[PATCH RFC v4 01/12] x86/mm: add untagged_addr_remote_unlocked()

[Rik van Riel]

__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@xxxxxxxxx>
Signed-off-by: Rik van Riel <riel@xxxxxxxxxxx>
---
 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