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

Pull arm64 updates from Catalin Marinas:

 - Pseudo NMI support for arm64 using GICv3 interrupt priorities

 - uaccess macros clean-up (unsafe user accessors also merged but
   reverted, waiting for objtool support on arm64)

 - ptrace regsets for Pointer Authentication (ARMv8.3) key management

 - inX() ordering w.r.t. delay() on arm64 and riscv (acks in place by
   the riscv maintainers)

 - arm64/perf updates: PMU bindings converted to json-schema, unused
   variable and misleading comment removed

 - arm64/debug fixes to ensure checking of the triggering exception
   level and to avoid the propagation of the UNKNOWN FAR value into the
   si_code for debug signals

 - Workaround for Fujitsu A64FX erratum 010001

 - lib/raid6 ARM NEON optimisations

 - NR_CPUS now defaults to 256 on arm64

 - Minor clean-ups (documentation/comments, Kconfig warning, unused
   asm-offsets, clang warnings)

 - MAINTAINERS update for list information to the ARM64 ACPI entry

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (54 commits)
  arm64: mmu: drop paging_init comments
  arm64: debug: Ensure debug handlers check triggering exception level
  arm64: debug: Don't propagate UNKNOWN FAR into si_code for debug signals
  Revert "arm64: uaccess: Implement unsafe accessors"
  arm64: avoid clang warning about self-assignment
  arm64: Kconfig.platforms: fix warning unmet direct dependencies
  lib/raid6: arm: optimize away a mask operation in NEON recovery routine
  lib/raid6: use vdupq_n_u8 to avoid endianness warnings
  arm64: io: Hook up __io_par() for inX() ordering
  riscv: io: Update __io_[p]ar() macros to take an argument
  asm-generic/io: Pass result of I/O accessor to __io_[p]ar()
  arm64: Add workaround for Fujitsu A64FX erratum 010001
  arm64: Rename get_thread_info()
  arm64: Remove documentation about TIF_USEDFPU
  arm64: irqflags: Fix clang build warnings
  arm64: Enable the support of pseudo-NMIs
  arm64: Skip irqflags tracing for NMI in IRQs disabled context
  arm64: Skip preemption when exiting an NMI
  arm64: Handle serror in NMI context
  irqchip/gic-v3: Allow interrupts to be set as pseudo-NMI
  ...

2 files changed, 10 insertions, 14 deletions

diff --git a/lib/raid6/neon.uc b/lib/raid6/neon.uc
index d5242f544551..b7c68030da4f 100644
--- a/lib/raid6/neon.uc
+++ b/lib/raid6/neon.uc
@@ -28,7 +28,6 @@
 
 typedef uint8x16_t unative_t;
 
-#define NBYTES(x) ((unative_t){x,x,x,x, x,x,x,x, x,x,x,x, x,x,x,x})
 #define NSIZE   sizeof(unative_t)
 
 /*
@@ -61,7 +60,7 @@ void raid6_neon$#_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs)
         int d, z, z0;
 
         register unative_t wd$$, wq$$, wp$$, w1$$, w2$$;
-        const unative_t x1d = NBYTES(0x1d);
+        const unative_t x1d = vdupq_n_u8(0x1d);
 
         z0 = disks - 3;         /* Highest data disk */
         p = dptr[z0+1];         /* XOR parity */
@@ -92,7 +91,7 @@ void raid6_neon$#_xor_syndrome_real(int disks, int start, int stop,
         int d, z, z0;
 
         register unative_t wd$$, wq$$, wp$$, w1$$, w2$$;
-        const unative_t x1d = NBYTES(0x1d);
+        const unative_t x1d = vdupq_n_u8(0x1d);
 
         z0 = stop;              /* P/Q right side optimization */
         p = dptr[disks-2];      /* XOR parity */
diff --git a/lib/raid6/recov_neon_inner.c b/lib/raid6/recov_neon_inner.c
index 8cd20c9f834a..f13c07f82297 100644
--- a/lib/raid6/recov_neon_inner.c
+++ b/lib/raid6/recov_neon_inner.c
@@ -10,11 +10,6 @@
 
 #include <arm_neon.h>
 
-static const uint8x16_t x0f = {
-        0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f,
-        0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f,
-};
-
 #ifdef CONFIG_ARM
 /*
  * AArch32 does not provide this intrinsic natively because it does not
@@ -41,6 +36,7 @@ void __raid6_2data_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dp,
         uint8x16_t pm1 = vld1q_u8(pbmul + 16);
         uint8x16_t qm0 = vld1q_u8(qmul);
         uint8x16_t qm1 = vld1q_u8(qmul + 16);
+        uint8x16_t x0f = vdupq_n_u8(0x0f);
 
         /*
          * while ( bytes-- ) {
@@ -60,14 +56,14 @@ void __raid6_2data_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dp,
                 px = veorq_u8(vld1q_u8(p), vld1q_u8(dp));
                 vx = veorq_u8(vld1q_u8(q), vld1q_u8(dq));
 
-                vy = (uint8x16_t)vshrq_n_s16((int16x8_t)vx, 4);
+                vy = vshrq_n_u8(vx, 4);
                 vx = vqtbl1q_u8(qm0, vandq_u8(vx, x0f));
-                vy = vqtbl1q_u8(qm1, vandq_u8(vy, x0f));
+                vy = vqtbl1q_u8(qm1, vy);
                 qx = veorq_u8(vx, vy);
 
-                vy = (uint8x16_t)vshrq_n_s16((int16x8_t)px, 4);
+                vy = vshrq_n_u8(px, 4);
                 vx = vqtbl1q_u8(pm0, vandq_u8(px, x0f));
-                vy = vqtbl1q_u8(pm1, vandq_u8(vy, x0f));
+                vy = vqtbl1q_u8(pm1, vy);
                 vx = veorq_u8(vx, vy);
                 db = veorq_u8(vx, qx);
 
@@ -87,6 +83,7 @@ void __raid6_datap_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dq,
 {
         uint8x16_t qm0 = vld1q_u8(qmul);
         uint8x16_t qm1 = vld1q_u8(qmul + 16);
+        uint8x16_t x0f = vdupq_n_u8(0x0f);
 
         /*
          * while (bytes--) {
@@ -100,9 +97,9 @@ void __raid6_datap_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dq,
 
                 vx = veorq_u8(vld1q_u8(q), vld1q_u8(dq));
 
-                vy = (uint8x16_t)vshrq_n_s16((int16x8_t)vx, 4);
+                vy = vshrq_n_u8(vx, 4);
                 vx = vqtbl1q_u8(qm0, vandq_u8(vx, x0f));
-                vy = vqtbl1q_u8(qm1, vandq_u8(vy, x0f));
+                vy = vqtbl1q_u8(qm1, vy);
                 vx = veorq_u8(vx, vy);
                 vy = veorq_u8(vx, vld1q_u8(p));