Batch submission via GuC
Subsystems (3)
v2 cover Batch submission via GuC
This patch series enables command submission via the GuC. In this mode, instead of the host CPU driving the execlist port directly, it hands over work items to the GuC, using a doorbell mechanism to tell the GuC that new items have been added to its work queue. The GuC then dispatches contexts to the various GPU engines, and manages the resulting context- switch interrupts. Completion of a batch is however still signalled to the CPU; the GuC is not involved in handling user interrupts.
There are four subsequences within the patch series:
drm/i915: Add i915_gem_object_create_from_data() drm/i915: Embedded microcontroller (uC) firmware loading support
These first two patches provide a generic framework for fetching the firmware that may be required by any embedded microcontroller from a file, using an asynchronous thread so that driver initialisation can continue while the firmware is being fetched. The framework provides synchronisation with the completion of the fetcher thread, so the load of the code into the device occurs synchronously at a subsequent time of the caller's choice. It is hoped that this framework is sufficiently general that it can be used for all curent and future microcontrollers.
drm/i915: Add GuC-related module parameters drm/i915: Add GuC-related header files drm/i915: GuC-specific firmware loader drm/i915: Debugfs interface to read GuC load status
These four patches complete the GuC loader. At this point in the sequence we can load and activate the GuC firmware, but not submit any batches through it. (This is nonetheless a potentially useful state, as the GuC could do other useful work even when not handling batch submissions).
drm/i915: Split late for_each_ring loop from i915_gem_init_hw() drm/i915: Defer default hardware context initialisation until first open
These two patches defer the later phases of hardware initialisation until the first time the device is opened. This allows firmware loading to be deferred until user processes are running, allowing it to work even when the firmware image is not available during driver load. In addition, this may speed up the appearance of the software-rendered bootsplash as it allows driver loading to return earlier, leaving the second phase of GPU initialisation (anything involving sending batches to the GPU engines) to be completed later.
drm/i915: Expose two LRC functions for GuC submission mode drm/i915: GuC submission setup, phase 1 drm/i915: Enable GuC firmware log
drm/i915: Implementation of GuC client
drm/i915: Interrupt routing for GuC submission drm/i915: Integrate GuC-based command submission drm/i915: Debugfs interface for GuC submission statistics Documentation/drm: kerneldoc for GuC
drm/i915: Enable GuC submission, where supported
In the final section, we implement the GuC submission mechanism, link it into the (execlist-based) submission path, and finally enable it (on supported platforms). On platforms where there is no GuC, or if the GuC firmware cannot be found or is invalid, batch submission will revert to using the execlist mechanism directly.
The GuC firmware itself is not included in this patchset; it is or will be available for download from https://01.org/linuxgraphics/downloads/
This driver works with and requires GuC firmware revision 3.x. It will not work with any firmware version 1.x, as the GuC protocol in those revisions was incompatible and is no longer supported.
Prerequisites: GuC submission will expose existing inadequacies in some of the existing codepaths unless certain other patches are applied. In particular we will require some version of Michel Thierry's patch
drm/i915/lrc: Update PDPx registers with LRI commands
(because the GuC support light-restore, which execlist mode doesn't), The previous prerequisite patch
drm/i915: Allocate OLR more safely (workaround until OLR goes away)
is no longer required as the OLR has now gone away :)
Alex Dai (7):
drm/i915: Add GuC-related module parameters drm/i915: GuC-specific firmware loader drm/i915: Debugfs interface to read GuC load status drm/i915: GuC submission setup, phase 1 drm/i915: Enable GuC firmware log
drm/i915: Integrate GuC-based command submission Documentation/drm: kerneldoc for GuC
Dave Gordon (10):
drm/i915: Add i915_gem_object_create_from_data()
drm/i915: Embedded microcontroller (uC) firmware loading support drm/i915: Add GuC-related header files
drm/i915: Split late for_each_ring loop from i915_gem_init_hw() drm/i915: Defer default hardware context initialisation until first open drm/i915: Expose two LRC functions for GuC submission mode drm/i915: Implementation of GuC client
drm/i915: Interrupt routing for GuC submission
drm/i915: Debugfs interface for GuC submission statistics drm/i915: Enable GuC submission, where supported
Ben Widawsky (0):
Vinit Azad (0):
Michael H. Nguyen (0):
created the original versions on which some of these patches are based.
Documentation/DocBook/drm.tmpl | 19 + drivers/gpu/drm/i915/Makefile | 7 + drivers/gpu/drm/i915/i915_debugfs.c | 116 +++- drivers/gpu/drm/i915/i915_dma.c | 4 + drivers/gpu/drm/i915/i915_drv.h | 18 + drivers/gpu/drm/i915/i915_gem.c | 131 +++-- drivers/gpu/drm/i915/i915_gem_context.c | 52 +- drivers/gpu/drm/i915/i915_guc_reg.h | 102 ++++ drivers/gpu/drm/i915/i915_guc_submission.c | 861 ++++++++++++++++++++++++++++ drivers/gpu/drm/i915/i915_irq.c | 48 ++ drivers/gpu/drm/i915/i915_params.c | 9 + drivers/gpu/drm/i915/i915_reg.h | 15 +- drivers/gpu/drm/i915/intel_guc.h | 101 ++++ drivers/gpu/drm/i915/intel_guc_fwif.h | 236 ++++++++ drivers/gpu/drm/i915/intel_guc_loader.c | 521 +++++++++++++++++ drivers/gpu/drm/i915/intel_lrc.c | 75 ++- drivers/gpu/drm/i915/intel_lrc.h | 11 + drivers/gpu/drm/i915/intel_uc_loader.c | 332 +++++++++++ drivers/gpu/drm/i915/intel_uc_loader.h | 86 +++ 19 files changed, 2673 insertions(+), 71 deletions(-) create mode 100644 drivers/gpu/drm/i915/i915_guc_reg.h create mode 100644 drivers/gpu/drm/i915/i915_guc_submission.c create mode 100644 drivers/gpu/drm/i915/intel_guc.h create mode 100644 drivers/gpu/drm/i915/intel_guc_fwif.h create mode 100644 drivers/gpu/drm/i915/intel_guc_loader.c create mode 100644 drivers/gpu/drm/i915/intel_uc_loader.c create mode 100644 drivers/gpu/drm/i915/intel_uc_loader.h
Signature · 6 lines
1.7.9.5 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH v2 1/17 drm/i915: Add i915_gem_object_create_from_data()
i915_gem_object_create_from_data() is a generic function to save data from a plain linear buffer in a new pageable gem object that can later be accessed by the CPU and/or GPU.
We will need this for the microcontroller firmware loading support code.
Derived from i915_gem_object_write(), originally by Alex Dai
v2:
Change of function: now allocates & fills a new object, rather than
writing to an existing object
New name courtesy of Chris Wilson
Explicit domain-setting and other improvements per review comments
by Chris Wilson & Daniel Vetter
Issue: VIZ-4884
--- drivers/gpu/drm/i915/i915_drv.h | 2 ++ drivers/gpu/drm/i915/i915_gem.c | 39 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 41 insertions(+)
drivers/gpu/drm/i915/i915_drv.h +2 -0
@@ -2729,6 +2729,8 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj, const struct drm_i915_gem_object_ops *ops);struct drm_i915_gem_object *i915_gem_alloc_object (struct drm_device *dev,size_t size); +struct drm_i915_gem_object *i915_gem_object_create_from_data ( +struct drm_device *dev,const void *data,size_t size);void i915_init_vm (struct drm_i915_private *dev_priv,struct i915_address_space *vm);void i915_gem_free_object (struct drm_gem_object *obj);
drivers/gpu/drm/i915/i915_gem.c +39 -0
@@ -5470,3 +5470,42 @@ bool i915_gem_obj_is_pinned(struct drm_i915_gem_object *obj)return false; } +/* Allocate a new GEM object and fill it with the supplied data */ +struct drm_i915_gem_object * +i915_gem_object_create_from_data (struct drm_device *dev, +const void *data,size_t size) +{ +struct drm_i915_gem_object *obj; +struct sg_table *sg; +size_t bytes; +int ret; + + obj =i915_gem_alloc_object (dev,round_up (size,PAGE_SIZE )); +if (IS_ERR_OR_NULL (obj)) +return obj; + + ret =i915_gem_object_set_to_cpu_domain (obj, true); +if (ret) + goto fail; + + ret =i915_gem_object_get_pages (obj); +if (ret) + goto fail; + +i915_gem_object_pin_pages (obj); + sg = obj->pages; + bytes =sg_copy_from_buffer (sg->sgl, sg->nents, (void *)data, size); +i915_gem_object_unpin_pages (obj); + +if (WARN_ON (bytes != size)) { +DRM_ERROR ("Incomplete copy, wrote %zu of %zu" , bytes, size); + ret = -EFAULT ; + goto fail; + } + +return obj; + +fail: +drm_gem_object_unreference (&obj->base); +return ERR_PTR (ret); +}
Signature · 6 lines
1.7.9.5 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH v2 2/17 drm/i915: Embedded microcontroller (uC) firmware loading support
In reply to Dave GordonCurrent devices may contain one or more programmable microcontrollers that need to have a firmware image (aka "binary blob") loaded from an external medium and transferred to the device's memory.
This file provides generic support functions for doing this; they can then be used by each uC-specific loader, thus reducing code duplication and testing effort.
v2:
Local functions should pass dev_priv rather than dev [Chris Wilson] Various other improvements per Chris Wilson's review comments
--- drivers/gpu/drm/i915/Makefile | 3 + drivers/gpu/drm/i915/intel_uc_loader.c | 332 ++++++++++++++++++++++++++++++++ drivers/gpu/drm/i915/intel_uc_loader.h | 86 +++++++++ 3 files changed, 421 insertions(+) create mode 100644 drivers/gpu/drm/i915/intel_uc_loader.c create mode 100644 drivers/gpu/drm/i915/intel_uc_loader.h
drivers/gpu/drm/i915/Makefile +3 -0
@@ -39,6 +39,9 @@ i915-y += i915_cmd_parser.o \ intel_ringbuffer.o \ intel_uncore.o +# generic ancilliary microcontroller support +i915-y += intel_uc_loader.o + # autogenerated null render state i915-y += intel_renderstate_gen6.o \ intel_renderstate_gen7.o \
drivers/gpu/drm/i915/intel_uc_loader.c new file +332 -0
332 lines not on this page · raw message
drivers/gpu/drm/i915/intel_uc_loader.h new file +86 -0
86 lines not on this page · raw message
Signature · 6 lines
1.7.9.5 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH v2 3/17 drm/i915: Add GuC-related module parameters
In reply to Dave GordonFrom: Alex Dai <[email protected]>
Two new module parameters: "enable_guc_submission" which will turn on submission of batchbuffers via the GuC (when implemented), and "guc_log_level" which controls the level of debugging logged by the GuC and captured by the host.
--- drivers/gpu/drm/i915/i915_drv.h | 2 ++ drivers/gpu/drm/i915/i915_params.c | 9 +++++++++ 2 files changed, 11 insertions(+)
drivers/gpu/drm/i915/i915_drv.h +2 -0
@@ -2580,6 +2580,8 @@ struct i915_params {bool reset;bool disable_display;bool disable_vtd_wa; +bool enable_guc_submission; +int guc_log_level;int use_mmio_flip;int mmio_debug;bool verbose_state_checks;
drivers/gpu/drm/i915/i915_params.c +9 -0
@@ -53,6 +53,8 @@ struct i915_params i915 __read_mostly = { .verbose_state_checks = 1, .nuclear_pageflip = 0, .edp_vswing = 0, + .enable_guc_submission = false, + .guc_log_level = -1, };module_param_named (modeset, i915.modeset, int,0400 );
@@ -186,3 +188,10 @@ MODULE_PARM_DESC(edp_vswing,"Ignore/Override vswing pre-emph table selection from VBT " "(0=use value from vbt [default], 1=low power swing(200mV)," "2=default swing(400mV))"); + +module_param_named (enable_guc_submission, i915.enable_guc_submission, bool,0400 ); +MODULE_PARM_DESC (enable_guc_submission,"Enable GuC submission (default:false)" ); + +module_param_named (guc_log_level, i915.guc_log_level, int,0400 ); +MODULE_PARM_DESC (guc_log_level, +"GuC firmware logging level (-1:disabled (default), 0-3:enabled)" );
Signature · 6 lines
1.7.9.5 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH v2 4/17 drm/i915: Add GuC-related header files
In reply to Dave Gordonintel_guc_fwif.h contains the subset of the GuC interface that we will need for submission of commands through the GuC. These MUST be kept in sync with the definitions used by the GuC firmware, and updates to this file will (or should) be autogenerated from the source files used to build the firmware. Editing this file is therefore not recommended.
i915_guc_reg.h contains definitions of GuC-related hardware:
registers, bitmasks, etc. These should match the BSpec.
v2:
Files renamed & resliced per review comments by Chris Wilson
Issue: VIZ-4884
--- drivers/gpu/drm/i915/i915_guc_reg.h | 102 ++++++++++++++ drivers/gpu/drm/i915/intel_guc_fwif.h | 236 +++++++++++++++++++++++++++++++++ 2 files changed, 338 insertions(+) create mode 100644 drivers/gpu/drm/i915/i915_guc_reg.h create mode 100644 drivers/gpu/drm/i915/intel_guc_fwif.h
drivers/gpu/drm/i915/i915_guc_reg.h new file +102 -0
@@ -0,0 +1,102 @@ +/* +* Copyright © 2014 Intel Corporation +* +* Permission is hereby granted, free of charge, to any person obtaining a +* copy of this software and associated documentation files (the "Software"), +* to deal in the Software without restriction, including without limitation +* the rights to use, copy, modify, merge, publish, distribute, sublicense, +* and/or sell copies of the Software, and to permit persons to whom the +* Software is furnished to do so, subject to the following conditions: +* +* The above copyright notice and this permission notice (including the next +* paragraph) shall be included in all copies or substantial portions of the +* Software. +* +* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL +* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS +* IN THE SOFTWARE. +* +*/ +#ifndef _I915_GUC_REG_H_ +#define _I915_GUC_REG_H_ + +/* Definitions of GuC H/W registers, bits, etc */ + +#define GUC_STATUS 0xc000 +#define GS_BOOTROM_SHIFT 1 +#define GS_BOOTROM_MASK (0x7F << GS_BOOTROM_SHIFT) +#define GS_BOOTROM_RSA_FAILED (0x50 << GS_BOOTROM_SHIFT) +#define GS_UKERNEL_SHIFT 8 +#define GS_UKERNEL_MASK (0xFF << GS_UKERNEL_SHIFT) +#define GS_UKERNEL_LAPIC_DONE (0x30 << GS_UKERNEL_SHIFT) +#define GS_UKERNEL_DPC_ERROR (0x60 << GS_UKERNEL_SHIFT) +#define GS_UKERNEL_READY (0xF0 << GS_UKERNEL_SHIFT) +#define GS_MIA_SHIFT 16 +#define GS_MIA_MASK (0x07 << GS_MIA_SHIFT) + +#define GUC_WOPCM_SIZE 0xc050 +#define GUC_WOPCM_SIZE_VALUE (0x80 << 12)/* 512KB */ +#define GUC_WOPCM_OFFSET 0x80000/* 512KB */ + +#define SOFT_SCRATCH (n) (0xc180 + ((n) * 4)) + +#define UOS_RSA_SCRATCH_0 0xc200 +#define DMA_ADDR_0_LOW 0xc300 +#define DMA_ADDR_0_HIGH 0xc304 +#define DMA_ADDR_1_LOW 0xc308 +#define DMA_ADDR_1_HIGH 0xc30c +#define DMA_ADDRESS_SPACE_WOPCM (7 << 16) +#define DMA_ADDRESS_SPACE_GTT (8 << 16) +#define DMA_COPY_SIZE 0xc310 +#define DMA_CTRL 0xc314 +#define UOS_MOVE (1<<4) +#define START_DMA (1<<0) +#define DMA_GUC_WOPCM_OFFSET 0xc340 + +#define GEN8_GT_PM_CONFIG 0x138140 +#define GEN9_GT_PM_CONFIG 0x13816c +#define GEN8_GT_DOORBELL_ENABLE (1<<0) + +#define GEN8_GTCR 0x4274 +#define GEN8_GTCR_INVALIDATE (1<<0) + +#define GUC_ARAT_C6DIS 0xA178 + +#define GUC_SHIM_CONTROL 0xc064 +#define GUC_DISABLE_SRAM_INIT_TO_ZEROES (1<<0) +#define GUC_ENABLE_READ_CACHE_LOGIC (1<<1) +#define GUC_ENABLE_MIA_CACHING (1<<2) +#define GUC_GEN10_MSGCH_ENABLE (1<<4) +#define GUC_ENABLE_READ_CACHE_FOR_SRAM_DATA (1<<9) +#define GUC_ENABLE_READ_CACHE_FOR_WOPCM_DATA (1<<10) +#define GUC_ENABLE_MIA_CLOCK_GATING (1<<15) +#define GUC_GEN10_SHIM_WC_ENABLE (1<<21) + +#define GUC_SHIM_CONTROL_VALUE (GUC_DISABLE_SRAM_INIT_TO_ZEROES | \ + GUC_ENABLE_READ_CACHE_LOGIC | \ + GUC_ENABLE_MIA_CACHING | \ + GUC_ENABLE_READ_CACHE_FOR_SRAM_DATA | \ + GUC_ENABLE_READ_CACHE_FOR_WOPCM_DATA) + +#define HOST2GUC_INTERRUPT 0xc4c8 +#define HOST2GUC_TRIGGER (1<<0) + +#define DRBMISC1 0x1984 +#define DOORBELL_ENABLE (1<<0) + +#define GEN8_DRBREGL (x) (0x1000 + (x) * 8) +#define GEN8_DRB_VALID (1<<0) +#define GEN8_DRBREGU (x) (GEN8_DRBREGL(x) + 4) + +#define DE_GUCRMR 0x44054 + +#define GUC_BCS_RCS_IER 0xC550 +#define GUC_VCS2_VCS1_IER 0xC554 +#define GUC_WD_VECS_IER 0xC558 +#define GUC_PM_P24C_IER 0xC55C + +#endif
drivers/gpu/drm/i915/intel_guc_fwif.h new file +236 -0
236 lines not on this page · raw message
Signature · 6 lines
1.7.9.5 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Re: [PATCH 04/17 v2] drm/i915: Add GuC-related header files
Quoted 6 lines · Dave Gordon
intel_guc_fwif.hcontains the subset of the GuC interface that we will need for submission of commands through the GuC. These MUST be kept in sync with the definitions used by the GuC firmware, and updates to this file will (or should) be autogenerated from the source files used to build the firmware. Editing this file is therefore not recommended.
[TOR:] That recommendation should be repeated in the file itself.
Quoted 11 lines
i915_guc_reg.hcontains definitions of GuC-related hardware:
registers, bitmasks, etc. These should match the BSpec.v2:
Files renamed & resliced per review comments by Chris WilsonIssue: VIZ-4884
Signed-off-by Alex Dai <[email protected]>Signed-off-by Dave Gordon <[email protected]>---
_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH v2 5/17 drm/i915: GuC-specific firmware loader
In reply to Dave GordonFrom: Alex Dai <[email protected]>
This uses the unified firmware loader to fetch the firmware image, then loads it into the GuC's memory via a dedicated DMA engine.
This patch is derived from GuC loading work originally done by Vinit Azad and Ben Widawsky. It has been reconstructed to accord with the unified firmware loading mechanism by Dave Gordon as well as new firmware layout etc.
v2:
Various improvements per review comments by Chris Wilson
Issue: VIZ-4884
--- drivers/gpu/drm/i915/Makefile | 3 + drivers/gpu/drm/i915/i915_dma.c | 4 + drivers/gpu/drm/i915/i915_drv.h | 11 + drivers/gpu/drm/i915/i915_gem.c | 3 + drivers/gpu/drm/i915/i915_reg.h | 4 +- drivers/gpu/drm/i915/intel_guc.h | 49 ++++ drivers/gpu/drm/i915/intel_guc_loader.c | 440 +++++++++++++++++++++++++++++++ 7 files changed, 513 insertions(+), 1 deletion(-) create mode 100644 drivers/gpu/drm/i915/intel_guc.h create mode 100644 drivers/gpu/drm/i915/intel_guc_loader.c
drivers/gpu/drm/i915/Makefile +3 -0
@@ -42,6 +42,9 @@ i915-y += i915_cmd_parser.o \ # generic ancilliary microcontroller support i915-y += intel_uc_loader.o +# general-purpose microcontroller (GuC) support +i915-y += intel_guc_loader.o + # autogenerated null render state i915-y += intel_renderstate_gen6.o \ intel_renderstate_gen7.o \
drivers/gpu/drm/i915/i915_dma.c +4 -0
@@ -469,6 +469,7 @@ static int i915_load_modeset_init(struct drm_device *dev) cleanup_gem:mutex_lock (&dev->struct_mutex); +intel_guc_ucode_fini (dev);i915_gem_cleanup_ringbuffer (dev);i915_gem_context_fini (dev);mutex_unlock (&dev->struct_mutex);
@@ -866,6 +867,8 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)intel_uncore_init (dev); +intel_guc_ucode_init (dev); +/* Load CSR Firmware for SKL */ intel_csr_ucode_init (dev);
@@ -1117,6 +1120,7 @@ int i915_driver_unload(struct drm_device *dev)flush_workqueue (dev_priv->wq);mutex_lock (&dev->struct_mutex); +intel_guc_ucode_fini (dev);i915_gem_cleanup_ringbuffer (dev);i915_gem_context_fini (dev);mutex_unlock (&dev->struct_mutex);
drivers/gpu/drm/i915/i915_drv.h +11 -0
@@ -50,6 +50,7 @@#include <linux/intel-iommu.h> #include <linux/kref.h> #include <linux/pm_qos.h> +#include "intel_guc.h" /* General customization: */
@@ -1676,6 +1677,8 @@ struct drm_i915_private {struct i915_virtual_gpu vgpu; +struct intel_guc guc; +struct intel_csr csr;/* Display CSR-related protection */
@@ -1920,6 +1923,11 @@ static inline struct drm_i915_private *dev_to_i915(struct device *dev)return to_i915 (dev_get_drvdata (dev)); } +static inline struct drm_i915_private *guc_to_i915 (struct intel_guc *guc) +{ + return container_of(guc, struct drm_i915_private, guc); +} +/* Iterate over initialised rings */ #define for_each_ring (ring__, dev_priv__, i__) \ for ((i__) = 0; (i__) < I915_NUM_RINGS; (i__)++) \
@@ -2520,6 +2528,9 @@ struct drm_i915_cmd_table {#define HAS_CSR (dev) (IS_SKYLAKE(dev)) +#define HAS_GUC_UCODE (dev) (IS_GEN9(dev)) +#define HAS_GUC_SCHED (dev) (IS_GEN9(dev)) +#define INTEL_PCH_DEVICE_ID_MASK 0xff00#define INTEL_PCH_IBX_DEVICE_ID_TYPE 0x3b00#define INTEL_PCH_CPT_DEVICE_ID_TYPE 0x1c00
drivers/gpu/drm/i915/i915_gem.c +3 -0
@@ -5073,6 +5073,9 @@ i915_gem_init_hw(struct drm_device *dev) goto out; } +/* We can't enable contexts until all firmware is loaded */ + ret =intel_guc_ucode_load (dev, true); +/* Now it is safe to go back round and do everything else: */ for_each_ring (ring, dev_priv, i) {struct drm_i915_gem_request *req;
drivers/gpu/drm/i915/i915_reg.h +3 -1
@@ -6795,7 +6795,9 @@ enum skl_disp_power_wells {#define GEN9_PGCTL_SSB_EU311_ACK (1 << 14)#define GEN7_MISCCPCTL (0x9424) -#define GEN7_DOP_CLOCK_GATE_ENABLE (1<<0) +#define GEN7_DOP_CLOCK_GATE_ENABLE (1<<0) +#define GEN8_DOP_CLOCK_GATE_CFCLK_ENABLE (1<<2) +#define GEN8_DOP_CLOCK_GATE_GUC_ENABLE (1<<4)/* IVYBRIDGE DPF */ #define GEN7_L3CDERRST1 0xB008/* L3CD Error Status 1 */
drivers/gpu/drm/i915/intel_guc.h new file +49 -0
49 lines not on this page · raw message
drivers/gpu/drm/i915/intel_guc_loader.c new file +440 -0
440 lines not on this page · raw message
Signature · 6 lines
1.7.9.5 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH v2 6/17 drm/i915: Debugfs interface to read GuC load status
In reply to Dave GordonFrom: Alex Dai <[email protected]>
The new node provides access to the status of the common uC loader code and the GuC-specific loader; also the scratch registers used for communication between the i915 driver and the GuC firmware.
v2:
Changes to output formats per Chris Wilson's suggestions
Issue: VIZ-4884
--- drivers/gpu/drm/i915/i915_debugfs.c | 45 +++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+)
drivers/gpu/drm/i915/i915_debugfs.c +45 -0
@@ -2334,6 +2334,50 @@ static int i915_llc(struct seq_file *m, void *data)return 0 ; } +static void i915_uc_load_status_info (struct seq_file *m,struct intel_uc_fw *uc_fw) +{ +seq_printf (m,"%s firmware status:\n" , + uc_fw->uc_name); +seq_printf (m,"\tpath: %s\n" , + uc_fw->uc_fw_path); +seq_printf (m,"\tfetch: %s\n" , +intel_uc_fw_status_repr (uc_fw->uc_fw_fetch_status)); +seq_printf (m,"\tload: %s\n" , +intel_uc_fw_status_repr (uc_fw->uc_fw_load_status)); +} + +static int i915_guc_load_status_info (struct seq_file *m,void *data) +{ +struct drm_info_node *node = m->private; +struct drm_i915_private *dev_priv = node->minor->dev->dev_private; +u32 tmp, i; + +if (!HAS_GUC_UCODE (dev_priv->dev)) +return 0 ; + +i915_uc_load_status_info (m, &dev_priv->guc.guc_fw); + +seq_printf (m,"\tversion wanted: %d.%d\n" , + dev_priv->guc.fw_major_wanted, dev_priv->guc.fw_minor_wanted); +seq_printf (m,"\tversion found: %d.%d\n" , + dev_priv->guc.fw_major_found, dev_priv->guc.fw_minor_found); + + tmp =I915_READ (GUC_STATUS ); + +seq_printf (m,"\nGuC status 0x%08x:\n" , tmp); +seq_printf (m,"\tBootrom status = 0x%x\n" , + (tmp &GS_BOOTROM_MASK ) >>GS_BOOTROM_SHIFT ); +seq_printf (m,"\tuKernel status = 0x%x\n" , + (tmp &GS_UKERNEL_MASK ) >>GS_UKERNEL_SHIFT ); +seq_printf (m,"\tMIA Core status = 0x%x\n" , + (tmp &GS_MIA_MASK ) >>GS_MIA_SHIFT ); +seq_puts (m,"\nScratch registers:\n" ); +for (i =0 ; i <16 ; i++) +seq_printf (m,"\t%2d: \t0x%x\n" , i,I915_READ (SOFT_SCRATCH (i))); + +return 0 ; +} +static int i915_edp_psr_status (struct seq_file *m,void *data) {struct drm_info_node *node = m->private;
@@ -5034,6 +5078,7 @@ static const struct drm_info_list i915_debugfs_list[] = { {"i915_gem_hws_bsd", i915_hws_info, 0, (void *)VCS}, {"i915_gem_hws_vebox", i915_hws_info, 0, (void *)VECS}, {"i915_gem_batch_pool", i915_gem_batch_pool_info, 0}, + {"i915_guc_load_status", i915_guc_load_status_info, 0}, {"i915_frequency_info", i915_frequency_info, 0}, {"i915_hangcheck_info", i915_hangcheck_info, 0}, {"i915_drpc_info", i915_drpc_info, 0},
Signature · 6 lines
1.7.9.5 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH v2 7/17 drm/i915: Split late for_each_ring loop from i915_gem_init_hw()
In reply to Dave GordonThis function was restructured by two recent patches:
drm/i915: Add explicit request management to i915_gem_init_hw() drm/i915: Moved the for_each_ring loop outside of i915_gem_context_enable()
Now we need to move the entire loop into a separate function i915_gem_init_hw_late(), replacing the inline loop with a call. This will allow a future patch to add a call from another locations (for now, there are no other calls).
--- drivers/gpu/drm/i915/i915_drv.h | 1 + drivers/gpu/drm/i915/i915_gem.c | 85 ++++++++++++++++++++++----------------- 2 files changed, 50 insertions(+), 36 deletions(-)
drivers/gpu/drm/i915/i915_drv.h +1 -0
@@ -2897,6 +2897,7 @@ bool i915_gem_clflush_object(struct drm_i915_gem_object *obj, bool force);int __must_check i915_gem_init (struct drm_device *dev);int i915_gem_init_rings (struct drm_device *dev);int __must_check i915_gem_init_hw (struct drm_device *dev); +int __must_check i915_gem_init_hw_late (struct drm_device *dev);int i915_gem_l3_remap (struct drm_i915_gem_request *req,int slice);void i915_gem_init_swizzling (struct drm_device *dev);void i915_gem_cleanup_ringbuffer (struct drm_device *dev);
drivers/gpu/drm/i915/i915_gem.c +49 -36
101 lines not on this page · raw message
Signature · 6 lines
1.7.9.5 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH v2 8/17 drm/i915: Defer default hardware context initialisation until first open
In reply to Dave GordonIn order to fully initialise the default contexts, we have to execute batchbuffer commands on the GPU engines. But in the case of GuC-based batch submission, we can't do that until any required firmware has been loaded, which may not be possible during driver load, because the filesystem(s) containing the firmware may not be mounted until later.
Therefore, we now allow the first call to the firmware-loading code to return -EAGAIN to indicate that it's not yet ready, and that it should be retried when the device is first opened from user code, by which time we expect that all required filesystems will have been mounted. The late-retry code will then re-attempt to load the firmware if the early attempt failed.
If the late retry fails, the current open-in-progress will fail, but the recovery code will disable GuC submission and reset the GPU and driver. The next open will therefore be in non-GuC mode, and will be allowed to complete even if the GuC cannot be loaded or used.
Issue: VIZ-4884
--- drivers/gpu/drm/i915/i915_drv.h | 2 ++ drivers/gpu/drm/i915/i915_gem.c | 8 ++++- drivers/gpu/drm/i915/i915_gem_context.c | 52 ++++++++++++++++++++++++++++--- drivers/gpu/drm/i915/i915_irq.c | 48 ++++++++++++++++++++++++++++ 4 files changed, 104 insertions(+), 6 deletions(-)
drivers/gpu/drm/i915/i915_drv.h +2 -0
@@ -1848,6 +1848,7 @@ struct drm_i915_private {/* hda/i915 audio component */ bool audio_component_registered; +bool contexts_ready;uint32_t hw_context_size;struct list_head context_list;
@@ -2637,6 +2638,7 @@ void i915_queue_hangcheck(struct drm_device *dev); __printf(3, 4)void i915_handle_error (struct drm_device *dev,bool wedged,const char *fmt, ...); +void i915_handle_guc_error (struct drm_device *dev,int err);extern void intel_irq_init (struct drm_i915_private *dev_priv);int intel_irq_install (struct drm_i915_private *dev_priv);
drivers/gpu/drm/i915/i915_gem.c +7 -1
@@ -5121,9 +5121,15 @@ i915_gem_init_hw(struct drm_device *dev) }/* We can't enable contexts until all firmware is loaded */ - ret =intel_guc_ucode_load (dev, true); + ret =intel_guc_ucode_load (dev, false); +if (ret == -EAGAIN ) { + ret =0 ; + goto out;/* too early */ + } ret =i915_gem_init_hw_late (dev); +if (ret ==0 ) + dev_priv->contexts_ready = true; out:intel_uncore_forcewake_put (dev_priv,FORCEWAKE_ALL );
drivers/gpu/drm/i915/i915_gem_context.c +47 -5
70 lines not on this page · raw message
drivers/gpu/drm/i915/i915_irq.c +48 -0
54 lines not on this page · raw message
Signature · 6 lines
1.7.9.5 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH v2 9/17 drm/i915: Expose two LRC functions for GuC submission mode
In reply to Dave GordonGuC submission is basically execlist submission, but with the GuC handling the actual writes to the ELSP and the resulting context switch interrupts. So to prepare a context for submission via the GuC, we need some of the same functions used in execlist mode. This commit exposes two such functions, changing their names to better describe what they do (they're related to logical ring contexts rather than to execlists per se).
v2:
Replaces previous "drm/i915: Move execlists defines from .c to .h"
Issue: VIZ-4884
--- drivers/gpu/drm/i915/intel_lrc.c | 27 +++++++++++++-------------- drivers/gpu/drm/i915/intel_lrc.h | 5 +++++ 2 files changed, 18 insertions(+), 14 deletions(-)
drivers/gpu/drm/i915/intel_lrc.c +13 -14
@@ -264,8 +264,8 @@ u32 intel_execlists_ctx_id(struct drm_i915_gem_object *ctx_obj)return lrca >>12 ; } -static uint64_t execlists_ctx_descriptor (struct intel_engine_cs *ring, -struct drm_i915_gem_object *ctx_obj) +uint64_t intel_lr_context_descriptor (struct intel_engine_cs *ring, +struct drm_i915_gem_object *ctx_obj) {struct drm_device *dev = ring->dev;uint64_t desc;
@@ -306,13 +306,13 @@ static void execlists_elsp_write(struct intel_engine_cs *ring,/* XXX: You must always write both descriptors in the order below. */ if (ctx_obj1) - temp =execlists_ctx_descriptor (ring, ctx_obj1); + temp =intel_lr_context_descriptor (ring, ctx_obj1);else temp =0 ; desc[1 ] = (u32)(temp >>32 ); desc[0 ] = (u32 )temp; - temp =execlists_ctx_descriptor (ring, ctx_obj0); + temp =intel_lr_context_descriptor (ring, ctx_obj0); desc[3 ] = (u32)(temp >>32 ); desc[2 ] = (u32 )temp;
@@ -331,10 +331,10 @@ static void execlists_elsp_write(struct intel_engine_cs *ring,spin_unlock (&dev_priv->uncore.lock); } -static int execlists_update_context (struct drm_i915_gem_object *ctx_obj, -struct drm_i915_gem_object *ring_obj, -struct i915_hw_ppgtt *ppgtt, -u32 tail) +/* Update the ringbuffer pointer and tail offset in a saved context image */ +void intel_lr_context_update (struct drm_i915_gem_object *ctx_obj, +struct drm_i915_gem_object *ring_obj, +u32 tail) {struct page *page;uint32_t *reg_state;
@@ -342,12 +342,11 @@ static int execlists_update_context(struct drm_i915_gem_object *ctx_obj, page =i915_gem_object_get_page (ctx_obj,1 ); reg_state =kmap_atomic (page); - reg_state[CTX_RING_TAIL +1 ] = tail; reg_state[CTX_RING_BUFFER_START +1 ] =i915_gem_obj_ggtt_offset (ring_obj); +if (tail != ~0u ) + reg_state[CTX_RING_TAIL +1 ] = tail;kunmap_atomic (reg_state); - -return 0 ; } static void execlists_submit_contexts(struct intel_engine_cs *ring,
@@ -363,7 +362,7 @@ static void execlists_submit_contexts(struct intel_engine_cs *ring,WARN_ON (!i915_gem_obj_is_pinned (ctx_obj0));WARN_ON (!i915_gem_obj_is_pinned (ringbuf0->obj)); -execlists_update_context (ctx_obj0, ringbuf0->obj, to0->ppgtt, tail0); +intel_lr_context_update (ctx_obj0, ringbuf0->obj, tail0);if (to1) { ringbuf1 = to1->engine[ring->id].ringbuf;
@@ -372,7 +371,7 @@ static void execlists_submit_contexts(struct intel_engine_cs *ring,WARN_ON (!i915_gem_obj_is_pinned (ctx_obj1));WARN_ON (!i915_gem_obj_is_pinned (ringbuf1->obj)); -execlists_update_context (ctx_obj1, ringbuf1->obj, to1->ppgtt, tail1); +intel_lr_context_update (ctx_obj1, ringbuf1->obj, tail1); }execlists_elsp_write (ring, ctx_obj0, ctx_obj1);
@@ -2029,7 +2028,7 @@ populate_lr_context(struct intel_context *ctx, struct drm_i915_gem_object *ctx_o reg_state[CTX_RING_TAIL +1 ] =0 ; reg_state[CTX_RING_BUFFER_START ] =RING_START (ring->mmio_base);/* Ring buffer start address is not known until the buffer is pinned. -* It is written to the context image in execlists_update_context() +* It is written to the context image in intel_lr_context_update() */ reg_state[CTX_RING_BUFFER_CONTROL ] =RING_CTL (ring->mmio_base); reg_state[CTX_RING_BUFFER_CONTROL+1] =
drivers/gpu/drm/i915/intel_lrc.h +5 -0
@@ -73,6 +73,11 @@ void intel_lr_context_unpin(struct intel_engine_cs *ring, struct intel_context *ctx);void intel_lr_context_reset (struct drm_device *dev,struct intel_context *ctx); +void intel_lr_context_update (struct drm_i915_gem_object *ctx_obj, +struct drm_i915_gem_object *ring_obj, +u32 tail); +uint64_t intel_lr_context_descriptor (struct intel_engine_cs *ring, +struct drm_i915_gem_object *ctx_obj);/* Execlists */ int intel_sanitize_enable_execlists (struct drm_device *dev,int enable_execlists);
Signature · 6 lines
1.7.9.5 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Re: [PATCH 09/17 v2] drm/i915: Expose two LRC functions for GuC submission mode
Quoted 65 lines · Dave Gordon
GuC submission is basically execlist submission, but with the GuC handling the actual writes to the ELSP and the resulting context switch interrupts. So to prepare a context for submission via the GuC, we need some of the same functions used in execlist mode. This commit exposes two such functions, changing their names to better describe what they do (they're related to logical ring contexts rather than to execlists per se).
v2:
Replaces previous "drm/i915: Move execlists defines from .c to .h"Issue: VIZ-4884
Signed-off-by Dave Gordon <[email protected]>--- drivers/gpu/drm/i915/intel_lrc.c | 27 +++++++++++++-------------- drivers/gpu/drm/i915/intel_lrc.h | 5 +++++ 2 files changed, 18 insertions(+), 14 deletions(-)drivers/gpu/drm/i915/intel_lrc.c +8
-8@@ -264,8 +264,8 @@ u32 intel_execlists_ctx_id(struct drm_i915_gem_object *ctx_obj)return lrca >>12 ; } -static uint64_t execlists_ctx_descriptor (struct intel_engine_cs *ring, -struct drm_i915_gem_object *ctx_obj) +uint64_t intel_lr_context_descriptor (struct intel_engine_cs *ring, +struct drm_i915_gem_object *ctx_obj) {struct drm_device *dev = ring->dev;uint64_t desc;@@ -306,13 +306,13 @@ static void execlists_elsp_write(struct intel_engine_cs *ring,/* XXX: You must always write both descriptors in the order below. */ if (ctx_obj1) - temp =execlists_ctx_descriptor (ring, ctx_obj1); + temp =intel_lr_context_descriptor (ring, ctx_obj1);else temp =0 ; desc[1 ] = (u32)(temp >>32 ); desc[0 ] = (u32 )temp; - temp =execlists_ctx_descriptor (ring, ctx_obj0); + temp =intel_lr_context_descriptor (ring, ctx_obj0); desc[3 ] = (u32)(temp >>32 ); desc[2 ] = (u32 )temp;@@ -331,10 +331,10 @@ static void execlists_elsp_write(struct intel_engine_cs *ring,spin_unlock (&dev_priv->uncore.lock); } -static int execlists_update_context (struct drm_i915_gem_object *ctx_obj, -struct drm_i915_gem_object *ring_obj, -struct i915_hw_ppgtt *ppgtt, -u32 tail) +/* Update the ringbuffer pointer and tail offset in a saved context image */ +void intel_lr_context_update (struct drm_i915_gem_object *ctx_obj, +struct drm_i915_gem_object *ring_obj, +u32 tail) {struct page *page;uint32_t *reg_state;
drivers/gpu/drm/i915/intel_lrc.c static int execlists_update_context(struct drm_i915_gem_object *ctx_obj, · line 347
Quoted 7 lines
drivers/gpu/drm/i915/intel_lrc.c +2
-1@@ -342,12 +342,11 @@ static int execlists_update_context(struct drm_i915_gem_object *ctx_obj, page =i915_gem_object_get_page (ctx_obj,1 ); reg_state =kmap_atomic (page); - reg_state[CTX_RING_TAIL +1 ] = tail; reg_state[CTX_RING_BUFFER_START +1 ] =i915_gem_obj_ggtt_offset (ring_obj); +if (tail != ~0u ) + reg_state[CTX_RING_TAIL +1 ] = tail;
I actually regret my original copycat of this function for guc. Because updating ring tail is moved to guc, there is no need to call this for each submission. Maybe we should split this call into two parts. The updating of ring buffer base is moved to where ring buffer is newly mapped. And the updating of tail is kept here for execlist submission only.
Alex
_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Re: [PATCH 09/17 v2] drm/i915: Expose two LRC functions for GuC submission mode
Quoted 66 lines · Yu Dai
Quoted 64 lines · Dave Gordon
GuC submission is basically execlist submission, but with the GuC handling the actual writes to the ELSP and the resulting context switch interrupts. So to prepare a context for submission via the GuC, we need some of the same functions used in execlist mode. This commit exposes two such functions, changing their names to better describe what they do (they're related to logical ring contexts rather than to execlists per se).
v2:
Replaces previous "drm/i915: Move execlists defines from .c to .h"Issue: VIZ-4884
Signed-off-by Dave Gordon <[email protected]>--- drivers/gpu/drm/i915/intel_lrc.c | 27 +++++++++++++-------------- drivers/gpu/drm/i915/intel_lrc.h | 5 +++++ 2 files changed, 18 insertions(+), 14 deletions(-)drivers/gpu/drm/i915/intel_lrc.c +8
-9@@ -264,8 +264,8 @@ u32 intel_execlists_ctx_id(struct drm_i915_gem_object *ctx_obj)return lrca >>12 ; } -static uint64_t execlists_ctx_descriptor (struct intel_engine_cs *ring, -struct drm_i915_gem_object *ctx_obj) +uint64_t intel_lr_context_descriptor (struct intel_engine_cs *ring, +struct drm_i915_gem_object *ctx_obj) {struct drm_device *dev = ring->dev;uint64_t desc;@@ -306,13 +306,13 @@ static void execlists_elsp_write(struct intel_engine_cs *ring,/* XXX: You must always write both descriptors in the order below. */ if (ctx_obj1) - temp =execlists_ctx_descriptor (ring, ctx_obj1); + temp =intel_lr_context_descriptor (ring, ctx_obj1);else temp =0 ; desc[1 ] = (u32)(temp >>32 ); desc[0 ] = (u32 )temp; - temp =execlists_ctx_descriptor (ring, ctx_obj0); + temp =intel_lr_context_descriptor (ring, ctx_obj0); desc[3 ] = (u32)(temp >>32 ); desc[2 ] = (u32 )temp;@@ -331,10 +331,10 @@ static void execlists_elsp_write(struct intel_engine_cs *ring,spin_unlock (&dev_priv->uncore.lock); } -static int execlists_update_context (struct drm_i915_gem_object *ctx_obj, -struct drm_i915_gem_object *ring_obj, -struct i915_hw_ppgtt *ppgtt, -u32 tail) +/* Update the ringbuffer pointer and tail offset in a saved context image */ +void intel_lr_context_update (struct drm_i915_gem_object *ctx_obj, +struct drm_i915_gem_object *ring_obj, +u32 tail) {struct page *page;uint32_t *reg_state;@@ -342,12 +342,11 @@ static int execlists_update_context(struct drm_i915_gem_object *ctx_obj, page =i915_gem_object_get_page (ctx_obj,1 ); reg_state =kmap_atomic (page); - reg_state[CTX_RING_TAIL +1 ] = tail; reg_state[CTX_RING_BUFFER_START +1 ] =i915_gem_obj_ggtt_offset (ring_obj);
Quoted 8 lines
drivers/gpu/drm/i915/intel_lrc.c static int execlists_update_context(struct drm_i915_gem_object *ctx_obj, · line 347
Quoted 2 lines
drivers/gpu/drm/i915/intel_lrc.c +2
-0+if (tail != ~0u ) + reg_state[CTX_RING_TAIL +1 ] = tail;I actually regret my original copycat of this function for guc. Because updating ring tail is moved to guc, there is no need to call this for each submission. Maybe we should split this call into two parts. The updating of ring buffer base is moved to where ring buffer is newly mapped. And the updating of tail is kept here for execlist submission only.
If you would be so kind to review patches that do just that, it would make intel_lrc a much nicer place to work, and execlists much faster. -Chris
Signature · 5 lines
Chris Wilson, Intel Open Source Technology Centre _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Re: [PATCH 09/17 v2] drm/i915: Expose two LRC functions for GuC submission mode
Quoted 77 lines · Chris Wilson
Quoted 67 lines · Yu Dai
Quoted 65 lines · Dave Gordon
GuC submission is basically execlist submission, but with the GuC handling the actual writes to the ELSP and the resulting context switch interrupts. So to prepare a context for submission via the GuC, we need some of the same functions used in execlist mode. This commit exposes two such functions, changing their names to better describe what they do (they're related to logical ring contexts rather than to execlists per se).
v2:
Replaces previous "drm/i915: Move execlists defines from .c to .h"Issue: VIZ-4884
Signed-off-by Dave Gordon <[email protected]>--- drivers/gpu/drm/i915/intel_lrc.c | 27 +++++++++++++-------------- drivers/gpu/drm/i915/intel_lrc.h | 5 +++++ 2 files changed, 18 insertions(+), 14 deletions(-)drivers/gpu/drm/i915/intel_lrc.c +9
-9@@ -264,8 +264,8 @@ u32 intel_execlists_ctx_id(struct drm_i915_gem_object *ctx_obj)return lrca >>12 ; } -static uint64_t execlists_ctx_descriptor (struct intel_engine_cs *ring, -struct drm_i915_gem_object *ctx_obj) +uint64_t intel_lr_context_descriptor (struct intel_engine_cs *ring, +struct drm_i915_gem_object *ctx_obj) {struct drm_device *dev = ring->dev;uint64_t desc;@@ -306,13 +306,13 @@ static void execlists_elsp_write(struct intel_engine_cs *ring,/* XXX: You must always write both descriptors in the order below. */ if (ctx_obj1) - temp =execlists_ctx_descriptor (ring, ctx_obj1); + temp =intel_lr_context_descriptor (ring, ctx_obj1);else temp =0 ; desc[1 ] = (u32)(temp >>32 ); desc[0 ] = (u32 )temp; - temp =execlists_ctx_descriptor (ring, ctx_obj0); + temp =intel_lr_context_descriptor (ring, ctx_obj0); desc[3 ] = (u32)(temp >>32 ); desc[2 ] = (u32 )temp;@@ -331,10 +331,10 @@ static void execlists_elsp_write(struct intel_engine_cs *ring,spin_unlock (&dev_priv->uncore.lock); } -static int execlists_update_context (struct drm_i915_gem_object *ctx_obj, -struct drm_i915_gem_object *ring_obj, -struct i915_hw_ppgtt *ppgtt, -u32 tail) +/* Update the ringbuffer pointer and tail offset in a saved context image */ +void intel_lr_context_update (struct drm_i915_gem_object *ctx_obj, +struct drm_i915_gem_object *ring_obj, +u32 tail) {struct page *page;uint32_t *reg_state;@@ -342,12 +342,11 @@ static int execlists_update_context(struct drm_i915_gem_object *ctx_obj, page =i915_gem_object_get_page (ctx_obj,1 ); reg_state =kmap_atomic (page); - reg_state[CTX_RING_TAIL +1 ] = tail; reg_state[CTX_RING_BUFFER_START +1 ] =i915_gem_obj_ggtt_offset (ring_obj); +if (tail != ~0u )Quoted 8 lines
drivers/gpu/drm/i915/intel_lrc.c static int execlists_update_context(struct drm_i915_gem_object *ctx_obj, · line 347
Quoted 1 line
drivers/gpu/drm/i915/intel_lrc.c +1
-0+ reg_state[CTX_RING_TAIL +1 ] = tail;I actually regret my original copycat of this function for guc. Because updating ring tail is moved to guc, there is no need to call this for each submission. Maybe we should split this call into two parts. The updating of ring buffer base is moved to where ring buffer is newly mapped. And the updating of tail is kept here for execlist submission only.
Quoted 3 lines
If you would be so kind to review patches that do just that, it would make
intel_lrca much nicer place to work, and execlists much faster. -Chris
I've deleted Alex's coy of this function in the GuC code; that's why the execlists/LRC version is exposed so that it can be shared with the GuC path, and the update of "tail" here is conditional, so the GuC call doesn't use that part.
I agree it would be nicer still to update the ringbuffer base address only at the point when it's pinned to the GGTT, rather than on each batch submission. As you say, that would allow us to remove this call entirely from the GuC path.
Another improvement would be to kmap the context whenever it's active, the way we already do for the ringbuffer, so we could get rid of the kmap_atomic calls here. Since contexts and ringbuffers are one-to-one in execlist/GuC modes, it should be simple to keep them mapped-and-pinned in paralell.
Further, perhaps we could allocate them in a single contiguous structure to further reduce overhead; 4 pages of ringbuffer, one page as a GuC shared channel, one page for the (PP)HWSP, some number of pages for the context image? All GGTT-pinned and kmapped together whenever they've got any work in-flight; all unpinned and unmapped either during retirement of the last-active-request in that context or lazily some time later.
I expect Chris has already implemented some of these ideas :)
.Dave.
_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH v2 10/17 drm/i915: GuC submission setup, phase 1
In reply to Dave GordonFrom: Alex Dai <[email protected]>
This adds the first of the data structures used to communicate with the GuC (the pool of guc_context structures).
We create a GuC-specific wrapper round the GEM object allocator as all GEM objects shared with the GuC must be pinned into GGTT space at an address that is NOT in the range [0..WOPCM_SIZE), as that range of GGTT addresses is not accessible to the GuC (from the GuC's point of view, it's permanently reserved for other objects such as the BootROM & SRAM).
Later, we will need to allocate additional GuC-sharable objects for the submission client(s) and the GuC's debug log.
v2:
Remove redundant initialisation [Chris Wilson]
Defer adding struct members until needed [Chris Wilson] Local functions should pass dev_priv rather than dev [Chris Wilson]
Issue: VIZ-4884
--- drivers/gpu/drm/i915/Makefile | 3 +- drivers/gpu/drm/i915/i915_guc_submission.c | 114 ++++++++++++++++++++++++++++ drivers/gpu/drm/i915/intel_guc.h | 7 ++ drivers/gpu/drm/i915/intel_guc_loader.c | 21 +++++ 4 files changed, 144 insertions(+), 1 deletion(-) create mode 100644 drivers/gpu/drm/i915/i915_guc_submission.c
drivers/gpu/drm/i915/Makefile +2 -1
@@ -43,7 +43,8 @@ i915-y += i915_cmd_parser.o \ i915-y += intel_uc_loader.o # general-purpose microcontroller (GuC) support -i915-y += intel_guc_loader.o +i915-y += intel_guc_loader.o \ + i915_guc_submission.o # autogenerated null render state i915-y += intel_renderstate_gen6.o \
drivers/gpu/drm/i915/i915_guc_submission.c new file +114 -0
114 lines not on this page · raw message
drivers/gpu/drm/i915/intel_guc.h +7 -0
@@ -39,6 +39,9 @@ struct intel_guc {uint16_t fw_minor_found;uint32_t log_flags; + +struct drm_i915_gem_object *ctx_pool_obj; +struct ida ctx_ids; };/* intel_guc_loader.c */
@@ -46,4 +49,8 @@ extern void intel_guc_ucode_init(struct drm_device *dev);extern int intel_guc_ucode_load (struct drm_device *dev,bool wait);extern void intel_guc_ucode_fini (struct drm_device *dev); +/* i915_guc_submission.c */ +int i915_guc_submission_init (struct drm_device *dev); +void i915_guc_submission_fini (struct drm_device *dev); +#endif
drivers/gpu/drm/i915/intel_guc_loader.c +21 -0
@@ -111,6 +111,21 @@ static void set_guc_init_params(struct drm_i915_private *dev_priv) i915.guc_log_level <<GUC_LOG_VERBOSITY_SHIFT ; } +/* If GuC scheduling is enabled, setup params here. */ +if (i915.enable_guc_submission) { +u32 pgs =i915_gem_obj_ggtt_offset (dev_priv->guc.ctx_pool_obj); +u32 ctx_in_16 =GUC_MAX_GPU_CONTEXTS /16 ; + + pgs >>=PAGE_SHIFT ; + params[GUC_CTL_CTXINFO ] = (pgs <<GUC_CTL_BASE_ADDR_SHIFT ) | + (ctx_in_16 <<GUC_CTL_CTXNUM_IN16_SHIFT ); + + params[GUC_CTL_FEATURE ] |=GUC_CTL_KERNEL_SUBMISSIONS ; + +/* Unmask this bit to enable GuC scheduler */ + params[GUC_CTL_FEATURE ] &= ~GUC_CTL_DISABLE_SCHEDULER ; + } +I915_WRITE (SOFT_SCRATCH (0 ),0 );for (i =0 ; i <GUC_CTL_MAX_DWORDS ; i++)
@@ -406,6 +421,10 @@ int intel_guc_ucode_load(struct drm_device *dev, bool wait)if (err) goto fail; + err =i915_guc_submission_init (dev); +if (err) + goto fail; + err =guc_ucode_xfer (dev_priv);if (err) goto fail;
@@ -436,5 +455,7 @@ void intel_guc_ucode_fini(struct drm_device *dev)struct drm_i915_private *dev_priv = dev->dev_private;struct intel_uc_fw *guc_fw = &dev_priv->guc.guc_fw; +i915_guc_submission_fini (dev); +intel_uc_fw_fini (guc_fw); }
Signature · 6 lines
1.7.9.5 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH v2 11/17 drm/i915: Enable GuC firmware log
In reply to Dave GordonFrom: Alex Dai <[email protected]>
Allocate a GEM object to hold GuC log data. A debugfs interface (i915_guc_log_dump) is provided to print out the log content.
v2:
Add struct members at point of use [Chris Wilson]
Issue: VIZ-4884
--- drivers/gpu/drm/i915/i915_debugfs.c | 29 ++++++++++++++++++ drivers/gpu/drm/i915/i915_guc_submission.c | 46 ++++++++++++++++++++++++++++ drivers/gpu/drm/i915/intel_guc.h | 1 + 3 files changed, 76 insertions(+)
drivers/gpu/drm/i915/i915_debugfs.c +29 -0
@@ -2378,6 +2378,34 @@ static int i915_guc_load_status_info(struct seq_file *m, void *data)return 0 ; } +static int i915_guc_log_dump (struct seq_file *m,void *data) +{ +struct drm_info_node *node = m->private; +struct drm_device *dev = node->minor->dev; +struct drm_i915_private *dev_priv = dev->dev_private; +struct drm_i915_gem_object *log_obj = dev_priv->guc.log_obj; +u32 *log; +int i =0 , pg; + +if (!log_obj) +return 0 ; + +for (pg =0 ; pg < log_obj->base.size /PAGE_SIZE ; pg++) { + log =kmap_atomic (i915_gem_object_get_page (log_obj, pg)); + +for (i =0 ; i <PAGE_SIZE /sizeof (u32); i +=4 ) +seq_printf (m,"0x%08x 0x%08x 0x%08x 0x%08x\n" , + *(log + i), *(log + i +1 ), + *(log + i +2 ), *(log + i +3 )); + +kunmap_atomic (log); + } + +seq_putc (m,'\n' ); + +return 0 ; +} +static int i915_edp_psr_status (struct seq_file *m,void *data) {struct drm_info_node *node = m->private;
@@ -5079,6 +5107,7 @@ static const struct drm_info_list i915_debugfs_list[] = { {"i915_gem_hws_vebox", i915_hws_info, 0, (void *)VECS}, {"i915_gem_batch_pool", i915_gem_batch_pool_info, 0}, {"i915_guc_load_status", i915_guc_load_status_info, 0}, + {"i915_guc_log_dump", i915_guc_log_dump, 0}, {"i915_frequency_info", i915_frequency_info, 0}, {"i915_hangcheck_info", i915_hangcheck_info, 0}, {"i915_drpc_info", i915_drpc_info, 0},
drivers/gpu/drm/i915/i915_guc_submission.c +46 -0
64 lines not on this page · raw message
drivers/gpu/drm/i915/intel_guc.h +1 -0
@@ -39,6 +39,7 @@ struct intel_guc {uint16_t fw_minor_found;uint32_t log_flags; +struct drm_i915_gem_object *log_obj;struct drm_i915_gem_object *ctx_pool_obj;struct ida ctx_ids;
Signature · 6 lines
1.7.9.5 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH v2 12/17 drm/i915: Implementation of GuC client
In reply to Dave GordonA GuC client has its own doorbell and workqueue. It maintains the doorbell cache line, process description object and work queue item.
A default guc_client is created for the i915 driver to use for normal-priority in-order submission.
Note that the created client is not yet ready for use; doorbell allocation will fail as we haven't yet linked the GuC's context descriptor to the default contexts for each ring (see later patch). However the driver will still be usable, automatically falling back to execlist mode.
v2:
Defer adding structure members until needed [Chris Wilson] Rationalise type declarations [Chris Wilson]
Issue: VIZ-4884
--- drivers/gpu/drm/i915/i915_guc_submission.c | 661 ++++++++++++++++++++++++++++ drivers/gpu/drm/i915/intel_guc.h | 43 ++ drivers/gpu/drm/i915/intel_guc_loader.c | 10 + 3 files changed, 714 insertions(+)
drivers/gpu/drm/i915/i915_guc_submission.c +661 -0
@@ -27,6 +27,524 @@#include "intel_guc.h" /** +* DOC: GuC Client +* +* i915_guc_client: +* We use the term client to avoid confusion with contexts. A i915_guc_client is +* equivalent to GuC object guc_context_desc. This context descriptor is +* allocated from a pool of 1024 entries. Kernel driver will allocate doorbell +* and workqueue for it. Also the process descriptor (guc_process_desc), which +* is mapped to client space. So the client can write Work Item then ring the +* doorbell. +* +* To simplify the implementation, we allocate one gem object that contains all +* pages for doorbell, process descriptor and workqueue. +* +* The Scratch registers: +* There are 16 MMIO-based registers start from 0xC180. The kernel driver writes +* a value to the action register (SOFT_SCRATCH_0) along with any data. It then +* triggers an interrupt on the GuC via another register write (0xC4C8). +* Firmware writes a success/fail code back to the action register after +* processes the request. The kernel driver polls waiting for this update and +* then proceeds. +* See host2guc_action() +* +* Doorbells: +* Doorbells are interrupts to uKernel. A doorbell is a single cache line (QW) +* mapped into process space. +* +* Work Items: +* There are several types of work items that the host may place into a +* workqueue, each with its own requirements and limitations. Currently only +* WQ_TYPE_INORDER is needed to support legacy submission via GuC, which +* represents in-order queue. The kernel driver packs ring tail pointer and an +* ELSP context descriptor dword into Work Item. +* See guc_add_workqueue_item() +* +*/ + +/* +* Read GuC command/status register (SOFT_SCRATCH_0) +* Return true if it contains a response rather than a command +*/ +static inline bool host2guc_action_response (struct drm_i915_private *dev_priv, +u32 *status) +{ +u32 val =I915_READ (SOFT_SCRATCH (0 )); + *status = val; +return GUC2HOST_IS_RESPONSE (val); +} + +static int host2guc_action (struct intel_guc *guc,u32 *data,u32 len) +{ +struct drm_i915_private *dev_priv =guc_to_i915 (guc); +u32 status; +int i; +int ret; + +if (WARN_ON (len <1 || len >15 )) +return -EINVAL ; + +spin_lock (&dev_priv->guc.host2guc_lock); + + dev_priv->guc.action_count +=1 ; + dev_priv->guc.action_cmd = data[0 ]; + +for (i =0 ; i < len; i++) +I915_WRITE (SOFT_SCRATCH (i), data[i]); + +POSTING_READ (SOFT_SCRATCH (i -1 )); + +I915_WRITE (HOST2GUC_INTERRUPT ,HOST2GUC_TRIGGER ); + + ret =wait_for_atomic (host2guc_action_response (dev_priv, &status),10 ); +if (status !=GUC2HOST_STATUS_SUCCESS ) { +/* either GuC doesn't respond, which is a TIMEOUT, +* or a failure code is returned. */ +if (ret != -ETIMEDOUT ) + ret = -EIO ; + +DRM_ERROR ("GUC: host2guc action 0x%X failed. ret=%d " +"status=0x%08X response=0x%08X\n" , + data[0 ], ret, status, +I915_READ (SOFT_SCRATCH (15 ))); + + dev_priv->guc.action_fail +=1 ; + dev_priv->guc.action_err = ret; + } + dev_priv->guc.action_status = status; + +spin_unlock (&dev_priv->guc.host2guc_lock); + +return ret; +} + +/* +* Tell the GuC to allocate or deallocate a specific doorbell +*/ + +static int host2guc_allocate_doorbell (struct intel_guc *guc, +struct i915_guc_client *client) +{ +u32 data[2 ]; + + data[0 ] =HOST2GUC_ACTION_ALLOCATE_DOORBELL ; + data[1 ] = client->ctx_index; + +return host2guc_action (guc, data,2 ); +} + +static int host2guc_release_doorbell (struct intel_guc *guc, +struct i915_guc_client *client) +{ +u32 data[2 ]; + + data[0 ] =HOST2GUC_ACTION_DEALLOCATE_DOORBELL ; + data[1 ] = client->ctx_index; + +return host2guc_action (guc, data,2 ); +} + +/* +* Initialise, update, or clear doorbell data shared with the GuC +* +* These functions modify shared data and so need access to the mapped +* client object which contains the page being used for the doorbell +*/ + +static void guc_init_doorbell (struct intel_guc *guc, +struct i915_guc_client *client) +{ +struct guc_doorbell_info *doorbell; +void *base; + + base =kmap_atomic (i915_gem_object_get_page (client->client_obj,0 )); + doorbell = base + client->doorbell_offset; + + doorbell->db_status =1 ; + doorbell->cookie =0 ; + +kunmap_atomic (base); +} + +static int guc_ring_doorbell (struct i915_guc_client *gc) +{ +struct guc_process_desc *desc; +union guc_doorbell_qw db_cmp, db_exc, db_ret; +union guc_doorbell_qw *db; +void *base; +int attempt =2 , ret = -EAGAIN ; + + base =kmap_atomic (i915_gem_object_get_page (gc->client_obj,0 )); + desc = base + gc->proc_desc_offset; + +/* Update the tail so it is visible to GuC */ + desc->tail = gc->wq_tail; + +/* current cookie */ + db_cmp.db_status =GUC_DOORBELL_ENABLED ; + db_cmp.cookie = gc->cookie; + +/* cookie to be updated */ + db_exc.db_status =GUC_DOORBELL_ENABLED ; + db_exc.cookie = gc->cookie +1 ; +if (db_exc.cookie ==0 ) + db_exc.cookie =1 ; + +/* pointer of current doorbell cacheline */ + db = base + gc->doorbell_offset; + +while (attempt--) { +/* lets ring the doorbell */ + db_ret.value_qw =atomic64_cmpxchg ((atomic64_t *)db, + db_cmp.value_qw, db_exc.value_qw); + +/* if the exchange was successfully executed */ +if (db_ret.value_qw == db_cmp.value_qw) { +/* db was successfully rung */ + gc->cookie = db_exc.cookie; + ret =0 ; +break ; + } + +/* XXX: doorbell was lost and need to acquire it again */ +if (db_ret.db_status ==GUC_DOORBELL_DISABLED ) +break ; + +DRM_ERROR ("Cookie mismatch. Expected %d, returned %d\n" , + db_cmp.cookie, db_ret.cookie); + +/* update the cookie to newly read cookie from GuC */ + db_cmp.cookie = db_ret.cookie; + db_exc.cookie = db_ret.cookie +1 ; +if (db_exc.cookie ==0 ) + db_exc.cookie =1 ; + } + +kunmap_atomic (base); +return ret; +} + +static void guc_disable_doorbell (struct intel_guc *guc, +struct i915_guc_client *client) +{ +struct drm_i915_private *dev_priv =guc_to_i915 (guc); +struct guc_doorbell_info *doorbell; +void *base; +int drbreg =GEN8_DRBREGL (client->doorbell_id); +int value; + + base =kmap_atomic (i915_gem_object_get_page (client->client_obj,0 )); + doorbell = base + client->doorbell_offset; + + doorbell->db_status =0 ; + +kunmap_atomic (base); + +I915_WRITE (drbreg,I915_READ (drbreg) & ~GEN8_DRB_VALID ); + + value =I915_READ (drbreg); +WARN_ON ((value &GEN8_DRB_VALID ) !=0 ); + +I915_WRITE (GEN8_DRBREGU (client->doorbell_id),0 ); +I915_WRITE (drbreg,0 ); + +/* XXX: wait for any interrupts */ +/* XXX: wait for workqueue to drain */ +} + +/* +* Select, assign and relase doorbell cachelines +* +* These functions track which doorbell cachelines are in use. +* The data they manipulate is protected by the host2guc lock. +*/ + +static uint32_t select_doorbell_cacheline (struct intel_guc *guc) +{ +const uint32_t cacheline_size = boot_cpu_data.x86_clflush_size; +uint32_t offset; + +spin_lock (&guc->host2guc_lock); + +/* Doorbell uses a single cache line within a page */ + offset = guc->db_cacheline &PAGE_MASK ; + +/* Moving to next cache line to reduce contention */ + guc->db_cacheline += cacheline_size; + +spin_unlock (&guc->host2guc_lock); + +return offset; +} + +static uint16_t assign_doorbell (struct intel_guc *guc,uint32_t priority) +{ +/* The bitmap is split into two halves - high and normal priority. */ +const uint16_t half =GUC_MAX_DOORBELLS /2 ; +const uint16_t start = (priority <=GUC_CTX_PRIORITY_HIGH ) ? half :0 ; +const uint16_t end = start + half; +uint16_t id; + +spin_lock (&guc->host2guc_lock); + id =find_next_zero_bit (guc->doorbell_bitmap, end, start); +if (id == end) + id =GUC_INVALID_DOORBELL_ID ; +else +bitmap_set (guc->doorbell_bitmap, id,1 ); +spin_unlock (&guc->host2guc_lock); + +return id; +} + +static void release_doorbell (struct intel_guc *guc,uint16_t id) +{ +spin_lock (&guc->host2guc_lock); +bitmap_clear (guc->doorbell_bitmap, id,1 ); +spin_unlock (&guc->host2guc_lock); +} + +/* +* Initialise the process descriptor shared with the GuC firmware. +*/ +static void guc_init_proc_desc (struct intel_guc *guc, +struct i915_guc_client *client) +{ +struct guc_process_desc *desc; +void *base; + + base =kmap_atomic (i915_gem_object_get_page (client->client_obj,0 )); + desc = base + client->proc_desc_offset; + +memset (desc,0 ,sizeof (*desc)); + +/* +* XXX: pDoorbell and WQVBaseAddress are pointers in process address +* space for ring3 clients (set them as in mmap_ioctl) or kernel +* space for kernel clients (map on demand instead? May make debug +* easier to have it mapped). +*/ + desc->wq_base_addr =0 ; + desc->db_base_addr =0 ; + + desc->context_id = client->ctx_index; + desc->wq_size_bytes = client->wq_size; + desc->wq_status =WQ_STATUS_ACTIVE ; + desc->priority = client->priority; + +kunmap_atomic (base); +} + +/* +* Initialise/clear the context descriptor shared with the GuC firmware. +* +* This descriptor tells the GuC where (in GGTT space) to find the important +* data structures relating to this client (doorbell, process descriptor, +* write queue, etc). +*/ + +static void guc_init_ctx_desc (struct intel_guc *guc, +struct i915_guc_client *client) +{ +struct guc_context_desc desc; +struct sg_table *sg; + +memset (&desc,0 ,sizeof (desc)); + + desc.attribute =GUC_CTX_DESC_ATTR_ACTIVE |GUC_CTX_DESC_ATTR_KERNEL ; + desc.context_id = client->ctx_index; + desc.priority = client->priority; + desc.engines_used = (1 <<RCS ) | (1 <<VCS ) | (1 <<BCS ) | + (1 <<VECS ) | (1 <<VCS2 );/* all engines */ + desc.db_id = client->doorbell_id; + +/* +* The CPU address is only needed at certain points, so kmap_atomic on +* demand instead of storing it in the ctx descriptor. +* XXX: May make debug easier to have it mapped +*/ + desc.db_trigger_cpu =0 ; + desc.db_trigger_uk = client->doorbell_offset + +i915_gem_obj_ggtt_offset (client->client_obj); + desc.db_trigger_phy = client->doorbell_offset + +sg_dma_address (client->client_obj->pages->sgl); + + desc.process_desc = client->proc_desc_offset + +i915_gem_obj_ggtt_offset (client->client_obj); + + desc.wq_addr = client->wq_offset + +i915_gem_obj_ggtt_offset (client->client_obj); + + desc.wq_size = client->wq_size; + +/* +* XXX: Take LRCs from an existing intel_context if this is not an +* IsKMDCreatedContext client +*/ + desc.desc_private = (uintptr_t )client; + +/* Pool context is pinned already */ + sg = guc->ctx_pool_obj->pages; +sg_pcopy_from_buffer (sg->sgl, sg->nents, &desc,sizeof (desc), +sizeof (desc) * client->ctx_index); +} + +static void guc_fini_ctx_desc (struct intel_guc *guc, +struct i915_guc_client *client) +{ +struct guc_context_desc desc; +struct sg_table *sg; + +memset (&desc,0 ,sizeof (desc)); + + sg = guc->ctx_pool_obj->pages; +sg_pcopy_from_buffer (sg->sgl, sg->nents, &desc,sizeof (desc), +sizeof (desc) * client->ctx_index); +} + +/* Get valid workqueue item and return it back to offset */ +static int guc_get_workqueue_space (struct i915_guc_client *gc,u32 *offset) +{ +struct guc_process_desc *desc; +void *base; +u32 size =sizeof (struct guc_wq_item ); +int ret =0 , timeout_counter =200 ; +unsigned long flags; + + base =kmap_atomic (i915_gem_object_get_page (gc->client_obj,0 )); + desc = base + gc->proc_desc_offset; + +while (timeout_counter-- >0 ) { +spin_lock_irqsave (&gc->wq_lock, flags); + + ret =wait_for_atomic (CIRC_SPACE (gc->wq_tail, desc->head, + gc->wq_size) >= size,1 ); + +if (!ret) { + *offset = gc->wq_tail; + +/* advance the tail for next workqueue item */ + gc->wq_tail += size; + gc->wq_tail &= gc->wq_size -1 ; + +/* this will break the loop */ + timeout_counter =0 ; + } + +spin_unlock_irqrestore (&gc->wq_lock, flags); + }; + +kunmap_atomic (base); + +return ret; +} + +static int guc_add_workqueue_item (struct i915_guc_client *gc, +struct intel_context *ctx, +struct intel_engine_cs *ring) +{ +struct drm_i915_gem_object *ctx_obj = ctx->engine[ring->id].state; +struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf; +struct guc_wq_item *wqi; +void *base; +u32 tail, wq_len, wq_off =0 ; +int ret; + + ret =guc_get_workqueue_space (gc, &wq_off); +if (ret) +return ret; + +/* For now workqueue item is 4 DWs; workqueue buffer is 2 pages. So we +* should not have the case where structure wqi is across page, neither +* wrapped to the beginning. This simplifies the implementation below. +* +* XXX: if not the case, we need save data to a temp wqi and copy it to +* workqueue buffer dw by dw. +*/ +WARN_ON (sizeof (struct guc_wq_item ) !=16 ); +WARN_ON (wq_off &3 ); + +/* wq starts from the page after doorbell / process_desc */ + base =kmap_atomic (i915_gem_object_get_page (gc->client_obj, + (wq_off +GUC_DB_SIZE ) >>PAGE_SHIFT )); + wq_off &=PAGE_SIZE -1 ; + wqi = (struct guc_wq_item *)((char *)base + wq_off); + +/* len does not include the header */ + wq_len =sizeof (struct guc_wq_item ) /sizeof (u32) -1 ; + wqi->header =WQ_TYPE_INORDER | + (wq_len <<WQ_LEN_SHIFT ) | + (ring->id <<WQ_TARGET_SHIFT ) | +WQ_NO_WCFLUSH_WAIT ; + +/* The GuC wants only the low-order word of the context descriptor */ + wqi->context_desc = (u32 )intel_lr_context_descriptor (ring, ctx_obj); + +/* The GuC firmware wants the tail index in QWords, not bytes */ + tail = ringbuf->tail >>3 ; + wqi->ring_tail = tail <<WQ_RING_TAIL_SHIFT ; + wqi->fence_id =0 ;/*XXX: what fence to be here */ + +kunmap_atomic (base); + +return 0 ; +} + +static void update_context_image (struct intel_context *ctx, +struct intel_engine_cs *ring) +{ +struct drm_i915_gem_object *ctx_obj = ctx->engine[ring->id].state; +struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf; + +intel_lr_context_update (ctx_obj, ringbuf->obj, ~0u ); +} + +/** +* i915_guc_submit() - Submit commands through GuC +* @client: the guc client where commands will go through +* @ctx: LRC where commands come from +* @ring: HW engine that will excute the commands +* +* Return: 0 if succeed +*/ +int i915_guc_submit (struct i915_guc_client *client, +struct intel_context *ctx, +struct intel_engine_cs *ring) +{ +int q_ret, b_ret; +unsigned long flags; + +/* Need this because of the deferred pin ctx and ring */ +/* Shall we move this right after ring is pinned? */ +update_context_image (ctx, ring); + + q_ret =guc_add_workqueue_item (client, ctx, ring); +if (q_ret ==0 ) + b_ret =guc_ring_doorbell (client); + +spin_lock_irqsave (&client->wq_lock, flags); + client->submissions +=1 ; +if (q_ret) { + client->q_fail +=1 ; + client->retcode = q_ret; + }else if (b_ret) { + client->b_fail +=1 ; + client->retcode = q_ret = b_ret; + }else { + client->retcode =0 ; + } +spin_unlock_irqrestore (&client->wq_lock, flags); + +return q_ret; +} + +/* +* Everything below here is concerned with setup & teardown, and is +* therefore not part of the somewhat time-critical batch-submission +* path of i915_guc_submit() above. +*/ + +/** * gem_allocate_guc_obj() - Allocate gem object for GuC usage * @dev: drm device * @size: size of object
@@ -75,6 +593,121 @@ static void gem_release_guc_obj(struct drm_i915_gem_object *obj)drm_gem_object_unreference (&obj->base); } +static void guc_client_free (struct drm_device *dev, +struct i915_guc_client *client) +{ +struct drm_i915_private *dev_priv = dev->dev_private; +struct intel_guc *guc = &dev_priv->guc; + +if (!client) +return ; + +if (client->doorbell_id !=GUC_INVALID_DOORBELL_ID ) { +/* +* First disable the doorbell, then tell the GuC we've +* finished with it, finally deallocate it in our bitmap +*/ +guc_disable_doorbell (guc, client); +host2guc_release_doorbell (guc, client); +release_doorbell (guc, client->doorbell_id); + } + +/* +* XXX: wait for any outstanding submissions before freeing memory. +* Be sure to drop any locks +*/ + +gem_release_guc_obj (client->client_obj); + +if (client->ctx_index !=GUC_INVALID_CTX_ID ) { +guc_fini_ctx_desc (guc, client); +ida_simple_remove (&guc->ctx_ids, client->ctx_index); + } + +kfree (client); +} + +/** +* guc_client_alloc() - Allocate an i915_guc_client +* @dev: drm device +* @priority: four levels priority _CRITICAL, _HIGH, _NORMAL and _LOW +* The kernel client to replace ExecList submission is created with +* NORMAL priority. Priority of a client for scheduler can be HIGH, +* while a preemption context can use CRITICAL. +* +* Return: An i915_guc_client object if success. +*/ +static struct i915_guc_client *guc_client_alloc (struct drm_device *dev, +uint32_t priority) +{ +struct i915_guc_client *client; +struct drm_i915_private *dev_priv = dev->dev_private; +struct intel_guc *guc = &dev_priv->guc; +struct drm_i915_gem_object *obj; + + client =kzalloc (sizeof (*client),GFP_KERNEL ); +if (!client) +return NULL ; + + client->doorbell_id =GUC_INVALID_DOORBELL_ID ; + client->priority = priority; + + client->ctx_index = (uint32_t )ida_simple_get (&guc->ctx_ids,0 , +GUC_MAX_GPU_CONTEXTS ,GFP_KERNEL ); +if (client->ctx_index >=GUC_MAX_GPU_CONTEXTS ) { + client->ctx_index =GUC_INVALID_CTX_ID ; + goto err; + } + +/* The first page is doorbell/proc_desc. Two followed pages are wq. */ + obj =gem_allocate_guc_obj (dev,GUC_DB_SIZE +GUC_WQ_SIZE ); +if (!obj) + goto err; + + client->client_obj = obj; + client->wq_offset =GUC_DB_SIZE ; + client->wq_size =GUC_WQ_SIZE ; +spin_lock_init (&client->wq_lock); + + client->doorbell_offset =select_doorbell_cacheline (guc); + +/* +* Since the doorbell only requires a single cacheline, we can save +* space by putting the application process descriptor in the same +* page. Use the half of the page that doesn't include the doorbell. +*/ +if (client->doorbell_offset >= (GUC_DB_SIZE /2 )) + client->proc_desc_offset =0 ; +else + client->proc_desc_offset = (GUC_DB_SIZE /2 ); + + client->doorbell_id =assign_doorbell (guc, client->priority); +if (client->doorbell_id ==GUC_INVALID_DOORBELL_ID ) +/* XXX: evict a doorbell instead */ + goto err; + +guc_init_proc_desc (guc, client); +guc_init_ctx_desc (guc, client); +guc_init_doorbell (guc, client); + +/* Invalidate GuC TLB to let GuC take the latest updates to GTT. */ +I915_WRITE (GEN8_GTCR ,GEN8_GTCR_INVALIDATE ); + +/* XXX: Any cache flushes needed? General domain mgmt calls? */ + +if (host2guc_allocate_doorbell (guc, client)) + goto err; + +DRM_DEBUG_DRIVER ("new priority %u client %p: ctx_index %u db_id %u\n" , + priority, client, client->ctx_index, client->doorbell_id); + +return client; + +err: +guc_client_free (dev, client); +return NULL ; +} +static void guc_create_log (struct intel_guc *guc) {struct drm_i915_private *dev_priv =guc_to_i915 (guc);
@@ -138,6 +771,8 @@ int i915_guc_submission_init(struct drm_device *dev)if (!guc->ctx_pool_obj)return -ENOMEM ; +spin_lock_init (&dev_priv->guc.host2guc_lock); +ida_init (&guc->ctx_ids);guc_create_log (guc);
@@ -145,6 +780,32 @@ int i915_guc_submission_init(struct drm_device *dev)return 0 ; } +int i915_guc_submission_enable (struct drm_device *dev) +{ +struct drm_i915_private *dev_priv = dev->dev_private; +struct intel_guc *guc = &dev_priv->guc; +struct i915_guc_client *client; + +/* client for execbuf submission */ + client =guc_client_alloc (dev,GUC_CTX_PRIORITY_NORMAL ); +if (!client) { +DRM_ERROR ("Failed to create execbuf guc_client\n" ); +return -ENOMEM ; + } + + guc->execbuf_client = client; +return 0 ; +} + +void i915_guc_submission_disable (struct drm_device *dev) +{ +struct drm_i915_private *dev_priv = dev->dev_private; +struct intel_guc *guc = &dev_priv->guc; + +guc_client_free (dev, guc->execbuf_client); + guc->execbuf_client =NULL ; +} +void i915_guc_submission_fini (struct drm_device *dev) {struct drm_i915_private *dev_priv = dev->dev_private;
drivers/gpu/drm/i915/intel_guc.h +43 -0
61 lines not on this page · raw message
drivers/gpu/drm/i915/intel_guc_loader.c +10 -0
@@ -409,6 +409,8 @@ int intel_guc_ucode_load(struct drm_device *dev, bool wait)if (guc_fw->uc_fw_fetch_status ==INTEL_UC_FIRMWARE_PENDING && !wait)return -EAGAIN ; +i915_guc_submission_disable (dev); +if (guc_fw->uc_fw_fetch_status ==INTEL_UC_FIRMWARE_NONE )return 0 ;
@@ -436,12 +438,20 @@ int intel_guc_ucode_load(struct drm_device *dev, bool wait)intel_uc_fw_status_repr (guc_fw->uc_fw_fetch_status), intel_uc_fw_status_repr(guc_fw->uc_fw_load_status)); +if (i915.enable_guc_submission) { + err =i915_guc_submission_enable (dev); +if (err) + goto fail; + } +return 0 ; fail:if (guc_fw->uc_fw_load_status ==INTEL_UC_FIRMWARE_PENDING ) guc_fw->uc_fw_load_status =INTEL_UC_FIRMWARE_FAIL ; +i915_guc_submission_disable (dev); +DRM_ERROR ("Failed to initialize GuC, error %d\n" , err);return err;
Signature · 6 lines
1.7.9.5 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH v2 13/17 drm/i915: Interrupt routing for GuC submission
In reply to Dave GordonTurn on interrupt steering to route necessary interrupts to GuC.
Issue: VIZ-4884
--- drivers/gpu/drm/i915/i915_reg.h | 11 +++++-- drivers/gpu/drm/i915/intel_guc_loader.c | 51 +++++++++++++++++++++++++++++++ 2 files changed, 60 insertions(+), 2 deletions(-)
drivers/gpu/drm/i915/i915_reg.h +9 -2
@@ -1643,12 +1643,18 @@ enum skl_disp_power_wells {#define GFX_MODE_GEN7 0x0229c#define RING_MODE_GEN7 (ring) ((ring)->mmio_base+0x29c)#define GFX_RUN_LIST_ENABLE (1<<15) +#define GFX_INTERRUPT_STEERING (1<<14)#define GFX_TLB_INVALIDATE_EXPLICIT (1<<13)#define GFX_SURFACE_FAULT_ENABLE (1<<12)#define GFX_REPLAY_MODE (1<<11)#define GFX_PSMI_GRANULARITY (1<<10)#define GFX_PPGTT_ENABLE (1<<9) +#define GFX_FORWARD_VBLANK_MASK (3<<5) +#define GFX_FORWARD_VBLANK_NEVER (0<<5) +#define GFX_FORWARD_VBLANK_ALWAYS (1<<5) +#define GFX_FORWARD_VBLANK_COND (2<<5) +#define VLV_DISPLAY_BASE 0x180000#define VLV_MIPI_BASE VLV_DISPLAY_BASE
@@ -5635,11 +5641,12 @@ enum skl_disp_power_wells {#define GEN8_GT_IIR (which) (0x44308 + (0x10 * (which)))#define GEN8_GT_IER (which) (0x4430c + (0x10 * (which))) -#define GEN8_BCS_IRQ_SHIFT 16#define GEN8_RCS_IRQ_SHIFT 0 -#define GEN8_VCS2_IRQ_SHIFT 16 +#define GEN8_BCS_IRQ_SHIFT 16#define GEN8_VCS1_IRQ_SHIFT 0 +#define GEN8_VCS2_IRQ_SHIFT 16#define GEN8_VECS_IRQ_SHIFT 0 +#define GEN8_WD_IRQ_SHIFT 16#define GEN8_DE_PIPE_ISR (pipe) (0x44400 + (0x10 * (pipe)))#define GEN8_DE_PIPE_IMR (pipe) (0x44404 + (0x10 * (pipe)))
drivers/gpu/drm/i915/intel_guc_loader.c +51 -0
81 lines not on this page · raw message
Signature · 6 lines
1.7.9.5 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH v2 14/17 drm/i915: Integrate GuC-based command submission
In reply to Dave GordonFrom: Alex Dai <[email protected]>
GuC-based submission is mostly the same as execlist mode, up to intel_logical_ring_advance_and_submit(), where the context being dispatched would be added to the execlist queue; at this point we submit the context to the GuC backend instead.
There are, however, a few other changes also required, notably:
1. Contexts must be pinned at GGTT addresses accessible by the GuC i.e. NOT in the range [0..WOPCM_SIZE), so we have to add the PIN_OFFSET_BIAS flag to the relevant GGTT-pinning calls.
2. The GuC's TLB must be invalidated after a context is pinned at a new GGTT address.
3. GuC firmware uses the one page before Ring Context as shared data. Therefore, whenever driver wants to get base address of LRC, we will offset one page for it. LRC_PPHWSP_PN is defined as the page number of LRCA.
4. In the work queue used to pass requests to the GuC, the GuC firmware requires the ring-tail-offset to be represented as an 11-bit value, expressed in QWords. Therefore, the ringbuffer size must be reduced to the representable range (4 pages).
v2:
Defer adding #defines until needed [Chris Wilson] Rationalise type declarations [Chris Wilson]
Issue: VIZ-4884
--- drivers/gpu/drm/i915/i915_debugfs.c | 2 +- drivers/gpu/drm/i915/i915_guc_submission.c | 48 +++++++++++++++++++++++++--- drivers/gpu/drm/i915/intel_guc.h | 1 + drivers/gpu/drm/i915/intel_lrc.c | 48 ++++++++++++++++++++-------- drivers/gpu/drm/i915/intel_lrc.h | 6 ++++ 5 files changed, 87 insertions(+), 18 deletions(-)
drivers/gpu/drm/i915/i915_debugfs.c +1 -1
@@ -1957,7 +1957,7 @@ static void i915_dump_lrc_obj(struct seq_file *m,return ; } - page =i915_gem_object_get_page (ctx_obj,1 ); + page =i915_gem_object_get_page (ctx_obj,LRC_STATE_PN );if (!WARN_ON (page ==NULL )) { reg_state =kmap_atomic (page);
drivers/gpu/drm/i915/i915_guc_submission.c +44 -4
87 lines not on this page · raw message
drivers/gpu/drm/i915/intel_guc.h +1 -0
@@ -30,6 +30,7 @@struct i915_guc_client {struct drm_i915_gem_object *client_obj; +struct intel_context *owner;uint32_t priority;uint32_t ctx_index;
drivers/gpu/drm/i915/intel_lrc.c +35 -13
141 lines not on this page · raw message
drivers/gpu/drm/i915/intel_lrc.h +6 -0
@@ -66,6 +66,12 @@ static inline void intel_logical_ring_emit(struct intel_ringbuffer *ringbuf, }/* Logical Ring Contexts */ + +/* One extra page is added before LRC for GuC as shared data */ +#define LRC_GUCSHR_PN (0) +#define LRC_PPHWSP_PN (LRC_GUCSHR_PN + 1) +#define LRC_STATE_PN (LRC_PPHWSP_PN + 1) +void intel_lr_context_free (struct intel_context *ctx);int intel_lr_context_deferred_create (struct intel_context *ctx,struct intel_engine_cs *ring);
Signature · 6 lines
1.7.9.5 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH v2 15/17 drm/i915: Debugfs interface for GuC submission statistics
In reply to Dave GordonThis provides a means of reading status and counts relating to GuC actions and submissions.
v2:
Remove surplus blank line in output [Chris Wilson]
--- drivers/gpu/drm/i915/i915_debugfs.c | 40 +++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+)
drivers/gpu/drm/i915/i915_debugfs.c +40 -0
@@ -2378,6 +2378,45 @@ static int i915_guc_load_status_info(struct seq_file *m, void *data)return 0 ; } +static int i915_guc_info (struct seq_file *m,void *data) +{ +struct drm_info_node *node = m->private; +struct drm_device *dev = node->minor->dev; +struct drm_i915_private *dev_priv = dev->dev_private; +struct intel_guc guc; +struct i915_guc_client client = { .client_obj =0 }; + +if (!HAS_GUC_SCHED (dev_priv->dev)) +return 0 ; + +/* Take a local copy of the GuC data, so we can dump it at leisure */ +spin_lock (&dev_priv->guc.host2guc_lock); + guc = dev_priv->guc; +if (guc.execbuf_client) { +spin_lock (&guc.execbuf_client->wq_lock); + client = *guc.execbuf_client; +spin_unlock (&guc.execbuf_client->wq_lock); + } +spin_unlock (&dev_priv->guc.host2guc_lock); + +seq_printf (m,"GuC total action count: %llu\n" , guc.action_count); +seq_printf (m,"GuC last action command: 0x%x\n" , guc.action_cmd); +seq_printf (m,"GuC last action status: 0x%x\n" , guc.action_status); + +seq_printf (m,"GuC action failure count: %u\n" , guc.action_fail); +seq_printf (m,"GuC last action error code: %d\n" , guc.action_err); + +seq_printf (m,"\nGuC execbuf client @ %p:\n" , guc.execbuf_client); +seq_printf (m,"\tTotal submissions: %llu\n" , client.submissions); +seq_printf (m,"\tFailed to queue: %u\n" , client.q_fail); +seq_printf (m,"\tFailed doorbell: %u\n" , client.b_fail); +seq_printf (m,"\tLast submission result: %d\n" , client.retcode); + +/* Add more as required ... */ + +return 0 ; +} +static int i915_guc_log_dump (struct seq_file *m,void *data) {struct drm_info_node *node = m->private;
@@ -5106,6 +5145,7 @@ static const struct drm_info_list i915_debugfs_list[] = { {"i915_gem_hws_bsd", i915_hws_info, 0, (void *)VCS}, {"i915_gem_hws_vebox", i915_hws_info, 0, (void *)VECS}, {"i915_gem_batch_pool", i915_gem_batch_pool_info, 0}, + {"i915_guc_info", i915_guc_info, 0}, {"i915_guc_load_status", i915_guc_load_status_info, 0}, {"i915_guc_log_dump", i915_guc_log_dump, 0}, {"i915_frequency_info", i915_frequency_info, 0},
Signature · 6 lines
1.7.9.5 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH v2 16/17 Documentation/drm: kerneldoc for GuC
In reply to Dave GordonFrom: Alex Dai <[email protected]>
Add overview design of GuC, plus some key points related to the implementation.
--- Documentation/DocBook/drm.tmpl | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+)
Documentation/DocBook/drm.tmpl +19 -0
@@ -4218,6 +4218,25 @@ int num_ioctls;</synopsis> </sect2> </sect1> <sect1> + <title>GuC-based Command Submission</title> + <sect2> + <title>Microcontroller (uC) firmware loading support</title> +!Pdrivers/gpu/drm/i915/intel_uc_loader.c Microcontroller (uC) firmware loading support +!Idrivers/gpu/drm/i915/intel_uc_loader.c + </sect2> + <sect2> + <title>GuC</title> +!Pdrivers/gpu/drm/i915/intel_guc_loader.c GuC-specific firmware loader +!Idrivers/gpu/drm/i915/intel_guc_loader.c + </sect2> + <sect2> + <title>GuC Client</title> +!Pdrivers/gpu/drm/i915/intel_guc_submission.c GuC-based command submissison +!Idrivers/gpu/drm/i915/intel_guc_submission.c + </sect2> + </sect1> + + <sect1> <title> Tracing </title> <para> This sections covers all things related to the tracepoints implemented in
Signature · 6 lines
1.7.9.5 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH v2 17/17 drm/i915: Enable GuC submission, where supported
In reply to Dave Gordon--- drivers/gpu/drm/i915/i915_params.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/gpu/drm/i915/i915_params.c +2 -2
@@ -53,7 +53,7 @@ struct i915_params i915 __read_mostly = { .verbose_state_checks = 1, .nuclear_pageflip = 0, .edp_vswing = 0, - .enable_guc_submission = false, + .enable_guc_submission = true, .guc_log_level = -1, };
@@ -190,7 +190,7 @@ MODULE_PARM_DESC(edp_vswing, "2=default swing(400mV))");module_param_named (enable_guc_submission, i915.enable_guc_submission, bool,0400 ); -MODULE_PARM_DESC (enable_guc_submission,"Enable GuC submission (default:false)" ); +MODULE_PARM_DESC (enable_guc_submission,"Enable GuC submission (default:true)" );module_param_named (guc_log_level, i915.guc_log_level, int,0400 ); MODULE_PARM_DESC(guc_log_level,
Signature · 6 lines
1.7.9.5 _______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx