Merge tag 'drm-next-2019-09-18' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "This is the main pull request for 5.4-rc1 merge window. I don't think
  there is anything outstanding so next week should just be fixes, but
  we'll see if I missed anything. I landed some fixes earlier in the
  week but got delayed writing summary and sending it out, due to a mix
  of sick kid and jetlag!

  There are some fixes pending, but I'd rather get the main merge out of
  the way instead of delaying it longer.

  It's also pretty large in commit count and new amd header file size.
  The largest thing is four new amdgpu products (navi12/14, arcturus and
  renoir APU support).

  Otherwise it's pretty much lots of work across the board, i915 has
  started landing tigerlake support, lots of icelake fixes and lots of
  locking reworking for future gpu support, lots of header file rework
  (drmP.h is nearly gone), some old legacy hacks (DRM_WAIT_ON) have been
  put into the places they are needed.

  uapi:
   - content protection type property for HDCP

  core:
   - rework include dependencies
   - lots of drmP.h removals
   - link rate calculation robustness fix
   - make fb helper map only when required
   - add connector->DDC adapter link
   - DRM_WAIT_ON removed
   - drop DRM_AUTH usage from drivers

  dma-buf:
   - reservation object fence helper

  dma-fence:
   - shrink dma_fence struct
   - merge signal functions
   - store timestamps in dma_fence
   - selftests

  ttm:
   - embed drm_get_object struct into ttm_buffer_object
   - release_notify callback

  bridges:
   - sii902x - audio graph card support
   - tc358767 - aux data handling rework
   - ti-snd64dsi86 - debugfs support, DSI mode flags support

  panels:
   - Support for GiantPlus GPM940B0, Sharp LQ070Y3DG3B, Ortustech
     COM37H3M, Novatek NT39016, Sharp LS020B1DD01D, Raydium RM67191, Boe
     Himax8279d, Sharp LD-D5116Z01B
   - TI nspire, NEC NL8048HL11, LG Philips LB035Q02, Sharp LS037V7DW01,
     Sony ACX565AKM, Toppoly TD028TTEC1 Toppoly TD043MTEA1

  i915:
   - Initial tigerlake platform support
   - Locking simplification work, general all over refactoring.
   - Selftests
   - HDCP debug info improvements
   - DSI properties
   - Icelake display PLL fixes, colorspace fixes, bandwidth fixes, DSI
     suspend/resume
   - GuC fixes
   - Perf fixes
   - ElkhartLake enablement
   - DP MST fixes
   - GVT - command parser enhancements

  amdgpu:
   - add wipe memory on release flag for buffer creation
   - Navi12/14 support (may be marked experimental)
   - Arcturus support
   - Renoir APU support
   - mclk DPM for Navi
   - DC display fixes
   - Raven scatter/gather support
   - RAS support for GFX
   - Navi12 + Arcturus power features
   - GPU reset for Picasso
   - smu11 i2c controller support

  amdkfd:
   - navi12/14 support
   - Arcturus support

  radeon:
   - kexec fix

  nouveau:
   - improved display color management
   - detect lack of GPU power cables

  vmwgfx:
   - evicition priority support
   - remove unused security feature

  msm:
   - msm8998 display support
   - better async commit support for cursor updates

  etnaviv:
   - per-process address space support
   - performance counter fixes
   - softpin support

  mcde:
   - DCS transfers fix

  exynos:
   - drmP.h cleanup

  lima:
   - reduce logging

  kirin:
   - misc clenaups

  komeda:
   - dual-link support
   - DT memory regions

  hisilicon:
   - misc fixes

  imx:
   - IPUv3 image converter fixes
   - 32-bit RGB V4L2 pixel format support

  ingenic:
   - more support for panel related cases

  mgag200:
   - cursor support fix

  panfrost:
   - export GPU features register to userspace
   - gpu heap allocations
   - per-fd address space support

  pl111:
   - CLD pads wiring support removed from DT

  rockchip:
   - rework to use DRM PSR helpers
   - fix bug in VOP_WIN_GET macro
   - DSI DT binding rework

  sun4i:
   - improve support for color encoding and range
   - DDC enabled GPIO

  tinydrm:
   - rework SPI support
   - improve MIPI-DBI support
   - moved to drm/tiny

  vkms:
   - rework CRC tracking

  dw-hdmi:
   - get_eld and i2s improvements

  gm12u320:
   - misc fixes

  meson:
   - global code cleanup
   - vpu feature detect

  omap:
   - alpha/pixel blend mode properties

  rcar-du:
   - misc fixes"

* tag 'drm-next-2019-09-18' of git://anongit.freedesktop.org/drm/drm: (2112 commits)
  drm/nouveau/bar/gm20b: Avoid BAR1 teardown during init
  drm/nouveau: Fix ordering between TTM and GEM release
  drm/nouveau/prime: Extend DMA reservation object lock
  drm/nouveau: Fix fallout from reservation object rework
  drm/nouveau/kms/nv50-: Don't create MSTMs for eDP connectors
  drm/i915: Use NOEVICT for first pass on attemping to pin a GGTT mmap
  drm/i915: to make vgpu ppgtt notificaiton as atomic operation
  drm/i915: Flush the existing fence before GGTT read/write
  drm/i915: Hold irq-off for the entire fake lock period
  drm/i915/gvt: update RING_START reg of vGPU when the context is submitted to i915
  drm/i915/gvt: update vgpu workload head pointer correctly
  drm/mcde: Fix DSI transfers
  drm/msm: Use the correct dma_sync calls harder
  drm/msm: remove unlikely() from WARN_ON() conditions
  drm/msm/dsi: Fix return value check for clk_get_parent
  drm/msm: add atomic traces
  drm/msm/dpu: async commit support
  drm/msm: async commit support
  drm/msm: split power control from prepare/complete_commit
  drm/msm: add kms->flush_commit()
  ...

1 files changed, 56 insertions, 150 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 812717ccc69b..b97a47fc7a68 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -35,15 +35,19 @@
 #define __I915_GEM_GTT_H__
 
 #include <linux/io-mapping.h>
+#include <linux/kref.h>
 #include <linux/mm.h>
 #include <linux/pagevec.h>
+#include <linux/workqueue.h>
+
+#include <drm/drm_mm.h>
 
 #include "gt/intel_reset.h"
 #include "i915_gem_fence_reg.h"
 #include "i915_request.h"
 #include "i915_scatterlist.h"
 #include "i915_selftest.h"
-#include "i915_timeline.h"
+#include "gt/intel_timeline.h"
 
 #define I915_GTT_PAGE_SIZE_4K	BIT_ULL(12)
 #define I915_GTT_PAGE_SIZE_64K	BIT_ULL(16)
@@ -64,12 +68,10 @@
 struct drm_i915_file_private;
 struct drm_i915_gem_object;
 struct i915_vma;
+struct intel_gt;
 
 typedef u32 gen6_pte_t;
 typedef u64 gen8_pte_t;
-typedef u64 gen8_pde_t;
-typedef u64 gen8_ppgtt_pdpe_t;
-typedef u64 gen8_ppgtt_pml4e_t;
 
 #define ggtt_total_entries(ggtt) ((ggtt)->vm.total >> PAGE_SHIFT)
 
@@ -113,30 +115,18 @@ typedef u64 gen8_ppgtt_pml4e_t;
 #define HSW_GTT_ADDR_ENCODE(addr)	((addr) | (((addr) >> 28) & 0x7f0))
 #define HSW_PTE_ADDR_ENCODE(addr)	HSW_GTT_ADDR_ENCODE(addr)
 
-/* GEN8 32b style address is defined as a 3 level page table:
+/*
+ * GEN8 32b style address is defined as a 3 level page table:
  * 31:30 | 29:21 | 20:12 |  11:0
  * PDPE  |  PDE  |  PTE  | offset
  * The difference as compared to normal x86 3 level page table is the PDPEs are
  * programmed via register.
- */
-#define GEN8_3LVL_PDPES			4
-#define GEN8_PDE_SHIFT			21
-#define GEN8_PDE_MASK			0x1ff
-#define GEN8_PTE_SHIFT			12
-#define GEN8_PTE_MASK			0x1ff
-#define GEN8_PTES			I915_PTES(sizeof(gen8_pte_t))
-
-/* GEN8 48b style address is defined as a 4 level page table:
+ *
+ * GEN8 48b style address is defined as a 4 level page table:
  * 47:39 | 38:30 | 29:21 | 20:12 |  11:0
  * PML4E | PDPE  |  PDE  |  PTE  | offset
  */
-#define GEN8_PML4ES_PER_PML4		512
-#define GEN8_PML4E_SHIFT		39
-#define GEN8_PML4E_MASK			(GEN8_PML4ES_PER_PML4 - 1)
-#define GEN8_PDPE_SHIFT			30
-/* NB: GEN8_PDPE_MASK is untrue for 32b platforms, but it has no impact on 32b page
- * tables */
-#define GEN8_PDPE_MASK			0x1ff
+#define GEN8_3LVL_PDPES			4
 
 #define PPAT_UNCACHED			(_PAGE_PWT | _PAGE_PCD)
 #define PPAT_CACHED_PDE			0 /* WB LLC */
@@ -155,11 +145,6 @@ typedef u64 gen8_ppgtt_pml4e_t;
 #define GEN8_PPAT_ELLC_OVERRIDE		(0<<2)
 #define GEN8_PPAT(i, x)			((u64)(x) << ((i) * 8))
 
-#define GEN8_PPAT_GET_CA(x) ((x) & 3)
-#define GEN8_PPAT_GET_TC(x) ((x) & (3 << 2))
-#define GEN8_PPAT_GET_AGE(x) ((x) & (3 << 4))
-#define CHV_PPAT_GET_SNOOP(x) ((x) & (1 << 6))
-
 #define GEN8_PDE_IPS_64K BIT(11)
 #define GEN8_PDE_PS_2M   BIT(7)
 
@@ -243,8 +228,10 @@ struct i915_page_dma {
 	};
 };
 
-#define px_base(px) (&(px)->base)
-#define px_dma(px) (px_base(px)->daddr)
+struct i915_page_scratch {
+	struct i915_page_dma base;
+	u64 encode;
+};
 
 struct i915_page_table {
 	struct i915_page_dma base;
@@ -252,12 +239,32 @@ struct i915_page_table {
 };
 
 struct i915_page_directory {
-	struct i915_page_dma base;
-	atomic_t used;
+	struct i915_page_table pt;
 	spinlock_t lock;
 	void *entry[512];
 };
 
+#define __px_choose_expr(x, type, expr, other) \
+	__builtin_choose_expr( \
+	__builtin_types_compatible_p(typeof(x), type) || \
+	__builtin_types_compatible_p(typeof(x), const type), \
+	({ type __x = (type)(x); expr; }), \
+	other)
+
+#define px_base(px) \
+	__px_choose_expr(px, struct i915_page_dma *, __x, \
+	__px_choose_expr(px, struct i915_page_scratch *, &__x->base, \
+	__px_choose_expr(px, struct i915_page_table *, &__x->base, \
+	__px_choose_expr(px, struct i915_page_directory *, &__x->pt.base, \
+	(void)0))))
+#define px_dma(px) (px_base(px)->daddr)
+
+#define px_pt(px) \
+	__px_choose_expr(px, struct i915_page_table *, __x, \
+	__px_choose_expr(px, struct i915_page_directory *, &__x->pt, \
+	(void)0))
+#define px_used(px) (&px_pt(px)->used)
+
 struct i915_vma_ops {
 	/* Map an object into an address space with the given cache flags. */
 	int (*bind_vma)(struct i915_vma *vma,
@@ -280,8 +287,10 @@ struct pagestash {
 
 struct i915_address_space {
 	struct kref ref;
+	struct rcu_work rcu;
 
 	struct drm_mm mm;
+	struct intel_gt *gt;
 	struct drm_i915_private *i915;
 	struct device *dma;
 	/* Every address space belongs to a struct file - except for the global
@@ -302,12 +311,9 @@ struct i915_address_space {
 #define VM_CLASS_GGTT 0
 #define VM_CLASS_PPGTT 1
 
-	u64 scratch_pte;
-	int scratch_order;
-	struct i915_page_dma scratch_page;
-	struct i915_page_table *scratch_pt;
-	struct i915_page_directory *scratch_pd;
-	struct i915_page_directory *scratch_pdp; /* GEN8+ & 48b PPGTT */
+	struct i915_page_scratch scratch[4];
+	unsigned int scratch_order;
+	unsigned int top;
 
 	/**
 	 * List of vma currently bound.
@@ -386,7 +392,10 @@ struct i915_ggtt {
 
 	/** "Graphics Stolen Memory" holds the global PTEs */
 	void __iomem *gsm;
-	void (*invalidate)(struct drm_i915_private *dev_priv);
+	void (*invalidate)(struct i915_ggtt *ggtt);
+
+	/** PPGTT used for aliasing the PPGTT with the GTT */
+	struct i915_ppgtt *alias;
 
 	bool do_idle_maps;
 
@@ -425,8 +434,6 @@ struct gen6_ppgtt {
 
 	unsigned int pin_count;
 	bool scan_for_unused_pt;
-
-	struct gen6_ppgtt_cleanup_work *work;
 };
 
 #define __to_gen6_ppgtt(base) container_of(base, struct gen6_ppgtt, base)
@@ -506,15 +513,6 @@ static inline u32 gen6_pde_index(u32 addr)
 	return i915_pde_index(addr, GEN6_PDE_SHIFT);
 }
 
-static inline unsigned int
-i915_pdpes_per_pdp(const struct i915_address_space *vm)
-{
-	if (i915_vm_is_4lvl(vm))
-		return GEN8_PML4ES_PER_PML4;
-
-	return GEN8_3LVL_PDPES;
-}
-
 static inline struct i915_page_table *
 i915_pt_entry(const struct i915_page_directory * const pd,
 	      const unsigned short n)
@@ -529,73 +527,12 @@ i915_pd_entry(const struct i915_page_directory * const pdp,
 	return pdp->entry[n];
 }
 
-static inline struct i915_page_directory *
-i915_pdp_entry(const struct i915_page_directory * const pml4,
-	       const unsigned short n)
-{
-	return pml4->entry[n];
-}
-
-/* Equivalent to the gen6 version, For each pde iterates over every pde
- * between from start until start + length. On gen8+ it simply iterates
- * over every page directory entry in a page directory.
- */
-#define gen8_for_each_pde(pt, pd, start, length, iter)			\
-	for (iter = gen8_pde_index(start);				\
-	     length > 0 && iter < I915_PDES &&				\
-		     (pt = i915_pt_entry(pd, iter), true);		\
-	     ({ u64 temp = ALIGN(start+1, 1 << GEN8_PDE_SHIFT);		\
-		    temp = min(temp - start, length);			\
-		    start += temp, length -= temp; }), ++iter)
-
-#define gen8_for_each_pdpe(pd, pdp, start, length, iter)		\
-	for (iter = gen8_pdpe_index(start);				\
-	     length > 0 && iter < i915_pdpes_per_pdp(vm) &&		\
-		     (pd = i915_pd_entry(pdp, iter), true);		\
-	     ({ u64 temp = ALIGN(start+1, 1 << GEN8_PDPE_SHIFT);	\
-		    temp = min(temp - start, length);			\
-		    start += temp, length -= temp; }), ++iter)
-
-#define gen8_for_each_pml4e(pdp, pml4, start, length, iter)		\
-	for (iter = gen8_pml4e_index(start);				\
-	     length > 0 && iter < GEN8_PML4ES_PER_PML4 &&		\
-		     (pdp = i915_pdp_entry(pml4, iter), true);		\
-	     ({ u64 temp = ALIGN(start+1, 1ULL << GEN8_PML4E_SHIFT);	\
-		    temp = min(temp - start, length);			\
-		    start += temp, length -= temp; }), ++iter)
-
-static inline u32 gen8_pte_index(u64 address)
-{
-	return i915_pte_index(address, GEN8_PDE_SHIFT);
-}
-
-static inline u32 gen8_pde_index(u64 address)
-{
-	return i915_pde_index(address, GEN8_PDE_SHIFT);
-}
-
-static inline u32 gen8_pdpe_index(u64 address)
-{
-	return (address >> GEN8_PDPE_SHIFT) & GEN8_PDPE_MASK;
-}
-
-static inline u32 gen8_pml4e_index(u64 address)
-{
-	return (address >> GEN8_PML4E_SHIFT) & GEN8_PML4E_MASK;
-}
-
-static inline u64 gen8_pte_count(u64 address, u64 length)
-{
-	return i915_pte_count(address, length, GEN8_PDE_SHIFT);
-}
-
 static inline dma_addr_t
 i915_page_dir_dma_addr(const struct i915_ppgtt *ppgtt, const unsigned int n)
 {
-	struct i915_page_directory *pd;
+	struct i915_page_dma *pt = ppgtt->pd->entry[n];
 
-	pd = i915_pdp_entry(ppgtt->pd, n);
-	return px_dma(pd);
+	return px_dma(pt ?: px_base(&ppgtt->vm.scratch[ppgtt->vm.top]));
 }
 
 static inline struct i915_ggtt *
@@ -614,46 +551,15 @@ i915_vm_to_ppgtt(struct i915_address_space *vm)
 	return container_of(vm, struct i915_ppgtt, vm);
 }
 
-#define INTEL_MAX_PPAT_ENTRIES 8
-#define INTEL_PPAT_PERFECT_MATCH (~0U)
-
-struct intel_ppat;
-
-struct intel_ppat_entry {
-	struct intel_ppat *ppat;
-	struct kref ref;
-	u8 value;
-};
-
-struct intel_ppat {
-	struct intel_ppat_entry entries[INTEL_MAX_PPAT_ENTRIES];
-	DECLARE_BITMAP(used, INTEL_MAX_PPAT_ENTRIES);
-	DECLARE_BITMAP(dirty, INTEL_MAX_PPAT_ENTRIES);
-	unsigned int max_entries;
-	u8 clear_value;
-	/*
-	 * Return a score to show how two PPAT values match,
-	 * a INTEL_PPAT_PERFECT_MATCH indicates a perfect match
-	 */
-	unsigned int (*match)(u8 src, u8 dst);
-	void (*update_hw)(struct drm_i915_private *i915);
-
-	struct drm_i915_private *i915;
-};
-
-const struct intel_ppat_entry *
-intel_ppat_get(struct drm_i915_private *i915, u8 value);
-void intel_ppat_put(const struct intel_ppat_entry *entry);
-
 int i915_ggtt_probe_hw(struct drm_i915_private *dev_priv);
 int i915_ggtt_init_hw(struct drm_i915_private *dev_priv);
 int i915_ggtt_enable_hw(struct drm_i915_private *dev_priv);
-void i915_ggtt_enable_guc(struct drm_i915_private *i915);
-void i915_ggtt_disable_guc(struct drm_i915_private *i915);
-int i915_gem_init_ggtt(struct drm_i915_private *dev_priv);
-void i915_ggtt_cleanup_hw(struct drm_i915_private *dev_priv);
+void i915_ggtt_enable_guc(struct i915_ggtt *ggtt);
+void i915_ggtt_disable_guc(struct i915_ggtt *ggtt);
+int i915_init_ggtt(struct drm_i915_private *dev_priv);
+void i915_ggtt_driver_release(struct drm_i915_private *dev_priv);
 
-int i915_ppgtt_init_hw(struct drm_i915_private *dev_priv);
+int i915_ppgtt_init_hw(struct intel_gt *gt);
 
 struct i915_ppgtt *i915_ppgtt_create(struct drm_i915_private *dev_priv);
 
@@ -694,9 +600,9 @@ int i915_gem_gtt_insert(struct i915_address_space *vm,
 			u64 start, u64 end, unsigned int flags);
 
 /* Flags used by pin/bind&friends. */
-#define PIN_NONBLOCK		BIT_ULL(0)
-#define PIN_NONFAULT		BIT_ULL(1)
-#define PIN_NOEVICT		BIT_ULL(2)
+#define PIN_NOEVICT		BIT_ULL(0)
+#define PIN_NOSEARCH		BIT_ULL(1)
+#define PIN_NONBLOCK		BIT_ULL(2)
 #define PIN_MAPPABLE		BIT_ULL(3)
 #define PIN_ZONE_4G		BIT_ULL(4)
 #define PIN_HIGH		BIT_ULL(5)