for high order memory requests. You shouldn't
+ disable this option unless there really is a strong reason for
+ it and then we would be really interested to hear about that at
+ linux-mm@kvack.org.
#
# support for page migration
diff --git a/mm/Makefile b/mm/Makefile
index fc059666c760..2ca1faf3fa09 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -21,6 +21,9 @@ KCOV_INSTRUMENT_memcontrol.o := n
KCOV_INSTRUMENT_mmzone.o := n
KCOV_INSTRUMENT_vmstat.o := n
+# Since __builtin_frame_address does work as used, disable the warning.
+CFLAGS_usercopy.o += $(call cc-disable-warning, frame-address)
+
mmu-y := nommu.o
mmu-$(CONFIG_MMU) := gup.o highmem.o memory.o mincore.o \
mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \
@@ -99,3 +102,4 @@ obj-$(CONFIG_USERFAULTFD) += userfaultfd.o
obj-$(CONFIG_IDLE_PAGE_TRACKING) += page_idle.o
obj-$(CONFIG_FRAME_VECTOR) += frame_vector.o
obj-$(CONFIG_DEBUG_PAGE_REF) += debug_page_ref.o
+obj-$(CONFIG_HARDENED_USERCOPY) += usercopy.o
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 2373f0a7d340..a6abd76baa72 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1078,7 +1078,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
goto out;
page = pmd_page(*pmd);
- VM_BUG_ON_PAGE(!PageHead(page), page);
+ VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page);
if (flags & FOLL_TOUCH)
touch_pmd(vma, addr, pmd);
if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
@@ -1116,7 +1116,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
}
skip_mlock:
page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT;
- VM_BUG_ON_PAGE(!PageCompound(page), page);
+ VM_BUG_ON_PAGE(!PageCompound(page) && !is_zone_device_page(page), page);
if (flags & FOLL_GET)
get_page(page);
@@ -1512,7 +1512,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
struct page *page;
pgtable_t pgtable;
pmd_t _pmd;
- bool young, write, dirty;
+ bool young, write, dirty, soft_dirty;
unsigned long addr;
int i;
@@ -1546,6 +1546,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
write = pmd_write(*pmd);
young = pmd_young(*pmd);
dirty = pmd_dirty(*pmd);
+ soft_dirty = pmd_soft_dirty(*pmd);
pmdp_huge_split_prepare(vma, haddr, pmd);
pgtable = pgtable_trans_huge_withdraw(mm, pmd);
@@ -1562,6 +1563,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
swp_entry_t swp_entry;
swp_entry = make_migration_entry(page + i, write);
entry = swp_entry_to_pte(swp_entry);
+ if (soft_dirty)
+ entry = pte_swp_mksoft_dirty(entry);
} else {
entry = mk_pte(page + i, vma->vm_page_prot);
entry = maybe_mkwrite(entry, vma);
@@ -1569,6 +1572,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
entry = pte_wrprotect(entry);
if (!young)
entry = pte_mkold(entry);
+ if (soft_dirty)
+ entry = pte_mksoft_dirty(entry);
}
if (dirty)
SetPageDirty(page + i);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index b9aa1b0b38b0..87e11d8ad536 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1448,6 +1448,7 @@ static void dissolve_free_huge_page(struct page *page)
list_del(&page->lru);
h->free_huge_pages--;
h->free_huge_pages_node[nid]--;
+ h->max_huge_pages--;
update_and_free_page(h, page);
}
spin_unlock(&hugetlb_lock);
diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c
index b6728a33a4ac..baabaad4a4aa 100644
--- a/mm/kasan/quarantine.c
+++ b/mm/kasan/quarantine.c
@@ -217,11 +217,8 @@ void quarantine_reduce(void)
new_quarantine_size = (READ_ONCE(totalram_pages) << PAGE_SHIFT) /
QUARANTINE_FRACTION;
percpu_quarantines = QUARANTINE_PERCPU_SIZE * num_online_cpus();
- if (WARN_ONCE(new_quarantine_size < percpu_quarantines,
- "Too little memory, disabling global KASAN quarantine.\n"))
- new_quarantine_size = 0;
- else
- new_quarantine_size -= percpu_quarantines;
+ new_quarantine_size = (new_quarantine_size < percpu_quarantines) ?
+ 0 : new_quarantine_size - percpu_quarantines;
WRITE_ONCE(quarantine_size, new_quarantine_size);
last = global_quarantine.head;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 66beca1ad92f..9a6a51a7c416 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2337,8 +2337,11 @@ int memcg_kmem_charge(struct page *page, gfp_t gfp, int order)
return 0;
memcg = get_mem_cgroup_from_mm(current->mm);
- if (!mem_cgroup_is_root(memcg))
+ if (!mem_cgroup_is_root(memcg)) {
ret = memcg_kmem_charge_memcg(page, gfp, order, memcg);
+ if (!ret)
+ __SetPageKmemcg(page);
+ }
css_put(&memcg->css);
return ret;
}
@@ -2365,6 +2368,11 @@ void memcg_kmem_uncharge(struct page *page, int order)
page_counter_uncharge(&memcg->memsw, nr_pages);
page->mem_cgroup = NULL;
+
+ /* slab pages do not have PageKmemcg flag set */
+ if (PageKmemcg(page))
+ __ClearPageKmemcg(page);
+
css_put_many(&memcg->css, nr_pages);
}
#endif /* !CONFIG_SLOB */
@@ -4069,14 +4077,14 @@ static struct cftype mem_cgroup_legacy_files[] = {
static DEFINE_IDR(mem_cgroup_idr);
-static void mem_cgroup_id_get(struct mem_cgroup *memcg)
+static void mem_cgroup_id_get_many(struct mem_cgroup *memcg, unsigned int n)
{
- atomic_inc(&memcg->id.ref);
+ atomic_add(n, &memcg->id.ref);
}
-static void mem_cgroup_id_put(struct mem_cgroup *memcg)
+static void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n)
{
- if (atomic_dec_and_test(&memcg->id.ref)) {
+ if (atomic_sub_and_test(n, &memcg->id.ref)) {
idr_remove(&mem_cgroup_idr, memcg->id.id);
memcg->id.id = 0;
@@ -4085,6 +4093,16 @@ static void mem_cgroup_id_put(struct mem_cgroup *memcg)
}
}
+static inline void mem_cgroup_id_get(struct mem_cgroup *memcg)
+{
+ mem_cgroup_id_get_many(memcg, 1);
+}
+
+static inline void mem_cgroup_id_put(struct mem_cgroup *memcg)
+{
+ mem_cgroup_id_put_many(memcg, 1);
+}
+
/**
* mem_cgroup_from_id - look up a memcg from a memcg id
* @id: the memcg id to look up
@@ -4719,6 +4737,8 @@ static void __mem_cgroup_clear_mc(void)
if (!mem_cgroup_is_root(mc.from))
page_counter_uncharge(&mc.from->memsw, mc.moved_swap);
+ mem_cgroup_id_put_many(mc.from, mc.moved_swap);
+
/*
* we charged both to->memory and to->memsw, so we
* should uncharge to->memory.
@@ -4726,9 +4746,9 @@ static void __mem_cgroup_clear_mc(void)
if (!mem_cgroup_is_root(mc.to))
page_counter_uncharge(&mc.to->memory, mc.moved_swap);
- css_put_many(&mc.from->css, mc.moved_swap);
+ mem_cgroup_id_get_many(mc.to, mc.moved_swap);
+ css_put_many(&mc.to->css, mc.moved_swap);
- /* we've already done css_get(mc.to) */
mc.moved_swap = 0;
}
memcg_oom_recover(from);
@@ -5537,8 +5557,10 @@ static void uncharge_list(struct list_head *page_list)
else
nr_file += nr_pages;
pgpgout++;
- } else
+ } else {
nr_kmem += 1 << compound_order(page);
+ __ClearPageKmemcg(page);
+ }
page->mem_cgroup = NULL;
} while (next != page_list);
@@ -5781,6 +5803,24 @@ static int __init mem_cgroup_init(void)
subsys_initcall(mem_cgroup_init);
#ifdef CONFIG_MEMCG_SWAP
+static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg)
+{
+ while (!atomic_inc_not_zero(&memcg->id.ref)) {
+ /*
+ * The root cgroup cannot be destroyed, so it's refcount must
+ * always be >= 1.
+ */
+ if (WARN_ON_ONCE(memcg == root_mem_cgroup)) {
+ VM_BUG_ON(1);
+ break;
+ }
+ memcg = parent_mem_cgroup(memcg);
+ if (!memcg)
+ memcg = root_mem_cgroup;
+ }
+ return memcg;
+}
+
/**
* mem_cgroup_swapout - transfer a memsw charge to swap
* @page: page whose memsw charge to transfer
@@ -5790,7 +5830,7 @@ subsys_initcall(mem_cgroup_init);
*/
void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
{
- struct mem_cgroup *memcg;
+ struct mem_cgroup *memcg, *swap_memcg;
unsigned short oldid;
VM_BUG_ON_PAGE(PageLRU(page), page);
@@ -5805,16 +5845,27 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
if (!memcg)
return;
- mem_cgroup_id_get(memcg);
- oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg));
+ /*
+ * In case the memcg owning these pages has been offlined and doesn't
+ * have an ID allocated to it anymore, charge the closest online
+ * ancestor for the swap instead and transfer the memory+swap charge.
+ */
+ swap_memcg = mem_cgroup_id_get_online(memcg);
+ oldid = swap_cgroup_record(entry, mem_cgroup_id(swap_memcg));
VM_BUG_ON_PAGE(oldid, page);
- mem_cgroup_swap_statistics(memcg, true);
+ mem_cgroup_swap_statistics(swap_memcg, true);
page->mem_cgroup = NULL;
if (!mem_cgroup_is_root(memcg))
page_counter_uncharge(&memcg->memory, 1);
+ if (memcg != swap_memcg) {
+ if (!mem_cgroup_is_root(swap_memcg))
+ page_counter_charge(&swap_memcg->memsw, 1);
+ page_counter_uncharge(&memcg->memsw, 1);
+ }
+
/*
* Interrupts should be disabled here because the caller holds the
* mapping->tree_lock lock which is taken with interrupts-off. It is
@@ -5853,11 +5904,14 @@ int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
if (!memcg)
return 0;
+ memcg = mem_cgroup_id_get_online(memcg);
+
if (!mem_cgroup_is_root(memcg) &&
- !page_counter_try_charge(&memcg->swap, 1, &counter))
+ !page_counter_try_charge(&memcg->swap, 1, &counter)) {
+ mem_cgroup_id_put(memcg);
return -ENOMEM;
+ }
- mem_cgroup_id_get(memcg);
oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg));
VM_BUG_ON_PAGE(oldid, page);
mem_cgroup_swap_statistics(memcg, true);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 3894b65b1555..41266dc29f33 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1219,6 +1219,7 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
/* init node's zones as empty zones, we don't have any present pages.*/
free_area_init_node(nid, zones_size, start_pfn, zholes_size);
+ pgdat->per_cpu_nodestats = alloc_percpu(struct per_cpu_nodestat);
/*
* The node we allocated has no zone fallback lists. For avoiding
@@ -1249,6 +1250,7 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
static void rollback_node_hotadd(int nid, pg_data_t *pgdat)
{
arch_refresh_nodedata(nid, NULL);
+ free_percpu(pgdat->per_cpu_nodestats);
arch_free_nodedata(pgdat);
return;
}
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index d8c4e38fb5f4..2da72a5b6ecc 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2336,6 +2336,23 @@ out:
return ret;
}
+/*
+ * Drop the (possibly final) reference to task->mempolicy. It needs to be
+ * dropped after task->mempolicy is set to NULL so that any allocation done as
+ * part of its kmem_cache_free(), such as by KASAN, doesn't reference a freed
+ * policy.
+ */
+void mpol_put_task_policy(struct task_struct *task)
+{
+ struct mempolicy *pol;
+
+ task_lock(task);
+ pol = task->mempolicy;
+ task->mempolicy = NULL;
+ task_unlock(task);
+ mpol_put(pol);
+}
+
static void sp_delete(struct shared_policy *sp, struct sp_node *n)
{
pr_debug("deleting %lx-l%lx\n", n->start, n->end);
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 7d0a275df822..d53a9aa00977 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -764,7 +764,7 @@ bool task_will_free_mem(struct task_struct *task)
{
struct mm_struct *mm = task->mm;
struct task_struct *p;
- bool ret;
+ bool ret = true;
/*
* Skip tasks without mm because it might have passed its exit_mm and
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index fb975cec3518..a2214c64ed3c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1008,10 +1008,8 @@ static __always_inline bool free_pages_prepare(struct page *page,
}
if (PageMappingFlags(page))
page->mapping = NULL;
- if (memcg_kmem_enabled() && PageKmemcg(page)) {
+ if (memcg_kmem_enabled() && PageKmemcg(page))
memcg_kmem_uncharge(page, order);
- __ClearPageKmemcg(page);
- }
if (check_free)
bad += free_pages_check(page);
if (bad)
@@ -3139,54 +3137,6 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
return NULL;
}
-static inline bool
-should_compact_retry(struct alloc_context *ac, int order, int alloc_flags,
- enum compact_result compact_result,
- enum compact_priority *compact_priority,
- int compaction_retries)
-{
- int max_retries = MAX_COMPACT_RETRIES;
-
- if (!order)
- return false;
-
- /*
- * compaction considers all the zone as desperately out of memory
- * so it doesn't really make much sense to retry except when the
- * failure could be caused by insufficient priority
- */
- if (compaction_failed(compact_result)) {
- if (*compact_priority > MIN_COMPACT_PRIORITY) {
- (*compact_priority)--;
- return true;
- }
- return false;
- }
-
- /*
- * make sure the compaction wasn't deferred or didn't bail out early
- * due to locks contention before we declare that we should give up.
- * But do not retry if the given zonelist is not suitable for
- * compaction.
- */
- if (compaction_withdrawn(compact_result))
- return compaction_zonelist_suitable(ac, order, alloc_flags);
-
- /*
- * !costly requests are much more important than __GFP_REPEAT
- * costly ones because they are de facto nofail and invoke OOM
- * killer to move on while costly can fail and users are ready
- * to cope with that. 1/4 retries is rather arbitrary but we
- * would need much more detailed feedback from compaction to
- * make a better decision.
- */
- if (order > PAGE_ALLOC_COSTLY_ORDER)
- max_retries /= 4;
- if (compaction_retries <= max_retries)
- return true;
-
- return false;
-}
#else
static inline struct page *
__alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
@@ -3197,6 +3147,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
return NULL;
}
+#endif /* CONFIG_COMPACTION */
+
static inline bool
should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_flags,
enum compact_result compact_result,
@@ -3223,7 +3175,6 @@ should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_fla
}
return false;
}
-#endif /* CONFIG_COMPACTION */
/* Perform direct synchronous page reclaim */
static int
@@ -3756,12 +3707,10 @@ no_zone:
}
out:
- if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) && page) {
- if (unlikely(memcg_kmem_charge(page, gfp_mask, order))) {
- __free_pages(page, order);
- page = NULL;
- } else
- __SetPageKmemcg(page);
+ if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) && page &&
+ unlikely(memcg_kmem_charge(page, gfp_mask, order) != 0)) {
+ __free_pages(page, order);
+ page = NULL;
}
if (kmemcheck_enabled && page)
@@ -4064,7 +4013,7 @@ long si_mem_available(void)
int lru;
for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
- pages[lru] = global_page_state(NR_LRU_BASE + lru);
+ pages[lru] = global_node_page_state(NR_LRU_BASE + lru);
for_each_zone(zone)
wmark_low += zone->watermark[WMARK_LOW];
@@ -4411,7 +4360,7 @@ static int build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist,
do {
zone_type--;
zone = pgdat->node_zones + zone_type;
- if (populated_zone(zone)) {
+ if (managed_zone(zone)) {
zoneref_set_zone(zone,
&zonelist->_zonerefs[nr_zones++]);
check_highest_zone(zone_type);
@@ -4649,7 +4598,7 @@ static void build_zonelists_in_zone_order(pg_data_t *pgdat, int nr_nodes)
for (j = 0; j < nr_nodes; j++) {
node = node_order[j];
z = &NODE_DATA(node)->node_zones[zone_type];
- if (populated_zone(z)) {
+ if (managed_zone(z)) {
zoneref_set_zone(z,
&zonelist->_zonerefs[pos++]);
check_highest_zone(zone_type);
@@ -4761,6 +4710,8 @@ int local_memory_node(int node)
}
#endif
+static void setup_min_unmapped_ratio(void);
+static void setup_min_slab_ratio(void);
#else /* CONFIG_NUMA */
static void set_zonelist_order(void)
@@ -5882,9 +5833,6 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
zone->managed_pages = is_highmem_idx(j) ? realsize : freesize;
#ifdef CONFIG_NUMA
zone->node = nid;
- pgdat->min_unmapped_pages += (freesize*sysctl_min_unmapped_ratio)
- / 100;
- pgdat->min_slab_pages += (freesize * sysctl_min_slab_ratio) / 100;
#endif
zone->name = zone_names[j];
zone->zone_pgdat = pgdat;
@@ -6805,6 +6753,12 @@ int __meminit init_per_zone_wmark_min(void)
setup_per_zone_wmarks();
refresh_zone_stat_thresholds();
setup_per_zone_lowmem_reserve();
+
+#ifdef CONFIG_NUMA
+ setup_min_unmapped_ratio();
+ setup_min_slab_ratio();
+#endif
+
return 0;
}
core_initcall(init_per_zone_wmark_min)
@@ -6846,43 +6800,58 @@ int watermark_scale_factor_sysctl_handler(struct ctl_table *table, int write,
}
#ifdef CONFIG_NUMA
+static void setup_min_unmapped_ratio(void)
+{
+ pg_data_t *pgdat;
+ struct zone *zone;
+
+ for_each_online_pgdat(pgdat)
+ pgdat->min_unmapped_pages = 0;
+
+ for_each_zone(zone)
+ zone->zone_pgdat->min_unmapped_pages += (zone->managed_pages *
+ sysctl_min_unmapped_ratio) / 100;
+}
+
+
int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
{
- struct pglist_data *pgdat;
- struct zone *zone;
int rc;
rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
if (rc)
return rc;
+ setup_min_unmapped_ratio();
+
+ return 0;
+}
+
+static void setup_min_slab_ratio(void)
+{
+ pg_data_t *pgdat;
+ struct zone *zone;
+
for_each_online_pgdat(pgdat)
pgdat->min_slab_pages = 0;
for_each_zone(zone)
- zone->zone_pgdat->min_unmapped_pages += (zone->managed_pages *
- sysctl_min_unmapped_ratio) / 100;
- return 0;
+ zone->zone_pgdat->min_slab_pages += (zone->managed_pages *
+ sysctl_min_slab_ratio) / 100;
}
int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
{
- struct pglist_data *pgdat;
- struct zone *zone;
int rc;
rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
if (rc)
return rc;
- for_each_online_pgdat(pgdat)
- pgdat->min_slab_pages = 0;
+ setup_min_slab_ratio();
- for_each_zone(zone)
- zone->zone_pgdat->min_slab_pages += (zone->managed_pages *
- sysctl_min_slab_ratio) / 100;
return 0;
}
#endif
diff --git a/mm/readahead.c b/mm/readahead.c
index 65ec288dc057..c8a955b1297e 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -8,6 +8,7 @@
*/
#include <linux/kernel.h>
+#include <linux/dax.h>
#include <linux/gfp.h>
#include <linux/export.h>
#include <linux/blkdev.h>
@@ -544,6 +545,14 @@ do_readahead(struct address_space *mapping, struct file *filp,
if (!mapping || !mapping->a_ops)
return -EINVAL;
+ /*
+ * Readahead doesn't make sense for DAX inodes, but we don't want it
+ * to report a failure either. Instead, we just return success and
+ * don't do any work.
+ */
+ if (dax_mapping(mapping))
+ return 0;
+
return force_page_cache_readahead(mapping, filp, index, nr);
}
diff --git a/mm/rmap.c b/mm/rmap.c
index 709bc83703b1..1ef36404e7b2 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1284,8 +1284,9 @@ void page_add_file_rmap(struct page *page, bool compound)
VM_BUG_ON_PAGE(!PageSwapBacked(page), page);
__inc_node_page_state(page, NR_SHMEM_PMDMAPPED);
} else {
- if (PageTransCompound(page)) {
- VM_BUG_ON_PAGE(!PageLocked(page), page);
+ if (PageTransCompound(page) && page_mapping(page)) {
+ VM_WARN_ON_ONCE(!PageLocked(page));
+
SetPageDoubleMap(compound_head(page));
if (PageMlocked(page))
clear_page_mlock(compound_head(page));
@@ -1303,7 +1304,7 @@ static void page_remove_file_rmap(struct page *page, bool compound)
{
int i, nr = 1;
- VM_BUG_ON_PAGE(compound && !PageTransHuge(page), page);
+ VM_BUG_ON_PAGE(compound && !PageHead(page), page);
lock_page_memcg(page);
/* Hugepages are not counted in NR_FILE_MAPPED for now. */
diff --git a/mm/shmem.c b/mm/shmem.c
index 7f7748a0f9e1..fd8b2b5741b1 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3975,7 +3975,9 @@ static ssize_t shmem_enabled_store(struct kobject *kobj,
struct kobj_attribute shmem_enabled_attr =
__ATTR(shmem_enabled, 0644, shmem_enabled_show, shmem_enabled_store);
+#endif /* CONFIG_TRANSPARENT_HUGE_PAGECACHE && CONFIG_SYSFS */
+#ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE
bool shmem_huge_enabled(struct vm_area_struct *vma)
{
struct inode *inode = file_inode(vma->vm_file);
@@ -4006,7 +4008,7 @@ bool shmem_huge_enabled(struct vm_area_struct *vma)
return false;
}
}
-#endif /* CONFIG_TRANSPARENT_HUGE_PAGECACHE && CONFIG_SYSFS */
+#endif /* CONFIG_TRANSPARENT_HUGE_PAGECACHE */
#else /* !CONFIG_SHMEM */
diff --git a/mm/slab.c b/mm/slab.c
index 261147ba156f..b67271024135 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -4441,6 +4441,36 @@ static int __init slab_proc_init(void)
module_init(slab_proc_init);
#endif
+#ifdef CONFIG_HARDENED_USERCOPY
+/*
+ * Rejects objects that are incorrectly sized.
+ *
+ * Returns NULL if check passes, otherwise const char * to name of cache
+ * to indicate an error.
+ */
+const char *__check_heap_object(const void *ptr, unsigned long n,
+ struct page *page)
+{
+ struct kmem_cache *cachep;
+ unsigned int objnr;
+ unsigned long offset;
+
+ /* Find and validate object. */
+ cachep = page->slab_cache;
+ objnr = obj_to_index(cachep, page, (void *)ptr);
+ BUG_ON(objnr >= cachep->num);
+
+ /* Find offset within object. */
+ offset = ptr - index_to_obj(cachep, page, objnr) - obj_offset(cachep);
+
+ /* Allow address range falling entirely within object size. */
+ if (offset <= cachep->object_size && n <= cachep->object_size - offset)
+ return NULL;
+
+ return cachep->name;
+}
+#endif /* CONFIG_HARDENED_USERCOPY */
+
/**
* ksize - get the actual amount of memory allocated for a given object
* @objp: Pointer to the object
diff --git a/mm/slub.c b/mm/slub.c
index 850737bdfbd8..9adae58462f8 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3629,6 +3629,7 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page,
*/
static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n)
{
+ LIST_HEAD(discard);
struct page *page, *h;
BUG_ON(irqs_disabled());
@@ -3636,13 +3637,16 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n)
list_for_each_entry_safe(page, h, &n->partial, lru) {
if (!page->inuse) {
remove_partial(n, page);
- discard_slab(s, page);
+ list_add(&page->lru, &discard);
} else {
list_slab_objects(s, page,
"Objects remaining in %s on __kmem_cache_shutdown()");
}
}
spin_unlock_irq(&n->list_lock);
+
+ list_for_each_entry_safe(page, h, &discard, lru)
+ discard_slab(s, page);
}
/*
@@ -3764,6 +3768,46 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node)
EXPORT_SYMBOL(__kmalloc_node);
#endif
+#ifdef CONFIG_HARDENED_USERCOPY
+/*
+ * Rejects objects that are incorrectly sized.
+ *
+ * Returns NULL if check passes, otherwise const char * to name of cache
+ * to indicate an error.
+ */
+const char *__check_heap_object(const void *ptr, unsigned long n,
+ struct page *page)
+{
+ struct kmem_cache *s;
+ unsigned long offset;
+ size_t object_size;
+
+ /* Find object and usable object size. */
+ s = page->slab_cache;
+ object_size = slab_ksize(s);
+
+ /* Reject impossible pointers. */
+ if (ptr < page_address(page))
+ return s->name;
+
+ /* Find offset within object. */
+ offset = (ptr - page_address(page)) % s->size;
+
+ /* Adjust for redzone and reject if within the redzone. */
+ if (kmem_cache_debug(s) && s->flags & SLAB_RED_ZONE) {
+ if (offset < s->red_left_pad)
+ return s->name;
+ offset -= s->red_left_pad;
+ }
+
+ /* Allow address range falling entirely within object size. */
+ if (offset <= object_size && n <= object_size - offset)
+ return NULL;
+
+ return s->name;
+}
+#endif /* CONFIG_HARDENED_USERCOPY */
+
static size_t __ksize(const void *object)
{
struct page *page;
diff --git a/mm/usercopy.c b/mm/usercopy.c
new file mode 100644
index 000000000000..089328f2b920
--- /dev/null
+++ b/mm/usercopy.c
@@ -0,0 +1,277 @@
+/*
+ * This implements the various checks for CONFIG_HARDENED_USERCOPY*,
+ * which are designed to protect kernel memory from needless exposure
+ * and overwrite under many unintended conditions. This code is based
+ * on PAX_USERCOPY, which is:
+ *
+ * Copyright (C) 2001-2016 PaX Team, Bradley Spengler, Open Source
+ * Security Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <asm/sections.h>
+
+enum {
+ BAD_STACK = -1,
+ NOT_STACK = 0,
+ GOOD_FRAME,
+ GOOD_STACK,
+};
+
+/*
+ * Checks if a given pointer and length is contained by the current
+ * stack frame (if possible).
+ *
+ * Returns:
+ * NOT_STACK: not at all on the stack
+ * GOOD_FRAME: fully within a valid stack frame
+ * GOOD_STACK: fully on the stack (when can't do frame-checking)
+ * BAD_STACK: error condition (invalid stack position or bad stack frame)
+ */
+static noinline int check_stack_object(const void *obj, unsigned long len)
+{
+ const void * const stack = task_stack_page(current);
+ const void * const stackend = stack + THREAD_SIZE;
+ int ret;
+
+ /* Object is not on the stack at all. */
+ if (obj + len <= stack || stackend <= obj)
+ return NOT_STACK;
+
+ /*
+ * Reject: object partially overlaps the stack (passing the
+ * the check above means at least one end is within the stack,
+ * so if this check fails, the other end is outside the stack).
+ */
+ if (obj < stack || stackend < obj + len)
+ return BAD_STACK;
+
+ /* Check if object is safely within a valid frame. */
+ ret = arch_within_stack_frames(stack, stackend, obj, len);
+ if (ret)
+ return ret;
+
+ return GOOD_STACK;
+}
+
+static void report_usercopy(const void *ptr, unsigned long len,
+ bool to_user, const char *type)
+{
+ pr_emerg("kernel memory %s attempt detected %s %p (%s) (%lu bytes)\n",
+ to_user ? "exposure" : "overwrite",
+ to_user ? "from" : "to", ptr, type ? : "unknown", len);
+ /*
+ * For greater effect, it would be nice to do do_group_exit(),
+ * but BUG() actually hooks all the lock-breaking and per-arch
+ * Oops code, so that is used here instead.
+ */
+ BUG();
+}
+
+/* Returns true if any portion of [ptr,ptr+n) over laps with [low,high). */
+static bool overlaps(const void *ptr, unsigned long n, unsigned long low,
+ unsigned long high)
+{
+ unsigned long check_low = (uintptr_t)ptr;
+ unsigned long check_high = check_low + n;
+
+ /* Does not overlap if entirely above or entirely below. */
+ if (check_low >= high || check_high <= low)
+ return false;
+
+ return true;
+}
+
+/* Is this address range in the kernel text area? */
+static inline const char *check_kernel_text_object(const void *ptr,
+ unsigned long n)
+{
+ unsigned long textlow = (unsigned long)_stext;
+ unsigned long texthigh = (unsigned long)_etext;
+ unsigned long textlow_linear, texthigh_linear;
+
+ if (overlaps(ptr, n, textlow, texthigh))
+ return "<kernel text>";
+
+ /*
+ * Some architectures have virtual memory mappings with a secondary
+ * mapping of the kernel text, i.e. there is more than one virtual
+ * kernel address that points to the kernel image. It is usually
+ * when there is a separate linear physical memory mapping, in that
+ * __pa() is not just the reverse of __va(). This can be detected
+ * and checked:
+ */
+ textlow_linear = (unsigned long)__va(__pa(textlow));
+ /* No different mapping: we're done. */
+ if (textlow_linear == textlow)
+ return NULL;
+
+ /* Check the secondary mapping... */
+ texthigh_linear = (unsigned long)__va(__pa(texthigh));
+ if (overlaps(ptr, n, textlow_linear, texthigh_linear))
+ return "<linear kernel text>";
+
+ return NULL;
+}
+
+static inline const char *check_bogus_address(const void *ptr, unsigned long n)
+{
+ /* Reject if object wraps past end of memory. */
+ if ((unsigned long)ptr + n < (unsigned long)ptr)
+ return "<wrapped address>";
+
+ /* Reject if NULL or ZERO-allocation. */
+ if (ZERO_OR_NULL_PTR(ptr))
+ return "<null>";
+
+ return NULL;
+}
+
+/* Checks for allocs that are marked in some way as spanning multiple pages. */
+static inline const char *check_page_span(const void *ptr, unsigned long n,
+ struct page *page, bool to_user)
+{
+#ifdef CONFIG_HARDENED_USERCOPY_PAGESPAN
+ const void *end = ptr + n - 1;
+ struct page *endpage;
+ bool is_reserved, is_cma;
+
+ /*
+ * Sometimes the kernel data regions are not marked Reserved (see
+ * check below). And sometimes [_sdata,_edata) does not cover
+ * rodata and/or bss, so check each range explicitly.
+ */
+
+ /* Allow reads of kernel rodata region (if not marked as Reserved). */
+ if (ptr >= (const void *)__start_rodata &&
+ end <= (const void *)__end_rodata) {
+ if (!to_user)
+ return "<rodata>";
+ return NULL;
+ }
+
+ /* Allow kernel data region (if not marked as Reserved). */
+ if (ptr >= (const void *)_sdata && end <= (const void *)_edata)
+ return NULL;
+
+ /* Allow kernel bss region (if not marked as Reserved). */
+ if (ptr >= (const void *)__bss_start &&
+ end <= (const void *)__bss_stop)
+ return NULL;
+
+ /* Is the object wholly within one base page? */
+ if (likely(((unsigned long)ptr & (unsigned long)PAGE_MASK) ==
+ ((unsigned long)end & (unsigned long)PAGE_MASK)))
+ return NULL;
+
+ /* Allow if fully inside the same compound (__GFP_COMP) page. */
+ endpage = virt_to_head_page(end);
+ if (likely(endpage == page))
+ return NULL;
+
+ /*
+ * Reject if range is entirely either Reserved (i.e. special or
+ * device memory), or CMA. Otherwise, reject since the object spans
+ * several independently allocated pages.
+ */
+ is_reserved = PageReserved(page);
+ is_cma = is_migrate_cma_page(page);
+ if (!is_reserved && !is_cma)
+ return "<spans multiple pages>";
+
+ for (ptr += PAGE_SIZE; ptr <= end; ptr += PAGE_SIZE) {
+ page = virt_to_head_page(ptr);
+ if (is_reserved && !PageReserved(page))
+ return "<spans Reserved and non-Reserved pages>";
+ if (is_cma && !is_migrate_cma_page(page))
+ return "<spans CMA and non-CMA pages>";
+ }
+#endif
+
+ return NULL;
+}
+
+static inline const char *check_heap_object(const void *ptr, unsigned long n,
+ bool to_user)
+{
+ struct page *page;
+
+ /*
+ * Some architectures (arm64) return true for virt_addr_valid() on
+ * vmalloced addresses. Work around this by checking for vmalloc
+ * first.
+ */
+ if (is_vmalloc_addr(ptr))
+ return NULL;
+
+ if (!virt_addr_valid(ptr))
+ return NULL;
+
+ page = virt_to_head_page(ptr);
+
+ /* Check slab allocator for flags and size. */
+ if (PageSlab(page))
+ return __check_heap_object(ptr, n, page);
+
+ /* Verify object does not incorrectly span multiple pages. */
+ return check_page_span(ptr, n, page, to_user);
+}
+
+/*
+ * Validates that the given object is:
+ * - not bogus address
+ * - known-safe heap or stack object
+ * - not in kernel text
+ */
+void __check_object_size(const void *ptr, unsigned long n, bool to_user)
+{
+ const char *err;
+
+ /* Skip all tests if size is zero. */
+ if (!n)
+ return;
+
+ /* Check for invalid addresses. */
+ err = check_bogus_address(ptr, n);
+ if (err)
+ goto report;
+
+ /* Check for bad heap object. */
+ err = check_heap_object(ptr, n, to_user);
+ if (err)
+ goto report;
+
+ /* Check for bad stack object. */
+ switch (check_stack_object(ptr, n)) {
+ case NOT_STACK:
+ /* Object is not touching the current process stack. */
+ break;
+ case GOOD_FRAME:
+ case GOOD_STACK:
+ /*
+ * Object is either in the correct frame (when it
+ * is possible to check) or just generally on the
+ * process stack (when frame checking not available).
+ */
+ return;
+ default:
+ err = "<process stack>";
+ goto report;
+ }
+
+ /* Check for object in kernel to avoid text exposure. */
+ err = check_kernel_text_object(ptr, n);
+ if (!err)
+ return;
+
+report:
+ report_usercopy(ptr, n, to_user, err);
+}
+EXPORT_SYMBOL(__check_object_size);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 374d95d04178..b1e12a1ea9cf 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1665,7 +1665,7 @@ static bool inactive_reclaimable_pages(struct lruvec *lruvec,
for (zid = sc->reclaim_idx; zid >= 0; zid--) {
zone = &pgdat->node_zones[zid];
- if (!populated_zone(zone))
+ if (!managed_zone(zone))
continue;
if (zone_page_state_snapshot(zone, NR_ZONE_LRU_BASE +
@@ -2036,7 +2036,7 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
struct zone *zone = &pgdat->node_zones[zid];
unsigned long inactive_zone, active_zone;
- if (!populated_zone(zone))
+ if (!managed_zone(zone))
continue;
inactive_zone = zone_page_state(zone,
@@ -2171,7 +2171,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
for (z = 0; z < MAX_NR_ZONES; z++) {
struct zone *zone = &pgdat->node_zones[z];
- if (!populated_zone(zone))
+ if (!managed_zone(zone))
continue;
total_high_wmark += high_wmark_pages(zone);
@@ -2510,7 +2510,7 @@ static inline bool should_continue_reclaim(struct pglist_data *pgdat,
/* If compaction would go ahead or the allocation would succeed, stop */
for (z = 0; z <= sc->reclaim_idx; z++) {
struct zone *zone = &pgdat->node_zones[z];
- if (!populated_zone(zone))
+ if (!managed_zone(zone))
continue;
switch (compaction_suitable(zone, sc->order, 0, sc->reclaim_idx)) {
@@ -2840,7 +2840,7 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
for (i = 0; i <= ZONE_NORMAL; i++) {
zone = &pgdat->node_zones[i];
- if (!populated_zone(zone) ||
+ if (!managed_zone(zone) ||
pgdat_reclaimable_pages(pgdat) == 0)
continue;
@@ -3141,7 +3141,7 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int classzone_idx)
for (i = 0; i <= classzone_idx; i++) {
struct zone *zone = pgdat->node_zones + i;
- if (!populated_zone(zone))
+ if (!managed_zone(zone))
continue;
if (!zone_balanced(zone, order, classzone_idx))
@@ -3169,7 +3169,7 @@ static bool kswapd_shrink_node(pg_data_t *pgdat,
sc->nr_to_reclaim = 0;
for (z = 0; z <= sc->reclaim_idx; z++) {
zone = pgdat->node_zones + z;
- if (!populated_zone(zone))
+ if (!managed_zone(zone))
continue;
sc->nr_to_reclaim += max(high_wmark_pages(zone), SWAP_CLUSTER_MAX);
@@ -3242,7 +3242,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
if (buffer_heads_over_limit) {
for (i = MAX_NR_ZONES - 1; i >= 0; i--) {
zone = pgdat->node_zones + i;
- if (!populated_zone(zone))
+ if (!managed_zone(zone))
continue;
sc.reclaim_idx = i;
@@ -3262,7 +3262,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
*/
for (i = classzone_idx; i >= 0; i--) {
zone = pgdat->node_zones + i;
- if (!populated_zone(zone))
+ if (!managed_zone(zone))
continue;
if (zone_balanced(zone, sc.order, classzone_idx))
@@ -3508,7 +3508,7 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
pg_data_t *pgdat;
int z;
- if (!populated_zone(zone))
+ if (!managed_zone(zone))
return;
if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL))
@@ -3522,7 +3522,7 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
/* Only wake kswapd if all zones are unbalanced */
for (z = 0; z <= classzone_idx; z++) {
zone = pgdat->node_zones + z;
- if (!populated_zone(zone))
+ if (!managed_zone(zone))
continue;
if (zone_balanced(zone, order, classzone_idx))
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.