From nobody Sun Nov 24 01:36:56 2024 Received: from out30-112.freemail.mail.aliyun.com (out30-112.freemail.mail.aliyun.com [115.124.30.112]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 7B10E13CF82 for ; Fri, 8 Nov 2024 04:13:27 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=115.124.30.112 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1731039210; cv=none; b=UaaacHrmOtIsQA935FTIzzR2Iekh/D6RoMpa/fLPXHAIMo1vdivaIfjD75krZ+PIzVZ9Y0ZpO5t94wxvojG5QaZ3fYN+n+9AGGy1bYP15yYZ7hB2E+Gqu0eupb3+4GHKom6lxateTTuBcN/qMgvyad/DtB8nGrqSK3W61aZZAaw= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1731039210; c=relaxed/simple; bh=aW+mk2ePZEaHmiZzVO05BzffwyUJkOfhEC+jcUFwaoc=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=fzmeLenLbgd5rt0glus3IZs+3Pm+7XfLRPyyD2GsH/M3HPEHyvS86KLkFMPcQlkGB5z0kpD4R080RNZN0luJPUk8oDPBLzQDZIt4k08MYn1M5JoiFL5lukAg7nBj/0k3NMzg7yYDWAHsoscZjdSni0agYmHbo+g3yT5BevvpHkA= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.alibaba.com; spf=pass smtp.mailfrom=linux.alibaba.com; dkim=pass (1024-bit key) header.d=linux.alibaba.com header.i=@linux.alibaba.com header.b=BLT+bTHW; arc=none smtp.client-ip=115.124.30.112 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.alibaba.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.alibaba.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux.alibaba.com header.i=@linux.alibaba.com header.b="BLT+bTHW" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.alibaba.com; s=default; t=1731039205; h=From:To:Subject:Date:Message-Id:MIME-Version; bh=GjeDj7oC1iiZ/gkwEo4XJZE2Kubqr3JwCuLq6Y0HOAU=; b=BLT+bTHW3cS/tkPHBwAItgUH4HiKzcYqMyXkO2UGmTrI4NkzHvCenBhi0FMSRFY3kuT8WS4tORB+M+EGw6NKS3mI7t15HlziENqLRZvzzMZc23hYMpTHtrakOLXrEYRFzdOhl2GGY1lWExPYb2U5QQHsfTFW1HJ97nGYvf8bGVw= Received: from localhost(mailfrom:baolin.wang@linux.alibaba.com fp:SMTPD_---0WIxXGhc_1731039203 cluster:ay36) by smtp.aliyun-inc.com; Fri, 08 Nov 2024 12:13:23 +0800 From: Baolin Wang To: akpm@linux-foundation.org, hughd@google.com Cc: willy@infradead.org, david@redhat.com, wangkefeng.wang@huawei.com, 21cnbao@gmail.com, ryan.roberts@arm.com, ioworker0@gmail.com, da.gomez@samsung.com, baolin.wang@linux.alibaba.com, linux-mm@kvack.org, linux-kernel@vger.kernel.org Subject: [PATCH 1/4] mm: factor out the order calculation into a new helper Date: Fri, 8 Nov 2024 12:12:55 +0800 Message-Id: X-Mailer: git-send-email 2.39.3 In-Reply-To: References: Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" Factor out the order calculation into a new helper, which can be reused by shmem in the following patch. Suggested-by: Matthew Wilcox Signed-off-by: Baolin Wang Reviewed-by: Barry Song Reviewed-by: David Hildenbrand --- include/linux/pagemap.h | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index bcf0865a38ae..d796c8a33647 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -727,6 +727,16 @@ typedef unsigned int __bitwise fgf_t; =20 #define FGP_WRITEBEGIN (FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE) =20 +static inline unsigned int filemap_get_order(size_t size) +{ + unsigned int shift =3D ilog2(size); + + if (shift <=3D PAGE_SHIFT) + return 0; + + return shift - PAGE_SHIFT; +} + /** * fgf_set_order - Encode a length in the fgf_t flags. * @size: The suggested size of the folio to create. @@ -740,11 +750,11 @@ typedef unsigned int __bitwise fgf_t; */ static inline fgf_t fgf_set_order(size_t size) { - unsigned int shift =3D ilog2(size); + unsigned int order =3D filemap_get_order(size); =20 - if (shift <=3D PAGE_SHIFT) + if (!order) return 0; - return (__force fgf_t)((shift - PAGE_SHIFT) << 26); + return (__force fgf_t)(order << 26); } =20 void *filemap_get_entry(struct address_space *mapping, pgoff_t index); --=20 2.39.3 From nobody Sun Nov 24 01:36:56 2024 Received: from out30-132.freemail.mail.aliyun.com (out30-132.freemail.mail.aliyun.com [115.124.30.132]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id B5BE31CF5F4 for ; Fri, 8 Nov 2024 04:13:33 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=115.124.30.132 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1731039215; cv=none; b=QiYv+grVog7CRW3decDh2aZtfDZ++1dJU9U3qsmwVDb5T0cXgDOclzqzqXicsRCn/Hrj3mGHYnI8/8KYTI73xLaeZ1lWA0VggQrSmJRNWdZrnkAbhEgYUwdWYvnRrpTN0AyEYhFUUqH7GehNIHvTx+eD94s+LvrQOPnCmoHV/eA= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1731039215; c=relaxed/simple; bh=pIINmnRuMhBwhKo7Aoq6MuHbbIlkpLT5NNRZGvEsE3I=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=pSzWrROXRTGBqJolJqeQm0JtwXoiO4qkE8p4UehJv/6kRNtYr94E5FPRXxGt5PoWhOXne4VHvAjlOzwDfwk3pFlLrrDKf1hmGIFqNYhKfcaDNBRf5WHCfo/dWG7wzRdxnmRp9qawmuEoStYzr1JdIRAl01vlSaBNeMho50jjBck= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.alibaba.com; spf=pass smtp.mailfrom=linux.alibaba.com; dkim=pass (1024-bit key) header.d=linux.alibaba.com header.i=@linux.alibaba.com header.b=Rwm+hqD7; arc=none smtp.client-ip=115.124.30.132 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.alibaba.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.alibaba.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux.alibaba.com header.i=@linux.alibaba.com header.b="Rwm+hqD7" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.alibaba.com; s=default; t=1731039206; h=From:To:Subject:Date:Message-Id:MIME-Version; bh=OAXkgfSC/TSIsttX/eS9fvBNEIFaQACVaW/jTgI39Ao=; b=Rwm+hqD79ng0V3+gkZY7ifxG0EexZrRinnxWZM74LSYPR7l/LN4/38agX9VUIPHFeE792YQkYAKjzo3umiexnvFk2f7VLj1JPh9Gvyey+oe5C31JAvTsCwPY8PKfXo23/0DkpXqfzM13nBgESoPmas7FQsKgPv+Ba6a+stDplug= Received: from localhost(mailfrom:baolin.wang@linux.alibaba.com fp:SMTPD_---0WIxZtPU_1731039204 cluster:ay36) by smtp.aliyun-inc.com; Fri, 08 Nov 2024 12:13:24 +0800 From: Baolin Wang To: akpm@linux-foundation.org, hughd@google.com Cc: willy@infradead.org, david@redhat.com, wangkefeng.wang@huawei.com, 21cnbao@gmail.com, ryan.roberts@arm.com, ioworker0@gmail.com, da.gomez@samsung.com, baolin.wang@linux.alibaba.com, linux-mm@kvack.org, linux-kernel@vger.kernel.org Subject: [PATCH 2/4] mm: shmem: change shmem_huge_global_enabled() to return huge order bitmap Date: Fri, 8 Nov 2024 12:12:56 +0800 Message-Id: X-Mailer: git-send-email 2.39.3 In-Reply-To: References: Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" Change the shmem_huge_global_enabled() to return the suitable huge order bitmap, and return 0 if huge pages are not allowed. This is a preparation for supporting various huge orders allocation of tmpfs in the following patches. No functional changes. Signed-off-by: Baolin Wang --- mm/shmem.c | 45 ++++++++++++++++++++++++--------------------- 1 file changed, 24 insertions(+), 21 deletions(-) diff --git a/mm/shmem.c b/mm/shmem.c index 579e58cb3262..361da46c4bd5 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -549,37 +549,37 @@ static bool shmem_confirm_swap(struct address_space *= mapping, =20 static int shmem_huge __read_mostly =3D SHMEM_HUGE_NEVER; =20 -static bool shmem_huge_global_enabled(struct inode *inode, pgoff_t index, - loff_t write_end, bool shmem_huge_force, - unsigned long vm_flags) +static unsigned int shmem_huge_global_enabled(struct inode *inode, pgoff_t= index, + loff_t write_end, bool shmem_huge_force, + unsigned long vm_flags) { loff_t i_size; =20 if (HPAGE_PMD_ORDER > MAX_PAGECACHE_ORDER) - return false; + return 0; if (!S_ISREG(inode->i_mode)) - return false; + return 0; if (shmem_huge =3D=3D SHMEM_HUGE_DENY) - return false; + return 0; if (shmem_huge_force || shmem_huge =3D=3D SHMEM_HUGE_FORCE) - return true; + return BIT(HPAGE_PMD_ORDER); =20 switch (SHMEM_SB(inode->i_sb)->huge) { case SHMEM_HUGE_ALWAYS: - return true; + return BIT(HPAGE_PMD_ORDER); case SHMEM_HUGE_WITHIN_SIZE: index =3D round_up(index + 1, HPAGE_PMD_NR); i_size =3D max(write_end, i_size_read(inode)); i_size =3D round_up(i_size, PAGE_SIZE); if (i_size >> PAGE_SHIFT >=3D index) - return true; + return BIT(HPAGE_PMD_ORDER); fallthrough; case SHMEM_HUGE_ADVISE: if (vm_flags & VM_HUGEPAGE) - return true; + return BIT(HPAGE_PMD_ORDER); fallthrough; default: - return false; + return 0; } } =20 @@ -774,11 +774,11 @@ static unsigned long shmem_unused_huge_shrink(struct = shmem_sb_info *sbinfo, return 0; } =20 -static bool shmem_huge_global_enabled(struct inode *inode, pgoff_t index, - loff_t write_end, bool shmem_huge_force, - unsigned long vm_flags) +static unsigned int shmem_huge_global_enabled(struct inode *inode, pgoff_t= index, + loff_t write_end, bool shmem_huge_force, + unsigned long vm_flags) { - return false; + return 0; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ =20 @@ -1173,8 +1173,11 @@ static int shmem_getattr(struct mnt_idmap *idmap, generic_fillattr(idmap, request_mask, inode, stat); inode_unlock_shared(inode); =20 - if (shmem_huge_global_enabled(inode, 0, 0, false, 0)) +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (shmem_huge_global_enabled(inode, 0, 0, false, 0) =3D=3D + BIT(HPAGE_PMD_ORDER)) stat->blksize =3D HPAGE_PMD_SIZE; +#endif =20 if (request_mask & STATX_BTIME) { stat->result_mask |=3D STATX_BTIME; @@ -1682,21 +1685,21 @@ unsigned long shmem_allowable_huge_orders(struct in= ode *inode, unsigned long mask =3D READ_ONCE(huge_shmem_orders_always); unsigned long within_size_orders =3D READ_ONCE(huge_shmem_orders_within_s= ize); unsigned long vm_flags =3D vma ? vma->vm_flags : 0; - bool global_huge; + unsigned int global_orders; loff_t i_size; int order; =20 if (thp_disabled_by_hw() || (vma && vma_thp_disabled(vma, vm_flags))) return 0; =20 - global_huge =3D shmem_huge_global_enabled(inode, index, write_end, - shmem_huge_force, vm_flags); + global_orders =3D shmem_huge_global_enabled(inode, index, write_end, + shmem_huge_force, vm_flags); if (!vma || !vma_is_anon_shmem(vma)) { /* * For tmpfs, we now only support PMD sized THP if huge page * is enabled, otherwise fallback to order 0. */ - return global_huge ? BIT(HPAGE_PMD_ORDER) : 0; + return global_orders; } =20 /* @@ -1729,7 +1732,7 @@ unsigned long shmem_allowable_huge_orders(struct inod= e *inode, if (vm_flags & VM_HUGEPAGE) mask |=3D READ_ONCE(huge_shmem_orders_madvise); =20 - if (global_huge) + if (global_orders > 0) mask |=3D READ_ONCE(huge_shmem_orders_inherit); =20 return THP_ORDERS_ALL_FILE_DEFAULT & mask; --=20 2.39.3 From nobody Sun Nov 24 01:36:56 2024 Received: from out30-110.freemail.mail.aliyun.com (out30-110.freemail.mail.aliyun.com [115.124.30.110]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 91E563BBEA for ; Fri, 8 Nov 2024 04:13:29 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=115.124.30.110 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1731039211; cv=none; b=bgLiLeMkMfvHtG90ifkiNu9T/NkevyHSliVVtVlis1w1BFBJtE+reS5K9W4phZfDcEliC2zCdSK/yh/w4mRyvQw9fBOBI3HSyiWut0w0a6uJGntVtbL4XMrCMduvHElC0kYw/CzzkHzp13Jj7JSrPALVZ+F6C4DFFSyGGzsympk= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1731039211; c=relaxed/simple; bh=0DCuG3JDJ1q8FqeEYHOrNP3qle6nG5SinTRjy21kvLI=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=WiaX+iZclzUXVJxVqiNxTYbTPjwqbaxmmC7J7iQoE8VZqWHF6ezG28IuSzcS4Dl3X/tcc3Jvq2j5QwafjwMXGudM5Fd0iFcJaqPgFa5pusqpWJtdaF8vHTkVLVIXiUcgX0m8VQa3uShXAvyBtibTZa7A7lKX12NZdsj+GVg+50w= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.alibaba.com; spf=pass smtp.mailfrom=linux.alibaba.com; dkim=pass (1024-bit key) header.d=linux.alibaba.com header.i=@linux.alibaba.com header.b=RQhA4ZW/; arc=none smtp.client-ip=115.124.30.110 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.alibaba.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.alibaba.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux.alibaba.com header.i=@linux.alibaba.com header.b="RQhA4ZW/" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.alibaba.com; s=default; t=1731039207; h=From:To:Subject:Date:Message-Id:MIME-Version; bh=kKtwOTm/io/miazqQHXaa70Oq2bCu/U2TTLxQP5qiDM=; b=RQhA4ZW/CqyHM20Pm0dsvDGk0WoRKfNOoFL30lfD0TMTlqZdur4/MxZqrycQn/ONM0/HvX/t94CKxjaOGodXbQlQYTOvGzIsBoWlbGu/EkU2vchNY9rPjJ2vDLjoREEJt58sZcY1mhYppwSctG0q5icNhD/JfjkkGGKy5YNUM38= Received: from localhost(mailfrom:baolin.wang@linux.alibaba.com fp:SMTPD_---0WIxRHWc_1731039205 cluster:ay36) by smtp.aliyun-inc.com; Fri, 08 Nov 2024 12:13:25 +0800 From: Baolin Wang To: akpm@linux-foundation.org, hughd@google.com Cc: willy@infradead.org, david@redhat.com, wangkefeng.wang@huawei.com, 21cnbao@gmail.com, ryan.roberts@arm.com, ioworker0@gmail.com, da.gomez@samsung.com, baolin.wang@linux.alibaba.com, linux-mm@kvack.org, linux-kernel@vger.kernel.org Subject: [PATCH 3/4] mm: shmem: add large folio support for tmpfs Date: Fri, 8 Nov 2024 12:12:57 +0800 Message-Id: X-Mailer: git-send-email 2.39.3 In-Reply-To: References: Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" Add large folio support for tmpfs write and fallocate paths matching the same high order preference mechanism used in the iomap buffered IO path as used in __filemap_get_folio(). Add shmem_mapping_size_orders() to get a hint for the orders of the folio based on the file size which takes care of the mapping requirements. Traditionally, tmpfs only supported PMD-sized huge folios. However nowadays with other file systems supporting any sized large folios, and extending anonymous to support mTHP, we should not restrict tmpfs to allocating only PMD-sized huge folios, making it more special. Instead, we should allow tmpfs can allocate any sized large folios. Considering that tmpfs already has the 'huge=3D' option to control the huge folios allocation, we can extend the 'huge=3D' option to allow any sized hu= ge folios. The semantics of the 'huge=3D' mount option are: huge=3Dnever: no any sized huge folios huge=3Dalways: any sized huge folios huge=3Dwithin_size: like 'always' but respect the i_size huge=3Dadvise: like 'always' if requested with fadvise()/madvise() Note: for tmpfs mmap() faults, due to the lack of a write size hint, still allocate the PMD-sized huge folios if huge=3Dalways/within_size/advise is s= et. Moreover, the 'deny' and 'force' testing options controlled by '/sys/kernel/mm/transparent_hugepage/shmem_enabled', still retain the same semantics. The 'deny' can disable any sized large folios for tmpfs, while the 'force' can enable PMD sized large folios for tmpfs. Co-developed-by: Daniel Gomez Signed-off-by: Daniel Gomez Signed-off-by: Baolin Wang --- mm/shmem.c | 91 +++++++++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 77 insertions(+), 14 deletions(-) diff --git a/mm/shmem.c b/mm/shmem.c index 361da46c4bd5..98503a93a404 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -549,10 +549,50 @@ static bool shmem_confirm_swap(struct address_space *= mapping, =20 static int shmem_huge __read_mostly =3D SHMEM_HUGE_NEVER; =20 +/** + * shmem_mapping_size_orders - Get allowable folio orders for the given fi= le size. + * @mapping: Target address_space. + * @index: The page index. + * @size: The suggested size of the folio to create. + * + * This returns a high order for folios (when supported) based on the file= size + * which the mapping currently allows at the given index. The index is rel= evant + * due to alignment considerations the mapping might have. The returned or= der + * may be less than the size passed. + * + * Return: The orders. + */ +static inline unsigned int +shmem_mapping_size_orders(struct address_space *mapping, pgoff_t index, lo= ff_t write_end) +{ + unsigned int order; + size_t size; + + if (!mapping_large_folio_support(mapping) || !write_end) + return 0; + + /* Calculate the write size based on the write_end */ + size =3D write_end - (index << PAGE_SHIFT); + order =3D filemap_get_order(size); + if (!order) + return 0; + + /* If we're not aligned, allocate a smaller folio */ + if (index & ((1UL << order) - 1)) + order =3D __ffs(index); + + order =3D min_t(size_t, order, MAX_PAGECACHE_ORDER); + return order > 0 ? BIT(order + 1) - 1 : 0; +} + static unsigned int shmem_huge_global_enabled(struct inode *inode, pgoff_t= index, loff_t write_end, bool shmem_huge_force, + struct vm_area_struct *vma, unsigned long vm_flags) { + unsigned long within_size_orders; + unsigned int order; + pgoff_t aligned_index; loff_t i_size; =20 if (HPAGE_PMD_ORDER > MAX_PAGECACHE_ORDER) @@ -564,15 +604,41 @@ static unsigned int shmem_huge_global_enabled(struct = inode *inode, pgoff_t index if (shmem_huge_force || shmem_huge =3D=3D SHMEM_HUGE_FORCE) return BIT(HPAGE_PMD_ORDER); =20 + /* + * The huge order allocation for anon shmem is controlled through + * the mTHP interface, so we still use PMD-sized huge order to + * check whether global control is enabled. + * + * For tmpfs mmap()'s huge order, we still use PMD-sized order to + * allocate huge pages due to lack of a write size hint. + * + * Otherwise, tmpfs will allow getting a highest order hint based on + * the size of write and fallocate paths, then will try each allowable + * huge orders. + */ switch (SHMEM_SB(inode->i_sb)->huge) { case SHMEM_HUGE_ALWAYS: - return BIT(HPAGE_PMD_ORDER); - case SHMEM_HUGE_WITHIN_SIZE: - index =3D round_up(index + 1, HPAGE_PMD_NR); - i_size =3D max(write_end, i_size_read(inode)); - i_size =3D round_up(i_size, PAGE_SIZE); - if (i_size >> PAGE_SHIFT >=3D index) + if (vma) return BIT(HPAGE_PMD_ORDER); + + return shmem_mapping_size_orders(inode->i_mapping, index, write_end); + case SHMEM_HUGE_WITHIN_SIZE: + if (vma) + within_size_orders =3D BIT(HPAGE_PMD_ORDER); + else + within_size_orders =3D shmem_mapping_size_orders(inode->i_mapping, + index, write_end); + + order =3D highest_order(within_size_orders); + while (within_size_orders) { + aligned_index =3D round_up(index + 1, 1 << order); + i_size =3D max(write_end, i_size_read(inode)); + i_size =3D round_up(i_size, PAGE_SIZE); + if (i_size >> PAGE_SHIFT >=3D aligned_index) + return within_size_orders; + + order =3D next_order(&within_size_orders, order); + } fallthrough; case SHMEM_HUGE_ADVISE: if (vm_flags & VM_HUGEPAGE) @@ -776,6 +842,7 @@ static unsigned long shmem_unused_huge_shrink(struct sh= mem_sb_info *sbinfo, =20 static unsigned int shmem_huge_global_enabled(struct inode *inode, pgoff_t= index, loff_t write_end, bool shmem_huge_force, + struct vm_area_struct *vma, unsigned long vm_flags) { return 0; @@ -1174,7 +1241,7 @@ static int shmem_getattr(struct mnt_idmap *idmap, inode_unlock_shared(inode); =20 #ifdef CONFIG_TRANSPARENT_HUGEPAGE - if (shmem_huge_global_enabled(inode, 0, 0, false, 0) =3D=3D + if (shmem_huge_global_enabled(inode, 0, 0, false, NULL, 0) =3D=3D BIT(HPAGE_PMD_ORDER)) stat->blksize =3D HPAGE_PMD_SIZE; #endif @@ -1693,14 +1760,10 @@ unsigned long shmem_allowable_huge_orders(struct in= ode *inode, return 0; =20 global_orders =3D shmem_huge_global_enabled(inode, index, write_end, - shmem_huge_force, vm_flags); - if (!vma || !vma_is_anon_shmem(vma)) { - /* - * For tmpfs, we now only support PMD sized THP if huge page - * is enabled, otherwise fallback to order 0. - */ + shmem_huge_force, vma, vm_flags); + /* Tmpfs huge pages allocation? */ + if (!vma || !vma_is_anon_shmem(vma)) return global_orders; - } =20 /* * Following the 'deny' semantics of the top level, force the huge --=20 2.39.3 From nobody Sun Nov 24 01:36:56 2024 Received: from out30-131.freemail.mail.aliyun.com (out30-131.freemail.mail.aliyun.com [115.124.30.131]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id D51701D0143 for ; Fri, 8 Nov 2024 04:13:35 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=115.124.30.131 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1731039218; cv=none; b=hfhk2PZ5HrsIREBqOp2dWG9M68VELcT8r64uPHoqRHwErFUjpX6aCEqf36qGOp4s2ki1O8WK02WZqFAdhNhnu209g4QECpbwxCJgIEe7jU+7Rb2v4mNZbjjtWZtKX8jhnF38O0D9+WLDw/S7RiE/VafOcFoQ9h182YjWxIw8rns= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1731039218; c=relaxed/simple; bh=TC8NDwoOUMeA/My5O/A8g5mi2sVobB8mozFqxOI+boY=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=bqLeI6KpDkx4pk2Nhv0BC3a4bq6KFN2/6g1Xx8b6+BK0KleI1I/HYwJ7XZNGmC8sSr5+wUpSTb/ga01qcM1413z/whw1gJ3qItFCwLNcV10G0WPIrO4xdVOYImzH7NC9xqabunWc75M9t07aiLh2pS/i/eW39psG8WUTaMz+BJo= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.alibaba.com; spf=pass smtp.mailfrom=linux.alibaba.com; dkim=pass (1024-bit key) header.d=linux.alibaba.com header.i=@linux.alibaba.com header.b=QMJJ5uvD; arc=none smtp.client-ip=115.124.30.131 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.alibaba.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.alibaba.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux.alibaba.com header.i=@linux.alibaba.com header.b="QMJJ5uvD" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.alibaba.com; s=default; t=1731039208; h=From:To:Subject:Date:Message-Id:MIME-Version; bh=ZMgQiGlmb/wE6nW4qxF+A3bZ7Id2I6Bajbakd8brhAI=; b=QMJJ5uvDLvcQ59uDe4rhb6psDskUZfYEmx7Z5vYS+YDUxMjT0UWg9+BXpwReBewdT2bMYvGcbbzIVS2z3unIfoUf1Zs00s6/b+grz2Ayaq9l6A7VRg5w6Sqblnj9VCER1vSXzC6cE4rz0oVGsp8eyWmh34yjN+l0QhVjiwcv/N4= Received: from localhost(mailfrom:baolin.wang@linux.alibaba.com fp:SMTPD_---0WIxRHWz_1731039206 cluster:ay36) by smtp.aliyun-inc.com; Fri, 08 Nov 2024 12:13:26 +0800 From: Baolin Wang To: akpm@linux-foundation.org, hughd@google.com Cc: willy@infradead.org, david@redhat.com, wangkefeng.wang@huawei.com, 21cnbao@gmail.com, ryan.roberts@arm.com, ioworker0@gmail.com, da.gomez@samsung.com, baolin.wang@linux.alibaba.com, linux-mm@kvack.org, linux-kernel@vger.kernel.org Subject: [PATCH 4/4] docs: tmpfs: update the huge folios policy for tmpfs and shmem Date: Fri, 8 Nov 2024 12:12:58 +0800 Message-Id: X-Mailer: git-send-email 2.39.3 In-Reply-To: References: Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" From: David Hildenbrand Update the huge folios policy for tmpfs and shmem. Signed-off-by: David Hildenbrand Signed-off-by: Baolin Wang --- Documentation/admin-guide/mm/transhuge.rst | 52 +++++++++++++++------- 1 file changed, 36 insertions(+), 16 deletions(-) diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/adm= in-guide/mm/transhuge.rst index 5034915f4e8e..2a7705bf622d 100644 --- a/Documentation/admin-guide/mm/transhuge.rst +++ b/Documentation/admin-guide/mm/transhuge.rst @@ -352,8 +352,21 @@ default to ``never``. Hugepages in tmpfs/shmem =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D =20 -You can control hugepage allocation policy in tmpfs with mount option -``huge=3D``. It can have following values: +Traditionally, tmpfs only supported a single huge page size ("PMD"). Today, +it also supports smaller sizes just like anonymous memory, often referred +to as "multi-size THP" (mTHP). Huge pages of any size are commonly +represented in the kernel as "large folios". + +While there is fine control over the huge page sizes to use for the intern= al +shmem mount (see below), ordinary tmpfs mounts will make use of all availa= ble +huge page sizes without any control over the exact sizes, behaving more li= ke +other file systems. + +tmpfs mounts +------------ + +The THP allocation policy for tmpfs mounts can be adjusted using the mount +option: ``huge=3D``. It can have following values: =20 always Attempt to allocate huge pages every time we need a new page; @@ -374,13 +387,9 @@ The default policy is ``never``. ``huge=3Dnever`` will not attempt to break up huge pages at all, just stop= more from being allocated. =20 -There's also sysfs knob to control hugepage allocation policy for internal -shmem mount: /sys/kernel/mm/transparent_hugepage/shmem_enabled. The mount -is used for SysV SHM, memfds, shared anonymous mmaps (of /dev/zero or -MAP_ANONYMOUS), GPU drivers' DRM objects, Ashmem. - -In addition to policies listed above, shmem_enabled allows two further -values: +In addition to policies listed above, the sysfs knob +/sys/kernel/mm/transparent_hugepage/shmem_enabled will affect the +allocation policy of tmpfs mounts, when set to the following values: =20 deny For use in emergencies, to force the huge option off from @@ -388,13 +397,24 @@ deny force Force the huge option on for all - very useful for testing; =20 -Shmem can also use "multi-size THP" (mTHP) by adding a new sysfs knob to -control mTHP allocation: -'/sys/kernel/mm/transparent_hugepage/hugepages-kB/shmem_enabled', -and its value for each mTHP is essentially consistent with the global -setting. An 'inherit' option is added to ensure compatibility with these -global settings. Conversely, the options 'force' and 'deny' are dropped, -which are rather testing artifacts from the old ages. +shmem / internal tmpfs +---------------------- +The mount internal tmpfs mount is used for SysV SHM, memfds, shared anonym= ous +mmaps (of /dev/zero or MAP_ANONYMOUS), GPU drivers' DRM objects, Ashmem. + +To control the THP allocation policy for this internal tmpfs mount, the +sysfs knob /sys/kernel/mm/transparent_hugepage/shmem_enabled and the knobs +per THP size in +'/sys/kernel/mm/transparent_hugepage/hugepages-kB/shmem_enabled' +can be used. + +The global knob has the same semantics as the ``huge=3D`` mount options +for tmpfs mounts, except that the different huge page sizes can be control= led +individually, and will only use the setting of the global knob when the +per-size knob is set to 'inherit'. + +The options 'force' and 'deny' are dropped for the individual sizes, which +are rather testing artifacts from the old ages. =20 always Attempt to allocate huge pages every time we need a new page; --=20 2.39.3