summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-05-26 12:32:41 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2022-05-26 12:32:41 -0700
commit98931dd95fd489fcbfa97da563505a6f071d7c77 (patch)
tree44683fc4a92efa614acdca2742a7ff19d26da1e3 /include
parentdf202b452fe6c6d6f1351bad485e2367ef1e644e (diff)
parentf403f22f8ccb12860b2b62fec3173c6ccd45938b (diff)
downloadlinux-98931dd95fd489fcbfa97da563505a6f071d7c77.tar.gz
linux-98931dd95fd489fcbfa97da563505a6f071d7c77.tar.bz2
linux-98931dd95fd489fcbfa97da563505a6f071d7c77.zip
Merge tag 'mm-stable-2022-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull MM updates from Andrew Morton: "Almost all of MM here. A few things are still getting finished off, reviewed, etc. - Yang Shi has improved the behaviour of khugepaged collapsing of readonly file-backed transparent hugepages. - Johannes Weiner has arranged for zswap memory use to be tracked and managed on a per-cgroup basis. - Munchun Song adds a /proc knob ("hugetlb_optimize_vmemmap") for runtime enablement of the recent huge page vmemmap optimization feature. - Baolin Wang contributes a series to fix some issues around hugetlb pagetable invalidation. - Zhenwei Pi has fixed some interactions between hwpoisoned pages and virtualization. - Tong Tiangen has enabled the use of the presently x86-only page_table_check debugging feature on arm64 and riscv. - David Vernet has done some fixup work on the memcg selftests. - Peter Xu has taught userfaultfd to handle write protection faults against shmem- and hugetlbfs-backed files. - More DAMON development from SeongJae Park - adding online tuning of the feature and support for monitoring of fixed virtual address ranges. Also easier discovery of which monitoring operations are available. - Nadav Amit has done some optimization of TLB flushing during mprotect(). - Neil Brown continues to labor away at improving our swap-over-NFS support. - David Hildenbrand has some fixes to anon page COWing versus get_user_pages(). - Peng Liu fixed some errors in the core hugetlb code. - Joao Martins has reduced the amount of memory consumed by device-dax's compound devmaps. - Some cleanups of the arch-specific pagemap code from Anshuman Khandual. - Muchun Song has found and fixed some errors in the TLB flushing of transparent hugepages. - Roman Gushchin has done more work on the memcg selftests. ... and, of course, many smaller fixes and cleanups. Notably, the customary million cleanup serieses from Miaohe Lin" * tag 'mm-stable-2022-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (381 commits) mm: kfence: use PAGE_ALIGNED helper selftests: vm: add the "settings" file with timeout variable selftests: vm: add "test_hmm.sh" to TEST_FILES selftests: vm: check numa_available() before operating "merge_across_nodes" in ksm_tests selftests: vm: add migration to the .gitignore selftests/vm/pkeys: fix typo in comment ksm: fix typo in comment selftests: vm: add process_mrelease tests Revert "mm/vmscan: never demote for memcg reclaim" mm/kfence: print disabling or re-enabling message include/trace/events/percpu.h: cleanup for "percpu: improve percpu_alloc_percpu event trace" include/trace/events/mmflags.h: cleanup for "tracing: incorrect gfp_t conversion" mm: fix a potential infinite loop in start_isolate_page_range() MAINTAINERS: add Muchun as co-maintainer for HugeTLB zram: fix Kconfig dependency warning mm/shmem: fix shmem folio swapoff hang cgroup: fix an error handling path in alloc_pagecache_max_30M() mm: damon: use HPAGE_PMD_SIZE tracing: incorrect isolate_mote_t cast in mm_vmscan_lru_isolate nodemask.h: fix compilation error with GCC12 ...
Diffstat (limited to 'include')
-rw-r--r--include/asm-generic/hugetlb.h28
-rw-r--r--include/asm-generic/pgtable-nopmd.h2
-rw-r--r--include/asm-generic/tlb.h14
-rw-r--r--include/linux/cma.h4
-rw-r--r--include/linux/compaction.h5
-rw-r--r--include/linux/damon.h14
-rw-r--r--include/linux/fault-inject.h2
-rw-r--r--include/linux/fs.h9
-rw-r--r--include/linux/gfp.h20
-rw-r--r--include/linux/highmem-internal.h18
-rw-r--r--include/linux/highmem.h53
-rw-r--r--include/linux/huge_mm.h20
-rw-r--r--include/linux/hugetlb.h42
-rw-r--r--include/linux/kasan.h8
-rw-r--r--include/linux/khugepaged.h44
-rw-r--r--include/linux/ksm.h4
-rw-r--r--include/linux/memcontrol.h72
-rw-r--r--include/linux/memory_hotplug.h14
-rw-r--r--include/linux/migrate.h39
-rw-r--r--include/linux/mm.h70
-rw-r--r--include/linux/mm_inline.h43
-rw-r--r--include/linux/mm_types.h20
-rw-r--r--include/linux/mman.h4
-rw-r--r--include/linux/mmzone.h5
-rw-r--r--include/linux/nfs_fs.h2
-rw-r--r--include/linux/nodemask.h13
-rw-r--r--include/linux/page-flags.h62
-rw-r--r--include/linux/page-isolation.h6
-rw-r--r--include/linux/pgtable.h84
-rw-r--r--include/linux/printk.h1
-rw-r--r--include/linux/rmap.h149
-rw-r--r--include/linux/sched/coredump.h3
-rw-r--r--include/linux/shmem_fs.h6
-rw-r--r--include/linux/slab.h12
-rw-r--r--include/linux/swap.h191
-rw-r--r--include/linux/swap_slots.h2
-rw-r--r--include/linux/swapops.h124
-rw-r--r--include/linux/userfaultfd_k.h84
-rw-r--r--include/linux/vm_event_item.h7
-rw-r--r--include/linux/writeback.h7
-rw-r--r--include/ras/ras_event.h1
-rw-r--r--include/trace/events/btrfs.h4
-rw-r--r--include/trace/events/compaction.h4
-rw-r--r--include/trace/events/kmem.h26
-rw-r--r--include/trace/events/mmflags.h84
-rw-r--r--include/trace/events/percpu.h23
-rw-r--r--include/trace/events/vmscan.h20
-rw-r--r--include/uapi/linux/userfaultfd.h10
48 files changed, 1061 insertions, 418 deletions
diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
index 8e1e6244a89d..a57d667addd2 100644
--- a/include/asm-generic/hugetlb.h
+++ b/include/asm-generic/hugetlb.h
@@ -2,6 +2,9 @@
#ifndef _ASM_GENERIC_HUGETLB_H
#define _ASM_GENERIC_HUGETLB_H
+#include <linux/swap.h>
+#include <linux/swapops.h>
+
static inline pte_t mk_huge_pte(struct page *page, pgprot_t pgprot)
{
return mk_pte(page, pgprot);
@@ -32,6 +35,21 @@ static inline pte_t huge_pte_modify(pte_t pte, pgprot_t newprot)
return pte_modify(pte, newprot);
}
+static inline pte_t huge_pte_mkuffd_wp(pte_t pte)
+{
+ return pte_mkuffd_wp(pte);
+}
+
+static inline pte_t huge_pte_clear_uffd_wp(pte_t pte)
+{
+ return pte_clear_uffd_wp(pte);
+}
+
+static inline int huge_pte_uffd_wp(pte_t pte)
+{
+ return pte_uffd_wp(pte);
+}
+
#ifndef __HAVE_ARCH_HUGE_PTE_CLEAR
static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, unsigned long sz)
@@ -66,10 +84,10 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
#endif
#ifndef __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
+static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
- ptep_clear_flush(vma, addr, ptep);
+ return ptep_clear_flush(vma, addr, ptep);
}
#endif
@@ -80,6 +98,12 @@ static inline int huge_pte_none(pte_t pte)
}
#endif
+/* Please refer to comments above pte_none_mostly() for the usage */
+static inline int huge_pte_none_mostly(pte_t pte)
+{
+ return huge_pte_none(pte) || is_pte_marker(pte);
+}
+
#ifndef __HAVE_ARCH_HUGE_PTE_WRPROTECT
static inline pte_t huge_pte_wrprotect(pte_t pte)
{
diff --git a/include/asm-generic/pgtable-nopmd.h b/include/asm-generic/pgtable-nopmd.h
index 10789cf51d16..8ffd64e7a24c 100644
--- a/include/asm-generic/pgtable-nopmd.h
+++ b/include/asm-generic/pgtable-nopmd.h
@@ -30,6 +30,8 @@ typedef struct { pud_t pud; } pmd_t;
static inline int pud_none(pud_t pud) { return 0; }
static inline int pud_bad(pud_t pud) { return 0; }
static inline int pud_present(pud_t pud) { return 1; }
+static inline int pud_user(pud_t pud) { return 0; }
+static inline int pud_leaf(pud_t pud) { return 0; }
static inline void pud_clear(pud_t *pud) { }
#define pmd_ERROR(pmd) (pud_ERROR((pmd).pud))
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index eee6f7763a39..ff3e82553a76 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -658,6 +658,20 @@ static inline void tlb_flush_p4d_range(struct mmu_gather *tlb,
} while (0)
#endif
+#ifndef pte_needs_flush
+static inline bool pte_needs_flush(pte_t oldpte, pte_t newpte)
+{
+ return true;
+}
+#endif
+
+#ifndef huge_pmd_needs_flush
+static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd)
+{
+ return true;
+}
+#endif
+
#endif /* CONFIG_MMU */
#endif /* _ASM_GENERIC__TLB_H */
diff --git a/include/linux/cma.h b/include/linux/cma.h
index a6f637342740..63873b93deaa 100644
--- a/include/linux/cma.h
+++ b/include/linux/cma.h
@@ -17,11 +17,11 @@
#define CMA_MAX_NAME 64
/*
- * TODO: once the buddy -- especially pageblock merging and alloc_contig_range()
+ * the buddy -- especially pageblock merging and alloc_contig_range()
* -- can deal with only some pageblocks of a higher-order page being
* MIGRATE_CMA, we can use pageblock_nr_pages.
*/
-#define CMA_MIN_ALIGNMENT_PAGES MAX_ORDER_NR_PAGES
+#define CMA_MIN_ALIGNMENT_PAGES pageblock_nr_pages
#define CMA_MIN_ALIGNMENT_BYTES (PAGE_SIZE * CMA_MIN_ALIGNMENT_PAGES)
struct cma;
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 34bce35c808d..52a9ff65faee 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -177,7 +177,7 @@ static inline bool compaction_withdrawn(enum compact_result result)
bool compaction_zonelist_suitable(struct alloc_context *ac, int order,
int alloc_flags);
-extern int kcompactd_run(int nid);
+extern void kcompactd_run(int nid);
extern void kcompactd_stop(int nid);
extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int highest_zoneidx);
@@ -212,9 +212,8 @@ static inline bool compaction_withdrawn(enum compact_result result)
return true;
}
-static inline int kcompactd_run(int nid)
+static inline void kcompactd_run(int nid)
{
- return 0;
}
static inline void kcompactd_stop(int nid)
{
diff --git a/include/linux/damon.h b/include/linux/damon.h
index f23cbfa4248d..7c62da31ce4b 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -261,10 +261,14 @@ struct damos {
* enum damon_ops_id - Identifier for each monitoring operations implementation
*
* @DAMON_OPS_VADDR: Monitoring operations for virtual address spaces
+ * @DAMON_OPS_FVADDR: Monitoring operations for only fixed ranges of virtual
+ * address spaces
* @DAMON_OPS_PADDR: Monitoring operations for the physical address space
+ * @NR_DAMON_OPS: Number of monitoring operations implementations
*/
enum damon_ops_id {
DAMON_OPS_VADDR,
+ DAMON_OPS_FVADDR,
DAMON_OPS_PADDR,
NR_DAMON_OPS,
};
@@ -340,6 +344,7 @@ struct damon_operations {
* struct damon_callback - Monitoring events notification callbacks.
*
* @before_start: Called before starting the monitoring.
+ * @after_wmarks_check: Called after each schemes' watermarks check.
* @after_sampling: Called after each sampling.
* @after_aggregation: Called after each aggregation.
* @before_terminate: Called before terminating the monitoring.
@@ -350,6 +355,11 @@ struct damon_operations {
* respectively. Therefore, those are good places for installing and cleaning
* @private.
*
+ * The monitoring thread calls @after_wmarks_check after each DAMON-based
+ * operation schemes' watermarks check. If users need to make changes to the
+ * attributes of the monitoring context while it's deactivated due to the
+ * watermarks, this is the good place to do.
+ *
* The monitoring thread calls @after_sampling and @after_aggregation for each
* of the sampling intervals and aggregation intervals, respectively.
* Therefore, users can safely access the monitoring results without additional
@@ -362,6 +372,7 @@ struct damon_callback {
void *private;
int (*before_start)(struct damon_ctx *context);
+ int (*after_wmarks_check)(struct damon_ctx *context);
int (*after_sampling)(struct damon_ctx *context);
int (*after_aggregation)(struct damon_ctx *context);
void (*before_terminate)(struct damon_ctx *context);
@@ -484,6 +495,8 @@ static inline void damon_insert_region(struct damon_region *r,
void damon_add_region(struct damon_region *r, struct damon_target *t);
void damon_destroy_region(struct damon_region *r, struct damon_target *t);
+int damon_set_regions(struct damon_target *t, struct damon_addr_range *ranges,
+ unsigned int nr_ranges);
struct damos *damon_new_scheme(
unsigned long min_sz_region, unsigned long max_sz_region,
@@ -509,6 +522,7 @@ int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int,
int damon_set_schemes(struct damon_ctx *ctx,
struct damos **schemes, ssize_t nr_schemes);
int damon_nr_running_ctxs(void);
+bool damon_is_registered_ops(enum damon_ops_id id);
int damon_register_ops(struct damon_operations *ops);
int damon_select_ops(struct damon_ctx *ctx, enum damon_ops_id id);
diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h
index 2d04f6448cde..9f6e25467844 100644
--- a/include/linux/fault-inject.h
+++ b/include/linux/fault-inject.h
@@ -20,6 +20,7 @@ struct fault_attr {
atomic_t space;
unsigned long verbose;
bool task_filter;
+ bool no_warn;
unsigned long stacktrace_depth;
unsigned long require_start;
unsigned long require_end;
@@ -39,6 +40,7 @@ struct fault_attr {
.ratelimit_state = RATELIMIT_STATE_INIT_DISABLED, \
.verbose = 2, \
.dname = NULL, \
+ .no_warn = false, \
}
#define DECLARE_FAULT_ATTR(name) struct fault_attr name = FAULT_ATTR_INITIALIZER
diff --git a/include/linux/fs.h b/include/linux/fs.h
index f58ae40235ab..1225f8c75650 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -162,6 +162,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
/* File is stream-like */
#define FMODE_STREAM ((__force fmode_t)0x200000)
+/* File supports DIRECT IO */
+#define FMODE_CAN_ODIRECT ((__force fmode_t)0x400000)
+
/* File was opened by fanotify and shouldn't generate fanotify events */
#define FMODE_NONOTIFY ((__force fmode_t)0x4000000)
@@ -376,6 +379,7 @@ struct address_space_operations {
int (*swap_activate)(struct swap_info_struct *sis, struct file *file,
sector_t *span);
void (*swap_deactivate)(struct file *file);
+ int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter);
};
extern const struct address_space_operations empty_aops;
@@ -457,6 +461,11 @@ static inline void i_mmap_unlock_write(struct address_space *mapping)
up_write(&mapping->i_mmap_rwsem);
}
+static inline int i_mmap_trylock_read(struct address_space *mapping)
+{
+ return down_read_trylock(&mapping->i_mmap_rwsem);
+}
+
static inline void i_mmap_lock_read(struct address_space *mapping)
{
down_read(&mapping->i_mmap_rwsem);
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 3e3d36fc2109..2d2ccae933c2 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -367,7 +367,7 @@ static inline int gfp_migratetype(const gfp_t gfp_flags)
return MIGRATE_UNMOVABLE;
/* Group based on mobility */
- return (gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT;
+ return (__force unsigned long)(gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT;
}
#undef GFP_MOVABLE_MASK
#undef GFP_MOVABLE_SHIFT
@@ -613,13 +613,8 @@ static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask,
#ifdef CONFIG_NUMA
struct page *alloc_pages(gfp_t gfp, unsigned int order);
struct folio *folio_alloc(gfp_t gfp, unsigned order);
-struct page *alloc_pages_vma(gfp_t gfp_mask, int order,
- struct vm_area_struct *vma, unsigned long addr,
- bool hugepage);
struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma,
unsigned long addr, bool hugepage);
-#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \
- alloc_pages_vma(gfp_mask, order, vma, addr, true)
#else
static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order)
{
@@ -629,16 +624,17 @@ static inline struct folio *folio_alloc(gfp_t gfp, unsigned int order)
{
return __folio_alloc_node(gfp, order, numa_node_id());
}
-#define alloc_pages_vma(gfp_mask, order, vma, addr, hugepage) \
- alloc_pages(gfp_mask, order)
#define vma_alloc_folio(gfp, order, vma, addr, hugepage) \
folio_alloc(gfp, order)
-#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \
- alloc_pages(gfp_mask, order)
#endif
#define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0)
-#define alloc_page_vma(gfp_mask, vma, addr) \
- alloc_pages_vma(gfp_mask, 0, vma, addr, false)
+static inline struct page *alloc_page_vma(gfp_t gfp,
+ struct vm_area_struct *vma, unsigned long addr)
+{
+ struct folio *folio = vma_alloc_folio(gfp, 0, vma, addr, false);
+
+ return &folio->page;
+}
extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order);
extern unsigned long get_zeroed_page(gfp_t gfp_mask);
diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h
index 337bd9f32921..cddb42ff0473 100644
--- a/include/linux/highmem-internal.h
+++ b/include/linux/highmem-internal.h
@@ -246,9 +246,21 @@ static inline bool is_kmap_addr(const void *x)
#endif /* CONFIG_HIGHMEM */
-/*
- * Prevent people trying to call kunmap_atomic() as if it were kunmap()
- * kunmap_atomic() should get the return value of kmap_atomic, not the page.
+/**
+ * kunmap_atomic - Unmap the virtual address mapped by kmap_atomic() - deprecated!
+ * @__addr: Virtual address to be unmapped
+ *
+ * Unmaps an address previously mapped by kmap_atomic() and re-enables
+ * pagefaults. Depending on PREEMP_RT configuration, re-enables also
+ * migration and preemption. Users should not count on these side effects.
+ *
+ * Mappings should be unmapped in the reverse order that they were mapped.
+ * See kmap_local_page() for details on nesting.
+ *
+ * @__addr can be any address within the mapped page, so there is no need
+ * to subtract any offset that has been added. In contrast to kunmap(),
+ * this function takes the address returned from kmap_atomic(), not the
+ * page passed to it. The compiler will warn you if you pass the page.
*/
#define kunmap_atomic(__addr) \
do { \
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 39bb9b47fa9c..3af34de54330 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -37,7 +37,7 @@ static inline void *kmap(struct page *page);
/**
* kunmap - Unmap the virtual address mapped by kmap()
- * @addr: Virtual address to be unmapped
+ * @page: Pointer to the page which was mapped by kmap()
*
* Counterpart to kmap(). A NOOP for CONFIG_HIGHMEM=n and for mappings of
* pages in the low memory area.
@@ -138,23 +138,46 @@ static inline void *kmap_local_folio(struct folio *folio, size_t offset);
*
* Returns: The virtual address of the mapping
*
- * Effectively a wrapper around kmap_local_page() which disables pagefaults
- * and preemption.
+ * In fact a wrapper around kmap_local_page() which also disables pagefaults
+ * and, depending on PREEMPT_RT configuration, also CPU migration and
+ * preemption. Therefore users should not count on the latter two side effects.
+ *
+ * Mappings should always be released by kunmap_atomic().
*
* Do not use in new code. Use kmap_local_page() instead.
- */
-static inline void *kmap_atomic(struct page *page);
-
-/**
- * kunmap_atomic - Unmap the virtual address mapped by kmap_atomic()
- * @addr: Virtual address to be unmapped
*
- * Counterpart to kmap_atomic().
+ * It is used in atomic context when code wants to access the contents of a
+ * page that might be allocated from high memory (see __GFP_HIGHMEM), for
+ * example a page in the pagecache. The API has two functions, and they
+ * can be used in a manner similar to the following:
+ *
+ * -- Find the page of interest. --
+ * struct page *page = find_get_page(mapping, offset);
+ *
+ * -- Gain access to the contents of that page. --
+ * void *vaddr = kmap_atomic(page);
+ *
+ * -- Do something to the contents of that page. --
+ * memset(vaddr, 0, PAGE_SIZE);
+ *
+ * -- Unmap that page. --
+ * kunmap_atomic(vaddr);
*
- * Effectively a wrapper around kunmap_local() which additionally undoes
- * the side effects of kmap_atomic(), i.e. reenabling pagefaults and
- * preemption.
+ * Note that the kunmap_atomic() call takes the result of the kmap_atomic()
+ * call, not the argument.
+ *
+ * If you need to map two pages because you want to copy from one page to
+ * another you need to keep the kmap_atomic calls strictly nested, like:
+ *
+ * vaddr1 = kmap_atomic(page1);
+ * vaddr2 = kmap_atomic(page2);
+ *
+ * memcpy(vaddr1, vaddr2, PAGE_SIZE);
+ *
+ * kunmap_atomic(vaddr2);
+ * kunmap_atomic(vaddr1);
*/
+static inline void *kmap_atomic(struct page *page);
/* Highmem related interfaces for management code */
static inline unsigned int nr_free_highpages(void);
@@ -191,6 +214,8 @@ static inline void clear_user_highpage(struct page *page, unsigned long vaddr)
* @vma: The VMA the page is to be allocated for
* @vaddr: The virtual address the page will be inserted into
*
+ * Returns: The allocated and zeroed HIGHMEM page
+ *
* This function will allocate a page for a VMA that the caller knows will
* be able to migrate in the future using move_pages() or reclaimed
*
@@ -358,6 +383,8 @@ static inline void memcpy_to_page(struct page *page, size_t offset,
static inline void memzero_page(struct page *page, size_t offset, size_t len)
{
char *addr = kmap_local_page(page);
+
+ VM_BUG_ON(offset + len > PAGE_SIZE);
memset(addr + offset, 0, len);
flush_dcache_page(page);
kunmap_local(addr);
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 2999190adc22..de29821231c9 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -36,8 +36,9 @@ int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud,
unsigned long addr);
bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd);
-int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr,
- pgprot_t newprot, unsigned long cp_flags);
+int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
+ pmd_t *pmd, unsigned long addr, pgprot_t newprot,
+ unsigned long cp_flags);
vm_fault_t vmf_insert_pfn_pmd_prot(struct vm_fault *vmf, pfn_t pfn,
pgprot_t pgprot, bool write);
@@ -172,6 +173,20 @@ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma)
return false;
}
+static inline bool file_thp_enabled(struct vm_area_struct *vma)
+{
+ struct inode *inode;
+
+ if (!vma->vm_file)
+ return false;
+
+ 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 transparent_hugepage_active(struct vm_area_struct *vma);
#define transparent_hugepage_use_zero_page() \
@@ -347,7 +362,6 @@ static inline void prep_transhuge_page(struct page *page) {}
static inline bool
can_split_folio(struct folio *folio, int *pextra_pins)
{
- BUILD_BUG();
return false;
}
static inline int
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index ac2a1d758a80..0f2894d01333 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -137,17 +137,19 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma,
struct vm_area_struct *new_vma,
unsigned long old_addr, unsigned long new_addr,
unsigned long len);
-int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *);
+int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *,
+ struct vm_area_struct *, struct vm_area_struct *);
long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *,
struct page **, struct vm_area_struct **,
unsigned long *, unsigned long *, long, unsigned int,
int *);
void unmap_hugepage_range(struct vm_area_struct *,
- unsigned long, unsigned long, struct page *);
+ unsigned long, unsigned long, struct page *,
+ zap_flags_t);
void __unmap_hugepage_range_final(struct mmu_gather *tlb,
struct vm_area_struct *vma,
unsigned long start, unsigned long end,
- struct page *ref_page);
+ struct page *ref_page, zap_flags_t zap_flags);
void hugetlb_report_meminfo(struct seq_file *);
int hugetlb_report_node_meminfo(char *buf, int len, int nid);
void hugetlb_show_meminfo(void);
@@ -160,7 +162,8 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, pte_t *dst_pte,
unsigned long dst_addr,
unsigned long src_addr,
enum mcopy_atomic_mode mode,
- struct page **pagep);
+ struct page **pagep,
+ bool wp_copy);
#endif /* CONFIG_USERFAULTFD */
bool hugetlb_reserve_pages(struct inode *inode, long from, long to,
struct vm_area_struct *vma,
@@ -210,7 +213,8 @@ struct page *follow_huge_pgd(struct mm_struct *mm, unsigned long address,
int pmd_huge(pmd_t pmd);
int pud_huge(pud_t pud);
unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
- unsigned long address, unsigned long end, pgprot_t newprot);
+ unsigned long address, unsigned long end, pgprot_t newprot,
+ unsigned long cp_flags);
bool is_hugetlb_entry_migration(pte_t pte);
void hugetlb_unshare_all_pmds(struct vm_area_struct *vma);
@@ -266,7 +270,9 @@ static inline struct page *follow_huge_addr(struct mm_struct *mm,
}
static inline int copy_hugetlb_page_range(struct mm_struct *dst,
- struct mm_struct *src, struct vm_area_struct *vma)
+ struct mm_struct *src,
+ struct vm_area_struct *dst_vma,
+ struct vm_area_struct *src_vma)
{
BUG();
return 0;
@@ -356,7 +362,8 @@ static inline int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
unsigned long dst_addr,
unsigned long src_addr,
enum mcopy_atomic_mode mode,
- struct page **pagep)
+ struct page **pagep,
+ bool wp_copy)
{
BUG();
return 0;
@@ -395,14 +402,16 @@ static inline void move_hugetlb_state(struct page *oldpage,
static inline unsigned long hugetlb_change_protection(
struct vm_area_struct *vma, unsigned long address,
- unsigned long end, pgprot_t newprot)