From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:20:52 +0000
Subject: [PATCH] add new system file
---
kernel/mm/gup.c | 2378 +++++++++++++++++++++++++++++++++++++++++++----------------
1 files changed, 1,727 insertions(+), 651 deletions(-)
diff --git a/kernel/mm/gup.c b/kernel/mm/gup.c
index 216253a..86ce78f 100644
--- a/kernel/mm/gup.c
+++ b/kernel/mm/gup.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/err.h>
@@ -13,13 +14,363 @@
#include <linux/sched/signal.h>
#include <linux/rwsem.h>
#include <linux/hugetlb.h>
+#include <linux/migrate.h>
+#include <linux/mm_inline.h>
+#include <linux/sched/mm.h>
+
+#include <linux/page_pinner.h>
#include <asm/mmu_context.h>
-#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include "internal.h"
+struct follow_page_context {
+ struct dev_pagemap *pgmap;
+ unsigned int page_mask;
+};
+
+static void hpage_pincount_add(struct page *page, int refs)
+{
+ VM_BUG_ON_PAGE(!hpage_pincount_available(page), page);
+ VM_BUG_ON_PAGE(page != compound_head(page), page);
+
+ atomic_add(refs, compound_pincount_ptr(page));
+}
+
+static void hpage_pincount_sub(struct page *page, int refs)
+{
+ VM_BUG_ON_PAGE(!hpage_pincount_available(page), page);
+ VM_BUG_ON_PAGE(page != compound_head(page), page);
+
+ atomic_sub(refs, compound_pincount_ptr(page));
+}
+
+/* Equivalent to calling put_page() @refs times. */
+static void put_page_refs(struct page *page, int refs)
+{
+#ifdef CONFIG_DEBUG_VM
+ if (VM_WARN_ON_ONCE_PAGE(page_ref_count(page) < refs, page))
+ return;
+#endif
+
+ /*
+ * Calling put_page() for each ref is unnecessarily slow. Only the last
+ * ref needs a put_page().
+ */
+ if (refs > 1)
+ page_ref_sub(page, refs - 1);
+ put_page(page);
+}
+
+/*
+ * Return the compound head page with ref appropriately incremented,
+ * or NULL if that failed.
+ */
+static inline struct page *try_get_compound_head(struct page *page, int refs)
+{
+ struct page *head = compound_head(page);
+
+ if (WARN_ON_ONCE(page_ref_count(head) < 0))
+ return NULL;
+ if (unlikely(!page_cache_add_speculative(head, refs)))
+ return NULL;
+
+ /*
+ * At this point we have a stable reference to the head page; but it
+ * could be that between the compound_head() lookup and the refcount
+ * increment, the compound page was split, in which case we'd end up
+ * holding a reference on a page that has nothing to do with the page
+ * we were given anymore.
+ * So now that the head page is stable, recheck that the pages still
+ * belong together.
+ */
+ if (unlikely(compound_head(page) != head)) {
+ put_page_refs(head, refs);
+ return NULL;
+ }
+
+ return head;
+}
+
+/*
+ * try_grab_compound_head() - attempt to elevate a page's refcount, by a
+ * flags-dependent amount.
+ *
+ * "grab" names in this file mean, "look at flags to decide whether to use
+ * FOLL_PIN or FOLL_GET behavior, when incrementing the page's refcount.
+ *
+ * Either FOLL_PIN or FOLL_GET (or neither) must be set, but not both at the
+ * same time. (That's true throughout the get_user_pages*() and
+ * pin_user_pages*() APIs.) Cases:
+ *
+ * FOLL_GET: page's refcount will be incremented by 1.
+ * FOLL_PIN: page's refcount will be incremented by GUP_PIN_COUNTING_BIAS.
+ *
+ * Return: head page (with refcount appropriately incremented) for success, or
+ * NULL upon failure. If neither FOLL_GET nor FOLL_PIN was set, that's
+ * considered failure, and furthermore, a likely bug in the caller, so a warning
+ * is also emitted.
+ */
+static __maybe_unused struct page *try_grab_compound_head(struct page *page,
+ int refs,
+ unsigned int flags)
+{
+ if (flags & FOLL_GET) {
+ struct page *head = try_get_compound_head(page, refs);
+ if (head)
+ set_page_pinner(head, compound_order(head));
+ return head;
+ } else if (flags & FOLL_PIN) {
+ int orig_refs = refs;
+
+ /*
+ * Can't do FOLL_LONGTERM + FOLL_PIN with CMA in the gup fast
+ * path, so fail and let the caller fall back to the slow path.
+ */
+ if (unlikely(flags & FOLL_LONGTERM) &&
+ is_migrate_cma_page(page))
+ return NULL;
+
+ /*
+ * CAUTION: Don't use compound_head() on the page before this
+ * point, the result won't be stable.
+ */
+ page = try_get_compound_head(page, refs);
+ if (!page)
+ return NULL;
+
+ /*
+ * When pinning a compound page of order > 1 (which is what
+ * hpage_pincount_available() checks for), use an exact count to
+ * track it, via hpage_pincount_add/_sub().
+ *
+ * However, be sure to *also* increment the normal page refcount
+ * field at least once, so that the page really is pinned.
+ */
+ if (hpage_pincount_available(page))
+ hpage_pincount_add(page, refs);
+ else
+ page_ref_add(page, refs * (GUP_PIN_COUNTING_BIAS - 1));
+
+ mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_ACQUIRED,
+ orig_refs);
+
+ return page;
+ }
+
+ WARN_ON_ONCE(1);
+ return NULL;
+}
+
+static void put_compound_head(struct page *page, int refs, unsigned int flags)
+{
+ if (flags & FOLL_PIN) {
+ mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_RELEASED,
+ refs);
+
+ if (hpage_pincount_available(page))
+ hpage_pincount_sub(page, refs);
+ else
+ refs *= GUP_PIN_COUNTING_BIAS;
+ }
+
+ if (flags & FOLL_GET)
+ reset_page_pinner(page, compound_order(page));
+ put_page_refs(page, refs);
+}
+
+/**
+ * try_grab_page() - elevate a page's refcount by a flag-dependent amount
+ *
+ * This might not do anything at all, depending on the flags argument.
+ *
+ * "grab" names in this file mean, "look at flags to decide whether to use
+ * FOLL_PIN or FOLL_GET behavior, when incrementing the page's refcount.
+ *
+ * @page: pointer to page to be grabbed
+ * @flags: gup flags: these are the FOLL_* flag values.
+ *
+ * Either FOLL_PIN or FOLL_GET (or neither) may be set, but not both at the same
+ * time. Cases:
+ *
+ * FOLL_GET: page's refcount will be incremented by 1.
+ * FOLL_PIN: page's refcount will be incremented by GUP_PIN_COUNTING_BIAS.
+ *
+ * Return: true for success, or if no action was required (if neither FOLL_PIN
+ * nor FOLL_GET was set, nothing is done). False for failure: FOLL_GET or
+ * FOLL_PIN was set, but the page could not be grabbed.
+ */
+bool __must_check try_grab_page(struct page *page, unsigned int flags)
+{
+ WARN_ON_ONCE((flags & (FOLL_GET | FOLL_PIN)) == (FOLL_GET | FOLL_PIN));
+
+ if (flags & FOLL_GET) {
+ bool ret = try_get_page(page);
+
+ if (ret) {
+ page = compound_head(page);
+ set_page_pinner(page, compound_order(page));
+ }
+ return ret;
+ } else if (flags & FOLL_PIN) {
+ int refs = 1;
+
+ page = compound_head(page);
+
+ if (WARN_ON_ONCE(page_ref_count(page) <= 0))
+ return false;
+
+ if (hpage_pincount_available(page))
+ hpage_pincount_add(page, 1);
+ else
+ refs = GUP_PIN_COUNTING_BIAS;
+
+ /*
+ * Similar to try_grab_compound_head(): even if using the
+ * hpage_pincount_add/_sub() routines, be sure to
+ * *also* increment the normal page refcount field at least
+ * once, so that the page really is pinned.
+ */
+ page_ref_add(page, refs);
+
+ mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_ACQUIRED, 1);
+ }
+
+ return true;
+}
+
+/**
+ * unpin_user_page() - release a dma-pinned page
+ * @page: pointer to page to be released
+ *
+ * Pages that were pinned via pin_user_pages*() must be released via either
+ * unpin_user_page(), or one of the unpin_user_pages*() routines. This is so
+ * that such pages can be separately tracked and uniquely handled. In
+ * particular, interactions with RDMA and filesystems need special handling.
+ */
+void unpin_user_page(struct page *page)
+{
+ put_compound_head(compound_head(page), 1, FOLL_PIN);
+}
+EXPORT_SYMBOL(unpin_user_page);
+
+/*
+ * put_user_page() - release a page obtained using get_user_pages() or
+ * follow_page(FOLL_GET)
+ * @page: pointer to page to be released
+ *
+ * Pages that were obtained via get_user_pages()/follow_page(FOLL_GET) must be
+ * released via put_user_page.
+ * note: If it's not a page from GUP or follow_page(FOLL_GET), it's harmless.
+ */
+void put_user_page(struct page *page)
+{
+ struct page *head = compound_head(page);
+
+ reset_page_pinner(head, compound_order(head));
+ put_page(page);
+}
+EXPORT_SYMBOL(put_user_page);
+
+/**
+ * unpin_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages
+ * @pages: array of pages to be maybe marked dirty, and definitely released.
+ * @npages: number of pages in the @pages array.
+ * @make_dirty: whether to mark the pages dirty
+ *
+ * "gup-pinned page" refers to a page that has had one of the get_user_pages()
+ * variants called on that page.
+ *
+ * For each page in the @pages array, make that page (or its head page, if a
+ * compound page) dirty, if @make_dirty is true, and if the page was previously
+ * listed as clean. In any case, releases all pages using unpin_user_page(),
+ * possibly via unpin_user_pages(), for the non-dirty case.
+ *
+ * Please see the unpin_user_page() documentation for details.
+ *
+ * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is
+ * required, then the caller should a) verify that this is really correct,
+ * because _lock() is usually required, and b) hand code it:
+ * set_page_dirty_lock(), unpin_user_page().
+ *
+ */
+void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages,
+ bool make_dirty)
+{
+ unsigned long index;
+
+ /*
+ * TODO: this can be optimized for huge pages: if a series of pages is
+ * physically contiguous and part of the same compound page, then a
+ * single operation to the head page should suffice.
+ */
+
+ if (!make_dirty) {
+ unpin_user_pages(pages, npages);
+ return;
+ }
+
+ for (index = 0; index < npages; index++) {
+ struct page *page = compound_head(pages[index]);
+ /*
+ * Checking PageDirty at this point may race with
+ * clear_page_dirty_for_io(), but that's OK. Two key
+ * cases:
+ *
+ * 1) This code sees the page as already dirty, so it
+ * skips the call to set_page_dirty(). That could happen
+ * because clear_page_dirty_for_io() called
+ * page_mkclean(), followed by set_page_dirty().
+ * However, now the page is going to get written back,
+ * which meets the original intention of setting it
+ * dirty, so all is well: clear_page_dirty_for_io() goes
+ * on to call TestClearPageDirty(), and write the page
+ * back.
+ *
+ * 2) This code sees the page as clean, so it calls
+ * set_page_dirty(). The page stays dirty, despite being
+ * written back, so it gets written back again in the
+ * next writeback cycle. This is harmless.
+ */
+ if (!PageDirty(page))
+ set_page_dirty_lock(page);
+ unpin_user_page(page);
+ }
+}
+EXPORT_SYMBOL(unpin_user_pages_dirty_lock);
+
+/**
+ * unpin_user_pages() - release an array of gup-pinned pages.
+ * @pages: array of pages to be marked dirty and released.
+ * @npages: number of pages in the @pages array.
+ *
+ * For each page in the @pages array, release the page using unpin_user_page().
+ *
+ * Please see the unpin_user_page() documentation for details.
+ */
+void unpin_user_pages(struct page **pages, unsigned long npages)
+{
+ unsigned long index;
+
+ /*
+ * If this WARN_ON() fires, then the system *might* be leaking pages (by
+ * leaving them pinned), but probably not. More likely, gup/pup returned
+ * a hard -ERRNO error to the caller, who erroneously passed it here.
+ */
+ if (WARN_ON(IS_ERR_VALUE(npages)))
+ return;
+ /*
+ * TODO: this can be optimized for huge pages: if a series of pages is
+ * physically contiguous and part of the same compound page, then a
+ * single operation to the head page should suffice.
+ */
+ for (index = 0; index < npages; index++)
+ unpin_user_page(pages[index]);
+}
+EXPORT_SYMBOL(unpin_user_pages);
+
+#ifdef CONFIG_MMU
static struct page *no_page_table(struct vm_area_struct *vma,
unsigned int flags)
{
@@ -31,7 +382,8 @@
* But we can only make this optimization where a hole would surely
* be zero-filled if handle_mm_fault() actually did handle it.
*/
- if ((flags & FOLL_DUMP) && (!vma->vm_ops || !vma->vm_ops->fault))
+ if ((flags & FOLL_DUMP) &&
+ (vma_is_anonymous(vma) || !vma->vm_ops->fault))
return ERR_PTR(-EFAULT);
return NULL;
}
@@ -61,32 +413,40 @@
}
/*
- * FOLL_FORCE or a forced COW break can write even to unwritable pte's,
- * but only after we've gone through a COW cycle and they are dirty.
+ * FOLL_FORCE can write to even unwritable pte's, but only
+ * after we've gone through a COW cycle and they are dirty.
*/
static inline bool can_follow_write_pte(pte_t pte, unsigned int flags)
{
- return pte_write(pte) || ((flags & FOLL_COW) && pte_dirty(pte));
-}
-
-/*
- * A (separate) COW fault might break the page the other way and
- * get_user_pages() would return the page from what is now the wrong
- * VM. So we need to force a COW break at GUP time even for reads.
- */
-static inline bool should_force_cow_break(struct vm_area_struct *vma, unsigned int flags)
-{
- return is_cow_mapping(vma->vm_flags) && (flags & FOLL_GET);
+ return pte_write(pte) ||
+ ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte));
}
static struct page *follow_page_pte(struct vm_area_struct *vma,
- unsigned long address, pmd_t *pmd, unsigned int flags)
+ unsigned long address, pmd_t *pmd, unsigned int flags,
+ struct dev_pagemap **pgmap)
{
struct mm_struct *mm = vma->vm_mm;
- struct dev_pagemap *pgmap = NULL;
struct page *page;
spinlock_t *ptl;
pte_t *ptep, pte;
+ int ret;
+
+ /* FOLL_GET and FOLL_PIN are mutually exclusive. */
+ if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) ==
+ (FOLL_PIN | FOLL_GET)))
+ return ERR_PTR(-EINVAL);
+
+ /*
+ * Considering PTE level hugetlb, like continuous-PTE hugetlb on
+ * ARM64 architecture.
+ */
+ if (is_vm_hugetlb_page(vma)) {
+ page = follow_huge_pmd_pte(vma, address, flags);
+ if (page)
+ return page;
+ return no_page_table(vma, flags);
+ }
retry:
if (unlikely(pmd_bad(*pmd)))
@@ -120,13 +480,14 @@
}
page = vm_normal_page(vma, address, pte);
- if (!page && pte_devmap(pte) && (flags & FOLL_GET)) {
+ if (!page && pte_devmap(pte) && (flags & (FOLL_GET | FOLL_PIN))) {
/*
- * Only return device mapping pages in the FOLL_GET case since
- * they are only valid while holding the pgmap reference.
+ * Only return device mapping pages in the FOLL_GET or FOLL_PIN
+ * case since they are only valid while holding the pgmap
+ * reference.
*/
- pgmap = get_dev_pagemap(pte_pfn(pte), NULL);
- if (pgmap)
+ *pgmap = get_dev_pagemap(pte_pfn(pte), *pgmap);
+ if (*pgmap)
page = pte_page(pte);
else
goto no_page;
@@ -140,8 +501,6 @@
if (is_zero_pfn(pte_pfn(pte))) {
page = pte_page(pte);
} else {
- int ret;
-
ret = follow_pfn_pte(vma, address, ptep, flags);
page = ERR_PTR(ret);
goto out;
@@ -149,7 +508,6 @@
}
if (flags & FOLL_SPLIT && PageTransCompound(page)) {
- int ret;
get_page(page);
pte_unmap_unlock(ptep, ptl);
lock_page(page);
@@ -161,16 +519,22 @@
goto retry;
}
- if (flags & FOLL_GET) {
- if (unlikely(!try_get_page(page))) {
- page = ERR_PTR(-ENOMEM);
+ /* try_grab_page() does nothing unless FOLL_GET or FOLL_PIN is set. */
+ if (unlikely(!try_grab_page(page, flags))) {
+ page = ERR_PTR(-ENOMEM);
+ goto out;
+ }
+ /*
+ * We need to make the page accessible if and only if we are going
+ * to access its content (the FOLL_PIN case). Please see
+ * Documentation/core-api/pin_user_pages.rst for details.
+ */
+ if (flags & FOLL_PIN) {
+ ret = arch_make_page_accessible(page);
+ if (ret) {
+ unpin_user_page(page);
+ page = ERR_PTR(ret);
goto out;
- }
-
- /* drop the pgmap reference now that we hold the page */
- if (pgmap) {
- put_dev_pagemap(pgmap);
- pgmap = NULL;
}
}
if (flags & FOLL_TOUCH) {
@@ -222,7 +586,8 @@
static struct page *follow_pmd_mask(struct vm_area_struct *vma,
unsigned long address, pud_t *pudp,
- unsigned int flags, unsigned int *page_mask)
+ unsigned int flags,
+ struct follow_page_context *ctx)
{
pmd_t *pmd, pmdval;
spinlock_t *ptl;
@@ -237,8 +602,8 @@
pmdval = READ_ONCE(*pmd);
if (pmd_none(pmdval))
return no_page_table(vma, flags);
- if (pmd_huge(pmdval) && vma->vm_flags & VM_HUGETLB) {
- page = follow_huge_pmd(mm, address, pmd, flags);
+ if (pmd_huge(pmdval) && is_vm_hugetlb_page(vma)) {
+ page = follow_huge_pmd_pte(vma, address, flags);
if (page)
return page;
return no_page_table(vma, flags);
@@ -262,7 +627,7 @@
pmdval = READ_ONCE(*pmd);
/*
* MADV_DONTNEED may convert the pmd to null because
- * mmap_sem is held in read mode
+ * mmap_lock is held in read mode
*/
if (pmd_none(pmdval))
return no_page_table(vma, flags);
@@ -270,13 +635,13 @@
}
if (pmd_devmap(pmdval)) {
ptl = pmd_lock(mm, pmd);
- page = follow_devmap_pmd(vma, address, pmd, flags);
+ page = follow_devmap_pmd(vma, address, pmd, flags, &ctx->pgmap);
spin_unlock(ptl);
if (page)
return page;
}
if (likely(!pmd_trans_huge(pmdval)))
- return follow_page_pte(vma, address, pmd, flags);
+ return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
if ((flags & FOLL_NUMA) && pmd_protnone(pmdval))
return no_page_table(vma, flags);
@@ -296,9 +661,9 @@
}
if (unlikely(!pmd_trans_huge(*pmd))) {
spin_unlock(ptl);
- return follow_page_pte(vma, address, pmd, flags);
+ return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
}
- if (flags & FOLL_SPLIT) {
+ if (flags & (FOLL_SPLIT | FOLL_SPLIT_PMD)) {
int ret;
page = pmd_page(*pmd);
if (is_huge_zero_page(page)) {
@@ -307,7 +672,7 @@
split_huge_pmd(vma, pmd, address);
if (pmd_trans_unstable(pmd))
ret = -EBUSY;
- } else {
+ } else if (flags & FOLL_SPLIT) {
if (unlikely(!try_get_page(page))) {
spin_unlock(ptl);
return ERR_PTR(-ENOMEM);
@@ -319,21 +684,25 @@
put_page(page);
if (pmd_none(*pmd))
return no_page_table(vma, flags);
+ } else { /* flags & FOLL_SPLIT_PMD */
+ spin_unlock(ptl);
+ split_huge_pmd(vma, pmd, address);
+ ret = pte_alloc(mm, pmd) ? -ENOMEM : 0;
}
return ret ? ERR_PTR(ret) :
- follow_page_pte(vma, address, pmd, flags);
+ follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
}
page = follow_trans_huge_pmd(vma, address, pmd, flags);
spin_unlock(ptl);
- *page_mask = HPAGE_PMD_NR - 1;
+ ctx->page_mask = HPAGE_PMD_NR - 1;
return page;
}
-
static struct page *follow_pud_mask(struct vm_area_struct *vma,
unsigned long address, p4d_t *p4dp,
- unsigned int flags, unsigned int *page_mask)
+ unsigned int flags,
+ struct follow_page_context *ctx)
{
pud_t *pud;
spinlock_t *ptl;
@@ -343,7 +712,7 @@
pud = pud_offset(p4dp, address);
if (pud_none(*pud))
return no_page_table(vma, flags);
- if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) {
+ if (pud_huge(*pud) && is_vm_hugetlb_page(vma)) {
page = follow_huge_pud(mm, address, pud, flags);
if (page)
return page;
@@ -359,7 +728,7 @@
}
if (pud_devmap(*pud)) {
ptl = pud_lock(mm, pud);
- page = follow_devmap_pud(vma, address, pud, flags);
+ page = follow_devmap_pud(vma, address, pud, flags, &ctx->pgmap);
spin_unlock(ptl);
if (page)
return page;
@@ -367,13 +736,13 @@
if (unlikely(pud_bad(*pud)))
return no_page_table(vma, flags);
- return follow_pmd_mask(vma, address, pud, flags, page_mask);
+ return follow_pmd_mask(vma, address, pud, flags, ctx);
}
-
static struct page *follow_p4d_mask(struct vm_area_struct *vma,
unsigned long address, pgd_t *pgdp,
- unsigned int flags, unsigned int *page_mask)
+ unsigned int flags,
+ struct follow_page_context *ctx)
{
p4d_t *p4d;
struct page *page;
@@ -393,7 +762,7 @@
return page;
return no_page_table(vma, flags);
}
- return follow_pud_mask(vma, address, p4d, flags, page_mask);
+ return follow_pud_mask(vma, address, p4d, flags, ctx);
}
/**
@@ -401,28 +770,34 @@
* @vma: vm_area_struct mapping @address
* @address: virtual address to look up
* @flags: flags modifying lookup behaviour
- * @page_mask: on output, *page_mask is set according to the size of the page
+ * @ctx: contains dev_pagemap for %ZONE_DEVICE memory pinning and a
+ * pointer to output page_mask
*
* @flags can have FOLL_ flags set, defined in <linux/mm.h>
*
- * Returns the mapped (struct page *), %NULL if no mapping exists, or
+ * When getting pages from ZONE_DEVICE memory, the @ctx->pgmap caches
+ * the device's dev_pagemap metadata to avoid repeating expensive lookups.
+ *
+ * On output, the @ctx->page_mask is set according to the size of the page.
+ *
+ * Return: the mapped (struct page *), %NULL if no mapping exists, or
* an error pointer if there is a mapping to something not represented
* by a page descriptor (see also vm_normal_page()).
*/
-struct page *follow_page_mask(struct vm_area_struct *vma,
+static struct page *follow_page_mask(struct vm_area_struct *vma,
unsigned long address, unsigned int flags,
- unsigned int *page_mask)
+ struct follow_page_context *ctx)
{
pgd_t *pgd;
struct page *page;
struct mm_struct *mm = vma->vm_mm;
- *page_mask = 0;
+ ctx->page_mask = 0;
/* make this handle hugepd */
page = follow_huge_addr(mm, address, flags & FOLL_WRITE);
if (!IS_ERR(page)) {
- BUG_ON(flags & FOLL_GET);
+ WARN_ON_ONCE(flags & (FOLL_GET | FOLL_PIN));
return page;
}
@@ -446,7 +821,19 @@
return no_page_table(vma, flags);
}
- return follow_p4d_mask(vma, address, pgd, flags, page_mask);
+ return follow_p4d_mask(vma, address, pgd, flags, ctx);
+}
+
+struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
+ unsigned int foll_flags)
+{
+ struct follow_page_context ctx = { NULL };
+ struct page *page;
+
+ page = follow_page_mask(vma, address, foll_flags, &ctx);
+ if (ctx.pgmap)
+ put_dev_pagemap(ctx.pgmap);
+ return page;
}
static int get_gate_page(struct mm_struct *mm, unsigned long address,
@@ -490,15 +877,8 @@
if ((gup_flags & FOLL_DUMP) || !is_zero_pfn(pte_pfn(*pte)))
goto unmap;
*page = pte_page(*pte);
-
- /*
- * This should never happen (a device public page in the gate
- * area).
- */
- if (is_device_public_page(*page))
- goto unmap;
}
- if (unlikely(!try_get_page(*page))) {
+ if (unlikely(!try_grab_page(*page, gup_flags))) {
ret = -ENOMEM;
goto unmap;
}
@@ -510,12 +890,12 @@
}
/*
- * mmap_sem must be held on entry. If @nonblocking != NULL and
- * *@flags does not include FOLL_NOWAIT, the mmap_sem may be released.
- * If it is, *@nonblocking will be set to 0 and -EBUSY returned.
+ * mmap_lock must be held on entry. If @locked != NULL and *@flags
+ * does not include FOLL_NOWAIT, the mmap_lock may be released. If it
+ * is, *@locked will be set to 0 and -EBUSY returned.
*/
-static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
- unsigned long address, unsigned int *flags, int *nonblocking)
+static int faultin_page(struct vm_area_struct *vma,
+ unsigned long address, unsigned int *flags, int *locked)
{
unsigned int fault_flags = 0;
vm_fault_t ret;
@@ -527,16 +907,19 @@
fault_flags |= FAULT_FLAG_WRITE;
if (*flags & FOLL_REMOTE)
fault_flags |= FAULT_FLAG_REMOTE;
- if (nonblocking)
- fault_flags |= FAULT_FLAG_ALLOW_RETRY;
+ if (locked)
+ fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
if (*flags & FOLL_NOWAIT)
fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT;
if (*flags & FOLL_TRIED) {
- VM_WARN_ON_ONCE(fault_flags & FAULT_FLAG_ALLOW_RETRY);
+ /*
+ * Note: FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_TRIED
+ * can co-exist
+ */
fault_flags |= FAULT_FLAG_TRIED;
}
- ret = handle_mm_fault(vma, address, fault_flags);
+ ret = handle_mm_fault(vma, address, fault_flags, NULL);
if (ret & VM_FAULT_ERROR) {
int err = vm_fault_to_errno(ret, *flags);
@@ -545,16 +928,9 @@
BUG();
}
- if (tsk) {
- if (ret & VM_FAULT_MAJOR)
- tsk->maj_flt++;
- else
- tsk->min_flt++;
- }
-
if (ret & VM_FAULT_RETRY) {
- if (nonblocking && !(fault_flags & FAULT_FLAG_RETRY_NOWAIT))
- *nonblocking = 0;
+ if (locked && !(fault_flags & FAULT_FLAG_RETRY_NOWAIT))
+ *locked = 0;
return -EBUSY;
}
@@ -583,6 +959,9 @@
if (gup_flags & FOLL_ANON && !vma_is_anonymous(vma))
return -EFAULT;
+
+ if ((gup_flags & FOLL_LONGTERM) && vma_is_fsdax(vma))
+ return -EOPNOTSUPP;
if (write) {
if (!(vm_flags & VM_WRITE)) {
@@ -621,7 +1000,6 @@
/**
* __get_user_pages() - pin user pages in memory
- * @tsk: task_struct of target task
* @mm: mm_struct of target mm
* @start: starting user address
* @nr_pages: number of pages from start to pin
@@ -631,15 +1009,22 @@
* only intends to ensure the pages are faulted in.
* @vmas: array of pointers to vmas corresponding to each page.
* Or NULL if the caller does not require them.
- * @nonblocking: whether waiting for disk IO or mmap_sem contention
+ * @locked: whether we're still with the mmap_lock held
*
- * Returns number of pages pinned. This may be fewer than the number
- * requested. If nr_pages is 0 or negative, returns 0. If no pages
- * were pinned, returns -errno. Each page returned must be released
- * with a put_page() call when it is finished with. vmas will only
- * remain valid while mmap_sem is held.
+ * Returns either number of pages pinned (which may be less than the
+ * number requested), or an error. Details about the return value:
*
- * Must be called with mmap_sem held. It may be released. See below.
+ * -- If nr_pages is 0, returns 0.
+ * -- If nr_pages is >0, but no pages were pinned, returns -errno.
+ * -- If nr_pages is >0, and some pages were pinned, returns the number of
+ * pages pinned. Again, this may be less than nr_pages.
+ * -- 0 return value is possible when the fault would need to be retried.
+ *
+ * The caller is responsible for releasing returned @pages, via put_page().
+ *
+ * @vmas are valid only as long as mmap_lock is held.
+ *
+ * Must be called with mmap_lock held. It may be released. See below.
*
* __get_user_pages walks a process's page tables and takes a reference to
* each struct page that each user address corresponds to at a given
@@ -660,14 +1045,12 @@
* appropriate) must be called after the page is finished with, and
* before put_page is called.
*
- * If @nonblocking != NULL, __get_user_pages will not wait for disk IO
- * or mmap_sem contention, and if waiting is needed to pin all pages,
- * *@nonblocking will be set to 0. Further, if @gup_flags does not
- * include FOLL_NOWAIT, the mmap_sem will be released via up_read() in
- * this case.
+ * If @locked != NULL, *@locked will be set to 0 when mmap_lock is
+ * released by an up_read(). That can happen if @gup_flags does not
+ * have FOLL_NOWAIT.
*
- * A caller using such a combination of @nonblocking and @gup_flags
- * must therefore hold the mmap_sem for reading only, and recognize
+ * A caller using such a combination of @locked and @gup_flags
+ * must therefore hold the mmap_lock for reading only, and recognize
* when it's been released. Otherwise, it must be held for either
* reading or writing and will not be released.
*
@@ -675,21 +1058,21 @@
* instead of __get_user_pages. __get_user_pages should be used only if
* you need some special @gup_flags.
*/
-static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+static long __get_user_pages(struct mm_struct *mm,
unsigned long start, unsigned long nr_pages,
unsigned int gup_flags, struct page **pages,
- struct vm_area_struct **vmas, int *nonblocking)
+ struct vm_area_struct **vmas, int *locked)
{
- long i = 0;
- unsigned int page_mask;
+ long ret = 0, i = 0;
struct vm_area_struct *vma = NULL;
+ struct follow_page_context ctx = { NULL };
if (!nr_pages)
return 0;
start = untagged_addr(start);
- VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET));
+ VM_BUG_ON(!!pages != !!(gup_flags & (FOLL_GET | FOLL_PIN)));
/*
* If FOLL_FORCE is set then do not force a full fault as the hinting
@@ -708,53 +1091,64 @@
if (!vma || start >= vma->vm_end) {
vma = find_extend_vma(mm, start);
if (!vma && in_gate_area(mm, start)) {
- int ret;
ret = get_gate_page(mm, start & PAGE_MASK,
gup_flags, &vma,
pages ? &pages[i] : NULL);
if (ret)
- return i ? : ret;
- page_mask = 0;
+ goto out;
+ ctx.page_mask = 0;
goto next_page;
}
- if (!vma || check_vma_flags(vma, gup_flags))
- return i ? : -EFAULT;
+ if (!vma) {
+ ret = -EFAULT;
+ goto out;
+ }
+ ret = check_vma_flags(vma, gup_flags);
+ if (ret)
+ goto out;
+
if (is_vm_hugetlb_page(vma)) {
- if (should_force_cow_break(vma, foll_flags))
- foll_flags |= FOLL_WRITE;
i = follow_hugetlb_page(mm, vma, pages, vmas,
&start, &nr_pages, i,
- foll_flags, nonblocking);
+ gup_flags, locked);
+ if (locked && *locked == 0) {
+ /*
+ * We've got a VM_FAULT_RETRY
+ * and we've lost mmap_lock.
+ * We must stop here.
+ */
+ BUG_ON(gup_flags & FOLL_NOWAIT);
+ BUG_ON(ret != 0);
+ goto out;
+ }
continue;
}
}
-
- if (should_force_cow_break(vma, foll_flags))
- foll_flags |= FOLL_WRITE;
-
retry:
/*
* If we have a pending SIGKILL, don't keep faulting pages and
* potentially allocating memory.
*/
- if (unlikely(fatal_signal_pending(current)))
- return i ? i : -ERESTARTSYS;
+ if (fatal_signal_pending(current)) {
+ ret = -EINTR;
+ goto out;
+ }
cond_resched();
- page = follow_page_mask(vma, start, foll_flags, &page_mask);
+
+ page = follow_page_mask(vma, start, foll_flags, &ctx);
if (!page) {
- int ret;
- ret = faultin_page(tsk, vma, start, &foll_flags,
- nonblocking);
+ ret = faultin_page(vma, start, &foll_flags, locked);
switch (ret) {
case 0:
goto retry;
+ case -EBUSY:
+ ret = 0;
+ fallthrough;
case -EFAULT:
case -ENOMEM:
case -EHWPOISON:
- return i ? i : ret;
- case -EBUSY:
- return i;
+ goto out;
case -ENOENT:
goto next_page;
}
@@ -766,27 +1160,31 @@
*/
goto next_page;
} else if (IS_ERR(page)) {
- return i ? i : PTR_ERR(page);
+ ret = PTR_ERR(page);
+ goto out;
}
if (pages) {
pages[i] = page;
flush_anon_page(vma, page, start);
flush_dcache_page(page);
- page_mask = 0;
+ ctx.page_mask = 0;
}
next_page:
if (vmas) {
vmas[i] = vma;
- page_mask = 0;
+ ctx.page_mask = 0;
}
- page_increm = 1 + (~(start >> PAGE_SHIFT) & page_mask);
+ page_increm = 1 + (~(start >> PAGE_SHIFT) & ctx.page_mask);
if (page_increm > nr_pages)
page_increm = nr_pages;
i += page_increm;
start += page_increm * PAGE_SIZE;
nr_pages -= page_increm;
} while (nr_pages);
- return i;
+out:
+ if (ctx.pgmap)
+ put_dev_pagemap(ctx.pgmap);
+ return i ? i : ret;
}
static bool vma_permits_fault(struct vm_area_struct *vma,
@@ -812,15 +1210,14 @@
return true;
}
-/*
+/**
* fixup_user_fault() - manually resolve a user page fault
- * @tsk: the task_struct to use for page fault accounting, or
- * NULL if faults are not to be recorded.
* @mm: mm_struct of target mm
* @address: user address
* @fault_flags:flags to pass down to handle_mm_fault()
- * @unlocked: did we unlock the mmap_sem while retrying, maybe NULL if caller
- * does not allow retry
+ * @unlocked: did we unlock the mmap_lock while retrying, maybe NULL if caller
+ * does not allow retry. If NULL, the caller must guarantee
+ * that fault_flags does not contain FAULT_FLAG_ALLOW_RETRY.
*
* This is meant to be called in the specific scenario where for locking reasons
* we try to access user memory in atomic context (within a pagefault_disable()
@@ -839,10 +1236,10 @@
* such architectures, gup() will not be enough to make a subsequent access
* succeed.
*
- * This function will not return with an unlocked mmap_sem. So it has not the
- * same semantics wrt the @mm->mmap_sem as does filemap_fault().
+ * This function will not return with an unlocked mmap_lock. So it has not the
+ * same semantics wrt the @mm->mmap_lock as does filemap_fault().
*/
-int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
+int fixup_user_fault(struct mm_struct *mm,
unsigned long address, unsigned int fault_flags,
bool *unlocked)
{
@@ -852,7 +1249,7 @@
address = untagged_addr(address);
if (unlocked)
- fault_flags |= FAULT_FLAG_ALLOW_RETRY;
+ fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
retry:
vma = find_extend_vma(mm, address);
@@ -862,7 +1259,11 @@
if (!vma_permits_fault(vma, fault_flags))
return -EFAULT;
- ret = handle_mm_fault(vma, address, fault_flags);
+ if ((fault_flags & FAULT_FLAG_KILLABLE) &&
+ fatal_signal_pending(current))
+ return -EINTR;
+
+ ret = handle_mm_fault(vma, address, fault_flags, NULL);
major |= ret & VM_FAULT_MAJOR;
if (ret & VM_FAULT_ERROR) {
int err = vm_fault_to_errno(ret, 0);
@@ -873,27 +1274,21 @@
}
if (ret & VM_FAULT_RETRY) {
- down_read(&mm->mmap_sem);
- if (!(fault_flags & FAULT_FLAG_TRIED)) {
- *unlocked = true;
- fault_flags &= ~FAULT_FLAG_ALLOW_RETRY;
- fault_flags |= FAULT_FLAG_TRIED;
- goto retry;
- }
+ mmap_read_lock(mm);
+ *unlocked = true;
+ fault_flags |= FAULT_FLAG_TRIED;
+ goto retry;
}
- if (tsk) {
- if (major)
- tsk->maj_flt++;
- else
- tsk->min_flt++;
- }
return 0;
}
EXPORT_SYMBOL_GPL(fixup_user_fault);
-static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
- struct mm_struct *mm,
+/*
+ * Please note that this function, unlike __get_user_pages will not
+ * return 0 for nr_pages > 0 without FOLL_NOWAIT
+ */
+static __always_inline long __get_user_pages_locked(struct mm_struct *mm,
unsigned long start,
unsigned long nr_pages,
struct page **pages,
@@ -911,13 +1306,25 @@
BUG_ON(*locked != 1);
}
- if (pages)
+ if (flags & FOLL_PIN)
+ atomic_set(&mm->has_pinned, 1);
+
+ /*
+ * FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior
+ * is to set FOLL_GET if the caller wants pages[] filled in (but has
+ * carelessly failed to specify FOLL_GET), so keep doing that, but only
+ * for FOLL_GET, not for the newer FOLL_PIN.
+ *
+ * FOLL_PIN always expects pages to be non-null, but no need to assert
+ * that here, as any failures will be obvious enough.
+ */
+ if (pages && !(flags & FOLL_PIN))
flags |= FOLL_GET;
pages_done = 0;
lock_dropped = false;
for (;;) {
- ret = __get_user_pages(tsk, mm, start, nr_pages, flags, pages,
+ ret = __get_user_pages(mm, start, nr_pages, flags, pages,
vmas, locked);
if (!locked)
/* VM_FAULT_RETRY couldn't trigger, bypass */
@@ -928,10 +1335,6 @@
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;
@@ -948,20 +1351,46 @@
pages_done = ret;
break;
}
- /* VM_FAULT_RETRY triggered, so seek to the faulting offset */
- pages += ret;
+ /*
+ * VM_FAULT_RETRY triggered, so seek to the faulting offset.
+ * For the prefault case (!pages) we only update counts.
+ */
+ if (likely(pages))
+ pages += ret;
start += ret << PAGE_SHIFT;
+ lock_dropped = true;
+retry:
/*
* Repeat on the address that fired VM_FAULT_RETRY
- * without FAULT_FLAG_ALLOW_RETRY but with
- * FAULT_FLAG_TRIED.
+ * with both FAULT_FLAG_ALLOW_RETRY and
+ * FAULT_FLAG_TRIED. Note that GUP can be interrupted
+ * by fatal signals, so we need to check it before we
+ * start trying again otherwise it can loop forever.
*/
+
+ if (fatal_signal_pending(current)) {
+ if (!pages_done)
+ pages_done = -EINTR;
+ break;
+ }
+
+ ret = mmap_read_lock_killable(mm);
+ if (ret) {
+ BUG_ON(ret > 0);
+ if (!pages_done)
+ pages_done = ret;
+ break;
+ }
+
*locked = 1;
- lock_dropped = true;
- down_read(&mm->mmap_sem);
- ret = __get_user_pages(tsk, mm, start, 1, flags | FOLL_TRIED,
- pages, NULL, NULL);
+ ret = __get_user_pages(mm, start, 1, flags | FOLL_TRIED,
+ pages, NULL, locked);
+ if (!*locked) {
+ /* Continue to retry until we succeeded */
+ BUG_ON(ret != 0);
+ goto retry;
+ }
if (ret != 1) {
BUG_ON(ret > 1);
if (!pages_done)
@@ -972,7 +1401,8 @@
pages_done++;
if (!nr_pages)
break;
- pages++;
+ if (likely(pages))
+ pages++;
start += PAGE_SIZE;
}
if (lock_dropped && *locked) {
@@ -980,243 +1410,34 @@
* 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);
+ mmap_read_unlock(mm);
*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(unsigned long start, unsigned long nr_pages,
- unsigned int gup_flags, struct page **pages,
- int *locked)
-{
- return __get_user_pages_locked(current, current->mm, start, nr_pages,
- pages, NULL, locked,
- gup_flags | FOLL_TOUCH);
-}
-EXPORT_SYMBOL(get_user_pages_locked);
-
-/*
- * 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 specific gup_flags
- * (e.g. FOLL_FORCE) are not required.
- */
-long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
- struct page **pages, unsigned int gup_flags)
-{
- struct mm_struct *mm = current->mm;
- int locked = 1;
- long ret;
-
- down_read(&mm->mmap_sem);
- ret = __get_user_pages_locked(current, mm, start, nr_pages, pages, NULL,
- &locked, gup_flags | FOLL_TOUCH);
- if (locked)
- up_read(&mm->mmap_sem);
- return ret;
-}
-EXPORT_SYMBOL(get_user_pages_unlocked);
-
-/*
- * get_user_pages_remote() - pin user pages in memory
- * @tsk: the task_struct to use for page fault accounting, or
- * NULL if faults are not to be recorded.
- * @mm: mm_struct of target mm
- * @start: starting user address
- * @nr_pages: number of pages from start to pin
- * @gup_flags: flags modifying lookup behaviour
- * @pages: array that receives pointers to the pages pinned.
- * Should be at least nr_pages long. Or NULL, if caller
- * only intends to ensure the pages are faulted in.
- * @vmas: array of pointers to vmas corresponding to each page.
- * Or NULL if the caller does not require them.
- * @locked: pointer to lock flag indicating whether lock is held and
- * subsequently whether VM_FAULT_RETRY functionality can be
- * utilised. Lock must initially be held.
- *
- * Returns number of pages pinned. This may be fewer than the number
- * requested. If nr_pages is 0 or negative, returns 0. If no pages
- * were pinned, returns -errno. Each page returned must be released
- * with a put_page() call when it is finished with. vmas will only
- * remain valid while mmap_sem is held.
- *
- * Must be called with mmap_sem held for read or write.
- *
- * get_user_pages walks a process's page tables and takes a reference to
- * each struct page that each user address corresponds to at a given
- * instant. That is, it takes the page that would be accessed if a user
- * thread accesses the given user virtual address at that instant.
- *
- * This does not guarantee that the page exists in the user mappings when
- * get_user_pages returns, and there may even be a completely different
- * page there in some cases (eg. if mmapped pagecache has been invalidated
- * and subsequently re faulted). However it does guarantee that the page
- * won't be freed completely. And mostly callers simply care that the page
- * contains data that was valid *at some point in time*. Typically, an IO
- * or similar operation cannot guarantee anything stronger anyway because
- * locks can't be held over the syscall boundary.
- *
- * If gup_flags & FOLL_WRITE == 0, the page must not be written to. If the page
- * is written to, set_page_dirty (or set_page_dirty_lock, as appropriate) must
- * be called after the page is finished with, and before put_page is called.
- *
- * get_user_pages is typically used for fewer-copy IO operations, to get a
- * handle on the memory by some means other than accesses via the user virtual
- * addresses. The pages may be submitted for DMA to devices or accessed via
- * their kernel linear mapping (via the kmap APIs). Care should be taken to
- * 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_remote(struct task_struct *tsk, 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)
-{
- return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas,
- locked,
- gup_flags | FOLL_TOUCH | FOLL_REMOTE);
-}
-EXPORT_SYMBOL(get_user_pages_remote);
-
-/*
- * This is the same as get_user_pages_remote(), just with a
- * less-flexible calling convention where we assume that the task
- * and mm being operated on are the current task's and don't allow
- * passing of a locked parameter. We also obviously don't pass
- * FOLL_REMOTE in here.
- */
-long get_user_pages(unsigned long start, unsigned long nr_pages,
- unsigned int gup_flags, struct page **pages,
- struct vm_area_struct **vmas)
-{
- return __get_user_pages_locked(current, current->mm, start, nr_pages,
- pages, vmas, NULL,
- gup_flags | FOLL_TOUCH);
-}
-EXPORT_SYMBOL(get_user_pages);
-
-#ifdef CONFIG_FS_DAX
-/*
- * This is the same as get_user_pages() in that it assumes we are
- * operating on the current task's mm, but it goes further to validate
- * that the vmas associated with the address range are suitable for
- * longterm elevated page reference counts. For example, filesystem-dax
- * mappings are subject to the lifetime enforced by the filesystem and
- * we need guarantees that longterm users like RDMA and V4L2 only
- * establish mappings that have a kernel enforced revocation mechanism.
- *
- * "longterm" == userspace controlled elevated page count lifetime.
- * Contrast this to iov_iter_get_pages() usages which are transient.
- */
-long get_user_pages_longterm(unsigned long start, unsigned long nr_pages,
- unsigned int gup_flags, struct page **pages,
- struct vm_area_struct **vmas_arg)
-{
- struct vm_area_struct **vmas = vmas_arg;
- struct vm_area_struct *vma_prev = NULL;
- long rc, i;
-
- if (!pages)
- return -EINVAL;
-
- if (!vmas) {
- vmas = kcalloc(nr_pages, sizeof(struct vm_area_struct *),
- GFP_KERNEL);
- if (!vmas)
- return -ENOMEM;
- }
-
- rc = get_user_pages(start, nr_pages, gup_flags, pages, vmas);
-
- for (i = 0; i < rc; i++) {
- struct vm_area_struct *vma = vmas[i];
-
- if (vma == vma_prev)
- continue;
-
- vma_prev = vma;
-
- if (vma_is_fsdax(vma))
- break;
- }
-
- /*
- * Either get_user_pages() failed, or the vma validation
- * succeeded, in either case we don't need to put_page() before
- * returning.
- */
- if (i >= rc)
- goto out;
-
- for (i = 0; i < rc; i++)
- put_page(pages[i]);
- rc = -EOPNOTSUPP;
-out:
- if (vmas != vmas_arg)
- kfree(vmas);
- return rc;
-}
-EXPORT_SYMBOL(get_user_pages_longterm);
-#endif /* CONFIG_FS_DAX */
/**
* populate_vma_page_range() - populate a range of pages in the vma.
* @vma: target vma
* @start: start address
* @end: end address
- * @nonblocking:
+ * @locked: whether the mmap_lock is still held
*
* This takes care of mlocking the pages too if VM_LOCKED is set.
*
- * return 0 on success, negative error code on error.
+ * Return either number of pages pinned in the vma, or a negative error
+ * code on error.
*
- * vma->vm_mm->mmap_sem must be held.
+ * vma->vm_mm->mmap_lock must be held.
*
- * If @nonblocking is NULL, it may be held for read or write and will
+ * If @locked is NULL, it may be held for read or write and will
* be unperturbed.
*
- * If @nonblocking is non-NULL, it must held for read only and may be
- * released. If it's released, *@nonblocking will be set to 0.
+ * If @locked is non-NULL, it must held for read only and may be
+ * released. If it's released, *@locked will be set to 0.
*/
long populate_vma_page_range(struct vm_area_struct *vma,
- unsigned long start, unsigned long end, int *nonblocking)
+ unsigned long start, unsigned long end, int *locked)
{
struct mm_struct *mm = vma->vm_mm;
unsigned long nr_pages = (end - start) / PAGE_SIZE;
@@ -1226,7 +1447,7 @@
VM_BUG_ON(end & ~PAGE_MASK);
VM_BUG_ON_VMA(start < vma->vm_start, vma);
VM_BUG_ON_VMA(end > vma->vm_end, vma);
- VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_sem), mm);
+ mmap_assert_locked(mm);
gup_flags = FOLL_TOUCH | FOLL_POPULATE | FOLL_MLOCK;
if (vma->vm_flags & VM_LOCKONFAULT)
@@ -1243,15 +1464,15 @@
* We want mlock to succeed for regions that have any permissions
* other than PROT_NONE.
*/
- if (vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC))
+ if (vma_is_accessible(vma))
gup_flags |= FOLL_FORCE;
/*
* We made sure addr is within a VMA, so the following will
* not result in a stack expansion that recurses back here.
*/
- return __get_user_pages(current, mm, start, nr_pages, gup_flags,
- NULL, NULL, nonblocking);
+ return __get_user_pages(mm, start, nr_pages, gup_flags,
+ NULL, NULL, locked);
}
/*
@@ -1259,7 +1480,7 @@
*
* This is used to implement mlock() and the MAP_POPULATE / MAP_LOCKED mmap
* flags. VMAs must be already marked with the desired vm_flags, and
- * mmap_sem must not be held.
+ * mmap_lock must not be held.
*/
int __mm_populate(unsigned long start, unsigned long len, int ignore_errors)
{
@@ -1278,7 +1499,7 @@
*/
if (!locked) {
locked = 1;
- down_read(&mm->mmap_sem);
+ mmap_read_lock(mm);
vma = find_vma(mm, nstart);
} else if (nstart >= vma->vm_end)
vma = vma->vm_next;
@@ -1310,9 +1531,53 @@
ret = 0;
}
if (locked)
- up_read(&mm->mmap_sem);
+ mmap_read_unlock(mm);
return ret; /* 0 or negative error code */
}
+#else /* CONFIG_MMU */
+static long __get_user_pages_locked(struct mm_struct *mm, unsigned long start,
+ unsigned long nr_pages, struct page **pages,
+ struct vm_area_struct **vmas, int *locked,
+ unsigned int foll_flags)
+{
+ struct vm_area_struct *vma;
+ unsigned long vm_flags;
+ int i;
+
+ /* calculate required read or write permissions.
+ * If FOLL_FORCE is set, we only require the "MAY" flags.
+ */
+ vm_flags = (foll_flags & FOLL_WRITE) ?
+ (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
+ vm_flags &= (foll_flags & FOLL_FORCE) ?
+ (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
+
+ for (i = 0; i < nr_pages; i++) {
+ vma = find_vma(mm, start);
+ if (!vma)
+ goto finish_or_fault;
+
+ /* protect what we can, including chardevs */
+ if ((vma->vm_flags & (VM_IO | VM_PFNMAP)) ||
+ !(vm_flags & vma->vm_flags))
+ goto finish_or_fault;
+
+ if (pages) {
+ pages[i] = virt_to_page(start);
+ if (pages[i])
+ get_page(pages[i]);
+ }
+ if (vmas)
+ vmas[i] = vma;
+ start = (start + PAGE_SIZE) & PAGE_MASK;
+ }
+
+ return i;
+
+finish_or_fault:
+ return i ? : -EFAULT;
+}
+#endif /* !CONFIG_MMU */
/**
* get_dump_page() - pin user page in memory while writing it to core dump
@@ -1326,25 +1591,429 @@
* NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found -
* allowing a hole to be left in the corefile to save diskspace.
*
- * Called without mmap_sem, but after all other threads have been killed.
+ * Called without mmap_lock (takes and releases the mmap_lock by itself).
*/
#ifdef CONFIG_ELF_CORE
struct page *get_dump_page(unsigned long addr)
{
- struct vm_area_struct *vma;
+ struct mm_struct *mm = current->mm;
struct page *page;
+ int locked = 1;
+ int ret;
- if (__get_user_pages(current, current->mm, addr, 1,
- FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma,
- NULL) < 1)
+ if (mmap_read_lock_killable(mm))
return NULL;
- flush_cache_page(vma, addr, page_to_pfn(page));
- return page;
+ ret = __get_user_pages_locked(mm, addr, 1, &page, NULL, &locked,
+ FOLL_FORCE | FOLL_DUMP | FOLL_GET);
+ if (locked)
+ mmap_read_unlock(mm);
+ return (ret == 1) ? page : NULL;
}
#endif /* CONFIG_ELF_CORE */
+#ifdef CONFIG_CMA
+static long check_and_migrate_cma_pages(struct mm_struct *mm,
+ unsigned long start,
+ unsigned long nr_pages,
+ struct page **pages,
+ struct vm_area_struct **vmas,
+ unsigned int gup_flags)
+{
+ unsigned long i, isolation_error_count;
+ bool drain_allow;
+ LIST_HEAD(cma_page_list);
+ long ret = nr_pages;
+ struct page *prev_head, *head;
+ struct migration_target_control mtc = {
+ .nid = NUMA_NO_NODE,
+ .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_NOWARN,
+ };
+
+check_again:
+ prev_head = NULL;
+ isolation_error_count = 0;
+ drain_allow = true;
+ for (i = 0; i < nr_pages; i++) {
+ head = compound_head(pages[i]);
+ if (head == prev_head)
+ continue;
+ prev_head = head;
+ /*
+ * If we get a page from the CMA zone, since we are going to
+ * be pinning these entries, we might as well move them out
+ * of the CMA zone if possible.
+ */
+ if (is_migrate_cma_page(head)) {
+ if (PageHuge(head)) {
+ if (isolate_hugetlb(head, &cma_page_list))
+ isolation_error_count++;
+ } else {
+ if (!PageLRU(head) && drain_allow) {
+ lru_add_drain_all();
+ drain_allow = false;
+ }
+
+ if (isolate_lru_page(head)) {
+ isolation_error_count++;
+ continue;
+ }
+ list_add_tail(&head->lru, &cma_page_list);
+ mod_node_page_state(page_pgdat(head),
+ NR_ISOLATED_ANON +
+ page_is_file_lru(head),
+ thp_nr_pages(head));
+ }
+ }
+ }
+
+ /*
+ * If list is empty, and no isolation errors, means that all pages are
+ * in the correct zone.
+ */
+ if (list_empty(&cma_page_list) && !isolation_error_count)
+ return ret;
+
+ if (!list_empty(&cma_page_list)) {
+ /*
+ * drop the above get_user_pages reference.
+ */
+ if (gup_flags & FOLL_PIN)
+ unpin_user_pages(pages, nr_pages);
+ else
+ for (i = 0; i < nr_pages; i++)
+ put_page(pages[i]);
+
+ ret = migrate_pages(&cma_page_list, alloc_migration_target,
+ NULL, (unsigned long)&mtc, MIGRATE_SYNC,
+ MR_CONTIG_RANGE);
+ if (ret) {
+ if (!list_empty(&cma_page_list))
+ putback_movable_pages(&cma_page_list);
+ return ret > 0 ? -ENOMEM : ret;
+ }
+
+ /* We unpinned pages before migration, pin them again */
+ ret = __get_user_pages_locked(mm, start, nr_pages, pages, vmas,
+ NULL, gup_flags);
+ if (ret <= 0)
+ return ret;
+ nr_pages = ret;
+ }
+
+ /*
+ * check again because pages were unpinned, and we also might have
+ * had isolation errors and need more pages to migrate.
+ */
+ goto check_again;
+}
+#else
+static long check_and_migrate_cma_pages(struct mm_struct *mm,
+ unsigned long start,
+ unsigned long nr_pages,
+ struct page **pages,
+ struct vm_area_struct **vmas,
+ unsigned int gup_flags)
+{
+ return nr_pages;
+}
+#endif /* CONFIG_CMA */
+
/*
- * Generic Fast GUP
+ * __gup_longterm_locked() is a wrapper for __get_user_pages_locked which
+ * allows us to process the FOLL_LONGTERM flag.
+ */
+static long __gup_longterm_locked(struct mm_struct *mm,
+ unsigned long start,
+ unsigned long nr_pages,
+ struct page **pages,
+ struct vm_area_struct **vmas,
+ unsigned int gup_flags)
+{
+ unsigned long flags = 0;
+ long rc;
+
+ if (gup_flags & FOLL_LONGTERM)
+ flags = memalloc_nocma_save();
+
+ rc = __get_user_pages_locked(mm, start, nr_pages, pages, vmas, NULL,
+ gup_flags);
+
+ if (gup_flags & FOLL_LONGTERM) {
+ if (rc > 0)
+ rc = check_and_migrate_cma_pages(mm, start, rc, pages,
+ vmas, gup_flags);
+ memalloc_nocma_restore(flags);
+ }
+ return rc;
+}
+
+static bool is_valid_gup_flags(unsigned int gup_flags)
+{
+ /*
+ * FOLL_PIN must only be set internally by the pin_user_pages*() APIs,
+ * never directly by the caller, so enforce that with an assertion:
+ */
+ if (WARN_ON_ONCE(gup_flags & FOLL_PIN))
+ return false;
+ /*
+ * FOLL_PIN is a prerequisite to FOLL_LONGTERM. Another way of saying
+ * that is, FOLL_LONGTERM is a specific case, more restrictive case of
+ * FOLL_PIN.
+ */
+ if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM))
+ return false;
+
+ return true;
+}
+
+#ifdef CONFIG_MMU
+static 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)
+{
+ /*
+ * Parts of FOLL_LONGTERM behavior are incompatible with
+ * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on
+ * vmas. However, this only comes up if locked is set, and there are
+ * callers that do request FOLL_LONGTERM, but do not set locked. So,
+ * allow what we can.
+ */
+ if (gup_flags & FOLL_LONGTERM) {
+ if (WARN_ON_ONCE(locked))
+ return -EINVAL;
+ /*
+ * This will check the vmas (even if our vmas arg is NULL)
+ * and return -ENOTSUPP if DAX isn't allowed in this case:
+ */
+ return __gup_longterm_locked(mm, start, nr_pages, pages,
+ vmas, gup_flags | FOLL_TOUCH |
+ FOLL_REMOTE);
+ }
+
+ return __get_user_pages_locked(mm, start, nr_pages, pages, vmas,
+ locked,
+ gup_flags | FOLL_TOUCH | FOLL_REMOTE);
+}
+
+/**
+ * get_user_pages_remote() - pin user pages in memory
+ * @mm: mm_struct of target mm
+ * @start: starting user address
+ * @nr_pages: number of pages from start to pin
+ * @gup_flags: flags modifying lookup behaviour
+ * @pages: array that receives pointers to the pages pinned.
+ * Should be at least nr_pages long. Or NULL, if caller
+ * only intends to ensure the pages are faulted in.
+ * @vmas: array of pointers to vmas corresponding to each page.
+ * Or NULL if the caller does not require them.
+ * @locked: pointer to lock flag indicating whether lock is held and
+ * subsequently whether VM_FAULT_RETRY functionality can be
+ * utilised. Lock must initially be held.
+ *
+ * Returns either number of pages pinned (which may be less than the
+ * number requested), or an error. Details about the return value:
+ *
+ * -- If nr_pages is 0, returns 0.
+ * -- If nr_pages is >0, but no pages were pinned, returns -errno.
+ * -- If nr_pages is >0, and some pages were pinned, returns the number of
+ * pages pinned. Again, this may be less than nr_pages.
+ *
+ * The caller is responsible for releasing returned @pages, via put_page().
+ *
+ * @vmas are valid only as long as mmap_lock is held.
+ *
+ * Must be called with mmap_lock held for read or write.
+ *
+ * get_user_pages_remote walks a process's page tables and takes a reference
+ * to each struct page that each user address corresponds to at a given
+ * instant. That is, it takes the page that would be accessed if a user
+ * thread accesses the given user virtual address at that instant.
+ *
+ * This does not guarantee that the page exists in the user mappings when
+ * get_user_pages_remote returns, and there may even be a completely different
+ * page there in some cases (eg. if mmapped pagecache has been invalidated
+ * and subsequently re faulted). However it does guarantee that the page
+ * won't be freed completely. And mostly callers simply care that the page
+ * contains data that was valid *at some point in time*. Typically, an IO
+ * or similar operation cannot guarantee anything stronger anyway because
+ * locks can't be held over the syscall boundary.
+ *
+ * If gup_flags & FOLL_WRITE == 0, the page must not be written to. If the page
+ * is written to, set_page_dirty (or set_page_dirty_lock, as appropriate) must
+ * be called after the page is finished with, and before put_page is called.
+ *
+ * get_user_pages_remote is typically used for fewer-copy IO operations,
+ * to get a handle on the memory by some means other than accesses
+ * via the user virtual addresses. The pages may be submitted for
+ * DMA to devices or accessed via their kernel linear mapping (via the
+ * kmap APIs). Care should be taken to use the correct cache flushing APIs.
+ *
+ * See also get_user_pages_fast, for performance critical applications.
+ *
+ * get_user_pages_remote should be phased out in favor of
+ * get_user_pages_locked|unlocked or get_user_pages_fast. Nothing
+ * should use get_user_pages_remote because it cannot pass
+ * FAULT_FLAG_ALLOW_RETRY to handle_mm_fault.
+ */
+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)
+{
+ if (!is_valid_gup_flags(gup_flags))
+ return -EINVAL;
+
+ return __get_user_pages_remote(mm, start, nr_pages, gup_flags,
+ pages, vmas, locked);
+}
+EXPORT_SYMBOL(get_user_pages_remote);
+
+#else /* CONFIG_MMU */
+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)
+{
+ return 0;
+}
+
+static 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)
+{
+ return 0;
+}
+#endif /* !CONFIG_MMU */
+
+/**
+ * get_user_pages() - pin user pages in memory
+ * @start: starting user address
+ * @nr_pages: number of pages from start to pin
+ * @gup_flags: flags modifying lookup behaviour
+ * @pages: array that receives pointers to the pages pinned.
+ * Should be at least nr_pages long. Or NULL, if caller
+ * only intends to ensure the pages are faulted in.
+ * @vmas: array of pointers to vmas corresponding to each page.
+ * Or NULL if the caller does not require them.
+ *
+ * This is the same as get_user_pages_remote(), just with a less-flexible
+ * calling convention where we assume that the mm being operated on belongs to
+ * the current task, and doesn't allow passing of a locked parameter. We also
+ * obviously don't pass FOLL_REMOTE in here.
+ */
+long get_user_pages(unsigned long start, unsigned long nr_pages,
+ unsigned int gup_flags, struct page **pages,
+ struct vm_area_struct **vmas)
+{
+ if (!is_valid_gup_flags(gup_flags))
+ return -EINVAL;
+
+ return __gup_longterm_locked(current->mm, start, nr_pages,
+ pages, vmas, gup_flags | FOLL_TOUCH);
+}
+EXPORT_SYMBOL(get_user_pages);
+
+/**
+ * get_user_pages_locked() is suitable to replace the form:
+ *
+ * mmap_read_lock(mm);
+ * do_something()
+ * get_user_pages(mm, ..., pages, NULL);
+ * mmap_read_unlock(mm);
+ *
+ * to:
+ *
+ * int locked = 1;
+ * mmap_read_lock(mm);
+ * do_something()
+ * get_user_pages_locked(mm, ..., pages, &locked);
+ * if (locked)
+ * mmap_read_unlock(mm);
+ *
+ * @start: starting user address
+ * @nr_pages: number of pages from start to pin
+ * @gup_flags: flags modifying lookup behaviour
+ * @pages: array that receives pointers to the pages pinned.
+ * Should be at least nr_pages long. Or NULL, if caller
+ * only intends to ensure the pages are faulted in.
+ * @locked: pointer to lock flag indicating whether lock is held and
+ * subsequently whether VM_FAULT_RETRY functionality can be
+ * utilised. Lock must initially be held.
+ *
+ * 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().
+ *
+ */
+long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
+ unsigned int gup_flags, struct page **pages,
+ int *locked)
+{
+ /*
+ * FIXME: Current FOLL_LONGTERM behavior is incompatible with
+ * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on
+ * vmas. As there are no users of this flag in this call we simply
+ * disallow this option for now.
+ */
+ if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM))
+ return -EINVAL;
+ /*
+ * FOLL_PIN must only be set internally by the pin_user_pages*() APIs,
+ * never directly by the caller, so enforce that:
+ */
+ if (WARN_ON_ONCE(gup_flags & FOLL_PIN))
+ return -EINVAL;
+
+ return __get_user_pages_locked(current->mm, start, nr_pages,
+ pages, NULL, locked,
+ gup_flags | FOLL_TOUCH);
+}
+EXPORT_SYMBOL(get_user_pages_locked);
+
+/*
+ * get_user_pages_unlocked() is suitable to replace the form:
+ *
+ * mmap_read_lock(mm);
+ * get_user_pages(mm, ..., pages, NULL);
+ * mmap_read_unlock(mm);
+ *
+ * with:
+ *
+ * get_user_pages_unlocked(mm, ..., pages);
+ *
+ * It is functionally equivalent to get_user_pages_fast so
+ * get_user_pages_fast should be used instead if specific gup_flags
+ * (e.g. FOLL_FORCE) are not required.
+ */
+long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
+ struct page **pages, unsigned int gup_flags)
+{
+ struct mm_struct *mm = current->mm;
+ int locked = 1;
+ long ret;
+
+ /*
+ * FIXME: Current FOLL_LONGTERM behavior is incompatible with
+ * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on
+ * vmas. As there are no users of this flag in this call we simply
+ * disallow this option for now.
+ */
+ if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM))
+ return -EINVAL;
+
+ mmap_read_lock(mm);
+ ret = __get_user_pages_locked(mm, start, nr_pages, pages, NULL,
+ &locked, gup_flags | FOLL_TOUCH);
+ if (locked)
+ mmap_read_unlock(mm);
+ return ret;
+}
+EXPORT_SYMBOL(get_user_pages_unlocked);
+
+/*
+ * Fast GUP
*
* get_user_pages_fast attempts to pin user pages by walking the page
* tables directly and avoids taking locks. Thus the walker needs to be
@@ -1365,7 +2034,7 @@
* Before activating this code, please be aware that the following assumptions
* are currently made:
*
- * *) Either HAVE_RCU_TABLE_FREE is enabled, and tlb_remove_table() is used to
+ * *) Either MMU_GATHER_RCU_TABLE_FREE is enabled, and tlb_remove_table() is used to
* free pages containing page tables or TLB flushing requires IPI broadcast.
*
* *) ptes can be read atomically by the architecture.
@@ -1376,47 +2045,101 @@
*
* This code is based heavily on the PowerPC implementation by Nick Piggin.
*/
-#ifdef CONFIG_HAVE_GENERIC_GUP
+#ifdef CONFIG_HAVE_FAST_GUP
+#ifdef CONFIG_GUP_GET_PTE_LOW_HIGH
-#ifndef gup_get_pte
/*
- * We assume that the PTE can be read atomically. If this is not the case for
- * your architecture, please provide the helper.
+ * WARNING: only to be used in the get_user_pages_fast() implementation.
+ *
+ * With get_user_pages_fast(), we walk down the pagetables without taking any
+ * locks. For this we would like to load the pointers atomically, but sometimes
+ * that is not possible (e.g. without expensive cmpxchg8b on x86_32 PAE). What
+ * we do have is the guarantee that a PTE will only either go from not present
+ * to present, or present to not present or both -- it will not switch to a
+ * completely different present page without a TLB flush in between; something
+ * that we are blocking by holding interrupts off.
+ *
+ * Setting ptes from not present to present goes:
+ *
+ * ptep->pte_high = h;
+ * smp_wmb();
+ * ptep->pte_low = l;
+ *
+ * And present to not present goes:
+ *
+ * ptep->pte_low = 0;
+ * smp_wmb();
+ * ptep->pte_high = 0;
+ *
+ * We must ensure here that the load of pte_low sees 'l' IFF pte_high sees 'h'.
+ * We load pte_high *after* loading pte_low, which ensures we don't see an older
+ * value of pte_high. *Then* we recheck pte_low, which ensures that we haven't
+ * picked up a changed pte high. We might have gotten rubbish values from
+ * pte_low and pte_high, but we are guaranteed that pte_low will not have the
+ * present bit set *unless* it is 'l'. Because get_user_pages_fast() only
+ * operates on present ptes we're safe.
*/
static inline pte_t gup_get_pte(pte_t *ptep)
{
- return READ_ONCE(*ptep);
+ pte_t pte;
+
+ do {
+ pte.pte_low = ptep->pte_low;
+ smp_rmb();
+ pte.pte_high = ptep->pte_high;
+ smp_rmb();
+ } while (unlikely(pte.pte_low != ptep->pte_low));
+
+ return pte;
}
-#endif
+#else /* CONFIG_GUP_GET_PTE_LOW_HIGH */
+/*
+ * We require that the PTE can be read atomically.
+ */
+static inline pte_t gup_get_pte(pte_t *ptep)
+{
+ return ptep_get(ptep);
+}
+#endif /* CONFIG_GUP_GET_PTE_LOW_HIGH */
static void __maybe_unused undo_dev_pagemap(int *nr, int nr_start,
+ unsigned int flags,
struct page **pages)
{
while ((*nr) - nr_start) {
struct page *page = pages[--(*nr)];
ClearPageReferenced(page);
- put_page(page);
+ if (flags & FOLL_PIN)
+ unpin_user_page(page);
+ else
+ put_page(page);
}
}
-/*
- * Return the compund head page with ref appropriately incremented,
- * or NULL if that failed.
- */
-static inline struct page *try_get_compound_head(struct page *page, int refs)
-{
- struct page *head = compound_head(page);
- if (WARN_ON_ONCE(page_ref_count(head) < 0))
- return NULL;
- if (unlikely(!page_cache_add_speculative(head, refs)))
- return NULL;
- return head;
-}
-
#ifdef CONFIG_ARCH_HAS_PTE_SPECIAL
-static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
- int write, struct page **pages, int *nr)
+/*
+ * Fast-gup relies on pte change detection to avoid concurrent pgtable
+ * operations.
+ *
+ * To pin the page, fast-gup needs to do below in order:
+ * (1) pin the page (by prefetching pte), then (2) check pte not changed.
+ *
+ * For the rest of pgtable operations where pgtable updates can be racy
+ * with fast-gup, we need to do (1) clear pte, then (2) check whether page
+ * is pinned.
+ *
+ * Above will work for all pte-level operations, including THP split.
+ *
+ * For THP collapse, it's a bit more complicated because fast-gup may be
+ * walking a pgtable page that is being freed (pte is still valid but pmd
+ * can be cleared already). To avoid race in such condition, we need to
+ * also check pmd here to make sure pmd doesn't change (corresponds to
+ * pmdp_collapse_flush() in the THP collapse code path).
+ */
+static int gup_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
+ unsigned long end, unsigned int flags,
+ struct page **pages, int *nr)
{
struct dev_pagemap *pgmap = NULL;
int nr_start = *nr, ret = 0;
@@ -1434,13 +2157,16 @@
if (pte_protnone(pte))
goto pte_unmap;
- if (!pte_access_permitted(pte, write))
+ if (!pte_access_permitted(pte, flags & FOLL_WRITE))
goto pte_unmap;
if (pte_devmap(pte)) {
+ if (unlikely(flags & FOLL_LONGTERM))
+ goto pte_unmap;
+
pgmap = get_dev_pagemap(pte_pfn(pte), pgmap);
if (unlikely(!pgmap)) {
- undo_dev_pagemap(nr, nr_start, pages);
+ undo_dev_pagemap(nr, nr_start, flags, pages);
goto pte_unmap;
}
} else if (pte_special(pte))
@@ -1449,17 +2175,31 @@
VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
page = pte_page(pte);
- head = try_get_compound_head(page, 1);
+ head = try_grab_compound_head(page, 1, flags);
if (!head)
goto pte_unmap;
- if (unlikely(pte_val(pte) != pte_val(*ptep))) {
- put_page(head);
+ if (unlikely(pmd_val(pmd) != pmd_val(*pmdp)) ||
+ unlikely(pte_val(pte) != pte_val(*ptep))) {
+ put_compound_head(head, 1, flags);
goto pte_unmap;
}
VM_BUG_ON_PAGE(compound_head(page) != head, page);
+ /*
+ * We need to make the page accessible if and only if we are
+ * going to access its content (the FOLL_PIN case). Please
+ * see Documentation/core-api/pin_user_pages.rst for
+ * details.
+ */
+ if (flags & FOLL_PIN) {
+ ret = arch_make_page_accessible(page);
+ if (ret) {
+ unpin_user_page(page);
+ goto pte_unmap;
+ }
+ }
SetPageReferenced(page);
pages[*nr] = page;
(*nr)++;
@@ -1482,19 +2222,21 @@
* to be special.
*
* For a futex to be placed on a THP tail page, get_futex_key requires a
- * __get_user_pages_fast implementation that can pin pages. Thus it's still
+ * get_user_pages_fast_only implementation that can pin pages. Thus it's still
* useful to have gup_huge_pmd even if we can't operate on ptes.
*/
-static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
- int write, struct page **pages, int *nr)
+static int gup_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
+ unsigned long end, unsigned int flags,
+ struct page **pages, int *nr)
{
return 0;
}
#endif /* CONFIG_ARCH_HAS_PTE_SPECIAL */
-#if defined(__HAVE_ARCH_PTE_DEVMAP) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
+#if defined(CONFIG_ARCH_HAS_PTE_DEVMAP) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
static int __gup_device_huge(unsigned long pfn, unsigned long addr,
- unsigned long end, struct page **pages, int *nr)
+ unsigned long end, unsigned int flags,
+ struct page **pages, int *nr)
{
int nr_start = *nr;
struct dev_pagemap *pgmap = NULL;
@@ -1504,12 +2246,15 @@
pgmap = get_dev_pagemap(pfn, pgmap);
if (unlikely(!pgmap)) {
- undo_dev_pagemap(nr, nr_start, pages);
+ undo_dev_pagemap(nr, nr_start, flags, pages);
return 0;
}
SetPageReferenced(page);
pages[*nr] = page;
- get_page(page);
+ if (unlikely(!try_grab_page(page, flags))) {
+ undo_dev_pagemap(nr, nr_start, flags, pages);
+ return 0;
+ }
(*nr)++;
pfn++;
} while (addr += PAGE_SIZE, addr != end);
@@ -1520,174 +2265,246 @@
}
static int __gup_device_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
- unsigned long end, struct page **pages, int *nr)
+ unsigned long end, unsigned int flags,
+ struct page **pages, int *nr)
{
unsigned long fault_pfn;
int nr_start = *nr;
fault_pfn = pmd_pfn(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
- if (!__gup_device_huge(fault_pfn, addr, end, pages, nr))
+ if (!__gup_device_huge(fault_pfn, addr, end, flags, pages, nr))
return 0;
if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {
- undo_dev_pagemap(nr, nr_start, pages);
+ undo_dev_pagemap(nr, nr_start, flags, pages);
return 0;
}
return 1;
}
static int __gup_device_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
- unsigned long end, struct page **pages, int *nr)
+ unsigned long end, unsigned int flags,
+ struct page **pages, int *nr)
{
unsigned long fault_pfn;
int nr_start = *nr;
fault_pfn = pud_pfn(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
- if (!__gup_device_huge(fault_pfn, addr, end, pages, nr))
+ if (!__gup_device_huge(fault_pfn, addr, end, flags, pages, nr))
return 0;
if (unlikely(pud_val(orig) != pud_val(*pudp))) {
- undo_dev_pagemap(nr, nr_start, pages);
+ undo_dev_pagemap(nr, nr_start, flags, pages);
return 0;
}
return 1;
}
#else
static int __gup_device_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
- unsigned long end, struct page **pages, int *nr)
+ unsigned long end, unsigned int flags,
+ struct page **pages, int *nr)
{
BUILD_BUG();
return 0;
}
static int __gup_device_huge_pud(pud_t pud, pud_t *pudp, unsigned long addr,
- unsigned long end, struct page **pages, int *nr)
+ unsigned long end, unsigned int flags,
+ struct page **pages, int *nr)
{
BUILD_BUG();
return 0;
}
#endif
+static int record_subpages(struct page *page, unsigned long addr,
+ unsigned long end, struct page **pages)
+{
+ int nr;
+
+ for (nr = 0; addr != end; addr += PAGE_SIZE)
+ pages[nr++] = page++;
+
+ return nr;
+}
+
+#ifdef CONFIG_ARCH_HAS_HUGEPD
+static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
+ unsigned long sz)
+{
+ unsigned long __boundary = (addr + sz) & ~(sz-1);
+ return (__boundary - 1 < end - 1) ? __boundary : end;
+}
+
+static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
+ unsigned long end, unsigned int flags,
+ struct page **pages, int *nr)
+{
+ unsigned long pte_end;
+ struct page *head, *page;
+ pte_t pte;
+ int refs;
+
+ pte_end = (addr + sz) & ~(sz-1);
+ if (pte_end < end)
+ end = pte_end;
+
+ pte = huge_ptep_get(ptep);
+
+ if (!pte_access_permitted(pte, flags & FOLL_WRITE))
+ return 0;
+
+ /* hugepages are never "special" */
+ VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+
+ head = pte_page(pte);
+ page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
+ refs = record_subpages(page, addr, end, pages + *nr);
+
+ head = try_grab_compound_head(head, refs, flags);
+ if (!head)
+ return 0;
+
+ if (unlikely(pte_val(pte) != pte_val(*ptep))) {
+ put_compound_head(head, refs, flags);
+ return 0;
+ }
+
+ *nr += refs;
+ SetPageReferenced(head);
+ return 1;
+}
+
+static int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
+ unsigned int pdshift, unsigned long end, unsigned int flags,
+ struct page **pages, int *nr)
+{
+ pte_t *ptep;
+ unsigned long sz = 1UL << hugepd_shift(hugepd);
+ unsigned long next;
+
+ ptep = hugepte_offset(hugepd, addr, pdshift);
+ do {
+ next = hugepte_addr_end(addr, end, sz);
+ if (!gup_hugepte(ptep, sz, addr, end, flags, pages, nr))
+ return 0;
+ } while (ptep++, addr = next, addr != end);
+
+ return 1;
+}
+#else
+static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
+ unsigned int pdshift, unsigned long end, unsigned int flags,
+ struct page **pages, int *nr)
+{
+ return 0;
+}
+#endif /* CONFIG_ARCH_HAS_HUGEPD */
+
static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
- unsigned long end, int write, struct page **pages, int *nr)
+ unsigned long end, unsigned int flags,
+ struct page **pages, int *nr)
{
struct page *head, *page;
int refs;
- if (!pmd_access_permitted(orig, write))
+ if (!pmd_access_permitted(orig, flags & FOLL_WRITE))
return 0;
- if (pmd_devmap(orig))
- return __gup_device_huge_pmd(orig, pmdp, addr, end, pages, nr);
-
- refs = 0;
- page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
- do {
- pages[*nr] = page;
- (*nr)++;
- page++;
- refs++;
- } while (addr += PAGE_SIZE, addr != end);
-
- head = try_get_compound_head(pmd_page(orig), refs);
- if (!head) {
- *nr -= refs;
- return 0;
+ if (pmd_devmap(orig)) {
+ if (unlikely(flags & FOLL_LONGTERM))
+ return 0;
+ return __gup_device_huge_pmd(orig, pmdp, addr, end, flags,
+ pages, nr);
}
+
+ page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
+ refs = record_subpages(page, addr, end, pages + *nr);
+
+ head = try_grab_compound_head(pmd_page(orig), refs, flags);
+ if (!head)
+ return 0;
if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {
- *nr -= refs;
- while (refs--)
- put_page(head);
+ put_compound_head(head, refs, flags);
return 0;
}
+ *nr += refs;
SetPageReferenced(head);
return 1;
}
static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
- unsigned long end, int write, struct page **pages, int *nr)
+ unsigned long end, unsigned int flags,
+ struct page **pages, int *nr)
{
struct page *head, *page;
int refs;
- if (!pud_access_permitted(orig, write))
+ if (!pud_access_permitted(orig, flags & FOLL_WRITE))
return 0;
- if (pud_devmap(orig))
- return __gup_device_huge_pud(orig, pudp, addr, end, pages, nr);
-
- refs = 0;
- page = pud_page(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
- do {
- pages[*nr] = page;
- (*nr)++;
- page++;
- refs++;
- } while (addr += PAGE_SIZE, addr != end);
-
- head = try_get_compound_head(pud_page(orig), refs);
- if (!head) {
- *nr -= refs;
- return 0;
+ if (pud_devmap(orig)) {
+ if (unlikely(flags & FOLL_LONGTERM))
+ return 0;
+ return __gup_device_huge_pud(orig, pudp, addr, end, flags,
+ pages, nr);
}
+
+ page = pud_page(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
+ refs = record_subpages(page, addr, end, pages + *nr);
+
+ head = try_grab_compound_head(pud_page(orig), refs, flags);
+ if (!head)
+ return 0;
if (unlikely(pud_val(orig) != pud_val(*pudp))) {
- *nr -= refs;
- while (refs--)
- put_page(head);
+ put_compound_head(head, refs, flags);
return 0;
}
+ *nr += refs;
SetPageReferenced(head);
return 1;
}
static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
- unsigned long end, int write,
+ unsigned long end, unsigned int flags,
struct page **pages, int *nr)
{
int refs;
struct page *head, *page;
- if (!pgd_access_permitted(orig, write))
+ if (!pgd_access_permitted(orig, flags & FOLL_WRITE))
return 0;
BUILD_BUG_ON(pgd_devmap(orig));
- refs = 0;
- page = pgd_page(orig) + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT);
- do {
- pages[*nr] = page;
- (*nr)++;
- page++;
- refs++;
- } while (addr += PAGE_SIZE, addr != end);
- head = try_get_compound_head(pgd_page(orig), refs);
- if (!head) {
- *nr -= refs;
+ page = pgd_page(orig) + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT);
+ refs = record_subpages(page, addr, end, pages + *nr);
+
+ head = try_grab_compound_head(pgd_page(orig), refs, flags);
+ if (!head)
return 0;
- }
if (unlikely(pgd_val(orig) != pgd_val(*pgdp))) {
- *nr -= refs;
- while (refs--)
- put_page(head);
+ put_compound_head(head, refs, flags);
return 0;
}
+ *nr += refs;
SetPageReferenced(head);
return 1;
}
-static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
- int write, struct page **pages, int *nr)
+static int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, unsigned long end,
+ unsigned int flags, struct page **pages, int *nr)
{
unsigned long next;
pmd_t *pmdp;
- pmdp = pmd_offset(&pud, addr);
+ pmdp = pmd_offset_lockless(pudp, pud, addr);
do {
pmd_t pmd = READ_ONCE(*pmdp);
@@ -1705,7 +2522,7 @@
if (pmd_protnone(pmd))
return 0;
- if (!gup_huge_pmd(pmd, pmdp, addr, next, write,
+ if (!gup_huge_pmd(pmd, pmdp, addr, next, flags,
pages, nr))
return 0;
@@ -1715,50 +2532,50 @@
* pmd format and THP pmd format
*/
if (!gup_huge_pd(__hugepd(pmd_val(pmd)), addr,
- PMD_SHIFT, next, write, pages, nr))
+ PMD_SHIFT, next, flags, pages, nr))
return 0;
- } else if (!gup_pte_range(pmd, addr, next, write, pages, nr))
+ } else if (!gup_pte_range(pmd, pmdp, addr, next, flags, pages, nr))
return 0;
} while (pmdp++, addr = next, addr != end);
return 1;
}
-static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end,
- int write, struct page **pages, int *nr)
+static int gup_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr, unsigned long end,
+ unsigned int flags, struct page **pages, int *nr)
{
unsigned long next;
pud_t *pudp;
- pudp = pud_offset(&p4d, addr);
+ pudp = pud_offset_lockless(p4dp, p4d, addr);
do {
pud_t pud = READ_ONCE(*pudp);
next = pud_addr_end(addr, end);
- if (pud_none(pud))
+ if (unlikely(!pud_present(pud)))
return 0;
- if (unlikely(pud_huge(pud))) {
- if (!gup_huge_pud(pud, pudp, addr, next, write,
+ if (unlikely(pud_huge(pud) || pud_devmap(pud))) {
+ if (!gup_huge_pud(pud, pudp, addr, next, flags,
pages, nr))
return 0;
} else if (unlikely(is_hugepd(__hugepd(pud_val(pud))))) {
if (!gup_huge_pd(__hugepd(pud_val(pud)), addr,
- PUD_SHIFT, next, write, pages, nr))
+ PUD_SHIFT, next, flags, pages, nr))
return 0;
- } else if (!gup_pmd_range(pud, addr, next, write, pages, nr))
+ } else if (!gup_pmd_range(pudp, pud, addr, next, flags, pages, nr))
return 0;
} while (pudp++, addr = next, addr != end);
return 1;
}
-static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end,
- int write, struct page **pages, int *nr)
+static int gup_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr, unsigned long end,
+ unsigned int flags, struct page **pages, int *nr)
{
unsigned long next;
p4d_t *p4dp;
- p4dp = p4d_offset(&pgd, addr);
+ p4dp = p4d_offset_lockless(pgdp, pgd, addr);
do {
p4d_t p4d = READ_ONCE(*p4dp);
@@ -1768,9 +2585,9 @@
BUILD_BUG_ON(p4d_huge(p4d));
if (unlikely(is_hugepd(__hugepd(p4d_val(p4d))))) {
if (!gup_huge_pd(__hugepd(p4d_val(p4d)), addr,
- P4D_SHIFT, next, write, pages, nr))
+ P4D_SHIFT, next, flags, pages, nr))
return 0;
- } else if (!gup_pud_range(p4d, addr, next, write, pages, nr))
+ } else if (!gup_pud_range(p4dp, p4d, addr, next, flags, pages, nr))
return 0;
} while (p4dp++, addr = next, addr != end);
@@ -1778,7 +2595,7 @@
}
static void gup_pgd_range(unsigned long addr, unsigned long end,
- int write, struct page **pages, int *nr)
+ unsigned int flags, struct page **pages, int *nr)
{
unsigned long next;
pgd_t *pgdp;
@@ -1791,152 +2608,411 @@
if (pgd_none(pgd))
return;
if (unlikely(pgd_huge(pgd))) {
- if (!gup_huge_pgd(pgd, pgdp, addr, next, write,
+ if (!gup_huge_pgd(pgd, pgdp, addr, next, flags,
pages, nr))
return;
} else if (unlikely(is_hugepd(__hugepd(pgd_val(pgd))))) {
if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr,
- PGDIR_SHIFT, next, write, pages, nr))
+ PGDIR_SHIFT, next, flags, pages, nr))
return;
- } else if (!gup_p4d_range(pgd, addr, next, write, pages, nr))
+ } else if (!gup_p4d_range(pgdp, pgd, addr, next, flags, pages, nr))
return;
} while (pgdp++, addr = next, addr != end);
}
+#else
+static inline void gup_pgd_range(unsigned long addr, unsigned long end,
+ unsigned int flags, struct page **pages, int *nr)
+{
+}
+#endif /* CONFIG_HAVE_FAST_GUP */
#ifndef gup_fast_permitted
/*
- * Check if it's allowed to use __get_user_pages_fast() for the range, or
+ * Check if it's allowed to use get_user_pages_fast_only() for the range, or
* we need to fall back to the slow version:
*/
-bool gup_fast_permitted(unsigned long start, int nr_pages, int write)
+static bool gup_fast_permitted(unsigned long start, unsigned long end)
{
- unsigned long len, end;
-
- len = (unsigned long) nr_pages << PAGE_SHIFT;
- end = start + len;
- return end >= start;
+ return true;
}
#endif
-/*
- * Like get_user_pages_fast() except it's IRQ-safe in that it won't fall back to
- * the regular GUP.
- * Note a difference with get_user_pages_fast: this always returns the
- * number of pages pinned, 0 if no pages were pinned.
- *
- * Careful, careful! COW breaking can go either way, so a non-write
- * access can get ambiguous page results. If you call this function without
- * 'write' set, you'd better be sure that you're ok with that ambiguity.
- */
-int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
- struct page **pages)
+static int __gup_longterm_unlocked(unsigned long start, int nr_pages,
+ unsigned int gup_flags, struct page **pages)
{
- unsigned long addr, len, end;
- unsigned long flags;
- int nr = 0;
-
- start &= PAGE_MASK;
- addr = start;
- len = (unsigned long) nr_pages << PAGE_SHIFT;
- end = start + len;
-
- if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ,
- (void __user *)start, len)))
- return 0;
+ int ret;
/*
- * Disable interrupts. We use the nested form as we can already have
- * interrupts disabled by get_futex_key.
- *
- * With interrupts disabled, we block page table pages from being
- * freed from under us. See mmu_gather_tlb in asm-generic/tlb.h
- * for more details.
- *
- * We do not adopt an rcu_read_lock(.) here as we also want to
- * block IPIs that come from THPs splitting.
- *
- * NOTE! We allow read-only gup_fast() here, but you'd better be
- * careful about possible COW pages. You'll get _a_ COW page, but
- * not necessarily the one you intended to get depending on what
- * COW event happens after this. COW may break the page copy in a
- * random direction.
+ * FIXME: FOLL_LONGTERM does not work with
+ * get_user_pages_unlocked() (see comments in that function)
*/
-
- if (gup_fast_permitted(start, nr_pages, write)) {
- local_irq_save(flags);
- gup_pgd_range(addr, end, write, pages, &nr);
- local_irq_restore(flags);
- }
-
- return nr;
-}
-
-/**
- * get_user_pages_fast() - pin user pages in memory
- * @start: starting user address
- * @nr_pages: number of pages from start to pin
- * @write: whether pages will be written to
- * @pages: array that receives pointers to the pages pinned.
- * Should be at least nr_pages long.
- *
- * Attempt to pin user pages in memory without taking mm->mmap_sem.
- * If not successful, it will fall back to taking the lock and
- * calling get_user_pages().
- *
- * Returns number of pages pinned. This may be fewer than the number
- * requested. If nr_pages is 0 or negative, returns 0. If no pages
- * were pinned, returns -errno.
- */
-int get_user_pages_fast(unsigned long start, int nr_pages, int write,
- struct page **pages)
-{
- unsigned long addr, len, end;
- int nr = 0, ret = 0;
-
- start &= PAGE_MASK;
- addr = start;
- len = (unsigned long) nr_pages << PAGE_SHIFT;
- end = start + len;
-
- if (nr_pages <= 0)
- return 0;
-
- if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ,
- (void __user *)start, len)))
- return -EFAULT;
-
- /*
- * The FAST_GUP case requires FOLL_WRITE even for pure reads,
- * because get_user_pages() may need to cause an early COW in
- * order to avoid confusing the normal COW routines. So only
- * targets that are already writable are safe to do by just
- * looking at the page tables.
- */
- if (gup_fast_permitted(start, nr_pages, write)) {
- local_irq_disable();
- gup_pgd_range(addr, end, 1, pages, &nr);
- local_irq_enable();
- ret = nr;
- }
-
- if (nr < nr_pages) {
- /* Try to get the remaining pages with get_user_pages */
- start += nr << PAGE_SHIFT;
- pages += nr;
-
- ret = get_user_pages_unlocked(start, nr_pages - nr, pages,
- write ? FOLL_WRITE : 0);
-
- /* Have to be a bit careful with return values */
- if (nr > 0) {
- if (ret < 0)
- ret = nr;
- else
- ret += nr;
- }
+ if (gup_flags & FOLL_LONGTERM) {
+ mmap_read_lock(current->mm);
+ ret = __gup_longterm_locked(current->mm,
+ start, nr_pages,
+ pages, NULL, gup_flags);
+ mmap_read_unlock(current->mm);
+ } else {
+ ret = get_user_pages_unlocked(start, nr_pages,
+ pages, gup_flags);
}
return ret;
}
-#endif /* CONFIG_HAVE_GENERIC_GUP */
+static unsigned long lockless_pages_from_mm(unsigned long start,
+ unsigned long end,
+ unsigned int gup_flags,
+ struct page **pages)
+{
+ unsigned long flags;
+ int nr_pinned = 0;
+ unsigned seq;
+
+ if (!IS_ENABLED(CONFIG_HAVE_FAST_GUP) ||
+ !gup_fast_permitted(start, end))
+ return 0;
+
+ if (gup_flags & FOLL_PIN) {
+ seq = raw_read_seqcount(¤t->mm->write_protect_seq);
+ if (seq & 1)
+ return 0;
+ }
+
+ /*
+ * Disable interrupts. The nested form is used, in order to allow full,
+ * general purpose use of this routine.
+ *
+ * With interrupts disabled, we block page table pages from being freed
+ * from under us. See struct mmu_table_batch comments in
+ * include/asm-generic/tlb.h for more details.
+ *
+ * We do not adopt an rcu_read_lock() here as we also want to block IPIs
+ * that come from THPs splitting.
+ */
+ local_irq_save(flags);
+ gup_pgd_range(start, end, gup_flags, pages, &nr_pinned);
+ local_irq_restore(flags);
+
+ /*
+ * When pinning pages for DMA there could be a concurrent write protect
+ * from fork() via copy_page_range(), in this case always fail fast GUP.
+ */
+ if (gup_flags & FOLL_PIN) {
+ if (read_seqcount_retry(¤t->mm->write_protect_seq, seq)) {
+ unpin_user_pages(pages, nr_pinned);
+ return 0;
+ }
+ }
+ return nr_pinned;
+}
+
+static int internal_get_user_pages_fast(unsigned long start,
+ unsigned long nr_pages,
+ unsigned int gup_flags,
+ struct page **pages)
+{
+ unsigned long len, end;
+ unsigned long nr_pinned;
+ int ret;
+
+ if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM |
+ FOLL_FORCE | FOLL_PIN | FOLL_GET |
+ FOLL_FAST_ONLY)))
+ return -EINVAL;
+
+ if (gup_flags & FOLL_PIN)
+ atomic_set(¤t->mm->has_pinned, 1);
+
+ if (!(gup_flags & FOLL_FAST_ONLY))
+ might_lock_read(¤t->mm->mmap_lock);
+
+ start = untagged_addr(start) & PAGE_MASK;
+ len = nr_pages << PAGE_SHIFT;
+ if (check_add_overflow(start, len, &end))
+ return 0;
+ if (unlikely(!access_ok((void __user *)start, len)))
+ return -EFAULT;
+
+ nr_pinned = lockless_pages_from_mm(start, end, gup_flags, pages);
+ if (nr_pinned == nr_pages || gup_flags & FOLL_FAST_ONLY)
+ return nr_pinned;
+
+ /* Slow path: try to get the remaining pages with get_user_pages */
+ start += nr_pinned << PAGE_SHIFT;
+ pages += nr_pinned;
+ ret = __gup_longterm_unlocked(start, nr_pages - nr_pinned, gup_flags,
+ pages);
+ if (ret < 0) {
+ /*
+ * The caller has to unpin the pages we already pinned so
+ * returning -errno is not an option
+ */
+ if (nr_pinned)
+ return nr_pinned;
+ return ret;
+ }
+ return ret + nr_pinned;
+}
+
+/**
+ * get_user_pages_fast_only() - pin user pages in memory
+ * @start: starting user address
+ * @nr_pages: number of pages from start to pin
+ * @gup_flags: flags modifying pin behaviour
+ * @pages: array that receives pointers to the pages pinned.
+ * Should be at least nr_pages long.
+ *
+ * Like get_user_pages_fast() except it's IRQ-safe in that it won't fall back to
+ * the regular GUP.
+ * Note a difference with get_user_pages_fast: this always returns the
+ * number of pages pinned, 0 if no pages were pinned.
+ *
+ * If the architecture does not support this function, simply return with no
+ * pages pinned.
+ *
+ * Careful, careful! COW breaking can go either way, so a non-write
+ * access can get ambiguous page results. If you call this function without
+ * 'write' set, you'd better be sure that you're ok with that ambiguity.
+ */
+int get_user_pages_fast_only(unsigned long start, int nr_pages,
+ unsigned int gup_flags, struct page **pages)
+{
+ int nr_pinned;
+ /*
+ * Internally (within mm/gup.c), gup fast variants must set FOLL_GET,
+ * because gup fast is always a "pin with a +1 page refcount" request.
+ *
+ * FOLL_FAST_ONLY is required in order to match the API description of
+ * this routine: no fall back to regular ("slow") GUP.
+ */
+ gup_flags |= FOLL_GET | FOLL_FAST_ONLY;
+
+ nr_pinned = internal_get_user_pages_fast(start, nr_pages, gup_flags,
+ pages);
+
+ /*
+ * As specified in the API description above, this routine is not
+ * allowed to return negative values. However, the common core
+ * routine internal_get_user_pages_fast() *can* return -errno.
+ * Therefore, correct for that here:
+ */
+ if (nr_pinned < 0)
+ nr_pinned = 0;
+
+ return nr_pinned;
+}
+EXPORT_SYMBOL_GPL(get_user_pages_fast_only);
+
+/**
+ * get_user_pages_fast() - pin user pages in memory
+ * @start: starting user address
+ * @nr_pages: number of pages from start to pin
+ * @gup_flags: flags modifying pin behaviour
+ * @pages: array that receives pointers to the pages pinned.
+ * Should be at least nr_pages long.
+ *
+ * Attempt to pin user pages in memory without taking mm->mmap_lock.
+ * If not successful, it will fall back to taking the lock and
+ * calling get_user_pages().
+ *
+ * Returns number of pages pinned. This may be fewer than the number requested.
+ * If nr_pages is 0 or negative, returns 0. If no pages were pinned, returns
+ * -errno.
+ */
+int get_user_pages_fast(unsigned long start, int nr_pages,
+ unsigned int gup_flags, struct page **pages)
+{
+ if (!is_valid_gup_flags(gup_flags))
+ return -EINVAL;
+
+ /*
+ * The caller may or may not have explicitly set FOLL_GET; either way is
+ * OK. However, internally (within mm/gup.c), gup fast variants must set
+ * FOLL_GET, because gup fast is always a "pin with a +1 page refcount"
+ * request.
+ */
+ gup_flags |= FOLL_GET;
+ return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages);
+}
+EXPORT_SYMBOL_GPL(get_user_pages_fast);
+
+/**
+ * pin_user_pages_fast() - pin user pages in memory without taking locks
+ *
+ * @start: starting user address
+ * @nr_pages: number of pages from start to pin
+ * @gup_flags: flags modifying pin behaviour
+ * @pages: array that receives pointers to the pages pinned.
+ * Should be at least nr_pages long.
+ *
+ * Nearly the same as get_user_pages_fast(), except that FOLL_PIN is set. See
+ * get_user_pages_fast() for documentation on the function arguments, because
+ * the arguments here are identical.
+ *
+ * FOLL_PIN means that the pages must be released via unpin_user_page(). Please
+ * see Documentation/core-api/pin_user_pages.rst for further details.
+ */
+int pin_user_pages_fast(unsigned long start, int nr_pages,
+ unsigned int gup_flags, struct page **pages)
+{
+ /* FOLL_GET and FOLL_PIN are mutually exclusive. */
+ if (WARN_ON_ONCE(gup_flags & FOLL_GET))
+ return -EINVAL;
+
+ gup_flags |= FOLL_PIN;
+ return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages);
+}
+EXPORT_SYMBOL_GPL(pin_user_pages_fast);
+
+/*
+ * This is the FOLL_PIN equivalent of get_user_pages_fast_only(). Behavior
+ * is the same, except that this one sets FOLL_PIN instead of FOLL_GET.
+ *
+ * The API rules are the same, too: no negative values may be returned.
+ */
+int pin_user_pages_fast_only(unsigned long start, int nr_pages,
+ unsigned int gup_flags, struct page **pages)
+{
+ int nr_pinned;
+
+ /*
+ * FOLL_GET and FOLL_PIN are mutually exclusive. Note that the API
+ * rules require returning 0, rather than -errno:
+ */
+ if (WARN_ON_ONCE(gup_flags & FOLL_GET))
+ return 0;
+ /*
+ * FOLL_FAST_ONLY is required in order to match the API description of
+ * this routine: no fall back to regular ("slow") GUP.
+ */
+ gup_flags |= (FOLL_PIN | FOLL_FAST_ONLY);
+ nr_pinned = internal_get_user_pages_fast(start, nr_pages, gup_flags,
+ pages);
+ /*
+ * This routine is not allowed to return negative values. However,
+ * internal_get_user_pages_fast() *can* return -errno. Therefore,
+ * correct for that here:
+ */
+ if (nr_pinned < 0)
+ nr_pinned = 0;
+
+ return nr_pinned;
+}
+EXPORT_SYMBOL_GPL(pin_user_pages_fast_only);
+
+/**
+ * pin_user_pages_remote() - pin pages of a remote process
+ *
+ * @mm: mm_struct of target mm
+ * @start: starting user address
+ * @nr_pages: number of pages from start to pin
+ * @gup_flags: flags modifying lookup behaviour
+ * @pages: array that receives pointers to the pages pinned.
+ * Should be at least nr_pages long. Or NULL, if caller
+ * only intends to ensure the pages are faulted in.
+ * @vmas: array of pointers to vmas corresponding to each page.
+ * Or NULL if the caller does not require them.
+ * @locked: pointer to lock flag indicating whether lock is held and
+ * subsequently whether VM_FAULT_RETRY functionality can be
+ * utilised. Lock must initially be held.
+ *
+ * Nearly the same as get_user_pages_remote(), except that FOLL_PIN is set. See
+ * get_user_pages_remote() for documentation on the function arguments, because
+ * the arguments here are identical.
+ *
+ * FOLL_PIN means that the pages must be released via unpin_user_page(). Please
+ * see Documentation/core-api/pin_user_pages.rst for details.
+ */
+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)
+{
+ /* FOLL_GET and FOLL_PIN are mutually exclusive. */
+ if (WARN_ON_ONCE(gup_flags & FOLL_GET))
+ return -EINVAL;
+
+ gup_flags |= FOLL_PIN;
+ return __get_user_pages_remote(mm, start, nr_pages, gup_flags,
+ pages, vmas, locked);
+}
+EXPORT_SYMBOL(pin_user_pages_remote);
+
+/**
+ * pin_user_pages() - pin user pages in memory for use by other devices
+ *
+ * @start: starting user address
+ * @nr_pages: number of pages from start to pin
+ * @gup_flags: flags modifying lookup behaviour
+ * @pages: array that receives pointers to the pages pinned.
+ * Should be at least nr_pages long. Or NULL, if caller
+ * only intends to ensure the pages are faulted in.
+ * @vmas: array of pointers to vmas corresponding to each page.
+ * Or NULL if the caller does not require them.
+ *
+ * Nearly the same as get_user_pages(), except that FOLL_TOUCH is not set, and
+ * FOLL_PIN is set.
+ *
+ * FOLL_PIN means that the pages must be released via unpin_user_page(). Please
+ * see Documentation/core-api/pin_user_pages.rst for details.
+ */
+long pin_user_pages(unsigned long start, unsigned long nr_pages,
+ unsigned int gup_flags, struct page **pages,
+ struct vm_area_struct **vmas)
+{
+ /* FOLL_GET and FOLL_PIN are mutually exclusive. */
+ if (WARN_ON_ONCE(gup_flags & FOLL_GET))
+ return -EINVAL;
+
+ gup_flags |= FOLL_PIN;
+ return __gup_longterm_locked(current->mm, start, nr_pages,
+ pages, vmas, gup_flags);
+}
+EXPORT_SYMBOL(pin_user_pages);
+
+/*
+ * pin_user_pages_unlocked() is the FOLL_PIN variant of
+ * get_user_pages_unlocked(). Behavior is the same, except that this one sets
+ * FOLL_PIN and rejects FOLL_GET.
+ */
+long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
+ struct page **pages, unsigned int gup_flags)
+{
+ /* FOLL_GET and FOLL_PIN are mutually exclusive. */
+ if (WARN_ON_ONCE(gup_flags & FOLL_GET))
+ return -EINVAL;
+
+ gup_flags |= FOLL_PIN;
+ return get_user_pages_unlocked(start, nr_pages, pages, gup_flags);
+}
+EXPORT_SYMBOL(pin_user_pages_unlocked);
+
+/*
+ * pin_user_pages_locked() is the FOLL_PIN variant of get_user_pages_locked().
+ * Behavior is the same, except that this one sets FOLL_PIN and rejects
+ * FOLL_GET.
+ */
+long pin_user_pages_locked(unsigned long start, unsigned long nr_pages,
+ unsigned int gup_flags, struct page **pages,
+ int *locked)
+{
+ /*
+ * FIXME: Current FOLL_LONGTERM behavior is incompatible with
+ * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on
+ * vmas. As there are no users of this flag in this call we simply
+ * disallow this option for now.
+ */
+ if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM))
+ return -EINVAL;
+
+ /* FOLL_GET and FOLL_PIN are mutually exclusive. */
+ if (WARN_ON_ONCE(gup_flags & FOLL_GET))
+ return -EINVAL;
+
+ gup_flags |= FOLL_PIN;
+ return __get_user_pages_locked(current->mm, start, nr_pages,
+ pages, NULL, locked,
+ gup_flags | FOLL_TOUCH);
+}
+EXPORT_SYMBOL(pin_user_pages_locked);
--
Gitblit v1.6.2