* [PATCH v2] lib/lz4: explicitly support in-place decompression [not found] <20201121191024.2631523-1-hsiangkao@redhat.com> @ 2020-11-22 3:07 ` Gao Xiang 2020-11-30 18:19 ` Nick Terrell via Linux-erofs 0 siblings, 1 reply; 3+ messages in thread From: Gao Xiang @ 2020-11-22 3:07 UTC (permalink / raw) To: Andrew Morton; +Cc: linux-erofs, LKML, Nick Terrell, Yann Collet, Miao Xie LZ4 final literal copy could be overlapped when doing in-place decompression, so it's unsafe to just use memcpy() on an optimized memcpy approach but memmove() instead. Upstream LZ4 has updated this years ago [1] (and the impact is non-sensible [2] plus only a few bytes remain), this commit just synchronizes LZ4 upstream code to the kernel side as well. It can be observed as EROFS in-place decompression failure on specific files when X86_FEATURE_ERMS is unsupported, memcpy() optimization of commit 59daa706fbec ("x86, mem: Optimize memcpy by avoiding memory false dependece") will be enabled then. Currently most modern x86-CPUs support ERMS, these CPUs just use "rep movsb" approach so no problem at all. However, it can still be verified with forcely disabling ERMS feature... arch/x86/lib/memcpy_64.S: ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \ - "jmp memcpy_erms", X86_FEATURE_ERMS + "jmp memcpy_orig", X86_FEATURE_ERMS We didn't observe any strange on arm64/arm/x86 platform before since most memcpy() would behave in an increasing address order ("copy upwards" [3]) and it's the correct order of in-place decompression but it really needs an update to memmove() for sure considering it's an undefined behavior according to the standard and some unique optimization already exists in the kernel. [1] https://github.com/lz4/lz4/commit/33cb8518ac385835cc17be9a770b27b40cd0e15b [2] https://github.com/lz4/lz4/pull/717#issuecomment-497818921 [3] https://sourceware.org/bugzilla/show_bug.cgi?id=12518 Cc: Yann Collet <yann.collet.73@gmail.com> Cc: Nick Terrell <terrelln@fb.com> Cc: Miao Xie <miaoxie@huawei.com> Cc: Chao Yu <yuchao0@huawei.com> Cc: Li Guifu <bluce.liguifu@huawei.com> Cc: Guo Xuenan <guoxuenan@huawei.com> Signed-off-by: Gao Xiang <hsiangkao@redhat.com> --- changes since v1: - refine commit message; - Cc more people. Hi Andrew, Could you kindly consider picking this patch up, although the impact is EROFS but it touchs in-kernel lz4 library anyway... Thanks, Gao Xiang lib/lz4/lz4_decompress.c | 6 +++++- lib/lz4/lz4defs.h | 1 + 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c index 00cb0d0b73e1..8a7724a6ce2f 100644 --- a/lib/lz4/lz4_decompress.c +++ b/lib/lz4/lz4_decompress.c @@ -263,7 +263,11 @@ static FORCE_INLINE int LZ4_decompress_generic( } } - LZ4_memcpy(op, ip, length); + /* + * supports overlapping memory regions; only matters + * for in-place decompression scenarios + */ + LZ4_memmove(op, ip, length); ip += length; op += length; diff --git a/lib/lz4/lz4defs.h b/lib/lz4/lz4defs.h index c91dd96ef629..673bd206aa98 100644 --- a/lib/lz4/lz4defs.h +++ b/lib/lz4/lz4defs.h @@ -146,6 +146,7 @@ static FORCE_INLINE void LZ4_writeLE16(void *memPtr, U16 value) * environments. This is needed when decompressing the Linux Kernel, for example. */ #define LZ4_memcpy(dst, src, size) __builtin_memcpy(dst, src, size) +#define LZ4_memmove(dst, src, size) __builtin_memmove(dst, src, size) static FORCE_INLINE void LZ4_copy8(void *dst, const void *src) { -- 2.18.4 ^ permalink raw reply related [flat|nested] 3+ messages in thread
* Re: [PATCH v2] lib/lz4: explicitly support in-place decompression 2020-11-22 3:07 ` [PATCH v2] lib/lz4: explicitly support in-place decompression Gao Xiang @ 2020-11-30 18:19 ` Nick Terrell via Linux-erofs 2020-11-30 18:54 ` Gao Xiang 0 siblings, 1 reply; 3+ messages in thread From: Nick Terrell via Linux-erofs @ 2020-11-30 18:19 UTC (permalink / raw) To: Gao Xiang; +Cc: linux-erofs, LKML, Yann Collet, Andrew Morton, Miao Xie > On Nov 21, 2020, at 7:07 PM, Gao Xiang <hsiangkao@redhat.com> wrote: > > LZ4 final literal copy could be overlapped when doing > in-place decompression, so it's unsafe to just use memcpy() > on an optimized memcpy approach but memmove() instead. > > Upstream LZ4 has updated this years ago [1] (and the impact > is non-sensible [2] plus only a few bytes remain), this commit > just synchronizes LZ4 upstream code to the kernel side as well. > > It can be observed as EROFS in-place decompression failure > on specific files when X86_FEATURE_ERMS is unsupported, > memcpy() optimization of commit 59daa706fbec ("x86, mem: > Optimize memcpy by avoiding memory false dependece") will > be enabled then. > > Currently most modern x86-CPUs support ERMS, these CPUs just > use "rep movsb" approach so no problem at all. However, it can > still be verified with forcely disabling ERMS feature... > > arch/x86/lib/memcpy_64.S: > ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \ > - "jmp memcpy_erms", X86_FEATURE_ERMS > + "jmp memcpy_orig", X86_FEATURE_ERMS > > We didn't observe any strange on arm64/arm/x86 platform before > since most memcpy() would behave in an increasing address order > ("copy upwards" [3]) and it's the correct order of in-place > decompression but it really needs an update to memmove() for sure > considering it's an undefined behavior according to the standard > and some unique optimization already exists in the kernel. > > [1] https://github.com/lz4/lz4/commit/33cb8518ac385835cc17be9a770b27b40cd0e15b > [2] https://github.com/lz4/lz4/pull/717#issuecomment-497818921 > [3] https://sourceware.org/bugzilla/show_bug.cgi?id=12518 > Cc: Yann Collet <yann.collet.73@gmail.com> > Cc: Nick Terrell <terrelln@fb.com> > Cc: Miao Xie <miaoxie@huawei.com> > Cc: Chao Yu <yuchao0@huawei.com> > Cc: Li Guifu <bluce.liguifu@huawei.com> > Cc: Guo Xuenan <guoxuenan@huawei.com> > Signed-off-by: Gao Xiang <hsiangkao@redhat.com> > --- > changes since v1: > - refine commit message; > - Cc more people. > > Hi Andrew, > > Could you kindly consider picking this patch up, although > the impact is EROFS but it touchs in-kernel lz4 library > anyway... > > Thanks, > Gao Xiang > > lib/lz4/lz4_decompress.c | 6 +++++- > lib/lz4/lz4defs.h | 1 + > 2 files changed, 6 insertions(+), 1 deletion(-) > > diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c > index 00cb0d0b73e1..8a7724a6ce2f 100644 > --- a/lib/lz4/lz4_decompress.c > +++ b/lib/lz4/lz4_decompress.c > @@ -263,7 +263,11 @@ static FORCE_INLINE int LZ4_decompress_generic( > } > } > > - LZ4_memcpy(op, ip, length); > + /* > + * supports overlapping memory regions; only matters > + * for in-place decompression scenarios > + */ > + LZ4_memmove(op, ip, length); > ip += length; > op += length; > > diff --git a/lib/lz4/lz4defs.h b/lib/lz4/lz4defs.h > index c91dd96ef629..673bd206aa98 100644 > --- a/lib/lz4/lz4defs.h > +++ b/lib/lz4/lz4defs.h > @@ -146,6 +146,7 @@ static FORCE_INLINE void LZ4_writeLE16(void *memPtr, U16 value) > * environments. This is needed when decompressing the Linux Kernel, for example. > */ > #define LZ4_memcpy(dst, src, size) __builtin_memcpy(dst, src, size) > +#define LZ4_memmove(dst, src, size) __builtin_memmove(dst, src, size) > > static FORCE_INLINE void LZ4_copy8(void *dst, const void *src) > { > -- > 2.18.4 > Looks good to me! You can add: Reviewed-by: Nick Terrell <terrelln@fb.com> ^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [PATCH v2] lib/lz4: explicitly support in-place decompression 2020-11-30 18:19 ` Nick Terrell via Linux-erofs @ 2020-11-30 18:54 ` Gao Xiang 0 siblings, 0 replies; 3+ messages in thread From: Gao Xiang @ 2020-11-30 18:54 UTC (permalink / raw) To: Nick Terrell; +Cc: linux-erofs, LKML, Yann Collet, Andrew Morton, Miao Xie On Mon, Nov 30, 2020 at 06:19:34PM +0000, Nick Terrell wrote: > <too long snip> > > Looks good to me! You can add: > > Reviewed-by: Nick Terrell <terrelln@fb.com> Thanks for reviewing this! Thanks, Gao Xiang > ^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2020-11-30 19:03 UTC | newest] Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed) -- links below jump to the message on this page -- [not found] <20201121191024.2631523-1-hsiangkao@redhat.com> 2020-11-22 3:07 ` [PATCH v2] lib/lz4: explicitly support in-place decompression Gao Xiang 2020-11-30 18:19 ` Nick Terrell via Linux-erofs 2020-11-30 18:54 ` Gao Xiang
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox; as well as URLs for NNTP newsgroup(s).