return NULL;
}
+struct page *
+follow_huge_pud(struct mm_struct *mm, unsigned long address,
+ pud_t *pud, int write)
+{
+ BUG();
+ return NULL;
+}
+
static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
unsigned long sz)
{
*/
pdshift = PUD_SHIFT;
pudp = pud_offset(&pgd, ea);
- pud = ACCESS_ONCE(*pudp);
+ pud = READ_ONCE(*pudp);
if (pud_none(pud))
return NULL;
else {
pdshift = PMD_SHIFT;
pmdp = pmd_offset(&pud, ea);
- pmd = ACCESS_ONCE(*pmdp);
+ pmd = READ_ONCE(*pmdp);
/*
* A hugepage collapse is captured by pmd_none, because
* it mark the pmd none and do a hpte invalidate.
static inline pte_t gup_get_pte(pte_t *ptep)
{
#ifndef CONFIG_X2TLB
- return ACCESS_ONCE(*ptep);
+ return READ_ONCE(*ptep);
#else
/*
* With get_user_pages_fast, we walk down the pagetables without
start += nr << PAGE_SHIFT;
pages += nr;
- down_read(&mm->mmap_sem);
- ret = get_user_pages(current, mm, start,
- (end - start) >> PAGE_SHIFT, write, 0, pages, NULL);
- up_read(&mm->mmap_sem);
+ ret = get_user_pages_unlocked(current, mm, start,
+ (end - start) >> PAGE_SHIFT, write, 0, pages);
/* Have to be a bit careful with return values */
if (nr > 0) {
#define PMDS_PER_MID_PAGE (P2M_MID_PER_PAGE / PTRS_PER_PTE)
-static void __init m2p_override_init(void);
-
unsigned long *xen_p2m_addr __read_mostly;
EXPORT_SYMBOL_GPL(xen_p2m_addr);
unsigned long xen_p2m_size __read_mostly;
return (void *)__get_free_page(GFP_KERNEL | __GFP_REPEAT);
}
-/* Only to be called in case of a race for a page just allocated! */
-static void free_p2m_page(void *p)
+static void __ref free_p2m_page(void *p)
{
- BUG_ON(!slab_is_available());
+ if (unlikely(!slab_is_available())) {
+ free_bootmem((unsigned long)p, PAGE_SIZE);
+ return;
+ }
+
free_page((unsigned long)p);
}
p2m_missing_pte : p2m_identity_pte;
for (i = 0; i < PMDS_PER_MID_PAGE; i++) {
pmdp = populate_extra_pmd(
- (unsigned long)(p2m + pfn + i * PTRS_PER_PTE));
+ (unsigned long)(p2m + pfn) + i * PMD_SIZE);
set_pmd(pmdp, __pmd(__pa(ptep) | _KERNPG_TABLE));
}
}
xen_p2m_size = xen_max_p2m_pfn;
xen_inv_extra_mem();
-
- m2p_override_init();
}
unsigned long get_phys_to_machine(unsigned long pfn)
* a new pmd is to replace p2m_missing_pte or p2m_identity_pte by a individual
* pmd. In case of PAE/x86-32 there are multiple pmds to allocate!
*/
-static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *ptep, pte_t *pte_pg)
+static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *pte_pg)
{
pte_t *ptechk;
- pte_t *pteret = ptep;
pte_t *pte_newpg[PMDS_PER_MID_PAGE];
pmd_t *pmdp;
unsigned int level;
if (ptechk == pte_pg) {
set_pmd(pmdp,
__pmd(__pa(pte_newpg[i]) | _KERNPG_TABLE));
- if (vaddr == (addr & ~(PMD_SIZE - 1)))
- pteret = pte_offset_kernel(pmdp, addr);
pte_newpg[i] = NULL;
}
vaddr += PMD_SIZE;
}
- return pteret;
+ return lookup_address(addr, &level);
}
/*
if (pte_pg == p2m_missing_pte || pte_pg == p2m_identity_pte) {
/* PMD level is missing, allocate a new one */
- ptep = alloc_p2m_pmd(addr, ptep, pte_pg);
+ ptep = alloc_p2m_pmd(addr, pte_pg);
if (!ptep)
return false;
}
mid_mfn = NULL;
}
- p2m_pfn = pte_pfn(ACCESS_ONCE(*ptep));
+ p2m_pfn = pte_pfn(READ_ONCE(*ptep));
if (p2m_pfn == PFN_DOWN(__pa(p2m_identity)) ||
p2m_pfn == PFN_DOWN(__pa(p2m_missing))) {
/* p2m leaf page is missing */
return true;
}
-#define M2P_OVERRIDE_HASH_SHIFT 10
-#define M2P_OVERRIDE_HASH (1 << M2P_OVERRIDE_HASH_SHIFT)
-
-static struct list_head *m2p_overrides;
-static DEFINE_SPINLOCK(m2p_override_lock);
-
-static void __init m2p_override_init(void)
-{
- unsigned i;
-
- m2p_overrides = alloc_bootmem_align(
- sizeof(*m2p_overrides) * M2P_OVERRIDE_HASH,
- sizeof(unsigned long));
-
- for (i = 0; i < M2P_OVERRIDE_HASH; i++)
- INIT_LIST_HEAD(&m2p_overrides[i]);
-}
-
-static unsigned long mfn_hash(unsigned long mfn)
-{
- return hash_long(mfn, M2P_OVERRIDE_HASH_SHIFT);
-}
-
-/* Add an MFN override for a particular page */
-static int m2p_add_override(unsigned long mfn, struct page *page,
- struct gnttab_map_grant_ref *kmap_op)
-{
- unsigned long flags;
- unsigned long pfn;
- unsigned long uninitialized_var(address);
- unsigned level;
- pte_t *ptep = NULL;
-
- pfn = page_to_pfn(page);
- if (!PageHighMem(page)) {
- address = (unsigned long)__va(pfn << PAGE_SHIFT);
- ptep = lookup_address(address, &level);
- if (WARN(ptep == NULL || level != PG_LEVEL_4K,
- "m2p_add_override: pfn %lx not mapped", pfn))
- return -EINVAL;
- }
-
- if (kmap_op != NULL) {
- if (!PageHighMem(page)) {
- struct multicall_space mcs =
- xen_mc_entry(sizeof(*kmap_op));
-
- MULTI_grant_table_op(mcs.mc,
- GNTTABOP_map_grant_ref, kmap_op, 1);
-
- xen_mc_issue(PARAVIRT_LAZY_MMU);
- }
- }
- spin_lock_irqsave(&m2p_override_lock, flags);
- list_add(&page->lru, &m2p_overrides[mfn_hash(mfn)]);
- spin_unlock_irqrestore(&m2p_override_lock, flags);
-
- /* p2m(m2p(mfn)) == mfn: the mfn is already present somewhere in
- * this domain. Set the FOREIGN_FRAME_BIT in the p2m for the other
- * pfn so that the following mfn_to_pfn(mfn) calls will return the
- * pfn from the m2p_override (the backend pfn) instead.
- * We need to do this because the pages shared by the frontend
- * (xen-blkfront) can be already locked (lock_page, called by
- * do_read_cache_page); when the userspace backend tries to use them
- * with direct_IO, mfn_to_pfn returns the pfn of the frontend, so
- * do_blockdev_direct_IO is going to try to lock the same pages
- * again resulting in a deadlock.
- * As a side effect get_user_pages_fast might not be safe on the
- * frontend pages while they are being shared with the backend,
- * because mfn_to_pfn (that ends up being called by GUPF) will
- * return the backend pfn rather than the frontend pfn. */
- pfn = mfn_to_pfn_no_overrides(mfn);
- if (__pfn_to_mfn(pfn) == mfn)
- set_phys_to_machine(pfn, FOREIGN_FRAME(mfn));
-
- return 0;
-}
-
int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
struct gnttab_map_grant_ref *kmap_ops,
struct page **pages, unsigned int count)
{
int i, ret = 0;
- bool lazy = false;
pte_t *pte;
if (xen_feature(XENFEAT_auto_translated_physmap))
return 0;
- if (kmap_ops &&
- !in_interrupt() &&
- paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
- arch_enter_lazy_mmu_mode();
- lazy = true;
+ if (kmap_ops) {
+ ret = HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref,
+ kmap_ops, count);
+ if (ret)
+ goto out;
}
for (i = 0; i < count; i++) {
}
pfn = page_to_pfn(pages[i]);
- WARN_ON(PagePrivate(pages[i]));
- SetPagePrivate(pages[i]);
- set_page_private(pages[i], mfn);
- pages[i]->index = pfn_to_mfn(pfn);
+ WARN(pfn_to_mfn(pfn) != INVALID_P2M_ENTRY, "page must be ballooned");
if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)))) {
ret = -ENOMEM;
goto out;
}
-
- if (kmap_ops) {
- ret = m2p_add_override(mfn, pages[i], &kmap_ops[i]);
- if (ret)
- goto out;
- }
}
out:
- if (lazy)
- arch_leave_lazy_mmu_mode();
-
return ret;
}
EXPORT_SYMBOL_GPL(set_foreign_p2m_mapping);
-static struct page *m2p_find_override(unsigned long mfn)
-{
- unsigned long flags;
- struct list_head *bucket;
- struct page *p, *ret;
-
- if (unlikely(!m2p_overrides))
- return NULL;
-
- ret = NULL;
- bucket = &m2p_overrides[mfn_hash(mfn)];
-
- spin_lock_irqsave(&m2p_override_lock, flags);
-
- list_for_each_entry(p, bucket, lru) {
- if (page_private(p) == mfn) {
- ret = p;
- break;
- }
- }
-
- spin_unlock_irqrestore(&m2p_override_lock, flags);
-
- return ret;
-}
-
-static int m2p_remove_override(struct page *page,
- struct gnttab_map_grant_ref *kmap_op,
- unsigned long mfn)
-{
- unsigned long flags;
- unsigned long pfn;
- unsigned long uninitialized_var(address);
- unsigned level;
- pte_t *ptep = NULL;
-
- pfn = page_to_pfn(page);
-
- if (!PageHighMem(page)) {
- address = (unsigned long)__va(pfn << PAGE_SHIFT);
- ptep = lookup_address(address, &level);
-
- if (WARN(ptep == NULL || level != PG_LEVEL_4K,
- "m2p_remove_override: pfn %lx not mapped", pfn))
- return -EINVAL;
- }
-
- spin_lock_irqsave(&m2p_override_lock, flags);
- list_del(&page->lru);
- spin_unlock_irqrestore(&m2p_override_lock, flags);
-
- if (kmap_op != NULL) {
- if (!PageHighMem(page)) {
- struct multicall_space mcs;
- struct gnttab_unmap_and_replace *unmap_op;
- struct page *scratch_page = get_balloon_scratch_page();
- unsigned long scratch_page_address = (unsigned long)
- __va(page_to_pfn(scratch_page) << PAGE_SHIFT);
-
- /*
- * It might be that we queued all the m2p grant table
- * hypercalls in a multicall, then m2p_remove_override
- * get called before the multicall has actually been
- * issued. In this case handle is going to -1 because
- * it hasn't been modified yet.
- */
- if (kmap_op->handle == -1)
- xen_mc_flush();
- /*
- * Now if kmap_op->handle is negative it means that the
- * hypercall actually returned an error.
- */
- if (kmap_op->handle == GNTST_general_error) {
- pr_warn("m2p_remove_override: pfn %lx mfn %lx, failed to modify kernel mappings",
- pfn, mfn);
- put_balloon_scratch_page();
- return -1;
- }
-
- xen_mc_batch();
-
- mcs = __xen_mc_entry(
- sizeof(struct gnttab_unmap_and_replace));
- unmap_op = mcs.args;
- unmap_op->host_addr = kmap_op->host_addr;
- unmap_op->new_addr = scratch_page_address;
- unmap_op->handle = kmap_op->handle;
-
- MULTI_grant_table_op(mcs.mc,
- GNTTABOP_unmap_and_replace, unmap_op, 1);
-
- mcs = __xen_mc_entry(0);
- MULTI_update_va_mapping(mcs.mc, scratch_page_address,
- pfn_pte(page_to_pfn(scratch_page),
- PAGE_KERNEL_RO), 0);
-
- xen_mc_issue(PARAVIRT_LAZY_MMU);
-
- kmap_op->host_addr = 0;
- put_balloon_scratch_page();
- }
- }
-
- /* p2m(m2p(mfn)) == FOREIGN_FRAME(mfn): the mfn is already present
- * somewhere in this domain, even before being added to the
- * m2p_override (see comment above in m2p_add_override).
- * If there are no other entries in the m2p_override corresponding
- * to this mfn, then remove the FOREIGN_FRAME_BIT from the p2m for
- * the original pfn (the one shared by the frontend): the backend
- * cannot do any IO on this page anymore because it has been
- * unshared. Removing the FOREIGN_FRAME_BIT from the p2m entry of
- * the original pfn causes mfn_to_pfn(mfn) to return the frontend
- * pfn again. */
- mfn &= ~FOREIGN_FRAME_BIT;
- pfn = mfn_to_pfn_no_overrides(mfn);
- if (__pfn_to_mfn(pfn) == FOREIGN_FRAME(mfn) &&
- m2p_find_override(mfn) == NULL)
- set_phys_to_machine(pfn, mfn);
-
- return 0;
-}
-
int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
- struct gnttab_map_grant_ref *kmap_ops,
+ struct gnttab_unmap_grant_ref *kunmap_ops,
struct page **pages, unsigned int count)
{
int i, ret = 0;
- bool lazy = false;
if (xen_feature(XENFEAT_auto_translated_physmap))
return 0;
- if (kmap_ops &&
- !in_interrupt() &&
- paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
- arch_enter_lazy_mmu_mode();
- lazy = true;
- }
-
for (i = 0; i < count; i++) {
unsigned long mfn = __pfn_to_mfn(page_to_pfn(pages[i]));
unsigned long pfn = page_to_pfn(pages[i]);
goto out;
}
- set_page_private(pages[i], INVALID_P2M_ENTRY);
- WARN_ON(!PagePrivate(pages[i]));
- ClearPagePrivate(pages[i]);
- set_phys_to_machine(pfn, pages[i]->index);
-
- if (kmap_ops)
- ret = m2p_remove_override(pages[i], &kmap_ops[i], mfn);
- if (ret)
- goto out;
+ set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
}
-
+ if (kunmap_ops)
+ ret = HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref,
+ kunmap_ops, count);
out:
- if (lazy)
- arch_leave_lazy_mmu_mode();
return ret;
}
EXPORT_SYMBOL_GPL(clear_foreign_p2m_mapping);
-unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn)
-{
- struct page *p = m2p_find_override(mfn);
- unsigned long ret = pfn;
-
- if (p)
- ret = page_to_pfn(p);
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(m2p_find_override_pfn);
-
#ifdef CONFIG_XEN_DEBUG_FS
#include <linux/debugfs.h>
#include "debugfs.h"
#include <linux/compiler-gcc.h>
#endif
+#ifdef CC_USING_HOTPATCH
+#define notrace __attribute__((hotpatch(0,0)))
+#else
#define notrace __attribute__((no_instrument_function))
+#endif
/* Intel compiler defines __GNUC__. So we will overwrite implementations
* coming from above header files here
}
}
-static __always_inline void __assign_once_size(volatile void *p, void *res, int size)
+static __always_inline void __write_once_size(volatile void *p, void *res, int size)
{
switch (size) {
case 1: *(volatile __u8 *)p = *(__u8 *)res; break;
/*
* Prevent the compiler from merging or refetching reads or writes. The
* compiler is also forbidden from reordering successive instances of
- * READ_ONCE, ASSIGN_ONCE and ACCESS_ONCE (see below), but only when the
+ * READ_ONCE, WRITE_ONCE and ACCESS_ONCE (see below), but only when the
* compiler is aware of some particular ordering. One way to make the
* compiler aware of ordering is to put the two invocations of READ_ONCE,
- * ASSIGN_ONCE or ACCESS_ONCE() in different C statements.
+ * WRITE_ONCE or ACCESS_ONCE() in different C statements.
*
* In contrast to ACCESS_ONCE these two macros will also work on aggregate
* data types like structs or unions. If the size of the accessed data
* type exceeds the word size of the machine (e.g., 32 bits or 64 bits)
- * READ_ONCE() and ASSIGN_ONCE() will fall back to memcpy and print a
+ * READ_ONCE() and WRITE_ONCE() will fall back to memcpy and print a
* compile-time warning.
*
* Their two major use cases are: (1) Mediating communication between
#define READ_ONCE(x) \
({ typeof(x) __val; __read_once_size(&x, &__val, sizeof(__val)); __val; })
-#define ASSIGN_ONCE(val, x) \
- ({ typeof(x) __val; __val = val; __assign_once_size(&x, &__val, sizeof(__val)); __val; })
+#define WRITE_ONCE(x, val) \
+ ({ typeof(x) __val; __val = val; __write_once_size(&x, &__val, sizeof(__val)); __val; })
#endif /* __KERNEL__ */
/* Is this type a native word size -- useful for atomic operations */
#ifndef __native_word
-# define __native_word(t) (sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long))
+# define __native_word(t) (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long))
#endif
/* Compile time object size, -1 for unknown */
* to make the compiler aware of ordering is to put the two invocations of
* ACCESS_ONCE() in different C statements.
*
- * This macro does absolutely -nothing- to prevent the CPU from reordering,
- * merging, or refetching absolutely anything at any time. Its main intended
- * use is to mediate communication between process-level code and irq/NMI
- * handlers, all running on the same CPU.
+ * ACCESS_ONCE will only work on scalar types. For union types, ACCESS_ONCE
+ * on a union member will work as long as the size of the member matches the
+ * size of the union and the size is smaller than word size.
+ *
+ * The major use cases of ACCESS_ONCE used to be (1) Mediating communication
+ * between process-level code and irq/NMI handlers, all running on the same CPU,
+ * and (2) Ensuring that the compiler does not fold, spindle, or otherwise
+ * mutilate accesses that either do not require ordering or that interact
+ * with an explicit memory barrier or atomic instruction that provides the
+ * required ordering.
+ *
+ * If possible use READ_ONCE/ASSIGN_ONCE instead.
*/
- #define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x))
+ #define __ACCESS_ONCE(x) ({ \
+ __maybe_unused typeof(x) __var = (__force typeof(x)) 0; \
+ (volatile typeof(x) *)&(x); })
+ #define ACCESS_ONCE(x) (*__ACCESS_ONCE(x))
/* Ignore/forbid kprobes attach on very low level functions marked by this attribute: */
#ifdef CONFIG_KPROBES
*/
if (likely(!(flags & FOLL_MIGRATION)))
goto no_page;
- if (pte_none(pte) || pte_file(pte))
+ if (pte_none(pte))
goto no_page;
entry = pte_to_swp_entry(pte);
if (!is_migration_entry(entry))
migration_entry_wait(mm, pmd, address);
goto retry;
}
- if ((flags & FOLL_NUMA) && pte_numa(pte))
+ if ((flags & FOLL_NUMA) && pte_protnone(pte))
goto no_page;
if ((flags & FOLL_WRITE) && !pte_write(pte)) {
pte_unmap_unlock(ptep, ptl);
if (pud_none(*pud))
return no_page_table(vma, flags);
if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) {
- if (flags & FOLL_GET)
- return NULL;
- page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE);
- return page;
+ page = follow_huge_pud(mm, address, pud, flags);
+ if (page)
+ return page;
+ return no_page_table(vma, flags);
}
if (unlikely(pud_bad(*pud)))
return no_page_table(vma, flags);
if (pmd_none(*pmd))
return no_page_table(vma, flags);
if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) {
- page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE);
- if (flags & FOLL_GET) {
- /*
- * Refcount on tail pages are not well-defined and
- * shouldn't be taken. The caller should handle a NULL
- * return when trying to follow tail pages.
- */
- if (PageHead(page))
- get_page(page);
- else
- page = NULL;
- }
- return page;
+ page = follow_huge_pmd(mm, address, pmd, flags);
+ if (page)
+ return page;
+ return no_page_table(vma, flags);
}
- if ((flags & FOLL_NUMA) && pmd_numa(*pmd))
+ if ((flags & FOLL_NUMA) && pmd_protnone(*pmd))
return no_page_table(vma, flags);
if (pmd_trans_huge(*pmd)) {
if (flags & FOLL_SPLIT) {
return -ENOMEM;
if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE))
return *flags & FOLL_HWPOISON ? -EHWPOISON : -EFAULT;
- if (ret & VM_FAULT_SIGBUS)
+ if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV))
return -EFAULT;
BUG();
}
return -ENOMEM;
if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE))
return -EHWPOISON;
- if (ret & VM_FAULT_SIGBUS)
+ if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV))
return -EFAULT;
BUG();
}
return 0;
}
+static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
+ struct mm_struct *mm,
+ unsigned long start,
+ unsigned long nr_pages,
+ int write, int force,
+ struct page **pages,
+ struct vm_area_struct **vmas,
+ int *locked, bool notify_drop,
+ unsigned int flags)
+{
+ long ret, pages_done;
+ bool lock_dropped;
+
+ if (locked) {
+ /* if VM_FAULT_RETRY can be returned, vmas become invalid */
+ BUG_ON(vmas);
+ /* check caller initialized locked */
+ BUG_ON(*locked != 1);
+ }
+
+ if (pages)
+ flags |= FOLL_GET;
+ if (write)
+ flags |= FOLL_WRITE;
+ if (force)
+ flags |= FOLL_FORCE;
+
+ pages_done = 0;
+ lock_dropped = false;
+ for (;;) {
+ ret = __get_user_pages(tsk, mm, start, nr_pages, flags, pages,
+ vmas, locked);
+ if (!locked)
+ /* VM_FAULT_RETRY couldn't trigger, bypass */
+ return ret;
+
+ /* VM_FAULT_RETRY cannot return errors */
+ if (!*locked) {
+ BUG_ON(ret < 0);
+ BUG_ON(ret >= nr_pages);
+ }
+
+ if (!pages)
+ /* If it's a prefault don't insist harder */
+ return ret;
+
+ if (ret > 0) {
+ nr_pages -= ret;
+ pages_done += ret;
+ if (!nr_pages)
+ break;
+ }
+ if (*locked) {
+ /* VM_FAULT_RETRY didn't trigger */
+ if (!pages_done)
+ pages_done = ret;
+ break;
+ }
+ /* VM_FAULT_RETRY triggered, so seek to the faulting offset */
+ pages += ret;
+ start += ret << PAGE_SHIFT;
+
+ /*
+ * Repeat on the address that fired VM_FAULT_RETRY
+ * without FAULT_FLAG_ALLOW_RETRY but with
+ * FAULT_FLAG_TRIED.
+ */
+ *locked = 1;
+ lock_dropped = true;
+ down_read(&mm->mmap_sem);
+ ret = __get_user_pages(tsk, mm, start, 1, flags | FOLL_TRIED,
+ pages, NULL, NULL);
+ if (ret != 1) {
+ BUG_ON(ret > 1);
+ if (!pages_done)
+ pages_done = ret;
+ break;
+ }
+ nr_pages--;
+ pages_done++;
+ if (!nr_pages)
+ break;
+ pages++;
+ start += PAGE_SIZE;
+ }
+ if (notify_drop && lock_dropped && *locked) {
+ /*
+ * We must let the caller know we temporarily dropped the lock
+ * and so the critical section protected by it was lost.
+ */
+ up_read(&mm->mmap_sem);
+ *locked = 0;
+ }
+ return pages_done;
+}
+
+/*
+ * We can leverage the VM_FAULT_RETRY functionality in the page fault
+ * paths better by using either get_user_pages_locked() or
+ * get_user_pages_unlocked().
+ *
+ * get_user_pages_locked() is suitable to replace the form:
+ *
+ * down_read(&mm->mmap_sem);
+ * do_something()
+ * get_user_pages(tsk, mm, ..., pages, NULL);
+ * up_read(&mm->mmap_sem);
+ *
+ * to:
+ *
+ * int locked = 1;
+ * down_read(&mm->mmap_sem);
+ * do_something()
+ * get_user_pages_locked(tsk, mm, ..., pages, &locked);
+ * if (locked)
+ * up_read(&mm->mmap_sem);
+ */
+long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm,
+ unsigned long start, unsigned long nr_pages,
+ int write, int force, struct page **pages,
+ int *locked)
+{
+ return __get_user_pages_locked(tsk, mm, start, nr_pages, write, force,
+ pages, NULL, locked, true, FOLL_TOUCH);
+}
+EXPORT_SYMBOL(get_user_pages_locked);
+
+/*
+ * Same as get_user_pages_unlocked(...., FOLL_TOUCH) but it allows to
+ * pass additional gup_flags as last parameter (like FOLL_HWPOISON).
+ *
+ * NOTE: here FOLL_TOUCH is not set implicitly and must be set by the
+ * caller if required (just like with __get_user_pages). "FOLL_GET",
+ * "FOLL_WRITE" and "FOLL_FORCE" are set implicitly as needed
+ * according to the parameters "pages", "write", "force"
+ * respectively.
+ */
+__always_inline long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
+ unsigned long start, unsigned long nr_pages,
+ int write, int force, struct page **pages,
+ unsigned int gup_flags)
+{
+ long ret;
+ int locked = 1;
+ down_read(&mm->mmap_sem);
+ ret = __get_user_pages_locked(tsk, mm, start, nr_pages, write, force,
+ pages, NULL, &locked, false, gup_flags);
+ if (locked)
+ up_read(&mm->mmap_sem);
+ return ret;
+}
+EXPORT_SYMBOL(__get_user_pages_unlocked);
+
+/*
+ * get_user_pages_unlocked() is suitable to replace the form:
+ *
+ * down_read(&mm->mmap_sem);
+ * get_user_pages(tsk, mm, ..., pages, NULL);
+ * up_read(&mm->mmap_sem);
+ *
+ * with:
+ *
+ * get_user_pages_unlocked(tsk, mm, ..., pages);
+ *
+ * It is functionally equivalent to get_user_pages_fast so
+ * get_user_pages_fast should be used instead, if the two parameters
+ * "tsk" and "mm" are respectively equal to current and current->mm,
+ * or if "force" shall be set to 1 (get_user_pages_fast misses the
+ * "force" parameter).
+ */
+long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
+ unsigned long start, unsigned long nr_pages,
+ int write, int force, struct page **pages)
+{
+ return __get_user_pages_unlocked(tsk, mm, start, nr_pages, write,
+ force, pages, FOLL_TOUCH);
+}
+EXPORT_SYMBOL(get_user_pages_unlocked);
+
/*
* get_user_pages() - pin user pages in memory
* @tsk: the task_struct to use for page fault accounting, or
* use the correct cache flushing APIs.
*
* See also get_user_pages_fast, for performance critical applications.
+ *
+ * get_user_pages should be phased out in favor of
+ * get_user_pages_locked|unlocked or get_user_pages_fast. Nothing
+ * should use get_user_pages because it cannot pass
+ * FAULT_FLAG_ALLOW_RETRY to handle_mm_fault.
*/
long get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
unsigned long start, unsigned long nr_pages, int write,
int force, struct page **pages, struct vm_area_struct **vmas)
{
- int flags = FOLL_TOUCH;
-
- if (pages)
- flags |= FOLL_GET;
- if (write)
- flags |= FOLL_WRITE;
- if (force)
- flags |= FOLL_FORCE;
-
- return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas,
- NULL);
+ return __get_user_pages_locked(tsk, mm, start, nr_pages, write, force,
+ pages, vmas, NULL, false, FOLL_TOUCH);
}
EXPORT_SYMBOL(get_user_pages);
/*
* Similar to the PMD case below, NUMA hinting must take slow
- * path
+ * path using the pte_protnone check.
*/
if (!pte_present(pte) || pte_special(pte) ||
- pte_numa(pte) || (write && !pte_write(pte)))
+ pte_protnone(pte) || (write && !pte_write(pte)))
goto pte_unmap;
VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
pmdp = pmd_offset(&pud, addr);
do {
- pmd_t pmd = ACCESS_ONCE(*pmdp);
+ pmd_t pmd = READ_ONCE(*pmdp);
next = pmd_addr_end(addr, end);
if (pmd_none(pmd) || pmd_trans_splitting(pmd))
* slowpath for accounting purposes and so that they
* can be serialised against THP migration.
*/
- if (pmd_numa(pmd))
+ if (pmd_protnone(pmd))
return 0;
if (!gup_huge_pmd(pmd, pmdp, addr, next, write,
start += nr << PAGE_SHIFT;
pages += nr;
- down_read(&mm->mmap_sem);
- ret = get_user_pages(current, mm, start,
- nr_pages - nr, write, 0, pages, NULL);
- up_read(&mm->mmap_sem);
+ ret = get_user_pages_unlocked(current, mm, start,
+ nr_pages - nr, write, 0, pages);
/* Have to be a bit careful with return values */
if (nr > 0) {