linux-kernel - [PATCH v4 12/21] 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: <20240710192250.4114783-13-Liam.Howlett@oracle.com>
Date: Wed, 10 Jul 2024 15:22:41 -0400
From: "Liam R. Howlett" <Liam.Howlett@...cle.com>
To: linux-mm@...ck.org, Andrew Morton <akpm@...ux-foundation.org>
Cc: 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>,
        Bert Karwatzki <spasswolf@....de>, Jiri Olsa <olsajiri@...il.com>,
        linux-kernel@...r.kernel.org, Kees Cook <kees@...nel.org>,
        "Liam R. Howlett" <Liam.Howlett@...cle.com>,
        Lorenzo Stoakes <lorenzo.stoakes@...cle.com>
Subject: [PATCH v4 12/21] mm/mmap: Track start and end of munmap in vma_munmap_struct

From: "Liam R. Howlett" <Liam.Howlett@...cle.com>

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/internal.h |  2 ++
 mm/mmap.c     | 35 ++++++++++++++++++++++++++++-------
 2 files changed, 30 insertions(+), 7 deletions(-)

diff --git a/mm/internal.h b/mm/internal.h
index a22547125c13..11e90c6e5a3e 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1493,6 +1493,8 @@ 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 */
diff --git a/mm/mmap.c b/mm/mmap.c
index 83cfe575c114..12a5ca6c979f 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -527,6 +527,8 @@ static inline void 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;
 }
 
 /*
@@ -2609,6 +2611,27 @@ 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
@@ -2630,13 +2653,7 @@ static 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 */
@@ -2698,6 +2715,8 @@ static 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
@@ -2760,6 +2779,8 @@ static 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. */
-- 
2.43.0