linux-kernel - Re: [PATCH v2 1/5] perf: arm_cspmu: Support 32-bit accesses to 64-bit registers

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <7269d265-154b-e79a-2622-287e149d85ad@arm.com>
Date:   Thu, 1 Jun 2023 15:49:13 +0100
From:   Robin Murphy <robin.murphy@....com>
To:     Ilkka Koskinen <ilkka@...amperecomputing.com>,
        Jonathan Corbet <corbet@....net>,
        Will Deacon <will@...nel.org>,
        Mark Rutland <mark.rutland@....com>,
        Besar Wicaksono <bwicaksono@...dia.com>,
        Suzuki K Poulose <suzuki.poulose@....com>
Cc:     linux-doc@...r.kernel.org, linux-kernel@...r.kernel.org,
        linux-arm-kernel@...ts.infradead.org
Subject: Re: [PATCH v2 1/5] perf: arm_cspmu: Support 32-bit accesses to 64-bit
 registers

On 2023-06-01 04:01, Ilkka Koskinen wrote:
> Split the 64-bit register accesses if 64-bit access is not supported
> by the PMU.
> 
> Signed-off-by: Ilkka Koskinen <ilkka@...amperecomputing.com>
> ---
>   drivers/perf/arm_cspmu/arm_cspmu.c | 8 ++++++--
>   drivers/perf/arm_cspmu/arm_cspmu.h | 1 +
>   2 files changed, 7 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/perf/arm_cspmu/arm_cspmu.c b/drivers/perf/arm_cspmu/arm_cspmu.c
> index a3f1c410b417..88547a2b73e6 100644
> --- a/drivers/perf/arm_cspmu/arm_cspmu.c
> +++ b/drivers/perf/arm_cspmu/arm_cspmu.c
> @@ -701,8 +701,12 @@ static void arm_cspmu_write_counter(struct perf_event *event, u64 val)
>   
>   	if (use_64b_counter_reg(cspmu)) {
>   		offset = counter_offset(sizeof(u64), event->hw.idx);
> -
> -		writeq(val, cspmu->base1 + offset);
> +		if (!cspmu->impl.split_64bit_access) {

Could we not just hang this off the 64-bit atomicity property to match 
the read path? It doesn't seem like there's much benefit in 
micro-optimising for whether the interconnect splits 64-bit accesses 
into 32-bit bursts vs. just not accepting them at all.

> +			writeq(val, cspmu->base1 + offset);
> +		} else {
> +			writel(lower_32_bits(val), cspmu->base1 + offset);
> +			writel(upper_32_bits(val), cspmu->base1 + offset + 4);

lo_hi_writeq() - the header's already included for 32-bit build 
coverage, so we may as well put it to use :)

Thanks,
Robin.

> +		}
>   	} else {
>   		offset = counter_offset(sizeof(u32), event->hw.idx);
>   
> diff --git a/drivers/perf/arm_cspmu/arm_cspmu.h b/drivers/perf/arm_cspmu/arm_cspmu.h
> index 51323b175a4a..c0412cf2bd97 100644
> --- a/drivers/perf/arm_cspmu/arm_cspmu.h
> +++ b/drivers/perf/arm_cspmu/arm_cspmu.h
> @@ -110,6 +110,7 @@ struct arm_cspmu_impl_ops {
>   /* Vendor/implementer descriptor. */
>   struct arm_cspmu_impl {
>   	u32 pmiidr;
> +	bool split_64bit_access;
>   	struct arm_cspmu_impl_ops ops;
>   	void *ctx;
>   };