> On Oct 17, 2017, at 4:29 PM, Joe Perches <j...@perches.com> wrote:
>
> So the line length check can be bypassed by its callers.
>
> Reported-by: Song Liu <songliubrav...@fb.com>
> Signed-off-by: Joe Perches <j...@perches.com>
> ---
> scripts/checkpa
> On Nov 23, 2017, at 2:22 AM, Peter Zijlstra <pet...@infradead.org> wrote:
>
> On Wed, Nov 15, 2017 at 09:23:33AM -0800, Song Liu wrote:
>> A new perf type PERF_TYPE_PROBE is added to allow creating [k,u]probe
>> with perf_event_open. These [k,u]probe are associated
Function load_and_attach() is updated to be able to create kprobes
with either old text based API, or the new PERF_TYPE_KPROBE API.
A global flag use_perf_type_probe is added to select between the
two APIs.
Signed-off-by: Song Liu <songliubrav...@fb.com>
Reviewed-by: Josef Bacik <jba.
: add type PERF_TYPE_KPROBE and PERF_TYPE_UPROBE
bcc patch:
bcc: Try use new API to create [k,u]probe with perf_event_open
kernel patches:
Song Liu (6):
perf: Add new types PERF_TYPE_KPROBE and PERF_TYPE_UPROBE
perf: copy new perf_event.h to tools/include/uapi
perf: implement support of PERF_TYPE_KPR
() and
destroy_local_trace_kprobe() are added to created and destroy these
local trace_kprobe.
Signed-off-by: Song Liu <songliubrav...@fb.com>
Reviewed-by: Yonghong Song <y...@fb.com>
Reviewed-by: Josef Bacik <jba...@fb.com>
---
include/linux/trace_events.h| 2 +
kernel/events/core
c: Try use new API to create [k,u]probe with perf_event_open
kernel patches:
Song Liu (6):
perf: prepare perf_event.h for new types perf_kprobe and perf_uprobe
perf: copy new perf_event.h to tools/include/uapi
perf: implement pmu perf_kprobe
perf: implement pmu perf_uprobe
bpf:
perf_event.h is updated in previous patch, this patch applies same
changes to the tools/ version. This is part is put in a separate
patch in case the two files are back ported separately.
Signed-off-by: Song Liu <songliubrav...@fb.com>
Reviewed-by: Yonghong Song <y...@fb.com>
Review
This patch adds perf_uprobe support with similar pattern as previous
patch (for kprobe).
Two functions, create_local_trace_uprobe() and
destroy_local_trace_uprobe(), are created so a uprobe can be created
and attached to the file descriptor created by perf_event_open().
Signed-off-by: Song Liu
New kernel API allows creating [k,u]probe with perf_event_open.
This patch tries to use the new API. If the new API doesn't work,
we fall back to old API.
bpf_detach_probe() looks up the event being removed. If the event
is not found, we skip the clean up procedure.
Signed-off-by: Song Liu
Two new types kprobe and uprobe are being added to perf_event_open,
which allow creating kprobe or uprobe with perf_event_open. This
patch adds information about these types.
Signed-off-by: Song Liu <songliubrav...@fb.com>
---
man2/perf_event_open.
to union config1 for pointers to
function name for kprobe or binary path for uprobe.
kprobe_addr and probe_offset are added to union config2 for kernel
address (when kprobe_func is NULL), or [k,u]probe offset.
Signed-off-by: Song Liu <songliubrav...@fb.com>
Reviewed-by: Yonghong Song <y.
5.077558 seconds
Cleaning 1000 kprobes with perf_kprobe (function name) takes 81.241354 seconds
Creating 1000 kprobes with perf_kprobe (function addr) takes 5.218255 seconds
Cleaning 1000 kprobes with perf_kprobe (function addr) takes 80.010731 seconds
Signed-off-by: Song Liu <songliubrav...@fb.
Function load_and_attach() is updated to be able to create kprobes
with either old text based API, or the new perf_event_open API.
A global flag use_perf_kprobe is added to select between the two
APIs.
Signed-off-by: Song Liu <songliubrav...@fb.com>
Reviewed-by: Josef Bacik <jba.
are added to union config1 for pointers
to function name for kprobe or binary path for uprobe.
kprobe_addr and probe_offset are added to union config2 for kernel
address (when kprobe_func is NULL), or [k,u]probe offset.
Signed-off-by: Song Liu <songliubrav...@fb.com>
Reviewed-by: Yonghong S
New kernel API allows creating [k,u]probe with perf_event_open.
This patch tries to use the new API. If the new API doesn't work,
we fall back to old API.
bpf_detach_probe() looks up the event being removed. If the event
is not found, we skip the clean up procedure.
Signed-off-by: Song Liu
perf_event.h is updated in previous patch, this patch applies same
changes to the tools/ version. This is part is put in a separate
patch in case the two files are back ported separately.
Signed-off-by: Song Liu <songliubrav...@fb.com>
Reviewed-by: Yonghong Song <y...@fb.com>
Review
, create_local_trace_kprobe() and
destroy_local_trace_kprobe() are added to created and destroy these
local trace_kprobe.
Signed-off-by: Song Liu <songliubrav...@fb.com>
Reviewed-by: Yonghong Song <y...@fb.com>
Reviewed-by: Josef Bacik <jba...@fb.com>
---
include/linux/trace_events.h|
This patch adds perf_uprobe support with similar pattern as previous
patch (for kprobe).
Two functions, create_local_trace_uprobe() and
destroy_local_trace_uprobe(), are created so a uprobe can be created
and attached to the file descriptor created by perf_event_open().
Signed-off-by: Song Liu
) takes 5.077558
seconds
Cleaning 1000 kprobes with PERF_TYPE_KPROBE (function name) takes 81.241354
seconds
Creating 1000 kprobes with PERF_TYPE_KPROBE (function addr) takes 5.218255
seconds
Cleaning 1000 kprobes with PERF_TYPE_KPROBE (function addr) takes 80.010731
seconds
Signed-off-by: Song
Two new types PERF_TYPE_KPROBE and PERF_TYPE_UPROBE are being added
to perf_event_attr. This patch adds information about this type.
Signed-off-by: Song Liu <songliubrav...@fb.com>
---
man2/perf_event_open.2 | 42 ++
1 file changed, 42 insertions(+)
> On Dec 3, 2017, at 9:03 AM, Alexei Starovoitov <alexei.starovoi...@gmail.com>
> wrote:
>
> On Thu, Nov 30, 2017 at 03:50:18PM -0800, Song Liu wrote:
>> Two new perf types, perf_kprobe and perf_uprobe, will be added to allow
>> creating [k,u]probe with per
+{
> + trace_tcp_set_state(sk, sk->sk_state, newstate);
> + sk_state_store(sk, newstate);
> +}
> +
> +void __tcp_set_state(struct sock *sk, int state)
> +{
> + trace_tcp_set_state(sk, sk->sk_state, state);
> + sk->sk_state = state;
> +}
> +
> void tcp_set_state(struct sock *sk, int state)
> {
> int oldstate = sk->sk_state;
> --
> 1.8.3.1
>
Asked-by: Song Liu <songliubrav...@fb.com>
Function load_and_attach() is updated to be able to create kprobes
with either old text based API, or the new perf_event_open API.
A global flag use_perf_kprobe is added to select between the two
APIs.
Signed-off-by: Song Liu <songliubrav...@fb.com>
Reviewed-by: Josef Bacik <jba.
perf_event.h is updated in previous patch, this patch applies same
changes to the tools/ version. This is part is put in a separate
patch in case the two files are back ported separately.
Signed-off-by: Song Liu <songliubrav...@fb.com>
Reviewed-by: Yonghong Song <y...@fb.com>
Review
New kernel API allows creating [k,u]probe with perf_event_open.
This patch tries to use the new API. If the new API doesn't work,
we fall back to old API.
bpf_detach_probe() looks up the event being removed. If the event
is not found, we skip the clean up procedure.
Signed-off-by: Song Liu
This patch adds perf_uprobe support with similar pattern as previous
patch (for kprobe).
Two functions, create_local_trace_uprobe() and
destroy_local_trace_uprobe(), are created so a uprobe can be created
and attached to the file descriptor created by perf_event_open().
Signed-off-by: Song Liu
Two new types kprobe and uprobe are being added to perf_event_open,
which allow creating kprobe or uprobe with perf_event_open. This
patch adds information about these types.
Signed-off-by: Song Liu <songliubrav...@fb.com>
---
man2/perf_event_open.
to union config1 for pointers to
function name for kprobe or binary path for uprobe.
kprobe_addr and probe_offset are added to union config2 for kernel
address (when kprobe_func is NULL), or [k,u]probe offset.
Signed-off-by: Song Liu <songliubrav...@fb.com>
Reviewed-by: Yonghong Song <y.
() and
destroy_local_trace_kprobe() are added to created and destroy these
local trace_kprobe.
Signed-off-by: Song Liu <songliubrav...@fb.com>
Reviewed-by: Yonghong Song <y...@fb.com>
Reviewed-by: Josef Bacik <jba...@fb.com>
---
include/linux/trace_events.h| 4 ++
kernel/events/core
5.077558 seconds
Cleaning 1000 kprobes with perf_kprobe (function name) takes 81.241354 seconds
Creating 1000 kprobes with perf_kprobe (function addr) takes 5.218255 seconds
Cleaning 1000 kprobes with perf_kprobe (function addr) takes 80.010731 seconds
Signed-off-by: Song Liu <songliubrav...@fb.
probe
bcc patch:
bcc: Try use new API to create [k,u]probe with perf_event_open
kernel patches:
Song Liu (6):
perf: prepare perf_event.h for new types perf_kprobe and perf_uprobe
perf: copy new perf_event.h to tools/include/uapi
perf: implement pmu perf_kprobe
perf: implement pmu perf_up
> On Dec 10, 2017, at 7:31 AM, Yafang Shao wrote:
>
> As sk_state is a common field for struct sock, so the state
> transition should not be a TCP specific feature.
> So I rename tcp_set_state tracepoint to sock_set_state tracepoint with
> some minor changes and move it
> On Dec 8, 2017, at 11:57 AM, Daniel Borkmann <dan...@iogearbox.net> wrote:
>
> On 12/06/2017 11:45 PM, Song Liu wrote:
>> Changes PATCH v4 to PATCH v5:
>> Remove PERF_PROBE_CONFIG_IS_RETPROBE from uapi, use PMU_FORMAT_ATTR
>> instead.
>>
>>
> On Dec 15, 2017, at 9:56 AM, Yafang Shao wrote:
>
> As sk_state is a common field for struct sock, so the state
> transition should not be a TCP specific feature.
> So I rename tcp_set_state tracepoint to sock_set_state tracepoint with
> some minor changes and move it
> On Nov 10, 2017, at 7:07 AM, Steven Rostedt wrote:
>
> On Fri, 10 Nov 2017 12:56:06 +0800
> Yafang Shao wrote:
>
>> Could the macro tcp_state_name() be renamed ?
>> If is included in include/net/tcp.h, it will
>
> Ideally, you don't want to
> On Nov 18, 2017, at 7:32 AM, Yafang Shao wrote:
>
> The TCP/IP transition from TCP_LISTEN to TCP_SYN_RECV and some other
> transitions are not traced with tcp_set_state tracepoint.
>
> In order to trace the whole tcp lifespans, two helpers are introduced,
> void
> On Nov 12, 2017, at 3:40 PM, Song Liu <songliubrav...@fb.com> wrote:
>
> Changes v1 to v2:
> Fix build issue reported by kbuild test bot by adding ifdef of
> CONFIG_KPROBE_EVENTS, and CONFIG_UPROBE_EVENTS.
>
> v1 cover letter:
>
> This is to follow up th
) takes 5.077558
seconds
Cleaning 1000 kprobes with PERF_TYPE_PROBE (function name) takes 81.241354
seconds
Creating 1000 kprobes with PERF_TYPE_PROBE (function addr) takes 5.218255
seconds
Cleaning 1000 kprobes with PERF_TYPE_PROBE (function addr) takes 80.010731
seconds
Signed-off-by: Song Liu
with the pointer, we will (in the following patches) copy probe_desc to
__aligned_u64 before using it as pointer.
Signed-off-by: Song Liu <songliubrav...@fb.com>
Reviewed-by: Yonghong Song <y...@fb.com>
Reviewed-by: Josef Bacik <jba...@fb.com>
Acked-by: Alexei Starovoitov <a...@kernel.o
are not included
in this patch.
write_backward : 1
namespaces : 1
Signed-off-by: Song Liu <songliubrav...@fb.com>
---
man2/perf_event_open.2 | 82 --
1 file changed, 80 insertions(+), 2 deletions(-)
diff --git
-by: Song Liu <songliubrav...@fb.com>
Reviewed-by: Yonghong Song <y...@fb.com>
Reviewed-by: Josef Bacik <jba...@fb.com>
---
kernel/trace/trace_event_perf.c | 48 +-
kernel/trace/trace_probe.h | 4 ++
kernel/trace/trace
Function load_and_attach() is updated to be able to create kprobes
with either old text based API, or the new PERF_TYPE_PROBE API.
A global flag use_perf_type_probe is added to select between the
two APIs.
Signed-off-by: Song Liu <songliubrav...@fb.com>
Reviewed-by: Josef Bacik <jba.
6/bcc/tree/perf_event_opn
Thanks,
Song
man-pages patch:
perf_event_open.2: add new type PERF_TYPE_PROBE
bcc patch:
bcc: Try use new API to create [k,u]probe with perf_event_open
kernel patches:
Song Liu (6):
perf: Add new type PERF_TYPE_PROBE
perf: copy new perf_event.h to tools/include/u
perf_event.h is updated in previous patch, this patch applies same
changes to the tools/ version. This is part is put in a separate
patch in case the two files are back ported separately.
Signed-off-by: Song Liu <songliubrav...@fb.com>
Reviewed-by: Yonghong Song <y...@fb.com>
Review
, create_local_trace_kprobe() and
destroy_local_trace_kprobe() are added to created and destroy these
local trace_kprobe.
Signed-off-by: Song Liu <songliubrav...@fb.com>
Reviewed-by: Yonghong Song <y...@fb.com>
Reviewed-by: Josef Bacik <jba...@fb.com>
---
include/linux/trace_events.h|
New kernel API allows creating [k,u]probe with perf_event_open.
This patch tries to use the new API. If the new API doesn't work,
we fall back to old API.
bpf_detach_probe() looks up the event being removed. If the event
is not found, we skip the clean up procedure.
Signed-off-by: Song Liu
pr_fmt in trace_uprobe.c should say "trace_uprobe" instead of
"trace_kprobe".
Cc: Masami Hiramatsu <mhira...@kernel.org>
Cc: Steven Rostedt <rost...@goodmis.org>
Signed-off-by: Song Liu <songliubrav...@fb.com>
---
kernel/trace/trace_uprobe.c | 2 +-
1 fi
> On Nov 9, 2017, at 10:18 AM, Steven Rostedt wrote:
>
> On Thu, 9 Nov 2017 15:43:29 +0900
> Alexei Starovoitov wrote:
>
>>> +TRACE_EVENT(tcp_set_state,
>>> + TP_PROTO(struct sock *sk, int oldstate, int newstate),
>>> + TP_ARGS(sk,
> On Nov 9, 2017, at 10:34 AM, Song Liu <songliubrav...@fb.com> wrote:
>
>>
>> On Nov 9, 2017, at 10:18 AM, Steven Rostedt <rost...@goodmis.org> wrote:
>>
>> On Thu, 9 Nov 2017 15:43:29 +0900
>> Alexei Starovoitov <alexei.starovoi...@gm
ate_name(TCP_SYN_RECV), \
> - tcp_state_name(TCP_FIN_WAIT1), \
> - tcp_state_name(TCP_FIN_WAIT2), \
> - tcp_state_name(TCP_TIME_WAIT), \
> - tcp_state_name(TCP_CLOSE), \
> - tcp_state_name(TCP_CLOSE_WAIT), \
> - tcp_state_name(TCP_LAST_ACK), \
> - tcp_state_name(TCP_LISTEN), \
> - tcp_state_name(TCP_CLOSING),\
> - tcp_state_name(TCP_NEW_SYN_RECV))
> + __print_symbolic(val, tcp_state_names)
>
> /*
> * tcp event with arguments sk and skb
> --
> 2.13.6
>
Reviewed-and-tested-by: Song Liu <songliubrav...@fb.com>
Two new types kprobe and uprobe are being added to perf_event_open,
which allow creating kprobe or uprobe with perf_event_open. This
patch adds information about these types.
Signed-off-by: Song Liu <songliubrav...@fb.com>
---
man2/perf_event_open.
perf_event.h is updated in previous patch, this patch applies same
changes to the tools/ version. This is part is put in a separate
patch in case the two files are back ported separately.
Signed-off-by: Song Liu <songliubrav...@fb.com>
Reviewed-by: Yonghong Song <y...@fb.com>
Review
to union config1 for pointers to
function name for kprobe or binary path for uprobe.
kprobe_addr and probe_offset are added to union config2 for kernel
address (when kprobe_func is NULL), or [k,u]probe offset.
Signed-off-by: Song Liu <songliubrav...@fb.com>
Reviewed-by: Yonghong Song <y.
5.077558 seconds
Cleaning 1000 kprobes with perf_kprobe (function name) takes 81.241354 seconds
Creating 1000 kprobes with perf_kprobe (function addr) takes 5.218255 seconds
Cleaning 1000 kprobes with perf_kprobe (function addr) takes 80.010731 seconds
Signed-off-by: Song Liu <songliubrav...@fb.
() and
destroy_local_trace_kprobe() are added to created and destroy these
local trace_kprobe.
Signed-off-by: Song Liu <songliubrav...@fb.com>
Reviewed-by: Yonghong Song <y...@fb.com>
Reviewed-by: Josef Bacik <jba...@fb.com>
---
include/linux/trace_events.h| 4 ++
kernel/events/core
Function load_and_attach() is updated to be able to create kprobes
with either old text based API, or the new perf_event_open API.
A global flag use_perf_kprobe is added to select between the two
APIs.
Signed-off-by: Song Liu <songliubrav...@fb.com>
Reviewed-by: Josef Bacik <jba.
m/liu-song-6/bcc/tree/perf_event_open
Thanks,
Song
man-pages patch:
perf_event_open.2: add type kprobe and uprobe
bcc patch:
bcc: Try use new API to create [k,u]probe with perf_event_open
kernel patches:
Song Liu (6):
perf: prepare perf_event.h for new types perf_kprobe and perf_uprobe
This patch adds perf_uprobe support with similar pattern as previous
patch (for kprobe).
Two functions, create_local_trace_uprobe() and
destroy_local_trace_uprobe(), are created so a uprobe can be created
and attached to the file descriptor created by perf_event_open().
Signed-off-by: Song Liu
New kernel API allows creating [k,u]probe with perf_event_open.
This patch tries to use the new API. If the new API doesn't work,
we fall back to old API.
bpf_detach_probe() looks up the event being removed. If the event
is not found, we skip the clean up procedure.
Signed-off-by: Song Liu
> On Dec 20, 2017, at 2:14 AM, Peter Zijlstra <pet...@infradead.org> wrote:
>
> On Wed, Dec 20, 2017 at 11:03:01AM +0100, Peter Zijlstra wrote:
>> On Wed, Dec 06, 2017 at 02:45:15PM -0800, Song Liu wrote:
>>> @@ -8537,7 +8620,7 @@ static int perf_event_set_filter
This patch tries to enable PMU sharing. To make perf event scheduling
fast, we use special data structures.
An array of "struct perf_event_dup" is added to the cpuctx, to remember
all the duplicated events under this cpuctx. All the events under this
cpuctx has a "dup_id" pointing to its
direction
of PMU counter sharing?
Thanks in advance.
Song
Song Liu (2):
perf: add move_dup() for PMU sharing.
perf: Sharing PMU counters across compatible events
arch/x86/events/core.c | 8 ++
include/linux/perf_event.h | 57 +
include/linux/trace_events.h| 3
To share PMU across different counters, we need a "master event" that
handles interaction with hardware or other software parts. It is
necessary to switch master event to another event. To make this move
compatible with the PMU, it is necessary to move connection or data
from one perf_event to
On Thu, May 17, 2018 at 10:31 AM, William Kucharski
wrote:
>
>
>> On May 17, 2018, at 9:23 AM, Matthew Wilcox wrote:
>>
>> I'm certain it is. The other thing I believe is true that we should be
>> able to share page tables (my motivation is
l not call khugepaged_enter().
This patch fixes these problems by reusing hugepage_vma_check() in
khugepaged_enter_vma_merge().
Signed-off-by: Song Liu <songliubrav...@fb.com>
---
mm/khugepaged.c | 12
1 file changed, 4 insertions(+), 8 deletions(-)
diff --git a/mm/khugepaged.c b
ge().
vma->vm_flags is not yet updated in khugepaged_enter_vma_merge(),
so we need to pass the new vm_flags to hugepage_vma_check() through
a separate argument.
Signed-off-by: Song Liu <songliubrav...@fb.com>
---
mm/khugepaged.c | 26 --
1 file changed, 12 inserti
Dear Peter,
Could you please share your comments on this minor fix?
Best,
Song
> On May 3, 2018, at 12:47 PM, Song Liu <songliubrav...@fb.com> wrote:
>
> When hw and sw events are mixed in the same group, they are all attached
> to the hw perf_event_context. This sometim
On May 22, 2018, at 5:13 AM, Michal Hocko <mho...@kernel.org> wrote:
>
> [CC Kirill]
>
> On Mon 21-05-18 12:38:53, Song Liu wrote:
>> khugepaged_enter_vma_merge() is using a different approach to check
>> whether a vma is valid for khugepaged_enter()
> On Apr 18, 2018, at 11:17 PM, Alexander Shishkin
> <alexander.shish...@linux.intel.com> wrote:
>
> On Tue, Apr 17, 2018 at 11:29:07PM -0700, Song Liu wrote:
>> As Miklos reported and suggested:
>>
>> This pattern repeats two times in trace_uprobe.c and
Hi,
We are seeing something probably related.
We run ethtool on a system with Broadcom NIC to increase number of
combined queues.
[root@ ~]# ethtool -l eth0
Channel parameters for eth0:
Pre-set maximums:
RX: 9
TX: 8
Other: 0
Adding Broadcom developers to the thread.
Hi Michael, Vasundhara, and Andy,
Could you please help look into the case I found? ethtool crashes the system
for both net/master and net-next/master.
Thanks,
Song
On Fri, May 25, 2018 at 1:10 PM, Song Liu <liu.song@gmail.com> wrote:
> H
olve_sink(const struct
> btf_verifier_env *env,
> !btf_type_is_array(next_type) &&
> !btf_type_is_struct(next_type);
> default:
> - BUG_ON(1);
> + BUG();
> }
> }
>
> --
> 2.9.0
>
Acked-by: Song Liu <songliubrav...@fb.com>
ILD_ID_VALID;
> }
>
> - if (!in_nmi_ctx) {
> + if (!work) {
> up_read(>mm->mmap_sem);
> } else {
> work->sem = >mm->mmap_sem;
> --
> 2.9.0
>
Acked-by: Song Liu <songliubrav...@fb.com>
> On May 25, 2018, at 3:14 AM, Yafang Shao <laoar.s...@gmail.com> wrote:
>
> skb->len is meaningless to user.
> data length could be more helpful, with which we can easily filter out
> the packet without payload.
>
> Signed-off-by: Yafang Shao <laoar.s.
> On May 24, 2018, at 5:48 AM, Yafang Shao wrote:
>
> skb->len is meaningless to user.
> data length could be more helpful, with which we can easily filter out
> the packet without payload.
>
> Signed-off-by: Yafang Shao
> ---
>
vent_dup.
Cc: Tejun Heo
Cc: Peter Zijlstra
Cc: Jiri Olsa
Cc: Alexey Budankov
Signed-off-by: Song Liu
---
include/linux/perf_event.h | 61 ++
kernel/events/core.c | 284 +++--
2 files changed, 335 insertions(+), 10 deletions(-)
diff -
cleaner.
This version has been stable in my tests.
Cc: Tejun Heo
Cc: Peter Zijlstra
Cc: Jiri Olsa
Cc: Alexey Budankov
Song Liu (1):
perf: Sharing PMU counters across compatible events
include/linux/perf_event.h | 61 ++
kernel/events/core.c | 284
> On May 28, 2018, at 7:27 AM, Thomas Gleixner wrote:
>
> On Mon, 28 May 2018, Tariq Toukan wrote:
>> On 28/05/2018 1:53 PM, Thomas Gleixner wrote:
>>> On Fri, 25 May 2018, Song Liu wrote:
>>>> On Wed, May 23, 2018 at 1:49 AM, Thomas Gleixner
>>
ge().
vma->vm_flags is not yet updated in khugepaged_enter_vma_merge(),
so we need to pass the new vm_flags to hugepage_vma_check() through
a separate argument.
Signed-off-by: Song Liu
---
mm/khugepaged.c | 53 -
1 file changed, 24 inse
> On May 28, 2018, at 4:15 AM, Peter Zijlstra wrote:
>
> On Fri, May 04, 2018 at 04:11:02PM -0700, Song Liu wrote:
>> Connection among perf_event and perf_event_dup are built with function
>> rebuild_event_dup_list(cpuctx). This function is only called when events
>>
> On May 28, 2018, at 3:57 AM, Kirill A. Shutemov wrote:
>
> On Tue, May 22, 2018 at 12:44:30PM -0700, Song Liu wrote:
>> khugepaged_enter_vma_merge() is using a different approach to check
>> whether a vma is valid for khugepaged_enter():
>>
On May 28, 2018, at 4:24 AM, Peter Zijlstra wrote:
>
> On Fri, May 04, 2018 at 04:11:02PM -0700, Song Liu wrote:
>> On the critical paths, perf_events are added to/removed from the
>> active_dup list of the perf_event. The first event added to the list
>> will be the ma
> On May 28, 2018, at 3:53 AM, Thomas Gleixner wrote:
>
> On Fri, 25 May 2018, Song Liu wrote:
>> On Wed, May 23, 2018 at 1:49 AM, Thomas Gleixner wrote:
>>> On Wed, 23 May 2018, Tariq Toukan wrote:
>>>> I have your patch merged into my inte
On Sun, May 27, 2018 at 4:28 AM, Eugene Syromiatnikov wrote:
> Use __aligned_u64 instead of __u64 everywhere in the UAPI header,
> similarly to v4.17-rc1~94^2~58^2 "RDMA: Change all uapi headers to use
> __aligned_u64 instead of __u64".
>
> This commit doesn't change structure layouts, but
.
>
> Reuse the new function in apic_ack_edge().
>
> Preparatory change for the real fix
>
> Fixes: dccfe3147b42 ("x86/vector: Simplify vector move cleanup")
> Signed-off-by: Thomas Gleixner
> Cc: sta...@vger.kernel.org
Tested-by: Song Liu
> ---
> arch/x86/i
Tested-by: Song Liu
On Mon, Jun 4, 2018 at 8:33 AM, Thomas Gleixner wrote:
>
Tested-by: Song Liu
On Mon, Jun 4, 2018 at 8:33 AM, Thomas Gleixner wrote:
>
Tested-by: Song Liu
On Mon, Jun 4, 2018 at 8:33 AM, Thomas Gleixner wrote:
>
cfe3147b42 ("x86/vector: Simplify vector move cleanup")
> Signed-off-by: Thomas Gleixner
> Cc: sta...@vger.kernel.org
Tested-by: Song Liu
> ---
> kernel/irq/manage.c | 37 +++--
> 1 file changed, 35 insertions(+), 2 deletions(-)
>
&g
t;
> Check the return value of irq_do_set_affinity() for -EBUSY, which indicates
> a pending cleanup, and rearm the pending move in the irq dexcriptor so it's
> tried again when the next interrupt arrives.
>
> Fixes: 996c591227d9 ("x86/irq: Plug vector cleanup race")
> Signed-off-by: Thomas
llow up patches.
>
> Fixes: 69cde0004a4b ("x86/vector: Use matrix allocator for vector assignment")
> Reported-by: Dmitry Safonov <0x7f454...@gmail.com>
> Reported-by: Tariq Toukan
> Reported-by: Song Liu
> Signed-off-by: Thomas Gleixner
> Cc: sta...@vger.kernel.org
> On May 29, 2018, at 1:35 AM, Thomas Gleixner wrote:
>
> On Mon, 28 May 2018, Song Liu wrote:
>>> On May 28, 2018, at 1:09 PM, Thomas Gleixner wrote:
>>>
>>> On Mon, 28 May 2018, Song Liu wrote:
>>>> This doesn't fix the issue with bnxt.
> On Jun 2, 2018, at 1:14 PM, Andy Lutomirski wrote:
>
> On Fri, Jun 1, 2018 at 10:04 PM Rik van Riel wrote:
>>
>> On Fri, 2018-06-01 at 20:35 -0700, Andy Lutomirski wrote:
>>> On Fri, Jun 1, 2018 at 3:13 PM Rik van Riel wrote:
On Fri, 1 Jun 2018 14:21:58 -0700
Andy
Dear Peter,
Could you please share you feedbacks/comments on this work?
Thanks,
Song
On Fri, Jun 8, 2018 at 3:47 PM, Song Liu wrote:
> This patch tries to enable PMU sharing. To make perf event scheduling
> fast, we use special data structures.
>
> An array of "struct perf_ev
> On May 1, 2018, at 10:50 PM, Stephen Rothwell <s...@canb.auug.org.au> wrote:
>
> Hi Song,
>
> On Wed, 2 May 2018 04:40:20 + Song Liu <songliubrav...@fb.com> wrote:
>>
>>> - CHECK(build_id_matches < 1, "build id match",
>
> On May 1, 2018, at 7:09 PM, Stephen Rothwell wrote:
>
> Hi all,
>
> Today's linux-next merge of the bpf-next tree got a conflict in:
>
> tools/testing/selftests/bpf/test_progs.c
>
> between commit:
>
> a4e21ff8d9a3 ("bpf: minor fix to selftest
r Zijlstra <pet...@infradead.org>
Signed-off-by: Song Liu <songliubrav...@fb.com>
---
include/linux/perf_event.h | 8
kernel/events/core.c | 21 +++--
2 files changed, 19 insertions(+), 10 deletions(-)
diff --git a/include/linux/perf_event.h b/incl
> On Jan 5, 2018, at 12:09 AM, Yafang Shao <laoar.s...@gmail.com> wrote:
>
> On Fri, Jan 5, 2018 at 3:21 PM, Song Liu <songliubrav...@fb.com> wrote:
>>
>>> On Jan 4, 2018, at 10:42 PM, Yafang Shao <laoar.s...@gmail.com> wrote:
>>>
>>>
do the filter.
>
> Both sk_family and sk_protocol are showed in the printk message, so we need
> not expose them as tracepoint arguments.
>
> Suggested-by: Brendan Gregg <brendan.d.gr...@gmail.com>
> Suggested-by: Song Liu <songliubrav...@fb.com>
> Signed-off-by: Yafang
> On Jan 4, 2018, at 10:42 PM, Yafang Shao wrote:
>
> sk->sk_protocol and sk->sk_family are exposed as tracepoint arguments.
> Then we can conveniently use these two arguments to do the filter.
>
> Suggested-by: Brendan Gregg
> Signed-off-by:
1 - 100 of 1577 matches
Mail list logo