Merge tag 'drm-next-2019-07-16' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "The biggest thing in this is the AMD Navi GPU support, this again
  contains a bunch of header files that are large. These are the new AMD
  RX5700 GPUs that just recently became available.

  New drivers:
   - ST-Ericsson MCDE driver
   - Ingenic JZ47xx SoC

  UAPI change:
   - HDR source metadata property

  Core:
   - HDR inforframes and EDID parsing
   - drm hdmi infoframe unpacking
   - remove prime sg_table caching into dma-buf
   - New gem vram helpers to reduce driver code
   - Lots of drmP.h removal
   - reservation fencing fix
   - documentation updates
   - drm_fb_helper_connector removed
   - mode name command handler rewrite

  fbcon:
   - Remove the fbcon notifiers

  ttm:
   - forward progress fixes

  dma-buf:
   - make mmap call optional
   - debugfs refcount fixes
   - dma-fence free with pending signals fix
   - each dma-buf gets an inode

  Panels:
   - Lots of additional panel bindings

  amdgpu:
   - initial navi10 support
   - avoid hw reset
   - HDR metadata support
   - new thermal sensors for vega asics
   - RAS fixes
   - use HMM rather than MMU notifier
   - xgmi topology via kfd
   - SR-IOV fixes
   - driver reload fixes
   - DC use a core bpc attribute
   - Aux fixes for DC
   - Bandwidth calc updates for DC
   - Clock handling refactor
   - kfd VEGAM support

  vmwgfx:
   - Coherent memory support changes

  i915:
   - HDR Support
   - HDMI i2c link
   - Icelake multi-segmented gamma support
   - GuC firmware update
   - Mule Creek Canyon PCH support for EHL
   - EHL platform updtes
   - move i915.alpha_support to i915.force_probe
   - runtime PM refactoring
   - VBT parsing refactoring
   - DSI fixes
   - struct mutex dependency reduction
   - GEM code reorg

  mali-dp:
   - Komeda driver features

  msm:
   - dsi vs EPROBE_DEFER fixes
   - msm8998 snapdragon 835 support
   - a540 gpu support
   - mdp5 and dpu interconnect support

  exynos:
   - drmP.h removal

  tegra:
   - misc fixes

  tda998x:
   - audio support improvements
   - pixel repeated mode support
   - quantisation range handling corrections
   - HDMI vendor info fix

  armada:
   - interlace support fix
   - overlay/video plane register handling refactor
   - add gamma support

  rockchip:
   - RX3328 support

  panfrost:
   - expose perf counters via hidden ioctls

  vkms:
   - enumerate CRC sources list

  ast:
   - rework BO handling

  mgag200:
   - rework BO handling

  dw-hdmi:
   - suspend/resume support

  rcar-du:
   - R8A774A1 Soc Support
   - LVDS dual-link mode support
   - Additional formats
   - Misc fixes

  omapdrm:
   - DSI command mode display support

  stm
   - fb modifier support
   - runtime PM support

  sun4i:
   - use vmap ops

  vc4:
   - binner bo binding rework

  v3d:
   - compute shader support
   - resync/sync fixes
   - job management refactoring

  lima:
   - NULL pointer in irq handler fix
   - scheduler default timeout

  virtio:
   - fence seqno support
   - trace events

  bochs:
   - misc fixes

  tc458767:
   - IRQ/HDP handling

  sii902x:
   - HDMI audio support

  atmel-hlcdc:
   - misc fixes

  meson:
   - zpos support"

* tag 'drm-next-2019-07-16' of git://anongit.freedesktop.org/drm/drm: (1815 commits)
  Revert "Merge branch 'vmwgfx-next' of git://people.freedesktop.org/~thomash/linux into drm-next"
  Revert "mm: adjust apply_to_pfn_range interface for dropped token."
  mm: adjust apply_to_pfn_range interface for dropped token.
  drm/amdgpu/navi10: add uclk activity sensor
  drm/amdgpu: properly guard the generic discovery code
  drm/amdgpu: add missing documentation on new module parameters
  drm/amdgpu: don't invalidate caches in RELEASE_MEM, only do the writeback
  drm/amd/display: avoid 64-bit division
  drm/amdgpu/psp11: simplify the ucode register logic
  drm/amdgpu: properly guard DC support in navi code
  drm/amd/powerplay: vega20: fix uninitialized variable use
  drm/amd/display: dcn20: include linux/delay.h
  amdgpu: make pmu support optional
  drm/amd/powerplay: Zero initialize current_rpm in vega20_get_fan_speed_percent
  drm/amd/powerplay: Zero initialize freq in smu_v11_0_get_current_clk_freq
  drm/amd/powerplay: Use memset to initialize metrics structs
  drm/amdgpu/mes10.1: Fix header guard
  drm/amd/powerplay: add temperature sensor support for navi10
  drm/amdgpu: fix scheduler timeout calc
  drm/amdgpu: Prepare for hmm_range_register API change (v2)
  ...

12 files changed, 235 insertions, 64 deletions

diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
index 8514f42367f2..5f7e98028eaf 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
@@ -384,19 +384,17 @@ static const unsigned int a3xx_registers[] = {
 	0x2200, 0x2212, 0x2214, 0x2217, 0x221a, 0x221a, 0x2240, 0x227e,
 	0x2280, 0x228b, 0x22c0, 0x22c0, 0x22c4, 0x22ce, 0x22d0, 0x22d8,
 	0x22df, 0x22e6, 0x22e8, 0x22e9, 0x22ec, 0x22ec, 0x22f0, 0x22f7,
-	0x22ff, 0x22ff, 0x2340, 0x2343, 0x2348, 0x2349, 0x2350, 0x2356,
-	0x2360, 0x2360, 0x2440, 0x2440, 0x2444, 0x2444, 0x2448, 0x244d,
-	0x2468, 0x2469, 0x246c, 0x246d, 0x2470, 0x2470, 0x2472, 0x2472,
-	0x2474, 0x2475, 0x2479, 0x247a, 0x24c0, 0x24d3, 0x24e4, 0x24ef,
-	0x2500, 0x2509, 0x250c, 0x250c, 0x250e, 0x250e, 0x2510, 0x2511,
-	0x2514, 0x2515, 0x25e4, 0x25e4, 0x25ea, 0x25ea, 0x25ec, 0x25ed,
-	0x25f0, 0x25f0, 0x2600, 0x2612, 0x2614, 0x2617, 0x261a, 0x261a,
-	0x2640, 0x267e, 0x2680, 0x268b, 0x26c0, 0x26c0, 0x26c4, 0x26ce,
-	0x26d0, 0x26d8, 0x26df, 0x26e6, 0x26e8, 0x26e9, 0x26ec, 0x26ec,
-	0x26f0, 0x26f7, 0x26ff, 0x26ff, 0x2740, 0x2743, 0x2748, 0x2749,
-	0x2750, 0x2756, 0x2760, 0x2760, 0x300c, 0x300e, 0x301c, 0x301d,
-	0x302a, 0x302a, 0x302c, 0x302d, 0x3030, 0x3031, 0x3034, 0x3036,
-	0x303c, 0x303c, 0x305e, 0x305f,
+	0x22ff, 0x22ff, 0x2340, 0x2343, 0x2440, 0x2440, 0x2444, 0x2444,
+	0x2448, 0x244d, 0x2468, 0x2469, 0x246c, 0x246d, 0x2470, 0x2470,
+	0x2472, 0x2472, 0x2474, 0x2475, 0x2479, 0x247a, 0x24c0, 0x24d3,
+	0x24e4, 0x24ef, 0x2500, 0x2509, 0x250c, 0x250c, 0x250e, 0x250e,
+	0x2510, 0x2511, 0x2514, 0x2515, 0x25e4, 0x25e4, 0x25ea, 0x25ea,
+	0x25ec, 0x25ed, 0x25f0, 0x25f0, 0x2600, 0x2612, 0x2614, 0x2617,
+	0x261a, 0x261a, 0x2640, 0x267e, 0x2680, 0x268b, 0x26c0, 0x26c0,
+	0x26c4, 0x26ce, 0x26d0, 0x26d8, 0x26df, 0x26e6, 0x26e8, 0x26e9,
+	0x26ec, 0x26ec, 0x26f0, 0x26f7, 0x26ff, 0x26ff, 0x2740, 0x2743,
+	0x300c, 0x300e, 0x301c, 0x301d, 0x302a, 0x302a, 0x302c, 0x302d,
+	0x3030, 0x3031, 0x3034, 0x3036, 0x303c, 0x303c, 0x305e, 0x305f,
 	~0   /* sentinel */
 };
 
diff --git a/drivers/gpu/drm/msm/adreno/a5xx.xml.h b/drivers/gpu/drm/msm/adreno/a5xx.xml.h
index cf4fe14ddd6e..4a61d4e72c98 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx.xml.h
+++ b/drivers/gpu/drm/msm/adreno/a5xx.xml.h
@@ -8,19 +8,19 @@ http://github.com/freedreno/envytools/
 git clone https://github.com/freedreno/envytools.git
 
 The rules-ng-ng source files this header was generated from are:
-- /home/robclark/src/envytools/rnndb/adreno.xml               (    501 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/freedreno_copyright.xml  (   1572 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/a2xx.xml          (  42463 bytes, from 2018-11-19 13:44:03)
-- /home/robclark/src/envytools/rnndb/adreno/adreno_common.xml (  14201 bytes, from 2018-12-02 17:29:54)
-- /home/robclark/src/envytools/rnndb/adreno/adreno_pm4.xml    (  43052 bytes, from 2018-12-02 17:29:54)
-- /home/robclark/src/envytools/rnndb/adreno/a3xx.xml          (  83840 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/a4xx.xml          ( 112086 bytes, from 2018-07-03 19:37:13)
-- /home/robclark/src/envytools/rnndb/adreno/a5xx.xml          ( 147240 bytes, from 2018-12-02 17:29:54)
-- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml          ( 140790 bytes, from 2018-12-02 17:29:54)
-- /home/robclark/src/envytools/rnndb/adreno/a6xx_gmu.xml      (  10431 bytes, from 2018-09-14 13:03:07)
-- /home/robclark/src/envytools/rnndb/adreno/ocmem.xml         (   1773 bytes, from 2018-07-03 19:37:13)
-
-Copyright (C) 2013-2018 by the following authors:
+- /home/ubuntu/envytools/envytools/rnndb/./adreno.xml             (    501 bytes, from 2019-05-29 01:28:15)
+- /home/ubuntu/envytools/envytools/rnndb/freedreno_copyright.xml  (   1572 bytes, from 2019-05-29 01:28:15)
+- /home/ubuntu/envytools/envytools/rnndb/adreno/a2xx.xml          (  79608 bytes, from 2019-05-29 01:28:15)
+- /home/ubuntu/envytools/envytools/rnndb/adreno/adreno_common.xml (  14239 bytes, from 2019-05-29 01:28:15)
+- /home/ubuntu/envytools/envytools/rnndb/adreno/adreno_pm4.xml    (  43155 bytes, from 2019-05-29 01:28:15)
+- /home/ubuntu/envytools/envytools/rnndb/adreno/a3xx.xml          (  83840 bytes, from 2019-05-29 01:28:15)
+- /home/ubuntu/envytools/envytools/rnndb/adreno/a4xx.xml          ( 112086 bytes, from 2019-05-29 01:28:15)
+- /home/ubuntu/envytools/envytools/rnndb/adreno/a5xx.xml          ( 147291 bytes, from 2019-05-29 14:51:41)
+- /home/ubuntu/envytools/envytools/rnndb/adreno/a6xx.xml          ( 148461 bytes, from 2019-05-29 01:28:15)
+- /home/ubuntu/envytools/envytools/rnndb/adreno/a6xx_gmu.xml      (  10431 bytes, from 2019-05-29 01:28:15)
+- /home/ubuntu/envytools/envytools/rnndb/adreno/ocmem.xml         (   1773 bytes, from 2019-05-29 01:28:15)
+
+Copyright (C) 2013-2019 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
 - Ilia Mirkin <imirkin@alum.mit.edu> (imirkin)
 
@@ -2148,6 +2148,8 @@ static inline uint32_t A5XX_VSC_RESOLVE_CNTL_Y(uint32_t val)
 
 #define REG_A5XX_HLSQ_TIMEOUT_THRESHOLD_1			0x00000e01
 
+#define REG_A5XX_HLSQ_DBG_ECO_CNTL				0x00000e04
+
 #define REG_A5XX_HLSQ_ADDR_MODE_CNTL				0x00000e05
 
 #define REG_A5XX_HLSQ_MODE_CNTL					0x00000e06
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c b/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c
index 3041c500c5cd..9f2dd76bd67a 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c
@@ -149,7 +149,6 @@ DEFINE_SIMPLE_ATTRIBUTE(reset_fops, NULL, reset_set, "%llx\n");
 int a5xx_debugfs_init(struct msm_gpu *gpu, struct drm_minor *minor)
 {
 	struct drm_device *dev;
-	struct dentry *ent;
 	int ret;
 
 	if (!minor)
@@ -166,11 +165,8 @@ int a5xx_debugfs_init(struct msm_gpu *gpu, struct drm_minor *minor)
 		return ret;
 	}
 
-	ent = debugfs_create_file("reset", S_IWUGO,
-		minor->debugfs_root,
-		dev, &reset_fops);
-	if (!ent)
-		return -ENOMEM;
+	debugfs_create_file("reset", S_IWUGO, minor->debugfs_root, dev,
+			    &reset_fops);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index a3c778df23a8..1671db47aa57 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -309,12 +309,18 @@ static const struct {
 
 void a5xx_set_hwcg(struct msm_gpu *gpu, bool state)
 {
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	unsigned int i;
 
 	for (i = 0; i < ARRAY_SIZE(a5xx_hwcg); i++)
 		gpu_write(gpu, a5xx_hwcg[i].offset,
 			state ? a5xx_hwcg[i].value : 0);
 
+	if (adreno_is_a540(adreno_gpu)) {
+		gpu_write(gpu, REG_A5XX_RBBM_CLOCK_DELAY_GPMU, state ? 0x00000770 : 0);
+		gpu_write(gpu, REG_A5XX_RBBM_CLOCK_HYST_GPMU, state ? 0x00000004 : 0);
+	}
+
 	gpu_write(gpu, REG_A5XX_RBBM_CLOCK_CNTL, state ? 0xAAA8AA00 : 0);
 	gpu_write(gpu, REG_A5XX_RBBM_ISDB_CNT, state ? 0x182 : 0x180);
 }
@@ -498,6 +504,9 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 
 	gpu_write(gpu, REG_A5XX_VBIF_ROUND_ROBIN_QOS_ARB, 0x00000003);
 
+	if (adreno_is_a540(adreno_gpu))
+		gpu_write(gpu, REG_A5XX_VBIF_GATE_OFF_WRREQ_EN, 0x00000009);
+
 	/* Make all blocks contribute to the GPU BUSY perf counter */
 	gpu_write(gpu, REG_A5XX_RBBM_PERFCTR_GPU_BUSY_MASKED, 0xFFFFFFFF);
 
@@ -558,7 +567,10 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 	gpu_write(gpu, REG_A5XX_UCHE_GMEM_RANGE_MAX_HI, 0x00000000);
 
 	gpu_write(gpu, REG_A5XX_CP_MEQ_THRESHOLDS, 0x40);
-	gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x40);
+	if (adreno_is_a530(adreno_gpu))
+		gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x40);
+	if (adreno_is_a540(adreno_gpu))
+		gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x400);
 	gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_2, 0x80000060);
 	gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_1, 0x40201B16);
 
@@ -583,6 +595,8 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 	/* Set the highest bank bit */
 	gpu_write(gpu, REG_A5XX_TPL1_MODE_CNTL, 2 << 7);
 	gpu_write(gpu, REG_A5XX_RB_MODE_CNTL, 2 << 1);
+	if (adreno_is_a540(adreno_gpu))
+		gpu_write(gpu, REG_A5XX_UCHE_DBG_ECO_CNTL_2, 2);
 
 	/* Protect registers from the CP */
 	gpu_write(gpu, REG_A5XX_CP_PROTECT_CNTL, 0x00000007);
@@ -633,6 +647,30 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 		REG_A5XX_RBBM_SECVID_TSB_TRUSTED_BASE_HI, 0x00000000);
 	gpu_write(gpu, REG_A5XX_RBBM_SECVID_TSB_TRUSTED_SIZE, 0x00000000);
 
+	/* Put the GPU into 64 bit by default */
+	gpu_write(gpu, REG_A5XX_CP_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A5XX_VSC_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A5XX_GRAS_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A5XX_RB_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A5XX_PC_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A5XX_HLSQ_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A5XX_VFD_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A5XX_VPC_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A5XX_UCHE_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A5XX_SP_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A5XX_TPL1_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A5XX_RBBM_SECVID_TSB_ADDR_MODE_CNTL, 0x1);
+
+	/*
+	 * VPC corner case with local memory load kill leads to corrupt
+	 * internal state. Normal Disable does not work for all a5x chips.
+	 * So do the following setting to disable it.
+	 */
+	if (adreno_gpu->info->quirks & ADRENO_QUIRK_LMLOADKILL_DISABLE) {
+		gpu_rmw(gpu, REG_A5XX_VPC_DBG_ECO_CNTL, 0, BIT(23));
+		gpu_rmw(gpu, REG_A5XX_HLSQ_DBG_ECO_CNTL, BIT(18), 0);
+	}
+
 	ret = adreno_hw_init(gpu);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_power.c b/drivers/gpu/drm/msm/adreno/a5xx_power.c
index 0ebfe2bb5707..a3a06db675ba 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_power.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_power.c
@@ -23,6 +23,18 @@
 #define AGC_POWER_CONFIG_PRODUCTION_ID 1
 #define AGC_INIT_MSG_VALUE 0xBABEFACE
 
+/* AGC_LM_CONFIG (A540+) */
+#define AGC_LM_CONFIG (136/4)
+#define AGC_LM_CONFIG_GPU_VERSION_SHIFT 17
+#define AGC_LM_CONFIG_ENABLE_GPMU_ADAPTIVE 1
+#define AGC_LM_CONFIG_THROTTLE_DISABLE (2 << 8)
+#define AGC_LM_CONFIG_ISENSE_ENABLE (1 << 4)
+#define AGC_LM_CONFIG_ENABLE_ERROR (3 << 4)
+#define AGC_LM_CONFIG_LLM_ENABLED (1 << 16)
+#define AGC_LM_CONFIG_BCL_DISABLED (1 << 24)
+
+#define AGC_LEVEL_CONFIG (140/4)
+
 static struct {
 	uint32_t reg;
 	uint32_t value;
@@ -107,7 +119,7 @@ static inline uint32_t _get_mvolts(struct msm_gpu *gpu, uint32_t freq)
 }
 
 /* Setup thermal limit management */
-static void a5xx_lm_setup(struct msm_gpu *gpu)
+static void a530_lm_setup(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu);
@@ -156,6 +168,45 @@ static void a5xx_lm_setup(struct msm_gpu *gpu)
 	gpu_write(gpu, AGC_INIT_MSG_MAGIC, AGC_INIT_MSG_VALUE);
 }
 
+#define PAYLOAD_SIZE(_size) ((_size) * sizeof(u32))
+#define LM_DCVS_LIMIT 1
+#define LEVEL_CONFIG ~(0x303)
+
+static void a540_lm_setup(struct msm_gpu *gpu)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	u32 config;
+
+	/* The battery current limiter isn't enabled for A540 */
+	config = AGC_LM_CONFIG_BCL_DISABLED;
+	config |= adreno_gpu->rev.patchid << AGC_LM_CONFIG_GPU_VERSION_SHIFT;
+
+	/* For now disable GPMU side throttling */
+	config |= AGC_LM_CONFIG_THROTTLE_DISABLE;
+
+	/* Until we get clock scaling 0 is always the active power level */
+	gpu_write(gpu, REG_A5XX_GPMU_GPMU_VOLTAGE, 0x80000000 | 0);
+
+	/* Fixed at 6000 for now */
+	gpu_write(gpu, REG_A5XX_GPMU_GPMU_PWR_THRESHOLD, 0x80000000 | 6000);
+
+	gpu_write(gpu, AGC_MSG_STATE, 0x80000001);
+	gpu_write(gpu, AGC_MSG_COMMAND, AGC_POWER_CONFIG_PRODUCTION_ID);
+
+	gpu_write(gpu, AGC_MSG_PAYLOAD(0), 5448);
+	gpu_write(gpu, AGC_MSG_PAYLOAD(1), 1);
+
+	gpu_write(gpu, AGC_MSG_PAYLOAD(2), _get_mvolts(gpu, gpu->fast_rate));
+	gpu_write(gpu, AGC_MSG_PAYLOAD(3), gpu->fast_rate / 1000000);
+
+	gpu_write(gpu, AGC_MSG_PAYLOAD(AGC_LM_CONFIG), config);
+	gpu_write(gpu, AGC_MSG_PAYLOAD(AGC_LEVEL_CONFIG), LEVEL_CONFIG);
+	gpu_write(gpu, AGC_MSG_PAYLOAD_SIZE,
+	PAYLOAD_SIZE(AGC_LEVEL_CONFIG + 1));
+
+	gpu_write(gpu, AGC_INIT_MSG_MAGIC, AGC_INIT_MSG_VALUE);
+}
+
 /* Enable SP/TP cpower collapse */
 static void a5xx_pc_init(struct msm_gpu *gpu)
 {
@@ -197,7 +248,8 @@ static int a5xx_gpmu_init(struct msm_gpu *gpu)
 		return -EINVAL;
 	}
 
-	gpu_write(gpu, REG_A5XX_GPMU_WFI_CONFIG, 0x4014);
+	if (adreno_is_a530(adreno_gpu))
+		gpu_write(gpu, REG_A5XX_GPMU_WFI_CONFIG, 0x4014);
 
 	/* Kick off the GPMU */
 	gpu_write(gpu, REG_A5XX_GPMU_CM3_SYSRESET, 0x0);
@@ -211,12 +263,26 @@ static int a5xx_gpmu_init(struct msm_gpu *gpu)
 		DRM_ERROR("%s: GPMU firmware initialization timed out\n",
 			gpu->name);
 
+	if (!adreno_is_a530(adreno_gpu)) {
+		u32 val = gpu_read(gpu, REG_A5XX_GPMU_GENERAL_1);
+
+		if (val)
+			DRM_ERROR("%s: GPMU firmware initialization failed: %d\n",
+				  gpu->name, val);
+	}
+
 	return 0;
 }
 
 /* Enable limits management */
 static void a5xx_lm_enable(struct msm_gpu *gpu)
 {
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+
+	/* This init sequence only applies to A530 */
+	if (!adreno_is_a530(adreno_gpu))
+		return;
+
 	gpu_write(gpu, REG_A5XX_GDPM_INT_MASK, 0x0);
 	gpu_write(gpu, REG_A5XX_GDPM_INT_EN, 0x0A);
 	gpu_write(gpu, REG_A5XX_GPMU_GPMU_VOLTAGE_INTR_EN_MASK, 0x01);
@@ -228,10 +294,14 @@ static void a5xx_lm_enable(struct msm_gpu *gpu)
 
 int a5xx_power_init(struct msm_gpu *gpu)
 {
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	int ret;
 
 	/* Set up the limits management */
-	a5xx_lm_setup(gpu);
+	if (adreno_is_a530(adreno_gpu))
+		a530_lm_setup(gpu);
+	else
+		a540_lm_setup(gpu);
 
 	/* Set up SP/TP power collpase */
 	a5xx_pc_init(gpu);
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index 38e2cfa9cec7..2ca470eb5cb8 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -74,7 +74,7 @@ bool a6xx_gmu_sptprac_is_on(struct a6xx_gmu *gmu)
 	u32 val;
 
 	/* This can be called from gpu state code so make sure GMU is valid */
-	if (IS_ERR_OR_NULL(gmu->mmio))
+	if (!gmu->initialized)
 		return false;
 
 	val = gmu_read(gmu, REG_A6XX_GMU_SPTPRAC_PWR_CLK_STATUS);
@@ -90,7 +90,7 @@ bool a6xx_gmu_gx_is_on(struct a6xx_gmu *gmu)
 	u32 val;
 
 	/* This can be called from gpu state code so make sure GMU is valid */
-	if (IS_ERR_OR_NULL(gmu->mmio))
+	if (!gmu->initialized)
 		return false;
 
 	val = gmu_read(gmu, REG_A6XX_GMU_SPTPRAC_PWR_CLK_STATUS);
@@ -504,8 +504,10 @@ static void a6xx_gmu_rpmh_init(struct a6xx_gmu *gmu)
 	wmb();
 
 err:
-	devm_iounmap(gmu->dev, pdcptr);
-	devm_iounmap(gmu->dev, seqptr);
+	if (!IS_ERR_OR_NULL(pdcptr))
+		iounmap(pdcptr);
+	if (!IS_ERR_OR_NULL(seqptr))
+		iounmap(seqptr);
 }
 
 /*
@@ -695,7 +697,7 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu)
 	struct a6xx_gmu *gmu = &a6xx_gpu->gmu;
 	int status, ret;
 
-	if (WARN(!gmu->mmio, "The GMU is not set up yet\n"))
+	if (WARN(!gmu->initialized, "The GMU is not set up yet\n"))
 		return 0;
 
 	gmu->hung = false;
@@ -765,7 +767,7 @@ bool a6xx_gmu_isidle(struct a6xx_gmu *gmu)
 {
 	u32 reg;
 
-	if (!gmu->mmio)
+	if (!gmu->initialized)
 		return true;
 
 	reg = gmu_read(gmu, REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS);
@@ -1195,7 +1197,7 @@ static void __iomem *a6xx_gmu_get_mmio(struct platform_device *pdev,
 		return ERR_PTR(-EINVAL);
 	}
 
-	ret = devm_ioremap(&pdev->dev, res->start, resource_size(res));
+	ret = ioremap(res->start, resource_size(res));
 	if (!ret) {
 		DRM_DEV_ERROR(&pdev->dev, "Unable to map the %s registers\n", name);
 		return ERR_PTR(-EINVAL);
@@ -1211,10 +1213,10 @@ static int a6xx_gmu_get_irq(struct a6xx_gmu *gmu, struct platform_device *pdev,
 
 	irq = platform_get_irq_byname(pdev, name);
 
-	ret = devm_request_irq(&pdev->dev, irq, handler, IRQF_TRIGGER_HIGH,
-		name, gmu);
+	ret = request_irq(irq, handler, IRQF_TRIGGER_HIGH, name, gmu);
 	if (ret) {
-		DRM_DEV_ERROR(&pdev->dev, "Unable to get interrupt %s\n", name);
+		DRM_DEV_ERROR(&pdev->dev, "Unable to get interrupt %s %d\n",
+			      name, ret);
 		return ret;
 	}
 
@@ -1227,27 +1229,35 @@ void a6xx_gmu_remove(struct a6xx_gpu *a6xx_gpu)
 {
 	struct a6xx_gmu *gmu = &a6xx_gpu->gmu;
 
-	if (IS_ERR_OR_NULL(gmu->mmio))
+	if (!gmu->initialized)
 		return;
 
-	a6xx_gmu_stop(a6xx_gpu);
-
-	pm_runtime_disable(gmu->dev);
+	pm_runtime_force_suspend(gmu->dev);
 
 	if (!IS_ERR_OR_NULL(gmu->gxpd)) {
 		pm_runtime_disable(gmu->gxpd);
 		dev_pm_domain_detach(gmu->gxpd, false);
 	}
 
-	a6xx_gmu_irq_disable(gmu);
+	iounmap(gmu->mmio);
+	gmu->mmio = NULL;
+
 	a6xx_gmu_memory_free(gmu, gmu->hfi);
 
 	iommu_detach_device(gmu->domain, gmu->dev);
 
 	iommu_domain_free(gmu->domain);
+
+	free_irq(gmu->gmu_irq, gmu);
+	free_irq(gmu->hfi_irq, gmu);
+
+	/* Drop reference taken in of_find_device_by_node */
+	put_device(gmu->dev);
+
+	gmu->initialized = false;
 }
 
-int a6xx_gmu_probe(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
+int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 {
 	struct a6xx_gmu *gmu = &a6xx_gpu->gmu;
 	struct platform_device *pdev = of_find_device_by_node(node);
@@ -1268,34 +1278,34 @@ int a6xx_gmu_probe(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 	/* Get the list of clocks */
 	ret = a6xx_gmu_clocks_probe(gmu);
 	if (ret)
-		return ret;
+		goto err_put_device;
 
 	/* Set up the IOMMU context bank */
 	ret = a6xx_gmu_memory_probe(gmu);
 	if (ret)
-		return ret;
+		goto err_put_device;
 
 	/* Allocate memory for for the HFI queues */
 	gmu->hfi = a6xx_gmu_memory_alloc(gmu, SZ_16K);
 	if (IS_ERR(gmu->hfi))
-		goto err;
+		goto err_memory;
 
 	/* Allocate memory for the GMU debug region */
 	gmu->debug = a6xx_gmu_memory_alloc(gmu, SZ_16K);
 	if (IS_ERR(gmu->debug))
-		goto err;
+		goto err_memory;
 
 	/* Map the GMU registers */
 	gmu->mmio = a6xx_gmu_get_mmio(pdev, "gmu");
 	if (IS_ERR(gmu->mmio))
-		goto err;
+		goto err_memory;
 
 	/* Get the HFI and GMU interrupts */
 	gmu->hfi_irq = a6xx_gmu_get_irq(gmu, pdev, "hfi", a6xx_hfi_irq);
 	gmu->gmu_irq = a6xx_gmu_get_irq(gmu, pdev, "gmu", a6xx_gmu_irq);
 
 	if (gmu->hfi_irq < 0 || gmu->gmu_irq < 0)
-		goto err;
+		goto err_mmio;
 
 	/*
 	 * Get a link to the GX power domain to reset the GPU in case of GMU
@@ -1309,8 +1319,15 @@ int a6xx_gmu_probe(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 	/* Set up the HFI queues */
 	a6xx_hfi_init(gmu);
 
+	gmu->initialized = true;
+
 	return 0;
-err:
+
+err_mmio:
+	iounmap(gmu->mmio);
+	free_irq(gmu->gmu_irq, gmu);
+	free_irq(gmu->hfi_irq, gmu);
+err_memory:
 	a6xx_gmu_memory_free(gmu, gmu->hfi);
 
 	if (gmu->domain) {
@@ -1318,6 +1335,11 @@ err:
 
 		iommu_domain_free(gmu->domain);
 	}
+	ret = -ENODEV;
 
-	return -ENODEV;
+err_put_device:
+	/* Drop reference taken in of_find_device_by_node */
+	put_device(gmu->dev);
+
+	return ret;
 }
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
index bedd8e6a63aa..39a26dd63674 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
@@ -75,6 +75,7 @@ struct a6xx_gmu {
 
 	struct a6xx_hfi_queue queues[2];
 
+	bool initialized;
 	bool hung;
 };
 
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index e74dce474250..be39cf01e51e 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -391,6 +391,20 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 		REG_A6XX_RBBM_SECVID_TSB_TRUSTED_BASE_HI, 0x00000000);
 	gpu_write(gpu, REG_A6XX_RBBM_SECVID_TSB_TRUSTED_SIZE, 0x00000000);
 
+	/* Turn on 64 bit addressing for all blocks */
+	gpu_write(gpu, REG_A6XX_CP_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A6XX_VSC_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A6XX_GRAS_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A6XX_RB_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A6XX_PC_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A6XX_HLSQ_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A6XX_VFD_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A6XX_VPC_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A6XX_UCHE_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A6XX_SP_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A6XX_TPL1_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A6XX_RBBM_SECVID_TSB_ADDR_MODE_CNTL, 0x1);
+
 	/* enable hardware clockgating */
 	a6xx_set_hwcg(gpu, true);
 
@@ -854,7 +868,7 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
 	/* FIXME: How do we gracefully handle this? */
 	BUG_ON(!node);
 
-	ret = a6xx_gmu_probe(a6xx_gpu, node);
+	ret = a6xx_gmu_init(a6xx_gpu, node);
 	if (ret) {
 		a6xx_destroy(&(a6xx_gpu->base.base));
 		return ERR_PTR(ret);
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
index b46279eb18c5..64399554f2dd 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
@@ -53,7 +53,7 @@ bool a6xx_gmu_isidle(struct a6xx_gmu *gmu);
 int a6xx_gmu_set_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state);
 void a6xx_gmu_clear_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state);
 
-int a6xx_gmu_probe(struct a6xx_gpu *a6xx_gpu, struct device_node *node);
+int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node);
 void a6xx_gmu_remove(struct a6xx_gpu *a6xx_gpu);
 
 void a6xx_gmu_set_freq(struct msm_gpu *gpu, unsigned long freq);
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index b3deb346a42b..40133a43960c 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -134,6 +134,24 @@ static const struct adreno_info gpulist[] = {
 		.init = a5xx_gpu_init,
 		.zapfw = "a530_zap.mdt",
 	}, {
+		.rev = ADRENO_REV(5, 4, 0, 2),
+		.revn = 540,
+		.name = "A540",
+		.fw = {
+			[ADRENO_FW_PM4] = "a530_pm4.fw",
+			[ADRENO_FW_PFP] = "a530_pfp.fw",
+			[ADRENO_FW_GPMU] = "a540_gpmu.fw2",
+		},
+		.gmem = SZ_1M,
+		/*
+		 * Increase inactive period to 250 to avoid bouncing
+		 * the GDSC which appears to make it grumpy
+		 */
+		.inactive_period = 250,
+		.quirks = ADRENO_QUIRK_LMLOADKILL_DISABLE,
+		.init = a5xx_gpu_init,
+		.zapfw = "a540_zap.mdt",
+	}, {
 		.rev = ADRENO_REV(6, 3, 0, ANY_ID),
 		.revn = 630,
 		.name = "A630",
@@ -340,7 +358,7 @@ static void adreno_unbind(struct device *dev, struct device *master,
 {
 	struct msm_gpu *gpu = dev_get_drvdata(dev);
 
-	gpu->funcs->pm_suspend(gpu);
+	pm_runtime_force_suspend(dev);
 	gpu->funcs->destroy(gpu);
 
 	set_gpu_pdev(dev_get_drvdata(master), NULL);
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index a9c0ac937b00..9acbbc0f3232 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -56,7 +56,6 @@ static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname,
 		return ret;
 
 	mem_phys = r.start;
-	mem_size = resource_size(&r);
 
 	/* Request the MDT file for the firmware */
 	fw = adreno_request_fw(to_adreno_gpu(gpu), fwname);
@@ -72,6 +71,13 @@ static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname,
 		goto out;
 	}
 
+	if (mem_size > resource_size(&r)) {
+		DRM_DEV_ERROR(dev,
+			"memory region is too small to load the MDT\n");
+		ret = -E2BIG;
+		goto out;
+	}
+
 	/* Allocate memory for the firmware image */
 	mem_region = memremap(mem_phys, mem_size,  MEMREMAP_WC);
 	if (!mem_region) {
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index c5ea1f0e7438..c7441fb8313e 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -50,6 +50,7 @@ enum {
 enum adreno_quirks {
 	ADRENO_QUIRK_TWO_PASS_USE_WFI = 1,
 	ADRENO_QUIRK_FAULT_DETECT_MASK = 2,
+	ADRENO_QUIRK_LMLOADKILL_DISABLE = 3,
 };
 
 struct adreno_rev {
@@ -210,6 +211,11 @@ static inline int adreno_is_a530(struct adreno_gpu *gpu)
 	return gpu->revn == 530;
 }
 
+static inline int adreno_is_a540(struct adreno_gpu *gpu)
+{
+	return gpu->revn == 540;
+}
+
 int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value);
 const struct firmware *adreno_request_fw(struct adreno_gpu *adreno_gpu,
 		const char *fwname);