linux-um archives
 help / color / mirror / Atom feed
* [PATCH] um: fix _nofault accesses
@ 2025-04-04 15:05 Johannes Berg
  2025-04-04 21:12 ` Nathan Chancellor
  0 siblings, 1 reply; 2+ messages in thread
From: Johannes Berg @ 2025-04-04 15:05 UTC (permalink / raw)
  To: linux-um; +Cc: Johannes Berg, Nathan Chancellor

From: Johannes Berg <johannes.berg@intel.com>

Nathan reported [1] that when built with clang, the um kernel
crashes pretty much immediately. This turned out to be an issue
with the inline assembly I had added, when clang used %rax/%eax
for both operands. Reorder it so current->thread.segv_continue
is written first, and then the lifetime of _faulted won't have
overlap with the lifetime of segv_continue.

In the email thread Benjamin also pointed out that current->mm
is only NULL for true kernel tasks, but we could do this for a
userspace task, so the current->thread.segv_continue logic must
be lifted out of the mm==NULL check.

Finally, while looking at this, put a barrier() so the NULL
assignment to thread.segv_continue cannot be reorder before
the possibly faulting operation.

Reported-by: Nathan Chancellor <nathan@kernel.org>
Closes: https://lore.kernel.org/r/20250402221254.GA384@ax162 [1]
Fixes: d1d7f01f7cd3 ("um: mark rodata read-only and implement _nofault accesses")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 arch/um/include/asm/uaccess.h            |  2 ++
 arch/um/kernel/trap.c                    | 26 ++++++++++++------------
 arch/x86/um/shared/sysdep/faultinfo_32.h |  2 +-
 arch/x86/um/shared/sysdep/faultinfo_64.h |  2 +-
 4 files changed, 17 insertions(+), 15 deletions(-)

diff --git a/arch/um/include/asm/uaccess.h b/arch/um/include/asm/uaccess.h
index 3a08f9029a3f..1c6e0ae41b0c 100644
--- a/arch/um/include/asm/uaccess.h
+++ b/arch/um/include/asm/uaccess.h
@@ -55,6 +55,7 @@ do {									\
 		goto err_label;						\
 	}								\
 	*((type *)dst) = get_unaligned((type *)(src));			\
+	barrier();							\
 	current->thread.segv_continue = NULL;				\
 } while (0)
 
@@ -66,6 +67,7 @@ do {									\
 	if (__faulted)							\
 		goto err_label;						\
 	put_unaligned(*((type *)src), (type *)(dst));			\
+	barrier();							\
 	current->thread.segv_continue = NULL;				\
 } while (0)
 
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index ce073150dc20..ef2272e92a43 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -225,20 +225,20 @@ unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user,
 			panic("Failed to sync kernel TLBs: %d", err);
 		goto out;
 	}
-	else if (current->mm == NULL) {
-		if (current->pagefault_disabled) {
-			if (!mc) {
-				show_regs(container_of(regs, struct pt_regs, regs));
-				panic("Segfault with pagefaults disabled but no mcontext");
-			}
-			if (!current->thread.segv_continue) {
-				show_regs(container_of(regs, struct pt_regs, regs));
-				panic("Segfault without recovery target");
-			}
-			mc_set_rip(mc, current->thread.segv_continue);
-			current->thread.segv_continue = NULL;
-			goto out;
+	else if (current->pagefault_disabled) {
+		if (!mc) {
+			show_regs(container_of(regs, struct pt_regs, regs));
+			panic("Segfault with pagefaults disabled but no mcontext");
 		}
+		if (!current->thread.segv_continue) {
+			show_regs(container_of(regs, struct pt_regs, regs));
+			panic("Segfault without recovery target");
+		}
+		mc_set_rip(mc, current->thread.segv_continue);
+		current->thread.segv_continue = NULL;
+		goto out;
+	}
+	else if (current->mm == NULL) {
 		show_regs(container_of(regs, struct pt_regs, regs));
 		panic("Segfault with no mm");
 	}
diff --git a/arch/x86/um/shared/sysdep/faultinfo_32.h b/arch/x86/um/shared/sysdep/faultinfo_32.h
index ab5c8e47049c..9193a7790a71 100644
--- a/arch/x86/um/shared/sysdep/faultinfo_32.h
+++ b/arch/x86/um/shared/sysdep/faultinfo_32.h
@@ -31,8 +31,8 @@ struct faultinfo {
 
 #define ___backtrack_faulted(_faulted)					\
 	asm volatile (							\
-		"mov $0, %0\n"						\
 		"movl $__get_kernel_nofault_faulted_%=,%1\n"		\
+		"mov $0, %0\n"						\
 		"jmp _end_%=\n"						\
 		"__get_kernel_nofault_faulted_%=:\n"			\
 		"mov $1, %0;"						\
diff --git a/arch/x86/um/shared/sysdep/faultinfo_64.h b/arch/x86/um/shared/sysdep/faultinfo_64.h
index 26fb4835d3e9..61e4ca1e0ab5 100644
--- a/arch/x86/um/shared/sysdep/faultinfo_64.h
+++ b/arch/x86/um/shared/sysdep/faultinfo_64.h
@@ -31,8 +31,8 @@ struct faultinfo {
 
 #define ___backtrack_faulted(_faulted)					\
 	asm volatile (							\
-		"mov $0, %0\n"						\
 		"movq $__get_kernel_nofault_faulted_%=,%1\n"		\
+		"mov $0, %0\n"						\
 		"jmp _end_%=\n"						\
 		"__get_kernel_nofault_faulted_%=:\n"			\
 		"mov $1, %0;"						\
-- 
2.49.0



^ permalink raw reply related	[flat|nested] 2+ messages in thread

* Re: [PATCH] um: fix _nofault accesses
  2025-04-04 15:05 [PATCH] um: fix _nofault accesses Johannes Berg
@ 2025-04-04 21:12 ` Nathan Chancellor
  0 siblings, 0 replies; 2+ messages in thread
From: Nathan Chancellor @ 2025-04-04 21:12 UTC (permalink / raw)
  To: Johannes Berg; +Cc: linux-um, Johannes Berg

On Fri, Apr 04, 2025 at 05:05:19PM +0200, Johannes Berg wrote:
> From: Johannes Berg <johannes.berg@intel.com>
> 
> Nathan reported [1] that when built with clang, the um kernel
> crashes pretty much immediately. This turned out to be an issue
> with the inline assembly I had added, when clang used %rax/%eax
> for both operands. Reorder it so current->thread.segv_continue
> is written first, and then the lifetime of _faulted won't have
> overlap with the lifetime of segv_continue.
> 
> In the email thread Benjamin also pointed out that current->mm
> is only NULL for true kernel tasks, but we could do this for a
> userspace task, so the current->thread.segv_continue logic must
> be lifted out of the mm==NULL check.
> 
> Finally, while looking at this, put a barrier() so the NULL
> assignment to thread.segv_continue cannot be reorder before
> the possibly faulting operation.
> 
> Reported-by: Nathan Chancellor <nathan@kernel.org>
> Closes: https://lore.kernel.org/r/20250402221254.GA384@ax162 [1]
> Fixes: d1d7f01f7cd3 ("um: mark rodata read-only and implement _nofault accesses")
> Signed-off-by: Johannes Berg <johannes.berg@intel.com>

Thanks, this makes my test case happy.

Tested-by: Nathan Chancellor <nathan@kernel.org>

> ---
>  arch/um/include/asm/uaccess.h            |  2 ++
>  arch/um/kernel/trap.c                    | 26 ++++++++++++------------
>  arch/x86/um/shared/sysdep/faultinfo_32.h |  2 +-
>  arch/x86/um/shared/sysdep/faultinfo_64.h |  2 +-
>  4 files changed, 17 insertions(+), 15 deletions(-)
> 
> diff --git a/arch/um/include/asm/uaccess.h b/arch/um/include/asm/uaccess.h
> index 3a08f9029a3f..1c6e0ae41b0c 100644
> --- a/arch/um/include/asm/uaccess.h
> +++ b/arch/um/include/asm/uaccess.h
> @@ -55,6 +55,7 @@ do {									\
>  		goto err_label;						\
>  	}								\
>  	*((type *)dst) = get_unaligned((type *)(src));			\
> +	barrier();							\
>  	current->thread.segv_continue = NULL;				\
>  } while (0)
>  
> @@ -66,6 +67,7 @@ do {									\
>  	if (__faulted)							\
>  		goto err_label;						\
>  	put_unaligned(*((type *)src), (type *)(dst));			\
> +	barrier();							\
>  	current->thread.segv_continue = NULL;				\
>  } while (0)
>  
> diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
> index ce073150dc20..ef2272e92a43 100644
> --- a/arch/um/kernel/trap.c
> +++ b/arch/um/kernel/trap.c
> @@ -225,20 +225,20 @@ unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user,
>  			panic("Failed to sync kernel TLBs: %d", err);
>  		goto out;
>  	}
> -	else if (current->mm == NULL) {
> -		if (current->pagefault_disabled) {
> -			if (!mc) {
> -				show_regs(container_of(regs, struct pt_regs, regs));
> -				panic("Segfault with pagefaults disabled but no mcontext");
> -			}
> -			if (!current->thread.segv_continue) {
> -				show_regs(container_of(regs, struct pt_regs, regs));
> -				panic("Segfault without recovery target");
> -			}
> -			mc_set_rip(mc, current->thread.segv_continue);
> -			current->thread.segv_continue = NULL;
> -			goto out;
> +	else if (current->pagefault_disabled) {
> +		if (!mc) {
> +			show_regs(container_of(regs, struct pt_regs, regs));
> +			panic("Segfault with pagefaults disabled but no mcontext");
>  		}
> +		if (!current->thread.segv_continue) {
> +			show_regs(container_of(regs, struct pt_regs, regs));
> +			panic("Segfault without recovery target");
> +		}
> +		mc_set_rip(mc, current->thread.segv_continue);
> +		current->thread.segv_continue = NULL;
> +		goto out;
> +	}
> +	else if (current->mm == NULL) {
>  		show_regs(container_of(regs, struct pt_regs, regs));
>  		panic("Segfault with no mm");
>  	}
> diff --git a/arch/x86/um/shared/sysdep/faultinfo_32.h b/arch/x86/um/shared/sysdep/faultinfo_32.h
> index ab5c8e47049c..9193a7790a71 100644
> --- a/arch/x86/um/shared/sysdep/faultinfo_32.h
> +++ b/arch/x86/um/shared/sysdep/faultinfo_32.h
> @@ -31,8 +31,8 @@ struct faultinfo {
>  
>  #define ___backtrack_faulted(_faulted)					\
>  	asm volatile (							\
> -		"mov $0, %0\n"						\
>  		"movl $__get_kernel_nofault_faulted_%=,%1\n"		\
> +		"mov $0, %0\n"						\
>  		"jmp _end_%=\n"						\
>  		"__get_kernel_nofault_faulted_%=:\n"			\
>  		"mov $1, %0;"						\
> diff --git a/arch/x86/um/shared/sysdep/faultinfo_64.h b/arch/x86/um/shared/sysdep/faultinfo_64.h
> index 26fb4835d3e9..61e4ca1e0ab5 100644
> --- a/arch/x86/um/shared/sysdep/faultinfo_64.h
> +++ b/arch/x86/um/shared/sysdep/faultinfo_64.h
> @@ -31,8 +31,8 @@ struct faultinfo {
>  
>  #define ___backtrack_faulted(_faulted)					\
>  	asm volatile (							\
> -		"mov $0, %0\n"						\
>  		"movq $__get_kernel_nofault_faulted_%=,%1\n"		\
> +		"mov $0, %0\n"						\
>  		"jmp _end_%=\n"						\
>  		"__get_kernel_nofault_faulted_%=:\n"			\
>  		"mov $1, %0;"						\
> -- 
> 2.49.0
> 


^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2025-04-04 21:12 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2025-04-04 15:05 [PATCH] um: fix _nofault accesses Johannes Berg
2025-04-04 21:12 ` Nathan Chancellor

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox