Linux-Fsdevel Archive mirror
 help / color / mirror / Atom feed
From: Alexandru Elisei <alexandru.elisei@arm.com>
To: catalin.marinas@arm.com, will@kernel.org, oliver.upton@linux.dev,
	maz@kernel.org, james.morse@arm.com, suzuki.poulose@arm.com,
	yuzenghui@huawei.com, arnd@arndb.de, akpm@linux-foundation.org,
	mingo@redhat.com, peterz@infradead.org, juri.lelli@redhat.com,
	vincent.guittot@linaro.org, dietmar.eggemann@arm.com,
	rostedt@goodmis.org, bsegall@google.com, mgorman@suse.de,
	bristot@redhat.com, vschneid@redhat.com, mhiramat@kernel.org,
	rppt@kernel.org, hughd@google.com
Cc: pcc@google.com, steven.price@arm.com, anshuman.khandual@arm.com,
	vincenzo.frascino@arm.com, david@redhat.com, eugenis@google.com,
	kcc@google.com, hyesoo.yu@samsung.com,
	linux-arm-kernel@lists.infradead.org,
	linux-kernel@vger.kernel.org, kvmarm@lists.linux.dev,
	linux-fsdevel@vger.kernel.org, linux-arch@vger.kernel.org,
	linux-mm@kvack.org, linux-trace-kernel@vger.kernel.org
Subject: [PATCH RFC v2 20/27] mm: hugepage: Handle huge page fault on access
Date: Sun, 19 Nov 2023 16:57:14 +0000	[thread overview]
Message-ID: <20231119165721.9849-21-alexandru.elisei@arm.com> (raw)
In-Reply-To: <20231119165721.9849-1-alexandru.elisei@arm.com>

Handle PAGE_FAULT_ON_ACCESS faults for huge pages in a similar way to
regular pages.

Signed-off-by: Alexandru Elisei <alexandru.elisei@arm.com>
---
 arch/arm64/include/asm/mte_tag_storage.h |  1 +
 arch/arm64/include/asm/pgtable.h         |  7 ++
 arch/arm64/mm/fault.c                    | 81 ++++++++++++++++++++++++
 include/linux/huge_mm.h                  |  2 +
 include/linux/pgtable.h                  |  5 ++
 mm/huge_memory.c                         |  4 +-
 mm/memory.c                              |  3 +
 7 files changed, 101 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/mte_tag_storage.h b/arch/arm64/include/asm/mte_tag_storage.h
index c70ced60a0cd..b97406d369ce 100644
--- a/arch/arm64/include/asm/mte_tag_storage.h
+++ b/arch/arm64/include/asm/mte_tag_storage.h
@@ -35,6 +35,7 @@ void free_tag_storage(struct page *page, int order);
 bool page_tag_storage_reserved(struct page *page);
 
 vm_fault_t handle_page_missing_tag_storage(struct vm_fault *vmf);
+vm_fault_t handle_huge_page_missing_tag_storage(struct vm_fault *vmf);
 #else
 static inline bool tag_storage_enabled(void)
 {
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 8cc135f1c112..1704411c096d 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -477,6 +477,13 @@ static inline vm_fault_t arch_do_page_fault_on_access(struct vm_fault *vmf)
 		return handle_page_missing_tag_storage(vmf);
 	return VM_FAULT_SIGBUS;
 }
+
+static inline vm_fault_t arch_do_huge_page_fault_on_access(struct vm_fault *vmf)
+{
+	if (tag_storage_enabled())
+		return handle_huge_page_missing_tag_storage(vmf);
+	return VM_FAULT_SIGBUS;
+}
 #endif /* CONFIG_ARCH_HAS_FAULT_ON_ACCESS */
 
 #define pmd_present_invalid(pmd)     (!!(pmd_val(pmd) & PMD_PRESENT_INVALID))
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index f5fa583acf18..6730a0812a24 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -1041,6 +1041,87 @@ vm_fault_t handle_page_missing_tag_storage(struct vm_fault *vmf)
 
 	return 0;
 
+out_retry:
+	put_page(page);
+	if (vmf->flags & FAULT_FLAG_VMA_LOCK)
+		vma_end_read(vma);
+	if (fault_flag_allow_retry_first(vmf->flags)) {
+		err = VM_FAULT_RETRY;
+	} else {
+		/* Replay the fault. */
+		err = 0;
+	}
+	return err;
+}
+
+vm_fault_t handle_huge_page_missing_tag_storage(struct vm_fault *vmf)
+{
+	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
+	struct vm_area_struct *vma = vmf->vma;
+	pmd_t old_pmd, new_pmd;
+	bool writable = false;
+	struct page *page;
+	vm_fault_t err;
+	int ret;
+
+	vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
+	if (unlikely(!pmd_same(vmf->orig_pmd, *vmf->pmd))) {
+		spin_unlock(vmf->ptl);
+		return 0;
+	}
+
+	old_pmd = vmf->orig_pmd;
+	new_pmd = pmd_modify(old_pmd, vma->vm_page_prot);
+
+	/*
+	 * Detect now whether the PMD could be writable; this information
+	 * is only valid while holding the PT lock.
+	 */
+	writable = pmd_write(new_pmd);
+	if (!writable && vma_wants_manual_pte_write_upgrade(vma) &&
+	    can_change_pmd_writable(vma, vmf->address, new_pmd))
+		writable = true;
+
+	page = vm_normal_page_pmd(vma, haddr, new_pmd);
+	if (!page)
+		goto out_map;
+
+	if (!(vma->vm_flags & VM_MTE))
+		goto out_map;
+
+	get_page(page);
+	vma_set_access_pid_bit(vma);
+
+	spin_unlock(vmf->ptl);
+	writable = false;
+
+	if (unlikely(is_migrate_isolate_page(page)))
+		goto out_retry;
+
+	ret = reserve_tag_storage(page, HPAGE_PMD_ORDER, GFP_HIGHUSER_MOVABLE);
+	if (ret)
+		goto out_retry;
+
+	put_page(page);
+
+	vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
+	if (unlikely(!pmd_same(old_pmd, *vmf->pmd))) {
+		spin_unlock(vmf->ptl);
+		return 0;
+	}
+
+out_map:
+	/* Restore the PMD */
+	new_pmd = pmd_modify(old_pmd, vma->vm_page_prot);
+	new_pmd = pmd_mkyoung(new_pmd);
+	if (writable)
+		new_pmd = pmd_mkwrite(new_pmd, vma);
+	set_pmd_at(vma->vm_mm, haddr, vmf->pmd, new_pmd);
+	update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
+	spin_unlock(vmf->ptl);
+
+	return 0;
+
 out_retry:
 	put_page(page);
 	if (vmf->flags & FAULT_FLAG_VMA_LOCK)
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index fa0350b0812a..bb84291f9231 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -36,6 +36,8 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		    pmd_t *pmd, unsigned long addr, pgprot_t newprot,
 		    unsigned long cp_flags);
+bool can_change_pmd_writable(struct vm_area_struct *vma, unsigned long addr,
+			     pmd_t pmd);
 
 vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write);
 vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write);
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index e2c761dd6c41..de45f475bf8d 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1473,6 +1473,11 @@ static inline vm_fault_t arch_do_page_fault_on_access(struct vm_fault *vmf)
 {
 	return VM_FAULT_SIGBUS;
 }
+
+static inline vm_fault_t arch_do_huge_page_fault_on_access(struct vm_fault *vmf)
+{
+	return VM_FAULT_SIGBUS;
+}
 #endif
 
 #endif /* CONFIG_MMU */
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 9beead961a65..d1402b43ea39 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1406,8 +1406,8 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf)
 	return VM_FAULT_FALLBACK;
 }
 
-static inline bool can_change_pmd_writable(struct vm_area_struct *vma,
-					   unsigned long addr, pmd_t pmd)
+inline bool can_change_pmd_writable(struct vm_area_struct *vma,
+				    unsigned long addr, pmd_t pmd)
 {
 	struct page *page;
 
diff --git a/mm/memory.c b/mm/memory.c
index a04a971200b9..46b926625503 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -5168,6 +5168,9 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
 			return 0;
 		}
 		if (pmd_trans_huge(vmf.orig_pmd) || pmd_devmap(vmf.orig_pmd)) {
+			if (fault_on_access_pmd(vmf.orig_pmd) && vma_is_accessible(vma))
+				return arch_do_huge_page_fault_on_access(&vmf);
+
 			if (pmd_protnone(vmf.orig_pmd) && vma_is_accessible(vma))
 				return do_huge_pmd_numa_page(&vmf);
 
-- 
2.42.1


  parent reply	other threads:[~2023-11-19 16:59 UTC|newest]

Thread overview: 98+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-11-19 16:56 [PATCH RFC v2 00/27] Add support for arm64 MTE dynamic tag storage reuse Alexandru Elisei
2023-11-19 16:56 ` [PATCH RFC v2 01/27] arm64: mte: Rework naming for tag manipulation functions Alexandru Elisei
2023-11-19 16:56 ` [PATCH RFC v2 02/27] arm64: mte: Rename __GFP_ZEROTAGS to __GFP_TAGGED Alexandru Elisei
2023-11-19 16:56 ` [PATCH RFC v2 03/27] mm: cma: Make CMA_ALLOC_SUCCESS/FAIL count the number of pages Alexandru Elisei
2023-11-19 16:56 ` [PATCH RFC v2 04/27] mm: migrate/mempolicy: Add hook to modify migration target gfp Alexandru Elisei
2023-11-25 10:03   ` Mike Rapoport
2023-11-27 11:52     ` Alexandru Elisei
2023-11-28  6:49       ` Mike Rapoport
2023-11-28 17:21         ` Alexandru Elisei
2023-11-19 16:56 ` [PATCH RFC v2 05/27] mm: page_alloc: Add an arch hook to allow prep_new_page() to fail Alexandru Elisei
2023-11-24 19:35   ` David Hildenbrand
2023-11-27 12:09     ` Alexandru Elisei
2023-11-28 16:57       ` David Hildenbrand
2023-11-28 17:17         ` Alexandru Elisei
2023-11-19 16:57 ` [PATCH RFC v2 06/27] mm: page_alloc: Allow an arch to hook early into free_pages_prepare() Alexandru Elisei
2023-11-24 19:36   ` David Hildenbrand
2023-11-27 13:03     ` Alexandru Elisei
2023-11-28 16:58       ` David Hildenbrand
2023-11-28 17:17         ` Alexandru Elisei
2023-11-19 16:57 ` [PATCH RFC v2 07/27] mm: page_alloc: Add an arch hook to filter MIGRATE_CMA allocations Alexandru Elisei
2023-11-19 16:57 ` [PATCH RFC v2 08/27] mm: page_alloc: Partially revert "mm: page_alloc: remove stale CMA guard code" Alexandru Elisei
2023-11-19 16:57 ` [PATCH RFC v2 09/27] mm: Allow an arch to hook into folio allocation when VMA is known Alexandru Elisei
2023-11-19 16:57 ` [PATCH RFC v2 10/27] mm: Call arch_swap_prepare_to_restore() before arch_swap_restore() Alexandru Elisei
2023-11-19 16:57 ` [PATCH RFC v2 11/27] arm64: mte: Reserve tag storage memory Alexandru Elisei
2023-11-29  8:44   ` Hyesoo Yu
2023-11-30 11:56     ` Alexandru Elisei
2023-12-03 12:14     ` Alexandru Elisei
2023-12-08  5:03       ` Hyesoo Yu
2023-12-11 14:45         ` Alexandru Elisei
2023-12-11 17:29   ` Rob Herring
2023-12-12 16:38     ` Alexandru Elisei
2023-12-12 18:44       ` Rob Herring
2023-12-13 13:04         ` Alexandru Elisei
2023-12-13 14:06           ` Rob Herring
2023-12-13 14:51             ` Alexandru Elisei
2023-12-13 17:22               ` Rob Herring
2023-12-13 17:44                 ` Alexandru Elisei
2023-12-13 20:30                   ` Rob Herring
2023-12-14 15:45                     ` Alexandru Elisei
2023-12-14 18:55                       ` Rob Herring
2023-12-18 10:59                         ` Alexandru Elisei
2023-11-19 16:57 ` [PATCH RFC v2 12/27] arm64: mte: Add tag storage pages to the MIGRATE_CMA migratetype Alexandru Elisei
2023-11-24 19:40   ` David Hildenbrand
2023-11-27 15:01     ` Alexandru Elisei
2023-11-28 17:03       ` David Hildenbrand
2023-11-29 10:44         ` Alexandru Elisei
2023-11-19 16:57 ` [PATCH RFC v2 13/27] arm64: mte: Make tag storage depend on ARCH_KEEP_MEMBLOCK Alexandru Elisei
2023-11-24 19:51   ` David Hildenbrand
2023-11-27 15:04     ` Alexandru Elisei
2023-11-28 17:05       ` David Hildenbrand
2023-11-29 10:46         ` Alexandru Elisei
2023-11-19 16:57 ` [PATCH RFC v2 14/27] arm64: mte: Disable dynamic tag storage management if HW KASAN is enabled Alexandru Elisei
2023-11-24 19:54   ` David Hildenbrand
2023-11-27 15:07     ` Alexandru Elisei
2023-11-28 17:05       ` David Hildenbrand
2023-11-19 16:57 ` [PATCH RFC v2 15/27] arm64: mte: Check that tag storage blocks are in the same zone Alexandru Elisei
2023-11-24 19:56   ` David Hildenbrand
2023-11-27 15:10     ` Alexandru Elisei
2023-11-29  8:57   ` Hyesoo Yu
2023-11-30 12:00     ` Alexandru Elisei
2023-12-08  5:27       ` Hyesoo Yu
2023-12-11 14:21         ` Alexandru Elisei
2023-11-19 16:57 ` [PATCH RFC v2 16/27] arm64: mte: Manage tag storage on page allocation Alexandru Elisei
2023-11-29  9:10   ` Hyesoo Yu
2023-11-29 13:33     ` Alexandru Elisei
2023-12-08  5:29       ` Hyesoo Yu
2023-11-19 16:57 ` [PATCH RFC v2 17/27] arm64: mte: Perform CMOs for tag blocks on tagged page allocation/free Alexandru Elisei
2023-11-19 16:57 ` [PATCH RFC v2 18/27] arm64: mte: Reserve tag block for the zero page Alexandru Elisei
2023-11-28 17:06   ` David Hildenbrand
2023-11-29 11:30     ` Alexandru Elisei
2023-11-29 13:13       ` David Hildenbrand
2023-11-29 13:41         ` Alexandru Elisei
2023-11-19 16:57 ` [PATCH RFC v2 19/27] mm: mprotect: Introduce PAGE_FAULT_ON_ACCESS for mprotect(PROT_MTE) Alexandru Elisei
2023-11-28 17:55   ` David Hildenbrand
2023-11-28 18:00     ` David Hildenbrand
2023-11-29 11:55     ` Alexandru Elisei
2023-11-29 12:48       ` David Hildenbrand
2023-11-29  9:27   ` Hyesoo Yu
2023-11-30 12:06     ` Alexandru Elisei
2023-11-30 12:49       ` David Hildenbrand
2023-11-30 13:32         ` Alexandru Elisei
2023-11-30 13:43           ` David Hildenbrand
2023-11-30 14:33             ` Alexandru Elisei
2023-11-30 14:39               ` David Hildenbrand
2023-11-19 16:57 ` Alexandru Elisei [this message]
2023-11-22  1:28   ` [PATCH RFC v2 20/27] mm: hugepage: Handle huge page fault on access Peter Collingbourne
2023-11-22  9:22     ` Alexandru Elisei
2023-11-28 17:56   ` David Hildenbrand
2023-11-29 11:56     ` Alexandru Elisei
2023-11-19 16:57 ` [PATCH RFC v2 21/27] mm: arm64: Handle tag storage pages mapped before mprotect(PROT_MTE) Alexandru Elisei
2023-11-28  5:39   ` Peter Collingbourne
2023-11-30 17:43     ` Alexandru Elisei
2023-11-19 16:57 ` [PATCH RFC v2 22/27] arm64: mte: swap: Handle tag restoring when missing tag storage Alexandru Elisei
2023-11-19 16:57 ` [PATCH RFC v2 23/27] arm64: mte: copypage: " Alexandru Elisei
2023-11-19 16:57 ` [PATCH RFC v2 24/27] arm64: mte: Handle fatal signal in reserve_tag_storage() Alexandru Elisei
2023-11-19 16:57 ` [PATCH RFC v2 25/27] KVM: arm64: Disable MTE if tag storage is enabled Alexandru Elisei
2023-11-19 16:57 ` [PATCH RFC v2 26/27] arm64: mte: Fast track reserving tag storage when the block is free Alexandru Elisei
2023-11-19 16:57 ` [PATCH RFC v2 27/27] arm64: mte: Enable dynamic tag storage reuse Alexandru Elisei

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=20231119165721.9849-21-alexandru.elisei@arm.com \
    --to=alexandru.elisei@arm.com \
    --cc=akpm@linux-foundation.org \
    --cc=anshuman.khandual@arm.com \
    --cc=arnd@arndb.de \
    --cc=bristot@redhat.com \
    --cc=bsegall@google.com \
    --cc=catalin.marinas@arm.com \
    --cc=david@redhat.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=eugenis@google.com \
    --cc=hughd@google.com \
    --cc=hyesoo.yu@samsung.com \
    --cc=james.morse@arm.com \
    --cc=juri.lelli@redhat.com \
    --cc=kcc@google.com \
    --cc=kvmarm@lists.linux.dev \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-trace-kernel@vger.kernel.org \
    --cc=maz@kernel.org \
    --cc=mgorman@suse.de \
    --cc=mhiramat@kernel.org \
    --cc=mingo@redhat.com \
    --cc=oliver.upton@linux.dev \
    --cc=pcc@google.com \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=rppt@kernel.org \
    --cc=steven.price@arm.com \
    --cc=suzuki.poulose@arm.com \
    --cc=vincent.guittot@linaro.org \
    --cc=vincenzo.frascino@arm.com \
    --cc=vschneid@redhat.com \
    --cc=will@kernel.org \
    --cc=yuzenghui@huawei.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 read-only IMAP folder(s) and NNTP newsgroup(s).