Merge branch 'android-goldfish-3.10' into genymotion-goldfish-3.10

* android-goldfish-3.10: (252 commits)
  platform: goldfish: pipe: don't log when dropping PIPE_ERROR_AGAIN
  platform: goldfish: pipe: add devicetree bindings
  arm64: ranchu: regenerate minimal defconfig
  arm64: Add ranchu defconfig
  goldfish_fb: Set pixclock = 0
  android_pipe: Pin pages to memory while copying and other cleanups
  android_pipe: don't be clever with #define offsets
  arm64: kernel: fix per-cpu offset restore on resume
  arm64: kernel: restore HW breakpoint registers in cpu_suspend
  arm64: hw_breakpoint compile error fixing
  arm64: kernel: add MPIDR_EL1 accessors macros
  arm64: add CPU power management menu/entries
  arm64: kernel: add PM build infrastructure
  arm64: kernel: add CPU idle call
  arm64: enable generic clockevent broadcast
  arm64: kernel: implement HW breakpoints CPU PM notifier
  arm64: kernel: refactor code to install/uninstall breakpoints
  arm: kvm: implement CPU PM notifier
  arm64: kernel: implement fpsimd CPU PM notifier
  arm64: kernel: cpu_{suspend/resume} implementation
  ...

Documentation/DMA-API-HOWTO.txt

@@ -101,14 +101,23 @@ style to do this even if your device holds the default setting,
 because this shows that you did think about these issues wrt. your
 device.
 
-The query is performed via a call to dma_set_mask():
+The query is performed via a call to dma_set_mask_and_coherent():
 
-	int dma_set_mask(struct device *dev, u64 mask);
+	int dma_set_mask_and_coherent(struct device *dev, u64 mask);
 
-The query for consistent allocations is performed via a call to
-dma_set_coherent_mask():
+which will query the mask for both streaming and coherent APIs together.
+If you have some special requirements, then the following two separate
+queries can be used instead:
 
-	int dma_set_coherent_mask(struct device *dev, u64 mask);
+	The query for streaming mappings is performed via a call to
+	dma_set_mask():
+
+		int dma_set_mask(struct device *dev, u64 mask);
+
+	The query for consistent allocations is performed via a call
+	to dma_set_coherent_mask():
+
+		int dma_set_coherent_mask(struct device *dev, u64 mask);
 
 Here, dev is a pointer to the device struct of your device, and mask
 is a bit mask describing which bits of an address your device
@@ -137,7 +146,7 @@ exactly why.
 
 The standard 32-bit addressing device would do something like this:
 
-	if (dma_set_mask(dev, DMA_BIT_MASK(32))) {
+	if (dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32))) {
 		printk(KERN_WARNING
 		       "mydev: No suitable DMA available.\n");
 		goto ignore_this_device;
@@ -171,22 +180,20 @@ the case would look like this:
 
 	int using_dac, consistent_using_dac;
 
-	if (!dma_set_mask(dev, DMA_BIT_MASK(64))) {
+	if (!dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64))) {
 		using_dac = 1;
 	   	consistent_using_dac = 1;
-		dma_set_coherent_mask(dev, DMA_BIT_MASK(64));
-	} else if (!dma_set_mask(dev, DMA_BIT_MASK(32))) {
+	} else if (!dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32))) {
 		using_dac = 0;
 		consistent_using_dac = 0;
-		dma_set_coherent_mask(dev, DMA_BIT_MASK(32));
 	} else {
 		printk(KERN_WARNING
 		       "mydev: No suitable DMA available.\n");
 		goto ignore_this_device;
 	}
 
-dma_set_coherent_mask() will always be able to set the same or a
-smaller mask as dma_set_mask(). However for the rare case that a
+The coherent coherent mask will always be able to set the same or a
+smaller mask as the streaming mask. However for the rare case that a
 device driver only uses consistent allocations, one would have to
 check the return value from dma_set_coherent_mask().
 
@@ -199,9 +206,9 @@ address you might do something like:
 		goto ignore_this_device;
 	}
 
-When dma_set_mask() is successful, and returns zero, the kernel saves
-away this mask you have provided.  The kernel will use this
-information later when you make DMA mappings.
+When dma_set_mask() or dma_set_mask_and_coherent() is successful, and
+returns zero, the kernel saves away this mask you have provided.  The
+kernel will use this information later when you make DMA mappings.
 
 There is a case which we are aware of at this time, which is worth
 mentioning in this documentation.  If your device supports multiple

Documentation/DMA-API.txt

@@ -141,6 +141,14 @@ won't change the current mask settings.  It is more intended as an
 internal API for use by the platform than an external API for use by
 driver writers.
 
+int
+dma_set_mask_and_coherent(struct device *dev, u64 mask)
+
+Checks to see if the mask is possible and updates the device
+streaming and coherent DMA mask parameters if it is.
+
+Returns: 0 if successful and a negative error if not.
+
 int
 dma_set_mask(struct device *dev, u64 mask)
 

Documentation/arm64/booting.txt

@@ -68,13 +68,23 @@ Image target is available instead.
 
 Requirement: MANDATORY
 
-The decompressed kernel image contains a 32-byte header as follows:
+The decompressed kernel image contains a 64-byte header as follows:
 
-  u32 magic	= 0x14000008;	/* branch to stext, little-endian */
-  u32 res0	= 0;		/* reserved */
+  u32 code0;			/* Executable code */
+  u32 code1;			/* Executable code */
   u64 text_offset;		/* Image load offset */
+  u64 res0	= 0;		/* reserved */
   u64 res1	= 0;		/* reserved */
   u64 res2	= 0;		/* reserved */
+  u64 res3	= 0;		/* reserved */
+  u64 res4	= 0;		/* reserved */
+  u32 magic	= 0x644d5241;	/* Magic number, little endian, "ARM\x64" */
+  u32 res5 = 0;      		/* reserved */
+
+
+Header notes:
+
+- code0/code1 are responsible for branching to stext.
 
 The image must be placed at the specified offset (currently 0x80000)
 from the start of the system RAM and called there. The start of the

Documentation/arm64/memory.txt

@@ -21,7 +21,7 @@ The swapper_pgd_dir address is written to TTBR1 and never written to
 TTBR0.
 
 
-AArch64 Linux memory layout:
+AArch64 Linux memory layout with 4KB pages:
 
 Start			End			Size		Use
 -----------------------------------------------------------------------
@@ -35,17 +35,46 @@ ffffffbc00000000	ffffffbdffffffff	   8GB		vmemmap
 
 ffffffbe00000000	ffffffbffbbfffff	  ~8GB		[guard, future vmmemap]
 
-ffffffbffbc00000	ffffffbffbdfffff	   2MB		earlyprintk device
+ffffffbffa000000	ffffffbffaffffff	  16MB		PCI I/O space
 
-ffffffbffbe00000	ffffffbffbe0ffff	  64KB		PCI I/O space
+ffffffbffb000000	ffffffbffbbfffff	  12MB		[guard]
 
-ffffffbbffff0000	ffffffbcffffffff	  ~2MB		[guard]
+ffffffbffbc00000	ffffffbffbdfffff	   2MB		fixed mappings
+
+ffffffbffbe00000	ffffffbffbffffff	   2MB		[guard]
 
 ffffffbffc000000	ffffffbfffffffff	  64MB		modules
 
 ffffffc000000000	ffffffffffffffff	 256GB		kernel logical memory map
 
 
+AArch64 Linux memory layout with 64KB pages:
+
+Start			End			Size		Use
+-----------------------------------------------------------------------
+0000000000000000	000003ffffffffff	   4TB		user
+
+fffffc0000000000	fffffdfbfffeffff	  ~2TB		vmalloc
+
+fffffdfbffff0000	fffffdfbffffffff	  64KB		[guard page]
+
+fffffdfc00000000	fffffdfdffffffff	   8GB		vmemmap
+
+fffffdfe00000000	fffffdfffbbfffff	  ~8GB		[guard, future vmmemap]
+
+fffffdfffa000000	fffffdfffaffffff	  16MB		PCI I/O space
+
+fffffdfffb000000	fffffdfffbbfffff	  12MB		[guard]
+
+fffffdfffbc00000	fffffdfffbdfffff	   2MB		fixed mappings
+
+fffffdfffbe00000	fffffdfffbffffff	   2MB		[guard]
+
+fffffdfffc000000	fffffdffffffffff	  64MB		modules
+
+fffffe0000000000	ffffffffffffffff	   2TB		kernel logical memory map
+
+
 Translation table lookup with 4KB pages:
 
 +--------+--------+--------+--------+--------+--------+--------+--------+

arch/arc/mm/init.c

@@ -157,9 +157,8 @@ void __init free_initrd_mem(unsigned long start, unsigned long end)
 #endif
 
 #ifdef CONFIG_OF_FLATTREE
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
-					    unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
 {
-	pr_err("%s(%lx, %lx)\n", __func__, start, end);
+	pr_err("%s(%llx, %llx)\n", __func__, start, end);
 }
 #endif /* CONFIG_OF_FLATTREE */

arch/arm/Kconfig

@@ -265,9 +265,6 @@ config GENERIC_BUG
 	def_bool y
 	depends on BUG
 
-config GOLDFISH
-	bool
-
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"

arch/arm/include/asm/arch_timer.h

@@ -80,15 +80,6 @@ static inline u32 arch_timer_get_cntfrq(void)
 	return val;
 }
 
-static inline u64 arch_counter_get_cntpct(void)
-{
-	u64 cval;
-
-	isb();
-	asm volatile("mrrc p15, 0, %Q0, %R0, c14" : "=r" (cval));
-	return cval;
-}
-
 static inline u64 arch_counter_get_cntvct(void)
 {
 	u64 cval;
@@ -98,17 +89,43 @@ static inline u64 arch_counter_get_cntvct(void)
 	return cval;
 }
 
-static inline void __cpuinit arch_counter_set_user_access(void)
+static inline u32 arch_timer_get_cntkctl(void)
 {
 	u32 cntkctl;
-
 	asm volatile("mrc p15, 0, %0, c14, c1, 0" : "=r" (cntkctl));
+	return cntkctl;
+}
 
-	/* disable user access to everything */
-	cntkctl &= ~((3 << 8) | (7 << 0));
-
+static inline void arch_timer_set_cntkctl(u32 cntkctl)
+{
 	asm volatile("mcr p15, 0, %0, c14, c1, 0" : : "r" (cntkctl));
 }
+
+static inline void __cpuinit arch_counter_set_user_access(void)
+{
+	u32 cntkctl = arch_timer_get_cntkctl();
+
+	/* Disable user access to both physical/virtual counters/timers */
+	/* Also disable virtual event stream */
+	cntkctl &= ~(ARCH_TIMER_USR_PT_ACCESS_EN
+			| ARCH_TIMER_USR_VT_ACCESS_EN
+			| ARCH_TIMER_VIRT_EVT_EN
+			| ARCH_TIMER_USR_VCT_ACCESS_EN
+			| ARCH_TIMER_USR_PCT_ACCESS_EN);
+	arch_timer_set_cntkctl(cntkctl);
+}
+
+static inline void arch_timer_evtstrm_enable(int divider)
+{
+	u32 cntkctl = arch_timer_get_cntkctl();
+	cntkctl &= ~ARCH_TIMER_EVT_TRIGGER_MASK;
+	/* Set the divider and enable virtual event stream */
+	cntkctl |= (divider << ARCH_TIMER_EVT_TRIGGER_SHIFT)
+			| ARCH_TIMER_VIRT_EVT_EN;
+	arch_timer_set_cntkctl(cntkctl);
+	elf_hwcap |= HWCAP_EVTSTRM;
+}
+
 #endif
 
 #endif

arch/arm/include/asm/dma-contiguous.h

@@ -2,10 +2,9 @@
 #define ASMARM_DMA_CONTIGUOUS_H
 
 #ifdef __KERNEL__
-#ifdef CONFIG_CMA
+#ifdef CONFIG_DMA_CMA
 
 #include <linux/types.h>
-#include <asm-generic/dma-contiguous.h>
 
 void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size);
 

arch/arm/include/asm/elf.h

@@ -19,8 +19,6 @@ typedef elf_greg_t elf_gregset_t[ELF_NGREG];
 
 typedef struct user_fp elf_fpregset_t;
 
-#define EM_ARM	40
-
 #define EF_ARM_EABI_MASK	0xff000000
 #define EF_ARM_EABI_UNKNOWN	0x00000000
 #define EF_ARM_EABI_VER1	0x01000000

arch/arm/include/uapi/asm/hwcap.h

@@ -25,6 +25,7 @@
 #define HWCAP_IDIVT	(1 << 18)
 #define HWCAP_VFPD32	(1 << 19)	/* set if VFP has 32 regs (not 16) */
 #define HWCAP_IDIV	(HWCAP_IDIVA | HWCAP_IDIVT)
-
+#define HWCAP_LPAE	(1 << 20)
+#define HWCAP_EVTSTRM	(1 << 21)
 
 #endif /* _UAPI__ASMARM_HWCAP_H */

arch/arm/kernel/setup.c

@@ -872,6 +872,9 @@ static const char *hwcap_str[] = {
 	"vfpv4",
 	"idiva",
 	"idivt",
+	"vfpd32",
+	"lpae",
+	"evtstrm",
 	NULL
 };
 

arch/arm/kvm/arm.c

@@ -17,6 +17,7 @@
  */
 
 #include <linux/cpu.h>
+#include <linux/cpu_pm.h>
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/kvm_host.h>
@@ -835,6 +836,33 @@ static struct notifier_block hyp_init_cpu_nb = {
 	.notifier_call = hyp_init_cpu_notify,
 };
 
+#ifdef CONFIG_CPU_PM
+static int hyp_init_cpu_pm_notifier(struct notifier_block *self,
+				    unsigned long cmd,
+				    void *v)
+{
+	if (cmd == CPU_PM_EXIT) {
+		cpu_init_hyp_mode(NULL);
+		return NOTIFY_OK;
+	}
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block hyp_init_cpu_pm_nb = {
+	.notifier_call = hyp_init_cpu_pm_notifier,
+};
+
+static void __init hyp_cpu_pm_init(void)
+{
+	cpu_pm_register_notifier(&hyp_init_cpu_pm_nb);
+}
+#else
+static inline void hyp_cpu_pm_init(void)
+{
+}
+#endif
+
 /**
  * Inits Hyp-mode on all online CPUs
  */
@@ -995,6 +1023,8 @@ int kvm_arch_init(void *opaque)
 		goto out_err;
 	}
 
+	hyp_cpu_pm_init();
+
 	kvm_coproc_table_init();
 	return 0;
 out_err:

arch/arm/mm/dma-mapping.c

@@ -358,7 +358,7 @@ static int __init atomic_pool_init(void)
 	if (!pages)
 		goto no_pages;
 
-	if (IS_ENABLED(CONFIG_CMA))
+	if (IS_ENABLED(CONFIG_DMA_CMA))
 		ptr = __alloc_from_contiguous(NULL, pool->size, prot, &page,
 					      atomic_pool_init);
 	else
@@ -670,7 +670,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 		addr = __alloc_simple_buffer(dev, size, gfp, &page);
 	else if (!(gfp & __GFP_WAIT))
 		addr = __alloc_from_pool(size, &page);
-	else if (!IS_ENABLED(CONFIG_CMA))
+	else if (!IS_ENABLED(CONFIG_DMA_CMA))
 		addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller);
 	else
 		addr = __alloc_from_contiguous(dev, size, prot, &page, caller);
@@ -759,7 +759,7 @@ static void __arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
 		__dma_free_buffer(page, size);
 	} else if (__free_from_pool(cpu_addr, size)) {
 		return;
-	} else if (!IS_ENABLED(CONFIG_CMA)) {
+	} else if (!IS_ENABLED(CONFIG_DMA_CMA)) {
 		__dma_free_remap(cpu_addr, size);
 		__dma_free_buffer(page, size);
 	} else {

arch/arm/mm/init.c

@@ -76,7 +76,7 @@ static int __init parse_tag_initrd2(const struct tag *tag)
 __tagtable(ATAG_INITRD2, parse_tag_initrd2);
 
 #ifdef CONFIG_OF_FLATTREE
-void __init early_init_dt_setup_initrd_arch(unsigned long start, unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
 {
 	phys_initrd_start = start;
 	phys_initrd_size = end - start;