diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-07-25 13:20:41 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-07-25 13:20:41 -0700 |
commit | 7e4dc77b2869a683fc43c0394fca5441816390ba (patch) | |
tree | 62e734c599bc1da2712fdb63be996622c415a83a /tools/arch/x86/lib/memcpy_64.S | |
parent | 89e7eb098adfe342bc036f00201eb579d448f033 (diff) | |
parent | 5048c2af078d5976895d521262a8802ea791f3b0 (diff) | |
download | linux-7e4dc77b2869a683fc43c0394fca5441816390ba.tar.bz2 |
Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf updates from Ingo Molnar:
"With over 300 commits it's been a busy cycle - with most of the work
concentrated on the tooling side (as it should).
The main kernel side enhancements were:
- Add per event callchain limit: Recently we introduced a sysctl to
tune the max-stack for all events for which callchains were
requested:
$ sysctl kernel.perf_event_max_stack
kernel.perf_event_max_stack = 127
Now this patch introduces a way to configure this per event, i.e.
this becomes possible:
$ perf record -e sched:*/max-stack=2/ -e block:*/max-stack=10/ -a
allowing finer tuning of how much buffer space callchains use.
This uses an u16 from the reserved space at the end, leaving
another u16 for future use.
There has been interest in even finer tuning, namely to control the
max stack for kernel and userspace callchains separately. Further
discussion is needed, we may for instance use the remaining u16 for
that and when it is present, assume that the sample_max_stack
introduced in this patch applies for the kernel, and the u16 left
is used for limiting the userspace callchain (Arnaldo Carvalho de
Melo)
- Optimize AUX event (hardware assisted side-band event) delivery
(Kan Liang)
- Rework Intel family name macro usage (this is partially x86 arch
work) (Dave Hansen)
- Refine and fix Intel LBR support (David Carrillo-Cisneros)
- Add support for Intel 'TopDown' events (Andi Kleen)
- Intel uncore PMU driver fixes and enhancements (Kan Liang)
- ... other misc changes.
Here's an incomplete list of the tooling enhancements (but there's
much more, see the shortlog and the git log for details):
- Support cross unwinding, i.e. collecting '--call-graph dwarf'
perf.data files in one machine and then doing analysis in another
machine of a different hardware architecture. This enables, for
instance, to do:
$ perf record -a --call-graph dwarf
on a x86-32 or aarch64 system and then do 'perf report' on it on a
x86_64 workstation (He Kuang)
- Allow reading from a backward ring buffer (one setup via
sys_perf_event_open() with perf_event_attr.write_backward = 1)
(Wang Nan)
- Finish merging initial SDT (Statically Defined Traces) support, see
cset comments for details about how it all works (Masami Hiramatsu)
- Support attaching eBPF programs to tracepoints (Wang Nan)
- Add demangling of symbols in programs written in the Rust language
(David Tolnay)
- Add support for tracepoints in the python binding, including an
example, that sets up and parses sched:sched_switch events,
tools/perf/python/tracepoint.py (Jiri Olsa)
- Introduce --stdio-color to set up the color output mode selection
in 'annotate' and 'report', allowing emit color escape sequences
when redirecting the output of these tools (Arnaldo Carvalho de
Melo)
- Add 'callindent' option to 'perf script -F', to indent the Intel PT
call stack, making this output more ftrace-like (Adrian Hunter,
Andi Kleen)
- Allow dumping the object files generated by llvm when processing
eBPF scriptlet events (Wang Nan)
- Add stackcollapse.py script to help generating flame graphs (Paolo
Bonzini)
- Add --ldlat option to 'perf mem' to specify load latency for loads
event (e.g. cpu/mem-loads/ ) (Jiri Olsa)
- Tooling support for Intel TopDown counters, recently added to the
kernel (Andi Kleen)"
* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (303 commits)
perf tests: Add is_printable_array test
perf tools: Make is_printable_array global
perf script python: Fix string vs byte array resolving
perf probe: Warn unmatched function filter correctly
perf cpu_map: Add more helpers
perf stat: Balance opening and reading events
tools: Copy linux/{hash,poison}.h and check for drift
perf tools: Remove include/linux/list.h from perf's MANIFEST
tools: Copy the bitops files accessed from the kernel and check for drift
Remove: kernel unistd*h files from perf's MANIFEST, not used
perf tools: Remove tools/perf/util/include/linux/const.h
perf tools: Remove tools/perf/util/include/asm/byteorder.h
perf tools: Add missing linux/compiler.h include to perf-sys.h
perf jit: Remove some no-op error handling
perf jit: Add missing curly braces
objtool: Initialize variable to silence old compiler
objtool: Add -I$(srctree)/tools/arch/$(ARCH)/include/uapi
perf record: Add --tail-synthesize option
perf session: Don't warn about out of order event if write_backward is used
perf tools: Enable overwrite settings
...
Diffstat (limited to 'tools/arch/x86/lib/memcpy_64.S')
-rw-r--r-- | tools/arch/x86/lib/memcpy_64.S | 297 |
1 files changed, 297 insertions, 0 deletions
diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S new file mode 100644 index 000000000000..2ec0b0abbfaa --- /dev/null +++ b/tools/arch/x86/lib/memcpy_64.S @@ -0,0 +1,297 @@ +/* Copyright 2002 Andi Kleen */ + +#include <linux/linkage.h> +#include <asm/errno.h> +#include <asm/cpufeatures.h> +#include <asm/alternative-asm.h> + +/* + * We build a jump to memcpy_orig by default which gets NOPped out on + * the majority of x86 CPUs which set REP_GOOD. In addition, CPUs which + * have the enhanced REP MOVSB/STOSB feature (ERMS), change those NOPs + * to a jmp to memcpy_erms which does the REP; MOVSB mem copy. + */ + +.weak memcpy + +/* + * memcpy - Copy a memory block. + * + * Input: + * rdi destination + * rsi source + * rdx count + * + * Output: + * rax original destination + */ +ENTRY(__memcpy) +ENTRY(memcpy) + ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \ + "jmp memcpy_erms", X86_FEATURE_ERMS + + movq %rdi, %rax + movq %rdx, %rcx + shrq $3, %rcx + andl $7, %edx + rep movsq + movl %edx, %ecx + rep movsb + ret +ENDPROC(memcpy) +ENDPROC(__memcpy) + +/* + * memcpy_erms() - enhanced fast string memcpy. This is faster and + * simpler than memcpy. Use memcpy_erms when possible. + */ +ENTRY(memcpy_erms) + movq %rdi, %rax + movq %rdx, %rcx + rep movsb + ret +ENDPROC(memcpy_erms) + +ENTRY(memcpy_orig) + movq %rdi, %rax + + cmpq $0x20, %rdx + jb .Lhandle_tail + + /* + * We check whether memory false dependence could occur, + * then jump to corresponding copy mode. + */ + cmp %dil, %sil + jl .Lcopy_backward + subq $0x20, %rdx +.Lcopy_forward_loop: + subq $0x20, %rdx + + /* + * Move in blocks of 4x8 bytes: + */ + movq 0*8(%rsi), %r8 + movq 1*8(%rsi), %r9 + movq 2*8(%rsi), %r10 + movq 3*8(%rsi), %r11 + leaq 4*8(%rsi), %rsi + + movq %r8, 0*8(%rdi) + movq %r9, 1*8(%rdi) + movq %r10, 2*8(%rdi) + movq %r11, 3*8(%rdi) + leaq 4*8(%rdi), %rdi + jae .Lcopy_forward_loop + addl $0x20, %edx + jmp .Lhandle_tail + +.Lcopy_backward: + /* + * Calculate copy position to tail. + */ + addq %rdx, %rsi + addq %rdx, %rdi + subq $0x20, %rdx + /* + * At most 3 ALU operations in one cycle, + * so append NOPS in the same 16 bytes trunk. + */ + .p2align 4 +.Lcopy_backward_loop: + subq $0x20, %rdx + movq -1*8(%rsi), %r8 + movq -2*8(%rsi), %r9 + movq -3*8(%rsi), %r10 + movq -4*8(%rsi), %r11 + leaq -4*8(%rsi), %rsi + movq %r8, -1*8(%rdi) + movq %r9, -2*8(%rdi) + movq %r10, -3*8(%rdi) + movq %r11, -4*8(%rdi) + leaq -4*8(%rdi), %rdi + jae .Lcopy_backward_loop + + /* + * Calculate copy position to head. + */ + addl $0x20, %edx + subq %rdx, %rsi + subq %rdx, %rdi +.Lhandle_tail: + cmpl $16, %edx + jb .Lless_16bytes + + /* + * Move data from 16 bytes to 31 bytes. + */ + movq 0*8(%rsi), %r8 + movq 1*8(%rsi), %r9 + movq -2*8(%rsi, %rdx), %r10 + movq -1*8(%rsi, %rdx), %r11 + movq %r8, 0*8(%rdi) + movq %r9, 1*8(%rdi) + movq %r10, -2*8(%rdi, %rdx) + movq %r11, -1*8(%rdi, %rdx) + retq + .p2align 4 +.Lless_16bytes: + cmpl $8, %edx + jb .Lless_8bytes + /* + * Move data from 8 bytes to 15 bytes. + */ + movq 0*8(%rsi), %r8 + movq -1*8(%rsi, %rdx), %r9 + movq %r8, 0*8(%rdi) + movq %r9, -1*8(%rdi, %rdx) + retq + .p2align 4 +.Lless_8bytes: + cmpl $4, %edx + jb .Lless_3bytes + + /* + * Move data from 4 bytes to 7 bytes. + */ + movl (%rsi), %ecx + movl -4(%rsi, %rdx), %r8d + movl %ecx, (%rdi) + movl %r8d, -4(%rdi, %rdx) + retq + .p2align 4 +.Lless_3bytes: + subl $1, %edx + jb .Lend + /* + * Move data from 1 bytes to 3 bytes. + */ + movzbl (%rsi), %ecx + jz .Lstore_1byte + movzbq 1(%rsi), %r8 + movzbq (%rsi, %rdx), %r9 + movb %r8b, 1(%rdi) + movb %r9b, (%rdi, %rdx) +.Lstore_1byte: + movb %cl, (%rdi) + +.Lend: + retq +ENDPROC(memcpy_orig) + +#ifndef CONFIG_UML +/* + * memcpy_mcsafe - memory copy with machine check exception handling + * Note that we only catch machine checks when reading the source addresses. + * Writes to target are posted and don't generate machine checks. + */ +ENTRY(memcpy_mcsafe) + cmpl $8, %edx + /* Less than 8 bytes? Go to byte copy loop */ + jb .L_no_whole_words + + /* Check for bad alignment of source */ + testl $7, %esi + /* Already aligned */ + jz .L_8byte_aligned + + /* Copy one byte at a time until source is 8-byte aligned */ + movl %esi, %ecx + andl $7, %ecx + subl $8, %ecx + negl %ecx + subl %ecx, %edx +.L_copy_leading_bytes: + movb (%rsi), %al + movb %al, (%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz .L_copy_leading_bytes + +.L_8byte_aligned: + /* Figure out how many whole cache lines (64-bytes) to copy */ + movl %edx, %ecx + andl $63, %edx + shrl $6, %ecx + jz .L_no_whole_cache_lines + + /* Loop copying whole cache lines */ +.L_cache_w0: movq (%rsi), %r8 +.L_cache_w1: movq 1*8(%rsi), %r9 +.L_cache_w2: movq 2*8(%rsi), %r10 +.L_cache_w3: movq 3*8(%rsi), %r11 + movq %r8, (%rdi) + movq %r9, 1*8(%rdi) + movq %r10, 2*8(%rdi) + movq %r11, 3*8(%rdi) +.L_cache_w4: movq 4*8(%rsi), %r8 +.L_cache_w5: movq 5*8(%rsi), %r9 +.L_cache_w6: movq 6*8(%rsi), %r10 +.L_cache_w7: movq 7*8(%rsi), %r11 + movq %r8, 4*8(%rdi) + movq %r9, 5*8(%rdi) + movq %r10, 6*8(%rdi) + movq %r11, 7*8(%rdi) + leaq 64(%rsi), %rsi + leaq 64(%rdi), %rdi + decl %ecx + jnz .L_cache_w0 + + /* Are there any trailing 8-byte words? */ +.L_no_whole_cache_lines: + movl %edx, %ecx + andl $7, %edx + shrl $3, %ecx + jz .L_no_whole_words + + /* Copy trailing words */ +.L_copy_trailing_words: + movq (%rsi), %r8 + mov %r8, (%rdi) + leaq 8(%rsi), %rsi + leaq 8(%rdi), %rdi + decl %ecx + jnz .L_copy_trailing_words + + /* Any trailing bytes? */ +.L_no_whole_words: + andl %edx, %edx + jz .L_done_memcpy_trap + + /* Copy trailing bytes */ + movl %edx, %ecx +.L_copy_trailing_bytes: + movb (%rsi), %al + movb %al, (%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz .L_copy_trailing_bytes + + /* Copy successful. Return zero */ +.L_done_memcpy_trap: + xorq %rax, %rax + ret +ENDPROC(memcpy_mcsafe) + + .section .fixup, "ax" + /* Return -EFAULT for any failure */ +.L_memcpy_mcsafe_fail: + mov $-EFAULT, %rax + ret + + .previous + + _ASM_EXTABLE_FAULT(.L_copy_leading_bytes, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w0, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w1, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w4, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w5, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w6, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w7, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_copy_trailing_words, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_copy_trailing_bytes, .L_memcpy_mcsafe_fail) +#endif |