Merge android-4.4.104 (8bc4213) into msm-4.4

* refs/heads/tmp-8bc4213
  Linux 4.4.104
  nfsd: Fix another OPEN stateid race
  nfsd: Fix stateid races between OPEN and CLOSE
  nfsd: Make init_open_stateid() a bit more whole
  drm/i915: Prevent zero length "index" write
  drm/i915: Don't try indexed reads to alternate slave addresses
  NFS: revalidate "." etc correctly on "open".
  mtd: nand: Fix writing mtdoops to nand flash.
  drm/panel: simple: Add missing panel_simple_unprepare() calls
  drm/radeon: fix atombios on big endian
  Revert "drm/radeon: dont switch vt on suspend"
  bcache: Fix building error on MIPS
  eeprom: at24: check at24_read/write arguments
  mmc: core: Do not leave the block driver in a suspended state
  KVM: x86: inject exceptions produced by x86_decode_insn
  KVM: x86: Exit to user-mode on #UD intercept when emulator requires
  KVM: x86: pvclock: Handle first-time write to pvclock-page contains random junk
  btrfs: clear space cache inode generation always
  mm/madvise.c: fix madvise() infinite loop under special circumstances
  mm, thp: Do not make page table dirty unconditionally in touch_p[mu]d()
  x86/efi-bgrt: Replace early_memremap() with memremap()
  x86/efi-bgrt: Fix kernel panic when mapping BGRT data
  ARM: dts: omap3: logicpd-torpedo-37xx-devkit: Fix MMC1 cd-gpio
  x86/efi: Build our own page table structures
  x86/efi: Hoist page table switching code into efi_call_virt()
  x86/mm/pat: Ensure cpa->pfn only contains page frame numbers
  ipsec: Fix aborted xfrm policy dump crash
  netlink: add a start callback for starting a netlink dump
  Documentation: tee subsystem and op-tee driver
  tee: add OP-TEE driver
  tee: generic TEE subsystem
  dt/bindings: add bindings for optee
  kernel.h: add u64_to_user_ptr()
  ARM: 8481/2: drivers: psci: replace psci firmware calls
  ARM: 8480/2: arm64: add implementation for arm-smccc
  ARM: 8479/2: add implementation for arm-smccc
  ARM: 8478/2: arm/arm64: add arm-smccc
  UPSTREAM: net: xfrm: allow clearing socket xfrm policies.

Conflicts:
	arch/arm64/kernel/arm64ksyms.c
	arch/arm64/kernel/asm-offsets.c
	arch/arm64/kvm/hyp/fpsimd.S
	drivers/Kconfig
	drivers/Makefile
	drivers/firmware/psci.c
	drivers/gpu/drm/msm/msm_gem_submit.c
	drivers/mmc/core/bus.c
	include/linux/arm-smccc.h

Change-Id: Ib22051f60c49ecf3bb7e18f9940ba9a4ac5143af
Signed-off-by: Srinivasarao P <spathi@codeaurora.org>

9 files changed, 58 insertions, 69 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
index f4cae5357e40..3e90ddcbb24a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
@@ -1575,34 +1575,32 @@ void amdgpu_atombios_scratch_regs_restore(struct amdgpu_device *adev)
 		WREG32(mmBIOS_SCRATCH_0 + i, adev->bios_scratch[i]);
 }
 
-/* Atom needs data in little endian format
- * so swap as appropriate when copying data to
- * or from atom. Note that atom operates on
- * dw units.
+/* Atom needs data in little endian format so swap as appropriate when copying
+ * data to or from atom. Note that atom operates on dw units.
+ *
+ * Use to_le=true when sending data to atom and provide at least
+ * ALIGN(num_bytes,4) bytes in the dst buffer.
+ *
+ * Use to_le=false when receiving data from atom and provide ALIGN(num_bytes,4)
+ * byes in the src buffer.
  */
 void amdgpu_atombios_copy_swap(u8 *dst, u8 *src, u8 num_bytes, bool to_le)
 {
 #ifdef __BIG_ENDIAN
-	u8 src_tmp[20], dst_tmp[20]; /* used for byteswapping */
-	u32 *dst32, *src32;
+	u32 src_tmp[5], dst_tmp[5];
 	int i;
+	u8 align_num_bytes = ALIGN(num_bytes, 4);
 
-	memcpy(src_tmp, src, num_bytes);
-	src32 = (u32 *)src_tmp;
-	dst32 = (u32 *)dst_tmp;
 	if (to_le) {
-		for (i = 0; i < ((num_bytes + 3) / 4); i++)
-			dst32[i] = cpu_to_le32(src32[i]);
-		memcpy(dst, dst_tmp, num_bytes);
+		memcpy(src_tmp, src, num_bytes);
+		for (i = 0; i < align_num_bytes / 4; i++)
+			dst_tmp[i] = cpu_to_le32(src_tmp[i]);
+		memcpy(dst, dst_tmp, align_num_bytes);
 	} else {
-		u8 dws = num_bytes & ~3;
-		for (i = 0; i < ((num_bytes + 3) / 4); i++)
-			dst32[i] = le32_to_cpu(src32[i]);
-		memcpy(dst, dst_tmp, dws);
-		if (num_bytes % 4) {
-			for (i = 0; i < (num_bytes % 4); i++)
-				dst[dws+i] = dst_tmp[dws+i];
-		}
+		memcpy(src_tmp, src, align_num_bytes);
+		for (i = 0; i < align_num_bytes / 4; i++)
+			dst_tmp[i] = le32_to_cpu(src_tmp[i]);
+		memcpy(dst, dst_tmp, num_bytes);
 	}
 #else
 	memcpy(dst, src, num_bytes);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 5044f2257e89..6fca39e1c419 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3475,11 +3475,6 @@ static inline uint32_t i915_vgacntrl_reg(struct drm_device *dev)
 		return VGACNTRL;
 }
 
-static inline void __user *to_user_ptr(u64 address)
-{
-	return (void __user *)(uintptr_t)address;
-}
-
 static inline unsigned long msecs_to_jiffies_timeout(const unsigned int m)
 {
 	unsigned long j = msecs_to_jiffies(m);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index f56af0aaafde..659b90657f36 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -324,7 +324,7 @@ i915_gem_phys_pwrite(struct drm_i915_gem_object *obj,
 {
 	struct drm_device *dev = obj->base.dev;
 	void *vaddr = obj->phys_handle->vaddr + args->offset;
-	char __user *user_data = to_user_ptr(args->data_ptr);
+	char __user *user_data = u64_to_user_ptr(args->data_ptr);
 	int ret = 0;
 
 	/* We manually control the domain here and pretend that it
@@ -605,7 +605,7 @@ i915_gem_shmem_pread(struct drm_device *dev,
 	int needs_clflush = 0;
 	struct sg_page_iter sg_iter;
 
-	user_data = to_user_ptr(args->data_ptr);
+	user_data = u64_to_user_ptr(args->data_ptr);
 	remain = args->size;
 
 	obj_do_bit17_swizzling = i915_gem_object_needs_bit17_swizzle(obj);
@@ -692,7 +692,7 @@ i915_gem_pread_ioctl(struct drm_device *dev, void *data,
 		return 0;
 
 	if (!access_ok(VERIFY_WRITE,
-		       to_user_ptr(args->data_ptr),
+		       u64_to_user_ptr(args->data_ptr),
 		       args->size))
 		return -EFAULT;
 
@@ -783,7 +783,7 @@ i915_gem_gtt_pwrite_fast(struct drm_device *dev,
 	if (ret)
 		goto out_unpin;
 
-	user_data = to_user_ptr(args->data_ptr);
+	user_data = u64_to_user_ptr(args->data_ptr);
 	remain = args->size;
 
 	offset = i915_gem_obj_ggtt_offset(obj) + args->offset;
@@ -907,7 +907,7 @@ i915_gem_shmem_pwrite(struct drm_device *dev,
 	int needs_clflush_before = 0;
 	struct sg_page_iter sg_iter;
 
-	user_data = to_user_ptr(args->data_ptr);
+	user_data = u64_to_user_ptr(args->data_ptr);
 	remain = args->size;
 
 	obj_do_bit17_swizzling = i915_gem_object_needs_bit17_swizzle(obj);
@@ -1036,12 +1036,12 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
 		return 0;
 
 	if (!access_ok(VERIFY_READ,
-		       to_user_ptr(args->data_ptr),
+		       u64_to_user_ptr(args->data_ptr),
 		       args->size))
 		return -EFAULT;
 
 	if (likely(!i915.prefault_disable)) {
-		ret = fault_in_multipages_readable(to_user_ptr(args->data_ptr),
+		ret = fault_in_multipages_readable(u64_to_user_ptr(args->data_ptr),
 						   args->size);
 		if (ret)
 			return -EFAULT;
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 201947b4377c..8800f410b2d2 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -492,7 +492,7 @@ i915_gem_execbuffer_relocate_vma(struct i915_vma *vma,
 	struct drm_i915_gem_exec_object2 *entry = vma->exec_entry;
 	int remain, ret;
 
-	user_relocs = to_user_ptr(entry->relocs_ptr);
+	user_relocs = u64_to_user_ptr(entry->relocs_ptr);
 
 	remain = entry->relocation_count;
 	while (remain) {
@@ -831,7 +831,7 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev,
 		u64 invalid_offset = (u64)-1;
 		int j;
 
-		user_relocs = to_user_ptr(exec[i].relocs_ptr);
+		user_relocs = u64_to_user_ptr(exec[i].relocs_ptr);
 
 		if (copy_from_user(reloc+total, user_relocs,
 				   exec[i].relocation_count * sizeof(*reloc))) {
@@ -975,7 +975,7 @@ validate_exec_list(struct drm_device *dev,
 		invalid_flags |= EXEC_OBJECT_NEEDS_GTT;
 
 	for (i = 0; i < count; i++) {
-		char __user *ptr = to_user_ptr(exec[i].relocs_ptr);
+		char __user *ptr = u64_to_user_ptr(exec[i].relocs_ptr);
 		int length; /* limited by fault_in_pages_readable() */
 
 		if (exec[i].flags & invalid_flags)
@@ -1633,7 +1633,7 @@ i915_gem_execbuffer(struct drm_device *dev, void *data,
 		return -ENOMEM;
 	}
 	ret = copy_from_user(exec_list,
-			     to_user_ptr(args->buffers_ptr),
+			     u64_to_user_ptr(args->buffers_ptr),
 			     sizeof(*exec_list) * args->buffer_count);
 	if (ret != 0) {
 		DRM_DEBUG("copy %d exec entries failed %d\n",
@@ -1669,7 +1669,7 @@ i915_gem_execbuffer(struct drm_device *dev, void *data,
 	ret = i915_gem_do_execbuffer(dev, data, file, &exec2, exec2_list);
 	if (!ret) {
 		struct drm_i915_gem_exec_object __user *user_exec_list =
-			to_user_ptr(args->buffers_ptr);
+			u64_to_user_ptr(args->buffers_ptr);
 
 		/* Copy the new buffer offsets back to the user's exec list. */
 		for (i = 0; i < args->buffer_count; i++) {
@@ -1721,7 +1721,7 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data,
 		return -ENOMEM;
 	}
 	ret = copy_from_user(exec2_list,
-			     to_user_ptr(args->buffers_ptr),
+			     u64_to_user_ptr(args->buffers_ptr),
 			     sizeof(*exec2_list) * args->buffer_count);
 	if (ret != 0) {
 		DRM_DEBUG("copy %d exec entries failed %d\n",
@@ -1734,7 +1734,7 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data,
 	if (!ret) {
 		/* Copy the new buffer offsets back to the user's exec list. */
 		struct drm_i915_gem_exec_object2 __user *user_exec_list =
-				   to_user_ptr(args->buffers_ptr);
+				   u64_to_user_ptr(args->buffers_ptr);
 		int i;
 
 		for (i = 0; i < args->buffer_count; i++) {
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index f3bee54c414f..cb4313c68f71 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -440,7 +440,9 @@ static bool
 gmbus_is_index_read(struct i2c_msg *msgs, int i, int num)
 {
 	return (i + 1 < num &&
-		!(msgs[i].flags & I2C_M_RD) && msgs[i].len <= 2 &&
+		msgs[i].addr == msgs[i + 1].addr &&
+		!(msgs[i].flags & I2C_M_RD) &&
+		(msgs[i].len == 1 || msgs[i].len == 2) &&
 		(msgs[i + 1].flags & I2C_M_RD));
 }
 
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index a11ec7b82b80..2e528b112e1f 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -29,11 +29,6 @@
 #define BO_LOCKED   0x4000
 #define BO_PINNED   0x2000
 
-static inline void __user *to_user_ptr(u64 address)
-{
-	return (void __user *)(uintptr_t)address;
-}
-
 static struct msm_gem_submit *submit_create(struct drm_device *dev,
 		struct msm_gem_address_space *aspace,
 		uint32_t nr_bos, uint32_t nr_cmds,
@@ -107,7 +102,7 @@ static int submit_lookup_objects(struct msm_gpu *gpu,
 		struct drm_gem_object *obj;
 		struct msm_gem_object *msm_obj;
 		void __user *userptr =
-			to_user_ptr(args->bos + (i * sizeof(submit_bo)));
+			u64_to_user_ptr(args->bos + (i * sizeof(submit_bo)));
 
 		if (copy_from_user_inatomic(&submit_bo, userptr,
 			sizeof(submit_bo))) {
@@ -362,7 +357,7 @@ static int submit_reloc(struct msm_gpu *gpu,
 	for (i = 0; i < nr_relocs; i++) {
 		struct drm_msm_gem_submit_reloc submit_reloc;
 		void __user *userptr =
-			to_user_ptr(relocs + (i * sizeof(submit_reloc)));
+			u64_to_user_ptr(relocs + (i * sizeof(submit_reloc)));
 		uint64_t iova;
 		uint32_t off;
 		bool valid;
@@ -473,7 +468,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	for (i = 0; i < args->nr_cmds; i++) {
 		struct drm_msm_gem_submit_cmd submit_cmd;
 		void __user *userptr =
-			to_user_ptr(args->cmds + (i * sizeof(submit_cmd)));
+			u64_to_user_ptr(args->cmds + (i * sizeof(submit_cmd)));
 		struct msm_gem_object *msm_obj;
 		uint64_t iova;
 		size_t size;
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index f97b73ec4713..f418c002d323 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -352,6 +352,7 @@ static int panel_simple_remove(struct device *dev)
 	drm_panel_remove(&panel->base);
 
 	panel_simple_disable(&panel->base);
+	panel_simple_unprepare(&panel->base);
 
 	if (panel->ddc)
 		put_device(&panel->ddc->dev);
@@ -367,6 +368,7 @@ static void panel_simple_shutdown(struct device *dev)
 	struct panel_simple *panel = dev_get_drvdata(dev);
 
 	panel_simple_disable(&panel->base);
+	panel_simple_unprepare(&panel->base);
 }
 
 static const struct drm_display_mode ampire_am800480r3tmqwa1h_mode = {
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index b5760851195c..0c6216a6ee9e 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -45,34 +45,32 @@ static char *pre_emph_names[] = {
 
 /***** radeon AUX functions *****/
 
-/* Atom needs data in little endian format
- * so swap as appropriate when copying data to
- * or from atom. Note that atom operates on
- * dw units.
+/* Atom needs data in little endian format so swap as appropriate when copying
+ * data to or from atom. Note that atom operates on dw units.
+ *
+ * Use to_le=true when sending data to atom and provide at least
+ * ALIGN(num_bytes,4) bytes in the dst buffer.
+ *
+ * Use to_le=false when receiving data from atom and provide ALIGN(num_bytes,4)
+ * byes in the src buffer.
  */
 void radeon_atom_copy_swap(u8 *dst, u8 *src, u8 num_bytes, bool to_le)
 {
 #ifdef __BIG_ENDIAN
-	u8 src_tmp[20], dst_tmp[20]; /* used for byteswapping */
-	u32 *dst32, *src32;
+	u32 src_tmp[5], dst_tmp[5];
 	int i;
+	u8 align_num_bytes = ALIGN(num_bytes, 4);
 
-	memcpy(src_tmp, src, num_bytes);
-	src32 = (u32 *)src_tmp;
-	dst32 = (u32 *)dst_tmp;
 	if (to_le) {
-		for (i = 0; i < ((num_bytes + 3) / 4); i++)
-			dst32[i] = cpu_to_le32(src32[i]);
-		memcpy(dst, dst_tmp, num_bytes);
+		memcpy(src_tmp, src, num_bytes);
+		for (i = 0; i < align_num_bytes / 4; i++)
+			dst_tmp[i] = cpu_to_le32(src_tmp[i]);
+		memcpy(dst, dst_tmp, align_num_bytes);
 	} else {
-		u8 dws = num_bytes & ~3;
-		for (i = 0; i < ((num_bytes + 3) / 4); i++)
-			dst32[i] = le32_to_cpu(src32[i]);
-		memcpy(dst, dst_tmp, dws);
-		if (num_bytes % 4) {
-			for (i = 0; i < (num_bytes % 4); i++)
-				dst[dws+i] = dst_tmp[dws+i];
-		}
+		memcpy(src_tmp, src, align_num_bytes);
+		for (i = 0; i < align_num_bytes / 4; i++)
+			dst_tmp[i] = le32_to_cpu(src_tmp[i]);
+		memcpy(dst, dst_tmp, num_bytes);
 	}
 #else
 	memcpy(dst, src, num_bytes);
diff --git a/drivers/gpu/drm/radeon/radeon_fb.c b/drivers/gpu/drm/radeon/radeon_fb.c
index 26da2f4d7b4f..a2937a693591 100644
--- a/drivers/gpu/drm/radeon/radeon_fb.c
+++ b/drivers/gpu/drm/radeon/radeon_fb.c
@@ -226,7 +226,6 @@ static int radeonfb_create(struct drm_fb_helper *helper,
 	}
 
 	info->par = rfbdev;
-	info->skip_vt_switch = true;
 
 	ret = radeon_framebuffer_init(rdev->ddev, &rfbdev->rfb, &mode_cmd, gobj);
 	if (ret) {