In a previous commit, we added the mfill_atomic_install_pte() helper.
This helper does the job of setting up PTEs for an existing page, to map
it into a given VMA. It deals with both the anon and shmem cases, as
well as the shared and private cases.
In other words, shmem_mfill_atomic_pte() duplicates a case it already
handles. So, expose it, and let shmem_mfill_atomic_pte() use it
directly, to reduce code duplication.
This requires that we refactor shmem_mfill_atomic_pte() a bit:
Instead of doing accounting (shmem_recalc_inode() et al) part-way
through the PTE setup, do it afterward. This frees up
mfill_atomic_install_pte() from having to care about this accounting,
and means we don't need to e.g. shmem_uncharge() in the error path.
A side effect is this switches shmem_mfill_atomic_pte() to use
lru_cache_add_inactive_or_unevictable() instead of just lru_cache_add().
This wrapper does some extra accounting in an exceptional case, if
appropriate, so it's actually the more correct thing to use.
Signed-off-by: Axel Rasmussen <[email protected]>
---
include/linux/userfaultfd_k.h | 5 +++
mm/shmem.c | 58 ++++++++---------------------------
mm/userfaultfd.c | 17 ++++------
3 files changed, 23 insertions(+), 57 deletions(-)
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 794d1538b8ba..331d2ccf0bcc 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -53,6 +53,11 @@ enum mcopy_atomic_mode {
MCOPY_ATOMIC_CONTINUE,
};
+extern int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd,
+ struct vm_area_struct *dst_vma,
+ unsigned long dst_addr, struct page *page,
+ bool newly_allocated, bool wp_copy);
+
extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start,
unsigned long src_start, unsigned long len,
bool *mmap_changing, __u64 mode);
diff --git a/mm/shmem.c b/mm/shmem.c
index e361f1d81c8d..2e9f56c83489 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2378,14 +2378,11 @@ int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
struct address_space *mapping = inode->i_mapping;
gfp_t gfp = mapping_gfp_mask(mapping);
pgoff_t pgoff = linear_page_index(dst_vma, dst_addr);
- spinlock_t *ptl;
void *page_kaddr;
struct page *page;
- pte_t _dst_pte, *dst_pte;
int ret;
pgoff_t max_off;
- ret = -ENOMEM;
if (!shmem_inode_acct_block(inode, 1)) {
/*
* We may have got a page, returned -ENOENT triggering a retry,
@@ -2396,10 +2393,11 @@ int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
put_page(*pagep);
*pagep = NULL;
}
- goto out;
+ return -ENOMEM;
}
if (!*pagep) {
+ ret = -ENOMEM;
page = shmem_alloc_page(gfp, info, pgoff);
if (!page)
goto out_unacct_blocks;
@@ -2414,9 +2412,9 @@ int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
/* fallback to copy_from_user outside mmap_lock */
if (unlikely(ret)) {
*pagep = page;
- shmem_inode_unacct_blocks(inode, 1);
+ ret = -ENOENT;
/* don't free the page */
- return -ENOENT;
+ goto out_unacct_blocks;
}
} else { /* ZEROPAGE */
clear_highpage(page);
@@ -2442,32 +2440,10 @@ int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
if (ret)
goto out_release;
- _dst_pte = mk_pte(page, dst_vma->vm_page_prot);
- if (dst_vma->vm_flags & VM_WRITE)
- _dst_pte = pte_mkwrite(pte_mkdirty(_dst_pte));
- else {
- /*
- * We don't set the pte dirty if the vma has no
- * VM_WRITE permission, so mark the page dirty or it
- * could be freed from under us. We could do it
- * unconditionally before unlock_page(), but doing it
- * only if VM_WRITE is not set is faster.
- */
- set_page_dirty(page);
- }
-
- dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
-
- ret = -EFAULT;
- max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
- if (unlikely(pgoff >= max_off))
- goto out_release_unlock;
-
- ret = -EEXIST;
- if (!pte_none(*dst_pte))
- goto out_release_unlock;
-
- lru_cache_add(page);
+ ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr,
+ page, true, false);
+ if (ret)
+ goto out_delete_from_cache;
spin_lock_irq(&info->lock);
info->alloced++;
@@ -2475,27 +2451,17 @@ int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
shmem_recalc_inode(inode);
spin_unlock_irq(&info->lock);
- inc_mm_counter(dst_mm, mm_counter_file(page));
- page_add_file_rmap(page, false);
- set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
-
- /* No need to invalidate - it was non-present before */
- update_mmu_cache(dst_vma, dst_addr, dst_pte);
- pte_unmap_unlock(dst_pte, ptl);
+ SetPageDirty(page);
unlock_page(page);
- ret = 0;
-out:
- return ret;
-out_release_unlock:
- pte_unmap_unlock(dst_pte, ptl);
- ClearPageDirty(page);
+ return 0;
+out_delete_from_cache:
delete_from_page_cache(page);
out_release:
unlock_page(page);
put_page(page);
out_unacct_blocks:
shmem_inode_unacct_blocks(inode, 1);
- goto out;
+ return ret;
}
#endif /* CONFIG_USERFAULTFD */
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index d1ac73a0d2a9..5508f7d9e2dc 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -51,18 +51,13 @@ struct vm_area_struct *find_dst_vma(struct mm_struct *dst_mm,
/*
* Install PTEs, to map dst_addr (within dst_vma) to page.
*
- * This function handles MCOPY_ATOMIC_CONTINUE (which is always file-backed),
- * whether or not dst_vma is VM_SHARED. It also handles the more general
- * MCOPY_ATOMIC_NORMAL case, when dst_vma is *not* VM_SHARED (it may be file
- * backed, or not).
- *
- * Note that MCOPY_ATOMIC_NORMAL for a VM_SHARED dst_vma is handled by
- * shmem_mcopy_atomic_pte instead.
+ * This function handles both MCOPY_ATOMIC_NORMAL and _CONTINUE for both shmem
+ * and anon, and for both shared and private VMAs.
*/
-static int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd,
- struct vm_area_struct *dst_vma,
- unsigned long dst_addr, struct page *page,
- bool newly_allocated, bool wp_copy)
+int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd,
+ struct vm_area_struct *dst_vma,
+ unsigned long dst_addr, struct page *page,
+ bool newly_allocated, bool wp_copy)
{
int ret;
pte_t _dst_pte, *dst_pte;
--
2.31.1.527.g47e6f16901-goog
Axel,
On Mon, May 03, 2021 at 11:07:33AM -0700, Axel Rasmussen wrote:
> In a previous commit, we added the mfill_atomic_install_pte() helper.
> This helper does the job of setting up PTEs for an existing page, to map
> it into a given VMA. It deals with both the anon and shmem cases, as
> well as the shared and private cases.
>
> In other words, shmem_mfill_atomic_pte() duplicates a case it already
> handles. So, expose it, and let shmem_mfill_atomic_pte() use it
> directly, to reduce code duplication.
>
> This requires that we refactor shmem_mfill_atomic_pte() a bit:
>
> Instead of doing accounting (shmem_recalc_inode() et al) part-way
> through the PTE setup, do it afterward. This frees up
> mfill_atomic_install_pte() from having to care about this accounting,
> and means we don't need to e.g. shmem_uncharge() in the error path.
>
> A side effect is this switches shmem_mfill_atomic_pte() to use
> lru_cache_add_inactive_or_unevictable() instead of just lru_cache_add().
> This wrapper does some extra accounting in an exceptional case, if
> appropriate, so it's actually the more correct thing to use.
>
> Signed-off-by: Axel Rasmussen <[email protected]>
(The moving of "ret = -ENOMEM" seems unnecessary, but not a big deal I think)
Reviewed-by: Peter Xu <[email protected]>
Thanks,
--
Peter Xu
On Mon, 3 May 2021, Axel Rasmussen wrote:
> In a previous commit, we added the mfill_atomic_install_pte() helper.
> This helper does the job of setting up PTEs for an existing page, to map
> it into a given VMA. It deals with both the anon and shmem cases, as
> well as the shared and private cases.
>
> In other words, shmem_mfill_atomic_pte() duplicates a case it already
> handles. So, expose it, and let shmem_mfill_atomic_pte() use it
> directly, to reduce code duplication.
>
> This requires that we refactor shmem_mfill_atomic_pte() a bit:
>
> Instead of doing accounting (shmem_recalc_inode() et al) part-way
> through the PTE setup, do it afterward. This frees up
> mfill_atomic_install_pte() from having to care about this accounting,
> and means we don't need to e.g. shmem_uncharge() in the error path.
>
> A side effect is this switches shmem_mfill_atomic_pte() to use
> lru_cache_add_inactive_or_unevictable() instead of just lru_cache_add().
> This wrapper does some extra accounting in an exceptional case, if
> appropriate, so it's actually the more correct thing to use.
>
> Signed-off-by: Axel Rasmussen <[email protected]>
Acked-by: Hugh Dickins <[email protected]>
And thanks for doing those late mcopy->mfill renamings,
I think those represent Andrea's intent better.
As far as I'm concerned, this series is now ripe for picking
into mmotm (bearing in mind the dependencies you noted in 00/10):
thank you Axel.
> ---
> include/linux/userfaultfd_k.h | 5 +++
> mm/shmem.c | 58 ++++++++---------------------------
> mm/userfaultfd.c | 17 ++++------
> 3 files changed, 23 insertions(+), 57 deletions(-)
>
> diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
> index 794d1538b8ba..331d2ccf0bcc 100644
> --- a/include/linux/userfaultfd_k.h
> +++ b/include/linux/userfaultfd_k.h
> @@ -53,6 +53,11 @@ enum mcopy_atomic_mode {
> MCOPY_ATOMIC_CONTINUE,
> };
>
> +extern int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd,
> + struct vm_area_struct *dst_vma,
> + unsigned long dst_addr, struct page *page,
> + bool newly_allocated, bool wp_copy);
> +
> extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start,
> unsigned long src_start, unsigned long len,
> bool *mmap_changing, __u64 mode);
> diff --git a/mm/shmem.c b/mm/shmem.c
> index e361f1d81c8d..2e9f56c83489 100644
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -2378,14 +2378,11 @@ int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
> struct address_space *mapping = inode->i_mapping;
> gfp_t gfp = mapping_gfp_mask(mapping);
> pgoff_t pgoff = linear_page_index(dst_vma, dst_addr);
> - spinlock_t *ptl;
> void *page_kaddr;
> struct page *page;
> - pte_t _dst_pte, *dst_pte;
> int ret;
> pgoff_t max_off;
>
> - ret = -ENOMEM;
> if (!shmem_inode_acct_block(inode, 1)) {
> /*
> * We may have got a page, returned -ENOENT triggering a retry,
> @@ -2396,10 +2393,11 @@ int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
> put_page(*pagep);
> *pagep = NULL;
> }
> - goto out;
> + return -ENOMEM;
> }
>
> if (!*pagep) {
> + ret = -ENOMEM;
> page = shmem_alloc_page(gfp, info, pgoff);
> if (!page)
> goto out_unacct_blocks;
> @@ -2414,9 +2412,9 @@ int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
> /* fallback to copy_from_user outside mmap_lock */
> if (unlikely(ret)) {
> *pagep = page;
> - shmem_inode_unacct_blocks(inode, 1);
> + ret = -ENOENT;
> /* don't free the page */
> - return -ENOENT;
> + goto out_unacct_blocks;
> }
> } else { /* ZEROPAGE */
> clear_highpage(page);
> @@ -2442,32 +2440,10 @@ int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
> if (ret)
> goto out_release;
>
> - _dst_pte = mk_pte(page, dst_vma->vm_page_prot);
> - if (dst_vma->vm_flags & VM_WRITE)
> - _dst_pte = pte_mkwrite(pte_mkdirty(_dst_pte));
> - else {
> - /*
> - * We don't set the pte dirty if the vma has no
> - * VM_WRITE permission, so mark the page dirty or it
> - * could be freed from under us. We could do it
> - * unconditionally before unlock_page(), but doing it
> - * only if VM_WRITE is not set is faster.
> - */
> - set_page_dirty(page);
> - }
> -
> - dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
> -
> - ret = -EFAULT;
> - max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
> - if (unlikely(pgoff >= max_off))
> - goto out_release_unlock;
> -
> - ret = -EEXIST;
> - if (!pte_none(*dst_pte))
> - goto out_release_unlock;
> -
> - lru_cache_add(page);
> + ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr,
> + page, true, false);
> + if (ret)
> + goto out_delete_from_cache;
>
> spin_lock_irq(&info->lock);
> info->alloced++;
> @@ -2475,27 +2451,17 @@ int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
> shmem_recalc_inode(inode);
> spin_unlock_irq(&info->lock);
>
> - inc_mm_counter(dst_mm, mm_counter_file(page));
> - page_add_file_rmap(page, false);
> - set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
> -
> - /* No need to invalidate - it was non-present before */
> - update_mmu_cache(dst_vma, dst_addr, dst_pte);
> - pte_unmap_unlock(dst_pte, ptl);
> + SetPageDirty(page);
> unlock_page(page);
> - ret = 0;
> -out:
> - return ret;
> -out_release_unlock:
> - pte_unmap_unlock(dst_pte, ptl);
> - ClearPageDirty(page);
> + return 0;
> +out_delete_from_cache:
> delete_from_page_cache(page);
> out_release:
> unlock_page(page);
> put_page(page);
> out_unacct_blocks:
> shmem_inode_unacct_blocks(inode, 1);
> - goto out;
> + return ret;
> }
> #endif /* CONFIG_USERFAULTFD */
>
> diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
> index d1ac73a0d2a9..5508f7d9e2dc 100644
> --- a/mm/userfaultfd.c
> +++ b/mm/userfaultfd.c
> @@ -51,18 +51,13 @@ struct vm_area_struct *find_dst_vma(struct mm_struct *dst_mm,
> /*
> * Install PTEs, to map dst_addr (within dst_vma) to page.
> *
> - * This function handles MCOPY_ATOMIC_CONTINUE (which is always file-backed),
> - * whether or not dst_vma is VM_SHARED. It also handles the more general
> - * MCOPY_ATOMIC_NORMAL case, when dst_vma is *not* VM_SHARED (it may be file
> - * backed, or not).
> - *
> - * Note that MCOPY_ATOMIC_NORMAL for a VM_SHARED dst_vma is handled by
> - * shmem_mcopy_atomic_pte instead.
> + * This function handles both MCOPY_ATOMIC_NORMAL and _CONTINUE for both shmem
> + * and anon, and for both shared and private VMAs.
> */
> -static int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd,
> - struct vm_area_struct *dst_vma,
> - unsigned long dst_addr, struct page *page,
> - bool newly_allocated, bool wp_copy)
> +int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd,
> + struct vm_area_struct *dst_vma,
> + unsigned long dst_addr, struct page *page,
> + bool newly_allocated, bool wp_copy)
> {
> int ret;
> pte_t _dst_pte, *dst_pte;
> --
> 2.31.1.527.g47e6f16901-goog
>
>