Merge tag 'drm-for-v4.12' of git://people.freedesktop.org/~airlied/linux

Pull drm u pdates from Dave Airlie:
 "This is the main drm pull request for v4.12. Apart from two fixes
  pulls, everything should have been in drm-next for at least 2 weeks.

  The biggest thing in here is AMD released the public headers for their
  upcoming VEGA GPUs. These as always are quite a sizeable chunk of
  header files. They've also added initial non-display support for those
  GPUs, though they aren't available in production yet.

  Otherwise it's pretty much normal.

  New bridge drivers:
   - megachips-stdpxxxx-ge-b850v3-fw LVDS->DP++
   - generic LVDS bridge support.

  Core:
   - Displayport link train failure reporting to userspace
   - debugfs interface cleaned up
   - subsystem TODO in kerneldoc now
   - Extended fbdev support (flipping and vblank wait)
   - drm_platform removed
   - EDP CRC support in helper
   - HF-VSDB SCDC support in EDID parser
   - Lots of code cleanups and header extraction
   - Thunderbolt external GPU awareness
   - Atomic helper improvements
   - Documentation improvements

  panel:
   - Sitronix and Samsung new panel support

  amdgpu:
   - Preliminary vega10 support
   - Multi-level page table support
   - GPU sensor support for userspace
   - PRT support for sparse buffers
   - SR-IOV improvements
   - Non-contig VRAM CPU mapping

  i915:
   - Atomic modesetting enabled by default on Gen5+
   - LSPCON improvements
   - Atomic state handling for cdclk
   - GPU reset improvements
   - In-kernel unit tests
   - Geminilake improvements and color manager support
   - Designware i2c fixes
   - vblank evasion improvements
   - Hotplug safe connector iterators
   - GVT scheduler QoS support
   - GVT Kabylake support

  nouveau:
   - Acceleration support for Pascal (GP10x).
   - Rearchitecture of code handling proprietary signed firmware
   - Fix GTX 970 with odd MMU configuration
   - GP10B support
   - GP107 acceleration support

  vmwgfx:
   - Atomic modesetting support for vmwgfx

  omapdrm:
   - Support for render nodes
   - Refactor omapdss code
   - Fix some probe ordering issues
   - Fix too dark RGB565 rendering

  sunxi:
   - prelim rework for multiple pipes.

  mali-dp:
   - Color management support
   - Plane scaling
   - Power management improvements

  imx-drm:
   - Prefetch Resolve Engine/Gasket on i.MX6QP
   - Deferred plane disabling
   - Separate alpha support

  mediatek:
   - Mediatek SoC MT2701 support

  rcar-du:
   - Gen3 HDMI support

  msm:
   - 4k support for newer chips
   - OPP bindings for gpu
   - prep work for per-process pagetables

  vc4:
   - HDMI audio support
   - fixes

  qxl:
   - minor fixes.

  dw-hdmi:
   - PHY improvements
   - CSC fixes
   - Amlogic GX SoC support"

* tag 'drm-for-v4.12' of git://people.freedesktop.org/~airlied/linux: (1778 commits)
  drm/nouveau/fb/gf100-: Fix 32 bit wraparound in new ram detection
  drm/nouveau/secboot/gm20b: fix the error return code in gm20b_secboot_tegra_read_wpr()
  drm/nouveau/kms: Increase max retries in scanout position queries.
  drm/nouveau/bios/bitP: check that table is long enough for optional pointers
  drm/nouveau/fifo/nv40: no ctxsw for pre-nv44 mpeg engine
  drm: mali-dp: use div_u64 for expensive 64-bit divisions
  drm/i915: Confirm the request is still active before adding it to the await
  drm/i915: Avoid busy-spinning on VLV_GLTC_PW_STATUS mmio
  drm/i915/selftests: Allocate inode/file dynamically
  drm/i915: Fix system hang with EI UP masked on Haswell
  drm/i915: checking for NULL instead of IS_ERR() in mock selftests
  drm/i915: Perform link quality check unconditionally during long pulse
  drm/i915: Fix use after free in lpe_audio_platdev_destroy()
  drm/i915: Use the right mapping_gfp_mask for final shmem allocation
  drm/i915: Make legacy cursor updates more unsynced
  drm/i915: Apply a cond_resched() to the saturated signaler
  drm/i915: Park the signaler before sleeping
  drm: mali-dp: Check the mclk rate and allow up/down scaling
  drm: mali-dp: Enable image enhancement when scaling
  drm: mali-dp: Add plane upscaling support
  ...

1 files changed, 104 insertions, 45 deletions

diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r361.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r361.c
index f0aff1d98474..14b36ef93628 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r361.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r361.c
@@ -20,58 +20,23 @@
  * DEALINGS IN THE SOFTWARE.
  */
 
-#include "acr_r352.h"
+#include "acr_r361.h"
 
 #include <engine/falcon.h>
-
-/**
- * struct acr_r361_flcn_bl_desc - DMEM bootloader descriptor
- * @signature:		16B signature for secure code. 0s if no secure code
- * @ctx_dma:		DMA context to be used by BL while loading code/data
- * @code_dma_base:	256B-aligned Physical FB Address where code is located
- *			(falcon's $xcbase register)
- * @non_sec_code_off:	offset from code_dma_base where the non-secure code is
- *                      located. The offset must be multiple of 256 to help perf
- * @non_sec_code_size:	the size of the nonSecure code part.
- * @sec_code_off:	offset from code_dma_base where the secure code is
- *                      located. The offset must be multiple of 256 to help perf
- * @sec_code_size:	offset from code_dma_base where the secure code is
- *                      located. The offset must be multiple of 256 to help perf
- * @code_entry_point:	code entry point which will be invoked by BL after
- *                      code is loaded.
- * @data_dma_base:	256B aligned Physical FB Address where data is located.
- *			(falcon's $xdbase register)
- * @data_size:		size of data block. Should be multiple of 256B
- *
- * Structure used by the bootloader to load the rest of the code. This has
- * to be filled by host and copied into DMEM at offset provided in the
- * hsflcn_bl_desc.bl_desc_dmem_load_off.
- */
-struct acr_r361_flcn_bl_desc {
-	u32 reserved[4];
-	u32 signature[4];
-	u32 ctx_dma;
-	struct flcn_u64 code_dma_base;
-	u32 non_sec_code_off;
-	u32 non_sec_code_size;
-	u32 sec_code_off;
-	u32 sec_code_size;
-	u32 code_entry_point;
-	struct flcn_u64 data_dma_base;
-	u32 data_size;
-};
+#include <core/msgqueue.h>
+#include <subdev/pmu.h>
+#include <engine/sec2.h>
 
 static void
 acr_r361_generate_flcn_bl_desc(const struct nvkm_acr *acr,
-			       const struct ls_ucode_img *_img, u64 wpr_addr,
+			       const struct ls_ucode_img *img, u64 wpr_addr,
 			       void *_desc)
 {
-	struct ls_ucode_img_r352 *img = ls_ucode_img_r352(_img);
 	struct acr_r361_flcn_bl_desc *desc = _desc;
-	const struct ls_ucode_img_desc *pdesc = &img->base.ucode_desc;
+	const struct ls_ucode_img_desc *pdesc = &img->ucode_desc;
 	u64 base, addr_code, addr_data;
 
-	base = wpr_addr + img->lsb_header.ucode_off + pdesc->app_start_offset;
+	base = wpr_addr + img->ucode_off + pdesc->app_start_offset;
 	addr_code = base + pdesc->app_resident_code_offset;
 	addr_data = base + pdesc->app_resident_data_offset;
 
@@ -84,7 +49,7 @@ acr_r361_generate_flcn_bl_desc(const struct nvkm_acr *acr,
 	desc->data_size = pdesc->app_resident_data_size;
 }
 
-static void
+void
 acr_r361_generate_hs_bl_desc(const struct hsf_load_header *hdr, void *_bl_desc,
 			    u64 offset)
 {
@@ -94,8 +59,8 @@ acr_r361_generate_hs_bl_desc(const struct hsf_load_header *hdr, void *_bl_desc,
 	bl_desc->code_dma_base = u64_to_flcn64(offset);
 	bl_desc->non_sec_code_off = hdr->non_sec_code_off;
 	bl_desc->non_sec_code_size = hdr->non_sec_code_size;
-	bl_desc->sec_code_off = hdr->app[0].sec_code_off;
-	bl_desc->sec_code_size = hdr->app[0].sec_code_size;
+	bl_desc->sec_code_off = hsf_load_header_app_off(hdr, 0);
+	bl_desc->sec_code_size = hsf_load_header_app_size(hdr, 0);
 	bl_desc->code_entry_point = 0;
 	bl_desc->data_dma_base = u64_to_flcn64(offset + hdr->data_dma_base);
 	bl_desc->data_size = hdr->data_size;
@@ -117,8 +82,100 @@ acr_r361_ls_gpccs_func = {
 	.lhdr_flags = LSF_FLAG_FORCE_PRIV_LOAD,
 };
 
+struct acr_r361_pmu_bl_desc {
+	u32 reserved;
+	u32 dma_idx;
+	struct flcn_u64 code_dma_base;
+	u32 total_code_size;
+	u32 code_size_to_load;
+	u32 code_entry_point;
+	struct flcn_u64 data_dma_base;
+	u32 data_size;
+	struct flcn_u64 overlay_dma_base;
+	u32 argc;
+	u32 argv;
+};
+
+static void
+acr_r361_generate_pmu_bl_desc(const struct nvkm_acr *acr,
+			      const struct ls_ucode_img *img, u64 wpr_addr,
+			      void *_desc)
+{
+	const struct ls_ucode_img_desc *pdesc = &img->ucode_desc;
+	const struct nvkm_pmu *pmu = acr->subdev->device->pmu;
+	struct acr_r361_pmu_bl_desc *desc = _desc;
+	u64 base, addr_code, addr_data;
+	u32 addr_args;
+
+	base = wpr_addr + img->ucode_off + pdesc->app_start_offset;
+	addr_code = base + pdesc->app_resident_code_offset;
+	addr_data = base + pdesc->app_resident_data_offset;
+	addr_args = pmu->falcon->data.limit;
+	addr_args -= NVKM_MSGQUEUE_CMDLINE_SIZE;
+
+	desc->dma_idx = FALCON_DMAIDX_UCODE;
+	desc->code_dma_base = u64_to_flcn64(addr_code);
+	desc->total_code_size = pdesc->app_size;
+	desc->code_size_to_load = pdesc->app_resident_code_size;
+	desc->code_entry_point = pdesc->app_imem_entry;
+	desc->data_dma_base = u64_to_flcn64(addr_data);
+	desc->data_size = pdesc->app_resident_data_size;
+	desc->overlay_dma_base = u64_to_flcn64(addr_code);
+	desc->argc = 1;
+	desc->argv = addr_args;
+}
+
+const struct acr_r352_ls_func
+acr_r361_ls_pmu_func = {
+	.load = acr_ls_ucode_load_pmu,
+	.generate_bl_desc = acr_r361_generate_pmu_bl_desc,
+	.bl_desc_size = sizeof(struct acr_r361_pmu_bl_desc),
+	.post_run = acr_ls_pmu_post_run,
+};
+
+static void
+acr_r361_generate_sec2_bl_desc(const struct nvkm_acr *acr,
+			       const struct ls_ucode_img *img, u64 wpr_addr,
+			       void *_desc)
+{
+	const struct ls_ucode_img_desc *pdesc = &img->ucode_desc;
+	const struct nvkm_sec2 *sec = acr->subdev->device->sec2;
+	struct acr_r361_pmu_bl_desc *desc = _desc;
+	u64 base, addr_code, addr_data;
+	u32 addr_args;
+
+	base = wpr_addr + img->ucode_off + pdesc->app_start_offset;
+	/* For some reason we should not add app_resident_code_offset here */
+	addr_code = base;
+	addr_data = base + pdesc->app_resident_data_offset;
+	addr_args = sec->falcon->data.limit;
+	addr_args -= NVKM_MSGQUEUE_CMDLINE_SIZE;
+
+	desc->dma_idx = FALCON_SEC2_DMAIDX_UCODE;
+	desc->code_dma_base = u64_to_flcn64(addr_code);
+	desc->total_code_size = pdesc->app_size;
+	desc->code_size_to_load = pdesc->app_resident_code_size;
+	desc->code_entry_point = pdesc->app_imem_entry;
+	desc->data_dma_base = u64_to_flcn64(addr_data);
+	desc->data_size = pdesc->app_resident_data_size;
+	desc->overlay_dma_base = u64_to_flcn64(addr_code);
+	desc->argc = 1;
+	/* args are stored at the beginning of EMEM */
+	desc->argv = 0x01000000;
+}
+
+const struct acr_r352_ls_func
+acr_r361_ls_sec2_func = {
+	.load = acr_ls_ucode_load_sec2,
+	.generate_bl_desc = acr_r361_generate_sec2_bl_desc,
+	.bl_desc_size = sizeof(struct acr_r361_pmu_bl_desc),
+	.post_run = acr_ls_sec2_post_run,
+};
+
+
 const struct acr_r352_func
 acr_r361_func = {
+	.fixup_hs_desc = acr_r352_fixup_hs_desc,
 	.generate_hs_bl_desc = acr_r361_generate_hs_bl_desc,
 	.hs_bl_desc_size = sizeof(struct acr_r361_flcn_bl_desc),
 	.ls_ucode_img_load = acr_r352_ls_ucode_img_load,
@@ -127,6 +184,8 @@ acr_r361_func = {
 	.ls_func = {
 		[NVKM_SECBOOT_FALCON_FECS] = &acr_r361_ls_fecs_func,
 		[NVKM_SECBOOT_FALCON_GPCCS] = &acr_r361_ls_gpccs_func,
+		[NVKM_SECBOOT_FALCON_PMU] = &acr_r361_ls_pmu_func,
+		[NVKM_SECBOOT_FALCON_SEC2] = &acr_r361_ls_sec2_func,
 	},
 };