Allow multiple callers to install pages simultaneously by downgrading
the mmap_sem to non-exclusive mode. Races to the same PTE are handled
using get_user_pages_remote() to retrieve the already installed page.
This method significantly reduces contention in the mmap semaphore.
To ensure safety, vma_lookup() is used (instead of alloc->vma) to avoid
operating on an isolated VMA. In addition, zap_page_range_single() is
called under the alloc->mutex to avoid racing with the shrinker.
Many thanks to Barry Song who posted a similar approach [1].
Link: https://lore.kernel.org/all/20240902225009.34576-1-21cnbao@gmail.com/ [1]
Cc: David Hildenbrand <david@redhat.com>
Cc: Barry Song <v-songbaohua@oppo.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Signed-off-by: Carlos Llamas <cmllamas@google.com>
---
drivers/android/binder_alloc.c | 64 +++++++++++++++++++++-------------
1 file changed, 40 insertions(+), 24 deletions(-)
diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 7241bf4a3ff2..acdc05552603 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -221,26 +221,14 @@ static int binder_install_single_page(struct binder_alloc *alloc,
struct binder_lru_page *lru_page,
unsigned long addr)
{
+ struct vm_area_struct *vma;
struct page *page;
- int ret = 0;
+ long npages;
+ int ret;
if (!mmget_not_zero(alloc->mm))
return -ESRCH;
- /*
- * Protected with mmap_sem in write mode as multiple tasks
- * might race to install the same page.
- */
- mmap_write_lock(alloc->mm);
- if (binder_get_installed_page(lru_page))
- goto out;
-
- if (!alloc->vma) {
- pr_err("%d: %s failed, no vma\n", alloc->pid, __func__);
- ret = -ESRCH;
- goto out;
- }
-
page = alloc_page(GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO);
if (!page) {
pr_err("%d: failed to allocate page\n", alloc->pid);
@@ -248,19 +236,47 @@ static int binder_install_single_page(struct binder_alloc *alloc,
goto out;
}
- ret = vm_insert_page(alloc->vma, addr, page);
- if (ret) {
- pr_err("%d: %s failed to insert page at offset %lx with %d\n",
- alloc->pid, __func__, addr - alloc->buffer, ret);
+ mmap_read_lock(alloc->mm);
+ vma = vma_lookup(alloc->mm, addr);
+ if (!vma || vma != alloc->vma) {
+ mmap_read_unlock(alloc->mm);
__free_page(page);
- ret = -ENOMEM;
+ pr_err("%d: %s failed, no vma\n", alloc->pid, __func__);
+ ret = -ESRCH;
goto out;
}
- /* Mark page installation complete and safe to use */
- binder_set_installed_page(lru_page, page);
+ ret = vm_insert_page(vma, addr, page);
+ switch (ret) {
+ case -EBUSY:
+ /*
+ * EBUSY is ok. Someone installed the pte first but the
+ * lru_page->page_ptr has not been updated yet. Discard
+ * our page and look up the one already installed.
+ */
+ ret = 0;
+ __free_page(page);
+ npages = get_user_pages_remote(alloc->mm, addr, 1, 0, &page, NULL);
+ if (npages <= 0) {
+ pr_err("%d: failed to find page at offset %lx\n",
+ alloc->pid, addr - alloc->buffer);
+ ret = -ESRCH;
+ break;
+ }
+ fallthrough;
+ case 0:
+ /* Mark page installation complete and safe to use */
+ binder_set_installed_page(lru_page, page);
+ break;
+ default:
+ __free_page(page);
+ pr_err("%d: %s failed to insert page at offset %lx with %d\n",
+ alloc->pid, __func__, addr - alloc->buffer, ret);
+ ret = -ENOMEM;
+ break;
+ }
+ mmap_read_unlock(alloc->mm);
out:
- mmap_write_unlock(alloc->mm);
mmput_async(alloc->mm);
return ret;
}
@@ -1091,7 +1107,6 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
trace_binder_unmap_kernel_end(alloc, index);
list_lru_isolate(lru, item);
- mutex_unlock(&alloc->mutex);
spin_unlock(lock);
if (vma) {
@@ -1102,6 +1117,7 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
trace_binder_unmap_user_end(alloc, index);
}
+ mutex_unlock(&alloc->mutex);
mmap_read_unlock(mm);
mmput_async(mm);
__free_page(page_to_free);
--
2.47.0.199.ga7371fff76-googOn Wed, Nov 6, 2024 at 8:02 PM Carlos Llamas <cmllamas@google.com> wrote:
>
> Allow multiple callers to install pages simultaneously by downgrading
> the mmap_sem to non-exclusive mode. Races to the same PTE are handled
> using get_user_pages_remote() to retrieve the already installed page.
> This method significantly reduces contention in the mmap semaphore.
>
> To ensure safety, vma_lookup() is used (instead of alloc->vma) to avoid
> operating on an isolated VMA. In addition, zap_page_range_single() is
> called under the alloc->mutex to avoid racing with the shrinker.
>
> Many thanks to Barry Song who posted a similar approach [1].
>
> Link: https://lore.kernel.org/all/20240902225009.34576-1-21cnbao@gmail.com/ [1]
> Cc: David Hildenbrand <david@redhat.com>
> Cc: Barry Song <v-songbaohua@oppo.com>
> Cc: Suren Baghdasaryan <surenb@google.com>
> Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
> Signed-off-by: Carlos Llamas <cmllamas@google.com>
> ---
> drivers/android/binder_alloc.c | 64 +++++++++++++++++++++-------------
> 1 file changed, 40 insertions(+), 24 deletions(-)
>
> diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
> index 7241bf4a3ff2..acdc05552603 100644
> --- a/drivers/android/binder_alloc.c
> +++ b/drivers/android/binder_alloc.c
> @@ -221,26 +221,14 @@ static int binder_install_single_page(struct binder_alloc *alloc,
> struct binder_lru_page *lru_page,
> unsigned long addr)
> {
> + struct vm_area_struct *vma;
> struct page *page;
> - int ret = 0;
> + long npages;
> + int ret;
>
> if (!mmget_not_zero(alloc->mm))
> return -ESRCH;
>
> - /*
> - * Protected with mmap_sem in write mode as multiple tasks
> - * might race to install the same page.
> - */
> - mmap_write_lock(alloc->mm);
> - if (binder_get_installed_page(lru_page))
> - goto out;
> -
> - if (!alloc->vma) {
> - pr_err("%d: %s failed, no vma\n", alloc->pid, __func__);
> - ret = -ESRCH;
> - goto out;
> - }
> -
> page = alloc_page(GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO);
> if (!page) {
> pr_err("%d: failed to allocate page\n", alloc->pid);
> @@ -248,19 +236,47 @@ static int binder_install_single_page(struct binder_alloc *alloc,
> goto out;
> }
>
> - ret = vm_insert_page(alloc->vma, addr, page);
> - if (ret) {
> - pr_err("%d: %s failed to insert page at offset %lx with %d\n",
> - alloc->pid, __func__, addr - alloc->buffer, ret);
> + mmap_read_lock(alloc->mm);
> + vma = vma_lookup(alloc->mm, addr);
> + if (!vma || vma != alloc->vma) {
> + mmap_read_unlock(alloc->mm);
nit: instead of unlocking here you could have another label before
mmap_read_unlock() at the end and jump to it.
> __free_page(page);
> - ret = -ENOMEM;
> + pr_err("%d: %s failed, no vma\n", alloc->pid, __func__);
> + ret = -ESRCH;
> goto out;
> }
>
> - /* Mark page installation complete and safe to use */
> - binder_set_installed_page(lru_page, page);
> + ret = vm_insert_page(vma, addr, page);
> + switch (ret) {
> + case -EBUSY:
> + /*
> + * EBUSY is ok. Someone installed the pte first but the
> + * lru_page->page_ptr has not been updated yet. Discard
> + * our page and look up the one already installed.
> + */
> + ret = 0;
> + __free_page(page);
> + npages = get_user_pages_remote(alloc->mm, addr, 1, 0, &page, NULL);
> + if (npages <= 0) {
> + pr_err("%d: failed to find page at offset %lx\n",
> + alloc->pid, addr - alloc->buffer);
> + ret = -ESRCH;
> + break;
> + }
> + fallthrough;
> + case 0:
> + /* Mark page installation complete and safe to use */
> + binder_set_installed_page(lru_page, page);
> + break;
> + default:
> + __free_page(page);
> + pr_err("%d: %s failed to insert page at offset %lx with %d\n",
> + alloc->pid, __func__, addr - alloc->buffer, ret);
> + ret = -ENOMEM;
vm_insert_page() can return EINVAL (see
validate_page_before_insert()). Instead of converting other codes into
ENOMEM why not return "ret" as is?
> + break;
> + }
> + mmap_read_unlock(alloc->mm);
> out:
> - mmap_write_unlock(alloc->mm);
> mmput_async(alloc->mm);
> return ret;
> }
> @@ -1091,7 +1107,6 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
> trace_binder_unmap_kernel_end(alloc, index);
>
> list_lru_isolate(lru, item);
> - mutex_unlock(&alloc->mutex);
> spin_unlock(lock);
>
> if (vma) {
> @@ -1102,6 +1117,7 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
> trace_binder_unmap_user_end(alloc, index);
> }
>
> + mutex_unlock(&alloc->mutex);
> mmap_read_unlock(mm);
> mmput_async(mm);
> __free_page(page_to_free);
> --
> 2.47.0.199.ga7371fff76-goog
>
On Thu, Nov 07, 2024 at 07:10:28AM -0800, Suren Baghdasaryan wrote:
> On Wed, Nov 6, 2024 at 8:02 PM Carlos Llamas <cmllamas@google.com> wrote:
> >
> > Allow multiple callers to install pages simultaneously by downgrading
> > the mmap_sem to non-exclusive mode. Races to the same PTE are handled
> > using get_user_pages_remote() to retrieve the already installed page.
> > This method significantly reduces contention in the mmap semaphore.
> >
> > To ensure safety, vma_lookup() is used (instead of alloc->vma) to avoid
> > operating on an isolated VMA. In addition, zap_page_range_single() is
> > called under the alloc->mutex to avoid racing with the shrinker.
> >
> > Many thanks to Barry Song who posted a similar approach [1].
> >
> > Link: https://lore.kernel.org/all/20240902225009.34576-1-21cnbao@gmail.com/ [1]
> > Cc: David Hildenbrand <david@redhat.com>
> > Cc: Barry Song <v-songbaohua@oppo.com>
> > Cc: Suren Baghdasaryan <surenb@google.com>
> > Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
> > Signed-off-by: Carlos Llamas <cmllamas@google.com>
> > ---
> > drivers/android/binder_alloc.c | 64 +++++++++++++++++++++-------------
> > 1 file changed, 40 insertions(+), 24 deletions(-)
> >
> > diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
> > index 7241bf4a3ff2..acdc05552603 100644
> > --- a/drivers/android/binder_alloc.c
> > +++ b/drivers/android/binder_alloc.c
> > @@ -221,26 +221,14 @@ static int binder_install_single_page(struct binder_alloc *alloc,
> > struct binder_lru_page *lru_page,
> > unsigned long addr)
> > {
> > + struct vm_area_struct *vma;
> > struct page *page;
> > - int ret = 0;
> > + long npages;
> > + int ret;
> >
> > if (!mmget_not_zero(alloc->mm))
> > return -ESRCH;
> >
> > - /*
> > - * Protected with mmap_sem in write mode as multiple tasks
> > - * might race to install the same page.
> > - */
> > - mmap_write_lock(alloc->mm);
> > - if (binder_get_installed_page(lru_page))
> > - goto out;
> > -
> > - if (!alloc->vma) {
> > - pr_err("%d: %s failed, no vma\n", alloc->pid, __func__);
> > - ret = -ESRCH;
> > - goto out;
> > - }
> > -
> > page = alloc_page(GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO);
> > if (!page) {
> > pr_err("%d: failed to allocate page\n", alloc->pid);
> > @@ -248,19 +236,47 @@ static int binder_install_single_page(struct binder_alloc *alloc,
> > goto out;
> > }
> >
> > - ret = vm_insert_page(alloc->vma, addr, page);
> > - if (ret) {
> > - pr_err("%d: %s failed to insert page at offset %lx with %d\n",
> > - alloc->pid, __func__, addr - alloc->buffer, ret);
> > + mmap_read_lock(alloc->mm);
> > + vma = vma_lookup(alloc->mm, addr);
> > + if (!vma || vma != alloc->vma) {
> > + mmap_read_unlock(alloc->mm);
>
> nit: instead of unlocking here you could have another label before
> mmap_read_unlock() at the end and jump to it.
Sounds good, I'll do this.
>
> > __free_page(page);
> > - ret = -ENOMEM;
> > + pr_err("%d: %s failed, no vma\n", alloc->pid, __func__);
> > + ret = -ESRCH;
> > goto out;
> > }
> >
> > - /* Mark page installation complete and safe to use */
> > - binder_set_installed_page(lru_page, page);
> > + ret = vm_insert_page(vma, addr, page);
> > + switch (ret) {
> > + case -EBUSY:
> > + /*
> > + * EBUSY is ok. Someone installed the pte first but the
> > + * lru_page->page_ptr has not been updated yet. Discard
> > + * our page and look up the one already installed.
> > + */
> > + ret = 0;
> > + __free_page(page);
> > + npages = get_user_pages_remote(alloc->mm, addr, 1, 0, &page, NULL);
> > + if (npages <= 0) {
> > + pr_err("%d: failed to find page at offset %lx\n",
> > + alloc->pid, addr - alloc->buffer);
> > + ret = -ESRCH;
> > + break;
> > + }
> > + fallthrough;
> > + case 0:
> > + /* Mark page installation complete and safe to use */
> > + binder_set_installed_page(lru_page, page);
> > + break;
> > + default:
> > + __free_page(page);
> > + pr_err("%d: %s failed to insert page at offset %lx with %d\n",
> > + alloc->pid, __func__, addr - alloc->buffer, ret);
> > + ret = -ENOMEM;
>
> vm_insert_page() can return EINVAL (see
> validate_page_before_insert()). Instead of converting other codes into
> ENOMEM why not return "ret" as is?
This is purely historical, binder has always propagated -ENOMEM to
userspace on errors from vm_insert_page() and I'm not sure why.
FWIW, I've dropped the behavior in the last patch and now I just forward
whatever vm_insert_page() returns. I had a look at libbinder code and it
doesn't really make a difference.
Perhaps, I should be explicit about this move and do it in a separate
commit.
Thanks,
--
Carlos Llamas
© 2016 - 2024 Red Hat, Inc.