Merge tag 'drm-next-2020-01-30' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Davbe Airlie:
 "This is the main pull request for graphics for 5.6. Usual selection of
  changes all over.

  I've got one outstanding vmwgfx pull that touches mm so kept it
  separate until after all of this lands. I'll try and get it to you
  soon after this, but it might be early next week (nothing wrong with
  code, just my schedule is messy)

  This also hits a lot of fbdev drivers with some cleanups.

  Other notables:
   - vulkan timeline semaphore support added to syncobjs
   - nouveau turing secureboot/graphics support
   - Displayport MST display stream compression support

  Detailed summary:

  uapi:
   - dma-buf heaps added (and fixed)
   - command line add support for panel oreientation
   - command line allow overriding penguin count

  drm:
   - mipi dsi definition updates
   - lockdep annotations for dma_resv
   - remove dma-buf kmap/kunmap support
   - constify fb_ops in all fbdev drivers
   - MST fix for daisy chained hotplug-
   - CTA-861-G modes with VIC >= 193 added
   - fix drm_panel_of_backlight export
   - LVDS decoder support
   - more device based logging support
   - scanline alighment for dumb buffers
   - MST DSC helpers

  scheduler:
   - documentation fixes
   - job distribution improvements

  panel:
   - Logic PD type 28 panel support
   - Jimax8729d MIPI-DSI
   - igenic JZ4770
   - generic DSI devicetree bindings
   - sony acx424AKP panel
   - Leadtek LTK500HD1829
   - xinpeng XPP055C272
   - AUO B116XAK01
   - GiantPlus GPM940B0
   - BOE NV140FHM-N49
   - Satoz SAT050AT40H12R2
   - Sharp LS020B1DD01D panels.

  ttm:
   - use blocking WW lock

  i915:
   - hw/uapi state separation
   - Lock annotation improvements
   - selftest improvements
   - ICL/TGL DSI VDSC support
   - VBT parsing improvments
   - Display refactoring
   - DSI updates + fixes
   - HDCP 2.2 for CFL
   - CML PCI ID fixes
   - GLK+ fbc fix
   - PSR fixes
   - GEN/GT refactor improvments
   - DP MST fixes
   - switch context id alloc to xarray
   - workaround updates
   - LMEM debugfs support
   - tiled monitor fixes
   - ICL+ clock gating programming removed
   - DP MST disable sequence fixed
   - LMEM discontiguous object maps
   - prefaulting for discontiguous objects
   - use LMEM for dumb buffers if possible
   - add LMEM mmap support

  amdgpu:
   - enable sync object timelines for vulkan
   - MST atomic routines
   - enable MST DSC support
   - add DMCUB display microengine support
   - DC OEM i2c support
   - Renoir DC fixes
   - Initial HDCP 2.x support
   - BACO support for Arcturus
   - Use BACO for runtime PM power save
   - gfxoff on navi10
   - gfx10 golden updates and fixes
   - DCN support on POWER
   - GFXOFF for raven1 refresh
   - MM engine idle handlers cleanup
   - 10bpc EDP panel fixes
   - renoir watermark fixes
   - SR-IOV fixes
   - Arcturus VCN fixes
   - GDDR6 training fixes
   - freesync fixes
   - Pollock support

  amdkfd:
   - unify more codepath with amdgpu
   - use KIQ to setup HIQ rather than MMIO

  radeon:
   - fix vma fault handler race
   - PPC DMA fix
   - register check fixes for r100/r200

  nouveau:
   - mmap_sem vs dma_resv fix
   - rewrite the ACR secure boot code for Turing
   - TU10x graphics engine support (TU11x pending)
   - Page kind mapping for turing
   - 10-bit LUT support
   - GP10B Tegra fixes
   - HD audio regression fix

  hisilicon/hibmc:
   - use generic fbdev code and helpers

  rockchip:
   - dsi/px30 support

  virtio:
   - fb damage support
   - static some functions

  vc4:
   - use dma_resv lock wrappers

  msm:
   - use dma_resv lock wrappers
   - sc7180 display + DSI support
   - a618 support
   - UBWC support improvements

  vmwgfx:
   - updates + new logging uapi

  exynos:
   - enable/disable callback cleanups

  etnaviv:
   - use dma_resv lock wrappers

  atmel-hlcdc:
   - clock fixes

  mediatek:
   - cmdq support
   - non-smooth cursor fixes
   - ctm property support

  sun4i:
   - suspend support
   - A64 mipi dsi support

  rcar-du:
   - Color management module support
   - LVDS encoder dual-link support
   - R8A77980 support

  analogic:
   - add support for an6345

  ast:
   - atomic modeset support
   - primary plane garbage fix

  arcgpu:
   - fixes for fourcc handling

  tegra:
   - minor fixes and improvments

  mcde:
   - vblank support

  meson:
   - OSD1 plane AFBC commit

  gma500:
   - add pageflip support
   - reomve global drm_dev

  komeda:
   - tweak debugfs output
   - d32 support
   - runtime PM suppotr

  udl:
   - use generic shmem helpers
   - cleanup and fixes"

* tag 'drm-next-2020-01-30' of git://anongit.freedesktop.org/drm/drm: (1998 commits)
  drm/nouveau/fb/gp102-: allow module to load even when scrubber binary is missing
  drm/nouveau/acr: return error when registering LSF if ACR not supported
  drm/nouveau/disp/gv100-: not all channel types support reporting error codes
  drm/nouveau/disp/nv50-: prevent oops when no channel method map provided
  drm/nouveau: support synchronous pushbuf submission
  drm/nouveau: signal pending fences when channel has been killed
  drm/nouveau: reject attempts to submit to dead channels
  drm/nouveau: zero vma pointer even if we only unreference it rather than free
  drm/nouveau: Add HD-audio component notifier support
  drm/nouveau: fix build error without CONFIG_IOMMU_API
  drm/nouveau/kms/nv04: remove set but not used variable 'width'
  drm/nouveau/kms/nv50: remove set but not unused variable 'nv_connector'
  drm/nouveau/mmu: fix comptag memory leak
  drm/nouveau/gr/gp10b: Use gp100_grctx and gp100_gr_zbc
  drm/nouveau/pmu/gm20b,gp10b: Fix Falcon bootstrapping
  drm/exynos: Rename Exynos to lowercase
  drm/exynos: change callback names
  drm/mst: Don't do atomic checks over disabled managers
  drm/amdgpu: add the lost mutex_init back
  drm/amd/display: skip opp blank or unblank if test pattern enabled
  ...

1 files changed, 296 insertions, 1 deletions

diff --git a/drivers/gpu/drm/amd/display/dc/dc_helper.c b/drivers/gpu/drm/amd/display/dc/dc_helper.c
index 30b2f9edd42f..737048d8a96c 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dc_helper.c
@@ -32,6 +32,74 @@
 #include "dm_services.h"
 #include <stdarg.h>
 
+#include "dc.h"
+#include "dc_dmub_srv.h"
+
+static inline void submit_dmub_read_modify_write(
+	struct dc_reg_helper_state *offload,
+	const struct dc_context *ctx)
+{
+	struct dmub_rb_cmd_read_modify_write *cmd_buf = &offload->cmd_data.read_modify_write;
+	bool gather = false;
+
+	offload->should_burst_write =
+			(offload->same_addr_count == (DMUB_READ_MODIFY_WRITE_SEQ__MAX - 1));
+	cmd_buf->header.payload_bytes =
+			sizeof(struct dmub_cmd_read_modify_write_sequence) * offload->reg_seq_count;
+
+	gather = ctx->dmub_srv->reg_helper_offload.gather_in_progress;
+	ctx->dmub_srv->reg_helper_offload.gather_in_progress = false;
+
+	dc_dmub_srv_cmd_queue(ctx->dmub_srv, &cmd_buf->header);
+
+	ctx->dmub_srv->reg_helper_offload.gather_in_progress = gather;
+
+	memset(cmd_buf, 0, sizeof(*cmd_buf));
+
+	offload->reg_seq_count = 0;
+	offload->same_addr_count = 0;
+}
+
+static inline void submit_dmub_burst_write(
+	struct dc_reg_helper_state *offload,
+	const struct dc_context *ctx)
+{
+	struct dmub_rb_cmd_burst_write *cmd_buf = &offload->cmd_data.burst_write;
+	bool gather = false;
+
+	cmd_buf->header.payload_bytes =
+			sizeof(uint32_t) * offload->reg_seq_count;
+
+	gather = ctx->dmub_srv->reg_helper_offload.gather_in_progress;
+	ctx->dmub_srv->reg_helper_offload.gather_in_progress = false;
+
+	dc_dmub_srv_cmd_queue(ctx->dmub_srv, &cmd_buf->header);
+
+	ctx->dmub_srv->reg_helper_offload.gather_in_progress = gather;
+
+	memset(cmd_buf, 0, sizeof(*cmd_buf));
+
+	offload->reg_seq_count = 0;
+}
+
+static inline void submit_dmub_reg_wait(
+		struct dc_reg_helper_state *offload,
+		const struct dc_context *ctx)
+{
+	struct dmub_rb_cmd_reg_wait *cmd_buf = &offload->cmd_data.reg_wait;
+	bool gather = false;
+
+	gather = ctx->dmub_srv->reg_helper_offload.gather_in_progress;
+	ctx->dmub_srv->reg_helper_offload.gather_in_progress = false;
+
+	dc_dmub_srv_cmd_queue(ctx->dmub_srv, &cmd_buf->header);
+
+	memset(cmd_buf, 0, sizeof(*cmd_buf));
+	offload->reg_seq_count = 0;
+
+	ctx->dmub_srv->reg_helper_offload.gather_in_progress = gather;
+}
+
 struct dc_reg_value_masks {
 	uint32_t value;
 	uint32_t mask;
@@ -77,6 +145,100 @@ static void set_reg_field_values(struct dc_reg_value_masks *field_value_mask,
 	}
 }
 
+static void dmub_flush_buffer_execute(
+		struct dc_reg_helper_state *offload,
+		const struct dc_context *ctx)
+{
+	submit_dmub_read_modify_write(offload, ctx);
+	dc_dmub_srv_cmd_execute(ctx->dmub_srv);
+}
+
+static void dmub_flush_burst_write_buffer_execute(
+		struct dc_reg_helper_state *offload,
+		const struct dc_context *ctx)
+{
+	submit_dmub_burst_write(offload, ctx);
+	dc_dmub_srv_cmd_execute(ctx->dmub_srv);
+}
+
+static bool dmub_reg_value_burst_set_pack(const struct dc_context *ctx, uint32_t addr,
+		uint32_t reg_val)
+{
+	struct dc_reg_helper_state *offload = &ctx->dmub_srv->reg_helper_offload;
+	struct dmub_rb_cmd_burst_write *cmd_buf = &offload->cmd_data.burst_write;
+
+	/* flush command if buffer is full */
+	if (offload->reg_seq_count == DMUB_BURST_WRITE_VALUES__MAX)
+		dmub_flush_burst_write_buffer_execute(offload, ctx);
+
+	if (offload->cmd_data.cmd_common.header.type == DMUB_CMD__REG_SEQ_BURST_WRITE &&
+			addr != cmd_buf->addr) {
+		dmub_flush_burst_write_buffer_execute(offload, ctx);
+		return false;
+	}
+
+	cmd_buf->header.type = DMUB_CMD__REG_SEQ_BURST_WRITE;
+	cmd_buf->header.sub_type = 0;
+	cmd_buf->addr = addr;
+	cmd_buf->write_values[offload->reg_seq_count] = reg_val;
+	offload->reg_seq_count++;
+
+	return true;
+}
+
+static uint32_t dmub_reg_value_pack(const struct dc_context *ctx, uint32_t addr,
+		struct dc_reg_value_masks *field_value_mask)
+{
+	struct dc_reg_helper_state *offload = &ctx->dmub_srv->reg_helper_offload;
+	struct dmub_rb_cmd_read_modify_write *cmd_buf = &offload->cmd_data.read_modify_write;
+	struct dmub_cmd_read_modify_write_sequence *seq;
+
+	/* flush command if buffer is full */
+	if (offload->cmd_data.cmd_common.header.type != DMUB_CMD__REG_SEQ_BURST_WRITE &&
+			offload->reg_seq_count == DMUB_READ_MODIFY_WRITE_SEQ__MAX)
+		dmub_flush_buffer_execute(offload, ctx);
+
+	if (offload->should_burst_write) {
+		if (dmub_reg_value_burst_set_pack(ctx, addr, field_value_mask->value))
+			return field_value_mask->value;
+		else
+			offload->should_burst_write = false;
+	}
+
+	/* pack commands */
+	cmd_buf->header.type = DMUB_CMD__REG_SEQ_READ_MODIFY_WRITE;
+	cmd_buf->header.sub_type = 0;
+	seq = &cmd_buf->seq[offload->reg_seq_count];
+
+	if (offload->reg_seq_count) {
+		if (cmd_buf->seq[offload->reg_seq_count - 1].addr == addr)
+			offload->same_addr_count++;
+		else
+			offload->same_addr_count = 0;
+	}
+
+	seq->addr = addr;
+	seq->modify_mask = field_value_mask->mask;
+	seq->modify_value = field_value_mask->value;
+	offload->reg_seq_count++;
+
+	return field_value_mask->value;
+}
+
+static void dmub_reg_wait_done_pack(const struct dc_context *ctx, uint32_t addr,
+		uint32_t mask, uint32_t shift, uint32_t condition_value, uint32_t time_out_us)
+{
+	struct dc_reg_helper_state *offload = &ctx->dmub_srv->reg_helper_offload;
+	struct dmub_rb_cmd_reg_wait *cmd_buf = &offload->cmd_data.reg_wait;
+
+	cmd_buf->header.type = DMUB_CMD__REG_REG_WAIT;
+	cmd_buf->header.sub_type = 0;
+	cmd_buf->reg_wait.addr = addr;
+	cmd_buf->reg_wait.condition_field_value = mask & (condition_value << shift);
+	cmd_buf->reg_wait.mask = mask;
+	cmd_buf->reg_wait.time_out_us = time_out_us;
+}
+
 uint32_t generic_reg_update_ex(const struct dc_context *ctx,
 		uint32_t addr, int n,
 		uint8_t shift1, uint32_t mask1, uint32_t field_value1,
@@ -93,6 +255,11 @@ uint32_t generic_reg_update_ex(const struct dc_context *ctx,
 
 	va_end(ap);
 
+	if (ctx->dmub_srv &&
+	    ctx->dmub_srv->reg_helper_offload.gather_in_progress)
+		return dmub_reg_value_pack(ctx, addr, &field_value_mask);
+		/* todo: return void so we can decouple code running in driver from register states */
+
 	/* mmio write directly */
 	reg_val = dm_read_reg(ctx, addr);
 	reg_val = (reg_val & ~field_value_mask.mask) | field_value_mask.value;
@@ -118,6 +285,13 @@ uint32_t generic_reg_set_ex(const struct dc_context *ctx,
 
 	/* mmio write directly */
 	reg_val = (reg_val & ~field_value_mask.mask) | field_value_mask.value;
+
+	if (ctx->dmub_srv &&
+	    ctx->dmub_srv->reg_helper_offload.gather_in_progress) {
+		return dmub_reg_value_burst_set_pack(ctx, addr, reg_val);
+		/* todo: return void so we can decouple code running in driver from register states */
+	}
+
 	dm_write_reg(ctx, addr, reg_val);
 	return reg_val;
 }
@@ -134,6 +308,14 @@ uint32_t dm_read_reg_func(
 		return 0;
 	}
 #endif
+
+	if (ctx->dmub_srv &&
+	    ctx->dmub_srv->reg_helper_offload.gather_in_progress &&
+	    !ctx->dmub_srv->reg_helper_offload.should_burst_write) {
+		ASSERT(false);
+		return 0;
+	}
+
 	value = cgs_read_register(ctx->cgs_device, address);
 	trace_amdgpu_dc_rreg(&ctx->perf_trace->read_count, address, value);
 
@@ -299,7 +481,19 @@ void generic_reg_wait(const struct dc_context *ctx,
 	uint32_t reg_val;
 	int i;
 
-	/* something is terribly wrong if time out is > 200ms. (5Hz) */
+	if (ctx->dmub_srv &&
+	    ctx->dmub_srv->reg_helper_offload.gather_in_progress) {
+		dmub_reg_wait_done_pack(ctx, addr, mask, shift, condition_value,
+				delay_between_poll_us * time_out_num_tries);
+		return;
+	}
+
+	/*
+	 * Something is terribly wrong if time out is > 3000ms.
+	 * 3000ms is the maximum time needed for SMU to pass values back.
+	 * This value comes from experiments.
+	 *
+	 */
 	ASSERT(delay_between_poll_us * time_out_num_tries <= 3000000);
 
 	for (i = 0; i <= time_out_num_tries; i++) {
@@ -346,12 +540,48 @@ uint32_t generic_read_indirect_reg(const struct dc_context *ctx,
 {
 	uint32_t value = 0;
 
+	// when reg read, there should not be any offload.
+	if (ctx->dmub_srv &&
+	    ctx->dmub_srv->reg_helper_offload.gather_in_progress) {
+		ASSERT(false);
+	}
+
 	dm_write_reg(ctx, addr_index, index);
 	value = dm_read_reg(ctx, addr_data);
 
 	return value;
 }
 
+uint32_t generic_indirect_reg_get(const struct dc_context *ctx,
+		uint32_t addr_index, uint32_t addr_data,
+		uint32_t index, int n,
+		uint8_t shift1, uint32_t mask1, uint32_t *field_value1,
+		...)
+{
+	uint32_t shift, mask, *field_value;
+	uint32_t value = 0;
+	int i = 1;
+
+	va_list ap;
+
+	va_start(ap, field_value1);
+
+	value = generic_read_indirect_reg(ctx, addr_index, addr_data, index);
+	*field_value1 = get_reg_field_value_ex(value, mask1, shift1);
+
+	while (i < n) {
+		shift = va_arg(ap, uint32_t);
+		mask = va_arg(ap, uint32_t);
+		field_value = va_arg(ap, uint32_t *);
+
+		*field_value = get_reg_field_value_ex(value, mask, shift);
+		i++;
+	}
+
+	va_end(ap);
+
+	return value;
+}
 
 uint32_t generic_indirect_reg_update_ex(const struct dc_context *ctx,
 		uint32_t addr_index, uint32_t addr_data,
@@ -382,3 +612,68 @@ uint32_t generic_indirect_reg_update_ex(const struct dc_context *ctx,
 
 	return reg_val;
 }
+
+void reg_sequence_start_gather(const struct dc_context *ctx)
+{
+	/* if reg sequence is supported and enabled, set flag to
+	 * indicate we want to have REG_SET, REG_UPDATE macro build
+	 * reg sequence command buffer rather than MMIO directly.
+	 */
+
+	if (ctx->dmub_srv && ctx->dc->debug.dmub_offload_enabled) {
+		struct dc_reg_helper_state *offload =
+			&ctx->dmub_srv->reg_helper_offload;
+
+		/* caller sequence mismatch.  need to debug caller.  offload will not work!!! */
+		ASSERT(!offload->gather_in_progress);
+
+		offload->gather_in_progress = true;
+	}
+}
+
+void reg_sequence_start_execute(const struct dc_context *ctx)
+{
+	struct dc_reg_helper_state *offload;
+
+	if (!ctx->dmub_srv)
+		return;
+
+	offload = &ctx->dmub_srv->reg_helper_offload;
+
+	if (offload && offload->gather_in_progress) {
+		offload->gather_in_progress = false;
+		offload->should_burst_write = false;
+		switch (offload->cmd_data.cmd_common.header.type) {
+		case DMUB_CMD__REG_SEQ_READ_MODIFY_WRITE:
+			submit_dmub_read_modify_write(offload, ctx);
+			break;
+		case DMUB_CMD__REG_REG_WAIT:
+			submit_dmub_reg_wait(offload, ctx);
+			break;
+		case DMUB_CMD__REG_SEQ_BURST_WRITE:
+			submit_dmub_burst_write(offload, ctx);
+			break;
+		default:
+			return;
+		}
+
+		dc_dmub_srv_cmd_execute(ctx->dmub_srv);
+	}
+}
+
+void reg_sequence_wait_done(const struct dc_context *ctx)
+{
+	/* callback to DM to poll for last submission done*/
+	struct dc_reg_helper_state *offload;
+
+	if (!ctx->dmub_srv)
+		return;
+
+	offload = &ctx->dmub_srv->reg_helper_offload;
+
+	if (offload &&
+	    ctx->dc->debug.dmub_offload_enabled &&
+	    !ctx->dc->debug.dmcub_emulation) {
+		dc_dmub_srv_wait_idle(ctx->dmub_srv);
+	}
+}