arm64: alternative: add auto-nop infrastructure

In some cases, one side of an alternative sequence is simply a number of
NOPs used to balance the other side. Keeping track of this manually is
tedious, and the presence of large chains of NOPs makes the code more
painful to read than necessary.

To ameliorate matters, this patch adds a new alternative_else_nop_endif,
which automatically balances an alternative sequence with a trivial NOP
sled.

In many cases, we would like a NOP-sled in the default case, and
instructions patched in in the presence of a feature. To enable the NOPs
to be generated automatically for this case, this patch also adds a new
alternative_if, and updates alternative_else and alternative_endif to
work with either alternative_if or alternative_endif.

Cc: Andre Przywara <andre.przywara@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Martin <dave.martin@arm.com>
Cc: James Morse <james.morse@arm.com>
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
[will: use new nops macro to generate nop sequences]
Signed-off-by: Will Deacon <will.deacon@arm.com>

arch/arm64/include/asm/alternative.h

@@ -2,6 +2,7 @@
 #define __ASM_ALTERNATIVE_H
 
 #include <asm/cpufeature.h>
+#include <asm/insn.h>
 
 #ifndef __ASSEMBLY__
 
@@ -90,34 +91,55 @@ void apply_alternatives(void *start, size_t length);
 .endm
 
 /*
- * Begin an alternative code sequence.
+ * Alternative sequences
+ *
+ * The code for the case where the capability is not present will be
+ * assembled and linked as normal. There are no restrictions on this
+ * code.
+ *
+ * The code for the case where the capability is present will be
+ * assembled into a special section to be used for dynamic patching.
+ * Code for that case must:
+ *
+ * 1. Be exactly the same length (in bytes) as the default code
+ *    sequence.
  *
- * The code that follows this macro will be assembled and linked as
- * normal. There are no restrictions on this code.
+ * 2. Not contain a branch target that is used outside of the
+ *    alternative sequence it is defined in (branches into an
+ *    alternative sequence are not fixed up).
+ */
+
+/*
+ * Begin an alternative code sequence.
  */
 .macro alternative_if_not cap
+	.set .Lasm_alt_mode, 0
 	.pushsection .altinstructions, "a"
 	altinstruction_entry 661f, 663f, \cap, 662f-661f, 664f-663f
 	.popsection
 661:
 .endm
 
+.macro alternative_if cap
+	.set .Lasm_alt_mode, 1
+	.pushsection .altinstructions, "a"
+	altinstruction_entry 663f, 661f, \cap, 664f-663f, 662f-661f
+	.popsection
+	.pushsection .altinstr_replacement, "ax"
+	.align 2	/* So GAS knows label 661 is suitably aligned */
+661:
+.endm
+
 /*
- * Provide the alternative code sequence.
- *
- * The code that follows this macro is assembled into a special
- * section to be used for dynamic patching. Code that follows this
- * macro must:
- *
- * 1. Be exactly the same length (in bytes) as the default code
- *    sequence.
- *
- * 2. Not contain a branch target that is used outside of the
- *    alternative sequence it is defined in (branches into an
- *    alternative sequence are not fixed up).
+ * Provide the other half of the alternative code sequence.
  */
 .macro alternative_else
-662:	.pushsection .altinstr_replacement, "ax"
+662:
+	.if .Lasm_alt_mode==0
+	.pushsection .altinstr_replacement, "ax"
+	.else
+	.popsection
+	.endif
 663:
 .endm
 
@@ -125,11 +147,25 @@ void apply_alternatives(void *start, size_t length);
  * Complete an alternative code sequence.
  */
 .macro alternative_endif
-664:	.popsection
+664:
+	.if .Lasm_alt_mode==0
+	.popsection
+	.endif
 	.org	. - (664b-663b) + (662b-661b)
 	.org	. - (662b-661b) + (664b-663b)
 .endm
 
+/*
+ * Provides a trivial alternative or default sequence consisting solely
+ * of NOPs. The number of NOPs is chosen automatically to match the
+ * previous case.
+ */
+.macro alternative_else_nop_endif
+alternative_else
+	nops	(662b-661b) / AARCH64_INSN_SIZE
+alternative_endif
+.endm
+
 #define _ALTERNATIVE_CFG(insn1, insn2, cap, cfg, ...)	\
 	alternative_insn insn1, insn2, cap, IS_ENABLED(cfg)