lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20220603053738.1218681-6-ruansy.fnst@fujitsu.com>
Date:   Fri, 3 Jun 2022 13:37:29 +0800
From:   Shiyang Ruan <ruansy.fnst@...itsu.com>
To:     <linux-kernel@...r.kernel.org>, <linux-xfs@...r.kernel.org>,
        <nvdimm@...ts.linux.dev>, <linux-mm@...ck.org>,
        <linux-fsdevel@...r.kernel.org>
CC:     <djwong@...nel.org>, <dan.j.williams@...el.com>,
        <david@...morbit.com>, <hch@...radead.org>,
        <akpm@...ux-foundation.org>, <jane.chu@...cle.com>,
        <rgoldwyn@...e.de>, <viro@...iv.linux.org.uk>,
        <willy@...radead.org>, <naoya.horiguchi@....com>,
        <linmiaohe@...wei.com>, Christoph Hellwig <hch@....de>
Subject: [PATCH v2 05/14] mm: Introduce mf_dax_kill_procs() for fsdax case

This new function is a variant of mf_generic_kill_procs that accepts a
file, offset pair instead of a struct to support multiple files sharing
a DAX mapping.  It is intended to be called by the file systems as part
of the memory_failure handler after the file system performed a reverse
mapping from the storage address to the file and file offset.

Signed-off-by: Shiyang Ruan <ruansy.fnst@...itsu.com>
Reviewed-by: Dan Williams <dan.j.williams@...el.com>
Reviewed-by: Christoph Hellwig <hch@....de>
Reviewed-by: Darrick J. Wong <djwong@...nel.org>
Reviewed-by: Miaohe Lin <linmiaohe@...wei.com>
---
 include/linux/mm.h  |  2 +
 mm/memory-failure.c | 96 ++++++++++++++++++++++++++++++++++++++++-----
 2 files changed, 88 insertions(+), 10 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 8a96197b9afd..623c2ee8330a 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3250,6 +3250,8 @@ enum mf_flags {
 	MF_UNPOISON = 1 << 4,
 	MF_NO_RETRY = 1 << 5,
 };
+int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index,
+		      unsigned long count, int mf_flags);
 extern int memory_failure(unsigned long pfn, int flags);
 extern void memory_failure_queue(unsigned long pfn, int flags);
 extern void memory_failure_queue_kick(int cpu);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index a9d93c30a1e4..5d015e1387bd 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -301,10 +301,9 @@ void shake_page(struct page *p)
 }
 EXPORT_SYMBOL_GPL(shake_page);
 
-static unsigned long dev_pagemap_mapping_shift(struct page *page,
-		struct vm_area_struct *vma)
+static unsigned long dev_pagemap_mapping_shift(struct vm_area_struct *vma,
+		unsigned long address)
 {
-	unsigned long address = vma_address(page, vma);
 	unsigned long ret = 0;
 	pgd_t *pgd;
 	p4d_t *p4d;
@@ -344,10 +343,14 @@ static unsigned long dev_pagemap_mapping_shift(struct page *page,
 /*
  * Schedule a process for later kill.
  * Uses GFP_ATOMIC allocations to avoid potential recursions in the VM.
+ *
+ * Notice: @fsdax_pgoff is used only when @p is a fsdax page.
+ *   In other cases, such as anonymous and file-backend page, the address to be
+ *   killed can be caculated by @p itself.
  */
 static void add_to_kill(struct task_struct *tsk, struct page *p,
-		       struct vm_area_struct *vma,
-		       struct list_head *to_kill)
+			pgoff_t fsdax_pgoff, struct vm_area_struct *vma,
+			struct list_head *to_kill)
 {
 	struct to_kill *tk;
 
@@ -358,9 +361,15 @@ static void add_to_kill(struct task_struct *tsk, struct page *p,
 	}
 
 	tk->addr = page_address_in_vma(p, vma);
-	if (is_zone_device_page(p))
-		tk->size_shift = dev_pagemap_mapping_shift(p, vma);
-	else
+	if (is_zone_device_page(p)) {
+		/*
+		 * Since page->mapping is not used for fsdax, we need
+		 * calculate the address based on the vma.
+		 */
+		if (p->pgmap->type == MEMORY_DEVICE_FS_DAX)
+			tk->addr = vma_pgoff_address(fsdax_pgoff, 1, vma);
+		tk->size_shift = dev_pagemap_mapping_shift(vma, tk->addr);
+	} else
 		tk->size_shift = page_shift(compound_head(p));
 
 	/*
@@ -509,7 +518,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 			if (!page_mapped_in_vma(page, vma))
 				continue;
 			if (vma->vm_mm == t->mm)
-				add_to_kill(t, page, vma, to_kill);
+				add_to_kill(t, page, 0, vma, to_kill);
 		}
 	}
 	read_unlock(&tasklist_lock);
@@ -545,13 +554,41 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 			 * to be informed of all such data corruptions.
 			 */
 			if (vma->vm_mm == t->mm)
-				add_to_kill(t, page, vma, to_kill);
+				add_to_kill(t, page, 0, vma, to_kill);
 		}
 	}
 	read_unlock(&tasklist_lock);
 	i_mmap_unlock_read(mapping);
 }
 
+#ifdef CONFIG_FS_DAX
+/*
+ * Collect processes when the error hit a fsdax page.
+ */
+static void collect_procs_fsdax(struct page *page,
+		struct address_space *mapping, pgoff_t pgoff,
+		struct list_head *to_kill)
+{
+	struct vm_area_struct *vma;
+	struct task_struct *tsk;
+
+	i_mmap_lock_read(mapping);
+	read_lock(&tasklist_lock);
+	for_each_process(tsk) {
+		struct task_struct *t = task_early_kill(tsk, true);
+
+		if (!t)
+			continue;
+		vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) {
+			if (vma->vm_mm == t->mm)
+				add_to_kill(t, page, pgoff, vma, to_kill);
+		}
+	}
+	read_unlock(&tasklist_lock);
+	i_mmap_unlock_read(mapping);
+}
+#endif /* CONFIG_FS_DAX */
+
 /*
  * Collect the processes who have the corrupted page mapped to kill.
  */
@@ -1591,6 +1628,45 @@ static int mf_generic_kill_procs(unsigned long long pfn, int flags,
 	return rc;
 }
 
+#ifdef CONFIG_FS_DAX
+/**
+ * mf_dax_kill_procs - Collect and kill processes who are using this file range
+ * @mapping:	address_space of the file in use
+ * @index:	start pgoff of the range within the file
+ * @count:	length of the range, in unit of PAGE_SIZE
+ * @mf_flags:	memory failure flags
+ */
+int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index,
+		unsigned long count, int mf_flags)
+{
+	LIST_HEAD(to_kill);
+	dax_entry_t cookie;
+	struct page *page;
+	size_t end = index + count;
+
+	mf_flags |= MF_ACTION_REQUIRED | MF_MUST_KILL;
+
+	for (; index < end; index++) {
+		page = NULL;
+		cookie = dax_lock_mapping_entry(mapping, index, &page);
+		if (!cookie)
+			return -EBUSY;
+		if (!page)
+			goto unlock;
+
+		SetPageHWPoison(page);
+
+		collect_procs_fsdax(page, mapping, index, &to_kill);
+		unmap_and_kill(&to_kill, page_to_pfn(page), mapping,
+				index, mf_flags);
+unlock:
+		dax_unlock_mapping_entry(mapping, index, cookie);
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mf_dax_kill_procs);
+#endif /* CONFIG_FS_DAX */
+
 /*
  * Called from hugetlb code with hugetlb_lock held.
  *
-- 
2.36.1



Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ