[PATCH 2/8] binder: concurrent page installation

[Carlos Llamas <cmllamas@google.com>]

Allow multiple callers to install pages simultaneously by downgrading
the mmap_sem to non-exclusive mode. Races to the same PTE are handled
using folio_walk_start() 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, 42 insertions(+), 22 deletions(-)

diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 7241bf4a3ff2..0fc6048cbc72 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -23,6 +23,7 @@
 #include <linux/uaccess.h>
 #include <linux/highmem.h>
 #include <linux/sizes.h>
+#include <linux/pagewalk.h>
 #include "binder_alloc.h"
 #include "binder_trace.h"
 
@@ -221,26 +222,14 @@ 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 folio_walk fw;
 	struct page *page;
 	int ret = 0;
 
 	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 +237,50 @@ static int binder_install_single_page(struct binder_alloc *alloc,
 		goto out;
 	}
 
-	ret = vm_insert_page(alloc->vma, addr, page);
-	if (ret) {
+	mmap_read_lock(alloc->mm);
+	vma = vma_lookup(alloc->mm, addr);
+	if (!vma || vma != alloc->vma) {
+		pr_err("%d: %s failed, no vma\n", alloc->pid, __func__);
+		ret = -ESRCH;
+		goto unlock;
+	}
+
+	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);
+		if (!folio_walk_start(&fw, vma, addr, 0)) {
+			pr_err("%d: failed to find page at offset %lx\n",
+			       alloc->pid, addr - alloc->buffer);
+			ret = -ESRCH;
+			break;
+		}
+		page = fw.page;
+		folio_walk_end(&fw, vma);
+		fallthrough;
+	case 0:
+		/* Mark page installation complete and safe to use */
+		binder_set_installed_page(lru_page, page);
+		page = NULL;
+		break;
+	default:
 		pr_err("%d: %s failed to insert page at offset %lx with %d\n",
 		       alloc->pid, __func__, addr - alloc->buffer, ret);
-		__free_page(page);
 		ret = -ENOMEM;
-		goto out;
+		break;
 	}
 
-	/* Mark page installation complete and safe to use */
-	binder_set_installed_page(lru_page, page);
+unlock:
+	mmap_read_unlock(alloc->mm);
+	if (page)
+		__free_page(page);
 out:
-	mmap_write_unlock(alloc->mm);
 	mmput_async(alloc->mm);
 	return ret;
 }
@@ -1091,7 +1111,6 @@ 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 +1121,7 @@ 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