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

Pull arm64 updates from Will Deacon:
 "It's a bit all over the place this time with no "killer feature" to
  speak of.  Support for mismatched cache line sizes should help people
  seeing whacky JIT failures on some SoCs, and the big.LITTLE perf
  updates have been a long time coming, but a lot of the changes here
  are cleanups.

  We stray outside arch/arm64 in a few areas: the arch/arm/ arch_timer
  workaround is acked by Russell, the DT/OF bits are acked by Rob, the
  arch_timer clocksource changes acked by Marc, CPU hotplug by tglx and
  jump_label by Peter (all CC'd).

  Summary:

   - Support for execute-only page permissions
   - Support for hibernate and DEBUG_PAGEALLOC
   - Support for heterogeneous systems with mismatches cache line sizes
   - Errata workarounds (A53 843419 update and QorIQ A-008585 timer bug)
   - arm64 PMU perf updates, including cpumasks for heterogeneous systems
   - Set UTS_MACHINE for building rpm packages
   - Yet another head.S tidy-up
   - Some cleanups and refactoring, particularly in the NUMA code
   - Lots of random, non-critical fixes across the board"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (100 commits)
  arm64: tlbflush.h: add __tlbi() macro
  arm64: Kconfig: remove SMP dependence for NUMA
  arm64: Kconfig: select OF/ACPI_NUMA under NUMA config
  arm64: fix dump_backtrace/unwind_frame with NULL tsk
  arm/arm64: arch_timer: Use archdata to indicate vdso suitability
  arm64: arch_timer: Work around QorIQ Erratum A-008585
  arm64: arch_timer: Add device tree binding for A-008585 erratum
  arm64: Correctly bounds check virt_addr_valid
  arm64: migrate exception table users off module.h and onto extable.h
  arm64: pmu: Hoist pmu platform device name
  arm64: pmu: Probe default hw/cache counters
  arm64: pmu: add fallback probe table
  MAINTAINERS: Update ARM PMU PROFILING AND DEBUGGING entry
  arm64: Improve kprobes test for atomic sequence
  arm64/kvm: use alternative auto-nop
  arm64: use alternative auto-nop
  arm64: alternative: add auto-nop infrastructure
  arm64: lse: convert lse alternatives NOP padding to use __nops
  arm64: barriers: introduce nops and __nops macros for NOP sequences
  arm64: sysreg: replace open-coded mrs_s/msr_s with {read,write}_sysreg_s
  ...

1 files changed, 39 insertions, 43 deletions

diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 07d7352d7c38..58b5a906ff78 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -105,19 +105,20 @@ ENTRY(__clean_dcache_area_pou)
 ENDPROC(__clean_dcache_area_pou)
 
 /*
- *	__inval_cache_range(start, end)
- *	- start   - start address of region
- *	- end     - end address of region
+ *	__dma_inv_area(start, size)
+ *	- start   - virtual start address of region
+ *	- size    - size in question
  */
-ENTRY(__inval_cache_range)
+__dma_inv_area:
+	add	x1, x1, x0
 	/* FALLTHROUGH */
 
 /*
- *	__dma_inv_range(start, end)
- *	- start   - virtual start address of region
- *	- end     - virtual end address of region
+ *	__inval_cache_range(start, end)
+ *	- start   - start address of region
+ *	- end     - end address of region
  */
-__dma_inv_range:
+ENTRY(__inval_cache_range)
 	dcache_line_size x2, x3
 	sub	x3, x2, #1
 	tst	x1, x3				// end cache line aligned?
@@ -136,46 +137,43 @@ __dma_inv_range:
 	dsb	sy
 	ret
 ENDPIPROC(__inval_cache_range)
-ENDPROC(__dma_inv_range)
+ENDPROC(__dma_inv_area)
+
+/*
+ *	__clean_dcache_area_poc(kaddr, size)
+ *
+ * 	Ensure that any D-cache lines for the interval [kaddr, kaddr+size)
+ * 	are cleaned to the PoC.
+ *
+ *	- kaddr   - kernel address
+ *	- size    - size in question
+ */
+ENTRY(__clean_dcache_area_poc)
+	/* FALLTHROUGH */
 
 /*
- *	__dma_clean_range(start, end)
+ *	__dma_clean_area(start, size)
  *	- start   - virtual start address of region
- *	- end     - virtual end address of region
+ *	- size    - size in question
  */
-__dma_clean_range:
-	dcache_line_size x2, x3
-	sub	x3, x2, #1
-	bic	x0, x0, x3
-1:
-alternative_if_not ARM64_WORKAROUND_CLEAN_CACHE
-	dc	cvac, x0
-alternative_else
-	dc	civac, x0
-alternative_endif
-	add	x0, x0, x2
-	cmp	x0, x1
-	b.lo	1b
-	dsb	sy
+__dma_clean_area:
+	dcache_by_line_op cvac, sy, x0, x1, x2, x3
 	ret
-ENDPROC(__dma_clean_range)
+ENDPIPROC(__clean_dcache_area_poc)
+ENDPROC(__dma_clean_area)
 
 /*
- *	__dma_flush_range(start, end)
+ *	__dma_flush_area(start, size)
+ *
+ *	clean & invalidate D / U line
+ *
  *	- start   - virtual start address of region
- *	- end     - virtual end address of region
+ *	- size    - size in question
  */
-ENTRY(__dma_flush_range)
-	dcache_line_size x2, x3
-	sub	x3, x2, #1
-	bic	x0, x0, x3
-1:	dc	civac, x0			// clean & invalidate D / U line
-	add	x0, x0, x2
-	cmp	x0, x1
-	b.lo	1b
-	dsb	sy
+ENTRY(__dma_flush_area)
+	dcache_by_line_op civac, sy, x0, x1, x2, x3
 	ret
-ENDPIPROC(__dma_flush_range)
+ENDPIPROC(__dma_flush_area)
 
 /*
  *	__dma_map_area(start, size, dir)
@@ -184,10 +182,9 @@ ENDPIPROC(__dma_flush_range)
  *	- dir	- DMA direction
  */
 ENTRY(__dma_map_area)
-	add	x1, x1, x0
 	cmp	w2, #DMA_FROM_DEVICE
-	b.eq	__dma_inv_range
-	b	__dma_clean_range
+	b.eq	__dma_inv_area
+	b	__dma_clean_area
 ENDPIPROC(__dma_map_area)
 
 /*
@@ -197,8 +194,7 @@ ENDPIPROC(__dma_map_area)
  *	- dir	- DMA direction
  */
 ENTRY(__dma_unmap_area)
-	add	x1, x1, x0
 	cmp	w2, #DMA_TO_DEVICE
-	b.ne	__dma_inv_range
+	b.ne	__dma_inv_area
 	ret
 ENDPIPROC(__dma_unmap_area)