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
  ...

2 files changed, 9 insertions, 13 deletions

diff --git a/arch/arm64/crypto/aes-ce-ccm-core.S b/arch/arm64/crypto/aes-ce-ccm-core.S
index 432e4841cd81..a2a7fbcacc14 100644
--- a/arch/arm64/crypto/aes-ce-ccm-core.S
+++ b/arch/arm64/crypto/aes-ce-ccm-core.S
@@ -101,19 +101,19 @@ ENTRY(ce_aes_ccm_final)
 0:	mov	v4.16b, v3.16b
 1:	ld1	{v5.2d}, [x2], #16		/* load next round key */
 	aese	v0.16b, v4.16b
-	aese	v1.16b, v4.16b
 	aesmc	v0.16b, v0.16b
+	aese	v1.16b, v4.16b
 	aesmc	v1.16b, v1.16b
 2:	ld1	{v3.2d}, [x2], #16		/* load next round key */
 	aese	v0.16b, v5.16b
-	aese	v1.16b, v5.16b
 	aesmc	v0.16b, v0.16b
+	aese	v1.16b, v5.16b
 	aesmc	v1.16b, v1.16b
 3:	ld1	{v4.2d}, [x2], #16		/* load next round key */
 	subs	w3, w3, #3
 	aese	v0.16b, v3.16b
-	aese	v1.16b, v3.16b
 	aesmc	v0.16b, v0.16b
+	aese	v1.16b, v3.16b
 	aesmc	v1.16b, v1.16b
 	bpl	1b
 	aese	v0.16b, v4.16b
@@ -146,19 +146,19 @@ ENDPROC(ce_aes_ccm_final)
 	ld1	{v5.2d}, [x10], #16		/* load 2nd round key */
 2:	/* inner loop: 3 rounds, 2x interleaved */
 	aese	v0.16b, v4.16b
-	aese	v1.16b, v4.16b
 	aesmc	v0.16b, v0.16b
+	aese	v1.16b, v4.16b
 	aesmc	v1.16b, v1.16b
 3:	ld1	{v3.2d}, [x10], #16		/* load next round key */
 	aese	v0.16b, v5.16b
-	aese	v1.16b, v5.16b
 	aesmc	v0.16b, v0.16b
+	aese	v1.16b, v5.16b
 	aesmc	v1.16b, v1.16b
 4:	ld1	{v4.2d}, [x10], #16		/* load next round key */
 	subs	w7, w7, #3
 	aese	v0.16b, v3.16b
-	aese	v1.16b, v3.16b
 	aesmc	v0.16b, v0.16b
+	aese	v1.16b, v3.16b
 	aesmc	v1.16b, v1.16b
 	ld1	{v5.2d}, [x10], #16		/* load next round key */
 	bpl	2b
diff --git a/arch/arm64/crypto/aes-ce.S b/arch/arm64/crypto/aes-ce.S
index 685a18f731eb..78f3cfe92c08 100644
--- a/arch/arm64/crypto/aes-ce.S
+++ b/arch/arm64/crypto/aes-ce.S
@@ -45,18 +45,14 @@
 
 	.macro		do_enc_Nx, de, mc, k, i0, i1, i2, i3
 	aes\de		\i0\().16b, \k\().16b
-	.ifnb		\i1
-	aes\de		\i1\().16b, \k\().16b
-	.ifnb		\i3
-	aes\de		\i2\().16b, \k\().16b
-	aes\de		\i3\().16b, \k\().16b
-	.endif
-	.endif
 	aes\mc		\i0\().16b, \i0\().16b
 	.ifnb		\i1
+	aes\de		\i1\().16b, \k\().16b
 	aes\mc		\i1\().16b, \i1\().16b
 	.ifnb		\i3
+	aes\de		\i2\().16b, \k\().16b
 	aes\mc		\i2\().16b, \i2\().16b
+	aes\de		\i3\().16b, \k\().16b
 	aes\mc		\i3\().16b, \i3\().16b
 	.endif
 	.endif