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

Pull arm64 updates from Will Deacon:
 "The big highlight is support for the Scalable Vector Extension (SVE)
  which required extensive ABI work to ensure we don't break existing
  applications by blowing away their signal stack with the rather large
  new vector context (<= 2 kbit per vector register). There's further
  work to be done optimising things like exception return, but the ABI
  is solid now.

  Much of the line count comes from some new PMU drivers we have, but
  they're pretty self-contained and I suspect we'll have more of them in
  future.

  Plenty of acronym soup here:

   - initial support for the Scalable Vector Extension (SVE)

   - improved handling for SError interrupts (required to handle RAS
     events)

   - enable GCC support for 128-bit integer types

   - remove kernel text addresses from backtraces and register dumps

   - use of WFE to implement long delay()s

   - ACPI IORT updates from Lorenzo Pieralisi

   - perf PMU driver for the Statistical Profiling Extension (SPE)

   - perf PMU driver for Hisilicon's system PMUs

   - misc cleanups and non-critical fixes"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (97 commits)
  arm64: Make ARMV8_DEPRECATED depend on SYSCTL
  arm64: Implement __lshrti3 library function
  arm64: support __int128 on gcc 5+
  arm64/sve: Add documentation
  arm64/sve: Detect SVE and activate runtime support
  arm64/sve: KVM: Hide SVE from CPU features exposed to guests
  arm64/sve: KVM: Treat guest SVE use as undefined instruction execution
  arm64/sve: KVM: Prevent guests from using SVE
  arm64/sve: Add sysctl to set the default vector length for new processes
  arm64/sve: Add prctl controls for userspace vector length management
  arm64/sve: ptrace and ELF coredump support
  arm64/sve: Preserve SVE registers around EFI runtime service calls
  arm64/sve: Preserve SVE registers around kernel-mode NEON use
  arm64/sve: Probe SVE capabilities and usable vector lengths
  arm64: cpufeature: Move sys_caps_initialised declarations
  arm64/sve: Backend logic for setting the vector length
  arm64/sve: Signal handling support
  arm64/sve: Support vector length resetting for new processes
  arm64/sve: Core task context handling
  arm64/sve: Low-level CPU setup
  ...

1 files changed, 32 insertions, 19 deletions

diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index d58a6253c6ab..aef72d886677 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -25,12 +25,41 @@
 
 #include <asm/asm-offsets.h>
 #include <asm/cpufeature.h>
+#include <asm/debug-monitors.h>
 #include <asm/mmu_context.h>
 #include <asm/page.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/ptrace.h>
 #include <asm/thread_info.h>
 
+	.macro save_and_disable_daif, flags
+	mrs	\flags, daif
+	msr	daifset, #0xf
+	.endm
+
+	.macro disable_daif
+	msr	daifset, #0xf
+	.endm
+
+	.macro enable_daif
+	msr	daifclr, #0xf
+	.endm
+
+	.macro	restore_daif, flags:req
+	msr	daif, \flags
+	.endm
+
+	/* Only on aarch64 pstate, PSR_D_BIT is different for aarch32 */
+	.macro	inherit_daif, pstate:req, tmp:req
+	and	\tmp, \pstate, #(PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT)
+	msr	daif, \tmp
+	.endm
+
+	/* IRQ is the lowest priority flag, unconditionally unmask the rest. */
+	.macro enable_da_f
+	msr	daifclr, #(8 | 4 | 1)
+	.endm
+
 /*
  * Enable and disable interrupts.
  */
@@ -51,13 +80,6 @@
 	msr	daif, \flags
 	.endm
 
-/*
- * Enable and disable debug exceptions.
- */
-	.macro	disable_dbg
-	msr	daifset, #8
-	.endm
-
 	.macro	enable_dbg
 	msr	daifclr, #8
 	.endm
@@ -65,31 +87,22 @@
 	.macro	disable_step_tsk, flgs, tmp
 	tbz	\flgs, #TIF_SINGLESTEP, 9990f
 	mrs	\tmp, mdscr_el1
-	bic	\tmp, \tmp, #1
+	bic	\tmp, \tmp, #DBG_MDSCR_SS
 	msr	mdscr_el1, \tmp
 	isb	// Synchronise with enable_dbg
 9990:
 	.endm
 
+	/* call with daif masked */
 	.macro	enable_step_tsk, flgs, tmp
 	tbz	\flgs, #TIF_SINGLESTEP, 9990f
-	disable_dbg
 	mrs	\tmp, mdscr_el1
-	orr	\tmp, \tmp, #1
+	orr	\tmp, \tmp, #DBG_MDSCR_SS
 	msr	mdscr_el1, \tmp
 9990:
 	.endm
 
 /*
- * Enable both debug exceptions and interrupts. This is likely to be
- * faster than two daifclr operations, since writes to this register
- * are self-synchronising.
- */
-	.macro	enable_dbg_and_irq
-	msr	daifclr, #(8 | 2)
-	.endm
-
-/*
  * SMP data memory barrier
  */
 	.macro	smp_dmb, opt