Merge branch 'for-linus' of git://git.linaro.org/people/rmk/linux-arm

Pull second set of ARM updates from Russell King:
 "This is the second set of ARM updates for this merge window.

  Contained within are changes to allow the kernel to boot in hypervisor
  mode on CPUs supporting virtualization, and cache flushing support to
  the point of inner sharable unification, which are used by the
  suspend/resume code to avoid having to do a full cache flush.

  Also included is one fix for VFP code identified by Michael Olbrich."

* 'for-linus' of git://git.linaro.org/people/rmk/linux-arm:
  ARM: vfp: fix saving d16-d31 vfp registers on v6+ kernels
  ARM: 7549/1: HYP: fix boot on some ARM1136 cores
  ARM: 7542/1: mm: fix cache LoUIS API for xscale and feroceon
  ARM: mm: update __v7_setup() to the new LoUIS cache maintenance API
  ARM: kernel: update __cpu_disable to use cache LoUIS maintenance API
  ARM: kernel: update cpu_suspend code to use cache LoUIS operations
  ARM: mm: rename jump labels in v7_flush_dcache_all function
  ARM: mm: implement LoUIS API for cache maintenance ops
  ARM: virt: arch_timers: enable access to physical timers
  ARM: virt: Add CONFIG_ARM_VIRT_EXT option
  ARM: virt: Add boot-time diagnostics
  ARM: virt: Update documentation for hyp mode entry support
  ARM: zImage/virt: hyp mode entry support for the zImage loader
  ARM: virt: allow the kernel to be entered in HYP mode
  ARM: opcodes: add __ERET/__MSR_ELR_HYP instruction encoding

24 files changed, 123 insertions, 7 deletions

diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 101b9681c08c..c9a4963b5c3d 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -624,6 +624,23 @@ config ARM_THUMBEE
           Say Y here if you have a CPU with the ThumbEE extension and code to
           make use of it. Say N for code that can run on CPUs without ThumbEE.
 
+config ARM_VIRT_EXT
+        bool "Native support for the ARM Virtualization Extensions"
+        depends on MMU && CPU_V7
+        help
+          Enable the kernel to make use of the ARM Virtualization
+          Extensions to install hypervisors without run-time firmware
+          assistance.
+
+          A compliant bootloader is required in order to make maximum
+          use of this feature.  Refer to Documentation/arm/Booting for
+          details.
+
+          It is safe to enable this option even if the kernel may not be
+          booted in HYP mode, may not have support for the
+          virtualization extensions, or may be booted with a
+          non-compliant bootloader.
+
 config SWP_EMULATE
         bool "Emulate SWP/SWPB instructions"
         depends on !CPU_USE_DOMAINS && CPU_V7
diff --git a/arch/arm/mm/cache-fa.S b/arch/arm/mm/cache-fa.S
index 072016371093..e505befe51b5 100644
--- a/arch/arm/mm/cache-fa.S
+++ b/arch/arm/mm/cache-fa.S
@@ -240,6 +240,9 @@ ENTRY(fa_dma_unmap_area)
         mov     pc, lr
 ENDPROC(fa_dma_unmap_area)
 
+        .globl  fa_flush_kern_cache_louis
+        .equ    fa_flush_kern_cache_louis, fa_flush_kern_cache_all
+
         __INITDATA
 
         @ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
diff --git a/arch/arm/mm/cache-v3.S b/arch/arm/mm/cache-v3.S
index 52e35f32eefb..8a3fadece8d3 100644
--- a/arch/arm/mm/cache-v3.S
+++ b/arch/arm/mm/cache-v3.S
@@ -128,6 +128,9 @@ ENTRY(v3_dma_map_area)
 ENDPROC(v3_dma_unmap_area)
 ENDPROC(v3_dma_map_area)
 
+        .globl  v3_flush_kern_cache_louis
+        .equ    v3_flush_kern_cache_louis, v3_flush_kern_cache_all
+
         __INITDATA
 
         @ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
diff --git a/arch/arm/mm/cache-v4.S b/arch/arm/mm/cache-v4.S
index 022135d2b7e4..43e5d77be677 100644
--- a/arch/arm/mm/cache-v4.S
+++ b/arch/arm/mm/cache-v4.S
@@ -140,6 +140,9 @@ ENTRY(v4_dma_map_area)
 ENDPROC(v4_dma_unmap_area)
 ENDPROC(v4_dma_map_area)
 
+        .globl  v4_flush_kern_cache_louis
+        .equ    v4_flush_kern_cache_louis, v4_flush_kern_cache_all
+
         __INITDATA
 
         @ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
diff --git a/arch/arm/mm/cache-v4wb.S b/arch/arm/mm/cache-v4wb.S
index 8f1eeae340c8..cd4945321407 100644
--- a/arch/arm/mm/cache-v4wb.S
+++ b/arch/arm/mm/cache-v4wb.S
@@ -251,6 +251,9 @@ ENTRY(v4wb_dma_unmap_area)
         mov     pc, lr
 ENDPROC(v4wb_dma_unmap_area)
 
+        .globl  v4wb_flush_kern_cache_louis
+        .equ    v4wb_flush_kern_cache_louis, v4wb_flush_kern_cache_all
+
         __INITDATA
 
         @ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
diff --git a/arch/arm/mm/cache-v4wt.S b/arch/arm/mm/cache-v4wt.S
index b34a5f908a82..11e5e5838bc5 100644
--- a/arch/arm/mm/cache-v4wt.S
+++ b/arch/arm/mm/cache-v4wt.S
@@ -196,6 +196,9 @@ ENTRY(v4wt_dma_map_area)
 ENDPROC(v4wt_dma_unmap_area)
 ENDPROC(v4wt_dma_map_area)
 
+        .globl  v4wt_flush_kern_cache_louis
+        .equ    v4wt_flush_kern_cache_louis, v4wt_flush_kern_cache_all
+
         __INITDATA
 
         @ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
diff --git a/arch/arm/mm/cache-v6.S b/arch/arm/mm/cache-v6.S
index 4b10760c56d6..d8fd4d4bd3d4 100644
--- a/arch/arm/mm/cache-v6.S
+++ b/arch/arm/mm/cache-v6.S
@@ -326,6 +326,9 @@ ENTRY(v6_dma_unmap_area)
         mov     pc, lr
 ENDPROC(v6_dma_unmap_area)
 
+        .globl  v6_flush_kern_cache_louis
+        .equ    v6_flush_kern_cache_louis, v6_flush_kern_cache_all
+
         __INITDATA
 
         @ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 3b172275262e..cd956647c21a 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -33,6 +33,24 @@ ENTRY(v7_flush_icache_all)
         mov     pc, lr
 ENDPROC(v7_flush_icache_all)
 
+ /*
+ *     v7_flush_dcache_louis()
+ *
+ *     Flush the D-cache up to the Level of Unification Inner Shareable
+ *
+ *     Corrupted registers: r0-r7, r9-r11 (r6 only in Thumb mode)
+ */
+
+ENTRY(v7_flush_dcache_louis)
+        dmb                                     @ ensure ordering with previous memory accesses
+        mrc     p15, 1, r0, c0, c0, 1           @ read clidr, r0 = clidr
+        ands    r3, r0, #0xe00000               @ extract LoUIS from clidr
+        mov     r3, r3, lsr #20                 @ r3 = LoUIS * 2
+        moveq   pc, lr                          @ return if level == 0
+        mov     r10, #0                         @ r10 (starting level) = 0
+        b       flush_levels                    @ start flushing cache levels
+ENDPROC(v7_flush_dcache_louis)
+
 /*
  *      v7_flush_dcache_all()
  *
@@ -49,7 +67,7 @@ ENTRY(v7_flush_dcache_all)
         mov     r3, r3, lsr #23                 @ left align loc bit field
         beq     finished                        @ if loc is 0, then no need to clean
         mov     r10, #0                         @ start clean at cache level 0
-loop1:
+flush_levels:
         add     r2, r10, r10, lsr #1            @ work out 3x current cache level
         mov     r1, r0, lsr r2                  @ extract cache type bits from clidr
         and     r1, r1, #7                      @ mask of the bits for current cache only
@@ -71,9 +89,9 @@ loop1:
         clz     r5, r4                          @ find bit position of way size increment
         ldr     r7, =0x7fff
         ands    r7, r7, r1, lsr #13             @ extract max number of the index size
-loop2:
+loop1:
         mov     r9, r4                          @ create working copy of max way size
-loop3:
+loop2:
  ARM(   orr     r11, r10, r9, lsl r5    )       @ factor way and cache number into r11
  THUMB( lsl     r6, r9, r5              )
  THUMB( orr     r11, r10, r6            )       @ factor way and cache number into r11
@@ -82,13 +100,13 @@ loop3:
  THUMB( orr     r11, r11, r6            )       @ factor index number into r11
         mcr     p15, 0, r11, c7, c14, 2         @ clean & invalidate by set/way
         subs    r9, r9, #1                      @ decrement the way
-        bge     loop3
-        subs    r7, r7, #1                      @ decrement the index
         bge     loop2
+        subs    r7, r7, #1                      @ decrement the index
+        bge     loop1
 skip:
         add     r10, r10, #2                    @ increment cache number
         cmp     r3, r10
-        bgt     loop1
+        bgt     flush_levels
 finished:
         mov     r10, #0                         @ swith back to cache level 0
         mcr     p15, 2, r10, c0, c0, 0          @ select current cache level in cssr
@@ -120,6 +138,24 @@ ENTRY(v7_flush_kern_cache_all)
         mov     pc, lr
 ENDPROC(v7_flush_kern_cache_all)
 
+ /*
+ *     v7_flush_kern_cache_louis(void)
+ *
+ *     Flush the data cache up to Level of Unification Inner Shareable.
+ *     Invalidate the I-cache to the point of unification.
+ */
+ENTRY(v7_flush_kern_cache_louis)
+ ARM(   stmfd   sp!, {r4-r5, r7, r9-r11, lr}    )
+ THUMB( stmfd   sp!, {r4-r7, r9-r11, lr}        )
+        bl      v7_flush_dcache_louis
+        mov     r0, #0
+        ALT_SMP(mcr     p15, 0, r0, c7, c1, 0)  @ invalidate I-cache inner shareable
+        ALT_UP(mcr      p15, 0, r0, c7, c5, 0)  @ I+BTB cache invalidate
+ ARM(   ldmfd   sp!, {r4-r5, r7, r9-r11, lr}    )
+ THUMB( ldmfd   sp!, {r4-r7, r9-r11, lr}        )
+        mov     pc, lr
+ENDPROC(v7_flush_kern_cache_louis)
+
 /*
  *      v7_flush_cache_all()
  *
diff --git a/arch/arm/mm/proc-arm1020.S b/arch/arm/mm/proc-arm1020.S
index 0650bb87c1e3..2bb61e703d6c 100644
--- a/arch/arm/mm/proc-arm1020.S
+++ b/arch/arm/mm/proc-arm1020.S
@@ -368,6 +368,9 @@ ENTRY(arm1020_dma_unmap_area)
         mov     pc, lr
 ENDPROC(arm1020_dma_unmap_area)
 
+        .globl  arm1020_flush_kern_cache_louis
+        .equ    arm1020_flush_kern_cache_louis, arm1020_flush_kern_cache_all
+
         @ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
         define_cache_functions arm1020
 
diff --git a/arch/arm/mm/proc-arm1020e.S b/arch/arm/mm/proc-arm1020e.S
index 4188478325a6..8f96aa40f510 100644
--- a/arch/arm/mm/proc-arm1020e.S
+++ b/arch/arm/mm/proc-arm1020e.S
@@ -354,6 +354,9 @@ ENTRY(arm1020e_dma_unmap_area)
         mov     pc, lr
 ENDPROC(arm1020e_dma_unmap_area)
 
+        .globl  arm1020e_flush_kern_cache_louis
+        .equ    arm1020e_flush_kern_cache_louis, arm1020e_flush_kern_cache_all
+
         @ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
         define_cache_functions arm1020e
 
diff --git a/arch/arm/mm/proc-arm1022.S b/arch/arm/mm/proc-arm1022.S
index 33c68824bff0..8ebe4a469a22 100644
--- a/arch/arm/mm/proc-arm1022.S
+++ b/arch/arm/mm/proc-arm1022.S
@@ -343,6 +343,9 @@ ENTRY(arm1022_dma_unmap_area)
         mov     pc, lr
 ENDPROC(arm1022_dma_unmap_area)
 
+        .globl  arm1022_flush_kern_cache_louis
+        .equ    arm1022_flush_kern_cache_louis, arm1022_flush_kern_cache_all
+
         @ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
         define_cache_functions arm1022
 
diff --git a/arch/arm/mm/proc-arm1026.S b/arch/arm/mm/proc-arm1026.S
index fbc1d5fc24dc..093fc7e520c3 100644
--- a/arch/arm/mm/proc-arm1026.S
+++ b/arch/arm/mm/proc-arm1026.S
@@ -337,6 +337,9 @@ ENTRY(arm1026_dma_unmap_area)
         mov     pc, lr
 ENDPROC(arm1026_dma_unmap_area)
 
+        .globl  arm1026_flush_kern_cache_louis
+        .equ    arm1026_flush_kern_cache_louis, arm1026_flush_kern_cache_all
+
         @ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
         define_cache_functions arm1026
 
diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S
index 1a8c138eb897..2c3b9421ab5e 100644
--- a/arch/arm/mm/proc-arm920.S
+++ b/arch/arm/mm/proc-arm920.S
@@ -319,6 +319,9 @@ ENTRY(arm920_dma_unmap_area)
         mov     pc, lr
 ENDPROC(arm920_dma_unmap_area)
 
+        .globl  arm920_flush_kern_cache_louis
+        .equ    arm920_flush_kern_cache_louis, arm920_flush_kern_cache_all
+
         @ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
         define_cache_functions arm920
 #endif
diff --git a/arch/arm/mm/proc-arm922.S b/arch/arm/mm/proc-arm922.S
index 4c44d7e1c3ca..4464c49d7449 100644
--- a/arch/arm/mm/proc-arm922.S
+++ b/arch/arm/mm/proc-arm922.S
@@ -321,6 +321,9 @@ ENTRY(arm922_dma_unmap_area)
         mov     pc, lr
 ENDPROC(arm922_dma_unmap_area)
 
+        .globl  arm922_flush_kern_cache_louis
+        .equ    arm922_flush_kern_cache_louis, arm922_flush_kern_cache_all
+
         @ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
         define_cache_functions arm922
 #endif
diff --git a/arch/arm/mm/proc-arm925.S b/arch/arm/mm/proc-arm925.S
index ec5b1180994f..281eb9b9c1d6 100644
--- a/arch/arm/mm/proc-arm925.S
+++ b/arch/arm/mm/proc-arm925.S
@@ -376,6 +376,9 @@ ENTRY(arm925_dma_unmap_area)
         mov     pc, lr
 ENDPROC(arm925_dma_unmap_area)
 
+        .globl  arm925_flush_kern_cache_louis
+        .equ    arm925_flush_kern_cache_louis, arm925_flush_kern_cache_all
+
         @ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
         define_cache_functions arm925
 
diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S
index c31e62c606c0..f1803f7e2972 100644
--- a/arch/arm/mm/proc-arm926.S
+++ b/arch/arm/mm/proc-arm926.S
@@ -339,6 +339,9 @@ ENTRY(arm926_dma_unmap_area)
         mov     pc, lr
 ENDPROC(arm926_dma_unmap_area)
 
+        .globl  arm926_flush_kern_cache_louis
+        .equ    arm926_flush_kern_cache_louis, arm926_flush_kern_cache_all
+
         @ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
         define_cache_functions arm926
 
diff --git a/arch/arm/mm/proc-arm940.S b/arch/arm/mm/proc-arm940.S
index a613a7dd7146..8da189d4a402 100644
--- a/arch/arm/mm/proc-arm940.S
+++ b/arch/arm/mm/proc-arm940.S
@@ -267,6 +267,9 @@ ENTRY(arm940_dma_unmap_area)
         mov     pc, lr
 ENDPROC(arm940_dma_unmap_area)
 
+        .globl  arm940_flush_kern_cache_louis
+        .equ    arm940_flush_kern_cache_louis, arm940_flush_kern_cache_all
+
         @ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
         define_cache_functions arm940
 
diff --git a/arch/arm/mm/proc-arm946.S b/arch/arm/mm/proc-arm946.S
index 9f4f2999fdd0..f666cf34075a 100644
--- a/arch/arm/mm/proc-arm946.S
+++ b/arch/arm/mm/proc-arm946.S
@@ -310,6 +310,9 @@ ENTRY(arm946_dma_unmap_area)
         mov     pc, lr
 ENDPROC(arm946_dma_unmap_area)
 
+        .globl  arm946_flush_kern_cache_louis
+        .equ    arm946_flush_kern_cache_louis, arm946_flush_kern_cache_all
+
         @ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
         define_cache_functions arm946
 
diff --git a/arch/arm/mm/proc-feroceon.S b/arch/arm/mm/proc-feroceon.S
index 23a8e4c7f2bd..4106b09e0c29 100644
--- a/arch/arm/mm/proc-feroceon.S
+++ b/arch/arm/mm/proc-feroceon.S
@@ -415,6 +415,9 @@ ENTRY(feroceon_dma_unmap_area)
         mov     pc, lr
 ENDPROC(feroceon_dma_unmap_area)
 
+        .globl  feroceon_flush_kern_cache_louis
+        .equ    feroceon_flush_kern_cache_louis, feroceon_flush_kern_cache_all
+
         @ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
         define_cache_functions feroceon
 
@@ -431,6 +434,7 @@ ENDPROC(feroceon_dma_unmap_area)
         range_alias flush_icache_all
         range_alias flush_user_cache_all
         range_alias flush_kern_cache_all
+        range_alias flush_kern_cache_louis
         range_alias flush_user_cache_range
         range_alias coherent_kern_range
         range_alias coherent_user_range
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index 2d8ff3ad86d3..b29a2265af01 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -299,6 +299,7 @@ ENTRY(\name\()_processor_functions)
 ENTRY(\name\()_cache_fns)
         .long   \name\()_flush_icache_all
         .long   \name\()_flush_kern_cache_all
+        .long   \name\()_flush_kern_cache_louis
         .long   \name\()_flush_user_cache_all
         .long   \name\()_flush_user_cache_range
         .long   \name\()_coherent_kern_range
diff --git a/arch/arm/mm/proc-mohawk.S b/arch/arm/mm/proc-mohawk.S
index fbb2124a547d..82f9cdc751d6 100644
--- a/arch/arm/mm/proc-mohawk.S
+++ b/arch/arm/mm/proc-mohawk.S
@@ -303,6 +303,9 @@ ENTRY(mohawk_dma_unmap_area)
         mov     pc, lr
 ENDPROC(mohawk_dma_unmap_area)
 
+        .globl  mohawk_flush_kern_cache_louis
+        .equ    mohawk_flush_kern_cache_louis, mohawk_flush_kern_cache_all
+
         @ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
         define_cache_functions mohawk
 
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index c2e2b66f72b5..846d279f3176 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -172,7 +172,7 @@ __v7_ca15mp_setup:
 __v7_setup:
         adr     r12, __v7_setup_stack           @ the local stack
         stmia   r12, {r0-r5, r7, r9, r11, lr}
-        bl      v7_flush_dcache_all
+        bl      v7_flush_dcache_louis
         ldmia   r12, {r0-r5, r7, r9, r11, lr}
 
         mrc     p15, 0, r0, c0, c0, 0           @ read main ID register
diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S
index b0d57869da2d..eb93d6487f35 100644
--- a/arch/arm/mm/proc-xsc3.S
+++ b/arch/arm/mm/proc-xsc3.S
@@ -337,6 +337,9 @@ ENTRY(xsc3_dma_unmap_area)
         mov     pc, lr
 ENDPROC(xsc3_dma_unmap_area)
 
+        .globl  xsc3_flush_kern_cache_louis
+        .equ    xsc3_flush_kern_cache_louis, xsc3_flush_kern_cache_all
+
         @ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
         define_cache_functions xsc3
 
diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S
index 4ffebaa595ee..25510361aa18 100644
--- a/arch/arm/mm/proc-xscale.S
+++ b/arch/arm/mm/proc-xscale.S
@@ -410,6 +410,9 @@ ENTRY(xscale_dma_unmap_area)
         mov     pc, lr
 ENDPROC(xscale_dma_unmap_area)
 
+        .globl  xscale_flush_kern_cache_louis
+        .equ    xscale_flush_kern_cache_louis, xscale_flush_kern_cache_all
+
         @ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
         define_cache_functions xscale
 
@@ -439,6 +442,7 @@ ENDPROC(xscale_dma_unmap_area)
         a0_alias flush_icache_all
         a0_alias flush_user_cache_all
         a0_alias flush_kern_cache_all
+        a0_alias flush_kern_cache_louis
         a0_alias flush_user_cache_range
         a0_alias coherent_kern_range
         a0_alias coherent_user_range