提交 0cdf6d46 编写于 作者: L Linus Torvalds

Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf fixes from Thomas Gleixner:
 "A set of fixes for perf:

  Kernel side:

   - Fix the hardcoded index of extra PCI devices on Broadwell which
     caused a resource conflict and triggered warnings on CPU hotplug.

  Tooling:

   - Update the tools copy of several files, including perf_event.h,
     powerpc's asm/unistd.h (new io_pgetevents syscall), bpf.h and x86's
     memcpy_64.s (used in 'perf bench mem'), silencing the respective
     warnings during the perf tools build.

   - Fix the build on the alpine:edge distro"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86/intel/uncore: Fix hardcoded index of Broadwell extra PCI devices
  perf tools: Fix the build on the alpine:edge distro
  tools arch: Update arch/x86/lib/memcpy_64.S copy used in 'perf bench mem memcpy'
  tools headers uapi: Refresh linux/bpf.h copy
  tools headers powerpc: Update asm/unistd.h copy to pick new
  tools headers uapi: Update tools's copy of linux/perf_event.h
......@@ -28,7 +28,7 @@
#define UNCORE_PCI_DEV_TYPE(data) ((data >> 8) & 0xff)
#define UNCORE_PCI_DEV_IDX(data) (data & 0xff)
#define UNCORE_EXTRA_PCI_DEV 0xff
#define UNCORE_EXTRA_PCI_DEV_MAX 3
#define UNCORE_EXTRA_PCI_DEV_MAX 4
#define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff)
......
......@@ -1029,6 +1029,7 @@ void snbep_uncore_cpu_init(void)
enum {
SNBEP_PCI_QPI_PORT0_FILTER,
SNBEP_PCI_QPI_PORT1_FILTER,
BDX_PCI_QPI_PORT2_FILTER,
HSWEP_PCI_PCU_3,
};
......@@ -3286,15 +3287,18 @@ static const struct pci_device_id bdx_uncore_pci_ids[] = {
},
{ /* QPI Port 0 filter */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f86),
.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 0),
.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
SNBEP_PCI_QPI_PORT0_FILTER),
},
{ /* QPI Port 1 filter */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f96),
.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 1),
.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
SNBEP_PCI_QPI_PORT1_FILTER),
},
{ /* QPI Port 2 filter */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f46),
.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 2),
.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
BDX_PCI_QPI_PORT2_FILTER),
},
{ /* PCU.3 (for Capability registers) */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fc0),
......
......@@ -399,5 +399,6 @@
#define __NR_pkey_free 385
#define __NR_pkey_mprotect 386
#define __NR_rseq 387
#define __NR_io_pgetevents 388
#endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _MCSAFE_TEST_H_
#define _MCSAFE_TEST_H_
.macro MCSAFE_TEST_CTL
.endm
.macro MCSAFE_TEST_SRC reg count target
.endm
.macro MCSAFE_TEST_DST reg count target
.endm
#endif /* _MCSAFE_TEST_H_ */
......@@ -3,6 +3,7 @@
#include <linux/linkage.h>
#include <asm/errno.h>
#include <asm/cpufeatures.h>
#include <asm/mcsafe_test.h>
#include <asm/alternative-asm.h>
#include <asm/export.h>
......@@ -183,12 +184,15 @@ ENTRY(memcpy_orig)
ENDPROC(memcpy_orig)
#ifndef CONFIG_UML
MCSAFE_TEST_CTL
/*
* memcpy_mcsafe_unrolled - memory copy with machine check exception handling
* __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_unrolled)
ENTRY(__memcpy_mcsafe)
cmpl $8, %edx
/* Less than 8 bytes? Go to byte copy loop */
jb .L_no_whole_words
......@@ -204,58 +208,33 @@ ENTRY(memcpy_mcsafe_unrolled)
subl $8, %ecx
negl %ecx
subl %ecx, %edx
.L_copy_leading_bytes:
.L_read_leading_bytes:
movb (%rsi), %al
MCSAFE_TEST_SRC %rsi 1 .E_leading_bytes
MCSAFE_TEST_DST %rdi 1 .E_leading_bytes
.L_write_leading_bytes:
movb %al, (%rdi)
incq %rsi
incq %rdi
decl %ecx
jnz .L_copy_leading_bytes
jnz .L_read_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:
.L_read_words:
movq (%rsi), %r8
mov %r8, (%rdi)
leaq 8(%rsi), %rsi
leaq 8(%rdi), %rdi
MCSAFE_TEST_SRC %rsi 8 .E_read_words
MCSAFE_TEST_DST %rdi 8 .E_write_words
.L_write_words:
movq %r8, (%rdi)
addq $8, %rsi
addq $8, %rdi
decl %ecx
jnz .L_copy_trailing_words
jnz .L_read_words
/* Any trailing bytes? */
.L_no_whole_words:
......@@ -264,38 +243,55 @@ ENTRY(memcpy_mcsafe_unrolled)
/* Copy trailing bytes */
movl %edx, %ecx
.L_copy_trailing_bytes:
.L_read_trailing_bytes:
movb (%rsi), %al
MCSAFE_TEST_SRC %rsi 1 .E_trailing_bytes
MCSAFE_TEST_DST %rdi 1 .E_trailing_bytes
.L_write_trailing_bytes:
movb %al, (%rdi)
incq %rsi
incq %rdi
decl %ecx
jnz .L_copy_trailing_bytes
jnz .L_read_trailing_bytes
/* Copy successful. Return zero */
.L_done_memcpy_trap:
xorq %rax, %rax
ret
ENDPROC(memcpy_mcsafe_unrolled)
EXPORT_SYMBOL_GPL(memcpy_mcsafe_unrolled)
ENDPROC(__memcpy_mcsafe)
EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
.section .fixup, "ax"
/* Return -EFAULT for any failure */
.L_memcpy_mcsafe_fail:
mov $-EFAULT, %rax
/*
* Return number of bytes not copied for any failure. Note that
* there is no "tail" handling since the source buffer is 8-byte
* aligned and poison is cacheline aligned.
*/
.E_read_words:
shll $3, %ecx
.E_leading_bytes:
addl %edx, %ecx
.E_trailing_bytes:
mov %ecx, %eax
ret
/*
* For write fault handling, given the destination is unaligned,
* we handle faults on multi-byte writes with a byte-by-byte
* copy up to the write-protected page.
*/
.E_write_words:
shll $3, %ecx
addl %edx, %ecx
movl %ecx, %edx
jmp mcsafe_handle_tail
.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_w2, .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)
_ASM_EXTABLE_FAULT(.L_read_leading_bytes, .E_leading_bytes)
_ASM_EXTABLE_FAULT(.L_read_words, .E_read_words)
_ASM_EXTABLE_FAULT(.L_read_trailing_bytes, .E_trailing_bytes)
_ASM_EXTABLE(.L_write_leading_bytes, .E_leading_bytes)
_ASM_EXTABLE(.L_write_words, .E_write_words)
_ASM_EXTABLE(.L_write_trailing_bytes, .E_trailing_bytes)
#endif
......@@ -1857,7 +1857,8 @@ union bpf_attr {
* is resolved), the nexthop address is returned in ipv4_dst
* or ipv6_dst based on family, smac is set to mac address of
* egress device, dmac is set to nexthop mac address, rt_metric
* is set to metric from route (IPv4/IPv6 only).
* is set to metric from route (IPv4/IPv6 only), and ifindex
* is set to the device index of the nexthop from the FIB lookup.
*
* *plen* argument is the size of the passed in struct.
* *flags* argument can be a combination of one or more of the
......@@ -1873,9 +1874,10 @@ union bpf_attr {
* *ctx* is either **struct xdp_md** for XDP programs or
* **struct sk_buff** tc cls_act programs.
* Return
* Egress device index on success, 0 if packet needs to continue
* up the stack for further processing or a negative error in case
* of failure.
* * < 0 if any input argument is invalid
* * 0 on success (packet is forwarded, nexthop neighbor exists)
* * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
* * packet is not forwarded or needs assist from full stack
*
* int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags)
* Description
......@@ -2612,6 +2614,18 @@ struct bpf_raw_tracepoint_args {
#define BPF_FIB_LOOKUP_DIRECT BIT(0)
#define BPF_FIB_LOOKUP_OUTPUT BIT(1)
enum {
BPF_FIB_LKUP_RET_SUCCESS, /* lookup successful */
BPF_FIB_LKUP_RET_BLACKHOLE, /* dest is blackholed; can be dropped */
BPF_FIB_LKUP_RET_UNREACHABLE, /* dest is unreachable; can be dropped */
BPF_FIB_LKUP_RET_PROHIBIT, /* dest not allowed; can be dropped */
BPF_FIB_LKUP_RET_NOT_FWDED, /* packet is not forwarded */
BPF_FIB_LKUP_RET_FWD_DISABLED, /* fwding is not enabled on ingress */
BPF_FIB_LKUP_RET_UNSUPP_LWT, /* fwd requires encapsulation */
BPF_FIB_LKUP_RET_NO_NEIGH, /* no neighbor entry for nh */
BPF_FIB_LKUP_RET_FRAG_NEEDED, /* fragmentation required to fwd */
};
struct bpf_fib_lookup {
/* input: network family for lookup (AF_INET, AF_INET6)
* output: network family of egress nexthop
......@@ -2625,7 +2639,11 @@ struct bpf_fib_lookup {
/* total length of packet from network header - used for MTU check */
__u16 tot_len;
__u32 ifindex; /* L3 device index for lookup */
/* input: L3 device index for lookup
* output: device index from FIB lookup
*/
__u32 ifindex;
union {
/* inputs to lookup */
......
......@@ -143,6 +143,8 @@ enum perf_event_sample_format {
PERF_SAMPLE_PHYS_ADDR = 1U << 19,
PERF_SAMPLE_MAX = 1U << 20, /* non-ABI */
__PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63,
};
/*
......
// SPDX-License-Identifier: GPL-2.0
#include <string.h>
#include <linux/stddef.h>
#include <linux/perf_event.h>
#include "../../util/intel-pt.h"
......
......@@ -2,6 +2,7 @@
#include <stdbool.h>
#include <errno.h>
#include <linux/stddef.h>
#include <linux/perf_event.h>
#include "../../perf.h"
......
......@@ -7,6 +7,7 @@ perf-y += futex-wake-parallel.o
perf-y += futex-requeue.o
perf-y += futex-lock-pi.o
perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-lib.o
perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o
perf-$(CONFIG_X86_64) += mem-memset-x86-64-asm.o
......
......@@ -6,6 +6,7 @@
#define altinstr_replacement text
#define globl p2align 4; .globl
#define _ASM_EXTABLE_FAULT(x, y)
#define _ASM_EXTABLE(x, y)
#include "../../arch/x86/lib/memcpy_64.S"
/*
......
/*
* From code in arch/x86/lib/usercopy_64.c, copied to keep tools/ copy
* of the kernel's arch/x86/lib/memcpy_64.s used in 'perf bench mem memcpy'
* happy.
*/
#include <linux/types.h>
unsigned long __memcpy_mcsafe(void *dst, const void *src, size_t cnt);
unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len);
unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len)
{
for (; len; --len, to++, from++) {
/*
* Call the assembly routine back directly since
* memcpy_mcsafe() may silently fallback to memcpy.
*/
unsigned long rem = __memcpy_mcsafe(to, from, 1);
if (rem)
break;
}
return len;
}
......@@ -5,6 +5,7 @@
#include <time.h>
#include <stdbool.h>
#include <linux/types.h>
#include <linux/stddef.h>
#include <linux/perf_event.h>
extern bool test_attr__enabled;
......
......@@ -2,6 +2,7 @@
#ifndef __PERF_HEADER_H
#define __PERF_HEADER_H
#include <linux/stddef.h>
#include <linux/perf_event.h>
#include <sys/types.h>
#include <stdbool.h>
......
......@@ -10,6 +10,7 @@
#define __PERF_NAMESPACES_H
#include <sys/types.h>
#include <linux/stddef.h>
#include <linux/perf_event.h>
#include <linux/refcount.h>
#include <linux/types.h>
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册