From: Mark Rutland <mark.rutland@arm.com>
To: Julien Thierry <julien.thierry@arm.com>
Cc: peterz@infradead.org, liwei391@huawei.com, will.deacon@arm.com,
acme@kernel.org, alexander.shishkin@linux.intel.com,
mingo@redhat.com, Catalin Marinas <catalin.marinas@arm.com>,
namhyung@kernel.org, jolsa@redhat.com,
linux-arm-kernel@lists.infradead.org
Subject: Re: [PATCH v3 1/9] arm64: perf: avoid PMXEV* indirection
Date: Mon, 8 Jul 2019 16:03:31 +0100 [thread overview]
Message-ID: <20190708150330.GD33099@lakrids.cambridge.arm.com> (raw)
In-Reply-To: <1562596377-33196-2-git-send-email-julien.thierry@arm.com>
On Mon, Jul 08, 2019 at 03:32:49PM +0100, Julien Thierry wrote:
> From: Mark Rutland <mark.rutland@arm.com>
>
> Currently we access the counter registers and their respective type
> registers indirectly. This requires us to write to PMSELR, issue an ISB,
> then access the relevant PMXEV* registers.
>
> This is unfortunate, because:
>
> * Under virtualization, accessing one registers requires two traps to
> the hypervisor, even though we could access the register directly with
> a single trap.
>
> * We have to issue an ISB which we could otherwise avoid the cost of.
>
> * When we use NMIs, the NMI handler will have to save/restore the select
> register in case the code it preempted was attempting to access a
> counter or its type register.
>
> We can avoid these issues by directly accessing the relevant registers.
> This patch adds helpers to do so.
>
> Signed-off-by: Mark Rutland <mark.rutland@arm.com>
> [Julien T.: Don't inline read/write functions to avoid big code-size
> increase, remove unused read_pmevtypern function,
> fix counter index issue.]
> Signed-off-by: Julien Thierry <julien.thierry@arm.com>
> Cc: Will Deacon <will.deacon@arm.com>
> Cc: Peter Zijlstra <peterz@infradead.org>
> Cc: Ingo Molnar <mingo@redhat.com>
> Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
> Cc: Jiri Olsa <jolsa@redhat.com>
> Cc: Namhyung Kim <namhyung@kernel.org>
> Cc: Catalin Marinas <catalin.marinas@arm.com>
> ---
> arch/arm64/kernel/perf_event.c | 96 ++++++++++++++++++++++++++++++++++++------
> 1 file changed, 83 insertions(+), 13 deletions(-)
>
> diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
> index 96e90e2..7759f8a 100644
> --- a/arch/arm64/kernel/perf_event.c
> +++ b/arch/arm64/kernel/perf_event.c
> @@ -369,6 +369,77 @@ static inline bool armv8pmu_event_is_chained(struct perf_event *event)
> #define ARMV8_IDX_TO_COUNTER(x) \
> (((x) - ARMV8_IDX_COUNTER0) & ARMV8_PMU_COUNTER_MASK)
>
> +/*
> + * This code is really good
> + */
> +
> +#define PMEVN_CASE(n, case_macro) \
> + case n: case_macro(n); break
> +
> +#define PMEVN_SWITCH(x, case_macro) \
> + do { \
> + switch (x) { \
> + PMEVN_CASE(0, case_macro); \
> + PMEVN_CASE(1, case_macro); \
> + PMEVN_CASE(2, case_macro); \
> + PMEVN_CASE(3, case_macro); \
> + PMEVN_CASE(4, case_macro); \
> + PMEVN_CASE(5, case_macro); \
> + PMEVN_CASE(6, case_macro); \
> + PMEVN_CASE(7, case_macro); \
> + PMEVN_CASE(8, case_macro); \
> + PMEVN_CASE(9, case_macro); \
> + PMEVN_CASE(10, case_macro); \
> + PMEVN_CASE(11, case_macro); \
> + PMEVN_CASE(12, case_macro); \
> + PMEVN_CASE(13, case_macro); \
> + PMEVN_CASE(14, case_macro); \
> + PMEVN_CASE(15, case_macro); \
> + PMEVN_CASE(16, case_macro); \
> + PMEVN_CASE(17, case_macro); \
> + PMEVN_CASE(18, case_macro); \
> + PMEVN_CASE(19, case_macro); \
> + PMEVN_CASE(21, case_macro); \
> + PMEVN_CASE(22, case_macro); \
> + PMEVN_CASE(23, case_macro); \
> + PMEVN_CASE(24, case_macro); \
> + PMEVN_CASE(25, case_macro); \
> + PMEVN_CASE(26, case_macro); \
> + PMEVN_CASE(27, case_macro); \
> + PMEVN_CASE(28, case_macro); \
> + PMEVN_CASE(29, case_macro); \
> + PMEVN_CASE(30, case_macro); \
> + default: WARN(1, "Inavlid PMEV* index"); \
Nit: s/inavlid/invalid/
> + } \
> + } while (0)
> +
> +#define RETURN_READ_PMEVCNTRN(n) \
> + return read_sysreg(pmevcntr##n##_el0);
> +static unsigned long read_pmevcntrn(int n)
> +{
> + PMEVN_SWITCH(n, RETURN_READ_PMEVCNTRN);
> + return 0;
> +}
> +#undef RETURN_READ_PMEVCNTRN
> +
> +#define WRITE_PMEVCNTRN(n) \
> + write_sysreg(val, pmevcntr##n##_el0);
> +static void write_pmevcntrn(int n, unsigned long val)
> +{
> + PMEVN_SWITCH(n, WRITE_PMEVCNTRN);
> +}
> +#undef WRITE_PMEVCNTRN
> +
> +#define WRITE_PMEVTYPERN(n) \
> + write_sysreg(val, pmevtyper##n##_el0);
> +static void write_pmevtypern(int n, unsigned long val)
> +{
> + PMEVN_SWITCH(n, WRITE_PMEVTYPERN);
> +}
> +#undef WRITE_PMEVTYPERN
> +
> +#undef PMEVN_SWITCH
I think we can drop the undefs. These are local to this C file, and the
names are sufficiently unique to avoid collision. Note that we missed
the undef for PMEVN_CASE, and I imagine keeping that sane will be messy
in future.
Other than that, I haven't come up with a nicer way of writing the
above, so that looks good to me.
> +
> static inline u32 armv8pmu_pmcr_read(void)
> {
> return read_sysreg(pmcr_el0);
> @@ -397,17 +468,11 @@ static inline int armv8pmu_counter_has_overflowed(u32 pmnc, int idx)
> return pmnc & BIT(ARMV8_IDX_TO_COUNTER(idx));
> }
>
> -static inline void armv8pmu_select_counter(int idx)
> +static inline u32 armv8pmu_read_evcntr(int idx)
> {
> u32 counter = ARMV8_IDX_TO_COUNTER(idx);
> - write_sysreg(counter, pmselr_el0);
> - isb();
> -}
>
> -static inline u32 armv8pmu_read_evcntr(int idx)
> -{
> - armv8pmu_select_counter(idx);
> - return read_sysreg(pmxevcntr_el0);
> + return read_pmevcntrn(counter);
> }
>
> static inline u64 armv8pmu_read_hw_counter(struct perf_event *event)
> @@ -441,8 +506,9 @@ static u64 armv8pmu_read_counter(struct perf_event *event)
>
> static inline void armv8pmu_write_evcntr(int idx, u32 value)
> {
> - armv8pmu_select_counter(idx);
> - write_sysreg(value, pmxevcntr_el0);
> + u32 counter = ARMV8_IDX_TO_COUNTER(idx);
> +
> + write_pmevcntrn(counter, value);
> }
>
> static inline void armv8pmu_write_hw_counter(struct perf_event *event,
> @@ -483,9 +549,10 @@ static void armv8pmu_write_counter(struct perf_event *event, u64 value)
>
> static inline void armv8pmu_write_evtype(int idx, u32 val)
> {
> - armv8pmu_select_counter(idx);
> + u32 counter = ARMV8_IDX_TO_COUNTER(idx);
> +
> val &= ARMV8_PMU_EVTYPE_MASK;
> - write_sysreg(val, pmxevtyper_el0);
> + write_pmevtypern(counter, val);
> }
>
> static inline void armv8pmu_write_event_type(struct perf_event *event)
> @@ -505,7 +572,10 @@ static inline void armv8pmu_write_event_type(struct perf_event *event)
> armv8pmu_write_evtype(idx - 1, hwc->config_base);
> armv8pmu_write_evtype(idx, chain_evt);
> } else {
> - armv8pmu_write_evtype(idx, hwc->config_base);
> + if (idx == ARMV8_IDX_CYCLE_COUNTER)
> + write_sysreg(hwc->config_base, pmccfiltr_el0);
> + else
> + armv8pmu_write_evtype(idx, hwc->config_base);
> }
> }
... and this all looks sound.
With the typo fixed and undefs dropped:
Acked-by: Mark Rutland <mark.rutland@arm.com>
Thanks,
Mark.
>
> --
> 1.9.1
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
next prev parent reply other threads:[~2019-07-08 15:03 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-07-08 14:32 [PATCH v3 0/9] arm_pmu: Use NMI for perf interrupt Julien Thierry
2019-07-08 14:32 ` [PATCH v3 1/9] arm64: perf: avoid PMXEV* indirection Julien Thierry
2019-07-08 15:03 ` Mark Rutland [this message]
2019-07-10 10:57 ` Steven Price
2019-07-10 11:01 ` Julien Thierry
2019-07-16 10:33 ` Shijith Thotton
2019-07-16 10:54 ` Julien Thierry
2019-07-17 4:45 ` Shijith Thotton
2019-07-08 14:32 ` [PATCH v3 2/9] arm64: perf: Remove PMU locking Julien Thierry
2019-07-08 15:03 ` Mark Rutland
2019-07-08 15:34 ` Julien Thierry
2019-07-09 11:22 ` Mark Rutland
2019-07-08 14:32 ` [PATCH v3 3/9] arm: perf: save/resore pmsel Julien Thierry
2019-07-08 15:06 ` Mark Rutland
2019-07-08 15:40 ` Julien Thierry
2019-07-08 14:32 ` [PATCH v3 4/9] arm: perf: Remove Remove PMU locking Julien Thierry
2019-07-08 15:10 ` Mark Rutland
2019-07-08 14:32 ` [PATCH v3 5/9] perf/arm_pmu: Move PMU lock to ARMv6 events Julien Thierry
2019-07-08 15:19 ` Mark Rutland
2019-07-08 15:50 ` Julien Thierry
2019-07-08 14:32 ` [PATCH v3 6/9] arm64: perf: Do not call irq_work_run in NMI context Julien Thierry
2019-07-08 15:29 ` Mark Rutland
2019-07-08 16:00 ` Julien Thierry
2019-07-08 14:32 ` [PATCH v3 7/9] arm/arm64: kvm: pmu: Make overflow handler NMI safe Julien Thierry
2019-07-08 15:30 ` Mark Rutland
2019-07-11 12:38 ` Zenghui Yu
2019-07-08 14:32 ` [PATCH v3 8/9] arm_pmu: Introduce pmu_irq_ops Julien Thierry
2019-07-08 14:32 ` [PATCH v3 9/9] arm_pmu: Use NMIs for PMU Julien Thierry
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=20190708150330.GD33099@lakrids.cambridge.arm.com \
--to=mark.rutland@arm.com \
--cc=acme@kernel.org \
--cc=alexander.shishkin@linux.intel.com \
--cc=catalin.marinas@arm.com \
--cc=jolsa@redhat.com \
--cc=julien.thierry@arm.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=liwei391@huawei.com \
--cc=mingo@redhat.com \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
--cc=will.deacon@arm.com \
/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).