| 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
| ||
|
Message-Id: <20221108011910.350887-3-mike.kravetz@oracle.com>
Date: Mon, 7 Nov 2022 17:19:10 -0800
From: Mike Kravetz <mike.kravetz@...cle.com>
To: linux-mm@...ck.org, linux-kernel@...r.kernel.org
Cc: Naoya Horiguchi <naoya.horiguchi@...ux.dev>,
David Hildenbrand <david@...hat.com>,
Axel Rasmussen <axelrasmussen@...gle.com>,
Mina Almasry <almasrymina@...gle.com>,
Peter Xu <peterx@...hat.com>,
Nadav Amit <nadav.amit@...il.com>,
Rik van Riel <riel@...riel.com>,
Vlastimil Babka <vbabka@...e.cz>,
Matthew Wilcox <willy@...radead.org>,
Andrew Morton <akpm@...ux-foundation.org>,
Mike Kravetz <mike.kravetz@...cle.com>
Subject: [PATCH v8 2/2] mm: remove zap_page_range and change callers to use zap_vma_range
zap_page_range was originally designed to unmap pages within an address
range that could span multiple vmas. However, today all callers of
zap_page_range pass a range entirely within a single vma. In addition,
the mmu notification call within zap_page range is not correct as it
should be vma specific.
Instead of fixing zap_page_range, change all callers to use zap_vma_range
as it is designed for ranges within a single vma.
Signed-off-by: Mike Kravetz <mike.kravetz@...cle.com>
---
arch/arm64/kernel/vdso.c | 4 ++--
arch/powerpc/kernel/vdso.c | 2 +-
arch/powerpc/platforms/book3s/vas-api.c | 2 +-
arch/powerpc/platforms/pseries/vas.c | 2 +-
arch/riscv/kernel/vdso.c | 4 ++--
arch/s390/kernel/vdso.c | 2 +-
arch/s390/mm/gmap.c | 2 +-
arch/x86/entry/vdso/vma.c | 2 +-
drivers/android/binder_alloc.c | 2 +-
include/linux/mm.h | 2 --
mm/memory.c | 30 -------------------------
mm/page-writeback.c | 2 +-
net/ipv4/tcp.c | 6 ++---
13 files changed, 15 insertions(+), 47 deletions(-)
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 99ae81ab91a7..05aa0c68b609 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -141,10 +141,10 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
unsigned long size = vma->vm_end - vma->vm_start;
if (vma_is_special_mapping(vma, vdso_info[VDSO_ABI_AA64].dm))
- zap_page_range(vma, vma->vm_start, size);
+ zap_vma_range(vma, vma->vm_start, size);
#ifdef CONFIG_COMPAT_VDSO
if (vma_is_special_mapping(vma, vdso_info[VDSO_ABI_AA32].dm))
- zap_page_range(vma, vma->vm_start, size);
+ zap_vma_range(vma, vma->vm_start, size);
#endif
}
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index 4abc01949702..69210ca35dc8 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -123,7 +123,7 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
unsigned long size = vma->vm_end - vma->vm_start;
if (vma_is_special_mapping(vma, &vvar_spec))
- zap_page_range(vma, vma->vm_start, size);
+ zap_vma_range(vma, vma->vm_start, size);
}
mmap_read_unlock(mm);
diff --git a/arch/powerpc/platforms/book3s/vas-api.c b/arch/powerpc/platforms/book3s/vas-api.c
index 40f5ae5e1238..475925723981 100644
--- a/arch/powerpc/platforms/book3s/vas-api.c
+++ b/arch/powerpc/platforms/book3s/vas-api.c
@@ -414,7 +414,7 @@ static vm_fault_t vas_mmap_fault(struct vm_fault *vmf)
/*
* When the LPAR lost credits due to core removal or during
* migration, invalidate the existing mapping for the current
- * paste addresses and set windows in-active (zap_page_range in
+ * paste addresses and set windows in-active (zap_vma_range in
* reconfig_close_windows()).
* New mapping will be done later after migration or new credits
* available. So continue to receive faults if the user space
diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c
index 4ad6e510d405..b70afaa5e399 100644
--- a/arch/powerpc/platforms/pseries/vas.c
+++ b/arch/powerpc/platforms/pseries/vas.c
@@ -760,7 +760,7 @@ static int reconfig_close_windows(struct vas_caps *vcap, int excess_creds,
* is done before the original mmap() and after the ioctl.
*/
if (vma)
- zap_page_range(vma, vma->vm_start,
+ zap_vma_range(vma, vma->vm_start,
vma->vm_end - vma->vm_start);
mmap_write_unlock(task_ref->mm);
diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c
index 123d05255fcf..47b767215d15 100644
--- a/arch/riscv/kernel/vdso.c
+++ b/arch/riscv/kernel/vdso.c
@@ -127,10 +127,10 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
unsigned long size = vma->vm_end - vma->vm_start;
if (vma_is_special_mapping(vma, vdso_info.dm))
- zap_page_range(vma, vma->vm_start, size);
+ zap_vma_range(vma, vma->vm_start, size);
#ifdef CONFIG_COMPAT
if (vma_is_special_mapping(vma, compat_vdso_info.dm))
- zap_page_range(vma, vma->vm_start, size);
+ zap_vma_range(vma, vma->vm_start, size);
#endif
}
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index 119328e1e2b3..af50c3cefe45 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -78,7 +78,7 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
if (!vma_is_special_mapping(vma, &vvar_mapping))
continue;
- zap_page_range(vma, vma->vm_start, size);
+ zap_vma_range(vma, vma->vm_start, size);
break;
}
mmap_read_unlock(mm);
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 02d15c8dc92e..32f1d4a3d241 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -723,7 +723,7 @@ void gmap_discard(struct gmap *gmap, unsigned long from, unsigned long to)
if (is_vm_hugetlb_page(vma))
continue;
size = min(to - gaddr, PMD_SIZE - (gaddr & ~PMD_MASK));
- zap_page_range(vma, vmaddr, size);
+ zap_vma_range(vma, vmaddr, size);
}
mmap_read_unlock(gmap->mm);
}
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index d45c5fcfeac2..b3c269cf28d0 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -134,7 +134,7 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
unsigned long size = vma->vm_end - vma->vm_start;
if (vma_is_special_mapping(vma, &vvar_mapping))
- zap_page_range(vma, vma->vm_start, size);
+ zap_vma_range(vma, vma->vm_start, size);
}
mmap_read_unlock(mm);
diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 1c39cfce32fa..063a9b4a6c02 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -1012,7 +1012,7 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
if (vma) {
trace_binder_unmap_user_start(alloc, index);
- zap_page_range(vma, page_addr, PAGE_SIZE);
+ zap_vma_range(vma, page_addr, PAGE_SIZE);
trace_binder_unmap_user_end(alloc, index);
}
diff --git a/include/linux/mm.h b/include/linux/mm.h
index d205bcd9cd2e..16052a628ab2 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1838,8 +1838,6 @@ struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
unsigned long size);
-void zap_page_range(struct vm_area_struct *vma, unsigned long address,
- unsigned long size);
void zap_vma_range(struct vm_area_struct *vma, unsigned long address,
unsigned long size);
void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt,
diff --git a/mm/memory.c b/mm/memory.c
index af3a4724b464..a9b2aa1149b2 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1686,36 +1686,6 @@ void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt,
mmu_notifier_invalidate_range_end(&range);
}
-/**
- * zap_page_range - remove user pages in a given range
- * @vma: vm_area_struct holding the applicable pages
- * @start: starting address of pages to zap
- * @size: number of bytes to zap
- *
- * Caller must protect the VMA list
- */
-void zap_page_range(struct vm_area_struct *vma, unsigned long start,
- unsigned long size)
-{
- struct maple_tree *mt = &vma->vm_mm->mm_mt;
- unsigned long end = start + size;
- struct mmu_notifier_range range;
- struct mmu_gather tlb;
- MA_STATE(mas, mt, vma->vm_end, vma->vm_end);
-
- lru_add_drain();
- mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
- start, start + size);
- tlb_gather_mmu(&tlb, vma->vm_mm);
- update_hiwater_rss(vma->vm_mm);
- mmu_notifier_invalidate_range_start(&range);
- do {
- unmap_single_vma(&tlb, vma, start, range.end, NULL);
- } while ((vma = mas_find(&mas, end - 1)) != NULL);
- mmu_notifier_invalidate_range_end(&range);
- tlb_finish_mmu(&tlb);
-}
-
/**
* __zap_page_range_single - remove user pages in a given range
* @vma: vm_area_struct holding the applicable pages
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 7e9d8d857ecc..dbfa8b2062fc 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2601,7 +2601,7 @@ void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb)
*
* The caller must hold lock_page_memcg(). Most callers have the folio
* locked. A few have the folio blocked from truncation through other
- * means (eg zap_page_range() has it mapped and is holding the page table
+ * means (eg zap_vma_range() has it mapped and is holding the page table
* lock). This can also be called from mark_buffer_dirty(), which I
* cannot prove is always protected against truncate.
*/
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index de8f0cd7cb32..dea1d72ae4e2 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2092,7 +2092,7 @@ static int tcp_zerocopy_vm_insert_batch_error(struct vm_area_struct *vma,
maybe_zap_len = total_bytes_to_map - /* All bytes to map */
*length + /* Mapped or pending */
(pages_remaining * PAGE_SIZE); /* Failed map. */
- zap_page_range(vma, *address, maybe_zap_len);
+ zap_vma_range(vma, *address, maybe_zap_len);
err = 0;
}
@@ -2100,7 +2100,7 @@ static int tcp_zerocopy_vm_insert_batch_error(struct vm_area_struct *vma,
unsigned long leftover_pages = pages_remaining;
int bytes_mapped;
- /* We called zap_page_range, try to reinsert. */
+ /* We called zap_vma_range, try to reinsert. */
err = vm_insert_pages(vma, *address,
pending_pages,
&pages_remaining);
@@ -2234,7 +2234,7 @@ static int tcp_zerocopy_receive(struct sock *sk,
total_bytes_to_map = avail_len & ~(PAGE_SIZE - 1);
if (total_bytes_to_map) {
if (!(zc->flags & TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT))
- zap_page_range(vma, address, total_bytes_to_map);
+ zap_vma_range(vma, address, total_bytes_to_map);
zc->length = total_bytes_to_map;
zc->recv_skip_hint = 0;
} else {
--
2.37.3
Powered by blists - more mailing lists