summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
Diffstat (limited to 'include')
-rw-r--r--include/drm/ttm/ttm_pool.h2
-rw-r--r--include/linux/buffer_head.h9
-rw-r--r--include/linux/cpuhotplug.h1
-rw-r--r--include/linux/damon.h22
-rw-r--r--include/linux/fs.h2
-rw-r--r--include/linux/gfp_types.h17
-rw-r--r--include/linux/highmem.h76
-rw-r--r--include/linux/huge_mm.h184
-rw-r--r--include/linux/hugetlb.h2
-rw-r--r--include/linux/kasan.h162
-rw-r--r--include/linux/ksm.h10
-rw-r--r--include/linux/list_lru.h88
-rw-r--r--include/linux/maple_tree.h349
-rw-r--r--include/linux/memblock.h1
-rw-r--r--include/linux/memcontrol.h37
-rw-r--r--include/linux/mempool.h1
-rw-r--r--include/linux/memremap.h12
-rw-r--r--include/linux/mm.h50
-rw-r--r--include/linux/mm_types.h27
-rw-r--r--include/linux/mmzone.h66
-rw-r--r--include/linux/page-flags.h9
-rw-r--r--include/linux/pageblock-flags.h4
-rw-r--r--include/linux/pgtable.h9
-rw-r--r--include/linux/rmap.h411
-rw-r--r--include/linux/slab.h2
-rw-r--r--include/linux/stackdepot.h61
-rw-r--r--include/linux/swap.h8
-rw-r--r--include/linux/userfaultfd_k.h11
-rw-r--r--include/linux/vm_event_item.h4
-rw-r--r--include/linux/vmstat.h60
-rw-r--r--include/linux/zswap.h32
-rw-r--r--include/trace/events/ksm.h33
-rw-r--r--include/uapi/linux/fs.h1
-rw-r--r--include/uapi/linux/userfaultfd.h29
34 files changed, 1317 insertions, 475 deletions
diff --git a/include/drm/ttm/ttm_pool.h b/include/drm/ttm/ttm_pool.h
index 30a347e5aa11..4490d43c63e3 100644
--- a/include/drm/ttm/ttm_pool.h
+++ b/include/drm/ttm/ttm_pool.h
@@ -74,7 +74,7 @@ struct ttm_pool {
bool use_dma32;
struct {
- struct ttm_pool_type orders[MAX_ORDER + 1];
+ struct ttm_pool_type orders[NR_PAGE_ORDERS];
} caching[TTM_NUM_CACHING_TYPES];
};
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 5f23ee599889..d78454a4dd1f 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -205,7 +205,6 @@ struct buffer_head *create_empty_buffers(struct folio *folio,
unsigned long blocksize, unsigned long b_state);
void end_buffer_read_sync(struct buffer_head *bh, int uptodate);
void end_buffer_write_sync(struct buffer_head *bh, int uptodate);
-void end_buffer_async_write(struct buffer_head *bh, int uptodate);
/* Things to do with buffers at mapping->private_list */
void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode);
@@ -252,11 +251,10 @@ void __bh_read_batch(int nr, struct buffer_head *bhs[],
* address_spaces.
*/
void block_invalidate_folio(struct folio *folio, size_t offset, size_t length);
-int block_write_full_page(struct page *page, get_block_t *get_block,
- struct writeback_control *wbc);
+int block_write_full_folio(struct folio *folio, struct writeback_control *wbc,
+ void *get_block);
int __block_write_full_folio(struct inode *inode, struct folio *folio,
- get_block_t *get_block, struct writeback_control *wbc,
- bh_end_io_t *handler);
+ get_block_t *get_block, struct writeback_control *wbc);
int block_read_full_folio(struct folio *, get_block_t *);
bool block_is_partially_uptodate(struct folio *, size_t from, size_t count);
int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
@@ -270,7 +268,6 @@ int generic_write_end(struct file *, struct address_space *,
loff_t, unsigned, unsigned,
struct page *, void *);
void folio_zero_new_buffers(struct folio *folio, size_t from, size_t to);
-void clean_page_buffers(struct page *page);
int cont_write_begin(struct file *, struct address_space *, loff_t,
unsigned, struct page **, void **,
get_block_t *, loff_t *);
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 4f628d6a69d6..172d0a743e5d 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -118,7 +118,6 @@ enum cpuhp_state {
CPUHP_ARM_BL_PREPARE,
CPUHP_TRACE_RB_PREPARE,
CPUHP_MM_ZS_PREPARE,
- CPUHP_MM_ZSWP_MEM_PREPARE,
CPUHP_MM_ZSWP_POOL_PREPARE,
CPUHP_KVM_PPC_BOOK3S_PREPARE,
CPUHP_ZCOMP_PREPARE,
diff --git a/include/linux/damon.h b/include/linux/damon.h
index e00ddf1ed39c..5881e4ac30be 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -2,7 +2,7 @@
/*
* DAMON api
*
- * Author: SeongJae Park <sjpark@amazon.de>
+ * Author: SeongJae Park <sj@kernel.org>
*/
#ifndef _DAMON_H_
@@ -136,6 +136,9 @@ enum damos_action {
* @weight_nr_accesses: Weight of the region's nr_accesses for prioritization.
* @weight_age: Weight of the region's age for prioritization.
*
+ * @get_score: Feedback function for self-tuning quota.
+ * @get_score_arg: Parameter for @get_score
+ *
* To avoid consuming too much CPU time or IO resources for applying the
* &struct damos->action to large memory, DAMON allows users to set time and/or
* size quotas. The quotas can be set by writing non-zero values to &ms and
@@ -153,6 +156,17 @@ enum damos_action {
* You could customize the prioritization logic by setting &weight_sz,
* &weight_nr_accesses, and &weight_age, because monitoring operations are
* encouraged to respect those.
+ *
+ * If @get_score function pointer is set, DAMON calls it back with
+ * @get_score_arg and get the return value of it for every @reset_interval.
+ * Then, DAMON adjusts the effective quota using the return value as a feedback
+ * score to the current quota, using its internal feedback loop algorithm.
+ *
+ * The feedback loop algorithem assumes the quota input and the feedback score
+ * output are in a positive proportional relationship, and the goal of the
+ * tuning is getting the feedback screo value of 10,000. If @ms and/or @sz are
+ * set together, those work as a hard limit quota. If neither @ms nor @sz are
+ * set, the mechanism starts from the quota of one byte.
*/
struct damos_quota {
unsigned long ms;
@@ -163,6 +177,9 @@ struct damos_quota {
unsigned int weight_nr_accesses;
unsigned int weight_age;
+ unsigned long (*get_score)(void *arg);
+ void *get_score_arg;
+
/* private: */
/* For throughput estimation */
unsigned long total_charged_sz;
@@ -179,6 +196,9 @@ struct damos_quota {
/* For prioritization */
unsigned long histogram[DAMOS_MAX_SCORE + 1];
unsigned int min_score;
+
+ /* For feedback loop */
+ unsigned long esz_bp;
};
/**
diff --git a/include/linux/fs.h b/include/linux/fs.h
index cdbf43a8ea88..9314e8541745 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -434,7 +434,7 @@ struct address_space_operations {
bool (*is_partially_uptodate) (struct folio *, size_t from,
size_t count);
void (*is_dirty_writeback) (struct folio *, bool *dirty, bool *wb);
- int (*error_remove_page)(struct address_space *, struct page *);
+ int (*error_remove_folio)(struct address_space *, struct folio *);
/* swapfile support */
int (*swap_activate)(struct swap_info_struct *sis, struct file *file,
diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h
index 6583a58670c5..1b6053da8754 100644
--- a/include/linux/gfp_types.h
+++ b/include/linux/gfp_types.h
@@ -162,25 +162,25 @@ typedef unsigned int __bitwise gfp_t;
* %__GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim.
*
* The default allocator behavior depends on the request size. We have a concept
- * of so called costly allocations (with order > %PAGE_ALLOC_COSTLY_ORDER).
+ * of so-called costly allocations (with order > %PAGE_ALLOC_COSTLY_ORDER).
* !costly allocations are too essential to fail so they are implicitly
* non-failing by default (with some exceptions like OOM victims might fail so
* the caller still has to check for failures) while costly requests try to be
* not disruptive and back off even without invoking the OOM killer.
* The following three modifiers might be used to override some of these
- * implicit rules
+ * implicit rules.
*
* %__GFP_NORETRY: The VM implementation will try only very lightweight
* memory direct reclaim to get some memory under memory pressure (thus
* it can sleep). It will avoid disruptive actions like OOM killer. The
* caller must handle the failure which is quite likely to happen under
* heavy memory pressure. The flag is suitable when failure can easily be
- * handled at small cost, such as reduced throughput
+ * handled at small cost, such as reduced throughput.
*
* %__GFP_RETRY_MAYFAIL: The VM implementation will retry memory reclaim
* procedures that have previously failed if there is some indication
- * that progress has been made else where. It can wait for other
- * tasks to attempt high level approaches to freeing memory such as
+ * that progress has been made elsewhere. It can wait for other
+ * tasks to attempt high-level approaches to freeing memory such as
* compaction (which removes fragmentation) and page-out.
* There is still a definite limit to the number of retries, but it is
* a larger limit than with %__GFP_NORETRY.
@@ -230,7 +230,7 @@ typedef unsigned int __bitwise gfp_t;
* is being zeroed (either via __GFP_ZERO or via init_on_alloc, provided that
* __GFP_SKIP_ZERO is not set). This flag is intended for optimization: setting
* memory tags at the same time as zeroing memory has minimal additional
- * performace impact.
+ * performance impact.
*
* %__GFP_SKIP_KASAN makes KASAN skip unpoisoning on page allocation.
* Used for userspace and vmalloc pages; the latter are unpoisoned by
@@ -274,7 +274,8 @@ typedef unsigned int __bitwise gfp_t;
* accounted to kmemcg.
*
* %GFP_NOWAIT is for kernel allocations that should not stall for direct
- * reclaim, start physical IO or use any filesystem callback.
+ * reclaim, start physical IO or use any filesystem callback. It is very
+ * likely to fail to allocate memory, even for very small allocations.
*
* %GFP_NOIO will use direct reclaim to discard clean pages or slab pages
* that do not require the starting of any physical IO.
@@ -325,7 +326,7 @@ typedef unsigned int __bitwise gfp_t;
#define GFP_ATOMIC (__GFP_HIGH|__GFP_KSWAPD_RECLAIM)
#define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS)
#define GFP_KERNEL_ACCOUNT (GFP_KERNEL | __GFP_ACCOUNT)
-#define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM)
+#define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM | __GFP_NOWARN)
#define GFP_NOIO (__GFP_RECLAIM)
#define GFP_NOFS (__GFP_RECLAIM | __GFP_IO)
#define GFP_USER (__GFP_RECLAIM | __GFP_IO | __GFP_FS | __GFP_HARDWALL)
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index be20cff4ba73..451c1dff0e87 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -484,6 +484,82 @@ static inline void memcpy_to_folio(struct folio *folio, size_t offset,
}
/**
+ * folio_zero_tail - Zero the tail of a folio.
+ * @folio: The folio to zero.
+ * @offset: The byte offset in the folio to start zeroing at.
+ * @kaddr: The address the folio is currently mapped to.
+ *
+ * If you have already used kmap_local_folio() to map a folio, written
+ * some data to it and now need to zero the end of the folio (and flush
+ * the dcache), you can use this function. If you do not have the
+ * folio kmapped (eg the folio has been partially populated by DMA),
+ * use folio_zero_range() or folio_zero_segment() instead.
+ *
+ * Return: An address which can be passed to kunmap_local().
+ */
+static inline __must_check void *folio_zero_tail(struct folio *folio,
+ size_t offset, void *kaddr)
+{
+ size_t len = folio_size(folio) - offset;
+
+ if (folio_test_highmem(folio)) {
+ size_t max = PAGE_SIZE - offset_in_page(offset);
+
+ while (len > max) {
+ memset(kaddr, 0, max);
+ kunmap_local(kaddr);
+ len -= max;
+ offset += max;
+ max = PAGE_SIZE;
+ kaddr = kmap_local_folio(folio, offset);
+ }
+ }
+
+ memset(kaddr, 0, len);
+ flush_dcache_folio(folio);
+
+ return kaddr;
+}
+
+/**
+ * folio_fill_tail - Copy some data to a folio and pad with zeroes.
+ * @folio: The destination folio.
+ * @offset: The offset into @folio at which to start copying.
+ * @from: The data to copy.
+ * @len: How many bytes of data to copy.
+ *
+ * This function is most useful for filesystems which support inline data.
+ * When they want to copy data from the inode into the page cache, this
+ * function does everything for them. It supports large folios even on
+ * HIGHMEM configurations.
+ */
+static inline void folio_fill_tail(struct folio *folio, size_t offset,
+ const char *from, size_t len)
+{
+ char *to = kmap_local_folio(folio, offset);
+
+ VM_BUG_ON(offset + len > folio_size(folio));
+
+ if (folio_test_highmem(folio)) {
+ size_t max = PAGE_SIZE - offset_in_page(offset);
+
+ while (len > max) {
+ memcpy(to, from, max);
+ kunmap_local(to);
+ len -= max;
+ from += max;
+ offset += max;
+ max = PAGE_SIZE;
+ to = kmap_local_folio(folio, offset);
+ }
+ }
+
+ memcpy(to, from, len);
+ to = folio_zero_tail(folio, offset + len, to + len);
+ kunmap_local(to);
+}
+
+/**
* memcpy_from_file_folio - Copy some bytes from a file folio.
* @to: The destination buffer.
* @folio: The folio to copy from.
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index fa0350b0812a..5adb86af35fc 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -67,6 +67,26 @@ extern struct kobj_attribute shmem_enabled_attr;
#define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
#define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
+/*
+ * Mask of all large folio orders supported for anonymous THP; all orders up to
+ * and including PMD_ORDER, except order-0 (which is not "huge") and order-1
+ * (which is a limitation of the THP implementation).
+ */
+#define THP_ORDERS_ALL_ANON ((BIT(PMD_ORDER + 1) - 1) & ~(BIT(0) | BIT(1)))
+
+/*
+ * Mask of all large folio orders supported for file THP.
+ */
+#define THP_ORDERS_ALL_FILE (BIT(PMD_ORDER) | BIT(PUD_ORDER))
+
+/*
+ * Mask of all large folio orders supported for THP.
+ */
+#define THP_ORDERS_ALL (THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_FILE)
+
+#define thp_vma_allowable_order(vma, vm_flags, smaps, in_pf, enforce_sysfs, order) \
+ (!!thp_vma_allowable_orders(vma, vm_flags, smaps, in_pf, enforce_sysfs, BIT(order)))
+
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#define HPAGE_PMD_SHIFT PMD_SHIFT
#define HPAGE_PMD_SIZE ((1UL) << HPAGE_PMD_SHIFT)
@@ -77,45 +97,105 @@ extern struct kobj_attribute shmem_enabled_attr;
#define HPAGE_PUD_MASK (~(HPAGE_PUD_SIZE - 1))
extern unsigned long transparent_hugepage_flags;
+extern unsigned long huge_anon_orders_always;
+extern unsigned long huge_anon_orders_madvise;
+extern unsigned long huge_anon_orders_inherit;
-#define hugepage_flags_enabled() \
- (transparent_hugepage_flags & \
- ((1<<TRANSPARENT_HUGEPAGE_FLAG) | \
- (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)))
-#define hugepage_flags_always() \
- (transparent_hugepage_flags & \
- (1<<TRANSPARENT_HUGEPAGE_FLAG))
+static inline bool hugepage_global_enabled(void)
+{
+ return transparent_hugepage_flags &
+ ((1<<TRANSPARENT_HUGEPAGE_FLAG) |
+ (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG));
+}
+
+static inline bool hugepage_global_always(void)
+{
+ return transparent_hugepage_flags &
+ (1<<TRANSPARENT_HUGEPAGE_FLAG);
+}
+
+static inline bool hugepage_flags_enabled(void)
+{
+ /*
+ * We cover both the anon and the file-backed case here; we must return
+ * true if globally enabled, even when all anon sizes are set to never.
+ * So we don't need to look at huge_anon_orders_inherit.
+ */
+ return hugepage_global_enabled() ||
+ huge_anon_orders_always ||
+ huge_anon_orders_madvise;
+}
+
+static inline int highest_order(unsigned long orders)
+{
+ return fls_long(orders) - 1;
+}
+
+static inline int next_order(unsigned long *orders, int prev)
+{
+ *orders &= ~BIT(prev);
+ return highest_order(*orders);
+}
/*
* Do the below checks:
* - For file vma, check if the linear page offset of vma is
- * HPAGE_PMD_NR aligned within the file. The hugepage is
- * guaranteed to be hugepage-aligned within the file, but we must
- * check that the PMD-aligned addresses in the VMA map to
- * PMD-aligned offsets within the file, else the hugepage will
- * not be PMD-mappable.
- * - For all vmas, check if the haddr is in an aligned HPAGE_PMD_SIZE
+ * order-aligned within the file. The hugepage is
+ * guaranteed to be order-aligned within the file, but we must
+ * check that the order-aligned addresses in the VMA map to
+ * order-aligned offsets within the file, else the hugepage will
+ * not be mappable.
+ * - For all vmas, check if the haddr is in an aligned hugepage
* area.
*/
-static inline bool transhuge_vma_suitable(struct vm_area_struct *vma,
- unsigned long addr)
+static inline bool thp_vma_suitable_order(struct vm_area_struct *vma,
+ unsigned long addr, int order)
{
+ unsigned long hpage_size = PAGE_SIZE << order;
unsigned long haddr;
/* Don't have to check pgoff for anonymous vma */
if (!vma_is_anonymous(vma)) {
if (!IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff,
- HPAGE_PMD_NR))
+ hpage_size >> PAGE_SHIFT))
return false;
}
- haddr = addr & HPAGE_PMD_MASK;
+ haddr = ALIGN_DOWN(addr, hpage_size);
- if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end)
+ if (haddr < vma->vm_start || haddr + hpage_size > vma->vm_end)
return false;
return true;
}
+/*
+ * Filter the bitfield of input orders to the ones suitable for use in the vma.
+ * See thp_vma_suitable_order().
+ * All orders that pass the checks are returned as a bitfield.
+ */
+static inline unsigned long thp_vma_suitable_orders(struct vm_area_struct *vma,
+ unsigned long addr, unsigned long orders)
+{
+ int order;
+
+ /*
+ * Iterate over orders, highest to lowest, removing orders that don't
+ * meet alignment requirements from the set. Exit loop at first order
+ * that meets requirements, since all lower orders must also meet
+ * requirements.
+ */
+
+ order = highest_order(orders);
+
+ while (orders) {
+ if (thp_vma_suitable_order(vma, addr, order))
+ break;
+ order = next_order(&orders, order);
+ }
+
+ return orders;
+}
+
static inline bool file_thp_enabled(struct vm_area_struct *vma)
{
struct inode *inode;
@@ -126,12 +206,55 @@ static inline bool file_thp_enabled(struct vm_area_struct *vma)
inode = vma->vm_file->f_inode;
return (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS)) &&
- (vma->vm_flags & VM_EXEC) &&
!inode_is_open_for_write(inode) && S_ISREG(inode->i_mode);
}
-bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags,
- bool smaps, bool in_pf, bool enforce_sysfs);
+unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma,
+ unsigned long vm_flags, bool smaps,
+ bool in_pf, bool enforce_sysfs,
+ unsigned long orders);
+
+/**
+ * thp_vma_allowable_orders - determine hugepage orders that are allowed for vma
+ * @vma: the vm area to check
+ * @vm_flags: use these vm_flags instead of vma->vm_flags
+ * @smaps: whether answer will be used for smaps file
+ * @in_pf: whether answer will be used by page fault handler
+ * @enforce_sysfs: whether sysfs config should be taken into account
+ * @orders: bitfield of all orders to consider
+ *
+ * Calculates the intersection of the requested hugepage orders and the allowed
+ * hugepage orders for the provided vma. Permitted orders are encoded as a set
+ * bit at the corresponding bit position (bit-2 corresponds to order-2, bit-3
+ * corresponds to order-3, etc). Order-0 is never considered a hugepage order.
+ *
+ * Return: bitfield of orders allowed for hugepage in the vma. 0 if no hugepage
+ * orders are allowed.
+ */
+static inline
+unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma,
+ unsigned long vm_flags, bool smaps,
+ bool in_pf, bool enforce_sysfs,
+ unsigned long orders)
+{
+ /* Optimization to check if required orders are enabled early. */
+ if (enforce_sysfs && vma_is_anonymous(vma)) {
+ unsigned long mask = READ_ONCE(huge_anon_orders_always);
+
+ if (vm_flags & VM_HUGEPAGE)
+ mask |= READ_ONCE(huge_anon_orders_madvise);
+ if (hugepage_global_always() ||
+ ((vm_flags & VM_HUGEPAGE) && hugepage_global_enabled()))
+ mask |= READ_ONCE(huge_anon_orders_inherit);
+
+ orders &= mask;
+ if (!orders)
+ return 0;
+ }
+
+ return __thp_vma_allowable_orders(vma, vm_flags, smaps, in_pf,
+ enforce_sysfs, orders);
+}
#define transparent_hugepage_use_zero_page() \
(transparent_hugepage_flags & \
@@ -267,17 +390,24 @@ static inline bool folio_test_pmd_mappable(struct folio *folio)
return false;
}
-static inline bool transhuge_vma_suitable(struct vm_area_struct *vma,
- unsigned long addr)
+static inline bool thp_vma_suitable_order(struct vm_area_struct *vma,
+ unsigned long addr, int order)
{
return false;
}
-static inline bool hugepage_vma_check(struct vm_area_struct *vma,
- unsigned long vm_flags, bool smaps,
- bool in_pf, bool enforce_sysfs)
+static inline unsigned long thp_vma_suitable_orders(struct vm_area_struct *vma,
+ unsigned long addr, unsigned long orders)
{
- return false;
+ return 0;
+}
+
+static inline unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma,
+ unsigned long vm_flags, bool smaps,
+ bool in_pf, bool enforce_sysfs,
+ unsigned long orders)
+{
+ return 0;
}
static inline void folio_prep_large_rmappable(struct folio *folio) {}
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 236ec7b63c54..c1ee640d87b1 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -829,7 +829,7 @@ static inline unsigned huge_page_shift(struct hstate *h)
static inline bool hstate_is_gigantic(struct hstate *h)
{
- return huge_page_order(h) > MAX_ORDER;
+ return huge_page_order(h) > MAX_PAGE_ORDER;
}
static inline unsigned int pages_per_huge_page(const struct hstate *h)
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 72cb693b075b..dbb06d789e74 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -4,6 +4,7 @@
#include <linux/bug.h>
#include <linux/kasan-enabled.h>
+#include <linux/kasan-tags.h>
#include <linux/kernel.h>
#include <linux/static_key.h>
#include <linux/types.h>
@@ -129,20 +130,39 @@ static __always_inline void kasan_poison_slab(struct slab *slab)
__kasan_poison_slab(slab);
}
-void __kasan_unpoison_object_data(struct kmem_cache *cache, void *object);
-static __always_inline void kasan_unpoison_object_data(struct kmem_cache *cache,
+void __kasan_unpoison_new_object(struct kmem_cache *cache, void *object);
+/**
+ * kasan_unpoison_new_object - Temporarily unpoison a new slab object.
+ * @cache: Cache the object belong to.
+ * @object: Pointer to the object.
+ *
+ * This function is intended for the slab allocator's internal use. It
+ * temporarily unpoisons an object from a newly allocated slab without doing
+ * anything else. The object must later be repoisoned by
+ * kasan_poison_new_object().
+ */
+static __always_inline void kasan_unpoison_new_object(struct kmem_cache *cache,
void *object)
{
if (kasan_enabled())
- __kasan_unpoison_object_data(cache, object);
+ __kasan_unpoison_new_object(cache, object);
}
-void __kasan_poison_object_data(struct kmem_cache *cache, void *object);
-static __always_inline void kasan_poison_object_data(struct kmem_cache *cache,
+void __kasan_poison_new_object(struct kmem_cache *cache, void *object);
+/**
+ * kasan_unpoison_new_object - Repoison a new slab object.
+ * @cache: Cache the object belong to.
+ * @object: Pointer to the object.
+ *
+ * This function is intended for the slab allocator's internal use. It
+ * repoisons an object that was previously unpoisoned by
+ * kasan_unpoison_new_object() without doing anything else.
+ */
+static __always_inline void kasan_poison_new_object(struct kmem_cache *cache,
void *object)
{
if (kasan_enabled())
- __kasan_poison_object_data(cache, object);
+ __kasan_poison_new_object(cache, object);
}
void * __must_check __kasan_init_slab_obj(struct kmem_cache *cache,
@@ -172,13 +192,6 @@ static __always_inline void kasan_kfree_large(void *ptr)
__kasan_kfree_large(ptr, _RET_IP_);
}
-void __kasan_slab_free_mempool(void *ptr, unsigned long ip);
-static __always_inline void kasan_slab_free_mempool(void *ptr)
-{
- if (kasan_enabled())
- __kasan_slab_free_mempool(ptr, _RET_IP_);
-}
-
void * __must_check __kasan_slab_alloc(struct kmem_cache *s,
void *object, gfp_t flags, bool init);
static __always_inline void * __must_check kasan_slab_alloc(
@@ -219,6 +232,113 @@ static __always_inline void * __must_check kasan_krealloc(const void *object,
return (void *)object;
}
+bool __kasan_mempool_poison_pages(struct page *page, unsigned int order,
+ unsigned long ip);
+/**
+ * kasan_mempool_poison_pages - Check and poison a mempool page allocation.
+ * @page: Pointer to the page allocation.
+ * @order: Order of the allocation.
+ *
+ * This function is intended for kernel subsystems that cache page allocations
+ * to reuse them instead of freeing them back to page_alloc (e.g. mempool).
+ *
+ * This function is similar to kasan_mempool_poison_object() but operates on
+ * page allocations.
+ *
+ * Before the poisoned allocation can be reused, it must be unpoisoned via
+ * kasan_mempool_unpoison_pages().
+ *
+ * Return: true if the allocation can be safely reused; false otherwise.
+ */
+static __always_inline bool kasan_mempool_poison_pages(struct page *page,
+ unsigned int order)
+{
+ if (kasan_enabled())
+ return __kasan_mempool_poison_pages(page, order, _RET_IP_);
+ return true;
+}
+
+void __kasan_mempool_unpoison_pages(struct page *page, unsigned int order,
+ unsigned long ip);
+/**
+ * kasan_mempool_unpoison_pages - Unpoison a mempool page allocation.
+ * @page: Pointer to the page allocation.
+ * @order: Order of the allocation.
+ *
+ * This function is intended for kernel subsystems that cache page allocations
+ * to reuse them instead of freeing them back to page_alloc (e.g. mempool).
+ *
+ * This function unpoisons a page allocation that was previously poisoned by
+ * kasan_mempool_poison_pages() without zeroing the allocation's memory. For
+ * the tag-based modes, this function assigns a new tag to the allocation.
+ */
+static __always_inline void kasan_mempool_unpoison_pages(struct page *page,
+ unsigned int order)
+{
+ if (kasan_enabled())
+ __kasan_mempool_unpoison_pages(page, order, _RET_IP_);
+}
+
+bool __kasan_mempool_poison_object(void *ptr, unsigned long ip);
+/**
+ * kasan_mempool_poison_object - Check and poison a mempool slab allocation.
+ * @ptr: Pointer to the slab allocation.
+ *
+ * This function is intended for kernel subsystems that cache slab allocations
+ * to reuse them instead of freeing them back to the slab allocator (e.g.
+ * mempool).
+ *
+ * This function poisons a slab allocation and saves a free stack trace for it
+ * without initializing the allocation's memory and without putting it into the
+ * quarantine (for the Generic mode).
+ *
+ * This function also performs checks to detect double-free and invalid-free
+ * bugs and reports them. The caller can use the return value of this function
+ * to find out if the allocation is buggy.
+ *
+ * Before the poisoned allocation can be reused, it must be unpoisoned via
+ * kasan_mempool_unpoison_object().
+ *
+ * This function operates on all slab allocations including large kmalloc
+ * allocations (the ones returned by kmalloc_large() or by kmalloc() with the
+ * size > KMALLOC_MAX_SIZE).
+ *
+ * Return: true if the allocation can be safely reused; false otherwise.
+ */
+static __always_inline bool kasan_mempool_poison_object(void *ptr)
+{
+ if (kasan_enabled())
+ return __kasan_mempool_poison_object(ptr, _RET_IP_);
+ return true;
+}
+
+void __kasan_mempool_unpoison_object(void *ptr, size_t size, unsigned long ip);
+/**
+ * kasan_mempool_unpoison_object - Unpoison a mempool slab allocation.
+ * @ptr: Pointer to the slab allocation.
+ * @size: Size to be unpoisoned.
+ *
+ * This function is intended for kernel subsystems that cache slab allocations
+ * to reuse them instead of freeing them back to the slab allocator (e.g.
+ * mempool).
+ *
+ * This function unpoisons a slab allocation that was previously poisoned via
+ * kasan_mempool_poison_object() and saves an alloc stack trace for it without
+ * initializing the allocation's memory. For the tag-based modes, this function
+ * does not assign a new tag to the allocation and instead restores the
+ * original tags based on the pointer value.
+ *
+ * This function operates on all slab allocations including large kmalloc
+ * allocations (the ones returned by kmalloc_large() or by kmalloc() with the
+ * size > KMALLOC_MAX_SIZE).
+ */
+static __always_inline void kasan_mempool_unpoison_object(void *ptr,
+ size_t size)
+{
+ if (kasan_enabled())
+ __kasan_mempool_unpoison_object(ptr, size, _RET_IP_);
+}
+
/*
* Unlike kasan_check_read/write(), kasan_check_byte() is performed even for
* the hardware tag-based mode that doesn't rely on compiler instrumentation.
@@ -242,9 +362,9 @@ static inline bool kasan_unpoison_pages(struct page *page, unsigned int order,
return false;
}
static inline void kasan_poison_slab(struct slab *slab) {}
-static inline void kasan_unpoison_object_data(struct kmem_cache *cache,
+static inline void kasan_unpoison_new_object(struct kmem_cache *cache,
void *object) {}
-static inline void kasan_poison_object_data(struct kmem_cache *cache,
+static inline void kasan_poison_new_object(struct kmem_cache *cache,
void *object) {}
static inline void *kasan_init_slab_obj(struct kmem_cac