From nobody Wed Nov 27 18:35:13 2024 Received: from foss.arm.com (foss.arm.com [217.140.110.172]) by smtp.subspace.kernel.org (Postfix) with ESMTP id D52DE13AA47 for ; Tue, 8 Oct 2024 06:18:16 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=217.140.110.172 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1728368300; cv=none; b=tScrLfrQYBNSYkJWVGwsG2hbuzCx/b6kjrXEUxkN9Cpsm7qTffqGAnGdNKltQ+WvJth0FSacuRwrzVIHARjeE/0q0tqd7MSfRY+a3uN7I8aHkkHVFsoR09j9y93AQXyzFbkC7BGLlo4o8BNQMnxnzhv/avZTFH/lO6k6OisfR0c= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1728368300; c=relaxed/simple; bh=aL3Dc0Qya4abn7P46D37+Ebc6vndufk/+I0SS47hIrU=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=LcwaOr406Llt3FnrAdc49VBlqKtbji+O2Hndg3AU3SX6JT3UUZw9rQSY7Nmap8hdZdwTAClg4gLLV/as2N823sYUN9U39jxFB3RgX/4ogb/yzrkc0lNW9uTtv1FHQKn9bUOMJ8a+g+xazu/giTfxl42hdwrR4spTCw47Mh/1qrA= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=arm.com; spf=pass smtp.mailfrom=arm.com; arc=none smtp.client-ip=217.140.110.172 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=arm.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=arm.com 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 7C483FEC; Mon, 7 Oct 2024 23:18:45 -0700 (PDT) Received: from e116581.blr.arm.com (e116581.arm.com [10.162.43.142]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPA id 168493F73F; Mon, 7 Oct 2024 23:18:06 -0700 (PDT) From: Dev Jain To: akpm@linux-foundation.org, david@redhat.com, willy@infradead.org, kirill.shutemov@linux.intel.com Cc: ryan.roberts@arm.com, anshuman.khandual@arm.com, catalin.marinas@arm.com, cl@gentwo.org, vbabka@suse.cz, mhocko@suse.com, apopple@nvidia.com, dave.hansen@linux.intel.com, will@kernel.org, baohua@kernel.org, jack@suse.cz, mark.rutland@arm.com, hughd@google.com, aneesh.kumar@kernel.org, yang@os.amperecomputing.com, peterx@redhat.com, ioworker0@gmail.com, jglisse@google.com, wangkefeng.wang@huawei.com, ziy@nvidia.com, linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org, Dev Jain Subject: [PATCH v7 1/2] mm: Abstract THP allocation Date: Tue, 8 Oct 2024 11:47:45 +0530 Message-Id: <20241008061746.285961-2-dev.jain@arm.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20241008061746.285961-1-dev.jain@arm.com> References: <20241008061746.285961-1-dev.jain@arm.com> 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" In preparation for the second patch, abstract away the THP allocation logic present in the create_huge_pmd() path, which corresponds to the faulting case when no page is present. There should be no functional change as a result of applying this patch, except that, as David notes at [1], a PMD-aligned address should be passed to update_mmu_cache_pmd(). [1]: https://lore.kernel.org/all/ddd3fcd2-48b3-4170-bcaa-2fe66e093f43@redha= t.com/ Acked-by: David Hildenbrand Reviewed-by: Kefeng Wang =20 Signed-off-by: Dev Jain --- mm/huge_memory.c | 98 ++++++++++++++++++++++++++++-------------------- 1 file changed, 57 insertions(+), 41 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 3ca89e0279a7..e21c4f759e00 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1148,47 +1148,81 @@ unsigned long thp_get_unmapped_area(struct file *fi= lp, unsigned long addr, } EXPORT_SYMBOL_GPL(thp_get_unmapped_area); =20 -static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, - struct page *page, gfp_t gfp) +static struct folio *vma_alloc_anon_folio_pmd(struct vm_area_struct *vma, + unsigned long addr) { - struct vm_area_struct *vma =3D vmf->vma; - struct folio *folio =3D page_folio(page); - pgtable_t pgtable; - unsigned long haddr =3D vmf->address & HPAGE_PMD_MASK; - vm_fault_t ret =3D 0; + gfp_t gfp =3D vma_thp_gfp_mask(vma); + const int order =3D HPAGE_PMD_ORDER; + struct folio *folio; =20 - VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); + folio =3D vma_alloc_folio(gfp, order, vma, addr & HPAGE_PMD_MASK, true); =20 + if (unlikely(!folio)) { + count_vm_event(THP_FAULT_FALLBACK); + count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK); + return NULL; + } + + VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); if (mem_cgroup_charge(folio, vma->vm_mm, gfp)) { folio_put(folio); count_vm_event(THP_FAULT_FALLBACK); count_vm_event(THP_FAULT_FALLBACK_CHARGE); - count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_FALLBACK); - count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE); - return VM_FAULT_FALLBACK; + count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK); + count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE); + return NULL; } folio_throttle_swaprate(folio, gfp); =20 - pgtable =3D pte_alloc_one(vma->vm_mm); - if (unlikely(!pgtable)) { - ret =3D VM_FAULT_OOM; - goto release; - } - - folio_zero_user(folio, vmf->address); + folio_zero_user(folio, addr); /* * The memory barrier inside __folio_mark_uptodate makes sure that * folio_zero_user writes become visible before the set_pmd_at() * write. */ __folio_mark_uptodate(folio); + return folio; +} + +static void map_anon_folio_pmd(struct folio *folio, pmd_t *pmd, + struct vm_area_struct *vma, unsigned long haddr) +{ + pmd_t entry; + + entry =3D mk_huge_pmd(&folio->page, vma->vm_page_prot); + entry =3D maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); + folio_add_new_anon_rmap(folio, vma, haddr, RMAP_EXCLUSIVE); + folio_add_lru_vma(folio, vma); + set_pmd_at(vma->vm_mm, haddr, pmd, entry); + update_mmu_cache_pmd(vma, haddr, pmd); + add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR); + count_vm_event(THP_FAULT_ALLOC); + count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_ALLOC); + count_memcg_event_mm(vma->vm_mm, THP_FAULT_ALLOC); +} + +static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf) +{ + unsigned long haddr =3D vmf->address & HPAGE_PMD_MASK; + struct vm_area_struct *vma =3D vmf->vma; + struct folio *folio; + pgtable_t pgtable; + vm_fault_t ret =3D 0; + + folio =3D vma_alloc_anon_folio_pmd(vma, vmf->address); + if (unlikely(!folio)) + return VM_FAULT_FALLBACK; + + pgtable =3D pte_alloc_one(vma->vm_mm); + if (unlikely(!pgtable)) { + ret =3D VM_FAULT_OOM; + goto release; + } =20 vmf->ptl =3D pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_none(*vmf->pmd))) { goto unlock_release; } else { - pmd_t entry; - ret =3D check_stable_address_space(vma->vm_mm); if (ret) goto unlock_release; @@ -1202,21 +1236,11 @@ static vm_fault_t __do_huge_pmd_anonymous_page(stru= ct vm_fault *vmf, VM_BUG_ON(ret & VM_FAULT_FALLBACK); return ret; } - - entry =3D mk_huge_pmd(page, vma->vm_page_prot); - entry =3D maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); - folio_add_new_anon_rmap(folio, vma, haddr, RMAP_EXCLUSIVE); - folio_add_lru_vma(folio, vma); pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable); - set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry); - update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); - add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR); + map_anon_folio_pmd(folio, vmf->pmd, vma, haddr); mm_inc_nr_ptes(vma->vm_mm); deferred_split_folio(folio, false); spin_unlock(vmf->ptl); - count_vm_event(THP_FAULT_ALLOC); - count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_ALLOC); - count_memcg_event_mm(vma->vm_mm, THP_FAULT_ALLOC); } =20 return 0; @@ -1283,8 +1307,6 @@ static void set_huge_zero_folio(pgtable_t pgtable, st= ruct mm_struct *mm, vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) { struct vm_area_struct *vma =3D vmf->vma; - gfp_t gfp; - struct folio *folio; unsigned long haddr =3D vmf->address & HPAGE_PMD_MASK; vm_fault_t ret; =20 @@ -1335,14 +1357,8 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_faul= t *vmf) } return ret; } - gfp =3D vma_thp_gfp_mask(vma); - folio =3D vma_alloc_folio(gfp, HPAGE_PMD_ORDER, vma, haddr, true); - if (unlikely(!folio)) { - count_vm_event(THP_FAULT_FALLBACK); - count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_FALLBACK); - return VM_FAULT_FALLBACK; - } - return __do_huge_pmd_anonymous_page(vmf, &folio->page, gfp); + + return __do_huge_pmd_anonymous_page(vmf); } =20 static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, --=20 2.30.2 From nobody Wed Nov 27 18:35:13 2024 Received: from foss.arm.com (foss.arm.com [217.140.110.172]) by smtp.subspace.kernel.org (Postfix) with ESMTP id 481D113AA47 for ; Tue, 8 Oct 2024 06:18:26 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=217.140.110.172 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1728368307; cv=none; b=NS8sILDX1FURLN1pun+uFXu5Ne1JZvhY9jO7TxprXDUQZt4kYT/tORDjZSYoD/Ff/IHfUQ0SUnsKMkldBWfWbWw035bxopDd/wzOiG5GXcPF1FHCwfRbMVDta5zdvQTk/pMoLaFgn8czu/m/MTtpq/2ec4112cxHYkvbL2f95Zg= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1728368307; c=relaxed/simple; bh=N32P+d4hMhLobPDqT7RJO/7/otDqGCIEPXjh7ObafuE=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=ArzwdoPLyb/4TfJ+DTAvmRuUdWIxbTmYlu6RUnWHkPqLnY2459mSO0KTWbUldYgm+pF046ZVs6sREdblrq5RJmO3uRBTP+jl7fWVt6DHeR3UtkKvcw3XXlmVJ93QwGR2R7UFiYsmeqdX8DCCPPXmpDl6Cy4TPf4ZzUg83hEmxV8= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=arm.com; spf=pass smtp.mailfrom=arm.com; arc=none smtp.client-ip=217.140.110.172 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=arm.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=arm.com 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 2B0C4DA7; Mon, 7 Oct 2024 23:18:55 -0700 (PDT) Received: from e116581.blr.arm.com (e116581.arm.com [10.162.43.142]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPA id 8AA563F73F; Mon, 7 Oct 2024 23:18:16 -0700 (PDT) From: Dev Jain To: akpm@linux-foundation.org, david@redhat.com, willy@infradead.org, kirill.shutemov@linux.intel.com Cc: ryan.roberts@arm.com, anshuman.khandual@arm.com, catalin.marinas@arm.com, cl@gentwo.org, vbabka@suse.cz, mhocko@suse.com, apopple@nvidia.com, dave.hansen@linux.intel.com, will@kernel.org, baohua@kernel.org, jack@suse.cz, mark.rutland@arm.com, hughd@google.com, aneesh.kumar@kernel.org, yang@os.amperecomputing.com, peterx@redhat.com, ioworker0@gmail.com, jglisse@google.com, wangkefeng.wang@huawei.com, ziy@nvidia.com, linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org, Dev Jain Subject: [PATCH v7 2/2] mm: Allocate THP on hugezeropage wp-fault Date: Tue, 8 Oct 2024 11:47:46 +0530 Message-Id: <20241008061746.285961-3-dev.jain@arm.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20241008061746.285961-1-dev.jain@arm.com> References: <20241008061746.285961-1-dev.jain@arm.com> 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" Introduce do_huge_zero_wp_pmd() to handle wp-fault on a hugezeropage and replace it with a PMD-mapped THP. Remember to flush TLB entry corresponding to the hugezeropage. In case of failure, fallback to splitting the PMD. Acked-by: David Hildenbrand =20 Reviewed-by: Kefeng Wang =20 Signed-off-by: Dev Jain --- mm/huge_memory.c | 41 ++++++++++++++++++++++++++++++++++++++++- 1 file changed, 40 insertions(+), 1 deletion(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index e21c4f759e00..606ed782a15a 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1790,6 +1790,38 @@ void huge_pmd_set_accessed(struct vm_fault *vmf) spin_unlock(vmf->ptl); } =20 +static vm_fault_t do_huge_zero_wp_pmd(struct vm_fault *vmf) +{ + unsigned long haddr =3D vmf->address & HPAGE_PMD_MASK; + struct vm_area_struct *vma =3D vmf->vma; + struct mmu_notifier_range range; + struct folio *folio; + vm_fault_t ret =3D 0; + + folio =3D vma_alloc_anon_folio_pmd(vma, vmf->address); + if (unlikely(!folio)) + return VM_FAULT_FALLBACK; + + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, haddr, + haddr + HPAGE_PMD_SIZE); + mmu_notifier_invalidate_range_start(&range); + vmf->ptl =3D pmd_lock(vma->vm_mm, vmf->pmd); + if (unlikely(!pmd_same(pmdp_get(vmf->pmd), vmf->orig_pmd))) + goto release; + ret =3D check_stable_address_space(vma->vm_mm); + if (ret) + goto release; + (void)pmdp_huge_clear_flush(vma, haddr, vmf->pmd); + map_anon_folio_pmd(folio, vmf->pmd, vma, haddr); + goto unlock; +release: + folio_put(folio); +unlock: + spin_unlock(vmf->ptl); + mmu_notifier_invalidate_range_end(&range); + return ret; +} + vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf) { const bool unshare =3D vmf->flags & FAULT_FLAG_UNSHARE; @@ -1802,8 +1834,15 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf) vmf->ptl =3D pmd_lockptr(vma->vm_mm, vmf->pmd); VM_BUG_ON_VMA(!vma->anon_vma, vma); =20 - if (is_huge_zero_pmd(orig_pmd)) + if (is_huge_zero_pmd(orig_pmd)) { + vm_fault_t ret =3D do_huge_zero_wp_pmd(vmf); + + if (!(ret & VM_FAULT_FALLBACK)) + return ret; + + /* Fallback to splitting PMD if THP cannot be allocated */ goto fallback; + } =20 spin_lock(vmf->ptl); =20 --=20 2.30.2