work around gcc bugs with 'asm goto' with outputs

We've had issues with gcc and 'asm goto' before, and we created a
'asm_volatile_goto()' macro for that in the past: see commits
3f0116c3238a ("compiler/gcc4: Add quirk for 'asm goto' miscompilation
bug") and a9f180345f53 ("compiler/gcc4: Make quirk for
asm_volatile_goto() unconditional").

Then, much later, we ended up removing the workaround in commit
43c249ea0b1e ("compiler-gcc.h: remove ancient workaround for gcc PR
58670") because we no longer supported building the kernel with the
affected gcc versions, but we left the macro uses around.

Now, Sean Christopherson reports a new version of a very similar
problem, which is fixed by re-applying that ancient workaround.  But the
problem in question is limited to only the 'asm goto with outputs'
cases, so instead of re-introducing the old workaround as-is, let's
rename and limit the workaround to just that much less common case.

It looks like there are at least two separate issues that all hit in
this area:

 (a) some versions of gcc don't mark the asm goto as 'volatile' when it
     has outputs:

        https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98619
        https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110420

     which is easy to work around by just adding the 'volatile' by hand.

 (b) Internal compiler errors:

        https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110422

     which are worked around by adding the extra empty 'asm' as a
     barrier, as in the original workaround.

but the problem Sean sees may be a third thing since it involves bad
code generation (not an ICE) even with the manually added 'volatile'.

but the same old workaround works for this case, even if this feels a
bit like voodoo programming and may only be hiding the issue.

Reported-and-tested-by: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/all/20240208220604.140859-1-seanjc@google.com/
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Uros Bizjak <ubizjak@gmail.com>
Cc: Jakub Jelinek <jakub@redhat.com>
Cc: Andrew Pinski <quic_apinski@quicinc.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

6 files changed, 16 insertions, 16 deletions

diff --git a/arch/riscv/include/asm/arch_hweight.h b/arch/riscv/include/asm/arch_hweight.h
index c20236a0725b..85b2c443823e 100644
--- a/arch/riscv/include/asm/arch_hweight.h
+++ b/arch/riscv/include/asm/arch_hweight.h
@@ -20,7 +20,7 @@
 static __always_inline unsigned int __arch_hweight32(unsigned int w)
 {
 #ifdef CONFIG_RISCV_ISA_ZBB
-	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+	asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
 				      RISCV_ISA_EXT_ZBB, 1)
 			  : : : : legacy);
 
@@ -51,7 +51,7 @@ static inline unsigned int __arch_hweight8(unsigned int w)
 static __always_inline unsigned long __arch_hweight64(__u64 w)
 {
 # ifdef CONFIG_RISCV_ISA_ZBB
-	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+	asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
 				      RISCV_ISA_EXT_ZBB, 1)
 			  : : : : legacy);
 
diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h
index 9ffc35537024..329d8244a9b3 100644
--- a/arch/riscv/include/asm/bitops.h
+++ b/arch/riscv/include/asm/bitops.h
@@ -39,7 +39,7 @@ static __always_inline unsigned long variable__ffs(unsigned long word)
 {
 	int num;
 
-	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+	asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
 				      RISCV_ISA_EXT_ZBB, 1)
 			  : : : : legacy);
 
@@ -95,7 +95,7 @@ static __always_inline unsigned long variable__fls(unsigned long word)
 {
 	int num;
 
-	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+	asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
 				      RISCV_ISA_EXT_ZBB, 1)
 			  : : : : legacy);
 
@@ -154,7 +154,7 @@ static __always_inline int variable_ffs(int x)
 	if (!x)
 		return 0;
 
-	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+	asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
 				      RISCV_ISA_EXT_ZBB, 1)
 			  : : : : legacy);
 
@@ -209,7 +209,7 @@ static __always_inline int variable_fls(unsigned int x)
 	if (!x)
 		return 0;
 
-	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+	asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
 				      RISCV_ISA_EXT_ZBB, 1)
 			  : : : : legacy);
 
diff --git a/arch/riscv/include/asm/checksum.h b/arch/riscv/include/asm/checksum.h
index a5b60b54b101..88e6f1499e88 100644
--- a/arch/riscv/include/asm/checksum.h
+++ b/arch/riscv/include/asm/checksum.h
@@ -53,7 +53,7 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
 	    IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
 		unsigned long fold_temp;
 
-		asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
+		asm goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
 					      RISCV_ISA_EXT_ZBB, 1)
 		    :
 		    :
diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
index 5a626ed2c47a..0bd11862b760 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -80,7 +80,7 @@ riscv_has_extension_likely(const unsigned long ext)
 			   "ext must be < RISCV_ISA_EXT_MAX");
 
 	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
-		asm_volatile_goto(
+		asm goto(
 		ALTERNATIVE("j	%l[l_no]", "nop", 0, %[ext], 1)
 		:
 		: [ext] "i" (ext)
@@ -103,7 +103,7 @@ riscv_has_extension_unlikely(const unsigned long ext)
 			   "ext must be < RISCV_ISA_EXT_MAX");
 
 	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
-		asm_volatile_goto(
+		asm goto(
 		ALTERNATIVE("nop", "j	%l[l_yes]", 0, %[ext], 1)
 		:
 		: [ext] "i" (ext)
diff --git a/arch/riscv/include/asm/jump_label.h b/arch/riscv/include/asm/jump_label.h
index 14a5ea8d8ef0..4a35d787c019 100644
--- a/arch/riscv/include/asm/jump_label.h
+++ b/arch/riscv/include/asm/jump_label.h
@@ -17,7 +17,7 @@
 static __always_inline bool arch_static_branch(struct static_key * const key,
 					       const bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"	.align		2			\n\t"
 		"	.option push				\n\t"
 		"	.option norelax				\n\t"
@@ -39,7 +39,7 @@ label:
 static __always_inline bool arch_static_branch_jump(struct static_key * const key,
 						    const bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"	.align		2			\n\t"
 		"	.option push				\n\t"
 		"	.option norelax				\n\t"
diff --git a/arch/riscv/lib/csum.c b/arch/riscv/lib/csum.c
index af3df5274ccb..74af3ab520b6 100644
--- a/arch/riscv/lib/csum.c
+++ b/arch/riscv/lib/csum.c
@@ -53,7 +53,7 @@ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 		 * support, so nop when Zbb is available and jump when Zbb is
 		 * not available.
 		 */
-		asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
+		asm goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
 					      RISCV_ISA_EXT_ZBB, 1)
 				  :
 				  :
@@ -170,7 +170,7 @@ do_csum_with_alignment(const unsigned char *buff, int len)
 		 * support, so nop when Zbb is available and jump when Zbb is
 		 * not available.
 		 */
-		asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
+		asm goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
 					      RISCV_ISA_EXT_ZBB, 1)
 				  :
 				  :
@@ -178,7 +178,7 @@ do_csum_with_alignment(const unsigned char *buff, int len)
 				  : no_zbb);
 
 #ifdef CONFIG_32BIT
-		asm_volatile_goto(".option push			\n\
+		asm_goto_output(".option push			\n\
 		.option arch,+zbb				\n\
 			rori	%[fold_temp], %[csum], 16	\n\
 			andi	%[offset], %[offset], 1		\n\
@@ -193,7 +193,7 @@ do_csum_with_alignment(const unsigned char *buff, int len)
 
 		return (unsigned short)csum;
 #else /* !CONFIG_32BIT */
-		asm_volatile_goto(".option push			\n\
+		asm_goto_output(".option push			\n\
 		.option arch,+zbb				\n\
 			rori	%[fold_temp], %[csum], 32	\n\
 			add	%[csum], %[fold_temp], %[csum]	\n\
@@ -257,7 +257,7 @@ do_csum_no_alignment(const unsigned char *buff, int len)
 		 * support, so nop when Zbb is available and jump when Zbb is
 		 * not available.
 		 */
-		asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
+		asm goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
 					      RISCV_ISA_EXT_ZBB, 1)
 				  :
 				  :