| 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: <20230918230202.254631-8-mike.kravetz@oracle.com>
Date: Mon, 18 Sep 2023 16:01:59 -0700
From: Mike Kravetz <mike.kravetz@...cle.com>
To: linux-mm@...ck.org, linux-kernel@...r.kernel.org
Cc: Muchun Song <songmuchun@...edance.com>,
Joao Martins <joao.m.martins@...cle.com>,
Oscar Salvador <osalvador@...e.de>,
David Hildenbrand <david@...hat.com>,
Miaohe Lin <linmiaohe@...wei.com>,
David Rientjes <rientjes@...gle.com>,
Anshuman Khandual <anshuman.khandual@....com>,
Naoya Horiguchi <naoya.horiguchi@...ux.dev>,
Barry Song <21cnbao@...il.com>, Michal Hocko <mhocko@...e.com>,
Matthew Wilcox <willy@...radead.org>,
Xiongchun Duan <duanxiongchun@...edance.com>,
Andrew Morton <akpm@...ux-foundation.org>,
Mike Kravetz <mike.kravetz@...cle.com>
Subject: [PATCH v4 7/8] hugetlb: batch TLB flushes when freeing vmemmap
From: Joao Martins <joao.m.martins@...cle.com>
Now that a list of pages is deduplicated at once, the TLB
flush can be batched for all vmemmap pages that got remapped.
Expand the flags field value to pass whether to skip the TLB flush
on remap of the PTE.
The TLB flush is global as we don't have guarantees from caller
that the set of folios is contiguous, or to add complexity in
composing a list of kVAs to flush.
Modified by Mike Kravetz to perform TLB flush on single folio if an
error is encountered.
Signed-off-by: Joao Martins <joao.m.martins@...cle.com>
Signed-off-by: Mike Kravetz <mike.kravetz@...cle.com>
---
mm/hugetlb_vmemmap.c | 44 +++++++++++++++++++++++++++++++++-----------
1 file changed, 33 insertions(+), 11 deletions(-)
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index e8bc2f7567db..a6c356acb1fc 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -37,6 +37,7 @@ struct vmemmap_remap_walk {
unsigned long reuse_addr;
struct list_head *vmemmap_pages;
#define VMEMMAP_SPLIT_NO_TLB_FLUSH BIT(0)
+#define VMEMMAP_REMAP_NO_TLB_FLUSH BIT(1)
unsigned long flags;
};
@@ -211,7 +212,7 @@ static int vmemmap_remap_range(unsigned long start, unsigned long end,
return ret;
} while (pgd++, addr = next, addr != end);
- if (walk->remap_pte)
+ if (walk->remap_pte && !(walk->flags & VMEMMAP_REMAP_NO_TLB_FLUSH))
flush_tlb_kernel_range(start, end);
return 0;
@@ -355,19 +356,21 @@ static int vmemmap_remap_split(unsigned long start, unsigned long end,
* @reuse: reuse address.
* @vmemmap_pages: list to deposit vmemmap pages to be freed. It is callers
* responsibility to free pages.
+ * @flags: modifications to vmemmap_remap_walk flags
*
* Return: %0 on success, negative error code otherwise.
*/
static int vmemmap_remap_free(unsigned long start, unsigned long end,
unsigned long reuse,
- struct list_head *vmemmap_pages)
+ struct list_head *vmemmap_pages,
+ unsigned long flags)
{
int ret;
struct vmemmap_remap_walk walk = {
.remap_pte = vmemmap_remap_pte,
.reuse_addr = reuse,
.vmemmap_pages = vmemmap_pages,
- .flags = 0,
+ .flags = flags,
};
int nid = page_to_nid((struct page *)reuse);
gfp_t gfp_mask = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN;
@@ -628,7 +631,8 @@ static bool vmemmap_should_optimize(const struct hstate *h, const struct page *h
static int __hugetlb_vmemmap_optimize(const struct hstate *h,
struct page *head,
- struct list_head *vmemmap_pages)
+ struct list_head *vmemmap_pages,
+ unsigned long flags)
{
int ret = 0;
unsigned long vmemmap_start = (unsigned long)head, vmemmap_end;
@@ -639,6 +643,18 @@ static int __hugetlb_vmemmap_optimize(const struct hstate *h,
return ret;
static_branch_inc(&hugetlb_optimize_vmemmap_key);
+ /*
+ * Very Subtle
+ * If VMEMMAP_REMAP_NO_TLB_FLUSH is set, TLB flushing is not performed
+ * immediately after remapping. As a result, subsequent accesses
+ * and modifications to struct pages associated with the hugetlb
+ * page could be to the OLD struct pages. Set the vmemmap optimized
+ * flag here so that it is copied to the new head page. This keeps
+ * the old and new struct pages in sync.
+ * If there is an error during optimization, we will immediately FLUSH
+ * the TLB and clear the flag below.
+ */
+ SetHPageVmemmapOptimized(head);
vmemmap_end = vmemmap_start + hugetlb_vmemmap_size(h);
vmemmap_reuse = vmemmap_start;
@@ -650,11 +666,12 @@ static int __hugetlb_vmemmap_optimize(const struct hstate *h,
* mapping the range to vmemmap_pages list so that they can be freed by
* the caller.
*/
- ret = vmemmap_remap_free(vmemmap_start, vmemmap_end, vmemmap_reuse, vmemmap_pages);
- if (ret)
+ ret = vmemmap_remap_free(vmemmap_start, vmemmap_end, vmemmap_reuse,
+ vmemmap_pages, flags);
+ if (ret) {
static_branch_dec(&hugetlb_optimize_vmemmap_key);
- else
- SetHPageVmemmapOptimized(head);
+ ClearHPageVmemmapOptimized(head);
+ }
return ret;
}
@@ -673,7 +690,7 @@ void hugetlb_vmemmap_optimize(const struct hstate *h, struct page *head)
{
LIST_HEAD(vmemmap_pages);
- __hugetlb_vmemmap_optimize(h, head, &vmemmap_pages);
+ __hugetlb_vmemmap_optimize(h, head, &vmemmap_pages, 0);
free_vmemmap_page_list(&vmemmap_pages);
}
@@ -708,19 +725,24 @@ void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_l
list_for_each_entry(folio, folio_list, lru) {
int ret = __hugetlb_vmemmap_optimize(h, &folio->page,
- &vmemmap_pages);
+ &vmemmap_pages,
+ VMEMMAP_REMAP_NO_TLB_FLUSH);
/*
* Pages to be freed may have been accumulated. If we
* encounter an ENOMEM, free what we have and try again.
*/
if (ret == -ENOMEM && !list_empty(&vmemmap_pages)) {
+ flush_tlb_all();
free_vmemmap_page_list(&vmemmap_pages);
INIT_LIST_HEAD(&vmemmap_pages);
- __hugetlb_vmemmap_optimize(h, &folio->page, &vmemmap_pages);
+ __hugetlb_vmemmap_optimize(h, &folio->page,
+ &vmemmap_pages,
+ VMEMMAP_REMAP_NO_TLB_FLUSH);
}
}
+ flush_tlb_all();
free_vmemmap_page_list(&vmemmap_pages);
}
--
2.41.0
Powered by blists - more mailing lists