Skip to contentSkip to conversation

FAILED: patch "[PATCH] erofs: fix lz4 inplace decompression" failed to apply to 5.15-stable tree

PATCH New [email protected] 2 participants 3 messages Jan 26, 2024 – Feb 24, 2024

Subsystems (2)
Stable branch EROFS file system
lore
Share & tools
lore

[email protected]

author maintainer
#0 lore raw

The patch below does not apply to the 5.15-stable tree.
If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <[email protected]>.

To reproduce the conflict and resubmit, you may use the following commands:

git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y
git checkout FETCH_HEAD
git cherry-pick -x 3c12466b6b7bf1e56f9b32c366a3d83d87afb4de
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<[email protected]>' --in-reply-to '2024012648-backwater-colt-7290@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^..

Possible dependencies:

3c12466b6b7b ("erofs: fix lz4 inplace decompression") 123ec246ebe3 ("erofs: get rid of the remaining kmap_atomic()") ab749badf9f4 ("erofs: support unaligned data decompression") 10e5f6e482e1 ("erofs: introduce z_erofs_fixup_insize") d67aee76d418 ("erofs: tidy up z_erofs_lz4_decompress") 7e508f2ca8bb ("erofs: rename lz4_0pading to zero_padding") eaa9172ad988 ("erofs: get rid of ->lru usage")
622ceaddb764 ("erofs: lzma compression support")
966edfb0a3dc ("erofs: rename some generic methods in decompressor") 386292919c25 ("erofs: introduce readmore decompression strategy") 8f89926290c4 ("erofs: get compression algorithms directly on mapping") dfeab2e95a75 ("erofs: add multiple device support")
e62424651f43 ("erofs: decouple basic mount options from fs_context") 5b6e7e120e71 ("erofs: remove the fast path of per-CPU buffer decompression")

thanks,

greg k-h

------------------ original commit in Linus's tree ------------------

From 3c12466b6b7bf1e56f9b32c366a3d83d87afb4de Mon Sep 17 00:00:00 2001
From: Gao Xiang <[email protected]>
Date: Wed, 6 Dec 2023 12:55:34 +0800
Subject: [PATCH] erofs: fix lz4 inplace decompression

Currently EROFS can map another compressed buffer for inplace decompression, that was used to handle the cases that some pages of compressed data are actually not in-place I/O.

However, like most simple LZ77 algorithms, LZ4 expects the compressed data is arranged at the end of the decompressed buffer and it explicitly uses memmove() to handle overlapping:
__________________________________________________________
|_ direction of decompression --> ____ |_ compressed data _|

Although EROFS arranges compressed data like this, it typically maps two individual virtual buffers so the relative order is uncertain. Previously, it was hardly observed since LZ4 only uses memmove() for short overlapped literals and x86/arm64 memmove implementations seem to completely cover it up and they don't have this issue. Juhyung reported that EROFS data corruption can be found on a new Intel x86 processor. After some analysis, it seems that recent x86 processors with the new FSRM feature expose this issue with "rep movsb".

Let's strictly use the decompressed buffer for lz4 inplace decompression for now. Later, as an useful improvement, we could try to tie up these two buffers together in the correct order.

Reported-and-tested-by Juhyung Park <[email protected]>
Closes https://lore.kernel.org/r/CAD14+f2AVKf8Fa2OO1aAUdDNTDsVzzR6ctU_oJSmTyd6zSYR2Q@mail.gmail.com open here
Fixes 0ffd71bcc3a0 ("staging: erofs: introduce LZ4 decompression inplace")
Fixes 598162d05080 ("erofs: support decompress big pcluster for lz4 backend")
Cc stable <[email protected]> # 5.4+
Tested-by Yifan Zhao <[email protected]>
Signed-off-by Gao Xiang <[email protected]>
Link https://lore.kernel.org/r/[email protected] open here
fs/erofs/decompressor.c +16 -15
index 021be5feb1bc..e0d609c3958f 100644
@@ -121,11 +121,11 @@ static int z_erofs_lz4_prepare_dstpages(struct z_erofs_lz4_decompress_ctx *ctx,
 }
 
 static void *z_erofs_lz4_handle_overlap(struct z_erofs_lz4_decompress_ctx *ctx,
-			void *inpage, unsigned int *inputmargin, int *maptype,
-			bool may_inplace)
+			void *inpage, void *out, unsigned int *inputmargin,
+			int *maptype, bool may_inplace)
 {
 	struct z_erofs_decompress_req *rq = ctx->rq;
-	unsigned int omargin, total, i, j;
+	unsigned int omargin, total, i;
 	struct page **in;
 	void *src, *tmp;
 

@@ -135,12 +135,13 @@ static void *z_erofs_lz4_handle_overlap(struct z_erofs_lz4_decompress_ctx *ctx,
 		    omargin < LZ4_DECOMPRESS_INPLACE_MARGIN(rq->inputsize))
 			goto docopy;
 
-		for (i = 0; i < ctx->inpages; ++i) {
-			DBG_BUGON(rq->in[i] == NULL);
-			for (j = 0; j < ctx->outpages - ctx->inpages + i; ++j)
-				if (rq->out[j] == rq->in[i])
-					goto docopy;
-		}
+		for (i = 0; i < ctx->inpages; ++i)
+			if (rq->out[ctx->outpages - ctx->inpages + i] !=
+			    rq->in[i])
+				goto docopy;
+		kunmap_local(inpage);
+		*maptype = 3;
+		return out + ((ctx->outpages - ctx->inpages) << PAGE_SHIFT);
 	}
 
 	if (ctx->inpages <= 1) {

@@ -148,7 +149,6 @@ static void *z_erofs_lz4_handle_overlap(struct z_erofs_lz4_decompress_ctx *ctx,
 		return inpage;
 	}
 	kunmap_local(inpage);
-	might_sleep();
 	src = erofs_vm_map_ram(rq->in, ctx->inpages);
 	if (!src)
 		return ERR_PTR(-ENOMEM);

@@ -204,12 +204,12 @@ int z_erofs_fixup_insize(struct z_erofs_decompress_req *rq, const char *padbuf,
 }
 
 static int z_erofs_lz4_decompress_mem(struct z_erofs_lz4_decompress_ctx *ctx,
-				      u8 *out)
+				      u8 *dst)
 {
 	struct z_erofs_decompress_req *rq = ctx->rq;
 	bool support_0padding = false, may_inplace = false;
 	unsigned int inputmargin;
-	u8 *headpage, *src;
+	u8 *out, *headpage, *src;
 	int ret, maptype;
 
 	DBG_BUGON(*rq->in == NULL);

@@ -230,11 +230,12 @@ static int z_erofs_lz4_decompress_mem(struct z_erofs_lz4_decompress_ctx *ctx,
 	}
 
 	inputmargin = rq->pageofs_in;
-	src = z_erofs_lz4_handle_overlap(ctx, headpage, &inputmargin,
+	src = z_erofs_lz4_handle_overlap(ctx, headpage, dst, &inputmargin,
 					 &maptype, may_inplace);
 	if (IS_ERR(src))
 		return PTR_ERR(src);
 
+	out = dst + rq->pageofs_out;
 	/* legacy format could compress extra data in a pcluster. */
 	if (rq->partial_decoding || !support_0padding)
 		ret = LZ4_decompress_safe_partial(src + inputmargin, out,

@@ -265,7 +266,7 @@ static int z_erofs_lz4_decompress_mem(struct z_erofs_lz4_decompress_ctx *ctx,
 		vm_unmap_ram(src, ctx->inpages);
 	} else if (maptype == 2) {
 		erofs_put_pcpubuf(src);
-	} else {
+	} else if (maptype != 3) {
 		DBG_BUGON(1);
 		return -EFAULT;
 	}

@@ -308,7 +309,7 @@ static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq,
 	}
 
 dstmap_out:
-	ret = z_erofs_lz4_decompress_mem(&ctx, dst + rq->pageofs_out);
+	ret = z_erofs_lz4_decompress_mem(&ctx, dst);
 	if (!dst_maptype)
 		kunmap_local(dst);
 	else if (dst_maptype == 2)
#1 lore raw

Hi Greg,

Quoted 17 lines · On 2024/1/27 06:07, [email protected] wrote:

The patch below does not apply to the 5.15-stable tree.
If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <[email protected]>.

To reproduce the conflict and resubmit, you may use the following commands:

git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y
git checkout FETCH_HEAD
git cherry-pick -x 3c12466b6b7bf1e56f9b32c366a3d83d87afb4de
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<[email protected]>' --in-reply-to '2024012648-backwater-colt-7290@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^..

Possible dependencies:

Quoted 14 lines

3c12466b6b7b ("erofs: fix lz4 inplace decompression") 123ec246ebe3 ("erofs: get rid of the remaining kmap_atomic()") ab749badf9f4 ("erofs: support unaligned data decompression") 10e5f6e482e1 ("erofs: introduce z_erofs_fixup_insize") d67aee76d418 ("erofs: tidy up z_erofs_lz4_decompress") 7e508f2ca8bb ("erofs: rename lz4_0pading to zero_padding") eaa9172ad988 ("erofs: get rid of ->lru usage")
622ceaddb764 ("erofs: lzma compression support")
966edfb0a3dc ("erofs: rename some generic methods in decompressor") 386292919c25 ("erofs: introduce readmore decompression strategy") 8f89926290c4 ("erofs: get compression algorithms directly on mapping") dfeab2e95a75 ("erofs: add multiple device support")
e62424651f43 ("erofs: decouple basic mount options from fs_context") 5b6e7e120e71 ("erofs: remove the fast path of per-CPU buffer decompression")

I will take time on LTS versions manually soon.

Thanks,
Gao Xiang

Quoted 4 lines

thanks,

greg k-h

#2 lore raw

PATCH 1/1 erofs: fix lz4 inplace decompression

In reply to [email protected]

commit 3c12466b6b7bf1e56f9b32c366a3d83d87afb4de upstream.

Currently EROFS can map another compressed buffer for inplace decompression, that was used to handle the cases that some pages of compressed data are actually not in-place I/O.

However, like most simple LZ77 algorithms, LZ4 expects the compressed data is arranged at the end of the decompressed buffer and it explicitly uses memmove() to handle overlapping:
__________________________________________________________
|_ direction of decompression --> ____ |_ compressed data _|

Although EROFS arranges compressed data like this, it typically maps two individual virtual buffers so the relative order is uncertain. Previously, it was hardly observed since LZ4 only uses memmove() for short overlapped literals and x86/arm64 memmove implementations seem to completely cover it up and they don't have this issue. Juhyung reported that EROFS data corruption can be found on a new Intel x86 processor. After some analysis, it seems that recent x86 processors with the new FSRM feature expose this issue with "rep movsb".

Let's strictly use the decompressed buffer for lz4 inplace decompression for now. Later, as an useful improvement, we could try to tie up these two buffers together in the correct order.

Reported-and-tested-by Juhyung Park <[email protected]>
Closes https://lore.kernel.org/r/CAD14+f2AVKf8Fa2OO1aAUdDNTDsVzzR6ctU_oJSmTyd6zSYR2Q@mail.gmail.com open here
Fixes 0ffd71bcc3a0 ("staging: erofs: introduce LZ4 decompression inplace")
Fixes 598162d05080 ("erofs: support decompress big pcluster for lz4 backend")
Cc stable <[email protected]> # 5.4+
Tested-by Yifan Zhao <[email protected]>
Signed-off-by Gao Xiang <[email protected]>
Link https://lore.kernel.org/r/[email protected] open here

---
Adapt 5.15.y codebase due to non-trivial conflicts out of recent new features & cleanups.

I've done my own EROFS tests, yet more test on new x86 platform triggered by FSRM is helpful too.

 fs/erofs/decompressor.c | 34 +++++++++++++++++-----------------
 1 file changed, 17 insertions(+), 17 deletions(-)
fs/erofs/decompressor.c +17 -17
index 8193c14bb111..b4be6c524815 100644
@@ -124,11 +124,11 @@ static int z_erofs_lz4_prepare_destpages(struct z_erofs_decompress_req *rq,
 }
 
 static void *z_erofs_handle_inplace_io(struct z_erofs_decompress_req *rq,
-			void *inpage, unsigned int *inputmargin, int *maptype,
-			bool support_0padding)
+		void *inpage, void *out, unsigned int *inputmargin, int *maptype,
+		bool support_0padding)
 {
 	unsigned int nrpages_in, nrpages_out;
-	unsigned int ofull, oend, inputsize, total, i, j;
+	unsigned int ofull, oend, inputsize, total, i;
 	struct page **in;
 	void *src, *tmp;
 

@@ -143,12 +143,13 @@ static void *z_erofs_handle_inplace_io(struct z_erofs_decompress_req *rq,
 		    ofull - oend < LZ4_DECOMPRESS_INPLACE_MARGIN(inputsize))
 			goto docopy;
 
-		for (i = 0; i < nrpages_in; ++i) {
-			DBG_BUGON(rq->in[i] == NULL);
-			for (j = 0; j < nrpages_out - nrpages_in + i; ++j)
-				if (rq->out[j] == rq->in[i])
-					goto docopy;
-		}
+		for (i = 0; i < nrpages_in; ++i)
+			if (rq->out[nrpages_out - nrpages_in + i] !=
+			    rq->in[i])
+				goto docopy;
+		kunmap_atomic(inpage);
+		*maptype = 3;
+		return out + ((nrpages_out - nrpages_in) << PAGE_SHIFT);
 	}
 
 	if (nrpages_in <= 1) {

@@ -156,7 +157,6 @@ static void *z_erofs_handle_inplace_io(struct z_erofs_decompress_req *rq,
 		return inpage;
 	}
 	kunmap_atomic(inpage);
-	might_sleep();
 	src = erofs_vm_map_ram(rq->in, nrpages_in);
 	if (!src)
 		return ERR_PTR(-ENOMEM);

@@ -193,10 +193,10 @@ static void *z_erofs_handle_inplace_io(struct z_erofs_decompress_req *rq,
 	return src;
 }
 
-static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, u8 *out)
+static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, u8 *dst)
 {
 	unsigned int inputmargin;
-	u8 *headpage, *src;
+	u8 *out, *headpage, *src;
 	bool support_0padding;
 	int ret, maptype;
 

@@ -220,11 +220,12 @@ static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, u8 *out)
 	}
 
 	rq->inputsize -= inputmargin;
-	src = z_erofs_handle_inplace_io(rq, headpage, &inputmargin, &maptype,
-					support_0padding);
+	src = z_erofs_handle_inplace_io(rq, headpage, dst, &inputmargin,
+					&maptype, support_0padding);
 	if (IS_ERR(src))
 		return PTR_ERR(src);
 
+	out = dst + rq->pageofs_out;
 	/* legacy format could compress extra data in a pcluster. */
 	if (rq->partial_decoding || !support_0padding)
 		ret = LZ4_decompress_safe_partial(src + inputmargin, out,

@@ -253,7 +254,7 @@ static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, u8 *out)
 		vm_unmap_ram(src, PAGE_ALIGN(rq->inputsize) >> PAGE_SHIFT);
 	} else if (maptype == 2) {
 		erofs_put_pcpubuf(src);
-	} else {
+	} else if (maptype != 3) {
 		DBG_BUGON(1);
 		return -EFAULT;
 	}

@@ -354,8 +355,7 @@ static int z_erofs_decompress_generic(struct z_erofs_decompress_req *rq,
 	dst_maptype = 2;
 
 dstmap_out:
-	ret = alg->decompress(rq, dst + rq->pageofs_out);
-
+	ret = alg->decompress(rq, dst);
 	if (!dst_maptype)
 		kunmap_atomic(dst);
 	else if (dst_maptype == 2)
Signature · 1 line
2.39.3