diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-11-13 13:05:08 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-11-13 13:05:08 -0800 |
commit | 31486372a1e9a66ec2e9e2903b8792bba7e503e1 (patch) | |
tree | 84f61e0758695e6fbee8d2b7d7b9bc4a5ce6e03b /arch/x86/kernel/kprobes/opt.c | |
parent | 8e9a2dba8686187d8c8179e5b86640e653963889 (diff) | |
parent | fcdfafcb73be8fa45909327bbddca46fb362a675 (diff) |
Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf updates from Ingo Molnar:
"The main changes in this cycle were:
Kernel:
- kprobes updates: use better W^X patterns for code modifications,
improve optprobes, remove jprobes. (Masami Hiramatsu, Kees Cook)
- core fixes: event timekeeping (enabled/running times statistics)
fixes, perf_event_read() locking fixes and cleanups, etc. (Peter
Zijlstra)
- Extend x86 Intel free-running PEBS support and support x86
user-register sampling in perf record and perf script. (Andi Kleen)
Tooling:
- Completely rework the way inline frames are handled. Instead of
querying for the inline nodes on-demand in the individual tools, we
now create proper callchain nodes for inlined frames. (Milian
Wolff)
- 'perf trace' updates (Arnaldo Carvalho de Melo)
- Implement a way to print formatted output to per-event files in
'perf script' to facilitate generate flamegraphs, elliminating the
need to write scripts to do that separation (yuzhoujian, Arnaldo
Carvalho de Melo)
- Update vendor events JSON metrics for Intel's Broadwell, Broadwell
Server, Haswell, Haswell Server, IvyBridge, IvyTown, JakeTown,
Sandy Bridge, Skylake, SkyLake Server - and Goldmont Plus V1 (Andi
Kleen, Kan Liang)
- Multithread the synthesizing of PERF_RECORD_ events for
pre-existing threads in 'perf top', speeding up that phase, greatly
improving the user experience in systems such as Intel's Knights
Mill (Kan Liang)
- Introduce the concept of weak groups in 'perf stat': try to set up
a group, but if it's not schedulable fallback to not using a group.
That gives us the best of both worlds: groups if they work, but
still a usable fallback if they don't. E.g: (Andi Kleen)
- perf sched timehist enhancements (David Ahern)
- ... various other enhancements, updates, cleanups and fixes"
* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (139 commits)
kprobes: Don't spam the build log with deprecation warnings
arm/kprobes: Remove jprobe test case
arm/kprobes: Fix kretprobe test to check correct counter
perf srcline: Show correct function name for srcline of callchains
perf srcline: Fix memory leak in addr2inlines()
perf trace beauty kcmp: Beautify arguments
perf trace beauty: Implement pid_fd beautifier
tools include uapi: Grab a copy of linux/kcmp.h
perf callchain: Fix double mapping al->addr for children without self period
perf stat: Make --per-thread update shadow stats to show metrics
perf stat: Move the shadow stats scale computation in perf_stat__update_shadow_stats
perf tools: Add perf_data_file__write function
perf tools: Add struct perf_data_file
perf tools: Rename struct perf_data_file to perf_data
perf script: Print information about per-event-dump files
perf trace beauty prctl: Generate 'option' string table from kernel headers
tools include uapi: Grab a copy of linux/prctl.h
perf script: Allow creating per-event dump files
perf evsel: Restore evsel->priv as a tool private area
perf script: Use event_format__fprintf()
...
Diffstat (limited to 'arch/x86/kernel/kprobes/opt.c')
-rw-r--r-- | arch/x86/kernel/kprobes/opt.c | 79 |
1 files changed, 43 insertions, 36 deletions
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 4f98aad38237..e941136e24d8 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -142,11 +142,11 @@ void optprobe_template_func(void); STACK_FRAME_NON_STANDARD(optprobe_template_func); #define TMPL_MOVE_IDX \ - ((long)&optprobe_template_val - (long)&optprobe_template_entry) + ((long)optprobe_template_val - (long)optprobe_template_entry) #define TMPL_CALL_IDX \ - ((long)&optprobe_template_call - (long)&optprobe_template_entry) + ((long)optprobe_template_call - (long)optprobe_template_entry) #define TMPL_END_IDX \ - ((long)&optprobe_template_end - (long)&optprobe_template_entry) + ((long)optprobe_template_end - (long)optprobe_template_entry) #define INT3_SIZE sizeof(kprobe_opcode_t) @@ -154,17 +154,15 @@ STACK_FRAME_NON_STANDARD(optprobe_template_func); static void optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) { - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - unsigned long flags; - /* This is possible if op is under delayed unoptimizing */ if (kprobe_disabled(&op->kp)) return; - local_irq_save(flags); + preempt_disable(); if (kprobe_running()) { kprobes_inc_nmissed_count(&op->kp); } else { + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); /* Save skipped registers */ #ifdef CONFIG_X86_64 regs->cs = __KERNEL_CS; @@ -180,17 +178,17 @@ optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) opt_pre_handler(&op->kp, regs); __this_cpu_write(current_kprobe, NULL); } - local_irq_restore(flags); + preempt_enable_no_resched(); } NOKPROBE_SYMBOL(optimized_callback); -static int copy_optimized_instructions(u8 *dest, u8 *src) +static int copy_optimized_instructions(u8 *dest, u8 *src, u8 *real) { struct insn insn; int len = 0, ret; while (len < RELATIVEJUMP_SIZE) { - ret = __copy_instruction(dest + len, src + len, &insn); + ret = __copy_instruction(dest + len, src + len, real, &insn); if (!ret || !can_boost(&insn, src + len)) return -EINVAL; len += ret; @@ -343,57 +341,66 @@ void arch_remove_optimized_kprobe(struct optimized_kprobe *op) int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *__unused) { - u8 *buf; - int ret; + u8 *buf = NULL, *slot; + int ret, len; long rel; if (!can_optimize((unsigned long)op->kp.addr)) return -EILSEQ; - op->optinsn.insn = get_optinsn_slot(); - if (!op->optinsn.insn) + buf = kzalloc(MAX_OPTINSN_SIZE, GFP_KERNEL); + if (!buf) return -ENOMEM; + op->optinsn.insn = slot = get_optinsn_slot(); + if (!slot) { + ret = -ENOMEM; + goto out; + } + /* * Verify if the address gap is in 2GB range, because this uses * a relative jump. */ - rel = (long)op->optinsn.insn - (long)op->kp.addr + RELATIVEJUMP_SIZE; + rel = (long)slot - (long)op->kp.addr + RELATIVEJUMP_SIZE; if (abs(rel) > 0x7fffffff) { - __arch_remove_optimized_kprobe(op, 0); - return -ERANGE; + ret = -ERANGE; + goto err; } - buf = (u8 *)op->optinsn.insn; - set_memory_rw((unsigned long)buf & PAGE_MASK, 1); + /* Copy arch-dep-instance from template */ + memcpy(buf, optprobe_template_entry, TMPL_END_IDX); /* Copy instructions into the out-of-line buffer */ - ret = copy_optimized_instructions(buf + TMPL_END_IDX, op->kp.addr); - if (ret < 0) { - __arch_remove_optimized_kprobe(op, 0); - return ret; - } + ret = copy_optimized_instructions(buf + TMPL_END_IDX, op->kp.addr, + slot + TMPL_END_IDX); + if (ret < 0) + goto err; op->optinsn.size = ret; - - /* Copy arch-dep-instance from template */ - memcpy(buf, &optprobe_template_entry, TMPL_END_IDX); + len = TMPL_END_IDX + op->optinsn.size; /* Set probe information */ synthesize_set_arg1(buf + TMPL_MOVE_IDX, (unsigned long)op); /* Set probe function call */ - synthesize_relcall(buf + TMPL_CALL_IDX, optimized_callback); + synthesize_relcall(buf + TMPL_CALL_IDX, + slot + TMPL_CALL_IDX, optimized_callback); /* Set returning jmp instruction at the tail of out-of-line buffer */ - synthesize_reljump(buf + TMPL_END_IDX + op->optinsn.size, + synthesize_reljump(buf + len, slot + len, (u8 *)op->kp.addr + op->optinsn.size); - - set_memory_ro((unsigned long)buf & PAGE_MASK, 1); - - flush_icache_range((unsigned long) buf, - (unsigned long) buf + TMPL_END_IDX + - op->optinsn.size + RELATIVEJUMP_SIZE); - return 0; + len += RELATIVEJUMP_SIZE; + + /* We have to use text_poke for instuction buffer because it is RO */ + text_poke(slot, buf, len); + ret = 0; +out: + kfree(buf); + return ret; + +err: + __arch_remove_optimized_kprobe(op, 0); + goto out; } /* |