linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: kan.liang@linux.intel.com
Cc: acme@kernel.org, tglx@linutronix.de, mingo@redhat.com,
	linux-kernel@vger.kernel.org, eranian@google.com,
	jolsa@redhat.com, namhyung@kernel.org, ak@linux.intel.com,
	luto@amacapital.net, vbabka@suse.cz, will.deacon@arm.com,
	kirill@shutemov.name
Subject: Re: [PATCH V5 02/14] perf/x86: Add perf_get_page_size support
Date: Fri, 8 Feb 2019 21:07:31 +0100	[thread overview]
Message-ID: <20190208200731.GN32511@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <1549648509-12704-2-git-send-email-kan.liang@linux.intel.com>

On Fri, Feb 08, 2019 at 09:54:57AM -0800, kan.liang@linux.intel.com wrote:
> From: Kan Liang <kan.liang@linux.intel.com>
> 
> Implement a x86 specific version of perf_get_page_size(), which do full
> page-table walk of a given virtual address to retrieve page size.
> For x86, disabling IRQs over the walk is sufficient to prevent any tear
> down of the page tables.
> 
> The new sample type requires collecting the virtual address. The virtual
> address will not be output unless SAMPLE_ADDR is applied.
> 
> The large PEBS will be disabled with this sample type. Because we need
> to track munmap to flush the PEBS buffer for large PEBS. Perf doesn't
> support munmap tracking yet. The large PEBS can be enabled later
> separately when munmap tracking is supported.
> 
> Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
> ---
> 
> Changes since V4
> - Split patch 1 of V4 into two patches.
>   This patch add the x86 implementation
> 
>  arch/x86/events/core.c     | 31 +++++++++++++++++++++++++++++++
>  arch/x86/events/intel/ds.c |  3 ++-
>  2 files changed, 33 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
> index 374a197..229a73b 100644
> --- a/arch/x86/events/core.c
> +++ b/arch/x86/events/core.c
> @@ -2578,3 +2578,34 @@ void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap)
>  	cap->events_mask_len	= x86_pmu.events_mask_len;
>  }
>  EXPORT_SYMBOL_GPL(perf_get_x86_pmu_capability);
> +
> +u64 perf_get_page_size(u64 virt)
> +{
> +	unsigned long flags;
> +	unsigned int level;
> +	pte_t *pte;
> +
> +	if (!virt)
> +		return 0;
> +
> +	/*
> +	 * Interrupts are disabled, so it prevents any tear down
> +	 * of the page tables.
> +	 * See the comment near struct mmu_table_batch.
> +	 */
> +	local_irq_save(flags);
> +	if (virt >= TASK_SIZE)
> +		pte = lookup_address(virt, &level);
> +	else {
> +		if (current->mm) {
> +			pte = lookup_address_in_pgd(pgd_offset(current->mm, virt),
> +						    virt, &level);
> +		} else
> +			level = PG_LEVEL_NUM;
> +	}
> +	local_irq_restore(flags);
> +	if (level >= PG_LEVEL_NUM)
> +		return 0;
> +
> +	return (u64)page_level_size(level);
> +}

Full NAK on a pure x86 implementation.

  parent reply	other threads:[~2019-02-08 20:07 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-02-08 17:54 [PATCH V5 01/14] perf/core: Add PERF_SAMPLE_DATA_PAGE_SIZE kan.liang
2019-02-08 17:54 ` [PATCH V5 02/14] perf/x86: Add perf_get_page_size support kan.liang
2019-02-08 18:47   ` Thomas Gleixner
2019-02-08 20:07   ` Peter Zijlstra [this message]
2019-02-08 17:54 ` [PATCH V5 03/14] perf tools: Support new sample type for data page size kan.liang
2019-02-08 17:54 ` [PATCH V5 04/14] perf script: Support " kan.liang
2019-02-08 17:55 ` [PATCH V5 05/14] perf sort: Add sort option for " kan.liang
2019-02-08 17:55 ` [PATCH V5 06/14] perf mem: Factor out a function to generate sort order kan.liang
2019-02-08 17:55 ` [PATCH V5 07/14] perf mem: Clean up output format kan.liang
2019-02-08 17:55 ` [PATCH V5 08/14] perf mem: Support data page size kan.liang
2019-02-08 17:55 ` [PATCH V5 09/14] perf test: Add test case for PERF_SAMPLE_DATA_PAGE_SIZE kan.liang
2019-02-08 17:55 ` [PATCH V5 10/14] perf/core: Add support for PERF_SAMPLE_CODE_PAGE_SIZE kan.liang
2019-02-08 17:55 ` [PATCH V5 11/14] perf tools: " kan.liang
2019-02-08 17:55 ` [PATCH V5 12/14] perf script: " kan.liang
2019-02-08 17:55 ` [PATCH V5 13/14] perf report: " kan.liang
2019-02-08 17:55 ` [PATCH V5 14/14] perf test: Add test case " kan.liang

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=20190208200731.GN32511@hirez.programming.kicks-ass.net \
    --to=peterz@infradead.org \
    --cc=acme@kernel.org \
    --cc=ak@linux.intel.com \
    --cc=eranian@google.com \
    --cc=jolsa@redhat.com \
    --cc=kan.liang@linux.intel.com \
    --cc=kirill@shutemov.name \
    --cc=linux-kernel@vger.kernel.org \
    --cc=luto@amacapital.net \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=tglx@linutronix.de \
    --cc=vbabka@suse.cz \
    --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).