linux-kernel - [PATCH v5.1 12/19] mm/mmap: Track start and end of munmap in vma_munmap

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: <20240816111405.11793-13-spasswolf@web.de>
Date: Fri, 16 Aug 2024 13:13:53 +0200
From: Bert Karwatzki <spasswolf@....de>
To: "Liam R . Howlett" <Liam.Howlett@...cle.com>
Cc: Bert Karwatzki <spasswolf@....de>,
	Suren Baghdasaryan <surenb@...gle.com>,
	Vlastimil Babka <vbabka@...e.cz>,
	Lorenzo Stoakes <lstoakes@...il.com>,
	Matthew Wilcox <willy@...radead.org>,
	sidhartha.kumar@...cle.com,
	"Paul E . McKenney" <paulmck@...nel.org>,
	Jiri Olsa <olsajiri@...il.com>,
	linux-kernel@...r.kernel.org,
	linux-mm@...ck.org,
	Andrew Morton <akpm@...ux-foundation.org>,
	Kees Cook <kees@...nel.org>,
	Jeff Xu <jeffxu@...omium.org>,
	"Liam R . Howlett" <Liam.Howlett@...cle.com>,
	Lorenzo Stoakes <lorenzo.stoakes@...cle.com>
Subject: [PATCH v5.1 12/19] mm/mmap: Track start and end of munmap in vma_munmap_struct

Set the start and end address for munmap when the prev and next are
gathered.  This is needed to avoid incorrect addresses being used during
the vms_complete_munmap_vmas() function if the prev/next vma are
expanded.

Add a new helper vms_complete_pte_clear(), which is needed later and
will avoid growing the argument list to unmap_region() beyond the 9 it
already has.

Signed-off-by: Liam R. Howlett <Liam.Howlett@...cle.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@...cle.com>
---
 mm/vma.c | 38 ++++++++++++++++++++++++++++++--------
 mm/vma.h |  5 +++++
 2 files changed, 35 insertions(+), 8 deletions(-)

diff --git a/mm/vma.c b/mm/vma.c
index a5ca42b7161b..e106d412c4c3 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -373,6 +373,8 @@ init_vma_munmap(struct vma_munmap_struct *vms,
 	vms->vma_count = 0;
 	vms->nr_pages = vms->locked_vm = vms->nr_accounted = 0;
 	vms->exec_vm = vms->stack_vm = vms->data_vm = 0;
+	vms->unmap_start = FIRST_USER_ADDRESS;
+	vms->unmap_end = USER_PGTABLES_CEILING;
 }

 /*
@@ -684,7 +686,7 @@ void vma_complete(struct vma_prepare *vp,
  *
  * Reattach any detached vmas and free up the maple tree used to track the vmas.
  */
-static inline void abort_munmap_vmas(struct ma_state *mas_detach)
+void abort_munmap_vmas(struct ma_state *mas_detach)
 {
 	struct vm_area_struct *vma;

@@ -695,6 +697,28 @@ static inline void abort_munmap_vmas(struct ma_state *mas_detach)
 	__mt_destroy(mas_detach->tree);
 }

+static void vms_complete_pte_clear(struct vma_munmap_struct *vms,
+		struct ma_state *mas_detach, bool mm_wr_locked)
+{
+	struct mmu_gather tlb;
+
+	/*
+	 * We can free page tables without write-locking mmap_lock because VMAs
+	 * were isolated before we downgraded mmap_lock.
+	 */
+	mas_set(mas_detach, 1);
+	lru_add_drain();
+	tlb_gather_mmu(&tlb, vms->mm);
+	update_hiwater_rss(vms->mm);
+	unmap_vmas(&tlb, mas_detach, vms->vma, vms->start, vms->end,
+		   vms->vma_count, mm_wr_locked);
+	mas_set(mas_detach, 1);
+	/* start and end may be different if there is no prev or next vma. */
+	free_pgtables(&tlb, mas_detach, vms->vma, vms->unmap_start,
+		      vms->unmap_end, mm_wr_locked);
+	tlb_finish_mmu(&tlb);
+}
+
 /*
  * vms_complete_munmap_vmas() - Finish the munmap() operation
  * @vms: The vma munmap struct
@@ -717,13 +741,7 @@ void vms_complete_munmap_vmas(struct vma_munmap_struct *vms,
 	if (vms->unlock)
 		mmap_write_downgrade(mm);

-	/*
-	 * We can free page tables without write-locking mmap_lock because VMAs
-	 * were isolated before we downgraded mmap_lock.
-	 */
-	mas_set(mas_detach, 1);
-	unmap_region(mm, mas_detach, vms->vma, vms->prev, vms->next,
-		     vms->start, vms->end, vms->vma_count, !vms->unlock);
+	vms_complete_pte_clear(vms, mas_detach, !vms->unlock);
 	/* Update high watermark before we lower total_vm */
 	update_hiwater_vm(mm);
 	/* Stat accounting */
@@ -785,6 +803,8 @@ int vms_gather_munmap_vmas(struct vma_munmap_struct *vms,
 			goto start_split_failed;
 	}
 	vms->prev = vma_prev(vms->vmi);
+	if (vms->prev)
+		vms->unmap_start = vms->prev->vm_end;

 	/*
 	 * Detach a range of VMAs from the mm. Using next as a temp variable as
@@ -846,6 +866,8 @@ int vms_gather_munmap_vmas(struct vma_munmap_struct *vms,
 	}

 	vms->next = vma_next(vms->vmi);
+	if (vms->next)
+		vms->unmap_end = vms->next->vm_start;

 #if defined(CONFIG_DEBUG_VM_MAPLE_TREE)
 	/* Make sure no VMAs are about to be lost. */
diff --git a/mm/vma.h b/mm/vma.h
index 8b2401f93c74..b857e7dc4bfe 100644
--- a/mm/vma.h
+++ b/mm/vma.h
@@ -33,6 +33,8 @@ struct vma_munmap_struct {
 	struct list_head *uf;		/* Userfaultfd list_head */
 	unsigned long start;		/* Aligned start addr (inclusive) */
 	unsigned long end;		/* Aligned end addr (exclusive) */
+	unsigned long unmap_start;	/* Unmap PTE start */
+	unsigned long unmap_end;	/* Unmap PTE end */
 	int vma_count;			/* Number of vmas that will be removed */
 	unsigned long nr_pages;		/* Number of pages being removed */
 	unsigned long locked_vm;	/* Number of locked pages */
@@ -54,6 +56,9 @@ void validate_mm(struct mm_struct *mm);
 #define validate_mm(mm) do { } while (0)
 #endif

+/* Required for mmap_region() */
+void abort_munmap_vmas(struct ma_state *mas_detach);
+
 /* Required for expand_downwards(). */
 void anon_vma_interval_tree_pre_update_vma(struct vm_area_struct *vma);

--
2.45.2