From: Bert Karwatzki <spasswolf@web.de>
To: "Liam R . Howlett" <Liam.Howlett@oracle.com>
Cc: Bert Karwatzki <spasswolf@web.de>,
Suren Baghdasaryan <surenb@google.com>,
Vlastimil Babka <vbabka@suse.cz>,
Lorenzo Stoakes <lstoakes@gmail.com>,
Matthew Wilcox <willy@infradead.org>,
sidhartha.kumar@oracle.com,
"Paul E . McKenney" <paulmck@kernel.org>,
Jiri Olsa <olsajiri@gmail.com>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
Andrew Morton <akpm@linux-foundation.org>,
Kees Cook <kees@kernel.org>, Jeff Xu <jeffxu@chromium.org>,
"Liam R . Howlett" <Liam.Howlett@Oracle.com>,
Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Subject: [PATCH v5.1 12/19] mm/mmap: Track start and end of munmap in vma_munmap_struct
Date: Fri, 16 Aug 2024 13:13:53 +0200 [thread overview]
Message-ID: <20240816111405.11793-13-spasswolf@web.de> (raw)
In-Reply-To: <20240816111405.11793-1-spasswolf@web.de>
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@Oracle.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.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
next prev parent reply other threads:[~2024-08-16 11:14 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-08-16 11:13 [PATCH v5.1 00/19] Rebase v5 patchset to next-20240816 Bert Karwatzki
2024-08-16 11:13 ` [PATCH v5.1 01/19] mm/mmap: Correctly position vma_iterator in __split_vma() Bert Karwatzki
2024-08-16 11:13 ` [PATCH v5.1 02/19] mm/mmap: Introduce abort_munmap_vmas() Bert Karwatzki
2024-08-16 11:13 ` [PATCH v5.1 03/19] mm/mmap: Introduce vmi_complete_munmap_vmas() Bert Karwatzki
2024-08-16 11:13 ` [PATCH v5.1 04/19] mm/mmap: Extract the gathering of vmas from do_vmi_align_munmap() Bert Karwatzki
2024-08-16 11:13 ` [PATCH v5.1 05/19] mm/mmap: Introduce vma_munmap_struct for use in munmap operations Bert Karwatzki
2024-08-16 11:13 ` [PATCH v5.1 06/19] mm/mmap: Change munmap to use vma_munmap_struct() for accounting and surrounding vmas Bert Karwatzki
2024-08-16 11:13 ` [PATCH v5.1 07/19] mm/mmap: Extract validate_mm() from vma_complete() Bert Karwatzki
2024-08-16 11:13 ` [PATCH v5.1 08/19] mm/mmap: Inline munmap operation in mmap_region() Bert Karwatzki
2024-08-16 11:13 ` [PATCH v5.1 09/19] mm/mmap: Expand mmap_region() munmap call Bert Karwatzki
2024-08-16 11:13 ` [PATCH v5.1 10/19] mm/mmap: Support vma == NULL in init_vma_munmap() Bert Karwatzki
2024-08-16 11:13 ` [PATCH v5.1 11/19] mm/mmap: Reposition vma iterator in mmap_region() Bert Karwatzki
2024-08-16 11:13 ` Bert Karwatzki [this message]
2024-08-16 11:13 ` [PATCH v5.1 13/19] mm/mmap: Clean up unmap_region() argument list Bert Karwatzki
2024-08-16 11:13 ` [PATCH v5.1 14/19] mm/mmap: Avoid zeroing vma tree in mmap_region() Bert Karwatzki
2024-08-16 11:13 ` [PATCH v5.1 15/19] mm/mmap: Use PHYS_PFN " Bert Karwatzki
2024-08-16 11:33 ` [PATCH v5.1 00/19] Rebase v5 patchset to next-20240816 Lorenzo Stoakes
2024-08-16 11:55 ` Bert Karwatzki
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=20240816111405.11793-13-spasswolf@web.de \
--to=spasswolf@web.de \
--cc=Liam.Howlett@oracle.com \
--cc=akpm@linux-foundation.org \
--cc=jeffxu@chromium.org \
--cc=kees@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lorenzo.stoakes@oracle.com \
--cc=lstoakes@gmail.com \
--cc=olsajiri@gmail.com \
--cc=paulmck@kernel.org \
--cc=sidhartha.kumar@oracle.com \
--cc=surenb@google.com \
--cc=vbabka@suse.cz \
--cc=willy@infradead.org \
/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