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

Pull arm64 updates from Will Deacon:
 "Mostly just incremental improvements here:

   - Introduce AT_HWCAP2 for advertising CPU features to userspace

   - Expose SVE2 availability to userspace

   - Support for "data cache clean to point of deep persistence" (DC PODP)

   - Honour "mitigations=off" on the cmdline and advertise status via
     sysfs

   - CPU timer erratum workaround (Neoverse-N1 #1188873)

   - Introduce perf PMU driver for the SMMUv3 performance counters

   - Add config option to disable the kuser helpers page for AArch32 tasks

   - Futex modifications to ensure liveness under contention

   - Rework debug exception handling to seperate kernel and user
     handlers

   - Non-critical fixes and cleanup"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (92 commits)
  Documentation: Add ARM64 to kernel-parameters.rst
  arm64/speculation: Support 'mitigations=' cmdline option
  arm64: ssbs: Don't treat CPUs with SSBS as unaffected by SSB
  arm64: enable generic CPU vulnerabilites support
  arm64: add sysfs vulnerability show for speculative store bypass
  arm64: Fix size of __early_cpu_boot_status
  clocksource/arm_arch_timer: Use arch_timer_read_counter to access stable counters
  clocksource/arm_arch_timer: Remove use of workaround static key
  clocksource/arm_arch_timer: Drop use of static key in arch_timer_reg_read_stable
  clocksource/arm_arch_timer: Direcly assign set_next_event workaround
  arm64: Use arch_timer_read_counter instead of arch_counter_get_cntvct
  watchdog/sbsa: Use arch_timer_read_counter instead of arch_counter_get_cntvct
  ARM: vdso: Remove dependency with the arch_timer driver internals
  arm64: Apply ARM64_ERRATUM_1188873 to Neoverse-N1
  arm64: Add part number for Neoverse N1
  arm64: Make ARM64_ERRATUM_1188873 depend on COMPAT
  arm64: Restrict ARM64_ERRATUM_1188873 mitigation to AArch32
  arm64: mm: Remove pte_unmap_nested()
  arm64: Fix compiler warning from pte_unmap() with -Wunused-but-set-variable
  arm64: compat: Reduce address limit for 64K pages
  ...

1 files changed, 37 insertions, 22 deletions

diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index c7e1a7837706..a56efb5626fa 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -23,26 +23,34 @@
 
 #include <asm/errno.h>
 
+#define FUTEX_MAX_LOOPS	128 /* What's the largest number you can think of? */
+
 #define __futex_atomic_op(insn, ret, oldval, uaddr, tmp, oparg)		\
 do {									\
+	unsigned int loops = FUTEX_MAX_LOOPS;				\
+									\
 	uaccess_enable();						\
 	asm volatile(							\
 "	prfm	pstl1strm, %2\n"					\
 "1:	ldxr	%w1, %2\n"						\
 	insn "\n"							\
 "2:	stlxr	%w0, %w3, %2\n"						\
-"	cbnz	%w0, 1b\n"						\
-"	dmb	ish\n"							\
+"	cbz	%w0, 3f\n"						\
+"	sub	%w4, %w4, %w0\n"					\
+"	cbnz	%w4, 1b\n"						\
+"	mov	%w0, %w7\n"						\
 "3:\n"									\
+"	dmb	ish\n"							\
 "	.pushsection .fixup,\"ax\"\n"					\
 "	.align	2\n"							\
-"4:	mov	%w0, %w5\n"						\
+"4:	mov	%w0, %w6\n"						\
 "	b	3b\n"							\
 "	.popsection\n"							\
 	_ASM_EXTABLE(1b, 4b)						\
 	_ASM_EXTABLE(2b, 4b)						\
-	: "=&r" (ret), "=&r" (oldval), "+Q" (*uaddr), "=&r" (tmp)	\
-	: "r" (oparg), "Ir" (-EFAULT)					\
+	: "=&r" (ret), "=&r" (oldval), "+Q" (*uaddr), "=&r" (tmp),	\
+	  "+r" (loops)							\
+	: "r" (oparg), "Ir" (-EFAULT), "Ir" (-EAGAIN)			\
 	: "memory");							\
 	uaccess_disable();						\
 } while (0)
@@ -57,23 +65,23 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *_uaddr)
 
 	switch (op) {
 	case FUTEX_OP_SET:
-		__futex_atomic_op("mov	%w3, %w4",
+		__futex_atomic_op("mov	%w3, %w5",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	case FUTEX_OP_ADD:
-		__futex_atomic_op("add	%w3, %w1, %w4",
+		__futex_atomic_op("add	%w3, %w1, %w5",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	case FUTEX_OP_OR:
-		__futex_atomic_op("orr	%w3, %w1, %w4",
+		__futex_atomic_op("orr	%w3, %w1, %w5",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	case FUTEX_OP_ANDN:
-		__futex_atomic_op("and	%w3, %w1, %w4",
+		__futex_atomic_op("and	%w3, %w1, %w5",
 				  ret, oldval, uaddr, tmp, ~oparg);
 		break;
 	case FUTEX_OP_XOR:
-		__futex_atomic_op("eor	%w3, %w1, %w4",
+		__futex_atomic_op("eor	%w3, %w1, %w5",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	default:
@@ -93,6 +101,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *_uaddr,
 			      u32 oldval, u32 newval)
 {
 	int ret = 0;
+	unsigned int loops = FUTEX_MAX_LOOPS;
 	u32 val, tmp;
 	u32 __user *uaddr;
 
@@ -104,24 +113,30 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *_uaddr,
 	asm volatile("// futex_atomic_cmpxchg_inatomic\n"
 "	prfm	pstl1strm, %2\n"
 "1:	ldxr	%w1, %2\n"
-"	sub	%w3, %w1, %w4\n"
-"	cbnz	%w3, 3f\n"
-"2:	stlxr	%w3, %w5, %2\n"
-"	cbnz	%w3, 1b\n"
-"	dmb	ish\n"
+"	sub	%w3, %w1, %w5\n"
+"	cbnz	%w3, 4f\n"
+"2:	stlxr	%w3, %w6, %2\n"
+"	cbz	%w3, 3f\n"
+"	sub	%w4, %w4, %w3\n"
+"	cbnz	%w4, 1b\n"
+"	mov	%w0, %w8\n"
 "3:\n"
+"	dmb	ish\n"
+"4:\n"
 "	.pushsection .fixup,\"ax\"\n"
-"4:	mov	%w0, %w6\n"
-"	b	3b\n"
+"5:	mov	%w0, %w7\n"
+"	b	4b\n"
 "	.popsection\n"
-	_ASM_EXTABLE(1b, 4b)
-	_ASM_EXTABLE(2b, 4b)
-	: "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp)
-	: "r" (oldval), "r" (newval), "Ir" (-EFAULT)
+	_ASM_EXTABLE(1b, 5b)
+	_ASM_EXTABLE(2b, 5b)
+	: "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp), "+r" (loops)
+	: "r" (oldval), "r" (newval), "Ir" (-EFAULT), "Ir" (-EAGAIN)
 	: "memory");
 	uaccess_disable();
 
-	*uval = val;
+	if (!ret)
+		*uval = val;
+
 	return ret;
 }