arm64: lse: deal with clobbered IP registers after branch via PLT

The LSE atomics implementation uses runtime patching to patch in calls
to out of line non-LSE atomics implementations on cores that lack hardware
support for LSE. To avoid paying the overhead cost of a function call even
if no call ends up being made, the bl instruction is kept invisible to the
compiler, and the out of line implementations preserve all registers, not
just the ones that they are required to preserve as per the AAPCS64.

However, commit fd045f6cd98e ("arm64: add support for module PLTs") added
support for routing branch instructions via veneers if the branch target
offset exceeds the range of the ordinary relative branch instructions.
Since this deals with jump and call instructions that are exposed to ELF
relocations, the PLT code uses x16 to hold the address of the branch target
when it performs an indirect branch-to-register, something which is
explicitly allowed by the AAPCS64 (and ordinary compiler generated code
does not expect register x16 or x17 to retain their values across a bl
instruction).

Since the lse runtime patched bl instructions don't adhere to the AAPCS64,
they don't deal with this clobbering of registers x16 and x17. So add them
to the clobber list of the asm() statements that perform the call
instructions, and drop x16 and x17 from the list of registers that are
callee saved in the out of line non-LSE implementations.

In addition, since we have given these functions two scratch registers,
they no longer need to stack/unstack temp registers.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
[will: factored clobber list into #define, updated Makefile comment]
Signed-off-by: Will Deacon <will.deacon@arm.com>

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

3 files changed, 27 insertions, 25 deletions

diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h
index 197e06afbf71..39c1d340fec5 100644
--- a/arch/arm64/include/asm/atomic_lse.h
+++ b/arch/arm64/include/asm/atomic_lse.h
@@ -36,7 +36,7 @@ static inline void atomic_andnot(int i, atomic_t *v)
 	"	stclr	%w[i], %[v]\n")
 	: [i] "+r" (w0), [v] "+Q" (v->counter)
 	: "r" (x1)
-	: "x30");
+	: __LL_SC_CLOBBERS);
 }
 
 static inline void atomic_or(int i, atomic_t *v)
@@ -48,7 +48,7 @@ static inline void atomic_or(int i, atomic_t *v)
 	"	stset	%w[i], %[v]\n")
 	: [i] "+r" (w0), [v] "+Q" (v->counter)
 	: "r" (x1)
-	: "x30");
+	: __LL_SC_CLOBBERS);
 }
 
 static inline void atomic_xor(int i, atomic_t *v)
@@ -60,7 +60,7 @@ static inline void atomic_xor(int i, atomic_t *v)
 	"	steor	%w[i], %[v]\n")
 	: [i] "+r" (w0), [v] "+Q" (v->counter)
 	: "r" (x1)
-	: "x30");
+	: __LL_SC_CLOBBERS);
 }
 
 static inline void atomic_add(int i, atomic_t *v)
@@ -72,7 +72,7 @@ static inline void atomic_add(int i, atomic_t *v)
 	"	stadd	%w[i], %[v]\n")
 	: [i] "+r" (w0), [v] "+Q" (v->counter)
 	: "r" (x1)
-	: "x30");
+	: __LL_SC_CLOBBERS);
 }
 
 #define ATOMIC_OP_ADD_RETURN(name, mb, cl...)				\
@@ -90,7 +90,7 @@ static inline int atomic_add_return##name(int i, atomic_t *v)		\
 	"	add	%w[i], %w[i], w30")				\
 	: [i] "+r" (w0), [v] "+Q" (v->counter)				\
 	: "r" (x1)							\
-	: "x30" , ##cl);						\
+	: __LL_SC_CLOBBERS, ##cl);					\
 									\
 	return w0;							\
 }
@@ -116,7 +116,7 @@ static inline void atomic_and(int i, atomic_t *v)
 	"	stclr	%w[i], %[v]")
 	: [i] "+r" (w0), [v] "+Q" (v->counter)
 	: "r" (x1)
-	: "x30");
+	: __LL_SC_CLOBBERS);
 }
 
 static inline void atomic_sub(int i, atomic_t *v)
@@ -133,7 +133,7 @@ static inline void atomic_sub(int i, atomic_t *v)
 	"	stadd	%w[i], %[v]")
 	: [i] "+r" (w0), [v] "+Q" (v->counter)
 	: "r" (x1)
-	: "x30");
+	: __LL_SC_CLOBBERS);
 }
 
 #define ATOMIC_OP_SUB_RETURN(name, mb, cl...)				\
@@ -153,7 +153,7 @@ static inline int atomic_sub_return##name(int i, atomic_t *v)		\
 	"	add	%w[i], %w[i], w30")				\
 	: [i] "+r" (w0), [v] "+Q" (v->counter)				\
 	: "r" (x1)							\
-	: "x30" , ##cl);						\
+	: __LL_SC_CLOBBERS , ##cl);					\
 									\
 	return w0;							\
 }
@@ -177,7 +177,7 @@ static inline void atomic64_andnot(long i, atomic64_t *v)
 	"	stclr	%[i], %[v]\n")
 	: [i] "+r" (x0), [v] "+Q" (v->counter)
 	: "r" (x1)
-	: "x30");
+	: __LL_SC_CLOBBERS);
 }
 
 static inline void atomic64_or(long i, atomic64_t *v)
@@ -189,7 +189,7 @@ static inline void atomic64_or(long i, atomic64_t *v)
 	"	stset	%[i], %[v]\n")
 	: [i] "+r" (x0), [v] "+Q" (v->counter)
 	: "r" (x1)
-	: "x30");
+	: __LL_SC_CLOBBERS);
 }
 
 static inline void atomic64_xor(long i, atomic64_t *v)
@@ -201,7 +201,7 @@ static inline void atomic64_xor(long i, atomic64_t *v)
 	"	steor	%[i], %[v]\n")
 	: [i] "+r" (x0), [v] "+Q" (v->counter)
 	: "r" (x1)
-	: "x30");
+	: __LL_SC_CLOBBERS);
 }
 
 static inline void atomic64_add(long i, atomic64_t *v)
@@ -213,7 +213,7 @@ static inline void atomic64_add(long i, atomic64_t *v)
 	"	stadd	%[i], %[v]\n")
 	: [i] "+r" (x0), [v] "+Q" (v->counter)
 	: "r" (x1)
-	: "x30");
+	: __LL_SC_CLOBBERS);
 }
 
 #define ATOMIC64_OP_ADD_RETURN(name, mb, cl...)				\
@@ -231,7 +231,7 @@ static inline long atomic64_add_return##name(long i, atomic64_t *v)	\
 	"	add	%[i], %[i], x30")				\
 	: [i] "+r" (x0), [v] "+Q" (v->counter)				\
 	: "r" (x1)							\
-	: "x30" , ##cl);						\
+	: __LL_SC_CLOBBERS, ##cl);					\
 									\
 	return x0;							\
 }
@@ -257,7 +257,7 @@ static inline void atomic64_and(long i, atomic64_t *v)
 	"	stclr	%[i], %[v]")
 	: [i] "+r" (x0), [v] "+Q" (v->counter)
 	: "r" (x1)
-	: "x30");
+	: __LL_SC_CLOBBERS);
 }
 
 static inline void atomic64_sub(long i, atomic64_t *v)
@@ -274,7 +274,7 @@ static inline void atomic64_sub(long i, atomic64_t *v)
 	"	stadd	%[i], %[v]")
 	: [i] "+r" (x0), [v] "+Q" (v->counter)
 	: "r" (x1)
-	: "x30");
+	: __LL_SC_CLOBBERS);
 }
 
 #define ATOMIC64_OP_SUB_RETURN(name, mb, cl...)				\
@@ -294,7 +294,7 @@ static inline long atomic64_sub_return##name(long i, atomic64_t *v)	\
 	"	add	%[i], %[i], x30")				\
 	: [i] "+r" (x0), [v] "+Q" (v->counter)				\
 	: "r" (x1)							\
-	: "x30" , ##cl);						\
+	: __LL_SC_CLOBBERS, ##cl);					\
 									\
 	return x0;							\
 }
@@ -330,7 +330,7 @@ static inline long atomic64_dec_if_positive(atomic64_t *v)
 	"2:")
 	: [ret] "+&r" (x0), [v] "+Q" (v->counter)
 	:
-	: "x30", "cc", "memory");
+	: __LL_SC_CLOBBERS, "cc", "memory");
 
 	return x0;
 }
@@ -359,7 +359,7 @@ static inline unsigned long __cmpxchg_case_##name(volatile void *ptr,	\
 	"	mov	%" #w "[ret], " #w "30")			\
 	: [ret] "+r" (x0), [v] "+Q" (*(unsigned long *)ptr)		\
 	: [old] "r" (x1), [new] "r" (x2)				\
-	: "x30" , ##cl);						\
+	: __LL_SC_CLOBBERS, ##cl);					\
 									\
 	return x0;							\
 }
@@ -416,7 +416,7 @@ static inline long __cmpxchg_double##name(unsigned long old1,		\
 	  [v] "+Q" (*(unsigned long *)ptr)				\
 	: [new1] "r" (x2), [new2] "r" (x3), [ptr] "r" (x4),		\
 	  [oldval1] "r" (oldval1), [oldval2] "r" (oldval2)		\
-	: "x30" , ##cl);						\
+	: __LL_SC_CLOBBERS, ##cl);					\
 									\
 	return x0;							\
 }
diff --git a/arch/arm64/include/asm/lse.h b/arch/arm64/include/asm/lse.h
index 3de42d68611d..23acc00be32d 100644
--- a/arch/arm64/include/asm/lse.h
+++ b/arch/arm64/include/asm/lse.h
@@ -26,6 +26,7 @@ __asm__(".arch_extension	lse");
 
 /* Macro for constructing calls to out-of-line ll/sc atomics */
 #define __LL_SC_CALL(op)	"bl\t" __stringify(__LL_SC_PREFIX(op)) "\n"
+#define __LL_SC_CLOBBERS	"x16", "x17", "x30"
 
 /* In-line patching at runtime */
 #define ARM64_LSE_ATOMIC_INSN(llsc, lse)				\
diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile
index 1a811ecf71da..c86b7909ef31 100644
--- a/arch/arm64/lib/Makefile
+++ b/arch/arm64/lib/Makefile
@@ -4,15 +4,16 @@ lib-y		:= bitops.o clear_user.o delay.o copy_from_user.o	\
 		   memcmp.o strcmp.o strncmp.o strlen.o strnlen.o	\
 		   strchr.o strrchr.o
 
-# Tell the compiler to treat all general purpose registers as
-# callee-saved, which allows for efficient runtime patching of the bl
-# instruction in the caller with an atomic instruction when supported by
-# the CPU. Result and argument registers are handled correctly, based on
-# the function prototype.
+# Tell the compiler to treat all general purpose registers (with the
+# exception of the IP registers, which are already handled by the caller
+# in case of a PLT) as callee-saved, which allows for efficient runtime
+# patching of the bl instruction in the caller with an atomic instruction
+# when supported by the CPU. Result and argument registers are handled
+# correctly, based on the function prototype.
 lib-$(CONFIG_ARM64_LSE_ATOMICS) += atomic_ll_sc.o
 CFLAGS_atomic_ll_sc.o	:= -fcall-used-x0 -ffixed-x1 -ffixed-x2		\
 		   -ffixed-x3 -ffixed-x4 -ffixed-x5 -ffixed-x6		\
 		   -ffixed-x7 -fcall-saved-x8 -fcall-saved-x9		\
 		   -fcall-saved-x10 -fcall-saved-x11 -fcall-saved-x12	\
 		   -fcall-saved-x13 -fcall-saved-x14 -fcall-saved-x15	\
-		   -fcall-saved-x16 -fcall-saved-x17 -fcall-saved-x18
+		   -fcall-saved-x18