glibc/glibc-upstream-2.34-234.patch
Arjun Shankar 601650f878 Import glibc-2.34-35.fc35 from f35
* Tue May 31 2022 Arjun Shankar <arjun@redhat.com> - 2.34-35
- Sync with upstream branch release/2.34/master,
  commit ff450cdbdee0b8cb6b9d653d6d2fa892de29be31:
- Fix deadlock when pthread_atfork handler calls pthread_atfork or dlclose
- x86: Fallback {str|wcs}cmp RTM in the ncmp overflow case [BZ #29127]
- string.h: fix __fortified_attr_access macro call [BZ #29162]
- linux: Add a getauxval test [BZ #23293]
- rtld: Use generic argv adjustment in ld.so [BZ #23293]
- S390: Enable static PIE

* Thu May 19 2022 Florian Weimer <fweimer@redhat.com> - 2.34-34
- Sync with upstream branch release/2.34/master,
  commit ede8d94d154157d269b18f3601440ac576c1f96a:
- csu: Implement and use _dl_early_allocate during static startup
- Linux: Introduce __brk_call for invoking the brk system call
- Linux: Implement a useful version of _startup_fatal
- ia64: Always define IA64_USE_NEW_STUB as a flag macro
- Linux: Define MMAP_CALL_INTERNAL
- i386: Honor I386_USE_SYSENTER for 6-argument Linux system calls
- i386: Remove OPTIMIZE_FOR_GCC_5 from Linux libc-do-syscall.S
- elf: Remove __libc_init_secure
- Linux: Consolidate auxiliary vector parsing (redo)
- Linux: Include <dl-auxv.h> in dl-sysdep.c only for SHARED
- Revert "Linux: Consolidate auxiliary vector parsing"
- Linux: Consolidate auxiliary vector parsing
- Linux: Assume that NEED_DL_SYSINFO_DSO is always defined
- Linux: Remove DL_FIND_ARG_COMPONENTS
- Linux: Remove HAVE_AUX_SECURE, HAVE_AUX_XID, HAVE_AUX_PAGESIZE
- elf: Merge dl-sysdep.c into the Linux version
- elf: Remove unused NEED_DL_BASE_ADDR and _dl_base_addr
- x86: Optimize {str|wcs}rchr-evex
- x86: Optimize {str|wcs}rchr-avx2
- x86: Optimize {str|wcs}rchr-sse2
- x86: Cleanup page cross code in memcmp-avx2-movbe.S
- x86: Remove memcmp-sse4.S
- x86: Small improvements for wcslen
- x86: Remove AVX str{n}casecmp
- x86: Add EVEX optimized str{n}casecmp
- x86: Add AVX2 optimized str{n}casecmp
- x86: Optimize str{n}casecmp TOLOWER logic in strcmp-sse42.S
- x86: Optimize str{n}casecmp TOLOWER logic in strcmp.S
- x86: Remove strspn-sse2.S and use the generic implementation
- x86: Remove strpbrk-sse2.S and use the generic implementation
- x87: Remove strcspn-sse2.S and use the generic implementation
- x86: Optimize strspn in strspn-c.c
- x86: Optimize strcspn and strpbrk in strcspn-c.c
- x86: Code cleanup in strchr-evex and comment justifying branch
- x86: Code cleanup in strchr-avx2 and comment justifying branch
- x86_64: Remove bcopy optimizations
- x86-64: Remove bzero weak alias in SS2 memset
- x86_64/multiarch: Sort sysdep_routines and put one entry per line
- x86: Improve L to support L(XXX_SYMBOL (YYY, ZZZ))
- fortify: Ensure that __glibc_fortify condition is a constant [BZ #29141]

* Thu May 12 2022 Florian Weimer <fweimer@redhat.com> - 2.34-33
- Sync with upstream branch release/2.34/master,
  commit 91c2e6c3db44297bf4cb3a2e3c40236c5b6a0b23:
- dlfcn: Implement the RTLD_DI_PHDR request type for dlinfo
- manual: Document the dlinfo function
- x86: Fix fallback for wcsncmp_avx2 in strcmp-avx2.S [BZ #28896]
- x86: Fix bug in strncmp-evex and strncmp-avx2 [BZ #28895]
- x86: Set .text section in memset-vec-unaligned-erms
- x86-64: Optimize bzero
- x86: Remove SSSE3 instruction for broadcast in memset.S (SSE2 Only)
- x86: Improve vec generation in memset-vec-unaligned-erms.S
- x86-64: Fix strcmp-evex.S
- x86-64: Fix strcmp-avx2.S
- x86: Optimize strcmp-evex.S
- x86: Optimize strcmp-avx2.S
- manual: Clarify that abbreviations of long options are allowed
- Add HWCAP2_AFP, HWCAP2_RPRES from Linux 5.17 to AArch64 bits/hwcap.h
- aarch64: Add HWCAP2_ECV from Linux 5.16
- Add SOL_MPTCP, SOL_MCTP from Linux 5.16 to bits/socket.h
- Update kernel version to 5.17 in tst-mman-consts.py
- Update kernel version to 5.16 in tst-mman-consts.py
- Update syscall lists for Linux 5.17
- Add ARPHRD_CAN, ARPHRD_MCTP to net/if_arp.h
- Update kernel version to 5.15 in tst-mman-consts.py
- Add PF_MCTP, AF_MCTP from Linux 5.15 to bits/socket.h

Resolves: #2091541
2022-06-06 16:33:33 +02:00

498 lines
12 KiB
Diff

commit 00f09a14d2818f438959e764834abb3913f2b20a
Author: Noah Goldstein <goldstein.w.n@gmail.com>
Date: Thu Apr 21 20:52:29 2022 -0500
x86: Optimize {str|wcs}rchr-avx2
The new code unrolls the main loop slightly without adding too much
overhead and minimizes the comparisons for the search CHAR.
Geometric Mean of all benchmarks New / Old: 0.832
See email for all results.
Full xcheck passes on x86_64 with and without multiarch enabled.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
(cherry picked from commit df7e295d18ffa34f629578c0017a9881af7620f6)
diff --git a/sysdeps/x86_64/multiarch/strrchr-avx2.S b/sysdeps/x86_64/multiarch/strrchr-avx2.S
index 0deba97114d3b83d..b8dec737d5213b25 100644
--- a/sysdeps/x86_64/multiarch/strrchr-avx2.S
+++ b/sysdeps/x86_64/multiarch/strrchr-avx2.S
@@ -27,9 +27,13 @@
# ifdef USE_AS_WCSRCHR
# define VPBROADCAST vpbroadcastd
# define VPCMPEQ vpcmpeqd
+# define VPMIN vpminud
+# define CHAR_SIZE 4
# else
# define VPBROADCAST vpbroadcastb
# define VPCMPEQ vpcmpeqb
+# define VPMIN vpminub
+# define CHAR_SIZE 1
# endif
# ifndef VZEROUPPER
@@ -41,196 +45,304 @@
# endif
# define VEC_SIZE 32
+# define PAGE_SIZE 4096
- .section SECTION(.text),"ax",@progbits
-ENTRY (STRRCHR)
- movd %esi, %xmm4
- movl %edi, %ecx
+ .section SECTION(.text), "ax", @progbits
+ENTRY(STRRCHR)
+ movd %esi, %xmm7
+ movl %edi, %eax
/* Broadcast CHAR to YMM4. */
- VPBROADCAST %xmm4, %ymm4
+ VPBROADCAST %xmm7, %ymm7
vpxor %xmm0, %xmm0, %xmm0
- /* Check if we may cross page boundary with one vector load. */
- andl $(2 * VEC_SIZE - 1), %ecx
- cmpl $VEC_SIZE, %ecx
- ja L(cros_page_boundary)
+ /* Shift here instead of `andl` to save code size (saves a fetch
+ block). */
+ sall $20, %eax
+ cmpl $((PAGE_SIZE - VEC_SIZE) << 20), %eax
+ ja L(cross_page)
+L(page_cross_continue):
vmovdqu (%rdi), %ymm1
- VPCMPEQ %ymm1, %ymm0, %ymm2
- VPCMPEQ %ymm1, %ymm4, %ymm3
- vpmovmskb %ymm2, %ecx
- vpmovmskb %ymm3, %eax
- addq $VEC_SIZE, %rdi
+ /* Check end of string match. */
+ VPCMPEQ %ymm1, %ymm0, %ymm6
+ vpmovmskb %ymm6, %ecx
+ testl %ecx, %ecx
+ jz L(aligned_more)
+
+ /* Only check match with search CHAR if needed. */
+ VPCMPEQ %ymm1, %ymm7, %ymm1
+ vpmovmskb %ymm1, %eax
+ /* Check if match before first zero. */
+ blsmskl %ecx, %ecx
+ andl %ecx, %eax
+ jz L(ret0)
+ bsrl %eax, %eax
+ addq %rdi, %rax
+ /* We are off by 3 for wcsrchr if search CHAR is non-zero. If
+ search CHAR is zero we are correct. Either way `andq
+ -CHAR_SIZE, %rax` gets the correct result. */
+# ifdef USE_AS_WCSRCHR
+ andq $-CHAR_SIZE, %rax
+# endif
+L(ret0):
+L(return_vzeroupper):
+ ZERO_UPPER_VEC_REGISTERS_RETURN
+
+ /* Returns for first vec x1/x2 have hard coded backward search
+ path for earlier matches. */
+ .p2align 4,, 10
+L(first_vec_x1):
+ VPCMPEQ %ymm2, %ymm7, %ymm6
+ vpmovmskb %ymm6, %eax
+ blsmskl %ecx, %ecx
+ andl %ecx, %eax
+ jnz L(first_vec_x1_return)
+
+ .p2align 4,, 4
+L(first_vec_x0_test):
+ VPCMPEQ %ymm1, %ymm7, %ymm6
+ vpmovmskb %ymm6, %eax
+ testl %eax, %eax
+ jz L(ret1)
+ bsrl %eax, %eax
+ addq %r8, %rax
+# ifdef USE_AS_WCSRCHR
+ andq $-CHAR_SIZE, %rax
+# endif
+L(ret1):
+ VZEROUPPER_RETURN
+ .p2align 4,, 10
+L(first_vec_x0_x1_test):
+ VPCMPEQ %ymm2, %ymm7, %ymm6
+ vpmovmskb %ymm6, %eax
+ /* Check ymm2 for search CHAR match. If no match then check ymm1
+ before returning. */
testl %eax, %eax
- jnz L(first_vec)
+ jz L(first_vec_x0_test)
+ .p2align 4,, 4
+L(first_vec_x1_return):
+ bsrl %eax, %eax
+ leaq 1(%rdi, %rax), %rax
+# ifdef USE_AS_WCSRCHR
+ andq $-CHAR_SIZE, %rax
+# endif
+ VZEROUPPER_RETURN
- testl %ecx, %ecx
- jnz L(return_null)
- andq $-VEC_SIZE, %rdi
- xorl %edx, %edx
- jmp L(aligned_loop)
+ .p2align 4,, 10
+L(first_vec_x2):
+ VPCMPEQ %ymm3, %ymm7, %ymm6
+ vpmovmskb %ymm6, %eax
+ blsmskl %ecx, %ecx
+ /* If no in-range search CHAR match in ymm3 then need to check
+ ymm1/ymm2 for an earlier match (we delay checking search
+ CHAR matches until needed). */
+ andl %ecx, %eax
+ jz L(first_vec_x0_x1_test)
+ bsrl %eax, %eax
+ leaq (VEC_SIZE + 1)(%rdi, %rax), %rax
+# ifdef USE_AS_WCSRCHR
+ andq $-CHAR_SIZE, %rax
+# endif
+ VZEROUPPER_RETURN
+
.p2align 4
-L(first_vec):
- /* Check if there is a nul CHAR. */
+L(aligned_more):
+ /* Save original pointer if match was in VEC 0. */
+ movq %rdi, %r8
+
+ /* Align src. */
+ orq $(VEC_SIZE - 1), %rdi
+ vmovdqu 1(%rdi), %ymm2
+ VPCMPEQ %ymm2, %ymm0, %ymm6
+ vpmovmskb %ymm6, %ecx
testl %ecx, %ecx
- jnz L(char_and_nul_in_first_vec)
+ jnz L(first_vec_x1)
- /* Remember the match and keep searching. */
- movl %eax, %edx
- movq %rdi, %rsi
- andq $-VEC_SIZE, %rdi
- jmp L(aligned_loop)
+ vmovdqu (VEC_SIZE + 1)(%rdi), %ymm3
+ VPCMPEQ %ymm3, %ymm0, %ymm6
+ vpmovmskb %ymm6, %ecx
+ testl %ecx, %ecx
+ jnz L(first_vec_x2)
+ /* Save pointer again before realigning. */
+ movq %rdi, %rsi
+ addq $(VEC_SIZE + 1), %rdi
+ andq $-(VEC_SIZE * 2), %rdi
.p2align 4
-L(cros_page_boundary):
- andl $(VEC_SIZE - 1), %ecx
- andq $-VEC_SIZE, %rdi
- vmovdqa (%rdi), %ymm1
- VPCMPEQ %ymm1, %ymm0, %ymm2
- VPCMPEQ %ymm1, %ymm4, %ymm3
- vpmovmskb %ymm2, %edx
- vpmovmskb %ymm3, %eax
- shrl %cl, %edx
- shrl %cl, %eax
- addq $VEC_SIZE, %rdi
-
- /* Check if there is a CHAR. */
+L(first_aligned_loop):
+ /* Do 2x VEC at a time. Any more and the cost of finding the
+ match outweights loop benefit. */
+ vmovdqa (VEC_SIZE * 0)(%rdi), %ymm4
+ vmovdqa (VEC_SIZE * 1)(%rdi), %ymm5
+
+ VPCMPEQ %ymm4, %ymm7, %ymm6
+ VPMIN %ymm4, %ymm5, %ymm8
+ VPCMPEQ %ymm5, %ymm7, %ymm10
+ vpor %ymm6, %ymm10, %ymm5
+ VPCMPEQ %ymm8, %ymm0, %ymm8
+ vpor %ymm5, %ymm8, %ymm9
+
+ vpmovmskb %ymm9, %eax
+ addq $(VEC_SIZE * 2), %rdi
+ /* No zero or search CHAR. */
testl %eax, %eax
- jnz L(found_char)
-
- testl %edx, %edx
- jnz L(return_null)
+ jz L(first_aligned_loop)
- jmp L(aligned_loop)
-
- .p2align 4
-L(found_char):
- testl %edx, %edx
- jnz L(char_and_nul)
+ /* If no zero CHAR then go to second loop (this allows us to
+ throw away all prior work). */
+ vpmovmskb %ymm8, %ecx
+ testl %ecx, %ecx
+ jz L(second_aligned_loop_prep)
- /* Remember the match and keep searching. */
- movl %eax, %edx
- leaq (%rdi, %rcx), %rsi
+ /* Search char could be zero so we need to get the true match.
+ */
+ vpmovmskb %ymm5, %eax
+ testl %eax, %eax
+ jnz L(first_aligned_loop_return)
- .p2align 4
-L(aligned_loop):
- vmovdqa (%rdi), %ymm1
- VPCMPEQ %ymm1, %ymm0, %ymm2
- addq $VEC_SIZE, %rdi
- VPCMPEQ %ymm1, %ymm4, %ymm3
- vpmovmskb %ymm2, %ecx
- vpmovmskb %ymm3, %eax
- orl %eax, %ecx
- jnz L(char_nor_null)
-
- vmovdqa (%rdi), %ymm1
- VPCMPEQ %ymm1, %ymm0, %ymm2
- add $VEC_SIZE, %rdi
- VPCMPEQ %ymm1, %ymm4, %ymm3
- vpmovmskb %ymm2, %ecx
+ .p2align 4,, 4
+L(first_vec_x1_or_x2):
+ VPCMPEQ %ymm3, %ymm7, %ymm3
+ VPCMPEQ %ymm2, %ymm7, %ymm2
vpmovmskb %ymm3, %eax
- orl %eax, %ecx
- jnz L(char_nor_null)
-
- vmovdqa (%rdi), %ymm1
- VPCMPEQ %ymm1, %ymm0, %ymm2
- addq $VEC_SIZE, %rdi
- VPCMPEQ %ymm1, %ymm4, %ymm3
- vpmovmskb %ymm2, %ecx
- vpmovmskb %ymm3, %eax
- orl %eax, %ecx
- jnz L(char_nor_null)
-
- vmovdqa (%rdi), %ymm1
- VPCMPEQ %ymm1, %ymm0, %ymm2
- addq $VEC_SIZE, %rdi
- VPCMPEQ %ymm1, %ymm4, %ymm3
- vpmovmskb %ymm2, %ecx
- vpmovmskb %ymm3, %eax
- orl %eax, %ecx
- jz L(aligned_loop)
-
- .p2align 4
-L(char_nor_null):
- /* Find a CHAR or a nul CHAR in a loop. */
- testl %eax, %eax
- jnz L(match)
-L(return_value):
- testl %edx, %edx
- jz L(return_null)
- movl %edx, %eax
- movq %rsi, %rdi
+ vpmovmskb %ymm2, %edx
+ /* Use add for macro-fusion. */
+ addq %rax, %rdx
+ jz L(first_vec_x0_test)
+ /* NB: We could move this shift to before the branch and save a
+ bit of code size / performance on the fall through. The
+ branch leads to the null case which generally seems hotter
+ than char in first 3x VEC. */
+ salq $32, %rax
+ addq %rdx, %rax
+ bsrq %rax, %rax
+ leaq 1(%rsi, %rax), %rax
+# ifdef USE_AS_WCSRCHR
+ andq $-CHAR_SIZE, %rax
+# endif
+ VZEROUPPER_RETURN
+ .p2align 4,, 8
+L(first_aligned_loop_return):
+ VPCMPEQ %ymm4, %ymm0, %ymm4
+ vpmovmskb %ymm4, %edx
+ salq $32, %rcx
+ orq %rdx, %rcx
+
+ vpmovmskb %ymm10, %eax
+ vpmovmskb %ymm6, %edx
+ salq $32, %rax
+ orq %rdx, %rax
+ blsmskq %rcx, %rcx
+ andq %rcx, %rax
+ jz L(first_vec_x1_or_x2)
+
+ bsrq %rax, %rax
+ leaq -(VEC_SIZE * 2)(%rdi, %rax), %rax
# ifdef USE_AS_WCSRCHR
- /* Keep the first bit for each matching CHAR for bsr. */
- andl $0x11111111, %eax
+ andq $-CHAR_SIZE, %rax
# endif
- bsrl %eax, %eax
- leaq -VEC_SIZE(%rdi, %rax), %rax
-L(return_vzeroupper):
- ZERO_UPPER_VEC_REGISTERS_RETURN
+ VZEROUPPER_RETURN
+ /* Search char cannot be zero. */
.p2align 4
-L(match):
- /* Find a CHAR. Check if there is a nul CHAR. */
- vpmovmskb %ymm2, %ecx
- testl %ecx, %ecx
- jnz L(find_nul)
-
- /* Remember the match and keep searching. */
- movl %eax, %edx
+L(second_aligned_loop_set_furthest_match):
+ /* Save VEC and pointer from most recent match. */
+L(second_aligned_loop_prep):
movq %rdi, %rsi
- jmp L(aligned_loop)
+ vmovdqu %ymm6, %ymm2
+ vmovdqu %ymm10, %ymm3
.p2align 4
-L(find_nul):
-# ifdef USE_AS_WCSRCHR
- /* Keep the first bit for each matching CHAR for bsr. */
- andl $0x11111111, %ecx
- andl $0x11111111, %eax
-# endif
- /* Mask out any matching bits after the nul CHAR. */
- movl %ecx, %r8d
- subl $1, %r8d
- xorl %ecx, %r8d
- andl %r8d, %eax
+L(second_aligned_loop):
+ /* Search 2x at at time. */
+ vmovdqa (VEC_SIZE * 0)(%rdi), %ymm4
+ vmovdqa (VEC_SIZE * 1)(%rdi), %ymm5
+
+ VPCMPEQ %ymm4, %ymm7, %ymm6
+ VPMIN %ymm4, %ymm5, %ymm1
+ VPCMPEQ %ymm5, %ymm7, %ymm10
+ vpor %ymm6, %ymm10, %ymm5
+ VPCMPEQ %ymm1, %ymm0, %ymm1
+ vpor %ymm5, %ymm1, %ymm9
+
+ vpmovmskb %ymm9, %eax
+ addq $(VEC_SIZE * 2), %rdi
testl %eax, %eax
- /* If there is no CHAR here, return the remembered one. */
- jz L(return_value)
- bsrl %eax, %eax
- leaq -VEC_SIZE(%rdi, %rax), %rax
- VZEROUPPER_RETURN
-
- .p2align 4
-L(char_and_nul):
- /* Find both a CHAR and a nul CHAR. */
- addq %rcx, %rdi
- movl %edx, %ecx
-L(char_and_nul_in_first_vec):
-# ifdef USE_AS_WCSRCHR
- /* Keep the first bit for each matching CHAR for bsr. */
- andl $0x11111111, %ecx
- andl $0x11111111, %eax
-# endif
- /* Mask out any matching bits after the nul CHAR. */
- movl %ecx, %r8d
- subl $1, %r8d
- xorl %ecx, %r8d
- andl %r8d, %eax
+ jz L(second_aligned_loop)
+ vpmovmskb %ymm1, %ecx
+ testl %ecx, %ecx
+ jz L(second_aligned_loop_set_furthest_match)
+ vpmovmskb %ymm5, %eax
testl %eax, %eax
- /* Return null pointer if the nul CHAR comes first. */
- jz L(return_null)
- bsrl %eax, %eax
- leaq -VEC_SIZE(%rdi, %rax), %rax
+ jnz L(return_new_match)
+
+ /* This is the hot patch. We know CHAR is inbounds and that
+ ymm3/ymm2 have latest match. */
+ .p2align 4,, 4
+L(return_old_match):
+ vpmovmskb %ymm3, %eax
+ vpmovmskb %ymm2, %edx
+ salq $32, %rax
+ orq %rdx, %rax
+ bsrq %rax, %rax
+ /* Search char cannot be zero so safe to just use lea for
+ wcsrchr. */
+ leaq (VEC_SIZE * -2 -(CHAR_SIZE - 1))(%rsi, %rax), %rax
VZEROUPPER_RETURN
- .p2align 4
-L(return_null):
- xorl %eax, %eax
+ /* Last iteration also potentially has a match. */
+ .p2align 4,, 8
+L(return_new_match):
+ VPCMPEQ %ymm4, %ymm0, %ymm4
+ vpmovmskb %ymm4, %edx
+ salq $32, %rcx
+ orq %rdx, %rcx
+
+ vpmovmskb %ymm10, %eax
+ vpmovmskb %ymm6, %edx
+ salq $32, %rax
+ orq %rdx, %rax
+ blsmskq %rcx, %rcx
+ andq %rcx, %rax
+ jz L(return_old_match)
+ bsrq %rax, %rax
+ /* Search char cannot be zero so safe to just use lea for
+ wcsrchr. */
+ leaq (VEC_SIZE * -2 -(CHAR_SIZE - 1))(%rdi, %rax), %rax
VZEROUPPER_RETURN
-END (STRRCHR)
+ .p2align 4,, 4
+L(cross_page):
+ movq %rdi, %rsi
+ andq $-VEC_SIZE, %rsi
+ vmovdqu (%rsi), %ymm1
+ VPCMPEQ %ymm1, %ymm0, %ymm6
+ vpmovmskb %ymm6, %ecx
+ /* Shift out zero CHAR matches that are before the begining of
+ src (rdi). */
+ shrxl %edi, %ecx, %ecx
+ testl %ecx, %ecx
+ jz L(page_cross_continue)
+ VPCMPEQ %ymm1, %ymm7, %ymm1
+ vpmovmskb %ymm1, %eax
+
+ /* Shift out search CHAR matches that are before the begining of
+ src (rdi). */
+ shrxl %edi, %eax, %eax
+ blsmskl %ecx, %ecx
+ /* Check if any search CHAR match in range. */
+ andl %ecx, %eax
+ jz L(ret2)
+ bsrl %eax, %eax
+ addq %rdi, %rax
+# ifdef USE_AS_WCSRCHR
+ andq $-CHAR_SIZE, %rax
+# endif
+L(ret2):
+ VZEROUPPER_RETURN
+END(STRRCHR)
#endif