From patchwork Thu Jan 11 15:41:06 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Ryan Roberts X-Patchwork-Id: 13517557 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from bombadil.infradead.org (bombadil.infradead.org [198.137.202.133]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id CFFF3C47422 for ; Thu, 11 Jan 2024 15:41:50 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=lists.infradead.org; s=bombadil.20210309; h=Sender: Content-Transfer-Encoding:Content-Type:List-Subscribe:List-Help:List-Post: List-Archive:List-Unsubscribe:List-Id:MIME-Version:Message-Id:Date:Subject:Cc :To:From:Reply-To:Content-ID:Content-Description:Resent-Date:Resent-From: Resent-Sender:Resent-To:Resent-Cc:Resent-Message-ID:In-Reply-To:References: List-Owner; bh=9xje1i8Bdyqhx1fMxEC0RGck+p9AbJAVgZHRZCAYlN4=; b=3smoezDf96JfWb vskFj/RHEQRKE9WZTjLe3rTwjUivgq/oR/mTLuo/P80Rkf5TFmAvqNyyaJ8bvDimjqHqVhvIv8axU oYb8ByHdgzjg/NrfwFU7OazISsh7eLEerZIuq4XLRm3B3VO3S/U5+1naBlYBKAIpkBCz6QoN42gr5 ubyPk/ZjCETUf5wuRhEB+ykdCRGuvUoEtXniMMbLwKRf5pR7qGA+M9arUwqTLbBMvY57TUhYZ2OxI iJJdzuHcvHNiabzQuyZXhy8woY6gDD2DleuahwU1c4XCF2uVLf8yJiXqZeO/H2IoGxEUAxoi9ux68 5GUzP/Ww1rPJEg2rHIiw==; Received: from localhost ([::1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.96 #2 (Red Hat Linux)) id 1rNxBN-000TeW-1j; Thu, 11 Jan 2024 15:41:25 +0000 Received: from foss.arm.com ([217.140.110.172]) by bombadil.infradead.org with esmtp (Exim 4.96 #2 (Red Hat Linux)) id 1rNxBJ-000Tcy-1d for linux-arm-kernel@lists.infradead.org; Thu, 11 Jan 2024 15:41:23 +0000 Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.121.207.14]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id 1F9BE2F4; Thu, 11 Jan 2024 07:42:03 -0800 (PST) Received: from e125769.cambridge.arm.com (e125769.cambridge.arm.com [10.1.196.26]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPSA id 97C073F5A1; Thu, 11 Jan 2024 07:41:15 -0800 (PST) From: Ryan Roberts To: Catalin Marinas , Will Deacon , Mark Rutland , "Matthew Wilcox (Oracle)" , Andrew Morton , David Hildenbrand , Barry Song <21cnbao@gmail.com>, John Hubbard Cc: Ryan Roberts , linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org, linux-mm@kvack.org Subject: [RFC PATCH v1] mm/filemap: Allow arch to request folio size for exec memory Date: Thu, 11 Jan 2024 15:41:06 +0000 Message-Id: <20240111154106.3692206-1-ryan.roberts@arm.com> X-Mailer: git-send-email 2.25.1 MIME-Version: 1.0 X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20240111_074121_642493_D7F4B2A9 X-CRM114-Status: GOOD ( 31.20 ) X-BeenThere: linux-arm-kernel@lists.infradead.org X-Mailman-Version: 2.1.34 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: "linux-arm-kernel" Errors-To: linux-arm-kernel-bounces+linux-arm-kernel=archiver.kernel.org@lists.infradead.org Change the readahead config so that if it is being requested for an executable mapping, do a synchronous read of an arch-specified size in a naturally aligned manner. On arm64 if memory is physically contiguous and naturally aligned to the "contpte" size, we can use contpte mappings, which improves utilization of the TLB. When paired with the "multi-size THP" changes, this works well to reduce dTLB pressure. However iTLB pressure is still high due to executable mappings having a low liklihood of being in the required folio size and mapping alignment, even when the filesystem supports readahead into large folios (e.g. XFS). The reason for the low liklihood is that the current readahead algorithm starts with an order-2 folio and increases the folio order by 2 every time the readahead mark is hit. But most executable memory is faulted in fairly randomly and so the readahead mark is rarely hit and most executable folios remain order-2. This is observed impirically and confirmed from discussion with a gnu linker expert; in general, the linker does nothing to group temporally accessed text together spacially. Additionally, with the current read-around approach there are no alignment guarrantees between the file and folio. This is insufficient for arm64's contpte mapping requirement (order-4 for 4K base pages). So it seems reasonable to special-case the read(ahead) logic for executable mappings. The trade-off is performance improvement (due to more efficient storage of the translations in iTLB) vs potential read amplification (due to reading too much data around the fault which won't be used), and the latter is independent of base page size. I've chosen 64K folio size for arm64 which benefits both the 4K and 16K base page size configs and shouldn't lead to any further read-amplification since the old read-around path was (usually) reading blocks of 128K (with the last 32K being async). Performance Benchmarking ------------------------ The below shows kernel compilation and speedometer javascript benchmarks on Ampere Altra arm64 system. (The contpte patch series is applied in the baseline). First, confirmation that this patch causes more memory to be contained in 64K folios (this is for all file-backed memory so includes non-executable too): | File-backed folios | Speedometer | Kernel Compile | | by size as percentage |-----------------|-----------------| | of all mapped file mem | before | after | before | after | |=========================|========|========|========|========| |file-thp-aligned-16kB | 45% | 9% | 46% | 7% | |file-thp-aligned-32kB | 2% | 0% | 3% | 1% | |file-thp-aligned-64kB | 3% | 63% | 5% | 80% | |file-thp-aligned-128kB | 11% | 11% | 0% | 0% | |file-thp-unaligned-16kB | 1% | 0% | 3% | 1% | |file-thp-unaligned-128kB | 1% | 0% | 0% | 0% | |file-thp-partial | 0% | 0% | 0% | 0% | |-------------------------|--------|--------|--------|--------| |file-cont-aligned-64kB | 16% | 75% | 5% | 80% | The above shows that for both use cases, the amount of file memory backed by 16K folios reduces and the amount backed by 64K folios increases significantly. And the amount of memory that is contpte-mapped significantly increases (last line). And this is reflected in performance improvement: Kernel Compilation (smaller is faster): | kernel | real-time | kern-time | user-time | peak memory | |----------|-------------|-------------|-------------|---------------| | before | 0.0% | 0.0% | 0.0% | 0.0% | | after | -1.6% | -2.1% | -1.7% | 0.0% | Speedometer (bigger is faster): | kernel | runs_per_min | peak memory | |----------|----------------|---------------| | before | 0.0% | 0.0% | | after | 1.3% | 1.0% | Both benchmarks show a ~1.5% improvement once the patch is applied. Alternatives ------------ I considered (and rejected for now - but I anticipate this patch will stimulate discussion around what the best approach is) alternative approaches: - Expose a global user-controlled knob to set the preferred folio size; this would move policy to user space and allow (e.g.) setting it to PMD-size for even better iTLB utilizaiton. But this would add ABI, and I prefer to start with the simplest approach first. It also has the downside that a change wouldn't apply to memory already in the page cache that is in active use (e.g. libc) so we don't get the same level of utilization as for something that is fixed from boot. - Add a per-vma attribute to allow user space to specify preferred folio size for memory faulted from the range. (we've talked about such a control in the context of mTHP). The dynamic loader would then be responsible for adding the annotations. Again this feels like something that could be added later if value was demonstrated. - Enhance MADV_COLLAPSE to collapse to THP sizes less than PMD-size. This would still require dynamic linker involvement, but would additionally neccessitate a copy and all memory in the range would be synchronously faulted in, adding to application load time. It would work for filesystems that don't support large folios though. Signed-off-by: Ryan Roberts --- Hi all, I originally concocted something similar to this, with Matthew's help, as a quick proof of concept hack. Since then I've tried a few different approaches but always came back to this as the simplest solution. I expect this will raise a few eyebrows but given it is providing a real performance win, I hope we can converge to something that can be upstreamed. This depends on my contpte series to actually set the contiguous bit in the page table. Thanks, Ryan arch/arm64/include/asm/pgtable.h | 12 ++++++++++++ include/linux/pgtable.h | 12 ++++++++++++ mm/filemap.c | 19 +++++++++++++++++++ 3 files changed, 43 insertions(+) -- 2.25.1 diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index f5bf059291c3..8f8f3f7eb8d8 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -1143,6 +1143,18 @@ static inline void update_mmu_cache_range(struct vm_fault *vmf, */ #define arch_wants_old_prefaulted_pte cpu_has_hw_af +/* + * Request exec memory is read into pagecache in at least 64K folios. The + * trade-off here is performance improvement due to storing translations more + * effciently in the iTLB vs the potential for read amplification due to reading + * data from disk that won't be used. The latter is independent of base page + * size, so we set a page-size independent block size of 64K. This size can be + * contpte-mapped when 4K base pages are in use (16 pages into 1 iTLB entry), + * and HPA can coalesce it (4 pages into 1 TLB entry) when 16K base pages are in + * use. + */ +#define arch_wants_exec_folio_order(void) ilog2(SZ_64K >> PAGE_SHIFT) + static inline bool pud_sect_supported(void) { return PAGE_SIZE == SZ_4K; diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 170925379534..57090616d09c 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -428,6 +428,18 @@ static inline bool arch_has_hw_pte_young(void) } #endif +#ifndef arch_wants_exec_folio_order +/* + * Returns preferred minimum folio order for executable file-backed memory. Must + * be in range [0, PMD_ORDER]. Negative value implies that the HW has no + * preference and mm will not special-case executable memory in the pagecache. + */ +static inline int arch_wants_exec_folio_order(void) +{ + return -1; +} +#endif + #ifndef arch_check_zapped_pte static inline void arch_check_zapped_pte(struct vm_area_struct *vma, pte_t pte) diff --git a/mm/filemap.c b/mm/filemap.c index 67ba56ecdd32..80a76d755534 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3115,6 +3115,25 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf) } #endif + /* + * Allow arch to request a preferred minimum folio order for executable + * memory. This can often be beneficial to performance if (e.g.) arm64 + * can contpte-map the folio. Executable memory rarely benefits from + * read-ahead anyway, due to its random access nature. + */ + if (vm_flags & VM_EXEC) { + int order = arch_wants_exec_folio_order(); + + if (order >= 0) { + fpin = maybe_unlock_mmap_for_io(vmf, fpin); + ra->size = 1UL << order; + ra->async_size = 0; + ractl._index &= ~((unsigned long)ra->size - 1); + page_cache_ra_order(&ractl, ra, order); + return fpin; + } + } + /* If we don't want any read-ahead, don't bother */ if (vm_flags & VM_RAND_READ) return fpin;