perf: Fix bpf prologue generation, uaccess
Subsystems (2)
v2 cover perf: Fix bpf prologue generation, uaccess
Patches:
1. Fix bpf prologue generation. bpf_probe_read is unavailable for arch with overlapping address space. If uaccess, use bpf_probe_read_user. Otherwise, use bpf_probe_read_kernel.
2. Fix uaccess in kprobes. Now perf probe add with @user attribute works
v1->v2:
- Split the patches and add Acked-By
Thank you.
Sumanth Korikkar (2):
perf: Fix user attribute access in kprobes
perf: Fix bpf prologue generation
tools/perf/util/bpf-prologue.c | 14 ++++++++++---- tools/perf/util/probe-event.c | 7 +++++-- tools/perf/util/probe-file.c | 2 +- 3 files changed, 16 insertions(+), 7 deletions(-)
Signature · 1 line
2.17.1
PATCH v2 1/2 perf: Fix user attribute access in kprobes
Issue:
perf probe -a 'do_sched_setscheduler pid policy param->sched_priority@user' did not work before.
Fix:
Make (perf probe -a 'do_sched_setscheduler pid policy param->sched_priority@user') output equivalent to ftrace ('p:probe/do_sched_setscheduler _text+517384 pid=%r2:s32 policy=%r3:s32 sched_priority=+u0(%r4):s32' > kprobe_events)
Other:
1. Right now, __match_glob() does not handle [u]<offset>. For now, use *u]<offset>.
2. @user attribute was introduced in commit 1e032f7cfa14 ("perf-probe:
Add user memory access attribute support")
Test:
1. perf probe -a 'do_sched_setscheduler pid policy param->sched_priority@user'
2 ./perf script
sched 305669 [000] 1614458.838675: perf_bpf_probe:func: (2904e508) pid=261614 policy=2 sched_priority=1
3. cat /sys/kernel/debug/tracing/trace <...>-309956 [006] .... 1616098.093957: 0: prio: 1
--- tools/perf/util/probe-event.c | 7 +++++-- tools/perf/util/probe-file.c | 2 +- 2 files changed, 6 insertions(+), 3 deletions(-)
tools/perf/util/probe-event.c +5 -2
@@ -1575,7 +1575,7 @@ static int parse_perf_probe_arg(char *str, struct perf_probe_arg *arg) } tmp =strchr (str,'@' ); -if (tmp && tmp != str &&strcmp (tmp +1 ,"user" )) {/* user attr */ +if (tmp && tmp != str && !strcmp (tmp +1 ,"user" )) {/* user attr */ if (!user_access_is_supported ()) {semantic_error ("ftrace does not support user access\n" );return -EINVAL ;
@@ -1995,7 +1995,10 @@ static int __synthesize_probe_trace_arg_ref(struct probe_trace_arg_ref *ref,if (depth <0 )return depth; } - err =strbuf_addf (buf,"%+ld(" , ref->offset); +if (ref->user_access) + err =strbuf_addf (buf,"%s%ld(" ,"+u" , ref->offset); +else + err =strbuf_addf (buf,"%+ld(" , ref->offset);return (err <0 ) ? err : depth; }
tools/perf/util/probe-file.c +1 -1
@@ -1044,7 +1044,7 @@ static struct {DEFINE_TYPE (FTRACE_README_PROBE_TYPE_X ,"*type: * x8/16/32/64,*" ),DEFINE_TYPE (FTRACE_README_KRETPROBE_OFFSET ,"*place (kretprobe): *" ),DEFINE_TYPE (FTRACE_README_UPROBE_REF_CTR ,"*ref_ctr_offset*" ), -DEFINE_TYPE (FTRACE_README_USER_ACCESS ,"*[u]<offset>*" ), +DEFINE_TYPE (FTRACE_README_USER_ACCESS ,"*u]<offset>*" ),DEFINE_TYPE (FTRACE_README_MULTIPROBE_EVENT ,"*Create/append/*" ), DEFINE_TYPE(FTRACE_README_IMMEDIATE_VALUE, "*\\imm-value,*"), };
Signature · 1 line
2.17.1
Arnaldo Carvalho de Melo
maintainerRe: [PATCH v2 1/2] perf: Fix user attribute access in kprobes
Em Tue, Jun 09, 2020 at 10:10:18AM +0200, Sumanth Korikkar escreveu:
Quoted 20 lines
Issue:
perf probe -a 'do_sched_setschedulerpid policy param->sched_priority@user' did not work before.Fix:
Make (perf probe -a 'do_sched_setschedulerpid policy param->sched_priority@user') output equivalent to ftrace ('p:probe/do_sched_setscheduler _text+517384 pid=%r2:s32 policy=%r3:s32 sched_priority=+u0(%r4):s32' >kprobe_events)Other:
1. Right now,__match_glob()does not handle [u]<offset>. For now, use *u]<offset>.
2. @user attribute was introduced in commit1e032f7cfa14("perf-probe:
Add user memory access attribute support")Test:
1. perf probe -a 'do_sched_setschedulerpid policy param->sched_priority@user'
Quoted 6 lines
2 ./perf script
sched 305669 [000] 1614458.838675: perf_bpf_probe:func: (2904e508) pid=261614 policy=2 sched_priority=13. cat
/sys/kernel/debug/tracing/trace<...>-309956 [006] .... 1616098.093957: 0: prio: 1
Thanks, I'm adding this:
So that the stable guys pick this up eventually,
That first hunk with the strcmp() return check could have gone into a separate patch, but I'll process it as-is for expediency,
- Arnaldo
Quoted 49 lines
Signed-off-by Sumanth Korikkar <[email protected]>Reviewed-by Thomas Richter <[email protected]>Acked-by Masami Hiramatsu <[email protected]>--- tools/perf/util/probe-event.c | 7 +++++-- tools/perf/util/probe-file.c | 2 +- 2 files changed, 6 insertions(+), 3 deletions(-)tools/perf/util/probe-event.c +5
-2@@ -1575,7 +1575,7 @@ static int parse_perf_probe_arg(char *str, struct perf_probe_arg *arg) } tmp =strchr (str,'@' ); -if (tmp && tmp != str &&strcmp (tmp +1 ,"user" )) {/* user attr */ +if (tmp && tmp != str && !strcmp (tmp +1 ,"user" )) {/* user attr */ if (!user_access_is_supported ()) {semantic_error ("ftrace does not support user access\n" );return -EINVAL ;@@ -1995,7 +1995,10 @@ static int __synthesize_probe_trace_arg_ref(struct probe_trace_arg_ref *ref,if (depth <0 )return depth; } - err =strbuf_addf (buf,"%+ld(" , ref->offset); +if (ref->user_access) + err =strbuf_addf (buf,"%s%ld(" ,"+u" , ref->offset); +else + err =strbuf_addf (buf,"%+ld(" , ref->offset);return (err <0 ) ? err : depth; }tools/perf/util/probe-file.c +1
-1@@ -1044,7 +1044,7 @@ static struct {DEFINE_TYPE (FTRACE_README_PROBE_TYPE_X ,"*type: * x8/16/32/64,*" ),DEFINE_TYPE (FTRACE_README_KRETPROBE_OFFSET ,"*place (kretprobe): *" ),DEFINE_TYPE (FTRACE_README_UPROBE_REF_CTR ,"*ref_ctr_offset*" ), -DEFINE_TYPE (FTRACE_README_USER_ACCESS ,"*[u]<offset>*" ), +DEFINE_TYPE (FTRACE_README_USER_ACCESS ,"*u]<offset>*" ),DEFINE_TYPE (FTRACE_README_MULTIPROBE_EVENT ,"*Create/append/*" ), DEFINE_TYPE(FTRACE_README_IMMEDIATE_VALUE, "*\\imm-value,*"), };Signature · 1 line
2.17.1
Signature · 1 line
- Arnaldo
Arnaldo Carvalho de Melo
maintainerRe: [PATCH v2 1/2] perf: Fix user attribute access in kprobes
Em Tue, Jun 09, 2020 at 12:09:31PM -0300, Arnaldo Carvalho de Melo escreveu:
Quoted 30 lines
Em Tue, Jun 09, 2020 at 10:10:18AM +0200, Sumanth Korikkar escreveu:
Quoted 20 lines
Issue:
perf probe -a 'do_sched_setschedulerpid policy param->sched_priority@user' did not work before.Fix:
Make (perf probe -a 'do_sched_setschedulerpid policy param->sched_priority@user') output equivalent to ftrace ('p:probe/do_sched_setscheduler _text+517384 pid=%r2:s32 policy=%r3:s32 sched_priority=+u0(%r4):s32' >kprobe_events)Other:
1. Right now,__match_glob()does not handle [u]<offset>. For now, use *u]<offset>.
2. @user attribute was introduced in commit1e032f7cfa14("perf-probe:
Add user memory access attribute support")Test:
1. perf probe -a 'do_sched_setschedulerpid policy param->sched_priority@user'Quoted 6 lines
2 ./perf script
sched 305669 [000] 1614458.838675: perf_bpf_probe:func: (2904e508) pid=261614 policy=2 sched_priority=13. cat
/sys/kernel/debug/tracing/trace<...>-309956 [006] .... 1616098.093957: 0: prio: 1Thanks, I'm adding this:
Quoted 8 lines
Fixes 1e032f7cfa14 ("perf-probe: Add user memory access attribute support")Cc Masami Hiramatsu <[email protected]>Cc Steven Rostedt (VMware) <[email protected]>So that the stable guys pick this up eventually,
That first hunk with the
strcmp()return check could have gone into a separate patch, but I'll process it as-is for expediency,
I also added this:
ommitter testing:
Before:
# perf probe -a 'do_sched_setscheduler pid policy param->sched_priority@user'
param(type:sched_param) has no member sched_priority@user.
Error: Failed to add events.
# pahole sched_param
struct sched_param {
int sched_priority; /* 0 4 */ /* size: 4, cachelines: 1, members: 1 */
/* last cacheline: 4 bytes */ };
#
After:
# perf probe -a 'do_sched_setscheduler pid policy param->sched_priority@user'
Added new event:
probe:do_sched_setscheduler (on do_sched_setscheduler with pid policy sched_priority=param->sched_priority)You can now use it in all perf tools, such as:
perf record -e probe:do_sched_setscheduler -aR sleep 1
# cat /sys/kernel/debug/tracing/kprobe_events p:probe/do_sched_setscheduler _text+1113792 pid=%di:s32 policy=%si:s32 sched_priority=+u0(%dx):s32 #
Quoted 55 lines
- Arnaldo
Quoted 49 lines
Signed-off-by Sumanth Korikkar <[email protected]>Reviewed-by Thomas Richter <[email protected]>Acked-by Masami Hiramatsu <[email protected]>--- tools/perf/util/probe-event.c | 7 +++++-- tools/perf/util/probe-file.c | 2 +- 2 files changed, 6 insertions(+), 3 deletions(-)tools/perf/util/probe-event.c +5
-2@@ -1575,7 +1575,7 @@ static int parse_perf_probe_arg(char *str, struct perf_probe_arg *arg) } tmp =strchr (str,'@' ); -if (tmp && tmp != str &&strcmp (tmp +1 ,"user" )) {/* user attr */ +if (tmp && tmp != str && !strcmp (tmp +1 ,"user" )) {/* user attr */ if (!user_access_is_supported ()) {semantic_error ("ftrace does not support user access\n" );return -EINVAL ;@@ -1995,7 +1995,10 @@ static int __synthesize_probe_trace_arg_ref(struct probe_trace_arg_ref *ref,if (depth <0 )return depth; } - err =strbuf_addf (buf,"%+ld(" , ref->offset); +if (ref->user_access) + err =strbuf_addf (buf,"%s%ld(" ,"+u" , ref->offset); +else + err =strbuf_addf (buf,"%+ld(" , ref->offset);return (err <0 ) ? err : depth; }tools/perf/util/probe-file.c +1
-1@@ -1044,7 +1044,7 @@ static struct {DEFINE_TYPE (FTRACE_README_PROBE_TYPE_X ,"*type: * x8/16/32/64,*" ),DEFINE_TYPE (FTRACE_README_KRETPROBE_OFFSET ,"*place (kretprobe): *" ),DEFINE_TYPE (FTRACE_README_UPROBE_REF_CTR ,"*ref_ctr_offset*" ), -DEFINE_TYPE (FTRACE_README_USER_ACCESS ,"*[u]<offset>*" ), +DEFINE_TYPE (FTRACE_README_USER_ACCESS ,"*u]<offset>*" ),DEFINE_TYPE (FTRACE_README_MULTIPROBE_EVENT ,"*Create/append/*" ), DEFINE_TYPE(FTRACE_README_IMMEDIATE_VALUE, "*\\imm-value,*"), };Signature · 1 line
2.17.1Signature · 1 line
- Arnaldo
Signature · 1 line
- Arnaldo
PATCH v2 2/2 perf: Fix bpf prologue generation
In reply to Sumanth KorikkarIssue:bpf_probe_read is no longer available for architecture which has overlapping address space. Hence bpf prologue generation fails
Fix:
Use bpf_probe_read_kernel for kernel member access. For user attribute access in kprobes, use bpf_probe_read_user.
Other:
@user attribute was introduced in commit 1e032f7cfa14 ("perf-probe:
Add user memory access attribute support")
Test:
1. ulimit -l 128 ; ./perf record -e tests/bpf_sched_setscheduler.c
2. cat tests/bpf_sched_setscheduler.c
static void (*bpf_trace_printk)(const char *fmt, int fmt_size, ...) =
(void *) 6;
static int (*bpf_probe_read_user)(void *dst, __u32 size,
const void *unsafe_ptr) = (void *) 112;
static int (*bpf_probe_read_kernel)(void *dst, __u32 size,
const void *unsafe_ptr) = (void *) 113;SEC("func=do_sched_setscheduler pid policy param->sched_priority@user") int bpf_func__setscheduler(void *ctx, int err, pid_t pid, int policy,
int param)
{
char fmt[] = "prio: %ld";
bpf_trace_printk(fmt, sizeof(fmt), param);
return 1;
}char _license[] SEC("license") = "GPL";
int _version SEC("version") = LINUX_VERSION_CODE;
3. ./perf script
sched 305669 [000] 1614458.838675: perf_bpf_probe:func: (2904e508) pid=261614 policy=2 sched_priority=1
4. cat /sys/kernel/debug/tracing/trace <...>-309956 [006] .... 1616098.093957: 0: prio: 1
--- tools/perf/util/bpf-prologue.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-)
tools/perf/util/bpf-prologue.c +10 -4
@@ -142,7 +142,8 @@ static int gen_read_mem(struct bpf_insn_pos *pos, int src_base_addr_reg, int dst_addr_reg, - long offset) + long offset, + int probeid) { /* mov arg3, src_base_addr_reg */ if (src_base_addr_reg != BPF_REG_ARG3)
@@ -159,7 +160,7 @@ gen_read_mem(struct bpf_insn_pos *pos,ins (BPF_MOV64_REG (BPF_REG_ARG1 , dst_addr_reg), pos);/* Call probe_read */ -ins (BPF_EMIT_CALL (BPF_FUNC_probe_read), pos); +ins (BPF_EMIT_CALL (probeid), pos);/* * Error processing: if read fail, goto error code, * will be relocated. Target should be the start of
@@ -241,7 +242,7 @@ static int gen_prologue_slowpath(struct bpf_insn_pos *pos, struct probe_trace_arg *args, int nargs) { - int err, i; + int err, i, probeid;for (i =0 ; i < nargs; i++) {struct probe_trace_arg *arg = &args[i];
@@ -276,11 +277,16 @@ gen_prologue_slowpath(struct bpf_insn_pos *pos, stack_offset), pos); ref = arg->ref; + probeid = BPF_FUNC_probe_read_kernel;while (ref) {pr_debug ("prologue: arg %d: offset %ld\n" , i, ref->offset); + +if (ref->user_access) + probeid = BPF_FUNC_probe_read_user; + err =gen_read_mem (pos,BPF_REG_3 ,BPF_REG_7 , - ref->offset); + ref->offset, probeid);if (err) {pr_err ("prologue: failed to generate probe_read function call\n" ); goto errout;
Signature · 1 line
2.17.1
Arnaldo Carvalho de Melo
maintainerRe: [PATCH v2 2/2] perf: Fix bpf prologue generation
Em Tue, Jun 09, 2020 at 10:10:19AM +0200, Sumanth Korikkar escreveu:
Quoted 35 lines
Issue:
bpf_probe_readis no longer available for architecture which has overlapping address space. Hence bpf prologue generation failsFix:
Usebpf_probe_read_kernelfor kernel member access. For user attribute access in kprobes, usebpf_probe_read_user.Other:
@user attribute was introduced in commit1e032f7cfa14("perf-probe:
Add user memory access attribute support")Test:
1. ulimit -l 128 ; ./perf record -etests/bpf_sched_setscheduler.c
2. cattests/bpf_sched_setscheduler.cstatic void (*bpf_trace_printk)(const char *fmt, int
fmt_size, ...) =(void *) 6; static int (*bpf_probe_read_user)(void *dst, __u32 size, const void *unsafe_ptr) = (void *) 112; static int (*bpf_probe_read_kernel)(void *dst, __u32 size, const void *unsafe_ptr) = (void *) 113;
SEC("func=do_sched_setscheduler pid policy param->sched_priority@user")int bpf_func__setscheduler(void *ctx, int err,pid_tpid, int policy,
int param){ char fmt[] = "prio: %ld"; bpf_trace_printk(fmt, sizeof(fmt), param); return 1; }char _license[]
SEC("license")= "GPL";
int_versionSEC("version")=LINUX_VERSION_CODE;
Quoted 6 lines
3. ./perf script
sched 305669 [000] 1614458.838675: perf_bpf_probe:func: (2904e508) pid=261614 policy=2 sched_priority=14. cat
/sys/kernel/debug/tracing/trace<...>-309956 [006] .... 1616098.093957: 0: prio: 1
Thanks for providing a detailed set of steps to test your patch, that is great!
I added this, an alterenative way to test it, combining all the aspects in one 'perf trace' call:
Committer testing:
I had to add some missing headers in the bpf_sched_setscheduler.c test proggie, then instead of using record+script I used 'perf trace' to drive everything in one go:
# cat bpf_sched_setscheduler.c #include <linux/types.h> #include <bpf.h>
static void (*bpf_trace_printk)(const char *fmt, int fmt_size, ...) = (void *) 6;
static int (*bpf_probe_read_user)(void *dst, __u32 size, const void *unsafe_ptr) = (void *) 112;
static int (*bpf_probe_read_kernel)(void *dst, __u32 size, const void *unsafe_ptr) = (void *) 113;
SEC("func=do_sched_setscheduler pid policy param->sched_priority@user")
int bpf_func__setscheduler(void *ctx, int err, pid_t pid, int policy, int param)
{
char fmt[] = "prio: %ld";
bpf_trace_printk(fmt, sizeof(fmt), param);
return 1;
}
char _license[] SEC("license") = "GPL";
int _version SEC("version") = LINUX_VERSION_CODE;
#
#
# perf trace -e bpf_sched_setscheduler.c chrt -f 42 sleep 1
0.000 chrt/80125 perf_bpf_probe:func(__probe_ip: -1676607808, policy: 1, sched_priority: 42)
#And even with backtraces :-)
# perf trace -e bpf_sched_setscheduler.c/max-stack=8/ chrt -f 42 sleep 1
0.000 chrt/79805 perf_bpf_probe:func(__probe_ip: -1676607808, policy: 1, sched_priority: 42)
do_sched_setscheduler ([kernel.kallsyms])
__x64_sys_sched_setscheduler ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
entry_SYSCALL_64 ([kernel.kallsyms])
__GI___sched_setscheduler (/usr/lib64/libc-2.30.so)
# - Arnaldo