squashfs: extend "page actor" to handle missing pages

Patch series "Squashfs: handle missing pages decompressing into page
cache".

This patchset enables Squashfs to handle missing pages when directly
decompressing datablocks into the page cache.

Previously if the full set of pages needed was not available, Squashfs
would have to fall back to using an intermediate buffer (the older
method), which is slower, involving a memcopy, and it introduces
contention on a shared buffer.

The first patch extends the "page actor" code to handle missing pages.

The second patch updates Squashfs_readpage_block() to use the new
functionality, and removes the code that falls back to using an
intermediate buffer.

This patchset is independent of the readahead work, and it is standalone. 
It can be merged on its own.

But the readahead patch for efficiency also needs this patch-set.


This patch (of 2):

This patch extends the "page actor" code to handle missing pages.

Previously if the full set of pages needed to decompress a Squashfs
datablock was unavailable, this would cause decompression to fail on the
missing pages.

In this case direct decompression into the page cache could not be
achieved and the code would fall back to using the older intermediate
buffer method.

With this patch, direct decompression into the page cache can be achieved
with missing pages.

For "multi-shot" decompressors (zlib, xz, zstd), the page actor will
allocate a temporary buffer which is passed to the decompressor, and then
freed by the page actor.

For "single shot" decompressors (lz4, lzo) which decompress into a
contiguous "bounce buffer", and which is then copied into the page cache,
it would be pointless to allocate a temporary buffer, memcpy into it, and
then free it.  For these decompressors -ENOMEM is returned, which
signifies that the memcpy for that page should be skipped.

This also happens if the data block is uncompressed.

Link: https://lkml.kernel.org/r/20220611032133.5743-1-phillip@squashfs.org.uk
Link: https://lkml.kernel.org/r/20220611032133.5743-2-phillip@squashfs.org.uk
Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Hsin-Yi Wang <hsinyi@chromium.org>
Cc: Xiongwei Song <Xiongwei.Song@windriver.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 47 insertions, 8 deletions

diff --git a/fs/squashfs/page_actor.c b/fs/squashfs/page_actor.c
index 520d323a99ce..b23b780d8f42 100644
--- a/fs/squashfs/page_actor.c
+++ b/fs/squashfs/page_actor.c
@@ -7,6 +7,8 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/pagemap.h>
+#include "squashfs_fs_sb.h"
+#include "decompressor.h"
 #include "page_actor.h"
 
 /*
@@ -57,29 +59,62 @@ struct squashfs_page_actor *squashfs_page_actor_init(void **buffer,
 }
 
 /* Implementation of page_actor for decompressing directly into page cache. */
+static void *handle_next_page(struct squashfs_page_actor *actor)
+{
+	int max_pages = (actor->length + PAGE_SIZE - 1) >> PAGE_SHIFT;
+
+	if (actor->returned_pages == max_pages)
+		return NULL;
+
+	if ((actor->next_page == actor->pages) ||
+			(actor->next_index != actor->page[actor->next_page]->index)) {
+		if (actor->alloc_buffer) {
+			void *tmp_buffer = kmalloc(PAGE_SIZE, GFP_KERNEL);
+
+			if (tmp_buffer) {
+				actor->tmp_buffer = tmp_buffer;
+				actor->next_index++;
+				actor->returned_pages++;
+				return tmp_buffer;
+			}
+		}
+
+		actor->next_index++;
+		actor->returned_pages++;
+		return ERR_PTR(-ENOMEM);
+	}
+
+	actor->next_index++;
+	actor->returned_pages++;
+	return actor->pageaddr = kmap_local_page(actor->page[actor->next_page++]);
+}
+
 static void *direct_first_page(struct squashfs_page_actor *actor)
 {
-	actor->next_page = 1;
-	return actor->pageaddr = kmap_atomic(actor->page[0]);
+	return handle_next_page(actor);
 }
 
 static void *direct_next_page(struct squashfs_page_actor *actor)
 {
 	if (actor->pageaddr)
-		kunmap_atomic(actor->pageaddr);
+		kunmap_local(actor->pageaddr);
+
+	kfree(actor->tmp_buffer);
+	actor->pageaddr = actor->tmp_buffer = NULL;
 
-	return actor->pageaddr = actor->next_page == actor->pages ? NULL :
-		kmap_atomic(actor->page[actor->next_page++]);
+	return handle_next_page(actor);
 }
 
 static void direct_finish_page(struct squashfs_page_actor *actor)
 {
 	if (actor->pageaddr)
-		kunmap_atomic(actor->pageaddr);
+		kunmap_local(actor->pageaddr);
+
+	kfree(actor->tmp_buffer);
 }
 
-struct squashfs_page_actor *squashfs_page_actor_init_special(struct page **page,
-	int pages, int length)
+struct squashfs_page_actor *squashfs_page_actor_init_special(struct squashfs_sb_info *msblk,
+	struct page **page, int pages, int length)
 {
 	struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL);
 
@@ -90,7 +125,11 @@ struct squashfs_page_actor *squashfs_page_actor_init_special(struct page **page,
 	actor->page = page;
 	actor->pages = pages;
 	actor->next_page = 0;
+	actor->returned_pages = 0;
+	actor->next_index = page[0]->index & ~((1 << (msblk->block_log - PAGE_SHIFT)) - 1);
 	actor->pageaddr = NULL;
+	actor->tmp_buffer = NULL;
+	actor->alloc_buffer = msblk->decompressor->alloc_buffer;
 	actor->squashfs_first_page = direct_first_page;
 	actor->squashfs_next_page = direct_next_page;
 	actor->squashfs_finish_page = direct_finish_page;