Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Will Deacon:
 "Here are the core arm64 updates for 4.1.

  Highlights include a significant rework to head.S (allowing us to boot
  on machines with physical memory at a really high address), an AES
  performance boost on Cortex-A57 and the ability to run a 32-bit
  userspace with 64k pages (although this requires said userspace to be
  built with a recent binutils).

  The head.S rework spilt over into KVM, so there are some changes under
  arch/arm/ which have been acked by Marc Zyngier (KVM co-maintainer).
  In particular, the linker script changes caused us some issues in
  -next, so there are a few merge commits where we had to apply fixes on
  top of a stable branch.

  Other changes include:

   - AES performance boost for Cortex-A57
   - AArch32 (compat) userspace with 64k pages
   - Cortex-A53 erratum workaround for #845719
   - defconfig updates (new platforms, PCI, ...)"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (39 commits)
  arm64: fix midr range for Cortex-A57 erratum 832075
  arm64: errata: add workaround for cortex-a53 erratum #845719
  arm64: Use bool function return values of true/false not 1/0
  arm64: defconfig: updates for 4.1
  arm64: Extract feature parsing code from cpu_errata.c
  arm64: alternative: Allow immediate branch as alternative instruction
  arm64: insn: Add aarch64_insn_decode_immediate
  ARM: kvm: round HYP section to page size instead of log2 upper bound
  ARM: kvm: assert on HYP section boundaries not actual code size
  arm64: head.S: ensure idmap_t0sz is visible
  arm64: pmu: add support for interrupt-affinity property
  dt: pmu: extend ARM PMU binding to allow for explicit interrupt affinity
  arm64: head.S: ensure visibility of page tables
  arm64: KVM: use ID map with increased VA range if required
  arm64: mm: increase VA range of identity map
  ARM: kvm: implement replacement for ld's LOG2CEIL()
  arm64: proc: remove unused cpu_get_pgd macro
  arm64: enforce x1|x2|x3 == 0 upon kernel entry as per boot protocol
  arm64: remove __calc_phys_offset
  arm64: merge __enable_mmu and __turn_mmu_on
  ...

1 files changed, 53 insertions, 2 deletions

diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index ad7821d64a1d..21033bba9390 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -24,6 +24,7 @@
 #include <asm/cacheflush.h>
 #include <asm/alternative.h>
 #include <asm/cpufeature.h>
+#include <asm/insn.h>
 #include <linux/stop_machine.h>
 
 extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
@@ -33,6 +34,48 @@ struct alt_region {
 	struct alt_instr *end;
 };
 
+/*
+ * Decode the imm field of a b/bl instruction, and return the byte
+ * offset as a signed value (so it can be used when computing a new
+ * branch target).
+ */
+static s32 get_branch_offset(u32 insn)
+{
+	s32 imm = aarch64_insn_decode_immediate(AARCH64_INSN_IMM_26, insn);
+
+	/* sign-extend the immediate before turning it into a byte offset */
+	return (imm << 6) >> 4;
+}
+
+static u32 get_alt_insn(u8 *insnptr, u8 *altinsnptr)
+{
+	u32 insn;
+
+	aarch64_insn_read(altinsnptr, &insn);
+
+	/* Stop the world on instructions we don't support... */
+	BUG_ON(aarch64_insn_is_cbz(insn));
+	BUG_ON(aarch64_insn_is_cbnz(insn));
+	BUG_ON(aarch64_insn_is_bcond(insn));
+	/* ... and there is probably more. */
+
+	if (aarch64_insn_is_b(insn) || aarch64_insn_is_bl(insn)) {
+		enum aarch64_insn_branch_type type;
+		unsigned long target;
+
+		if (aarch64_insn_is_b(insn))
+			type = AARCH64_INSN_BRANCH_NOLINK;
+		else
+			type = AARCH64_INSN_BRANCH_LINK;
+
+		target = (unsigned long)altinsnptr + get_branch_offset(insn);
+		insn = aarch64_insn_gen_branch_imm((unsigned long)insnptr,
+						   target, type);
+	}
+
+	return insn;
+}
+
 static int __apply_alternatives(void *alt_region)
 {
 	struct alt_instr *alt;
@@ -40,16 +83,24 @@ static int __apply_alternatives(void *alt_region)
 	u8 *origptr, *replptr;
 
 	for (alt = region->begin; alt < region->end; alt++) {
+		u32 insn;
+		int i;
+
 		if (!cpus_have_cap(alt->cpufeature))
 			continue;
 
-		BUG_ON(alt->alt_len > alt->orig_len);
+		BUG_ON(alt->alt_len != alt->orig_len);
 
 		pr_info_once("patching kernel code\n");
 
 		origptr = (u8 *)&alt->orig_offset + alt->orig_offset;
 		replptr = (u8 *)&alt->alt_offset + alt->alt_offset;
-		memcpy(origptr, replptr, alt->alt_len);
+
+		for (i = 0; i < alt->alt_len; i += sizeof(insn)) {
+			insn = get_alt_insn(origptr + i, replptr + i);
+			aarch64_insn_write(origptr + i, insn);
+		}
+
 		flush_icache_range((uintptr_t)origptr,
 				   (uintptr_t)(origptr + alt->alt_len));
 	}