stable.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Sasha Levin <Alexander.Levin@microsoft.com>
To: "stable@vger.kernel.org" <stable@vger.kernel.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Jiri Olsa <jolsa@kernel.org>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Stephane Eranian <eranian@google.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Vince Weaver <vince@deater.net>, Ingo Molnar <mingo@kernel.org>,
	Sasha Levin <Alexander.Levin@microsoft.com>
Subject: [PATCH AUTOSEL for 3.18 003/101] perf/core: Correct event creation with PERF_FORMAT_GROUP
Date: Mon, 9 Apr 2018 00:35:11 +0000	[thread overview]
Message-ID: <20180409003505.164715-3-alexander.levin@microsoft.com> (raw)
In-Reply-To: <20180409003505.164715-1-alexander.levin@microsoft.com>

From: Peter Zijlstra <peterz@infradead.org>

[ Upstream commit ba5213ae6b88fb170c4771fef6553f759c7d8cdd ]

Andi was asking about PERF_FORMAT_GROUP vs inherited events, which led
to the discovery of a bug from commit:

  3dab77fb1bf8 ("perf: Rework/fix the whole read vs group stuff")

 -       PERF_SAMPLE_GROUP                       = 1U << 4,
 +       PERF_SAMPLE_READ                        = 1U << 4,

 -       if (attr->inherit && (attr->sample_type & PERF_SAMPLE_GROUP))
 +       if (attr->inherit && (attr->read_format & PERF_FORMAT_GROUP))

is a clear fail :/

While this changes user visible behaviour; it was previously possible
to create an inherited event with PERF_SAMPLE_READ; this is deemed
acceptible because its results were always incorrect.

Reported-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vince@deater.net>
Fixes:  3dab77fb1bf8 ("perf: Rework/fix the whole read vs group stuff")
Link: http://lkml.kernel.org/r/20170530094512.dy2nljns2uq7qa3j@hirez.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
---
 kernel/events/core.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index de3303aab7d6..9eb7710914fb 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4861,9 +4861,6 @@ static void perf_output_read_one(struct perf_output_handle *handle,
 	__output_copy(handle, values, n * sizeof(u64));
 }
 
-/*
- * XXX PERF_FORMAT_GROUP vs inherited events seems difficult.
- */
 static void perf_output_read_group(struct perf_output_handle *handle,
 			    struct perf_event *event,
 			    u64 enabled, u64 running)
@@ -4908,6 +4905,13 @@ static void perf_output_read_group(struct perf_output_handle *handle,
 #define PERF_FORMAT_TOTAL_TIMES (PERF_FORMAT_TOTAL_TIME_ENABLED|\
 				 PERF_FORMAT_TOTAL_TIME_RUNNING)
 
+/*
+ * XXX PERF_SAMPLE_READ vs inherited events seems difficult.
+ *
+ * The problem is that its both hard and excessively expensive to iterate the
+ * child list, not to mention that its impossible to IPI the children running
+ * on another CPU, from interrupt/NMI context.
+ */
 static void perf_output_read(struct perf_output_handle *handle,
 			     struct perf_event *event)
 {
@@ -7194,9 +7198,10 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	local64_set(&hwc->period_left, hwc->sample_period);
 
 	/*
-	 * we currently do not support PERF_FORMAT_GROUP on inherited events
+	 * We currently do not support PERF_SAMPLE_READ on inherited events.
+	 * See perf_output_read().
 	 */
-	if (attr->inherit && (attr->read_format & PERF_FORMAT_GROUP))
+	if (attr->inherit && (attr->sample_type & PERF_SAMPLE_READ))
 		goto err_ns;
 
 	pmu = perf_init_event(event);
-- 
2.15.1

  parent reply	other threads:[~2018-04-09  0:39 UTC|newest]

Thread overview: 52+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-04-09  0:35 [PATCH AUTOSEL for 3.18 001/101] ALSA: timer: Wrap with spinlock for queue access Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 002/101] e1000e: Undo e1000e_pm_freeze if __e1000_shutdown fails Sasha Levin
2018-04-09  0:35 ` Sasha Levin [this message]
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 004/101] MIPS: mm: fixed mappings: correct initialisation Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 005/101] MIPS: kprobes: flush_insn_slot should flush only if probe initialised Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 006/101] net: emac: fix reset timeout with AR8035 phy Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 007/101] perf tests: Decompress kernel module before objdump Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 008/101] xen: avoid type warning in xchg_xen_ulong Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 009/101] KEYS: put keyring if install_session_keyring_to_cred() fails Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 010/101] bnx2x: Allow vfs to disable txvlan offload Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 011/101] sctp: fix recursive locking warning in sctp_do_peeloff Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 012/101] sparc64: ldc abort during vds iso boot Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 013/101] iio: magnetometer: st_magn_spi: fix spi_device_id table Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 014/101] Bluetooth: Send HCI Set Event Mask Page 2 command only when needed Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 015/101] ACPICA: Events: Add runtime stub support for event APIs Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 016/101] ACPICA: Disassembler: Abort on an invalid/unknown AML opcode Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 017/101] s390/dasd: Display read-only attribute correctly Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 018/101] vxlan: dont migrate permanent fdb entries during learn Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 019/101] scsi: csiostor: Avoid content leaks and casts Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 020/101] scsi: megaraid: Fix a sleep-in-atomic bug Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 021/101] scsi: lpfc: Fix return value of board_mode store routine in case of online failure Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 022/101] usb: usbip tool: Check the return of get_nports() Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 023/101] usb: usbip tool: Fix refresh_imported_device_list() Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 024/101] PCI: Correct PCI_STD_RESOURCE_END usage Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 025/101] PCI: Add domain number check to find_smbios_instance_string() Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 026/101] mtd: handle partitioning on devices with 0 erasesize Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 027/101] platform/x86: acer-wmi: Detect RF Button capability Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 028/101] caif: Add sockaddr length check before accessing sa_family in connect handler Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 029/101] ixgbe: avoid permanent lock of *_PTP_TX_IN_PROGRESS Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 030/101] net_sched: move tcf_lock down after gen_replace_estimator() Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 031/101] PCI: Protect pci_error_handlers->reset_notify() usage with device_lock() Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 032/101] firmware: dmi_scan: Check DMI structure length Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 033/101] i2c: ismt: fix wrong device address when unmap the data buffer Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 034/101] drm/mgag200: Fix to always set HiPri for G200e4 V2 Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 035/101] r8152: add byte_enable for ocp_read_word function Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 036/101] Btrfs: skip commit transaction if we don't have enough pinned bytes Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 037/101] scsi: lpfc: Fix crash after firmware flash when IO is running Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 038/101] mmc: sdhci-esdhc: Add SDHCI_QUIRK_32BIT_DMA_ADDR Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 039/101] x86/nmi: Fix timeout test in test_nmi_ipi() Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 040/101] arm64: pass machine size to sparse Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 041/101] fib_rules: Resolve goto rules target on delete Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 042/101] dccp: call inet_add_protocol after register_pernet_subsys in dccp_v4_init Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 043/101] arm64: ptrace: Fix VFP register dumping in compat coredumps Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 044/101] veth: Be more robust on network device creation when no attributes Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 045/101] macvlan: Do not return error when setting the same mac address Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 046/101] sctp: adjust ssthresh when transport is idle Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 047/101] arm64: pass endianness info to sparse Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 048/101] scsi: bnx2i: missing error code in bnx2i_ep_connect() Sasha Levin
2018-04-09  0:35 ` [PATCH AUTOSEL for 3.18 049/101] powerpc: Fix /proc/cpuinfo revision for POWER9 DD2 Sasha Levin
2018-04-09  0:36 ` [PATCH AUTOSEL for 3.18 050/101] ACPI: EC: Fix EC command visibility for dynamic debug Sasha Levin
2018-04-09  0:36 ` [PATCH AUTOSEL for 3.18 051/101] scsi: sun_esp: fix device reference leaks Sasha Levin
2018-04-09  0:41 ` [PATCH AUTOSEL for 3.18 052/101] powerpc/fadump: avoid duplicates in crash memory ranges Sasha Levin

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20180409003505.164715-3-alexander.levin@microsoft.com \
    --to=alexander.levin@microsoft.com \
    --cc=acme@kernel.org \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=eranian@google.com \
    --cc=jolsa@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=peterz@infradead.org \
    --cc=stable@vger.kernel.org \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.org \
    --cc=vince@deater.net \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).