From: Rik van Riel <riel@surriel.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org,
kernel-team@meta.com, Dave Hansen <dave.hansen@linux.intel.com>,
Peter Zijlstra <peterz@infradead.org>,
Suren Baghdasaryan <surenb@google.com>,
Lorenzo Stoakes <ljs@kernel.org>,
Vlastimil Babka <vbabka@kernel.org>,
David Hildenbrand <david@kernel.org>,
"Liam R. Howlett" <liam@infradead.org>,
Mike Rapoport <rppt@kernel.org>, Michal Hocko <mhocko@suse.com>,
Jason Gunthorpe <jgg@ziepe.ca>,
John Hubbard <jhubbard@nvidia.com>, Peter Xu <peterx@redhat.com>,
Matthew Wilcox <willy@infradead.org>,
Usama Arif <usamaarif642@gmail.com>,
Rik van Riel <riel@surriel.com>,
Thomas Gleixner <tglx@kernel.org>, Ingo Molnar <mingo@redhat.com>,
Borislav Petkov <bp@alien8.de>,
x86@kernel.org, "H. Peter Anvin" <hpa@zytor.com>,
Usama Arif <usama.arif@linux.dev>
Subject: [PATCH RFC v4 01/12] x86/mm: add untagged_addr_remote_unlocked()
Date: Fri, 24 Jul 2026 18:29:23 -0400 [thread overview]
Message-ID: <20260724222934.1463812-2-riel@surriel.com> (raw)
In-Reply-To: <20260724222934.1463812-1-riel@surriel.com>
__access_remote_vm() reads another process's memory under the mmap lock. On
large machines running big multi-threaded applications, that lock is
contended between readers and writers: an mmap() or munmap() in one thread
stalls readers like /proc/PID/cmdline, /proc/PID/environ, or
process_vm_readv(), even though the memory they read is almost always
resident and reachable under the per-VMA lock instead.
Looking up the VMA first requires untagging the address.
untagged_addr_remote() asserts the mmap lock only because it reads
mm->context.untag_mask, which can race with the write in mm_enable_lam().
That mask changes only while the target is single-threaded, when it
enables LAM or resets it at exec. The read need not be stable: it is
already read locklessly elsewhere, and a remote untag is best-effort.
Add untagged_addr_remote_unlocked() for callers that have not taken the
mmap lock, and annotate access to mm->context.untag_mask with READ_ONCE()
and WRITE_ONCE() so the existing lockless reads are explicit and
KCSAN-clean. untagged_addr_remote() keeps its assertion and shares the same
code.
Assisted-by: Claude:claude-opus-4.8
Acked-by: Usama Arif <usama.arif@linux.dev>
Signed-off-by: Rik van Riel <riel@surriel.com>
---
arch/x86/include/asm/mmu_context.h | 6 +++---
arch/x86/include/asm/uaccess_64.h | 15 ++++++++++++---
arch/x86/kernel/process_64.c | 4 ++--
include/linux/uaccess.h | 7 +++++++
4 files changed, 24 insertions(+), 8 deletions(-)
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index ef5b507de34e..cee710f64658 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -100,18 +100,18 @@ static inline unsigned long mm_lam_cr3_mask(struct mm_struct *mm)
static inline void dup_lam(struct mm_struct *oldmm, struct mm_struct *mm)
{
mm->context.lam_cr3_mask = oldmm->context.lam_cr3_mask;
- mm->context.untag_mask = oldmm->context.untag_mask;
+ WRITE_ONCE(mm->context.untag_mask, READ_ONCE(oldmm->context.untag_mask));
}
#define mm_untag_mask mm_untag_mask
static inline unsigned long mm_untag_mask(struct mm_struct *mm)
{
- return mm->context.untag_mask;
+ return READ_ONCE(mm->context.untag_mask);
}
static inline void mm_reset_untag_mask(struct mm_struct *mm)
{
- mm->context.untag_mask = -1UL;
+ WRITE_ONCE(mm->context.untag_mask, -1UL);
}
#define arch_pgtable_dma_compat arch_pgtable_dma_compat
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 20de34cc9aa6..a095165eb648 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -39,18 +39,27 @@ static inline unsigned long __untagged_addr(unsigned long addr)
(__force __typeof__(addr))__untagged_addr(__addr); \
})
+/*
+ * mm->context.untag_mask changes only when the target enables LAM or execs,
+ * always single-threaded. An unlocked remote reader can race that; READ_ONCE
+ * keeps the value whole and the untag is best-effort.
+ */
static inline unsigned long __untagged_addr_remote(struct mm_struct *mm,
unsigned long addr)
{
- mmap_assert_locked(mm);
- return addr & (mm)->context.untag_mask;
+ return addr & READ_ONCE(mm->context.untag_mask);
}
-#define untagged_addr_remote(mm, addr) ({ \
+#define untagged_addr_remote_unlocked(mm, addr) ({ \
unsigned long __addr = (__force unsigned long)(addr); \
(__force __typeof__(addr))__untagged_addr_remote(mm, __addr); \
})
+#define untagged_addr_remote(mm, addr) ({ \
+ mmap_assert_locked(mm); \
+ untagged_addr_remote_unlocked(mm, addr); \
+})
+
#endif
#define valid_user_address(x) \
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index d44afbe005bb..9fa659117f38 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -814,7 +814,7 @@ static void enable_lam_func(void *__mm)
static void mm_enable_lam(struct mm_struct *mm)
{
mm->context.lam_cr3_mask = X86_CR3_LAM_U57;
- mm->context.untag_mask = ~GENMASK(62, 57);
+ WRITE_ONCE(mm->context.untag_mask, ~GENMASK(62, 57));
/*
* Even though the process must still be single-threaded at this
@@ -952,7 +952,7 @@ long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2)
#endif
#ifdef CONFIG_ADDRESS_MASKING
case ARCH_GET_UNTAG_MASK:
- return put_user(task->mm->context.untag_mask,
+ return put_user(mm_untag_mask(task->mm),
(unsigned long __user *)arg2);
case ARCH_ENABLE_TAGGED_ADDR:
return prctl_enable_tagged_addr(task->mm, arg2);
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index eddbbb65ccc4..7e6e4c89184c 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -34,6 +34,13 @@
})
#endif
+#ifndef untagged_addr_remote_unlocked
+#define untagged_addr_remote_unlocked(mm, addr) ({ \
+ (void)(mm); \
+ untagged_addr(addr); \
+})
+#endif
+
#ifdef masked_user_access_begin
#define can_do_masked_user_access() 1
# ifndef masked_user_write_access_begin
base-commit: 248951ddc14de84de3910f9b13f51491a8cd91df
--
2.53.0-Meta
next prev parent reply other threads:[~2026-07-24 22:40 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-07-24 22:29 [PATCH RFC v4 0/12] mm: use per-VMA lock in __access_remote_vm for improved monitoring reliability Rik van Riel
2026-07-24 22:29 ` Rik van Riel [this message]
2026-07-24 22:29 ` [PATCH RFC v4 02/12] riscv/mm: add untagged_addr_remote_unlocked() Rik van Riel
2026-07-24 22:29 ` [PATCH RFC v4 03/12] mm: rename get_user_page_vma_remote() to get_user_page_lookup_vma() Rik van Riel
2026-07-24 22:29 ` [PATCH RFC v4 04/12] mm/gup: let check_vma_flags() ignore selected VMA flags Rik van Riel
2026-07-24 22:29 ` [PATCH RFC v4 05/12] mm/gup: add get_user_page_vma() to fault in a page under a held lock Rik van Riel
2026-07-24 22:29 ` [PATCH RFC v4 06/12] mm: use per-VMA lock in __access_remote_vm() for single-VMA accesses Rik van Riel
2026-07-24 22:29 ` [PATCH RFC v4 07/12] mm: read remote strings under the per-VMA lock Rik van Riel
2026-07-24 22:29 ` [PATCH RFC v4 08/12] selftests/mm: cover /proc/pid/mem access to VM_PFNMAP memory Rik van Riel
2026-07-24 22:29 ` [PATCH RFC v4 09/12] mm/gup: build get_user_page_lookup_vma() on get_user_page_vma() Rik van Riel
2026-07-24 22:29 ` [PATCH RFC v4 10/12] mm/gup: pass an end address to follow_page_mask() and return a page count Rik van Riel
2026-07-24 22:29 ` [PATCH RFC v4 11/12] mm/gup: batch contiguous PTE-mapped large folios in follow_page_mask() Rik van Riel
2026-07-24 22:29 ` [PATCH RFC v4 12/12] selftests/mm: add a slow-GUP content and COW test for mTHP Rik van Riel
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=20260724222934.1463812-2-riel@surriel.com \
--to=riel@surriel.com \
--cc=akpm@linux-foundation.org \
--cc=bp@alien8.de \
--cc=dave.hansen@linux.intel.com \
--cc=david@kernel.org \
--cc=hpa@zytor.com \
--cc=jgg@ziepe.ca \
--cc=jhubbard@nvidia.com \
--cc=kernel-team@meta.com \
--cc=liam@infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=ljs@kernel.org \
--cc=mhocko@suse.com \
--cc=mingo@redhat.com \
--cc=peterx@redhat.com \
--cc=peterz@infradead.org \
--cc=rppt@kernel.org \
--cc=surenb@google.com \
--cc=tglx@kernel.org \
--cc=usama.arif@linux.dev \
--cc=usamaarif642@gmail.com \
--cc=vbabka@kernel.org \
--cc=willy@infradead.org \
--cc=x86@kernel.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