Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a7d626b..289c26f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -15,6 +15,7 @@
#include <linux/atomic.h>
#include <linux/debug_locks.h>
#include <linux/mm_types.h>
+#include <linux/mmap_lock.h>
#include <linux/range.h>
#include <linux/pfn.h>
#include <linux/percpu-refcount.h>
@@ -23,10 +24,13 @@
#include <linux/resource.h>
#include <linux/page_ext.h>
#include <linux/err.h>
+#include <linux/page-flags.h>
#include <linux/page_ref.h>
#include <linux/memremap.h>
#include <linux/overflow.h>
#include <linux/sizes.h>
+#include <linux/sched.h>
+#include <linux/pgtable.h>
struct mempolicy;
struct anon_vma;
@@ -35,6 +39,9 @@
struct user_struct;
struct writeback_control;
struct bdi_writeback;
+struct pt_regs;
+
+extern int sysctl_page_lock_unfairness;
void init_mm_internals(void);
@@ -70,11 +77,6 @@
atomic_long_add(count, &_totalram_pages);
}
-static inline void totalram_pages_set(long val)
-{
- atomic_long_set(&_totalram_pages, val);
-}
-
extern void * high_memory;
extern int page_cluster;
@@ -96,7 +98,6 @@
#endif
#include <asm/page.h>
-#include <asm/pgtable.h>
#include <asm/processor.h>
/*
@@ -158,11 +159,14 @@
switch (sizeof(struct page)) {
case 80:
- _pp[9] = 0; /* fallthrough */
+ _pp[9] = 0;
+ fallthrough;
case 72:
- _pp[8] = 0; /* fallthrough */
+ _pp[8] = 0;
+ fallthrough;
case 64:
- _pp[7] = 0; /* fallthrough */
+ _pp[7] = 0;
+ fallthrough;
case 56:
_pp[6] = 0;
_pp[5] = 0;
@@ -205,10 +209,12 @@
extern int sysctl_overcommit_ratio;
extern unsigned long sysctl_overcommit_kbytes;
-extern int overcommit_ratio_handler(struct ctl_table *, int, void __user *,
- size_t *, loff_t *);
-extern int overcommit_kbytes_handler(struct ctl_table *, int, void __user *,
- size_t *, loff_t *);
+int overcommit_ratio_handler(struct ctl_table *, int, void *, size_t *,
+ loff_t *);
+int overcommit_kbytes_handler(struct ctl_table *, int, void *, size_t *,
+ loff_t *);
+int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *,
+ loff_t *);
#define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n))
@@ -329,15 +335,19 @@
#elif defined(CONFIG_SPARC64)
# define VM_SPARC_ADI VM_ARCH_1 /* Uses ADI tag for access control */
# define VM_ARCH_CLEAR VM_SPARC_ADI
+#elif defined(CONFIG_ARM64)
+# define VM_ARM64_BTI VM_ARCH_1 /* BTI guarded page, a.k.a. GP bit */
+# define VM_ARCH_CLEAR VM_ARM64_BTI
#elif !defined(CONFIG_MMU)
# define VM_MAPPED_COPY VM_ARCH_1 /* T if mapped copy of data (nommu mmap) */
#endif
-#if defined(CONFIG_X86_INTEL_MPX)
-/* MPX specific bounds table or bounds directory */
-# define VM_MPX VM_HIGH_ARCH_4
+#if defined(CONFIG_ARM64_MTE)
+# define VM_MTE VM_HIGH_ARCH_0 /* Use Tagged memory for access control */
+# define VM_MTE_ALLOWED VM_HIGH_ARCH_1 /* Tagged memory permitted */
#else
-# define VM_MPX VM_NONE
+# define VM_MTE VM_NONE
+# define VM_MTE_ALLOWED VM_NONE
#endif
#ifndef VM_GROWSUP
@@ -347,6 +357,20 @@
/* Bits set in the VMA until the stack is in its final location */
#define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ)
+#define TASK_EXEC ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0)
+
+/* Common data flag combinations */
+#define VM_DATA_FLAGS_TSK_EXEC (VM_READ | VM_WRITE | TASK_EXEC | \
+ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+#define VM_DATA_FLAGS_NON_EXEC (VM_READ | VM_WRITE | VM_MAYREAD | \
+ VM_MAYWRITE | VM_MAYEXEC)
+#define VM_DATA_FLAGS_EXEC (VM_READ | VM_WRITE | VM_EXEC | \
+ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+
+#ifndef VM_DATA_DEFAULT_FLAGS /* arch can override this */
+#define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_EXEC
+#endif
+
#ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */
#define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS
#endif
@@ -359,12 +383,18 @@
#define VM_STACK_FLAGS (VM_STACK | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT)
+/* VMA basic access permission flags */
+#define VM_ACCESS_FLAGS (VM_READ | VM_WRITE | VM_EXEC)
+
+
/*
* Special vmas that are non-mergable, non-mlock()able.
- * Note: mm/huge_memory.c VM_NO_THP depends on this definition.
*/
#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP)
+/* This mask prevents VMA from being scanned with khugepaged */
+#define VM_NO_KHUGEPAGED (VM_SPECIAL | VM_HUGETLB)
+
/* This mask defines which mm->def_flags a process can inherit its parent */
#define VM_INIT_DEF_MASK VM_NOHUGEPAGE
@@ -383,15 +413,75 @@
*/
extern pgprot_t protection_map[16];
-#define FAULT_FLAG_WRITE 0x01 /* Fault was a write access */
-#define FAULT_FLAG_MKWRITE 0x02 /* Fault was mkwrite of existing pte */
-#define FAULT_FLAG_ALLOW_RETRY 0x04 /* Retry fault if blocking */
-#define FAULT_FLAG_RETRY_NOWAIT 0x08 /* Don't drop mmap_sem and wait when retrying */
-#define FAULT_FLAG_KILLABLE 0x10 /* The fault task is in SIGKILL killable region */
-#define FAULT_FLAG_TRIED 0x20 /* Second try */
-#define FAULT_FLAG_USER 0x40 /* The fault originated in userspace */
-#define FAULT_FLAG_REMOTE 0x80 /* faulting for non current tsk/mm */
-#define FAULT_FLAG_INSTRUCTION 0x100 /* The fault was during an instruction fetch */
+/**
+ * Fault flag definitions.
+ *
+ * @FAULT_FLAG_WRITE: Fault was a write fault.
+ * @FAULT_FLAG_MKWRITE: Fault was mkwrite of existing PTE.
+ * @FAULT_FLAG_ALLOW_RETRY: Allow to retry the fault if blocked.
+ * @FAULT_FLAG_RETRY_NOWAIT: Don't drop mmap_lock and wait when retrying.
+ * @FAULT_FLAG_KILLABLE: The fault task is in SIGKILL killable region.
+ * @FAULT_FLAG_TRIED: The fault has been tried once.
+ * @FAULT_FLAG_USER: The fault originated in userspace.
+ * @FAULT_FLAG_REMOTE: The fault is not for current task/mm.
+ * @FAULT_FLAG_INSTRUCTION: The fault was during an instruction fetch.
+ * @FAULT_FLAG_INTERRUPTIBLE: The fault can be interrupted by non-fatal signals.
+ *
+ * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify
+ * whether we would allow page faults to retry by specifying these two
+ * fault flags correctly. Currently there can be three legal combinations:
+ *
+ * (a) ALLOW_RETRY and !TRIED: this means the page fault allows retry, and
+ * this is the first try
+ *
+ * (b) ALLOW_RETRY and TRIED: this means the page fault allows retry, and
+ * we've already tried at least once
+ *
+ * (c) !ALLOW_RETRY and !TRIED: this means the page fault does not allow retry
+ *
+ * The unlisted combination (!ALLOW_RETRY && TRIED) is illegal and should never
+ * be used. Note that page faults can be allowed to retry for multiple times,
+ * in which case we'll have an initial fault with flags (a) then later on
+ * continuous faults with flags (b). We should always try to detect pending
+ * signals before a retry to make sure the continuous page faults can still be
+ * interrupted if necessary.
+ */
+#define FAULT_FLAG_WRITE 0x01
+#define FAULT_FLAG_MKWRITE 0x02
+#define FAULT_FLAG_ALLOW_RETRY 0x04
+#define FAULT_FLAG_RETRY_NOWAIT 0x08
+#define FAULT_FLAG_KILLABLE 0x10
+#define FAULT_FLAG_TRIED 0x20
+#define FAULT_FLAG_USER 0x40
+#define FAULT_FLAG_REMOTE 0x80
+#define FAULT_FLAG_INSTRUCTION 0x100
+#define FAULT_FLAG_INTERRUPTIBLE 0x200
+
+/*
+ * The default fault flags that should be used by most of the
+ * arch-specific page fault handlers.
+ */
+#define FAULT_FLAG_DEFAULT (FAULT_FLAG_ALLOW_RETRY | \
+ FAULT_FLAG_KILLABLE | \
+ FAULT_FLAG_INTERRUPTIBLE)
+
+/**
+ * fault_flag_allow_retry_first - check ALLOW_RETRY the first time
+ *
+ * This is mostly used for places where we want to try to avoid taking
+ * the mmap_lock for too long a time when waiting for another condition
+ * to change, in which case we can try to be polite to release the
+ * mmap_lock in the first round to avoid potential starvation of other
+ * processes that would also want the mmap_lock.
+ *
+ * Return: true if the page fault allows retry and this is the first
+ * attempt of the fault handling; false otherwise.
+ */
+static inline bool fault_flag_allow_retry_first(unsigned int flags)
+{
+ return (flags & FAULT_FLAG_ALLOW_RETRY) &&
+ (!(flags & FAULT_FLAG_TRIED));
+}
#define FAULT_FLAG_TRACE \
{ FAULT_FLAG_WRITE, "WRITE" }, \
@@ -402,10 +492,11 @@
{ FAULT_FLAG_TRIED, "TRIED" }, \
{ FAULT_FLAG_USER, "USER" }, \
{ FAULT_FLAG_REMOTE, "REMOTE" }, \
- { FAULT_FLAG_INSTRUCTION, "INSTRUCTION" }
+ { FAULT_FLAG_INSTRUCTION, "INSTRUCTION" }, \
+ { FAULT_FLAG_INTERRUPTIBLE, "INTERRUPTIBLE" }
/*
- * vm_fault is filled by the the pagefault handler and passed to the vma's
+ * vm_fault is filled by the pagefault handler and passed to the vma's
* ->fault function. The vma's ->fault is responsible for returning a bitmask
* of VM_FAULT_xxx flags that give details about how the fault was handled.
*
@@ -428,7 +519,6 @@
pte_t orig_pte; /* Value of PTE at the time of fault */
struct page *cow_page; /* Page handler may use for COW fault */
- struct mem_cgroup *memcg; /* Cgroup cow_page belongs to */
struct page *page; /* ->fault handlers should return a
* page here, unless VM_FAULT_NOPAGE
* is set (which is also implied by
@@ -509,7 +599,7 @@
* (vma,addr) marked as MPOL_SHARED. The shared policy infrastructure
* in mm/mempolicy.c will do this automatically.
* get_policy() must NOT add a ref if the policy at (vma,addr) is not
- * marked as MPOL_SHARED. vma policies are protected by the mmap_sem.
+ * marked as MPOL_SHARED. vma policies are protected by the mmap_lock.
* If no [shared/vma] mempolicy exists at the addr, get_policy() op
* must return NULL--i.e., do not "fallback" to task or system default
* policy.
@@ -546,6 +636,36 @@
return !vma->vm_ops;
}
+static inline bool vma_is_temporary_stack(struct vm_area_struct *vma)
+{
+ int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP);
+
+ if (!maybe_stack)
+ return false;
+
+ if ((vma->vm_flags & VM_STACK_INCOMPLETE_SETUP) ==
+ VM_STACK_INCOMPLETE_SETUP)
+ return true;
+
+ return false;
+}
+
+static inline bool vma_is_foreign(struct vm_area_struct *vma)
+{
+ if (!current->mm)
+ return true;
+
+ if (current->mm != vma->vm_mm)
+ return true;
+
+ return false;
+}
+
+static inline bool vma_is_accessible(struct vm_area_struct *vma)
+{
+ return vma->vm_flags & VM_ACCESS_FLAGS;
+}
+
#ifdef CONFIG_SHMEM
/*
* The vma_is_shmem is not inline because it is used only by slow
@@ -564,26 +684,6 @@
struct mmu_gather;
struct inode;
-#if !defined(CONFIG_ARCH_HAS_PTE_DEVMAP) || !defined(CONFIG_TRANSPARENT_HUGEPAGE)
-static inline int pmd_devmap(pmd_t pmd)
-{
- return 0;
-}
-static inline int pud_devmap(pud_t pud)
-{
- return 0;
-}
-static inline int pgd_devmap(pgd_t pgd)
-{
- return 0;
-}
-#endif
-
-/*
- * FIXME: take this include out, include page-flags.h in
- * files which need it (119 of them)
- */
-#include <linux/page-flags.h>
#include <linux/huge_mm.h>
/*
@@ -640,24 +740,19 @@
* On nommu, vmalloc/vfree wrap through kmalloc/kfree directly, so there
* is no special casing required.
*/
-static inline bool is_vmalloc_addr(const void *x)
-{
-#ifdef CONFIG_MMU
- unsigned long addr = (unsigned long)x;
-
- return addr >= VMALLOC_START && addr < VMALLOC_END;
-#else
- return false;
-#endif
-}
#ifndef is_ioremap_addr
#define is_ioremap_addr(x) is_vmalloc_addr(x)
#endif
#ifdef CONFIG_MMU
+extern bool is_vmalloc_addr(const void *x);
extern int is_vmalloc_or_module_addr(const void *x);
#else
+static inline bool is_vmalloc_addr(const void *x)
+{
+ return false;
+}
static inline int is_vmalloc_or_module_addr(const void *x)
{
return 0;
@@ -696,6 +791,11 @@
extern void kvfree(const void *addr);
extern void kvfree_sensitive(const void *addr, size_t len);
+static inline int head_compound_mapcount(struct page *head)
+{
+ return atomic_read(compound_mapcount_ptr(head)) + 1;
+}
+
/*
* Mapcount of compound page as a whole, does not include mapped sub-pages.
*
@@ -705,7 +805,7 @@
{
VM_BUG_ON_PAGE(!PageCompound(page), page);
page = compound_head(page);
- return atomic_read(compound_mapcount_ptr(page)) + 1;
+ return head_compound_mapcount(page);
}
/*
@@ -785,7 +885,7 @@
#endif
NR_COMPOUND_DTORS,
};
-extern compound_page_dtor * const compound_page_dtors[];
+extern compound_page_dtor * const compound_page_dtors[NR_COMPOUND_DTORS];
static inline void set_compound_page_dtor(struct page *page,
enum compound_dtor_id compound_dtor)
@@ -794,10 +894,10 @@
page[1].compound_dtor = compound_dtor;
}
-static inline compound_page_dtor *get_compound_page_dtor(struct page *page)
+static inline void destroy_compound_page(struct page *page)
{
VM_BUG_ON_PAGE(page[1].compound_dtor >= NR_COMPOUND_DTORS, page);
- return compound_page_dtors[page[1].compound_dtor];
+ compound_page_dtors[page[1].compound_dtor](page);
}
static inline unsigned int compound_order(struct page *page)
@@ -807,15 +907,41 @@
return page[1].compound_order;
}
+static inline bool hpage_pincount_available(struct page *page)
+{
+ /*
+ * Can the page->hpage_pinned_refcount field be used? That field is in
+ * the 3rd page of the compound page, so the smallest (2-page) compound
+ * pages cannot support it.
+ */
+ page = compound_head(page);
+ return PageCompound(page) && compound_order(page) > 1;
+}
+
+static inline int head_compound_pincount(struct page *head)
+{
+ return atomic_read(compound_pincount_ptr(head));
+}
+
+static inline int compound_pincount(struct page *page)
+{
+ VM_BUG_ON_PAGE(!hpage_pincount_available(page), page);
+ page = compound_head(page);
+ return head_compound_pincount(page);
+}
+
static inline void set_compound_order(struct page *page, unsigned int order)
{
page[1].compound_order = order;
+ page[1].compound_nr = 1U << order;
}
/* Returns the number of pages in this potentially compound page. */
static inline unsigned long compound_nr(struct page *page)
{
- return 1UL << compound_order(page);
+ if (!PageHead(page))
+ return 1;
+ return page[1].compound_nr;
}
/* Returns the number of bytes in this potentially compound page. */
@@ -846,8 +972,7 @@
return pte;
}
-vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg,
- struct page *page);
+vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page);
vm_fault_t finish_fault(struct vm_fault *vmf);
vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf);
#endif
@@ -948,10 +1073,6 @@
#define ZONEID_PGSHIFT (ZONEID_PGOFF * (ZONEID_SHIFT != 0))
-#if SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS
-#error SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS
-#endif
-
#define ZONES_MASK ((1UL << ZONES_WIDTH) - 1)
#define NODES_MASK ((1UL << NODES_WIDTH) - 1)
#define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1)
@@ -961,6 +1082,7 @@
static inline enum zone_type page_zonenum(const struct page *page)
{
+ ASSERT_EXCLUSIVE_BITS(page->flags, ZONES_MASK << ZONES_PGSHIFT);
return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK;
}
@@ -979,9 +1101,10 @@
#endif
#ifdef CONFIG_DEV_PAGEMAP_OPS
-void __put_devmap_managed_page(struct page *page);
+void free_devmap_managed_page(struct page *page);
DECLARE_STATIC_KEY_FALSE(devmap_managed_key);
-static inline bool put_devmap_managed_page(struct page *page)
+
+static inline bool page_is_devmap_managed(struct page *page)
{
if (!static_branch_unlikely(&devmap_managed_key))
return false;
@@ -990,7 +1113,6 @@
switch (page->pgmap->type) {
case MEMORY_DEVICE_PRIVATE:
case MEMORY_DEVICE_FS_DAX:
- __put_devmap_managed_page(page);
return true;
default:
break;
@@ -998,11 +1120,17 @@
return false;
}
+void put_devmap_managed_page(struct page *page);
+
#else /* CONFIG_DEV_PAGEMAP_OPS */
-static inline bool put_devmap_managed_page(struct page *page)
+static inline bool page_is_devmap_managed(struct page *page)
{
return false;
}
+
+static inline void put_devmap_managed_page(struct page *page)
+{
+}
#endif /* CONFIG_DEV_PAGEMAP_OPS */
static inline bool is_device_private_page(const struct page *page)
@@ -1036,6 +1164,8 @@
page_ref_inc(page);
}
+bool __must_check try_grab_page(struct page *page, unsigned int flags);
+
static inline __must_check bool try_get_page(struct page *page)
{
page = compound_head(page);
@@ -1055,38 +1185,96 @@
* need to inform the device driver through callback. See
* include/linux/memremap.h and HMM for details.
*/
- if (put_devmap_managed_page(page))
+ if (page_is_devmap_managed(page)) {
+ put_devmap_managed_page(page);
return;
+ }
if (put_page_testzero(page))
__put_page(page);
}
-/**
- * put_user_page() - release a gup-pinned page
- * @page: pointer to page to be released
+/*
+ * GUP_PIN_COUNTING_BIAS, and the associated functions that use it, overload
+ * the page's refcount so that two separate items are tracked: the original page
+ * reference count, and also a new count of how many pin_user_pages() calls were
+ * made against the page. ("gup-pinned" is another term for the latter).
*
- * Pages that were pinned via get_user_pages*() must be released via
- * either put_user_page(), or one of the put_user_pages*() routines
- * below. This is so that eventually, pages that are pinned via
- * get_user_pages*() can be separately tracked and uniquely handled. In
- * particular, interactions with RDMA and filesystems need special
- * handling.
+ * With this scheme, pin_user_pages() becomes special: such pages are marked as
+ * distinct from normal pages. As such, the unpin_user_page() call (and its
+ * variants) must be used in order to release gup-pinned pages.
*
- * put_user_page() and put_page() are not interchangeable, despite this early
- * implementation that makes them look the same. put_user_page() calls must
- * be perfectly matched up with get_user_page() calls.
+ * Choice of value:
+ *
+ * By making GUP_PIN_COUNTING_BIAS a power of two, debugging of page reference
+ * counts with respect to pin_user_pages() and unpin_user_page() becomes
+ * simpler, due to the fact that adding an even power of two to the page
+ * refcount has the effect of using only the upper N bits, for the code that
+ * counts up using the bias value. This means that the lower bits are left for
+ * the exclusive use of the original code that increments and decrements by one
+ * (or at least, by much smaller values than the bias value).
+ *
+ * Of course, once the lower bits overflow into the upper bits (and this is
+ * OK, because subtraction recovers the original values), then visual inspection
+ * no longer suffices to directly view the separate counts. However, for normal
+ * applications that don't have huge page reference counts, this won't be an
+ * issue.
+ *
+ * Locking: the lockless algorithm described in page_cache_get_speculative()
+ * and page_cache_gup_pin_speculative() provides safe operation for
+ * get_user_pages and page_mkclean and other calls that race to set up page
+ * table entries.
*/
-static inline void put_user_page(struct page *page)
+#define GUP_PIN_COUNTING_BIAS (1U << 10)
+
+void unpin_user_page(struct page *page);
+void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages,
+ bool make_dirty);
+void unpin_user_pages(struct page **pages, unsigned long npages);
+
+/**
+ * page_maybe_dma_pinned() - report if a page is pinned for DMA.
+ *
+ * This function checks if a page has been pinned via a call to
+ * pin_user_pages*().
+ *
+ * For non-huge pages, the return value is partially fuzzy: false is not fuzzy,
+ * because it means "definitely not pinned for DMA", but true means "probably
+ * pinned for DMA, but possibly a false positive due to having at least
+ * GUP_PIN_COUNTING_BIAS worth of normal page references".
+ *
+ * False positives are OK, because: a) it's unlikely for a page to get that many
+ * refcounts, and b) all the callers of this routine are expected to be able to
+ * deal gracefully with a false positive.
+ *
+ * For huge pages, the result will be exactly correct. That's because we have
+ * more tracking data available: the 3rd struct page in the compound page is
+ * used to track the pincount (instead using of the GUP_PIN_COUNTING_BIAS
+ * scheme).
+ *
+ * For more information, please see Documentation/core-api/pin_user_pages.rst.
+ *
+ * @page: pointer to page to be queried.
+ * @Return: True, if it is likely that the page has been "dma-pinned".
+ * False, if the page is definitely not dma-pinned.
+ */
+static inline bool page_maybe_dma_pinned(struct page *page)
{
- put_page(page);
+ if (hpage_pincount_available(page))
+ return compound_pincount(page) > 0;
+
+ /*
+ * page_ref_count() is signed. If that refcount overflows, then
+ * page_ref_count() returns a negative value, and callers will avoid
+ * further incrementing the refcount.
+ *
+ * Here, for that overflow case, use the signed bit to count a little
+ * bit higher via unsigned math, and thus still get an accurate result.
+ */
+ return ((unsigned int)page_ref_count(compound_head(page))) >=
+ GUP_PIN_COUNTING_BIAS;
}
-void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
- bool make_dirty);
-
-void put_user_pages(struct page **pages, unsigned long npages);
-
#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
#define SECTION_IN_PAGE_FLAGS
#endif
@@ -1212,7 +1400,7 @@
static inline bool cpupid_pid_unset(int cpupid)
{
- return 1;
+ return true;
}
static inline void page_cpupid_reset_last(struct page *page)
@@ -1435,6 +1623,7 @@
extern void pagefault_out_of_memory(void);
#define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK)
+#define offset_in_thp(page, p) ((unsigned long)(p) & (thp_size(page) - 1))
/*
* Flags passed to show_mem() and show_free_areas() to suppress output in
@@ -1478,8 +1667,8 @@
void free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
unsigned long end, unsigned long floor, unsigned long ceiling);
-int copy_page_range(struct mm_struct *dst, struct mm_struct *src,
- struct vm_area_struct *vma);
+int
+copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma);
int follow_invalidate_pte(struct mm_struct *mm, unsigned long address,
struct mmu_notifier_range *range, pte_t **ptepp,
pmd_t **pmdpp, spinlock_t **ptlp);
@@ -1502,8 +1691,9 @@
#ifdef CONFIG_MMU
extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma,
- unsigned long address, unsigned int flags);
-extern int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
+ unsigned long address, unsigned int flags,
+ struct pt_regs *regs);
+extern int fixup_user_fault(struct mm_struct *mm,
unsigned long address, unsigned int fault_flags,
bool *unlocked);
void unmap_mapping_page(struct page *page);
@@ -1513,14 +1703,14 @@
loff_t const holebegin, loff_t const holelen, int even_cows);
#else
static inline vm_fault_t handle_mm_fault(struct vm_area_struct *vma,
- unsigned long address, unsigned int flags)
+ unsigned long address, unsigned int flags,
+ struct pt_regs *regs)
{
/* should never happen if there's no MMU */
BUG();
return VM_FAULT_SIGBUS;
}
-static inline int fixup_user_fault(struct task_struct *tsk,
- struct mm_struct *mm, unsigned long address,
+static inline int fixup_user_fault(struct mm_struct *mm, unsigned long address,
unsigned int fault_flags, bool *unlocked)
{
/* should never happen if there's no MMU */
@@ -1547,20 +1737,33 @@
extern int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
unsigned long addr, void *buf, int len, unsigned int gup_flags);
-long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
+long get_user_pages_remote(struct mm_struct *mm,
unsigned long start, unsigned long nr_pages,
unsigned int gup_flags, struct page **pages,
struct vm_area_struct **vmas, int *locked);
+long pin_user_pages_remote(struct mm_struct *mm,
+ unsigned long start, unsigned long nr_pages,
+ unsigned int gup_flags, struct page **pages,
+ struct vm_area_struct **vmas, int *locked);
long get_user_pages(unsigned long start, unsigned long nr_pages,
unsigned int gup_flags, struct page **pages,
struct vm_area_struct **vmas);
+long pin_user_pages(unsigned long start, unsigned long nr_pages,
+ unsigned int gup_flags, struct page **pages,
+ struct vm_area_struct **vmas);
long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
unsigned int gup_flags, struct page **pages, int *locked);
+long pin_user_pages_locked(unsigned long start, unsigned long nr_pages,
+ unsigned int gup_flags, struct page **pages, int *locked);
long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
struct page **pages, unsigned int gup_flags);
+long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
+ struct page **pages, unsigned int gup_flags);
int get_user_pages_fast(unsigned long start, int nr_pages,
unsigned int gup_flags, struct page **pages);
+int pin_user_pages_fast(unsigned long start, int nr_pages,
+ unsigned int gup_flags, struct page **pages);
int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc);
int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc,
@@ -1572,7 +1775,7 @@
unsigned int nr_frames; /* Number of frames stored in ptrs array */
bool got_ref; /* Did we pin pages by getting page ref? */
bool is_pfns; /* Does array contain pages or pfns? */
- void *ptrs[0]; /* Array of pinned pfns / pages. Use
+ void *ptrs[]; /* Array of pinned pfns / pages. Use
* pfns_vector_pages() or pfns_vector_pfns()
* for access */
};
@@ -1643,9 +1846,26 @@
unsigned long old_addr, struct vm_area_struct *new_vma,
unsigned long new_addr, unsigned long len,
bool need_rmap_locks);
+
+/*
+ * Flags used by change_protection(). For now we make it a bitmap so
+ * that we can pass in multiple flags just like parameters. However
+ * for now all the callers are only use one of the flags at the same
+ * time.
+ */
+/* Whether we should allow dirty bit accounting */
+#define MM_CP_DIRTY_ACCT (1UL << 0)
+/* Whether this protection change is for NUMA hints */
+#define MM_CP_PROT_NUMA (1UL << 1)
+/* Whether this change is for write protecting */
+#define MM_CP_UFFD_WP (1UL << 2) /* do wp */
+#define MM_CP_UFFD_WP_RESOLVE (1UL << 3) /* Resolve wp */
+#define MM_CP_UFFD_WP_ALL (MM_CP_UFFD_WP | \
+ MM_CP_UFFD_WP_RESOLVE)
+
extern unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
unsigned long end, pgprot_t newprot,
- int dirty_accountable, int prot_numa);
+ unsigned long cp_flags);
extern int mprotect_fixup(struct vm_area_struct *vma,
struct vm_area_struct **pprev, unsigned long start,
unsigned long end, unsigned long newflags);
@@ -1653,8 +1873,16 @@
/*
* doesn't attempt to fault and will return short.
*/
-int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
- struct page **pages);
+int get_user_pages_fast_only(unsigned long start, int nr_pages,
+ unsigned int gup_flags, struct page **pages);
+int pin_user_pages_fast_only(unsigned long start, int nr_pages,
+ unsigned int gup_flags, struct page **pages);
+
+static inline bool get_user_page_fast_only(unsigned long addr,
+ unsigned int gup_flags, struct page **pagep)
+{
+ return get_user_pages_fast_only(addr, 1, gup_flags, pagep) == 1;
+}
/*
* per-process(per-mm_struct) statistics.
*/
@@ -1673,19 +1901,27 @@
return (unsigned long)val;
}
+void mm_trace_rss_stat(struct mm_struct *mm, int member, long count);
+
static inline void add_mm_counter(struct mm_struct *mm, int member, long value)
{
- atomic_long_add(value, &mm->rss_stat.count[member]);
+ long count = atomic_long_add_return(value, &mm->rss_stat.count[member]);
+
+ mm_trace_rss_stat(mm, member, count);
}
static inline void inc_mm_counter(struct mm_struct *mm, int member)
{
- atomic_long_inc(&mm->rss_stat.count[member]);
+ long count = atomic_long_inc_return(&mm->rss_stat.count[member]);
+
+ mm_trace_rss_stat(mm, member, count);
}
static inline void dec_mm_counter(struct mm_struct *mm, int member)
{
- atomic_long_dec(&mm->rss_stat.count[member]);
+ long count = atomic_long_dec_return(&mm->rss_stat.count[member]);
+
+ mm_trace_rss_stat(mm, member, count);
}
/* Optimized variant when page is already known not to be PageAnon */
@@ -1756,6 +1992,18 @@
}
#endif
+#ifndef CONFIG_ARCH_HAS_PTE_SPECIAL
+static inline int pte_special(pte_t pte)
+{
+ return 0;
+}
+
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+ return pte;
+}
+#endif
+
#ifndef CONFIG_ARCH_HAS_PTE_DEVMAP
static inline int pte_devmap(pte_t pte)
{
@@ -1875,13 +2123,8 @@
int __pte_alloc(struct mm_struct *mm, pmd_t *pmd);
int __pte_alloc_kernel(pmd_t *pmd);
-/*
- * The following ifdef needed to get the 4level-fixup.h header to work.
- * Remove it when 4level-fixup.h has been removed.
- */
-#if defined(CONFIG_MMU) && !defined(__ARCH_HAS_4LEVEL_HACK)
+#if defined(CONFIG_MMU)
-#ifndef __ARCH_HAS_5LEVEL_HACK
static inline p4d_t *p4d_alloc(struct mm_struct *mm, pgd_t *pgd,
unsigned long address)
{
@@ -1895,14 +2138,13 @@
return (unlikely(p4d_none(*p4d)) && __pud_alloc(mm, p4d, address)) ?
NULL : pud_offset(p4d, address);
}
-#endif /* !__ARCH_HAS_5LEVEL_HACK */
static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
{
return (unlikely(pud_none(*pud)) && __pmd_alloc(mm, pud, address))?
NULL: pmd_offset(pud, address);
}
-#endif /* CONFIG_MMU && !__ARCH_HAS_4LEVEL_HACK */
+#endif /* CONFIG_MMU */
#if USE_SPLIT_PTE_PTLOCKS
#if ALLOC_SPLIT_PTLOCKS
@@ -2030,7 +2272,7 @@
return ptlock_ptr(pmd_to_page(pmd));
}
-static inline bool pgtable_pmd_page_ctor(struct page *page)
+static inline bool pmd_ptlock_init(struct page *page)
{
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
page->pmd_huge_pte = NULL;
@@ -2038,7 +2280,7 @@
return ptlock_init(page);
}
-static inline void pgtable_pmd_page_dtor(struct page *page)
+static inline void pmd_ptlock_free(struct page *page)
{
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
VM_BUG_ON_PAGE(page->pmd_huge_pte, page);
@@ -2055,8 +2297,8 @@
return &mm->page_table_lock;
}
-static inline bool pgtable_pmd_page_ctor(struct page *page) { return true; }
-static inline void pgtable_pmd_page_dtor(struct page *page) {}
+static inline bool pmd_ptlock_init(struct page *page) { return true; }
+static inline void pmd_ptlock_free(struct page *page) {}
#define pmd_huge_pte(mm, pmd) ((mm)->pmd_huge_pte)
@@ -2069,6 +2311,22 @@
return ptl;
}
+static inline bool pgtable_pmd_page_ctor(struct page *page)
+{
+ if (!pmd_ptlock_init(page))
+ return false;
+ __SetPageTable(page);
+ inc_zone_page_state(page, NR_PAGETABLE);
+ return true;
+}
+
+static inline void pgtable_pmd_page_dtor(struct page *page)
+{
+ pmd_ptlock_free(page);
+ __ClearPageTable(page);
+ dec_zone_page_state(page, NR_PAGETABLE);
+}
+
/*
* No scalability reason to split PUD locks yet, but follow the same pattern
* as the PMD locks to make it easier if we decide to. The VM should not be
@@ -2089,9 +2347,7 @@
}
extern void __init pagecache_init(void);
-extern void free_area_init(unsigned long * zones_size);
-extern void __init free_area_init_node(int nid, unsigned long * zones_size,
- unsigned long zone_start_pfn, unsigned long *zholes_size);
+extern void __init free_area_init_memoryless_node(int nid);
extern void free_initmem(void);
/*
@@ -2161,34 +2417,23 @@
return phys_pages;
}
-#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
/*
- * With CONFIG_HAVE_MEMBLOCK_NODE_MAP set, an architecture may initialise its
- * zones, allocate the backing mem_map and account for memory holes in a more
- * architecture independent manner. This is a substitute for creating the
- * zone_sizes[] and zholes_size[] arrays and passing them to
- * free_area_init_node()
+ * Using memblock node mappings, an architecture may initialise its
+ * zones, allocate the backing mem_map and account for memory holes in an
+ * architecture independent manner.
*
* An architecture is expected to register range of page frames backed by
* physical memory with memblock_add[_node]() before calling
- * free_area_init_nodes() passing in the PFN each zone ends at. At a basic
+ * free_area_init() passing in the PFN each zone ends at. At a basic
* usage, an architecture is expected to do something like
*
* unsigned long max_zone_pfns[MAX_NR_ZONES] = {max_dma, max_normal_pfn,
* max_highmem_pfn};
* for_each_valid_physical_page_range()
* memblock_add_node(base, size, nid)
- * free_area_init_nodes(max_zone_pfns);
- *
- * free_bootmem_with_active_regions() calls free_bootmem_node() for each
- * registered physical page range. Similarly
- * sparse_memory_present_with_active_regions() calls memory_present() for
- * each range when SPARSEMEM is enabled.
- *
- * See mm/page_alloc.c for more information on each function exposed by
- * CONFIG_HAVE_MEMBLOCK_NODE_MAP.
+ * free_area_init(max_zone_pfns);
*/
-extern void free_area_init_nodes(unsigned long *max_zone_pfn);
+void free_area_init(unsigned long *max_zone_pfn);
unsigned long node_map_pfn_alignment(void);
unsigned long __absent_pages_in_range(int nid, unsigned long start_pfn,
unsigned long end_pfn);
@@ -2197,16 +2442,9 @@
extern void get_pfn_range_for_nid(unsigned int nid,
unsigned long *start_pfn, unsigned long *end_pfn);
extern unsigned long find_min_pfn_with_active_regions(void);
-extern void free_bootmem_with_active_regions(int nid,
- unsigned long max_low_pfn);
-extern void sparse_memory_present_with_active_regions(int nid);
-#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
-
-#if !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) && \
- !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID)
-static inline int __early_pfn_to_nid(unsigned long pfn,
- struct mminit_pfnnid_cache *state)
+#ifndef CONFIG_NEED_MULTIPLE_NODES
+static inline int early_pfn_to_nid(unsigned long pfn)
{
return 0;
}
@@ -2218,15 +2456,10 @@
struct mminit_pfnnid_cache *state);
#endif
-#if !defined(CONFIG_FLAT_NODE_MEM_MAP)
-void zero_resv_unavail(void);
-#else
-static inline void zero_resv_unavail(void) {}
-#endif
-
extern void set_dma_reserve(unsigned long new_dma_reserve);
-extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long,
- enum meminit_context, struct vmem_altmap *);
+extern void memmap_init_zone(unsigned long, int, unsigned long,
+ unsigned long, unsigned long, enum meminit_context,
+ struct vmem_altmap *, int migratetype);
extern void setup_per_zone_wmarks(void);
extern int __meminit init_per_zone_wmark_min(void);
extern void mem_init(void);
@@ -2244,13 +2477,11 @@
extern void setup_per_cpu_pageset(void);
-extern void zone_pcp_update(struct zone *zone);
-extern void zone_pcp_reset(struct zone *zone);
-
/* page_alloc.c */
extern int min_free_kbytes;
extern int watermark_boost_factor;
extern int watermark_scale_factor;
+extern bool arch_has_descending_max_zone_pfns(void);
/* nommu.c */
extern atomic_long_t mmap_pages_allocated;
@@ -2362,21 +2593,12 @@
struct list_head *uf);
extern unsigned long do_mmap(struct file *file, unsigned long addr,
unsigned long len, unsigned long prot, unsigned long flags,
- vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate,
- struct list_head *uf);
+ unsigned long pgoff, unsigned long *populate, struct list_head *uf);
extern int __do_munmap(struct mm_struct *, unsigned long, size_t,
struct list_head *uf, bool downgrade);
extern int do_munmap(struct mm_struct *, unsigned long, size_t,
struct list_head *uf);
-
-static inline unsigned long
-do_mmap_pgoff(struct file *file, unsigned long addr,
- unsigned long len, unsigned long prot, unsigned long flags,
- unsigned long pgoff, unsigned long *populate,
- struct list_head *uf)
-{
- return do_mmap(file, addr, len, prot, flags, 0, pgoff, populate, uf);
-}
+extern int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior);
#ifdef CONFIG_MMU
extern int __mm_populate(unsigned long addr, unsigned long len,
@@ -2408,26 +2630,7 @@
unsigned long align_offset;
};
-extern unsigned long unmapped_area(struct vm_unmapped_area_info *info);
-extern unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info);
-
-/*
- * Search for an unmapped address range.
- *
- * We are looking for a range that:
- * - does not intersect with any VMA;
- * - is contained within the [low_limit, high_limit) interval;
- * - is at least the desired size.
- * - satisfies (begin_addr & align_mask) == (align_offset & align_mask)
- */
-static inline unsigned long
-vm_unmapped_area(struct vm_unmapped_area_info *info)
-{
- if (info->flags & VM_UNMAPPED_AREA_TOPDOWN)
- return unmapped_area_topdown(info);
- else
- return unmapped_area(info);
-}
+extern unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info);
/* truncate.c */
extern void truncate_inode_pages(struct address_space *, loff_t);
@@ -2445,30 +2648,11 @@
int __must_check write_one_page(struct page *page);
void task_dirty_inc(struct task_struct *tsk);
-/* readahead.c */
-#define VM_READAHEAD_PAGES (SZ_128K / PAGE_SIZE)
-
-int force_page_cache_readahead(struct address_space *mapping, struct file *filp,
- pgoff_t offset, unsigned long nr_to_read);
-
-void page_cache_sync_readahead(struct address_space *mapping,
- struct file_ra_state *ra,
- struct file *filp,
- pgoff_t offset,
- unsigned long size);
-
-void page_cache_async_readahead(struct address_space *mapping,
- struct file_ra_state *ra,
- struct file *filp,
- struct page *pg,
- pgoff_t offset,
- unsigned long size);
-
extern unsigned long stack_guard_gap;
/* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */
extern int expand_stack(struct vm_area_struct *vma, unsigned long address);
-/* CONFIG_STACK_GROWSUP still needs to to grow downwards at some places */
+/* CONFIG_STACK_GROWSUP still needs to grow downwards at some places */
extern int expand_downwards(struct vm_area_struct *vma,
unsigned long address);
#if VM_GROWSUP
@@ -2563,6 +2747,8 @@
int remap_pfn_range(struct vm_area_struct *, unsigned long addr,
unsigned long pfn, unsigned long size, pgprot_t);
int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *);
+int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr,
+ struct page **pages, unsigned long *num);
int vm_map_pages(struct vm_area_struct *vma, struct page **pages,
unsigned long num);
int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages,
@@ -2573,6 +2759,8 @@
unsigned long pfn, pgprot_t pgprot);
vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
pfn_t pfn);
+vm_fault_t vmf_insert_mixed_prot(struct vm_area_struct *vma, unsigned long addr,
+ pfn_t pfn, pgprot_t pgprot);
vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma,
unsigned long addr, pfn_t pfn);
int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len);
@@ -2628,13 +2816,16 @@
#define FOLL_ANON 0x8000 /* don't do file mappings */
#define FOLL_LONGTERM 0x10000 /* mapping lifetime is indefinite: see below */
#define FOLL_SPLIT_PMD 0x20000 /* split huge pmd before returning */
+#define FOLL_PIN 0x40000 /* pages must be released via unpin_user_page */
+#define FOLL_FAST_ONLY 0x80000 /* gup_fast: prevent fall-back to slow gup */
/*
- * NOTE on FOLL_LONGTERM:
+ * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each
+ * other. Here is what they mean, and how to use them:
*
* FOLL_LONGTERM indicates that the page will be held for an indefinite time
- * period _often_ under userspace control. This is contrasted with
- * iov_iter_get_pages() where usages which are transient.
+ * period _often_ under userspace control. This is in contrast to
+ * iov_iter_get_pages(), whose usages are transient.
*
* FIXME: For pages which are part of a filesystem, mappings are subject to the
* lifetime enforced by the filesystem and we need guarantees that longterm
@@ -2649,11 +2840,39 @@
* Currently only get_user_pages() and get_user_pages_fast() support this flag
* and calls to get_user_pages_[un]locked are specifically not allowed. This
* is due to an incompatibility with the FS DAX check and
- * FAULT_FLAG_ALLOW_RETRY
+ * FAULT_FLAG_ALLOW_RETRY.
*
- * In the CMA case: longterm pins in a CMA region would unnecessarily fragment
- * that region. And so CMA attempts to migrate the page before pinning when
+ * In the CMA case: long term pins in a CMA region would unnecessarily fragment
+ * that region. And so, CMA attempts to migrate the page before pinning, when
* FOLL_LONGTERM is specified.
+ *
+ * FOLL_PIN indicates that a special kind of tracking (not just page->_refcount,
+ * but an additional pin counting system) will be invoked. This is intended for
+ * anything that gets a page reference and then touches page data (for example,
+ * Direct IO). This lets the filesystem know that some non-file-system entity is
+ * potentially changing the pages' data. In contrast to FOLL_GET (whose pages
+ * are released via put_page()), FOLL_PIN pages must be released, ultimately, by
+ * a call to unpin_user_page().
+ *
+ * FOLL_PIN is similar to FOLL_GET: both of these pin pages. They use different
+ * and separate refcounting mechanisms, however, and that means that each has
+ * its own acquire and release mechanisms:
+ *
+ * FOLL_GET: get_user_pages*() to acquire, and put_page() to release.
+ *
+ * FOLL_PIN: pin_user_pages*() to acquire, and unpin_user_pages to release.
+ *
+ * FOLL_PIN and FOLL_GET are mutually exclusive for a given function call.
+ * (The underlying pages may experience both FOLL_GET-based and FOLL_PIN-based
+ * calls applied to them, and that's perfectly OK. This is a constraint on the
+ * callers, not on the pages.)
+ *
+ * FOLL_PIN should be set internally by the pin_user_pages*() APIs, never
+ * directly by the caller. That's in order to help avoid mismatches when
+ * releasing pages: get_user_pages*() pages must be released via put_page(),
+ * while pin_user_pages*() pages must be released via unpin_user_page().
+ *
+ * Please see Documentation/core-api/pin_user_pages.rst for more information.
*/
static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags)
@@ -2670,7 +2889,9 @@
typedef int (*pte_fn_t)(pte_t *pte, unsigned long addr, void *data);
extern int apply_to_page_range(struct mm_struct *mm, unsigned long address,
unsigned long size, pte_fn_t fn, void *data);
-
+extern int apply_to_existing_page_range(struct mm_struct *mm,
+ unsigned long address, unsigned long size,
+ pte_fn_t fn, void *data);
#ifdef CONFIG_PAGE_POISONING
extern bool page_poisoning_enabled(void);
@@ -2774,8 +2995,8 @@
#ifdef CONFIG_SYSCTL
extern int sysctl_drop_caches;
-int drop_caches_sysctl_handler(struct ctl_table *, int,
- void __user *, size_t *, loff_t *);
+int drop_caches_sysctl_handler(struct ctl_table *, int, void *, size_t *,
+ loff_t *);
#endif
void drop_slab(void);
@@ -2803,14 +3024,15 @@
p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node);
pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node);
pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node);
-pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node);
+pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node,
+ struct vmem_altmap *altmap);
void *vmemmap_alloc_block(unsigned long size, int node);
struct vmem_altmap;
-void *vmemmap_alloc_block_buf(unsigned long size, int node);
-void *altmap_alloc_block_buf(unsigned long size, struct vmem_altmap *altmap);
+void *vmemmap_alloc_block_buf(unsigned long size, int node,
+ struct vmem_altmap *altmap);
void vmemmap_verify(pte_t *, int, unsigned long, unsigned long);
int vmemmap_populate_basepages(unsigned long start, unsigned long end,
- int node);
+ int node, struct vmem_altmap *altmap);
int vmemmap_populate(unsigned long start, unsigned long end, int node,
struct vmem_altmap *altmap);
void vmemmap_populate_print_last(void);
@@ -2829,14 +3051,13 @@
};
extern int memory_failure(unsigned long pfn, int flags);
extern void memory_failure_queue(unsigned long pfn, int flags);
+extern void memory_failure_queue_kick(int cpu);
extern int unpoison_memory(unsigned long pfn);
-extern int get_hwpoison_page(struct page *page);
-#define put_hwpoison_page(page) put_page(page)
extern int sysctl_memory_failure_early_kill;
extern int sysctl_memory_failure_recovery;
extern void shake_page(struct page *p, int access);
extern atomic_long_t num_poisoned_pages __read_mostly;
-extern int soft_offline_page(struct page *page, int flags);
+extern int soft_offline_page(unsigned long pfn, int flags);
/*
@@ -2871,6 +3092,7 @@
MF_MSG_BUDDY,
MF_MSG_BUDDY_2ND,
MF_MSG_DAX,
+ MF_MSG_UNSPLIT_THP,
MF_MSG_UNKNOWN,
};
@@ -2886,6 +3108,23 @@
const void __user *usr_src,
unsigned int pages_per_huge_page,
bool allow_pagefault);
+
+/**
+ * vma_is_special_huge - Are transhuge page-table entries considered special?
+ * @vma: Pointer to the struct vm_area_struct to consider
+ *
+ * Whether transhuge page-table entries are considered "special" following
+ * the definition in vm_normal_page().
+ *
+ * Return: true if transhuge page-table entries should be considered special,
+ * false otherwise.
+ */
+static inline bool vma_is_special_huge(const struct vm_area_struct *vma)
+{
+ return vma_is_dax(vma) || (vma->vm_file &&
+ (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)));
+}
+
#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */
#ifdef CONFIG_DEBUG_PAGEALLOC
@@ -2928,6 +3167,20 @@
return !memcmp_pages(page1, page2);
}
+#ifdef CONFIG_MAPPING_DIRTY_HELPERS
+unsigned long clean_record_shared_mapping_range(struct address_space *mapping,
+ pgoff_t first_index, pgoff_t nr,
+ pgoff_t bitmap_pgoff,
+ unsigned long *bitmap,
+ pgoff_t *start,
+ pgoff_t *end);
+
+unsigned long wp_shared_mapping_range(struct address_space *mapping,
+ pgoff_t first_index, pgoff_t nr);
+#endif
+
+extern int sysctl_nr_trim_pages;
+
/**
* seal_check_future_write - Check for F_SEAL_FUTURE_WRITE flag and handle it
* @seals: the seals to check