diff options
author | Dave Airlie <airlied@redhat.com> | 2021-08-12 09:43:38 +1000 |
---|---|---|
committer | Dave Airlie <airlied@redhat.com> | 2021-08-12 09:56:04 +1000 |
commit | 25fed6b324ac556859d6dd0b7827cc8fb653ca99 (patch) | |
tree | 3f634521c723d6434c921fc1adbefa0e7d7e4be7 /drivers/gpu/drm/i915/gt/uc | |
parent | 59b9d6baa1bea254d31042c42bcb8f946c263bae (diff) | |
parent | 927dfdd09d8c03ba100ed0c8c3915f8e1d1f5556 (diff) | |
download | linux-25fed6b324ac556859d6dd0b7827cc8fb653ca99.tar.bz2 |
Merge tag 'drm-intel-gt-next-2021-08-06-1' of ssh://git.freedesktop.org/git/drm/drm-intel into drm-next
UAPI Changes:
- Add I915_MMAP_OFFSET_FIXED
On devices with local memory `I915_MMAP_OFFSET_FIXED` is the only valid
type. On devices without local memory, this caching mode is invalid.
As caching mode when specifying `I915_MMAP_OFFSET_FIXED`, WC or WB will
be used, depending on the object placement on creation. WB will be used
when the object can only exist in system memory, WC otherwise.
Userspace: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11888
- Reinstate the mmap ioctl for (already released) integrated Gen12 platforms
Rationale: Otherwise media driver breaks eg. for ADL-P. Long term goal is
still to sunset the IOCTL even for integrated and require using mmap_offset.
- Reject caching/set_domain IOCTLs on discrete
Expected to become immutable property of the BO
- Disallow changing context parameters after first use on Gen12 and earlier
- Require setting context parameters at creation on platforms after Gen12
Rationale (for both): Allow less dynamic changes to the context to simplify
the implementation and avoid user shooting theirselves in the foot.
- Drop I915_CONTEXT_PARAM_RINGSIZE
Userspace PR for compute-driver has not been merged
- Drop I915_CONTEXT_PARAM_NO_ZEROMAP
Userspace PR for libdrm / Beignet was never landed
- Drop CONTEXT_CLONE API
Userspace PR for Mesa was never landed
- Drop getparam support for I915_CONTEXT_PARAM_ENGINES
Only existed for symmetry wrt. setparam, never used.
- Disallow bonding of virtual engines
Drop the prep work, no hardware has been released needing it.
- (Implicit) Disable gpu relocations
Media userspace was the last userspace to still use them. They
have converted so performance can be regained with an update.
Core Changes:
- Merge topic branch 'topic/i915-ttm-2021-06-11' (from Maarten)
- Merge topic branch 'topic/revid_steppings' (from Matt R)
- Merge topic branch 'topic/xehp-dg2-definitions-2021-07-21' (from Matt R)
- Backmerges drm-next (Rodrigo)
Driver Changes:
- Initial workarounds for ADL-P (Clint)
- Preliminary code for XeHP/DG2 (Stuart, Umesh, Matt R, Prathap, Ram,
Venkata, Akeem, Tvrtko, John, Lucas)
- Fix ADL-S DMA mask size to 39 bits (Tejas)
- Remove code for CNL (Lucas)
- Add ADL-P GuC/HuC firmwares (John)
- Update HuC to 7.9.3 for TGL/ADL-S/RKL (John)
- Fix -EDEADLK handling regression (Ville)
- Implement Wa_1508744258 for DG1 and Gen12 iGFX (Jose)
- Extend Wa_1406941453 to ADL-S (Jose)
- Drop unnecessary workarounds per stepping for SKL/BXT/ICL (Matt R)
- Use fuse info to enable SFC on Gen12 (Venkata)
- Unconditionally flush the pages on acquire on EHL/JSL (Matt A)
- Probe existence of backing struct pages upon userptr creation (Chris, Matt A)
- Add an intermediate GEM proto-context to delay real context creation (Jason)
- Implement SINGLE_TIMELINE with a syncobj (Jason)
- Set the watchdog timeout directly in intel_context_set_gem (Jason)
- Disallow userspace from creating contexts with too many engines (Jason)
- Revert "drm/i915/gem: Asynchronous cmdparser" (Jason)
- Revert "drm/i915: Propagate errors on awaiting already signaled fences" (Jason)
- Revert "drm/i915: Skip over MI_NOOP when parsing" (Jason)
- Revert "drm/i915: Shrink the GEM kmem_caches upon idling" (Daniel)
- Always let TTM handle object migration (Jason)
- Correct the locking and pin pattern for dma-buf (Thomas H, Michael R, Jason)
- Migrate to system at dma-buf attach time (Thomas, Michael R)
- MAJOR refactoring of the GuC backend code to allow for enabling on Gen11+
(Matt B, John, Michal Wa., Fernando, Daniele, Vinay)
- Update GuC firmware interface to v62.0.0 (John, Michal Wa., Matt B)
- Add GuCRC feature to hand over the control of HW RC6 to the GuC on
Gen12+ when GuC submission is enabled (Vinay, Sujaritha, Daniele,
John, Tvrtko)
- Use the correct IRQ during resume and eliminate DRM IRQ midlayer (Thomas Z)
- Add pipelined page migration and clearing (Chris, Thomas H)
- Use TTM for system memory on discrete (Thomas H)
- Implement object migration for display vs. dma-buf (Thomas H)
- Perform execbuffer object locking as a separate step (Thomas H)
- Add support for explicit L3BANK steering (Matt, Daniele)
- Remove duplicated call to ops->pread (Daniel)
- Fix pagefault disabling in the first execbuf slowpath (Daniel)
- Simplify userptr locking (Thomas H)
- Improvements to the GuC CTB code (Matt B, John)
- Make GT workaround upper bounds exclusive (Matt R)
- Check for nomodeset in i915_init() first (Daniel)
- Delete now unused gpu reloc code (Daniel)
- Document RFC plans for GuC submission, DRM scheduler and new parallel
submit uAPI (Matt B)
- Reintroduce buddy allocator this time with TTM (Matt A)
- Support forcing page size with LMEM (Matt A)
- Add i915_sched_engine to abstract a submission queue between backends (Matt B)
- Use accelerated move in TTM (Ram)
- Fix memory leaks from TTM backend (Thomas H)
- Introduce WW transaction helper (Thomas H)
- Improve debug Kconfig texts a bit (Daniel)
- Unify user object creation code (Jason)
- Use a table for i915_init/exit (Jason)
- Move slabs to module init/exit (Daniel)
- Remove now unused i915_globals (Daniel)
- Extract i915_module.c (Daniel)
- Consistently use adl-p/adl-s in WA comments (Jose)
- Finish INTEL_GEN and friends conversion (Lucas)
- Correct variable/function namings (Lucas)
- Code checker fixes (Wan, Matt A)
- Tracepoint improvements (Matt B)
- Kerneldoc improvements (Tvrtko, Jason, Matt A, Maarten)
- Selftest improvements (Chris, Matt A, Tejas, Thomas H, John, Matt B,
Rahul, Vinay)
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/YQ0JmYiXhGskNcrI@jlahtine-mobl.ger.corp.intel.com
Diffstat (limited to 'drivers/gpu/drm/i915/gt/uc')
25 files changed, 5470 insertions, 850 deletions
diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h index 90efef8a73e4..8ff582222aff 100644 --- a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h +++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h @@ -6,6 +6,113 @@ #ifndef _ABI_GUC_ACTIONS_ABI_H #define _ABI_GUC_ACTIONS_ABI_H +/** + * DOC: HOST2GUC_REGISTER_CTB + * + * This message is used as part of the `CTB based communication`_ setup. + * + * This message must be sent as `MMIO HXG Message`_. + * + * +---+-------+--------------------------------------------------------------+ + * | | Bits | Description | + * +===+=======+==============================================================+ + * | 0 | 31 | ORIGIN = GUC_HXG_ORIGIN_HOST_ | + * | +-------+--------------------------------------------------------------+ + * | | 30:28 | TYPE = GUC_HXG_TYPE_REQUEST_ | + * | +-------+--------------------------------------------------------------+ + * | | 27:16 | DATA0 = MBZ | + * | +-------+--------------------------------------------------------------+ + * | | 15:0 | ACTION = _`GUC_ACTION_HOST2GUC_REGISTER_CTB` = 0x4505 | + * +---+-------+--------------------------------------------------------------+ + * | 1 | 31:12 | RESERVED = MBZ | + * | +-------+--------------------------------------------------------------+ + * | | 11:8 | **TYPE** - type for the `CT Buffer`_ | + * | | | | + * | | | - _`GUC_CTB_TYPE_HOST2GUC` = 0 | + * | | | - _`GUC_CTB_TYPE_GUC2HOST` = 1 | + * | +-------+--------------------------------------------------------------+ + * | | 7:0 | **SIZE** - size of the `CT Buffer`_ in 4K units minus 1 | + * +---+-------+--------------------------------------------------------------+ + * | 2 | 31:0 | **DESC_ADDR** - GGTT address of the `CTB Descriptor`_ | + * +---+-------+--------------------------------------------------------------+ + * | 3 | 31:0 | **BUFF_ADDF** - GGTT address of the `CT Buffer`_ | + * +---+-------+--------------------------------------------------------------+ + * + * +---+-------+--------------------------------------------------------------+ + * | | Bits | Description | + * +===+=======+==============================================================+ + * | 0 | 31 | ORIGIN = GUC_HXG_ORIGIN_GUC_ | + * | +-------+--------------------------------------------------------------+ + * | | 30:28 | TYPE = GUC_HXG_TYPE_RESPONSE_SUCCESS_ | + * | +-------+--------------------------------------------------------------+ + * | | 27:0 | DATA0 = MBZ | + * +---+-------+--------------------------------------------------------------+ + */ +#define GUC_ACTION_HOST2GUC_REGISTER_CTB 0x4505 + +#define HOST2GUC_REGISTER_CTB_REQUEST_MSG_LEN (GUC_HXG_REQUEST_MSG_MIN_LEN + 3u) +#define HOST2GUC_REGISTER_CTB_REQUEST_MSG_0_MBZ GUC_HXG_REQUEST_MSG_0_DATA0 +#define HOST2GUC_REGISTER_CTB_REQUEST_MSG_1_MBZ (0xfffff << 12) +#define HOST2GUC_REGISTER_CTB_REQUEST_MSG_1_TYPE (0xf << 8) +#define GUC_CTB_TYPE_HOST2GUC 0u +#define GUC_CTB_TYPE_GUC2HOST 1u +#define HOST2GUC_REGISTER_CTB_REQUEST_MSG_1_SIZE (0xff << 0) +#define HOST2GUC_REGISTER_CTB_REQUEST_MSG_2_DESC_ADDR GUC_HXG_REQUEST_MSG_n_DATAn +#define HOST2GUC_REGISTER_CTB_REQUEST_MSG_3_BUFF_ADDR GUC_HXG_REQUEST_MSG_n_DATAn + +#define HOST2GUC_REGISTER_CTB_RESPONSE_MSG_LEN GUC_HXG_RESPONSE_MSG_MIN_LEN +#define HOST2GUC_REGISTER_CTB_RESPONSE_MSG_0_MBZ GUC_HXG_RESPONSE_MSG_0_DATA0 + +/** + * DOC: HOST2GUC_DEREGISTER_CTB + * + * This message is used as part of the `CTB based communication`_ teardown. + * + * This message must be sent as `MMIO HXG Message`_. + * + * +---+-------+--------------------------------------------------------------+ + * | | Bits | Description | + * +===+=======+==============================================================+ + * | 0 | 31 | ORIGIN = GUC_HXG_ORIGIN_HOST_ | + * | +-------+--------------------------------------------------------------+ + * | | 30:28 | TYPE = GUC_HXG_TYPE_REQUEST_ | + * | +-------+--------------------------------------------------------------+ + * | | 27:16 | DATA0 = MBZ | + * | +-------+--------------------------------------------------------------+ + * | | 15:0 | ACTION = _`GUC_ACTION_HOST2GUC_DEREGISTER_CTB` = 0x4506 | + * +---+-------+--------------------------------------------------------------+ + * | 1 | 31:12 | RESERVED = MBZ | + * | +-------+--------------------------------------------------------------+ + * | | 11:8 | **TYPE** - type of the `CT Buffer`_ | + * | | | | + * | | | see `GUC_ACTION_HOST2GUC_REGISTER_CTB`_ | + * | +-------+--------------------------------------------------------------+ + * | | 7:0 | RESERVED = MBZ | + * +---+-------+--------------------------------------------------------------+ + * + * +---+-------+--------------------------------------------------------------+ + * | | Bits | Description | + * +===+=======+==============================================================+ + * | 0 | 31 | ORIGIN = GUC_HXG_ORIGIN_GUC_ | + * | +-------+--------------------------------------------------------------+ + * | | 30:28 | TYPE = GUC_HXG_TYPE_RESPONSE_SUCCESS_ | + * | +-------+--------------------------------------------------------------+ + * | | 27:0 | DATA0 = MBZ | + * +---+-------+--------------------------------------------------------------+ + */ +#define GUC_ACTION_HOST2GUC_DEREGISTER_CTB 0x4506 + +#define HOST2GUC_DEREGISTER_CTB_REQUEST_MSG_LEN (GUC_HXG_REQUEST_MSG_MIN_LEN + 1u) +#define HOST2GUC_DEREGISTER_CTB_REQUEST_MSG_0_MBZ GUC_HXG_REQUEST_MSG_0_DATA0 +#define HOST2GUC_DEREGISTER_CTB_REQUEST_MSG_1_MBZ (0xfffff << 12) +#define HOST2GUC_DEREGISTER_CTB_REQUEST_MSG_1_TYPE (0xf << 8) +#define HOST2GUC_DEREGISTER_CTB_REQUEST_MSG_1_MBZ2 (0xff << 0) + +#define HOST2GUC_DEREGISTER_CTB_RESPONSE_MSG_LEN GUC_HXG_RESPONSE_MSG_MIN_LEN +#define HOST2GUC_DEREGISTER_CTB_RESPONSE_MSG_0_MBZ GUC_HXG_RESPONSE_MSG_0_DATA0 + +/* legacy definitions */ + enum intel_guc_action { INTEL_GUC_ACTION_DEFAULT = 0x0, INTEL_GUC_ACTION_REQUEST_PREEMPTION = 0x2, @@ -17,13 +124,33 @@ enum intel_guc_action { INTEL_GUC_ACTION_FORCE_LOG_BUFFER_FLUSH = 0x302, INTEL_GUC_ACTION_ENTER_S_STATE = 0x501, INTEL_GUC_ACTION_EXIT_S_STATE = 0x502, - INTEL_GUC_ACTION_SLPC_REQUEST = 0x3003, + INTEL_GUC_ACTION_GLOBAL_SCHED_POLICY_CHANGE = 0x506, + INTEL_GUC_ACTION_SCHED_CONTEXT = 0x1000, + INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_SET = 0x1001, + INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_DONE = 0x1002, + INTEL_GUC_ACTION_SCHED_ENGINE_MODE_SET = 0x1003, + INTEL_GUC_ACTION_SCHED_ENGINE_MODE_DONE = 0x1004, + INTEL_GUC_ACTION_SET_CONTEXT_PRIORITY = 0x1005, + INTEL_GUC_ACTION_SET_CONTEXT_EXECUTION_QUANTUM = 0x1006, + INTEL_GUC_ACTION_SET_CONTEXT_PREEMPTION_TIMEOUT = 0x1007, + INTEL_GUC_ACTION_CONTEXT_RESET_NOTIFICATION = 0x1008, + INTEL_GUC_ACTION_ENGINE_FAILURE_NOTIFICATION = 0x1009, + INTEL_GUC_ACTION_SETUP_PC_GUCRC = 0x3004, INTEL_GUC_ACTION_AUTHENTICATE_HUC = 0x4000, + INTEL_GUC_ACTION_REGISTER_CONTEXT = 0x4502, + INTEL_GUC_ACTION_DEREGISTER_CONTEXT = 0x4503, INTEL_GUC_ACTION_REGISTER_COMMAND_TRANSPORT_BUFFER = 0x4505, INTEL_GUC_ACTION_DEREGISTER_COMMAND_TRANSPORT_BUFFER = 0x4506, + INTEL_GUC_ACTION_DEREGISTER_CONTEXT_DONE = 0x4600, + INTEL_GUC_ACTION_RESET_CLIENT = 0x5507, INTEL_GUC_ACTION_LIMIT }; +enum intel_guc_rc_options { + INTEL_GUCRC_HOST_CONTROL, + INTEL_GUCRC_FIRMWARE_CONTROL, +}; + enum intel_guc_preempt_options { INTEL_GUC_PREEMPT_OPTION_DROP_WORK_Q = 0x4, INTEL_GUC_PREEMPT_OPTION_DROP_SUBMIT_Q = 0x8, diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h new file mode 100644 index 000000000000..7a8d4bfc5f6a --- /dev/null +++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h @@ -0,0 +1,235 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ + +#ifndef _GUC_ACTIONS_SLPC_ABI_H_ +#define _GUC_ACTIONS_SLPC_ABI_H_ + +#include <linux/types.h> +#include "i915_reg.h" + +/** + * DOC: SLPC SHARED DATA STRUCTURE + * + * +----+------+--------------------------------------------------------------+ + * | CL | Bytes| Description | + * +====+======+==============================================================+ + * | 1 | 0-3 | SHARED DATA SIZE | + * | +------+--------------------------------------------------------------+ + * | | 4-7 | GLOBAL STATE | + * | +------+--------------------------------------------------------------+ + * | | 8-11 | DISPLAY DATA ADDRESS | + * | +------+--------------------------------------------------------------+ + * | | 12:63| PADDING | + * +----+------+--------------------------------------------------------------+ + * | | 0:63 | PADDING(PLATFORM INFO) | + * +----+------+--------------------------------------------------------------+ + * | 3 | 0-3 | TASK STATE DATA | + * + +------+--------------------------------------------------------------+ + * | | 4:63 | PADDING | + * +----+------+--------------------------------------------------------------+ + * |4-21|0:1087| OVERRIDE PARAMS AND BIT FIELDS | + * +----+------+--------------------------------------------------------------+ + * | | | PADDING + EXTRA RESERVED PAGE | + * +----+------+--------------------------------------------------------------+ + */ + +/* + * SLPC exposes certain parameters for global configuration by the host. + * These are referred to as override parameters, because in most cases + * the host will not need to modify the default values used by SLPC. + * SLPC remembers the default values which allows the host to easily restore + * them by simply unsetting the override. The host can set or unset override + * parameters during SLPC (re-)initialization using the SLPC Reset event. + * The host can also set or unset override parameters on the fly using the + * Parameter Set and Parameter Unset events + */ + +#define SLPC_MAX_OVERRIDE_PARAMETERS 256 +#define SLPC_OVERRIDE_BITFIELD_SIZE \ + (SLPC_MAX_OVERRIDE_PARAMETERS / 32) + +#define SLPC_PAGE_SIZE_BYTES 4096 +#define SLPC_CACHELINE_SIZE_BYTES 64 +#define SLPC_SHARED_DATA_SIZE_BYTE_HEADER SLPC_CACHELINE_SIZE_BYTES +#define SLPC_SHARED_DATA_SIZE_BYTE_PLATFORM_INFO SLPC_CACHELINE_SIZE_BYTES +#define SLPC_SHARED_DATA_SIZE_BYTE_TASK_STATE SLPC_CACHELINE_SIZE_BYTES +#define SLPC_SHARED_DATA_MODE_DEFN_TABLE_SIZE SLPC_PAGE_SIZE_BYTES +#define SLPC_SHARED_DATA_SIZE_BYTE_MAX (2 * SLPC_PAGE_SIZE_BYTES) + +/* + * Cacheline size aligned (Total size needed for + * SLPM_KMD_MAX_OVERRIDE_PARAMETERS=256 is 1088 bytes) + */ +#define SLPC_OVERRIDE_PARAMS_TOTAL_BYTES (((((SLPC_MAX_OVERRIDE_PARAMETERS * 4) \ + + ((SLPC_MAX_OVERRIDE_PARAMETERS / 32) * 4)) \ + + (SLPC_CACHELINE_SIZE_BYTES - 1)) / SLPC_CACHELINE_SIZE_BYTES) * \ + SLPC_CACHELINE_SIZE_BYTES) + +#define SLPC_SHARED_DATA_SIZE_BYTE_OTHER (SLPC_SHARED_DATA_SIZE_BYTE_MAX - \ + (SLPC_SHARED_DATA_SIZE_BYTE_HEADER \ + + SLPC_SHARED_DATA_SIZE_BYTE_PLATFORM_INFO \ + + SLPC_SHARED_DATA_SIZE_BYTE_TASK_STATE \ + + SLPC_OVERRIDE_PARAMS_TOTAL_BYTES \ + + SLPC_SHARED_DATA_MODE_DEFN_TABLE_SIZE)) + +enum slpc_task_enable { + SLPC_PARAM_TASK_DEFAULT = 0, + SLPC_PARAM_TASK_ENABLED, + SLPC_PARAM_TASK_DISABLED, + SLPC_PARAM_TASK_UNKNOWN +}; + +enum slpc_global_state { + SLPC_GLOBAL_STATE_NOT_RUNNING = 0, + SLPC_GLOBAL_STATE_INITIALIZING = 1, + SLPC_GLOBAL_STATE_RESETTING = 2, + SLPC_GLOBAL_STATE_RUNNING = 3, + SLPC_GLOBAL_STATE_SHUTTING_DOWN = 4, + SLPC_GLOBAL_STATE_ERROR = 5 +}; + +enum slpc_param_id { + SLPC_PARAM_TASK_ENABLE_GTPERF = 0, + SLPC_PARAM_TASK_DISABLE_GTPERF = 1, + SLPC_PARAM_TASK_ENABLE_BALANCER = 2, + SLPC_PARAM_TASK_DISABLE_BALANCER = 3, + SLPC_PARAM_TASK_ENABLE_DCC = 4, + SLPC_PARAM_TASK_DISABLE_DCC = 5, + SLPC_PARAM_GLOBAL_MIN_GT_UNSLICE_FREQ_MHZ = 6, + SLPC_PARAM_GLOBAL_MAX_GT_UNSLICE_FREQ_MHZ = 7, + SLPC_PARAM_GLOBAL_MIN_GT_SLICE_FREQ_MHZ = 8, + SLPC_PARAM_GLOBAL_MAX_GT_SLICE_FREQ_MHZ = 9, + SLPC_PARAM_GTPERF_THRESHOLD_MAX_FPS = 10, + SLPC_PARAM_GLOBAL_DISABLE_GT_FREQ_MANAGEMENT = 11, + SLPC_PARAM_GTPERF_ENABLE_FRAMERATE_STALLING = 12, + SLPC_PARAM_GLOBAL_DISABLE_RC6_MODE_CHANGE = 13, + SLPC_PARAM_GLOBAL_OC_UNSLICE_FREQ_MHZ = 14, + SLPC_PARAM_GLOBAL_OC_SLICE_FREQ_MHZ = 15, + SLPC_PARAM_GLOBAL_ENABLE_IA_GT_BALANCING = 16, + SLPC_PARAM_GLOBAL_ENABLE_ADAPTIVE_BURST_TURBO = 17, + SLPC_PARAM_GLOBAL_ENABLE_EVAL_MODE = 18, + SLPC_PARAM_GLOBAL_ENABLE_BALANCER_IN_NON_GAMING_MODE = 19, + SLPC_PARAM_GLOBAL_RT_MODE_TURBO_FREQ_DELTA_MHZ = 20, + SLPC_PARAM_PWRGATE_RC_MODE = 21, + SLPC_PARAM_EDR_MODE_COMPUTE_TIMEOUT_MS = 22, + SLPC_PARAM_EDR_QOS_FREQ_MHZ = 23, + SLPC_PARAM_MEDIA_FF_RATIO_MODE = 24, + SLPC_PARAM_ENABLE_IA_FREQ_LIMITING = 25, + SLPC_PARAM_STRATEGIES = 26, + SLPC_PARAM_POWER_PROFILE = 27, + SLPC_PARAM_IGNORE_EFFICIENT_FREQUENCY = 28, + SLPC_MAX_PARAM = 32, +}; + +enum slpc_event_id { + SLPC_EVENT_RESET = 0, + SLPC_EVENT_SHUTDOWN = 1, + SLPC_EVENT_PLATFORM_INFO_CHANGE = 2, + SLPC_EVENT_DISPLAY_MODE_CHANGE = 3, + SLPC_EVENT_FLIP_COMPLETE = 4, + SLPC_EVENT_QUERY_TASK_STATE = 5, + SLPC_EVENT_PARAMETER_SET = 6, + SLPC_EVENT_PARAMETER_UNSET = 7, +}; + +struct slpc_task_state_data { + union { + u32 task_status_padding; + struct { + u32 status; +#define SLPC_GTPERF_TASK_ENABLED REG_BIT(0) +#define SLPC_DCC_TASK_ENABLED REG_BIT(11) +#define SLPC_IN_DCC REG_BIT(12) +#define SLPC_BALANCER_ENABLED REG_BIT(15) +#define SLPC_IBC_TASK_ENABLED REG_BIT(16) +#define SLPC_BALANCER_IA_LMT_ENABLED REG_BIT(17) +#define SLPC_BALANCER_IA_LMT_ACTIVE REG_BIT(18) + }; + }; + union { + u32 freq_padding; + struct { +#define SLPC_MAX_UNSLICE_FREQ_MASK REG_GENMASK(7, 0) +#define SLPC_MIN_UNSLICE_FREQ_MASK REG_GENMASK(15, 8) +#define SLPC_MAX_SLICE_FREQ_MASK REG_GENMASK(23, 16) +#define SLPC_MIN_SLICE_FREQ_MASK REG_GENMASK(31, 24) + u32 freq; + }; + }; +} __packed; + +struct slpc_shared_data_header { + /* Total size in bytes of this shared buffer. */ + u32 size; + u32 global_state; + u32 display_data_addr; +} __packed; + +struct slpc_override_params { + u32 bits[SLPC_OVERRIDE_BITFIELD_SIZE]; + u32 values[SLPC_MAX_OVERRIDE_PARAMETERS]; +} __packed; + +struct slpc_shared_data { + struct slpc_shared_data_header header; + u8 shared_data_header_pad[SLPC_SHARED_DATA_SIZE_BYTE_HEADER - + sizeof(struct slpc_shared_data_header)]; + + u8 platform_info_pad[SLPC_SHARED_DATA_SIZE_BYTE_PLATFORM_INFO]; + + struct slpc_task_state_data task_state_data; + u8 task_state_data_pad[SLPC_SHARED_DATA_SIZE_BYTE_TASK_STATE - + sizeof(struct slpc_task_state_data)]; + + struct slpc_override_params override_params; + u8 override_params_pad[SLPC_OVERRIDE_PARAMS_TOTAL_BYTES - + sizeof(struct slpc_override_params)]; + + u8 shared_data_pad[SLPC_SHARED_DATA_SIZE_BYTE_OTHER]; + + /* PAGE 2 (4096 bytes), mode based parameter will be removed soon */ + u8 reserved_mode_definition[4096]; +} __packed; + +/** + * DOC: SLPC H2G MESSAGE FORMAT + * + * +---+-------+--------------------------------------------------------------+ + * | | Bits | Description | + * +===+=======+==============================================================+ + * | 0 | 31 | ORIGIN = GUC_HXG_ORIGIN_HOST_ | + * | +-------+--------------------------------------------------------------+ + * | | 30:28 | TYPE = GUC_HXG_TYPE_REQUEST_ | + * | +-------+--------------------------------------------------------------+ + * | | 27:16 | DATA0 = MBZ | + * | +-------+--------------------------------------------------------------+ + * | | 15:0 | ACTION = _`GUC_ACTION_HOST2GUC_PC_SLPM_REQUEST` = 0x3003 | + * +---+-------+--------------------------------------------------------------+ + * | 1 | 31:8 | **EVENT_ID** | + * + +-------+--------------------------------------------------------------+ + * | | 7:0 | **EVENT_ARGC** - number of data arguments | + * +---+-------+--------------------------------------------------------------+ + * | 2 | 31:0 | **EVENT_DATA1** | + * +---+-------+--------------------------------------------------------------+ + * |...| 31:0 | ... | + * +---+-------+--------------------------------------------------------------+ + * |2+n| 31:0 | **EVENT_DATAn** | + * +---+-------+--------------------------------------------------------------+ + */ + +#define GUC_ACTION_HOST2GUC_PC_SLPC_REQUEST 0x3003 + +#define HOST2GUC_PC_SLPC_REQUEST_MSG_MIN_LEN \ + (GUC_HXG_REQUEST_MSG_MIN_LEN + 1u) +#define HOST2GUC_PC_SLPC_EVENT_MAX_INPUT_ARGS 9 +#define HOST2GUC_PC_SLPC_REQUEST_MSG_MAX_LEN \ + (HOST2GUC_PC_SLPC_REQUEST_REQUEST_MSG_MIN_LEN + \ + HOST2GUC_PC_SLPC_EVENT_MAX_INPUT_ARGS) +#define HOST2GUC_PC_SLPC_REQUEST_MSG_0_MBZ GUC_HXG_REQUEST_MSG_0_DATA0 +#define HOST2GUC_PC_SLPC_REQUEST_MSG_1_EVENT_ID (0xff << 8) +#define HOST2GUC_PC_SLPC_REQUEST_MSG_1_EVENT_ARGC (0xff << 0) +#define HOST2GUC_PC_SLPC_REQUEST_MSG_N_EVENT_DATA_N GUC_HXG_REQUEST_MSG_n_DATAn + +#endif diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_ctb_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_ctb_abi.h index d38935f47ecf..99e1fad5ca20 100644 --- a/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_ctb_abi.h +++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_ctb_abi.h @@ -7,6 +7,111 @@ #define _ABI_GUC_COMMUNICATION_CTB_ABI_H #include <linux/types.h> +#include <linux/build_bug.h> + +#include "guc_messages_abi.h" + +/** + * DOC: CT Buffer + * + * Circular buffer used to send `CTB Message`_ + */ + +/** + * DOC: CTB Descriptor + * + * +---+-------+--------------------------------------------------------------+ + * | | Bits | Description | + * +===+=======+==============================================================+ + * | 0 | 31:0 | **HEAD** - offset (in dwords) to the last dword that was | + * | | | read from the `CT Buffer`_. | + * | | | It can only be updated by the receiver. | + * +---+-------+--------------------------------------------------------------+ + * | 1 | 31:0 | **TAIL** - offset (in dwords) to the last dword that was | + * | | | written to the `CT Buffer`_. | + * | | | It can only be updated by the sender. | + * +---+-------+--------------------------------------------------------------+ + * | 2 | 31:0 | **STATUS** - status of the CTB | + * | | | | + * | | | - _`GUC_CTB_STATUS_NO_ERROR` = 0 (normal operation) | + * | | | - _`GUC_CTB_STATUS_OVERFLOW` = 1 (head/tail too large) | + * | | | - _`GUC_CTB_STATUS_UNDERFLOW` = 2 (truncated message) | + * | | | - _`GUC_CTB_STATUS_MISMATCH` = 4 (head/tail modified) | + * +---+-------+--------------------------------------------------------------+ + * |...| | RESERVED = MBZ | + * +---+-------+--------------------------------------------------------------+ + * | 15| 31:0 | RESERVED = MBZ | + * +---+-------+--------------------------------------------------------------+ + */ + +struct guc_ct_buffer_desc { + u32 head; + u32 tail; + u32 status; +#define GUC_CTB_STATUS_NO_ERROR 0 +#define GUC_CTB_STATUS_OVERFLOW (1 << 0) +#define GUC_CTB_STATUS_UNDERFLOW (1 << 1) +#define GUC_CTB_STATUS_MISMATCH (1 << 2) + u32 reserved[13]; +} __packed; +static_assert(sizeof(struct guc_ct_buffer_desc) == 64); + +/** + * DOC: CTB Message + * + * +---+-------+--------------------------------------------------------------+ + * | | Bits | Description | + * +===+=======+==============================================================+ + * | 0 | 31:16 | **FENCE** - message identifier | + * | +-------+--------------------------------------------------------------+ + * | | 15:12 | **FORMAT** - format of the CTB message | + * | | | - _`GUC_CTB_FORMAT_HXG` = 0 - see `CTB HXG Message`_ | + * | +-------+--------------------------------------------------------------+ + * | | 11:8 | **RESERVED** | + * | +-------+--------------------------------------------------------------+ + * | | 7:0 | **NUM_DWORDS** - length of the CTB message (w/o header) | + * +---+-------+--------------------------------------------------------------+ + * | 1 | 31:0 | optional (depends on FORMAT) | + * +---+-------+ | + * |...| | | + * +---+-------+ | + * | n | 31:0 | | + * +---+-------+--------------------------------------------------------------+ + */ + +#define GUC_CTB_HDR_LEN 1u +#define GUC_CTB_MSG_MIN_LEN GUC_CTB_HDR_LEN +#define GUC_CTB_MSG_MAX_LEN 256u +#define GUC_CTB_MSG_0_FENCE (0xffff << 16) +#define GUC_CTB_MSG_0_FORMAT (0xf << 12) +#define GUC_CTB_FORMAT_HXG 0u +#define GUC_CTB_MSG_0_RESERVED (0xf << 8) +#define GUC_CTB_MSG_0_NUM_DWORDS (0xff << 0) + +/** + * DOC: CTB HXG Message + * + * +---+-------+--------------------------------------------------------------+ + * | | Bits | Description | + * +===+=======+==============================================================+ + * | 0 | 31:16 | FENCE | + * | +-------+--------------------------------------------------------------+ + * | | 15:12 | FORMAT = GUC_CTB_FORMAT_HXG_ | + * | +-------+--------------------------------------------------------------+ + * | | 11:8 | RESERVED = MBZ | + * | +-------+--------------------------------------------------------------+ + * | | 7:0 | NUM_DWORDS = length (in dwords) of the embedded HXG message | + * +---+-------+--------------------------------------------------------------+ + * | 1 | 31:0 | +--------------------------------------------------------+ | + * +---+-------+ | | | + * |...| | | Embedded `HXG Message`_ | | + * +---+-------+ | | | + * | n | 31:0 | +--------------------------------------------------------+ | + * +---+-------+--------------------------------------------------------------+ + */ + +#define GUC_CTB_HXG_MSG_MIN_LEN (GUC_CTB_MSG_MIN_LEN + GUC_HXG_MSG_MIN_LEN) +#define GUC_CTB_HXG_MSG_MAX_LEN GUC_CTB_MSG_MAX_LEN /** * DOC: CTB based communication @@ -61,28 +166,6 @@ */ /* - * Describes single command transport buffer. - * Used by both guc-master and clients. - */ -struct guc_ct_buffer_desc { - u32 addr; /* gfx address */ - u64 host_private; /* host private data */ - u32 size; /* size in bytes */ - u32 head; /* offset updated by GuC*/ - u32 tail; /* offset updated by owner */ - u32 is_in_error; /* error indicator */ - u32 reserved1; - u32 reserved2; - u32 owner; /* id of the channel owner */ - u32 owner_sub_id; /* owner-defined field for extra tracking */ - u32 reserved[5]; -} __packed; - -/* Type of command transport buffer */ -#define INTEL_GUC_CT_BUFFER_TYPE_SEND 0x0u -#define INTEL_GUC_CT_BUFFER_TYPE_RECV 0x1u - -/* * Definition of the command transport message header (DW0) * * bit[4..0] message len (in dwords) diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_mmio_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_mmio_abi.h index be066a62e9e0..bbf1ddb77434 100644 --- a/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_mmio_abi.h +++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_mmio_abi.h @@ -7,46 +7,43 @@ #define _ABI_GUC_COMMUNICATION_MMIO_ABI_H /** - * DOC: MMIO based communication + * DOC: GuC MMIO based communication * - * The MMIO based communication between Host and GuC uses software scratch - * registers, where first register holds data treated as message header, - * and other registers are used to hold message payload. + * The MMIO based communication between Host and GuC relies on special + * hardware registers which format could be defined by the software + * (so called scratch registers). * - * For Gen9+, GuC uses software scratch registers 0xC180-0xC1B8, - * but no H2G command takes more than 8 parameters and the GuC FW - * itself uses an 8-element array to store the H2G message. + * Each MMIO based message, both Host to GuC (H2G) and GuC to Host (G2H) + * messages, which maximum length depends on number of available scratch + * registers, is directly written into those scratch registers. * - * +-----------+---------+---------+---------+ - * | MMIO[0] | MMIO[1] | ... | MMIO[n] | - * +-----------+---------+---------+---------+ - * | header | optional payload | - * +======+====+=========+=========+=========+ - * | 31:28|type| | | | - * +------+----+ | | | - * | 27:16|data| | | | - * +------+----+ | | | - * | 15:0|code| | | | - * +------+----+---------+---------+---------+ + * For Gen9+, there are 16 software scratch registers 0xC180-0xC1B8, + * but no H2G command takes more than 4 parameters and the GuC firmware + * itself uses an 4-element array to store the H2G message. * - * The message header consists of: + * For Gen11+, there are additional 4 registers 0x190240-0x19024C, which + * are, regardless on lower count, preferred over legacy ones. * - * - **type**, indicates message type - * - **code**, indicates message code, is specific for **type** - * - **data**, indicates message data, optional, depends on **code** - * - * The following message **types** are supported: - * - * - **REQUEST**, indicates Host-to-GuC request, requested GuC action code - * must be priovided in **code** field. Optional action specific parameters - * can be provided in remaining payload registers or **data** field. - * - * - **RESPONSE**, indicates GuC-to-Host response from earlier GuC request, - * action response status will be provided in **code** field. Optional - * response data can be returned in remaining payload registers or **data** - * field. + * The MMIO based communication is mainly used during driver initialization + * phase to setup the `CTB based communication`_ that will be used afterwards. */ -#define GUC_MAX_MMIO_MSG_LEN 8 +#define GUC_MAX_MMIO_MSG_LEN 4 + +/** + * DOC: MMIO HXG Message + * + * Format of the MMIO messages follows definitions of `HXG Message`_. + * + * +---+-------+--------------------------------------------------------------+ + * | | Bits | Description | + * +===+=======+==============================================================+ + * | 0 | 31:0 | +--------------------------------------------------------+ | + * +---+-------+ | | | + * |...| | | Embedded `HXG Message`_ | | + * +---+-------+ | | | + * | n | 31:0 | +--------------------------------------------------------+ | + * +---+-------+--------------------------------------------------------------+ + */ #endif /* _ABI_GUC_COMMUNICATION_MMIO_ABI_H */ diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_messages_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_messages_abi.h index 775e21f3058c..29ac823acd4c 100644 --- a/drivers/gpu/drm/i915/gt/uc/abi/guc_messages_abi.h +++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_messages_abi.h @@ -6,6 +6,219 @@ #ifndef _ABI_GUC_MESSAGES_ABI_H #define _ABI_GUC_MESSAGES_ABI_H +/** + * DOC: HXG Message + * + * All messages exchanged with GuC are defined using 32 bit dwords. + * First dword is treated as a message header. Remaining dwords are optional. + * + * +---+-------+--------------------------------------------------------------+ + * | | Bits | Description | + * +===+=======+==============================================================+ + * | | | | + * | 0 | 31 | **ORIGIN** - originator of the message | + * | | | - _`GUC_HXG_ORIGIN_HOST` = 0 | + * | | | - _`GUC_HXG_ORIGIN_GUC` = 1 | + * | | | | + * | +-------+--------------------------------------------------------------+ + * | | 30:28 | **TYPE** - message type | + * | | | - _`GUC_HXG_TYPE_REQUEST` = 0 | + * | | | - _`GUC_HXG_TYPE_EVENT` = 1 | + * | | | - _`GUC_HXG_TYPE_NO_RESPONSE_BUSY` = 3 | + * | | | - _`GUC_HXG_TYPE_NO_RESPONSE_RETRY` = 5 | + * | | | - _`GUC_HXG_TYPE_RESPONSE_FAILURE` = 6 | + * | | | - _`GUC_HXG_TYPE_RESPONSE_SUCCESS` = 7 | + * | +-------+--------------------------------------------------------------+ + * | | 27:0 | **AUX** - auxiliary data (depends on TYPE) | + * +---+-------+--------------------------------------------------------------+ + * | 1 | 31:0 | | + * +---+-------+ | + * |...| | **PAYLOAD** - optional payload (depends on TYPE) | + * +---+-------+ | + * | n | 31:0 | | + * +---+-------+--------------------------------------------------------------+ + */ + +#define GUC_HXG_MSG_MIN_LEN 1u +#define GUC_HXG_MSG_0_ORIGIN (0x1 << 31) +#define GUC_HXG_ORIGIN_HOST 0u +#define GUC_HXG_ORIGIN_GUC 1u +#define GUC_HXG_MSG_0_TYPE (0x7 << 28) +#define GUC_HXG_TYPE_REQUEST 0u +#define GUC_HXG_TYPE_EVENT 1u +#define GUC_HXG_TYPE_NO_RESPONSE_BUSY 3u +#define GUC_HXG_TYPE_NO_RESPONSE_RETRY 5u +#define GUC_HXG_TYPE_RESPONSE_FAILURE 6u +#define GUC_HXG_TYPE_RESPONSE_SUCCESS 7u +#define GUC_HXG_MSG_0_AUX (0xfffffff << 0) +#define GUC_HXG_MSG_n_PAYLOAD (0xffffffff << 0) + +/** + * DOC: HXG Request + * + * The `HXG Request`_ message should be used to initiate synchronous activity + * for which confirmation or return data is expected. + * + * The recipient of this message shall use `HXG Response`_, `HXG Failure`_ + * or `HXG Retry`_ message as a definite reply, and may use `HXG Busy`_ + * message as a intermediate reply. + * + * Format of @DATA0 and all @DATAn fields depends on the @ACTION code. + * + * +---+-------+--------------------------------------------------------------+ + * | | Bits | Description | + * +===+=======+==============================================================+ + * | 0 | 31 | ORIGIN | + * | +-------+--------------------------------------------------------------+ + * | | 30:28 | TYPE = GUC_HXG_TYPE_REQUEST_ | + * | +-------+--------------------------------------------------------------+ + * | | 27:16 | **DATA0** - request data (depends on ACTION) | + * | +-------+--------------------------------------------------------------+ + * | | 15:0 | **ACTION** - requested action code | + * +---+-------+--------------------------------------------------------------+ + * | 1 | 31:0 | | + * +---+-------+ | + * |...| | **DATAn** - optional data (depends on ACTION) | + * +---+-------+ | + * | n | 31:0 | | + * +---+-------+--------------------------------------------------------------+ + */ + +#define GUC_HXG_REQUEST_MSG_MIN_LEN GUC_HXG_MSG_MIN_LEN +#define GUC_HXG_REQUEST_MSG_0_DATA0 (0xfff << 16) +#define GUC_HXG_REQUEST_MSG_0_ACTION (0xffff << 0) +#define GUC_HXG_REQUEST_MSG_n_DATAn GUC_HXG_MSG_n_PAYLOAD + +/** + * DOC: HXG Event + * + * The `HXG Event`_ message should be used to initiate asynchronous activity + * that does not involves immediate confirmation nor data. + * + * Format of @DATA0 and all @DATAn fields depends on the @ACTION code. + * + * +---+-------+--------------------------------------------------------------+ + * | | Bits | Description | + * +===+=======+==============================================================+ + * | 0 | 31 | ORIGIN | + * | +-------+--------------------------------------------------------------+ + * | | 30:28 | TYPE = GUC_HXG_TYPE_EVENT_ | + * | +-------+--------------------------------------------------------------+ + * | | 27:16 | **DATA0** - event data (depends on ACTION) | + * | +-------+--------------------------------------------------------------+ + * | | 15:0 | **ACTION** - event action code | + * +---+-------+--------------------------------------------------------------+ + * | 1 | 31:0 | | + * +---+-------+ | + * |...| | **DATAn** - optional event data (depends on ACTION) | + * +---+-------+ | + * | n | 31:0 | | + * +---+-------+--------------------------------------------------------------+ + */ + +#define GUC_HXG_EVENT_MSG_MIN_LEN GUC_HXG_MSG_MIN_LEN +#define GUC_HXG_EVENT_MSG_0_DATA0 (0xfff << 16) +#define GUC_HXG_EVENT_MSG_0_ACTION (0xffff << 0) +#define GUC_HXG_EVENT_MSG_n_DATAn GUC_HXG_MSG_n_PAYLOAD + +/** + * DOC: HXG Busy + * + * The `HXG Busy`_ message may be used to acknowledge reception of the `HXG Request`_ + * message if the recipient expects that it processing will be longer than default + * timeout. + * + * The @COUNTER field may be used as a progress indicator. + * + * +---+-------+--------------------------------------------------------------+ + * | | Bits | Description | + * +===+=======+==============================================================+ + * | 0 | 31 | ORIGIN | + * | +-------+--------------------------------------------------------------+ + * | | 30:28 | TYPE = GUC_HXG_TYPE_NO_RESPONSE_BUSY_ | + * | +-------+--------------------------------------------------------------+ + * | | 27:0 | **COUNTER** - progress indicator | + * +---+-------+--------------------------------------------------------------+ + */ + +#define GUC_HXG_BUSY_MSG_LEN GUC_HXG_MSG_MIN_LEN +#define GUC_HXG_BUSY_MSG_0_COUNTER GUC_HXG_MSG_0_AUX + +/** + * DOC: HXG Retry + * + * The `HXG Retry`_ message should be used by recipient to indicate that the + * `HXG Request`_ message was dropped and it should be resent again. + * + * The @REASON field may be used to provide additional information. + * + * +---+-------+--------------------------------------------------------------+ + * | | Bits | Description | + * +===+=======+==============================================================+ + * | 0 | 31 | ORIGIN | + * | +-------+--------------------------------------------------------------+ + * | | 30:28 | TYPE = GUC_HXG_TYPE_NO_RESPONSE_RETRY_ | + * | +-------+--------------------------------------------------------------+ + * | | 27:0 | **REASON** - reason for retry | + * | | | - _`GUC_HXG_RETRY_REASON_UNSPECIFIED` = 0 | + * +---+-------+--------------------------------------------------------------+ + */ + +#define GUC_HXG_RETRY_MSG_LEN GUC_HXG_MSG_MIN_LEN +#define GUC_HXG_RETRY_MSG_0_REASON GUC_HXG_MSG_0_AUX +#define GUC_HXG_RETRY_REASON_UNSPECIFIED 0u + +/** + * DOC: HXG Failure + * + * The `HXG Failure`_ message shall be used as a reply to the `HXG Request`_ + * message that could not be processed due to an error. + * + * +---+-------+--------------------------------------------------------------+ + * | | Bits | Description | + * +===+=======+==============================================================+ + * | 0 | 31 | ORIGIN | + * | +-------+--------------------------------------------------------------+ + * | | 30:28 | TYPE = GUC_HXG_TYPE_RESPONSE_FAILURE_ | + * | +-------+--------------------------------------------------------------+ + * | | 27:16 | **HINT** - additional error hint | + * | +-------+--------------------------------------------------------------+ + * | | 15:0 | **ERROR** - error/result code | + * +---+-------+--------------------------------------------------------------+ + */ + +#define GUC_HXG_FAILURE_MSG_LEN GUC_HXG_MSG_MIN_LEN +#define GUC_HXG_FAILURE_MSG_0_HINT (0xfff << 16) +#define GUC_HXG_FAILURE_MSG_0_ERROR (0xffff << 0) + +/** + * DOC: HXG Response + * + * The `HXG Response`_ message shall be used as a reply to the `HXG Request`_ + * message that was successfully processed without an error. + * + * +---+-------+--------------------------------------------------------------+ + * | | Bits | Description | + * +===+=======+==============================================================+ + * | 0 | 31 | ORIGIN | + * | +-------+--------------------------------------------------------------+ + * | | 30:28 | TYPE = GUC_HXG_TYPE_RESPONSE_SUCCESS_ | + * | +-------+--------------------------------------------------------------+ + * | | 27:0 | **DATA0** - data (depends on ACTION from `HXG Request`_) | + * +---+-------+--------------------------------------------------------------+ + * | 1 | 31:0 | | + * +---+-------+ | + * |...| | **DATAn** - data (depends on ACTION from `HXG Request`_) | + * +---+-------+ | + * | n | 31:0 | | + * +---+-------+--------------------------------------------------------------+ + */ + +#define GUC_HXG_RESPONSE_MSG_MIN_LEN GUC_HXG_MSG_MIN_LEN +#define GUC_HXG_RESPONSE_MSG_0_DATA0 GUC_HXG_MSG_0_AUX +#define GUC_HXG_RESPONSE_MSG_n_DATAn GUC_HXG_MSG_n_PAYLOAD + +/* deprecated */ #define INTEL_GUC_MSG_TYPE_SHIFT 28 #define INTEL_GUC_MSG_TYPE_MASK (0xF << INTEL_GUC_MSG_TYPE_SHIFT) #define INTEL_GUC_MSG_DATA_SHIFT 16 diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c index f147cb389a20..fbfcae727d7f 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c @@ -7,6 +7,7 @@ #include "gt/intel_gt_irq.h" #include "gt/intel_gt_pm_irq.h" #include "intel_guc.h" +#include "intel_guc_slpc.h" #include "intel_guc_ads.h" #include "intel_guc_submission.h" #include "i915_drv.h" @@ -157,6 +158,8 @@ void intel_guc_init_early(struct intel_guc *guc) intel_guc_ct_init_early(&guc->ct); intel_guc_log_init_early(&guc->log); intel_guc_submission_init_early(guc); + intel_guc_slpc_init_early(&guc->slpc); + intel_guc_rc_init_early(guc); mutex_init(&guc->send_mutex); spin_lock_init(&guc->irq_lock); @@ -180,6 +183,11 @@ void intel_guc_init_early(struct intel_guc *guc) } } +void intel_guc_init_late(struct intel_guc *guc) +{ + intel_guc_ads_init_late(guc); +} + static u32 guc_ctl_debug_flags(struct intel_guc *guc) { u32 level = intel_guc_log_get_level(&guc->log); @@ -201,6 +209,9 @@ static u32 guc_ctl_feature_flags(struct intel_guc *guc) if (!intel_guc_submission_is_used(guc)) flags |= GUC_CTL_DISABLE_SCHEDULER; + if (intel_guc_slpc_is_used(guc)) + flags |= GUC_CTL_ENABLE_SLPC; + return flags; } @@ -219,24 +230,19 @@ static u32 guc_ctl_log_params_flags(struct intel_guc *guc) BUILD_BUG_ON(!CRASH_BUFFER_SIZE); BUILD_BUG_ON(!IS_ALIGNED(CRASH_BUFFER_SIZE, UNIT)); - BUILD_BUG_ON(!DPC_BUFFER_SIZE); - BUILD_BUG_ON(!IS_ALIGNED(DPC_BUFFER_SIZE, UNIT)); - BUILD_BUG_ON(!ISR_BUFFER_SIZE); - BUILD_BUG_ON(!IS_ALIGNED(ISR_BUFFER_SIZE, UNIT)); + BUILD_BUG_ON(!DEBUG_BUFFER_SIZE); + BUILD_BUG_ON(!IS_ALIGNED(DEBUG_BUFFER_SIZE, UNIT)); BUILD_BUG_ON((CRASH_BUFFER_SIZE / UNIT - 1) > (GUC_LOG_CRASH_MASK >> GUC_LOG_CRASH_SHIFT)); - BUILD_BUG_ON((DPC_BUFFER_SIZE / UNIT - 1) > - (GUC_LOG_DPC_MASK >> GUC_LOG_DPC_SHIFT)); - BUILD_BUG_ON((ISR_BUFFER_SIZE / UNIT - 1) > - (GUC_LOG_ISR_MASK >> GUC_LOG_ISR_SHIFT)); + BUILD_BUG_ON((DEBUG_BUFFER_SIZE / UNIT - 1) > + (GUC_LOG_DEBUG_MASK >> GUC_LOG_DEBUG_SHIFT)); flags = GUC_LOG_VALID | GUC_LOG_NOTIFY_ON_HALF_FULL | FLAG | ((CRASH_BUFFER_SIZE / UNIT - 1) << GUC_LOG_CRASH_SHIFT) | - ((DPC_BUFFER_SIZE / UNIT - 1) << GUC_LOG_DPC_SHIFT) | - ((ISR_BUFFER_SIZE / UNIT - 1) << GUC_LOG_ISR_SHIFT) | + ((DEBUG_BUFFER_SIZE / UNIT - 1) << GUC_LOG_DEBUG_SHIFT) | (offset << GUC_LOG_BUF_ADDR_SHIFT); #undef UNIT @@ -331,6 +337,12 @@ int intel_guc_init(struct intel_guc *guc) goto err_ct; } + if (intel_guc_slpc_is_used(guc)) { + ret = intel_guc_slpc_init(&guc->slpc); + if (ret) + goto err_submission; + } + /* now that everything is perma-pinned, initialize the parameters */ guc_init_params(guc); @@ -341,6 +353,8 @@ int intel_guc_init(struct intel_guc *guc) return 0; +err_submission: + intel_guc_submission_fini(guc); err_ct: intel_guc_ct_fini(&guc->ct); err_ads: @@ -363,6 +377,9 @@ void intel_guc_fini(struct intel_guc *guc) i915_ggtt_disable_guc(gt->ggtt); + if (intel_guc_slpc_is_used(guc)) + intel_guc_slpc_fini(&guc->slpc); + if (intel_guc_submission_is_used(guc)) intel_guc_submission_fini(guc); @@ -376,29 +393,27 @@ void intel_guc_fini(struct intel_guc *guc) /* * This function implements the MMIO based host to GuC interface. */ -int intel_guc_send_mmio(struct intel_guc *guc, const u32 *action, u32 len, +int intel_guc_send_mmio(struct intel_guc *guc, const u32 *request, u32 len, u32 *response_buf, u32 response_buf_size) { + struct drm_i915_private *i915 = guc_to_gt(guc)->i915; struct intel_uncore *uncore = guc_to_gt(guc)->uncore; - u32 status; + u32 header; int i; int ret; GEM_BUG_ON(!len); GEM_BUG_ON(len > guc->send_regs.count); - /* We expect only action code */ - GEM_BUG_ON(*action & ~INTEL_GUC_MSG_CODE_MASK); - - /* If CT is available, we expect to use MMIO only during init/fini */ - GEM_BUG_ON(*action != INTEL_GUC_ACTION_REGISTER_COMMAND_TRANSPORT_BUFFER && - *action != INTEL_GUC_ACTION_DEREGISTER_COMMAND_TRANSPORT_BUFFER); + GEM_BUG_ON(FIELD_GET(GUC_HXG_MSG_0_ORIGIN, request[0]) != GUC_HXG_ORIGIN_HOST); + GEM_BUG_ON(FIELD_GET(GUC_HXG_MSG_0_TYPE, request[0]) != GUC_HXG_TYPE_REQUEST); mutex_lock(&guc->send_mutex); intel_uncore_forcewake_get(uncore, guc->send_regs.fw_domains); +retry: for (i = 0; i < len; i++) - intel_uncore_write(uncore, guc_send_reg(guc, i), action[i]); + intel_uncore_write(uncore, guc_send_reg(guc, i), request[i]); intel_uncore_posting_read(uncore, guc_send_reg(guc, i - 1)); @@ -410,30 +425,74 @@ int intel_guc_send_mmio(struct intel_guc *guc, const u32 *action, u32 len, */ ret = __intel_wait_for_register_fw(uncore, guc_send_reg(guc, 0), - INTEL_GUC_MSG_TYPE_MASK, - INTEL_GUC_MSG_TYPE_RESPONSE << - INTEL_GUC_MSG_TYPE_SHIFT, - 10, 10, &status); - /* If GuC explicitly returned an error, convert it to -EIO */ - if (!ret && !INTEL_GUC_MSG_IS_RESPONSE_SUCCESS(status)) - ret = -EIO; + GUC_HXG_MSG_0_ORIGIN, + FIELD_PREP(GUC_HXG_MSG_0_ORIGIN, + GUC_HXG_ORIGIN_GUC), + 10, 10, &header); + if (unlikely(ret)) { +timeout: + drm_err(&i915->drm, "mmio request %#x: no reply %x\n", + request[0], header); + goto out; + } - if (ret) { - DRM_ERROR("MMIO: GuC action %#x failed with error %d %#x\n", - action[0], ret, status); + if (FIELD_GET(GUC_HXG_MSG_0_TYPE, header) == GUC_HXG_TYPE_NO_RESPONSE_BUSY) { +#define done ({ header = intel_uncore_read(uncore, guc_send_reg(guc, 0)); \ + FIELD_GET(GUC_HXG_MSG_0_ORIGIN, header) != GUC_HXG_ORIGIN_GUC || \ + FIELD_GET(GUC_HXG_MSG_0_TYPE, header) != GUC_HXG_TYPE_NO_RESPONSE_BUSY; }) + + ret = wait_for(done, 1000); + if (unlikely(ret)) + goto timeout; + if (unlikely(FIELD_GET(GUC_HXG_MSG_0_ORIGIN, header) != + GUC_HXG_ORIGIN_GUC)) + goto proto; +#undef done + } + + if (FIELD_GET(GUC_HXG_MSG_0_TYPE, header) == GUC_HXG_TYPE_NO_RESPONSE_RETRY) { + u32 reason = FIELD_GET(GUC_HXG_RETRY_MSG_0_REASON, header); + + drm_dbg(&i915->drm, "mmio request %#x: retrying, reason %u\n", + request[0], reason); + goto retry; + } + + if (FIELD_GET(GUC_HXG_MSG_0_TYPE, header) == GUC_HXG_TYPE_RESPONSE_FAILURE) { + u32 hint = FIELD_GET(GUC_HXG_FAILURE_MSG_0_HINT, header); + u32 error = FIELD_GET(GUC_HXG_FAILURE_MSG_0_ERROR, header); + + drm_err(&i915->drm, "mmio request %#x: failure %x/%u\n", + request[0], error, hint); + ret = -ENXIO; + goto out; + } + + if (FIELD_GET(GUC_HXG_MSG_0_TYPE, header) != GUC_HXG_TYPE_RESPONSE_SUCCESS) { +proto: + drm_err(&i915->drm, "mmio request %#x: unexpected reply %#x\n", + request[0], header); + ret = -EPROTO; goto out; } if (response_buf) { - int count = min(response_buf_size, guc->send_regs.count - 1); + int count = min(response_buf_size, guc->send_regs.count); + + GEM_BUG_ON(!count); - for (i = 0; i < count; i++) + response_buf[0] = header; + + for (i = 1; i < count; i++) response_buf[i] = intel_uncore_read(uncore, - guc_send_reg(guc, i + 1)); - } + guc_send_reg(guc, i)); - /* Use data from the GuC response as our return value */ - ret = INTEL_GUC_MSG_TO_DATA(status); + /* Use number of copied dwords as our return value */ + ret = count; + } else { + /* Use data from the GuC response as our return value */ + ret = FIELD_GET(GUC_HXG_RESPONSE_MSG_0_DATA0, header); + } out: intel_uncore_forcewake_put(uncore, guc->send_regs.fw_domains); @@ -487,65 +546,35 @@ int intel_guc_auth_huc(struct intel_guc *guc, u32 rsa_offset) */ int intel_guc_suspend(struct intel_guc *guc) { - struct intel_uncore *uncore = guc_to_gt(guc)->uncore; int ret; - u32 status; u32 action[] = { - INTEL_GUC_ACTION_ENTER_S_STATE, - GUC_POWER_D1, /* any value greater than GUC_POWER_D0 */ + INTEL_GUC_ACTION_RESET_CLIENT, }; - /* - * If GuC communication is enabled but submission is not supported, - * we do not need to suspend the GuC. - */ - if (!intel_guc_submission_is_used(guc) || !intel_guc_is_ready(guc)) + if (!intel_guc_is_ready(guc)) return 0; - /* - * The ENTER_S_STATE action queues the save/restore operation in GuC FW - * and then returns, so waiting on the H2G is not enough to guarantee - * GuC is done. When all the processing is done, GuC writes - * INTEL_GUC_SLEEP_STATE_SUCCESS to scratch register 14, so we can poll - * on that. Note that GuC does not ensure that the value in the register - * is different from INTEL_GUC_SLEEP_STATE_SUCCESS while the action is - * in progress so we need to take care of that ourselves as well. - */ - - intel_uncore_write(uncore, SOFT_SCRATCH(14), - INTEL_GUC_SLEEP_STATE_INVALID_MASK); - - ret = intel_guc_send(guc, action, ARRAY_SIZE(action)); - if (ret) - return ret; - - ret = __intel_wait_for_register(uncore, SOFT_SCRATCH(14), - INTEL_GUC_SLEEP_STATE_INVALID_MASK, - 0, 0, 10, &status); - if (ret) - return ret; - - if (status != INTEL_GUC_SLEEP_STATE_SUCCESS) { - DRM_ERROR("GuC failed to change sleep state. " - "action=0x%x, err=%u\n", - action[0], status); - return -EIO; + if (intel_guc_submission_is_used(guc)) { + /* + * This H2G MMIO command tears down the GuC in two steps. First it will + * generate a G2H CTB for every active context indicating a reset. In + * practice the i915 shouldn't ever get a G2H as suspend should only be + * called when the GPU is idle. Next, it tears down the CTBs and this + * H2G MMIO command completes. + * + * Don't abort on a failure code from the GuC. Keep going and do the + * clean up in santize() and re-initialisation on resume and hopefully + * the error here won't be problematic. + */ + ret = intel_guc_send_mmio(guc, action, ARRAY_SIZE(action), NULL, 0); + if (ret) + DRM_ERROR("GuC suspend: RESET_CLIENT action failed with error %d!\n", ret); } - return 0; -} - -/** - * intel_guc_reset_engine() - ask GuC to reset an engine - * @guc: intel_guc structure - * @engine: engine to be reset - */ -int intel_guc_reset_engine(struct intel_guc *guc, - struct intel_engine_cs *engine) -{ - /* XXX: to be implemented with submission interface rework */ + /* Signal that the GuC isn't running. */ + intel_guc_sanitize(guc); - return -ENODEV; + return 0; } /** @@ -554,7 +583,12 @@ int intel_guc_reset_engine(struct intel_guc *guc, */ int intel_guc_resume(struct intel_guc *guc) { - /* XXX: to be implemented with submission interface rework */ + /* + * NB: This function can still be called even if GuC submission is + * disabled, e.g. if GuC is enabled for HuC authentication only. Thus, + * if any code is later added here, it must be support doing nothing + * if submission is disabled (as per intel_guc_suspend). + */ return 0; } diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h index 4abc59f6f3cd..2e27fe59786b 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h @@ -6,12 +6,16 @@ #ifndef _INTEL_GUC_H_ #define _INTEL_GUC_H_ +#include <linux/xarray.h> +#include <linux/delay.h> + #include "intel_uncore.h" #include "intel_guc_fw.h" #include "intel_guc_fwif.h" #include "intel_guc_ct.h" #include "intel_guc_log.h" #include "intel_guc_reg.h" +#include "intel_guc_slpc_types.h" #include "intel_uc_fw.h" #include "i915_utils.h" #include "i915_vma.h" @@ -27,24 +31,47 @@ struct intel_guc { struct intel_uc_fw fw; struct intel_guc_log log; struct intel_guc_ct ct; + struct intel_guc_slpc slpc; + + /* Global engine used to submit requests to GuC */ + struct i915_sched_engine *sched_engine; + struct i915_request *stalled_request; /* intel_guc_recv interrupt related state */ spinlock_t irq_lock; unsigned int msg_enabled_mask; + atomic_t outstanding_submission_g2h; + struct { void (*reset)(struct intel_guc *guc); void (*enable)(struct intel_guc *guc); void (*disable)(struct intel_guc *guc); } interrupts; + /* + * contexts_lock protects the pool of free guc ids and a linked list of + * guc ids available to be stolen + */ + spinlock_t contexts_lock; + struct ida guc_ids; + struct list_head guc_id_list; + + bool submission_supported; bool submission_selected; + bool rc_supported; + bool rc_selected; struct i915_vma *ads_vma; struct __guc_ads_blob *ads_blob; + u32 ads_regset_size; + u32 ads_golden_ctxt_size; - struct i915_vma *stage_desc_pool; - void *stage_desc_pool_vaddr; + struct i915_vma *lrc_desc_pool; + void *lrc_desc_pool_vaddr; + + /* guc_id to intel_context lookup */ + struct xarray context_lookup; /* Control params for fw initialization */ u32 params[GUC_CTL_MAX_DWORDS]; @@ -74,7 +101,15 @@ static inline struct intel_guc *log_to_guc(struct intel_guc_log *log) static inline int intel_guc_send(struct intel_guc *guc, const u32 *action, u32 len) { - return intel_guc_ct_send(&guc->ct, action, len, NULL, 0); + return intel_guc_ct_send(&guc->ct, action, len, NULL, 0, 0); +} + +static +inline int intel_guc_send_nb(struct intel_guc *guc, const u32 *action, u32 len, + u32 g2h_len_dw) +{ + return intel_guc_ct_send(&guc->ct, action, len, NULL, 0, + MAKE_SEND_FLAGS(g2h_len_dw)); } static inline int @@ -82,7 +117,43 @@ intel_guc_send_and_receive(struct intel_guc *guc, const u32 *action, u32 len, u32 *response_buf, u32 response_buf_size) { return intel_guc_ct_send(&guc->ct, action, len, - response_buf, response_buf_size); + response_buf, response_buf_size, 0); +} + +static inline int intel_guc_send_busy_loop(struct intel_guc *guc, + const u32 *action, + u32 len, + u32 g2h_len_dw, + bool loop) +{ + int err; + unsigned int sleep_period_ms = 1; + bool not_atomic = !in_atomic() && !irqs_disabled(); + + /* + * FIXME: Have caller pass in if we are in an atomic context to avoid + * using in_atomic(). It is likely safe here as we check for irqs + * disabled which basically all the spin locks in the i915 do but + * regardless this should be cleaned up. + */ + + /* No sleeping with spin locks, just busy loop */ + might_sleep_if(loop && not_atomic); + +retry: + err = intel_guc_send_nb(guc, action, len, g2h_len_dw); + if (unlikely(err == -EBUSY && loop)) { + if (likely(not_atomic)) { + if (msleep_interruptible(sleep_period_ms)) + return -EINTR; + sleep_period_ms = sleep_period_ms << 1; + } else { + cpu_relax(); + } + goto retry; + } + + return err; } static inline void intel_guc_to_host_event_handler(struct intel_guc *guc) @@ -118,6 +189,7 @@ static inline u32 intel_guc_ggtt_offset(struct intel_guc *guc, } void intel_guc_init_early(struct intel_guc *guc); +void intel_guc_init_late(struct intel_guc *guc); void intel_guc_init_send_regs(struct intel_guc *guc); void intel_guc_write_params(struct intel_guc *guc); int intel_guc_init(struct intel_guc *guc); @@ -160,9 +232,25 @@ static inline bool intel_guc_is_ready(struct intel_guc *guc) return intel_guc_is_fw_running(guc) && intel_guc_ct_enabled(&guc->ct); } +static inline void intel_guc_reset_interrupts(struct intel_guc *guc) +{ + guc->interrupts.reset(guc); +} + +static inline void intel_guc_enable_interrupts(struct intel_guc *guc) +{ + guc->interrupts.enable(guc); +} + +static inline void intel_guc_disable_interrupts(struct intel_guc *guc) +{ + guc->interrupts.disable(guc); +} + static inline int intel_guc_sanitize(struct intel_guc *guc) { intel_uc_fw_sanitize(&guc->fw); + intel_guc_disable_interrupts(guc); intel_guc_ct_sanitize(&guc->ct); guc->mmio_msg = 0; @@ -183,8 +271,27 @@ static inline void intel_guc_disable_msg(struct intel_guc *guc, u32 mask) spin_unlock_irq(&guc->irq_lock); } -int intel_guc_reset_engine(struct intel_guc *guc, - struct intel_engine_cs *engine); +int intel_guc_wait_for_idle(struct intel_guc *guc, long timeout); + +int intel_guc_deregister_done_process_msg(struct intel_guc *guc, + const u32 *msg, u32 len); +int intel_guc_sched_done_process_msg(struct intel_guc *guc, + const u32 *msg, u32 len); +int intel_guc_context_reset_process_msg(struct intel_guc *guc, + const u32 *msg, u32 len); +int intel_guc_engine_failure_process_msg(struct intel_guc *guc, + const u32 *msg, u32 len); + +void intel_guc_find_hung_context(struct intel_engine_cs *engine); + +int intel_guc_global_policies_update(struct intel_guc *guc); + +void intel_guc_context_ban(struct intel_context *ce, struct i915_request *rq); + +void intel_guc_submission_reset_prepare(struct intel_guc *guc); +void intel_guc_submission_reset(struct intel_guc *guc, bool stalled); +void intel_guc_submission_reset_finish(struct intel_guc *guc); +void intel_guc_submission_cancel_requests(struct intel_guc *guc); void intel_guc_load_status(struct intel_guc *guc, struct drm_printer *p); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c index 9abfbc6edbd6..6926919bcac6 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c @@ -3,8 +3,11 @@ * Copyright © 2014-2019 Intel Corporation */ +#include <linux/bsearch.h> + #include "gt/intel_gt.h" #include "gt/intel_lrc.h" +#include "gt/shmem_utils.h" #include "intel_guc_ads.h" #include "intel_guc_fwif.h" #include "intel_uc.h" @@ -23,10 +26,15 @@ * | guc_policies | * +---------------------------------------+ * | guc_gt_system_info | - * +---------------------------------------+ - * | guc_clients_info | - * +---------------------------------------+ - * | guc_ct_pool_entry[size] | + * +---------------------------------------+ <== static + * | guc_mmio_reg[countA] (engine 0.0) | + * | guc_mmio_reg[countB] (engine 0.1) | + * | guc_mmio_reg[countC] (engine 1.0) | + * | ... | + * +---------------------------------------+ <== dynamic + * | padding | + * +---------------------------------------+ <== 4K aligned + * | golden contexts | * +---------------------------------------+ * | padding | * +---------------------------------------+ <== 4K aligned @@ -39,18 +47,49 @@ struct __guc_ads_blob { struct guc_ads ads; struct guc_policies policies; struct guc_gt_system_info system_info; - struct guc_clients_info clients_info; - struct guc_ct_pool_entry ct_pool[GUC_CT_POOL_SIZE]; + /* From here on, location is dynamic! Refer to above diagram. */ + struct guc_mmio_reg regset[0]; } __packed; +static u32 guc_ads_regset_size(struct intel_guc *guc) +{ + GEM_BUG_ON(!guc->ads_regset_size); + return guc->ads_regset_size; +} + +static u32 guc_ads_golden_ctxt_size(struct intel_guc *guc) +{ + return PAGE_ALIGN(guc->ads_golden_ctxt_size); +} + static u32 guc_ads_private_data_size(struct intel_guc *guc) { return PAGE_ALIGN(guc->fw.private_data_size); } +static u32 guc_ads_regset_offset(struct intel_guc *guc) +{ + return offsetof(struct __guc_ads_blob, regset); +} + +static u32 guc_ads_golden_ctxt_offset(struct intel_guc *guc) +{ + u32 offset; + + offset = guc_ads_regset_offset(guc) + + guc_ads_regset_size(guc); + + return PAGE_ALIGN(offset); +} + static u32 guc_ads_private_data_offset(struct intel_guc *guc) { - return PAGE_ALIGN(sizeof(struct __guc_ads_blob)); + u32 offset; + + offset = guc_ads_golden_ctxt_offset(guc) + + guc_ads_golden_ctxt_size(guc); + + return PAGE_ALIGN(offset); } static u32 guc_ads_blob_size(struct intel_guc *guc) @@ -59,36 +98,66 @@ static u32 guc_ads_blob_size(struct intel_guc *guc) guc_ads_private_data_size(guc); } -static void guc_policy_init(struct guc_policy *policy) +static void guc_policies_init(struct intel_guc *guc, struct guc_policies *policies) { - policy->execution_quantum = POLICY_DEFAULT_EXECUTION_QUANTUM_US; - policy->preemption_time = POLICY_DEFAULT_PREEMPTION_TIME_US; - policy->fault_time = POLICY_DEFAULT_FAULT_TIME_US; - policy->policy_flags = 0; + struct intel_gt *gt = guc_to_gt(guc); + struct drm_i915_private *i915 = gt->i915; + + policies->dpc_promote_time = GLOBAL_POLICY_DEFAULT_DPC_PROMOTE_TIME_US; + policies->max_num_work_items = GLOBAL_POLICY_MAX_NUM_WI; + + policies->global_flags = 0; + if (i915->params.reset < 2) + policies->global_flags |= GLOBAL_POLICY_DISABLE_ENGINE_RESET; + + policies->is_valid = 1; } -static void guc_policies_init(struct guc_policies *policies) +void intel_guc_ads_print_policy_info(struct intel_guc *guc, + struct drm_printer *dp) { - struct guc_policy *policy; - u32 p, i; + struct __guc_ads_blob *blob = guc->ads_blob; - policies->dpc_promote_time = POLICY_DEFAULT_DPC_PROMOTE_TIME_US; - policies->max_num_work_items = POLICY_MAX_NUM_WI; + if (unlikely(!blob)) + return; - for (p = 0; p < GUC_CLIENT_PRIORITY_NUM; p++) { - for (i = 0; i < GUC_MAX_ENGINE_CLASSES; i++) { - policy = &policies->policy[p][i]; + drm_printf(dp, "Global scheduling policies:\n"); + drm_printf(dp, " DPC promote time = %u\n", blob->policies.dpc_promote_time); + drm_printf(dp, " Max num work items = %u\n", blob->policies.max_num_work_items); + drm_printf(dp, " Flags = %u\n", blob->policies.global_flags); +} - guc_policy_init(policy); - } - } +static int guc_action_policies_update(struct intel_guc *guc, u32 policy_offset) +{ + u32 action[] = { + INTEL_GUC_ACTION_GLOBAL_SCHED_POLICY_CHANGE, + policy_offset + }; - policies->is_valid = 1; + return intel_guc_send_busy_loop(guc, action, ARRAY_SIZE(action), 0, true); } -static void guc_ct_pool_entries_init(struct guc_ct_pool_entry *pool, u32 num) +int intel_guc_global_policies_update(struct intel_guc *guc) { - memset(pool, 0, num * sizeof(*pool)); + struct __guc_ads_blob *blob = guc->ads_blob; + struct intel_gt *gt = guc_to_gt(guc); + intel_wakeref_t wakeref; + int ret; + + if (!blob) + return -EOPNOTSUPP; + + GEM_BUG_ON(!blob->ads.scheduler_policies); + + guc_policies_init(guc, &blob->policies); + + if (!intel_guc_is_ready(guc)) + return 0; + + with_intel_runtime_pm(>->i915->runtime_pm, wakeref) + ret = guc_action_policies_update(guc, blob->ads.scheduler_policies); + + return ret; } static void guc_mapping_table_init(struct intel_gt *gt, @@ -113,53 +182,324 @@ static void guc_mapping_table_init(struct intel_gt *gt, } /* - * The first 80 dwords of the register state context, containing the - * execlists and ppgtt registers. + * The save/restore register list must be pre-calculated to a temporary + * buffer of driver defined size before it can be generated in place + * inside the ADS. */ -#define LR_HW_CONTEXT_SIZE (80 * sizeof(u32)) +#define MAX_MMIO_REGS 128 /* Arbitrary size, increase as needed */ +struct temp_regset { + struct guc_mmio_reg *registers; + u32 used; + u32 size; +}; -static void __guc_ads_init(struct intel_guc *guc) +static int guc_mmio_reg_cmp(const void *a, const void *b) +{ + const struct guc_mmio_reg *ra = a; + const struct guc_mmio_reg *rb = b; + + return (int)ra->offset - (int)rb->offset; +} + +static void guc_mmio_reg_add(struct temp_regset *regset, + u32 offset, u32 flags) +{ + u32 count = regset->used; + struct guc_mmio_reg reg = { + .offset = offset, + .flags = flags, + }; + struct guc_mmio_reg *slot; + + GEM_BUG_ON(count >= regset->size); + + /* + * The mmio list is built using separate lists within the driver. + * It's possible that at some point we may attempt to add the same + * register more than once. Do not consider this an error; silently + * move on if the register is already in the list. + */ + if (bsearch(®, regset->registers, count, + sizeof(reg), guc_mmio_reg_cmp)) + return; + + slot = ®set->registers[count]; + regset->used++; + *slot = reg; + + while (slot-- > regset->registers) { + GEM_BUG_ON(slot[0].offset == slot[1].offset); + if (slot[1].offset > slot[0].offset) + break; + + swap(slot[1], slot[0]); + } +} + +#define GUC_MMIO_REG_ADD(regset, reg, masked) \ + guc_mmio_reg_add(regset, \ + i915_mmio_reg_offset((reg)), \ + (masked) ? GUC_REGSET_MASKED : 0) + +static void guc_mmio_regset_init(struct temp_regset *regset, + struct intel_engine_cs *engine) +{ + const u32 base = engine->mmio_base; + struct i915_wa_list *wal = &engine->wa_list; + struct i915_wa *wa; + unsigned int i; + + regset->used = 0; + + GUC_MMIO_REG_ADD(regset, RING_MODE_GEN7(base), true); + GUC_MMIO_REG_ADD(regset, RING_HWS_PGA(base), false); + GUC_MMIO_REG_ADD(regset, RING_IMR(base), false); + + for (i = 0, wa = wal->list; i < wal->count; i++, wa++) + GUC_MMIO_REG_ADD(regset, wa->reg, wa->masked_reg); + + /* Be extra paranoid and include all whitelist registers. */ + for (i = 0; i < RING_MAX_NONPRIV_SLOTS; i++) + GUC_MMIO_REG_ADD(regset, + RING_FORCE_TO_NONPRIV(base, i), + false); + + /* add in local MOCS registers */ + for (i = 0; i < GEN9_LNCFCMOCS_REG_COUNT; i++) + GUC_MMIO_REG_ADD(regset, GEN9_LNCFCMOCS(i), false); +} + +static int guc_mmio_reg_state_query(struct intel_guc *guc) { struct intel_gt *gt = guc_to_gt(guc); - struct drm_i915_private *i915 = gt->i915; + struct intel_engine_cs *engine; + enum intel_engine_id id; + struct temp_regset temp_set; + u32 total; + + /* + * Need to actually build the list in order to filter out + * duplicates and other such data dependent constructions. + */ + temp_set.size = MAX_MMIO_REGS; + temp_set.registers = kmalloc_array(temp_set.size, + sizeof(*temp_set.registers), + GFP_KERNEL); + if (!temp_set.registers) + return -ENOMEM; + + total = 0; + for_each_engine(engine, gt, id) { + guc_mmio_regset_init(&temp_set, engine); + total += temp_set.used; + } + + kfree(temp_set.registers); + + return total * sizeof(struct guc_mmio_reg); +} + +static void guc_mmio_reg_state_init(struct intel_guc *guc, + struct __guc_ads_blob *blob) +{ + struct intel_gt *gt = guc_to_gt(guc); + struct intel_engine_cs *engine; + enum intel_engine_id id; + struct temp_regset temp_set; + struct guc_mmio_reg_set *ads_reg_set; + u32 addr_ggtt, offset; + u8 guc_class; + + offset = guc_ads_regset_offset(guc); + addr_ggtt = intel_guc_ggtt_offset(guc, guc->ads_vma) + offset; + temp_set.registers = (struct guc_mmio_reg *)(((u8 *)blob) + offset); + temp_set.size = guc->ads_regset_size / sizeof(temp_set.registers[0]); + + for_each_engine(engine, gt, id) { + /* Class index is checked in class converter */ + GEM_BUG_ON(engine->instance >= GUC_MAX_INSTANCES_PER_CLASS); + + guc_class = engine_class_to_guc_class(engine->class); + ads_reg_set = &blob->ads.reg_state_list[guc_class][engine->instance]; + + guc_mmio_regset_init(&temp_set, engine); + if (!temp_set.used) { + ads_reg_set->address = 0; + ads_reg_set->count = 0; + continue; + } + + ads_reg_set->address = addr_ggtt; + ads_reg_set->count = temp_set.used; + + temp_set.size -= temp_set.used; + temp_set.registers += temp_set.used; + addr_ggtt += temp_set.used * sizeof(struct guc_mmio_reg); + } + + GEM_BUG_ON(temp_set.size); +} + +static void fill_engine_enable_masks(struct intel_gt *gt, + struct guc_gt_system_info *info) +{ + info->engine_enabled_masks[GUC_RENDER_CLASS] = 1; + info->engine_enabled_masks[GUC_BLITTER_CLASS] = 1; + info->engine_enabled_masks[GUC_VIDEO_CLASS] = VDBOX_MASK(gt); + info->engine_enabled_masks[GUC_VIDEOENHANCE_CLASS] = VEBOX_MASK(gt); +} + +static int guc_prep_golden_context(struct intel_guc *guc, + struct __guc_ads_blob *blob) +{ + struct intel_gt *gt = guc_to_gt(guc); + u32 addr_ggtt, offset; + u32 total_size = 0, alloc_size, real_size; + u8 engine_class, guc_class; + struct guc_gt_system_info *info, local_info; + + /* + * Reserve the memory for the golden contexts and point GuC at it but + * leave it empty for now. The context data will be filled in later + * once there is something available to put there. + * + * Note that the HWSP and ring context are not included. + * + * Note also that the storage must be pinned in the GGTT, so that the + * address won't change after GuC has been told where to find it. The + * GuC will also validate that the LRC base + size fall within the + * allowed GGTT range. + */ + if (blob) { + offset = guc_ads_golden_ctxt_offset(guc); + addr_ggtt = intel_guc_ggtt_offset(guc, guc->ads_vma) + offset; + info = &blob->system_info; + } else { + memset(&local_info, 0, sizeof(local_info)); + info = &local_info; + fill_engine_enable_masks(gt, info); + } + + for (engine_class = 0; engine_class <= MAX_ENGINE_CLASS; ++engine_class) { + if (engine_class == OTHER_CLASS) + continue; + + guc_class = engine_class_to_guc_class(engine_class); + + if (!info->engine_enabled_masks[guc_class]) + continue; + + real_size = intel_engine_context_size(gt, engine_class); + alloc_size = PAGE_ALIGN(real_size); + total_size += alloc_size; + + if (!blob) + continue; + + blob->ads.eng_state_size[guc_class] = real_size; + blob->ads.golden_context_lrca[guc_class] = addr_ggtt; + addr_ggtt += alloc_size; + } + + if (!blob) + return total_size; + + GEM_BUG_ON(guc->ads_golden_ctxt_size != total_size); + return total_size; +} + +static struct intel_engine_cs *find_engine_state(struct intel_gt *gt, u8 engine_class) +{ + struct intel_engine_cs *engine; + enum intel_engine_id id; + + for_each_engine(engine, gt, id) { + if (engine->class != engine_class) + continue; + + if (!engine->default_state) + continue; + + return engine; + } + + return NULL; +} + +static void guc_init_golden_context(struct intel_guc *guc) +{ struct __guc_ads_blob *blob = guc->ads_blob; - const u32 skipped_size = LRC_PPHWSP_SZ * PAGE_SIZE + LR_HW_CONTEXT_SIZE; - u32 base; + struct intel_engine_cs *engine; + struct intel_gt *gt = guc_to_gt(guc); + u32 addr_ggtt, offset; + u32 total_size = 0, alloc_size, real_size; u8 engine_class, guc_class; + u8 *ptr; - /* GuC scheduling policies */ - guc_policies_init(&blob->policies); + /* Skip execlist and PPGTT registers + HWSP */ + const u32 lr_hw_context_size = 80 * sizeof(u32); + const u32 skip_size = LRC_PPHWSP_SZ * PAGE_SIZE + + lr_hw_context_size; + + if (!intel_uc_uses_guc_submission(>->uc)) + return; + + GEM_BUG_ON(!blob); /* - * GuC expects a per-engine-class context image and size - * (minus hwsp and ring context). The context image will be - * used to reinitialize engines after a reset. It must exist - * and be pinned in the GGTT, so that the address won't change after - * we have told GuC where to find it. The context size will be used - * to validate that the LRC base + size fall within allowed GGTT. + * Go back and fill in the golden context data now that it is + * available. */ + offset = guc_ads_golden_ctxt_offset(guc); + addr_ggtt = intel_guc_ggtt_offset(guc, guc->ads_vma) + offset; + ptr = ((u8 *)blob) + offset; + for (engine_class = 0; engine_class <= MAX_ENGINE_CLASS; ++engine_class) { if (engine_class == OTHER_CLASS) continue; guc_class = engine_class_to_guc_class(engine_class); - /* - * TODO: Set context pointer to default state to allow - * GuC to re-init guilty contexts after internal reset. - */ - blob->ads.golden_context_lrca[guc_class] = 0; - blob->ads.eng_state_size[guc_class] = - intel_engine_context_size(guc_to_gt(guc), - engine_class) - - skipped_size; + if (!blob->system_info.engine_enabled_masks[guc_class]) + continue; + + real_size = intel_engine_context_size(gt, engine_class); + alloc_size = PAGE_ALIGN(real_size); + total_size += alloc_size; + + engine = find_engine_state(gt, engine_class); + if (!engine) { + drm_err(>->i915->drm, "No engine state recorded for class %d!\n", + engine_class); + blob->ads.eng_state_size[guc_class] = 0; + blob->ads.golden_context_lrca[guc_class] = 0; + continue; + } + + GEM_BUG_ON(blob->ads.eng_state_size[guc_class] != real_size); + GEM_BUG_ON(blob->ads.golden_context_lrca[guc_class] != addr_ggtt); + addr_ggtt += alloc_size; + + shmem_read(engine->default_state, skip_size, ptr + skip_size, + real_size - skip_size); + ptr += alloc_size; } + GEM_BUG_ON(guc->ads_golden_ctxt_size != total_size); +} + +static void __guc_ads_init(struct intel_guc *guc) +{ + struct intel_gt *gt = guc_to_gt(guc); + struct drm_i915_private *i915 = gt->i915; + struct __guc_ads_blob *blob = guc->ads_blob; + u32 base; + + /* GuC scheduling policies */ + guc_policies_init(guc, &blob->policies); + /* System info */ - blob->system_info.engine_enabled_masks[GUC_RENDER_CLASS] = 1; - blob->system_info.engine_enabled_masks[GUC_BLITTER_CLASS] = 1; - blob->system_info.engine_enabled_masks[GUC_VIDEO_CLASS] = VDBOX_MASK(gt); - blob->system_info.engine_enabled_masks[GUC_VIDEOENHANCE_CLASS] = VEBOX_MASK(gt); + fill_engine_enable_masks(gt, &blob->system_info); blob->system_info.generic_gt_sysinfo[GUC_GENERIC_GT_SYSINFO_SLICE_ENABLED] = hweight8(gt->info.sseu.slice_mask); @@ -174,21 +514,19 @@ static void __guc_ads_init(struct intel_guc *guc) GEN12_DOORBELLS_PER_SQIDI) + 1; } + /* Golden contexts for re-initialising after a watchdog reset */ + guc_prep_golden_context(guc, blob); + guc_mapping_table_init(guc_to_gt(guc), &blob->system_info); base = intel_guc_ggtt_offset(guc, guc->ads_vma); - /* Clients info */ - guc_ct_pool_entries_init(blob->ct_pool, ARRAY_SIZE(blob->ct_pool)); - - blob->clients_info.clients_num = 1; - blob->clients_info.ct_pool_addr = base + ptr_offset(blob, ct_pool); - blob->clients_info.ct_pool_count = ARRAY_SIZE(blob->ct_pool); - /* ADS */ blob->ads.scheduler_policies = base + ptr_offset(blob, policies); blob->ads.gt_system_info = base + ptr_offset(blob, system_info); - blob->ads.clients_info = base + ptr_offset(blob, clients_info); + + /* MMIO save/restore list */ + guc_mmio_reg_state_init(guc, blob); /* Private Data */ blob->ads.private_data = base + guc_ads_private_data_offset(guc); @@ -210,6 +548,19 @@ int intel_guc_ads_create(struct intel_guc *guc) GEM_BUG_ON(guc->ads_vma); + /* Need to calculate the reg state size dynamically: */ + ret = guc_mmio_reg_state_query(guc); + if (ret < 0) + return ret; + guc->ads_regset_size = ret; + + /* Likewise the golden contexts: */ + ret = guc_prep_golden_context(guc, NULL); + if (ret < 0) + return ret; + guc->ads_golden_ctxt_size = ret; + + /* Now the total size can be determined: */ size = guc_ads_blob_size(guc); ret = intel_guc_allocate_and_map_vma(guc, size, &guc->ads_vma, @@ -222,6 +573,18 @@ int intel_guc_ads_create(struct intel_guc *guc) return 0; } +void intel_guc_ads_init_late(struct intel_guc *guc) +{ + /* + * The golden context setup requires the saved engine state from + * __engines_record_defaults(). However, that requires engines to be + * operational which means the ADS must already have been configured. + * Fortunately, the golden context state is not needed until a hang + * occurs, so it can be filled in during this late init phase. + */ + guc_init_golden_context(guc); +} + void intel_guc_ads_destroy(struct intel_guc *guc) { i915_vma_unpin_and_release(&guc->ads_vma, I915_VMA_RELEASE_MAP); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.h index b00d3ae1113a..3d85051d57e4 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.h @@ -7,9 +7,13 @@ #define _INTEL_GUC_ADS_H_ struct intel_guc; +struct drm_printer; int intel_guc_ads_create(struct intel_guc *guc); void intel_guc_ads_destroy(struct intel_guc *guc); +void intel_guc_ads_init_late(struct intel_guc *guc); void intel_guc_ads_reset(struct intel_guc *guc); +void intel_guc_ads_print_policy_info(struct intel_guc *guc, + struct drm_printer *p); #endif diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c index 8f7b148fef58..22b4733b55e2 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c @@ -3,6 +3,11 @@ * Copyright © 2016-2019 Intel Corporation */ +#include <linux/circ_buf.h> +#include <linux/ktime.h> +#include <linux/time64.h> +#include <linux/timekeeping.h> + #include "i915_drv.h" #include "intel_guc_ct.h" #include "gt/intel_gt.h" @@ -58,11 +63,17 @@ static inline struct drm_device *ct_to_drm(struct intel_guc_ct *ct) * +--------+-----------------------------------------------+------+ * * Size of each `CT Buffer`_ must be multiple of 4K. - * As we don't expect too many messages, for now use minimum sizes. + * We don't expect too many messages in flight at any time, unless we are + * using the GuC submission. In that case each request requires a minimum + * 2 dwords which gives us a maximum 256 queue'd requests. Hopefully this + * enough space to avoid backpressure on the driver. We increase the size + * of the receive buffer (relative to the send) to ensure a G2H response + * CTB has a landing spot. */ #define CTB_DESC_SIZE ALIGN(sizeof(struct guc_ct_buffer_desc), SZ_2K) #define CTB_H2G_BUFFER_SIZE (SZ_4K) -#define CTB_G2H_BUFFER_SIZE (SZ_4K) +#define CTB_G2H_BUFFER_SIZE (4 * CTB_H2G_BUFFER_SIZE) +#define G2H_ROOM_BUFFER_SIZE (CTB_G2H_BUFFER_SIZE / 4) struct ct_request { struct list_head link; @@ -98,66 +109,84 @@ void intel_guc_ct_init_early(struct intel_guc_ct *ct) INIT_LIST_HEAD(&ct->requests.incoming); INIT_WORK(&ct->requests.worker, ct_incoming_request_worker_func); tasklet_setup(&ct->receive_tasklet, ct_receive_tasklet_func); + init_waitqueue_head(&ct->wq); } static inline const char *guc_ct_buffer_type_to_str(u32 type) { switch (type) { - case INTEL_GUC_CT_BUFFER_TYPE_SEND: + case GUC_CTB_TYPE_HOST2GUC: return "SEND"; - case INTEL_GUC_CT_BUFFER_TYPE_RECV: + case GUC_CTB_TYPE_GUC2HOST: return "RECV"; default: return "<invalid>"; } } -static void guc_ct_buffer_desc_init(struct guc_ct_buffer_desc *desc, - u32 cmds_addr, u32 size) +static void guc_ct_buffer_desc_init(struct guc_ct_buffer_desc *desc) { memset(desc, 0, sizeof(*desc)); - desc->addr = cmds_addr; - desc->size = size; - desc->owner = CTB_OWNER_HOST; } -static void guc_ct_buffer_reset(struct intel_guc_ct_buffer *ctb, u32 cmds_addr) +static void guc_ct_buffer_reset(struct intel_guc_ct_buffer *ctb) { - guc_ct_buffer_desc_init(ctb->desc, cmds_addr, ctb->size); + u32 space; + + ctb->broken = false; + ctb->tail = 0; + ctb->head = 0; + space = CIRC_SPACE(ctb->tail, ctb->head, ctb->size) - ctb->resv_space; + atomic_set(&ctb->space, space); + + guc_ct_buffer_desc_init(ctb->desc); } static void guc_ct_buffer_init(struct intel_guc_ct_buffer *ctb, struct guc_ct_buffer_desc *desc, - u32 *cmds, u32 size) + u32 *cmds, u32 size_in_bytes, u32 resv_space) { - GEM_BUG_ON(size % 4); + GEM_BUG_ON(size_in_bytes % 4); ctb->desc = desc; ctb->cmds = cmds; - ctb->size = size; + ctb->size = size_in_bytes / 4; + ctb->resv_space = resv_space / 4; - guc_ct_buffer_reset(ctb, 0); + guc_ct_buffer_reset(ctb); } -static int guc_action_register_ct_buffer(struct intel_guc *guc, - u32 desc_addr, - u32 type) +static int guc_action_register_ct_buffer(struct intel_guc *guc, u32 type, + u32 desc_addr, u32 buff_addr, u32 size) { - u32 action[] = { - INTEL_GUC_ACTION_REGISTER_COMMAND_TRANSPORT_BUFFER, - desc_addr, - sizeof(struct guc_ct_buffer_desc), - type + u32 request[HOST2GUC_REGISTER_CTB_REQUEST_MSG_LEN] = { + FIELD_PREP(GUC_HXG_MSG_0_ORIGIN, GUC_HXG_ORIGIN_HOST) | + FIELD_PREP(GUC_HXG_MSG_0_TYPE, GUC_HXG_TYPE_REQUEST) | + FIELD_PREP(GUC_HXG_REQUEST_MSG_0_ACTION, GUC_ACTION_HOST2GUC_REGISTER_CTB), + FIELD_PREP(HOST2GUC_REGISTER_CTB_REQUEST_MSG_1_SIZE, size / SZ_4K - 1) | + FIELD_PREP(HOST2GUC_REGISTER_CTB_REQUEST_MSG_1_TYPE, type), + FIELD_PREP(HOST2GUC_REGISTER_CTB_REQUEST_MSG_2_DESC_ADDR, desc_addr), + FIELD_PREP(HOST2GUC_REGISTER_CTB_REQUEST_MSG_3_BUFF_ADDR, buff_addr), }; - /* Can't use generic send(), CT registration must go over MMIO */ - return intel_guc_send_mmio(guc, action, ARRAY_SIZE(action), NULL, 0); + GEM_BUG_ON(type != GUC_CTB_TYPE_HOST2GUC && type != GUC_CTB_TYPE_GUC2HOST); + GEM_BUG_ON(size % SZ_4K); + + /* CT registration must go over MMIO */ + return intel_guc_send_mmio(guc, request, ARRAY_SIZE(request), NULL, 0); } -static int ct_register_buffer(struct intel_guc_ct *ct, u32 desc_addr, u32 type) +static int ct_register_buffer(struct intel_guc_ct *ct, u32 type, + u32 desc_addr, u32 buff_addr, u32 size) { - int err = guc_action_register_ct_buffer(ct_to_guc(ct), desc_addr, type); + int err; + + err = i915_inject_probe_error(guc_to_gt(ct_to_guc(ct))->i915, -ENXIO); + if (unlikely(err)) + return err; + err = guc_action_register_ct_buffer(ct_to_guc(ct), type, + desc_addr, buff_addr, size); if (unlikely(err)) CT_ERROR(ct, "Failed to register %s buffer (err=%d)\n", guc_ct_buffer_type_to_str(type), err); @@ -166,14 +195,17 @@ static int ct_register_buffer(struct intel_guc_ct *ct, u32 desc_addr, u32 type) static int guc_action_deregister_ct_buffer(struct intel_guc *guc, u32 type) { - u32 action[] = { - INTEL_GUC_ACTION_DEREGISTER_COMMAND_TRANSPORT_BUFFER, - CTB_OWNER_HOST, - type + u32 request[HOST2GUC_DEREGISTER_CTB_REQUEST_MSG_LEN] = { + FIELD_PREP(GUC_HXG_MSG_0_ORIGIN, GUC_HXG_ORIGIN_HOST) | + FIELD_PREP(GUC_HXG_MSG_0_TYPE, GUC_HXG_TYPE_REQUEST) | + FIELD_PREP(GUC_HXG_REQUEST_MSG_0_ACTION, GUC_ACTION_HOST2GUC_DEREGISTER_CTB), + FIELD_PREP(HOST2GUC_DEREGISTER_CTB_REQUEST_MSG_1_TYPE, type), }; - /* Can't use generic send(), CT deregistration must go over MMIO */ - return intel_guc_send_mmio(guc, action, ARRAY_SIZE(action), NULL, 0); + GEM_BUG_ON(type != GUC_CTB_TYPE_HOST2GUC && type != GUC_CTB_TYPE_GUC2HOST); + + /* CT deregistration must go over MMIO */ + return intel_guc_send_mmio(guc, request, ARRAY_SIZE(request), NULL, 0); } static int ct_deregister_buffer(struct intel_guc_ct *ct, u32 type) @@ -200,10 +232,15 @@ int intel_guc_ct_init(struct intel_guc_ct *ct) struct guc_ct_buffer_desc *desc; u32 blob_size; u32 cmds_size; + u32 resv_space; void *blob; u32 *cmds; int err; + err = i915_inject_probe_error(guc_to_gt(guc)->i915, -ENXIO); + if (err) + return err; + GEM_BUG_ON(ct->vma); blob_size = 2 * CTB_DESC_SIZE + CTB_H2G_BUFFER_SIZE + CTB_G2H_BUFFER_SIZE; @@ -220,19 +257,23 @@ int intel_guc_ct_init(struct intel_guc_ct *ct) desc = blob; cmds = blob + 2 * CTB_DESC_SIZE; cmds_size = CTB_H2G_BUFFER_SIZE; - CT_DEBUG(ct, "%s desc %#tx cmds %#tx size %u\n", "send", - ptrdiff(desc, blob), ptrdiff(cmds, blob), cmds_size); + resv_space = 0; + CT_DEBUG(ct, "%s desc %#tx cmds %#tx size %u/%u\n", "send", + ptrdiff(desc, blob), ptrdiff(cmds, blob), cmds_size, + resv_space); - guc_ct_buffer_init(&ct->ctbs.send, desc, cmds, cmds_size); + guc_ct_buffer_init(&ct->ctbs.send, desc, cmds, cmds_size, resv_space); /* store pointers to desc and cmds for recv ctb */ desc = blob + CTB_DESC_SIZE; cmds = blob + 2 * CTB_DESC_SIZE + CTB_H2G_BUFFER_SIZE; cmds_size = CTB_G2H_BUFFER_SIZE; - CT_DEBUG(ct, "%s desc %#tx cmds %#tx size %u\n", "recv", - ptrdiff(desc, blob), ptrdiff(cmds, blob), cmds_size); + resv_space = G2H_ROOM_BUFFER_SIZE; + CT_DEBUG(ct, "%s desc %#tx cmds %#tx size %u/%u\n", "recv", + ptrdiff(desc, blob), ptrdiff(cmds, blob), cmds_size, + resv_space); - guc_ct_buffer_init(&ct->ctbs.recv, desc, cmds, cmds_size); + guc_ct_buffer_init(&ct->ctbs.recv, desc, cmds, cmds_size, resv_space); return 0; } @@ -261,7 +302,7 @@ void intel_guc_ct_fini(struct intel_guc_ct *ct) int intel_guc_ct_enable(struct intel_guc_ct *ct) { struct intel_guc *guc = ct_to_guc(ct); - u32 base, cmds; + u32 base, desc, cmds; void *blob; int err; @@ -277,32 +318,36 @@ int intel_guc_ct_enable(struct intel_guc_ct *ct) GEM_BUG_ON(blob != ct->ctbs.send.desc); /* (re)initialize descriptors */ - cmds = base + ptrdiff(ct->ctbs.send.cmds, blob); - guc_ct_buffer_reset(&ct->ctbs.send, cmds); - - cmds = base + ptrdiff(ct->ctbs.recv.cmds, blob); - guc_ct_buffer_reset(&ct->ctbs.recv, cmds); + guc_ct_buffer_reset(&ct->ctbs.send); + guc_ct_buffer_reset(&ct->ctbs.recv); /* * Register both CT buffers starting with RECV buffer. * Descriptors are in first half of the blob. */ - err = ct_register_buffer(ct, base + ptrdiff(ct->ctbs.recv.desc, blob), - INTEL_GUC_CT_BUFFER_TYPE_RECV); + desc = base + ptrdiff(ct->ctbs.recv.desc, blob); + cmds = base + ptrdiff(ct->ctbs.recv.cmds, blob); + err = ct_register_buffer(ct, GUC_CTB_TYPE_GUC2HOST, + desc, cmds, ct->ctbs.recv.size * 4); + if (unlikely(err)) goto err_out; - err = ct_register_buffer(ct, base + ptrdiff(ct->ctbs.send.desc, blob), - INTEL_GUC_CT_BUFFER_TYPE_SEND); + desc = base + ptrdiff(ct->ctbs.send.desc, blob); + cmds = base + ptrdiff(ct->ctbs.send.cmds, blob); + err = ct_register_buffer(ct, GUC_CTB_TYPE_HOST2GUC, + desc, cmds, ct->ctbs.send.size * 4); + if (unlikely(err)) goto err_deregister; ct->enabled = true; + ct->stall_time = KTIME_MAX; return 0; err_deregister: - ct_deregister_buffer(ct, INTEL_GUC_CT_BUFFER_TYPE_RECV); + ct_deregister_buffer(ct, GUC_CTB_TYPE_GUC2HOST); err_out: CT_PROBE_ERROR(ct, "Failed to enable CTB (%pe)\n", ERR_PTR(err)); return err; @@ -321,8 +366,8 @@ void intel_guc_ct_disable(struct intel_guc_ct *ct) ct->enabled = false; if (intel_guc_is_fw_running(guc)) { - ct_deregister_buffer(ct, INTEL_GUC_CT_BUFFER_TYPE_SEND); - ct_deregister_buffer(ct, INTEL_GUC_CT_BUFFER_TYPE_RECV); + ct_deregister_buffer(ct, GUC_CTB_TYPE_HOST2GUC); + ct_deregister_buffer(ct, GUC_CTB_TYPE_GUC2HOST); } } @@ -354,81 +399,63 @@ static void write_barrier(struct intel_guc_ct *ct) } } -/** - * DOC: CTB Host to GuC request - * - * Format of the CTB Host to GuC request message is as follows:: - * - * +------------+---------+---------+---------+---------+ - * | msg[0] | [1] | [2] | ... | [n-1] | - * +------------+---------+---------+---------+---------+ - * | MESSAGE | MESSAGE PAYLOAD | - * + HEADER +---------+---------+---------+---------+ - * | | 0 | 1 | ... | n | - * +============+=========+=========+=========+=========+ - * | len >= 1 | FENCE | request specific data | - * +------+-----+---------+---------+---------+---------+ - * - * ^-----------------len-------------------^ - */ - static int ct_write(struct intel_guc_ct *ct, const u32 *action, u32 len /* in dwords */, - u32 fence) + u32 fence, u32 flags) { struct intel_guc_ct_buffer *ctb = &ct->ctbs.send; struct guc_ct_buffer_desc *desc = ctb->desc; - u32 head = desc->head; - u32 tail = desc->tail; + u32 tail = ctb->tail; u32 size = ctb->size; - u32 used; u32 header; + u32 hxg; + u32 type; u32 *cmds = ctb->cmds; unsigned int i; - if (unlikely(desc->is_in_error)) - return -EPIPE; - - if (unlikely(!IS_ALIGNED(head | tail, 4) || - (tail | head) >= size)) + if (unlikely(desc->status)) goto corrupted; - /* later calculations will be done in dwords */ - head /= 4; - tail /= 4; - size /= 4; - - /* - * tail == head condition indicates empty. GuC FW does not support - * using up the entire buffer to get tail == head meaning full. - */ - if (tail < head) - used = (size - head) + tail; - else - used = tail - head; + GEM_BUG_ON(tail > size); - /* make sure there is a space including extra dw for the fence */ - if (unlikely(used + len + 1 >= size)) - return -ENOSPC; +#ifdef CONFIG_DRM_I915_DEBUG_GUC + if (unlikely(tail != READ_ONCE(desc->tail))) { + CT_ERROR(ct, "Tail was modified %u != %u\n", + desc->tail, tail); + desc->status |= GUC_CTB_STATUS_MISMATCH; + goto corrupted; + } + if (unlikely(READ_ONCE(desc->head) >= size)) { + CT_ERROR(ct, "Invalid head offset %u >= %u)\n", + desc->head, size); + desc->status |= GUC_CTB_STATUS_OVERFLOW; + goto corrupted; + } +#endif /* - * Write the message. The format is the following: - * DW0: header (including action code) - * DW1: fence - * DW2+: action data + * dw0: CT header (including fence) + * dw1: HXG header (including action code) + * dw2+: action data */ - header = (len << GUC_CT_MSG_LEN_SHIFT) | - GUC_CT_MSG_SEND_STATUS | - (action[0] << GUC_CT_MSG_ACTION_SHIFT); + header = FIELD_PREP(GUC_CTB_MSG_0_FORMAT, GUC_CTB_FORMAT_HXG) | + FIELD_PREP(GUC_CTB_MSG_0_NUM_DWORDS, len) | + FIELD_PREP(GUC_CTB_MSG_0_FENCE, fence); - CT_DEBUG(ct, "writing %*ph %*ph %*ph\n", - 4, &header, 4, &fence, 4 * (len - 1), &action[1]); + type = (flags & INTEL_GUC_CT_SEND_NB) ? GUC_HXG_TYPE_EVENT : + GUC_HXG_TYPE_REQUEST; + hxg = FIELD_PREP(GUC_HXG_MSG_0_TYPE, type) | + FIELD_PREP(GUC_HXG_EVENT_MSG_0_ACTION | + GUC_HXG_EVENT_MSG_0_DATA0, action[0]); + + CT_DEBUG(ct, "writing (tail %u) %*ph %*ph %*ph\n", + tail, 4, &header, 4, &hxg, 4 * (len - 1), &action[1]); cmds[tail] = header; tail = (tail + 1) % size; - cmds[tail] = fence; + cmds[tail] = hxg; tail = (tail + 1) % size; for (i = 1; i < len; i++) { @@ -443,14 +470,20 @@ static int ct_write(struct intel_guc_ct *ct, */ write_barrier(ct); - /* now update desc tail (back in bytes) */ - desc->tail = tail * 4; + /* update local copies */ + ctb->tail = tail; + GEM_BUG_ON(atomic_read(&ctb->space) < len + GUC_CTB_HDR_LEN); + atomic_sub(len + GUC_CTB_HDR_LEN, &ctb->space); + + /* now update descriptor */ + WRITE_ONCE(desc->tail, tail); + return 0; corrupted: - CT_ERROR(ct, "Corrupted descriptor addr=%#x head=%u tail=%u size=%u\n", - desc->addr, desc->head, desc->tail, desc->size); - desc->is_in_error = 1; + CT_ERROR(ct, "Corrupted descriptor head=%u tail=%u status=%#x\n", + desc->head, desc->tail, desc->status); + ctb->broken = true; return -EPIPE; } @@ -459,7 +492,7 @@ corrupted: * @req: pointer to pending request * @status: placeholder for status * - * For each sent request, Guc shall send bac CT response message. + * For each sent request, GuC shall send back CT response message. * Our message handler will update status of tracked request once * response message with given fence is received. Wait here and * check for valid response status value. @@ -475,12 +508,18 @@ static int wait_for_ct_request_update(struct ct_request *req, u32 *status) /* * Fast commands should complete in less than 10us, so sample quickly * up to that length of time, then switch to a slower sleep-wait loop. - * No GuC command should ever take longer than 10ms. + * No GuC command should ever take longer than 10ms but many GuC + * commands can be inflight at time, so use a 1s timeout on the slower + * sleep-wait loop. */ -#define done INTEL_GUC_MSG_IS_RESPONSE(READ_ONCE(req->status)) - err = wait_for_us(done, 10); +#define GUC_CTB_RESPONSE_TIMEOUT_SHORT_MS 10 +#define GUC_CTB_RESPONSE_TIMEOUT_LONG_MS 1000 +#define done \ + (FIELD_GET(GUC_HXG_MSG_0_ORIGIN, READ_ONCE(req->status)) == \ + GUC_HXG_ORIGIN_GUC) + err = wait_for_us(done, GUC_CTB_RESPONSE_TIMEOUT_SHORT_MS); if (err) - err = wait_for(done, 10); + err = wait_for(done, GUC_CTB_RESPONSE_TIMEOUT_LONG_MS); #undef done if (unlikely(err)) @@ -490,6 +529,131 @@ static int wait_for_ct_request_update(struct ct_request *req, u32 *status) return err; } +#define GUC_CTB_TIMEOUT_MS 1500 +static inline bool ct_deadlocked(struct intel_guc_ct *ct) +{ + long timeout = GUC_CTB_TIMEOUT_MS; + bool ret = ktime_ms_delta(ktime_get(), ct->stall_time) > timeout; + + if (unlikely(ret)) { + struct guc_ct_buffer_desc *send = ct->ctbs.send.desc; + struct guc_ct_buffer_desc *recv = ct->ctbs.send.desc; + + CT_ERROR(ct, "Communication stalled for %lld ms, desc status=%#x,%#x\n", + ktime_ms_delta(ktime_get(), ct->stall_time), + send->status, recv->status); + ct->ctbs.send.broken = true; + } + + return ret; +} + +static inline bool g2h_has_room(struct intel_guc_ct *ct, u32 g2h_len_dw) +{ + struct intel_guc_ct_buffer *ctb = &ct->ctbs.recv; + + /* + * We leave a certain amount of space in the G2H CTB buffer for + * unexpected G2H CTBs (e.g. logging, engine hang, etc...) + */ + return !g2h_len_dw || atomic_read(&ctb->space) >= g2h_len_dw; +} + +static inline void g2h_reserve_space(struct intel_guc_ct *ct, u32 g2h_len_dw) +{ + lockdep_assert_held(&ct->ctbs.send.lock); + + GEM_BUG_ON(!g2h_has_room(ct, g2h_len_dw)); + + if (g2h_len_dw) + atomic_sub(g2h_len_dw, &ct->ctbs.recv.space); +} + +static inline void g2h_release_space(struct intel_guc_ct *ct, u32 g2h_len_dw) +{ + atomic_add(g2h_len_dw, &ct->ctbs.recv.space); +} + +static inline bool h2g_has_room(struct intel_guc_ct *ct, u32 len_dw) +{ + struct intel_guc_ct_buffer *ctb = &ct->ctbs.send; + struct guc_ct_buffer_desc *desc = ctb->desc; + u32 head; + u32 space; + + if (atomic_read(&ctb->space) >= len_dw) + return true; + + head = READ_ONCE(desc->head); + if (unlikely(head > ctb->size)) { + CT_ERROR(ct, "Invalid head offset %u >= %u)\n", + head, ctb->size); + desc->status |= GUC_CTB_STATUS_OVERFLOW; + ctb->broken = true; + return false; + } + + space = CIRC_SPACE(ctb->tail, head, ctb->size); + atomic_set(&ctb->space, space); + + return space >= len_dw; +} + +static int has_room_nb(struct intel_guc_ct *ct, u32 h2g_dw, u32 g2h_dw) +{ + lockdep_assert_held(&ct->ctbs.send.lock); + + if (unlikely(!h2g_has_room(ct, h2g_dw) || !g2h_has_room(ct, g2h_dw))) { + if (ct->stall_time == KTIME_MAX) + ct->stall_time = ktime_get(); + + if (unlikely(ct_deadlocked(ct))) + return -EPIPE; + else + return -EBUSY; + } + + ct->stall_time = KTIME_MAX; + return 0; +} + +#define G2H_LEN_DW(f) ({ \ + typeof(f) f_ = (f); \ + FIELD_GET(INTEL_GUC_CT_SEND_G2H_DW_MASK, f_) ? \ + FIELD_GET(INTEL_GUC_CT_SEND_G2H_DW_MASK, f_) + \ + GUC_CTB_HXG_MSG_MIN_LEN : 0; \ +}) +static int ct_send_nb(struct intel_guc_ct *ct, + const u32 *action, + u32 len, + u32 flags) +{ + struct intel_guc_ct_buffer *ctb = &ct->ctbs.send; + unsigned long spin_flags; + u32 g2h_len_dw = G2H_LEN_DW(flags); + u32 fence; + int ret; + + spin_lock_irqsave(&ctb->lock, spin_flags); + + ret = has_room_nb(ct, len + GUC_CTB_HDR_LEN, g2h_len_dw); + if (unlikely(ret)) + goto out; + + fence = ct_get_next_fence(ct); + ret = ct_write(ct, action, len, fence, flags); + if (unlikely(ret)) + goto out; + + g2h_reserve_space(ct, g2h_len_dw); + intel_guc_notify(ct_to_guc(ct)); + +out: + spin_unlock_irqrestore(&ctb->lock, spin_flags); + + return ret; +} + static int ct_send(struct intel_guc_ct *ct, const u32 *action, u32 len, @@ -497,8 +661,10 @@ static int ct_send(struct intel_guc_ct *ct, u32 response_buf_size, u32 *status) { + struct intel_guc_ct_buffer *ctb = &ct->ctbs.send; struct ct_request request; unsigned long flags; + unsigned int sleep_period_ms = 1; u32 fence; int err; @@ -506,8 +672,33 @@ static int ct_send(struct intel_guc_ct *ct, GEM_BUG_ON(!len); GEM_BUG_ON(len & ~GUC_CT_MSG_LEN_MASK); GEM_BUG_ON(!response_buf && response_buf_size); + might_sleep(); + + /* + * We use a lazy spin wait loop here as we believe that if the CT + * buffers are sized correctly the flow control condition should be + * rare. Reserving the maximum size in the G2H credits as we don't know + * how big the response is going to be. + */ +retry: + spin_lock_irqsave(&ctb->lock, flags); + if (unlikely(!h2g_has_room(ct, len + GUC_CTB_HDR_LEN) || + !g2h_has_room(ct, GUC_CTB_HXG_MSG_MAX_LEN))) { + if (ct->stall_time == KTIME_MAX) + ct->stall_time = ktime_get(); + spin_unlock_irqrestore(&ctb->lock, flags); + + if (unlikely(ct_deadlocked(ct))) + return -EPIPE; + + if (msleep_interruptible(sleep_period_ms)) + return -EINTR; + sleep_period_ms = sleep_period_ms << 1; + + goto retry; + } - spin_lock_irqsave(&ct->ctbs.send.lock, flags); + ct->stall_time = KTIME_MAX; fence = ct_get_next_fence(ct); request.fence = fence; @@ -519,9 +710,10 @@ static int ct_send(struct intel_guc_ct *ct, list_add_tail(&request.link, &ct->requests.pending); spin_unlock(&ct->requests.lock); - err = ct_write(ct, action, len, fence); + err = ct_write(ct, action, len, fence, 0); + g2h_reserve_space(ct, GUC_CTB_HXG_MSG_MAX_LEN); - spin_unlock_irqrestore(&ct->ctbs.send.lock, flags); + spin_unlock_irqrestore(&ctb->lock, flags); if (unlikely(err)) goto unlink; @@ -529,24 +721,25 @@ static int ct_send(struct intel_guc_ct *ct, intel_guc_notify(ct_to_guc(ct)); err = wait_for_ct_request_update(&request, status); + g2h_release_space(ct, GUC_CTB_HXG_MSG_MAX_LEN); if (unlikely(err)) goto unlink; - if (!INTEL_GUC_MSG_IS_RESPONSE_SUCCESS(*status)) { + if (FIELD_GET(GUC_HXG_MSG_0_TYPE, *status) != GUC_HXG_TYPE_RESPONSE_SUCCESS) { err = -EIO; goto unlink; } if (response_buf) { /* There shall be no data in the status */ - WARN_ON(INTEL_GUC_MSG_TO_DATA(request.status)); + WARN_ON(FIELD_GET(GUC_HXG_RESPONSE_MSG_0_DATA0, request.status)); /* Return actual response len */ err = request.response_len; } else { /* There shall be no response payload */ WARN_ON(request.response_len); /* Return data decoded from the status dword */ - err = INTEL_GUC_MSG_TO_DATA(*status); + err = FIELD_GET(GUC_HXG_RESPONSE_MSG_0_DATA0, *status); } unlink: @@ -561,16 +754,25 @@ unlink: * Command Transport (CT) buffer based GuC send function. */ int intel_guc_ct_send(struct intel_guc_ct *ct, const u32 *action, u32 len, - u32 *response_buf, u32 response_buf_size) + u32 *response_buf, u32 response_buf_size, u32 flags) { u32 status = ~0; /* undefined */ int ret; if (unlikely(!ct->enabled)) { - WARN(1, "Unexpected send: action=%#x\n", *action); + struct intel_guc *guc = ct_to_guc(ct); + struct intel_uc *uc = container_of(guc, struct intel_uc, guc); + + WARN(!uc->reset_in_progress, "Unexpected send: action=%#x\n", *action); return -ENODEV; } + if (unlikely(ct->ctbs.send.broken)) + return -EPIPE; + + if (flags & INTEL_GUC_CT_SEND_NB) + return ct_send_nb(ct, action, len, flags); + ret = ct_send(ct, action, len, response_buf, response_buf_size, &status); if (unlikely(ret < 0)) { CT_ERROR(ct, "Sending action %#x failed (err=%d status=%#X)\n", @@ -583,21 +785,6 @@ int intel_guc_ct_send(struct intel_guc_ct *ct, const u32 *action, u32 len, return ret; } -static inline unsigned int ct_header_get_len(u32 header) -{ - return (header >> GUC_CT_MSG_LEN_SHIFT) & GUC_CT_MSG_LEN_MASK; -} - -static inline unsigned int ct_header_get_action(u32 header) -{ - return (header >> GUC_CT_MSG_ACTION_SHIFT) & GUC_CT_MSG_ACTION_MASK; -} - -static inline bool ct_header_is_response(u32 header) -{ - return !!(header & GUC_CT_MSG_IS_RESPONSE); -} - static struct ct_incoming_msg *ct_alloc_msg(u32 num_dwords) { struct ct_incoming_msg *msg; @@ -621,8 +808,8 @@ static int ct_read(struct intel_guc_ct *ct, struct ct_incoming_msg **msg) { struct intel_guc_ct_buffer *ctb = &ct->ctbs.recv; struct guc_ct_buffer_desc *desc = ctb->desc; - u32 head = desc->head; - u32 tail = desc->tail; + u32 head = ctb->head; + u32 tail = READ_ONCE(desc->tail); u32 size = ctb->size; u32 *cmds = ctb->cmds; s32 available; @@ -630,17 +817,28 @@ static int ct_read(struct intel_guc_ct *ct, struct ct_incoming_msg **msg) unsigned int i; u32 header; - if (unlikely(desc->is_in_error)) + if (unlikely(ctb->broken)) return -EPIPE; - if (unlikely(!IS_ALIGNED(head | tail, 4) || - (tail | head) >= size)) + if (unlikely(desc->status)) goto corrupted; - /* later calculations will be done in dwords */ - head /= 4; - tail /= 4; - size /= 4; + GEM_BUG_ON(head > size); + +#ifdef CONFIG_DRM_I915_DEBUG_GUC + if (unlikely(head != READ_ONCE(desc->head))) { + CT_ERROR(ct, "Head was modified %u != %u\n", + desc->head, head); + desc->status |= GUC_CTB_STATUS_MISMATCH; + goto corrupted; + } +#endif + if (unlikely(tail >= size)) { + CT_ERROR(ct, "Invalid tail offset %u >= %u)\n", + tail, size); + desc->status |= GUC_CTB_STATUS_OVERFLOW; + goto corrupted; + } /* tail == head condition indicates empty */ available = tail - head; @@ -652,14 +850,14 @@ static int ct_read(struct intel_guc_ct *ct, struct ct_incoming_msg **msg) /* beware of buffer wrap case */ if (unlikely(available < 0)) available += size; - CT_DEBUG(ct, "available %d (%u:%u)\n", available, head, tail); + CT_DEBUG(ct, "available %d (%u:%u:%u)\n", available, head, tail, size); GEM_BUG_ON(available < 0); header = cmds[head]; head = (head + 1) % size; /* message len with header */ - len = ct_header_get_len(header) + 1; + len = FIELD_GET(GUC_CTB_MSG_0_NUM_DWORDS, header) + GUC_CTB_MSG_MIN_LEN; if (unlikely(len > (u32)available)) { CT_ERROR(ct, "Incomplete message %*ph %*ph %*ph\n", 4, &header, @@ -667,6 +865,7 @@ static int ct_read(struct intel_guc_ct *ct, struct ct_incoming_msg **msg) size - head : available - 1), &cmds[head], 4 * (head + available - 1 > size ? available - 1 - size + head : 0), &cmds[0]); + desc->status |= GUC_CTB_STATUS_UNDERFLOW; goto corrupted; } @@ -689,65 +888,39 @@ static int ct_read(struct intel_guc_ct *ct, struct ct_incoming_msg **msg) } CT_DEBUG(ct, "received %*ph\n", 4 * len, (*msg)->msg); - desc->head = head * 4; + /* update local copies */ + ctb->head = head; + + /* now update descriptor */ + WRITE_ONCE(desc->head, head); + return available - len; corrupted: - CT_ERROR(ct, "Corrupted descriptor addr=%#x head=%u tail=%u size=%u\n", - desc->addr, desc->head, desc->tail, desc->size); - desc->is_in_error = 1; + CT_ERROR(ct, "Corrupted descriptor head=%u tail=%u status=%#x\n", + desc->head, desc->tail, desc->status); + ctb->broken = true; return -EPIPE; } -/** - * DOC: CTB GuC to Host response - * - * Format of the CTB GuC to Host response message is as follows:: - * - * +------------+---------+---------+---------+---------+---------+ - * | msg[0] | [1] | [2] | [3] | ... | [n-1] | - * +------------+---------+---------+---------+---------+---------+ - * | MESSAGE | MESSAGE PAYLOAD | - * + HEADER +---------+---------+---------+---------+---------+ - * | | 0 | 1 | 2 | ... | n | - * +============+=========+=========+=========+=========+=========+ - * | len >= 2 | FENCE | STATUS | response specific data | - * +------+-----+---------+---------+---------+---------+---------+ - * - * ^-----------------------len-----------------------^ - */ - static int ct_handle_response(struct intel_guc_ct *ct, struct ct_incoming_msg *response) { - u32 header = response->msg[0]; - u32 len = ct_header_get_len(header); - u32 fence; - u32 status; - u32 datalen; + u32 len = FIELD_GET(GUC_CTB_MSG_0_NUM_DWORDS, response->msg[0]); + u32 fence = FIELD_GET(GUC_CTB_MSG_0_FENCE, response->msg[0]); + const u32 *hxg = &response->msg[GUC_CTB_MSG_MIN_LEN]; + const u32 *data = &hxg[GUC_HXG_MSG_MIN_LEN]; + u32 datalen = len - GUC_HXG_MSG_MIN_LEN; struct ct_request *req; unsigned long flags; bool found = false; int err = 0; - GEM_BUG_ON(!ct_header_is_response(header)); - - /* Response payload shall at least include fence and status */ - if (unlikely(len < 2)) { - CT_ERROR(ct, "Corrupted response (len %u)\n", len); - return -EPROTO; - } - - fence = response->msg[1]; - status = response->msg[2]; - datalen = len - 2; - - /* Format of the status follows RESPONSE message */ - if (unlikely(!INTEL_GUC_MSG_IS_RESPONSE(status))) { - CT_ERROR(ct, "Corrupted response (status %#x)\n", status); - return -EPROTO; - } + GEM_BUG_ON(len < GUC_HXG_MSG_MIN_LEN); + GEM_BUG_ON(FIELD_GET(GUC_HXG_MSG_0_ORIGIN, hxg[0]) != GUC_HXG_ORIGIN_GUC); + GEM_BUG_ON(FIELD_GET(GUC_HXG_MSG_0_TYPE, hxg[0]) != GUC_HXG_TYPE_RESPONSE_SUCCESS && + FIELD_GET(GUC_HXG_MSG_0_TYPE, hxg[0]) != GUC_HXG_TYPE_RESPONSE_FAILURE); - CT_DEBUG(ct, "response fence %u status %#x\n", fence, status); + CT_DEBUG(ct, "response fence %u status %#x\n", fence, hxg[0]); spin_lock_irqsave(&ct->requests.lock, flags); list_for_each_entry(req, &ct->requests.pending, link) { @@ -763,18 +936,22 @@ static int ct_handle_response(struct intel_guc_ct *ct, struct ct_incoming_msg *r err = -EMSGSIZE; } if (datalen) - memcpy(req->response_buf, response->msg + 3, 4 * datalen); + memcpy(req->response_buf, data, 4 * datalen); req->response_len = datalen; - WRITE_ONCE(req->status, status); + WRITE_ONCE(req->status, hxg[0]); found = true; break; } - spin_unlock_irqrestore(&ct->requests.lock, flags); - if (!found) { CT_ERROR(ct, "Unsolicited response (fence %u)\n", fence); - return -ENOKEY; + CT_ERROR(ct, "Could not find fence=%u, last_fence=%u\n", fence, + ct->requests.last_fence); + list_for_each_entry(req, &ct->requests.pending, link) + CT_ERROR(ct, "request %u awaits response\n", + req->fence); + err = -ENOKEY; } + spin_unlock_irqrestore(&ct->requests.lock, flags); if (unlikely(err)) return err; @@ -786,14 +963,16 @@ static int ct_handle_response(struct intel_guc_ct *ct, struct ct_incoming_msg *r static int ct_process_request(struct intel_guc_ct *ct, struct ct_incoming_msg *request) { struct intel_guc *guc = ct_to_guc(ct); - u32 header, action, len; + const u32 *hxg; const u32 *payload; + u32 hxg_len, action, len; int ret; - header = request->msg[0]; - payload = &request->msg[1]; - action = ct_header_get_action(header); - len = ct_header_get_len(header); + hxg = &request->msg[GUC_CTB_MSG_MIN_LEN]; + hxg_len = request->size - GUC_CTB_MSG_MIN_LEN; + payload = &hxg[GUC_HXG_MSG_MIN_LEN]; + action = FIELD_GET(GUC_HXG_EVENT_MSG_0_ACTION, hxg[0]); + len = hxg_len - GUC_HXG_MSG_MIN_LEN; CT_DEBUG(ct, "request %x %*ph\n", action, 4 * len, payload); @@ -801,6 +980,19 @@ static int ct_process_request(struct intel_guc_ct *ct, struct ct_incoming_msg *r case INTEL_GUC_ACTION_DEFAULT: ret = intel_guc_to_host_process_recv_msg(guc, payload, len); break; + case INTEL_GUC_ACTION_DEREGISTER_CONTEXT_DONE: + ret = intel_guc_deregister_done_process_msg(guc, payload, + len); + break; + case INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_DONE: + ret = intel_guc_sched_done_process_msg(guc, payload, len); + break; + case INTEL_GUC_ACTION_CONTEXT_RESET_NOTIFICATION: + ret = intel_guc_context_reset_process_msg(guc, payload, len); + break; + case INTEL_GUC_ACTION_ENGINE_FAILURE_NOTIFICATION: + ret = intel_guc_engine_failure_process_msg(guc, payload, len); + break; default: ret = -EOPNOTSUPP; break; @@ -855,29 +1047,24 @@ static void ct_incoming_request_worker_func(struct work_struct *w) queue_work(system_unbound_wq, &ct->requests.worker); } -/** - * DOC: CTB GuC to Host request - * - * Format of the CTB GuC to Host request message is as follows:: - * - * +------------+---------+---------+---------+---------+---------+ - * | msg[0] | [1] | [2] | [3] | ... | [n-1] | - * +------------+---------+---------+---------+---------+---------+ - * | MESSAGE | MESSAGE PAYLOAD | - * + HEADER +---------+---------+---------+---------+---------+ - * | | 0 | 1 | 2 | ... | n | - * +============+=========+=========+=========+=========+=========+ - * | len | request specific data | - * +------+-----+---------+---------+---------+---------+---------+ - * - * ^-----------------------len-----------------------^ - */ - -static int ct_handle_request(struct intel_guc_ct *ct, struct ct_incoming_msg *request) +static int ct_handle_event(struct intel_guc_ct *ct, struct ct_incoming_msg *request) { + const u32 *hxg = &request->msg[GUC_CTB_MSG_MIN_LEN]; + u32 action = FIELD_GET(GUC_HXG_EVENT_MSG_0_ACTION, hxg[0]); unsigned long flags; - GEM_BUG_ON(ct_header_is_response(request->msg[0])); + GEM_BUG_ON(FIELD_GET(GUC_HXG_MSG_0_TYPE, hxg[0]) != GUC_HXG_TYPE_EVENT); + + /* + * Adjusting the space must be done in IRQ or deadlock can occur as the + * CTB processing in the below workqueue can send CTBs which creates a + * circular dependency if the space was returned there. + */ + switch (action) { + case INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_DONE: + case INTEL_GUC_ACTION_DEREGISTER_CONTEXT_DONE: + g2h_release_space(ct, request->size); + } spin_lock_irqsave(&ct->requests.lock, flags); list_add_tail(&request->link, &ct->requests.incoming); @@ -887,15 +1074,53 @@ static int ct_handle_request(struct intel_guc_ct *ct, struct ct_incoming_msg *re return 0; } -static void ct_handle_msg(struct intel_guc_ct *ct, struct ct_incoming_msg *msg) +static int ct_handle_hxg(struct intel_guc_ct *ct, struct ct_incoming_msg *msg) { - u32 header = msg->msg[0]; + u32 origin, type; + u32 *hxg; int err; - if (ct_header_is_response(header)) + if (unlikely(msg->size < GUC_CTB_HXG_MSG_MIN_LEN)) + return -EBADMSG; + + hxg = &msg->msg[GUC_CTB_MSG_MIN_LEN]; + + origin = FIELD_GET(GUC_HXG_MSG_0_ORIGIN, hxg[0]); + if (unlikely(origin != GUC_HXG_ORIGIN_GUC)) { + err = -EPROTO; + goto failed; + } + + type = FIELD_GET(GUC_HXG_MSG_0_TYPE, hxg[0]); + switch (type) { + case GUC_HXG_TYPE_EVENT: + err = ct_handle_event(ct, msg); + break; + case GUC_HXG_TYPE_RESPONSE_SUCCESS: + case GUC_HXG_TYPE_RESPONSE_FAILURE: err = ct_handle_response(ct, msg); + break; + default: + err = -EOPNOTSUPP; + } + + if (unlikely(err)) { +failed: + CT_ERROR(ct, "Failed to handle HXG message (%pe) %*ph\n", + ERR_PTR(err), 4 * GUC_HXG_MSG_MIN_LEN, hxg); + } + return err; +} + +static void ct_handle_msg(struct intel_guc_ct *ct, struct ct_incoming_msg *msg) +{ + u32 format = FIELD_GET(GUC_CTB_MSG_0_FORMAT, msg->msg[0]); + int err; + + if (format == GUC_CTB_FORMAT_HXG) + err = ct_handle_hxg(ct, msg); else - err = ct_handle_request(ct, msg); + err = -EOPNOTSUPP; if (unlikely(err)) { CT_ERROR(ct, "Failed to process CT message (%pe) %*ph\n", @@ -958,3 +1183,25 @@ void intel_guc_ct_event_handler(struct intel_guc_ct *ct) ct_try_receive_message(ct); } + +void intel_guc_ct_print_info(struct intel_guc_ct *ct, + struct drm_printer *p) +{ + drm_printf(p, "CT %s\n", enableddisabled(ct->enabled)); + + if (!ct->enabled) + return; + + drm_printf(p, "H2G Space: %u\n", + atomic_read(&ct->ctbs.send.space) * 4); + drm_printf(p, "Head: %u\n", + ct->ctbs.send.desc->head); + drm_printf(p, "Tail: %u\n", + ct->ctbs.send.desc->tail); + drm_printf(p, "G2H Space: %u\n", + atomic_read(&ct->ctbs.recv.space) * 4); + drm_printf(p, "Head: %u\n", + ct->ctbs.recv.desc->head); + drm_printf(p, "Tail: %u\n", + ct->ctbs.recv.desc->tail); +} diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h index cb222f202301..f709a19c7e21 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h @@ -9,11 +9,14 @@ #include <linux/interrupt.h> #include <linux/spinlock.h> #include <linux/workqueue.h> +#include <linux/ktime.h> +#include <linux/wait.h> #include "intel_guc_fwif.h" struct i915_vma; struct intel_guc; +struct drm_printer; /** * DOC: Command Transport (CT). @@ -31,16 +34,25 @@ struct intel_guc; * @lock: protects access to the commands buffer and buffer descriptor * @desc: pointer to the buffer descriptor * @cmds: pointer to the commands buffer - * @size: size of the commands buffer + * @size: size of the commands buffer in dwords + * @resv_space: reserved space in buffer in dwords + * @head: local shadow copy of head in dwords + * @tail: local shadow copy of tail in dwords + * @space: local shadow copy of space in dwords + * @broken: flag to indicate if descriptor data is broken */ struct intel_guc_ct_buffer { spinlock_t lock; struct guc_ct_buffer_desc *desc; u32 *cmds; u32 size; + u32 resv_space; + u32 tail; + u32 head; + atomic_t space; + bool broken; }; - /** Top-level structure for Command Transport related data * * Includes a pair of CT buffers for bi-directional communication and tracking @@ -58,8 +70,11 @@ struct intel_guc_ct { struct tasklet_struct receive_tasklet; + /** @wq: wait queue for g2h chanenl */ + wait_queue_head_t wq; + struct { - u32 last_fence; /* last fence used to send request */ + u16 last_fence; /* last fence used to send request */ spinlock_t lock; /* protects pending requests list */ struct list_head pending; /* requests waiting for response */ @@ -67,6 +82,9 @@ struct intel_guc_ct { struct list_head incoming; /* incoming requests */ struct work_struct worker; /* handler for incoming requests */ } requests; + + /** @stall_time: time of first time a CTB submission is stalled */ + ktime_t stall_time; }; void intel_guc_ct_init_early(struct intel_guc_ct *ct); @@ -85,8 +103,18 @@ static inline bool intel_guc_ct_enabled(struct intel_guc_ct *ct) return ct->enabled; } +#define INTEL_GUC_CT_SEND_NB BIT(31) +#define INTEL_GUC_CT_SEND_G2H_DW_SHIFT 0 +#define INTEL_GUC_CT_SEND_G2H_DW_MASK (0xff << INTEL_GUC_CT_SEND_G2H_DW_SHIFT) +#define MAKE_SEND_FLAGS(len) ({ \ + typeof(len) len_ = (len); \ + GEM_BUG_ON(!FIELD_FIT(INTEL_GUC_CT_SEND_G2H_DW_MASK, len_)); \ + (FIELD_PREP(INTEL_GUC_CT_SEND_G2H_DW_MASK, len_) | INTEL_GUC_CT_SEND_NB); \ +}) int intel_guc_ct_send(struct intel_guc_ct *ct, const u32 *action, u32 len, - u32 *response_buf, u32 response_buf_size); + u32 *response_buf, u32 response_buf_size, u32 flags); void intel_guc_ct_event_handler(struct intel_guc_ct *ct); +void intel_guc_ct_print_info(struct intel_guc_ct *ct, struct drm_printer *p); + #endif /* _INTEL_GUC_CT_H_ */ diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c index fe7cb7b29a1e..887c8c8f35db 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c @@ -9,6 +9,10 @@ #include "intel_guc.h" #include "intel_guc_debugfs.h" #include "intel_guc_log_debugfs.h" +#include "gt/uc/intel_guc_ct.h" +#include "gt/uc/intel_guc_ads.h" +#include "gt/uc/intel_guc_submission.h" +#include "gt/uc/intel_guc_slpc.h" static int guc_info_show(struct seq_file *m, void *data) { @@ -22,16 +26,57 @@ static int guc_info_show(struct seq_file *m, void *data) drm_puts(&p, "\n"); intel_guc_log_info(&guc->log, &p); - /* Add more as required ... */ + if (!intel_guc_submission_is_used(guc)) + return 0; + + intel_guc_ct_print_info(&guc->ct, &p); + intel_guc_submission_print_info(guc, &p); + intel_guc_ads_print_policy_info(guc, &p); return 0; } DEFINE_GT_DEBUGFS_ATTRIBUTE(guc_info); +static int guc_registered_contexts_show(struct seq_file *m, void *data) +{ + struct intel_guc *guc = m->private; + struct drm_printer p = drm_seq_file_printer(m); + + if (!intel_guc_submission_is_used(guc)) + return -ENODEV; + + intel_guc_submission_print_context_info(guc, &p); + + return 0; +} +DEFINE_GT_DEBUGFS_ATTRIBUTE(guc_registered_contexts); + +static int guc_slpc_info_show(struct seq_file *m, void *unused) +{ + struct intel_guc *guc = m->private; + struct intel_guc_slpc *slpc = &guc->slpc; + struct drm_printer p = drm_seq_file_printer(m); + + if (!intel_guc_slpc_is_used(guc)) + return -ENODEV; + + return intel_guc_slpc_print_info(slpc, &p); +} +DEFINE_GT_DEBUGFS_ATTRIBUTE(guc_slpc_info); + +static bool intel_eval_slpc_support(void *data) +{ + struct intel_guc *guc = (struct intel_guc *)data; + + return intel_guc_slpc_is_used(guc); +} + void intel_guc_debugfs_register(struct intel_guc *guc, struct dentry *root) { static const struct debugfs_gt_file files[] = { { "guc_info", &guc_info_fops, NULL }, + { "guc_registered_contexts", &guc_registered_contexts_fops, NULL }, + { "guc_slpc_info", &guc_slpc_info_fops, &intel_eval_slpc_support}, }; if (!intel_guc_is_supported(guc)) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h index e9a9d85e2aa3..fa4be13c8854 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h @@ -12,19 +12,27 @@ #include "gt/intel_engine_types.h" #include "abi/guc_actions_abi.h" +#include "abi/guc_actions_slpc_abi.h" #include "abi/guc_errors_abi.h" #include "abi/guc_communication_mmio_abi.h" #include "abi/guc_communication_ctb_abi.h" #include "abi/guc_messages_abi.h" +/* Payload length only i.e. don't include G2H header length */ +#define G2H_LEN_DW_SCHED_CONTEXT_MODE_SET 2 +#define G2H_LEN_DW_DEREGISTER_CONTEXT 1 + +#define GUC_CONTEXT_DISABLE 0 +#define GUC_CONTEXT_ENABLE 1 + #define GUC_CLIENT_PRIORITY_KMD_HIGH 0 #define GUC_CLIENT_PRIORITY_HIGH 1 #define GUC_CLIENT_PRIORITY_KMD_NORMAL 2 #define GUC_CLIENT_PRIORITY_NORMAL 3 #define GUC_CLIENT_PRIORITY_NUM 4 -#define GUC_MAX_STAGE_DESCRIPTORS 1024 -#define GUC_INVALID_STAGE_ID GUC_MAX_STAGE_DESCRIPTORS +#define GUC_MAX_LRC_DESCRIPTORS 65535 +#define GUC_INVALID_LRC_ID GUC_MAX_LRC_DESCRIPTORS #define GUC_RENDER_ENGINE 0 #define GUC_VIDEO_ENGINE 1 @@ -81,15 +89,14 @@ #define GUC_LOG_ALLOC_IN_MEGABYTE (1 << 3) #define GUC_LOG_CRASH_SHIFT 4 #define GUC_LOG_CRASH_MASK (0x3 << GUC_LOG_CRASH_SHIFT) -#define GUC_LOG_DPC_SHIFT 6 -#define GUC_LOG_DPC_MASK (0x7 << GUC_LOG_DPC_SHIFT) -#define GUC_LOG_ISR_SHIFT 9 -#define GUC_LOG_ISR_MASK (0x7 << GUC_LOG_ISR_SHIFT) +#define GUC_LOG_DEBUG_SHIFT 6 +#define GUC_LOG_DEBUG_MASK (0xF << GUC_LOG_DEBUG_SHIFT) #define GUC_LOG_BUF_ADDR_SHIFT 12 #define GUC_CTL_WA 1 #define GUC_CTL_FEATURE 2 #define GUC_CTL_DISABLE_SCHEDULER (1 << 14) +#define GUC_CTL_ENABLE_SLPC BIT(2) #define GUC_CTL_DEBUG 3 #define GUC_LOG_VERBOSITY_SHIFT 0 @@ -136,6 +143,11 @@ #define GUC_ID_TO_ENGINE_INSTANCE(guc_id) \ (((guc_id) & GUC_ENGINE_INSTANCE_MASK) >> GUC_ENGINE_INSTANCE_SHIFT) +#define SLPC_EVENT(id, c) (\ +FIELD_PREP(HOST2GUC_PC_SLPC_REQUEST_MSG_1_EVENT_ID, id) | \ +FIELD_PREP(HOST2GUC_PC_SLPC_REQUEST_MSG_1_EVENT_ARGC, c) \ +) + static inline u8 engine_class_to_guc_class(u8 class) { BUILD_BUG_ON(GUC_RENDER_CLASS != RENDER_CLASS); @@ -177,66 +189,40 @@ struct guc_process_desc { u32 reserved[30]; } __packed; -/* engine id and context id is packed into guc_execlist_context.context_id*/ -#define GUC_ELC_CTXID_OFFSET 0 -#define GUC_ELC_ENGINE_OFFSET 29 +#define CONTEXT_REGISTRATION_FLAG_KMD BIT(0) -/* The execlist context including software and HW information */ -struct guc_execlist_context { - u32 context_desc; - u32 context_id; - u32 ring_status; - u32 ring_lrca; - u32 ring_begin; - u32 ring_end; - u32 ring_next_free_location; - u32 ring_current_tail_pointer_value; - u8 engine_state_submit_value; - u8 engine_state_wait_value; - u16 pagefault_count; - u16 engine_submit_queue_count; -} __packed; +#define CONTEXT_POLICY_DEFAULT_EXECUTION_QUANTUM_US 1000000 +#define CONTEXT_POLICY_DEFAULT_PREEMPTION_TIME_US 500000 + +/* Preempt to idle on quantum expiry */ +#define CONTEXT_POLICY_FLAG_PREEMPT_TO_IDLE BIT(0) /* - * This structure describes a stage set arranged for a particular communication - * between uKernel (GuC) and Driver (KMD). Technically, this is known as a - * "GuC Context descriptor" in the specs, but we use the term "stage descriptor" - * to avoid confusion with all the other things already named "context" in the - * driver. A static pool of these descriptors are stored inside a GEM object - * (stage_desc_pool) which is held for the entire lifetime of our interaction - * with the GuC, being allocated before the GuC is loaded with its firmware. + * GuC Context registration descriptor. + * FIXME: This is only required to exist during context registration. + * The current 1:1 between guc_lrc_desc and LRCs for the lifetime of the LRC + * is not required. */ -struct guc_stage_desc { - u32 sched_common_area; - u32 stage_id; - u32 pas_id; - u8 engines_used; - u64 db_trigger_cpu; - u32 db_trigger_uk; - u64 db_trigger_phy; - u16 db_id; - - struct guc_execlist_context lrc[GUC_MAX_ENGINES_NUM]; - - u8 attribute; - +struct guc_lrc_desc { + u32 hw_context_desc; + u32 slpm_perf_mode_hint; /* SPLC v1 only */ + u32 slpm_freq_hint; + u32 engine_submit_mask; /* In logical space */ + u8 engine_class; + u8 reserved0[3]; u32 priority; - - u32 wq_sampled_tail_offset; - u32 wq_total_submit_enqueues; - u32 process_desc; u32 wq_addr; u32 wq_size; - - u32 engine_presence; - - u8 engine_suspended; - - u8 reserved0[3]; - u64 reserved1[1]; - - u64 desc_private; + u32 context_flags; /* CONTEXT_REGISTRATION_* */ + /* Time for one workload to execute. (in micro seconds) */ + u32 execution_quantum; + /* Time to wait for a preemption request to complete before issuing a + * reset. (in micro seconds). + */ + u32 preemption_timeout; + u32 policy_flags; /* CONTEXT_POLICY_* */ + u32 reserved1[19]; } __packed; #define GUC_POWER_UNSPECIFIED 0 @@ -247,32 +233,14 @@ struct guc_stage_desc { /* Scheduling policy settings */ -/* Reset engine upon preempt failure */ -#define POLICY_RESET_ENGINE (1<<0) -/* Preempt to idle on quantum expiry */ -#define POLICY_PREEMPT_TO_IDLE (1<<1) +#define GLOBAL_POLICY_MAX_NUM_WI 15 -#define POLICY_MAX_NUM_WI 15 -#define POLICY_DEFAULT_DPC_PROMOTE_TIME_US 500000 -#define POLICY_DEFAULT_EXECUTION_QUANTUM_US 1000000 -#define POLICY_DEFAULT_PREEMPTION_TIME_US 500000 -#define POLICY_DEFAULT_FAULT_TIME_US 250000 +/* Don't reset an engine upon preemption failure */ +#define GLOBAL_POLICY_DISABLE_ENGINE_RESET BIT(0) -struct guc_policy { - /* Time for one workload to execute. (in micro seconds) */ - u32 execution_quantum; - /* Time to wait for a preemption request to completed before issuing a - * reset. (in micro seconds). */ - u32 preemption_time; - /* How much time to allow to run after the first fault is observed. - * Then preempt afterwards. (in micro seconds) */ - u32 fault_time; - u32 policy_flags; - u32 reserved[8]; -} __packed; +#define GLOBAL_POLICY_DEFAULT_DPC_PROMOTE_TIME_US 500000 struct guc_policies { - struct guc_policy policy[GUC_CLIENT_PRIORITY_NUM][GUC_MAX_ENGINE_CLASSES]; u32 submission_queue_depth[GUC_MAX_ENGINE_CLASSES]; /* In micro seconds. How much time to allow before DPC processing is * called back via interrupt (to prevent DPC queue drain starving). @@ -286,6 +254,7 @@ struct guc_policies { * idle. */ u32 max_num_work_items; + u32 global_flags; u32 reserved[4]; } __packed; @@ -311,29 +280,13 @@ struct guc_gt_system_info { u32 generic_gt_sysinfo[GUC_GENERIC_GT_SYSINFO_MAX]; } __packed; -/* Clients info */ -struct guc_ct_pool_entry { - struct guc_ct_buffer_desc desc; - u32 reserved[7]; -} __packed; - -#define GUC_CT_POOL_SIZE 2 - -struct guc_clients_info { - u32 clients_num; - u32 reserved0[13]; - u32 ct_pool_addr; - u32 ct_pool_count; - u32 reserved[4]; -} __packed; - /* GuC Additional Data Struct */ struct guc_ads { struct guc_mmio_reg_set reg_state_list[GUC_MAX_ENGINE_CLASSES][GUC_MAX_INSTANCES_PER_CLASS]; u32 reserved0; u32 scheduler_policies; u32 gt_system_info; - u32 clients_info; + u32 reserved1; u32 control_data; u32 golden_context_lrca[GUC_MAX_ENGINE_CLASSES]; u32 eng_state_size[GUC_MAX_ENGINE_CLASSES]; @@ -344,8 +297,7 @@ struct guc_ads { /* GuC logging structures */ enum guc_log_buffer_type { - GUC_ISR_LOG_BUFFER, - GUC_DPC_LOG_BUFFER, + GUC_DEBUG_LOG_BUFFER, GUC_CRASH_DUMP_LOG_BUFFER, GUC_MAX_LOG_BUFFER }; @@ -414,23 +366,6 @@ struct guc_shared_ctx_data { struct guc_ctx_report preempt_ctx_report[GUC_MAX_ENGINES_NUM]; } __packed; -#define __INTEL_GUC_MSG_GET(T, m) \ - (((m) & INTEL_GUC_MSG_ ## T ## _MASK) >> INTEL_GUC_MSG_ ## T ## _SHIFT) -#define INTEL_GUC_MSG_TO_TYPE(m) __INTEL_GUC_MSG_GET(TYPE, m) -#define INTEL_GUC_MSG_TO_DATA(m) __INTEL_GUC_MSG_GET(DATA, m) -#define INTEL_GUC_MSG_TO_CODE(m) __INTEL_GUC_MSG_GET(CODE, m) - -#define __INTEL_GUC_MSG_TYPE_IS(T, m) \ - (INTEL_GUC_MSG_TO_TYPE(m) == INTEL_GUC_MSG_TYPE_ ## T) -#define INTEL_GUC_MSG_IS_REQUEST(m) __INTEL_GUC_MSG_TYPE_IS(REQUEST, m) -#define INTEL_GUC_MSG_IS_RESPONSE(m) __INTEL_GUC_MSG_TYPE_IS(RESPONSE, m) - -#define INTEL_GUC_MSG_IS_RESPONSE_SUCCESS(m) \ - (typecheck(u32, (m)) && \ - ((m) & (INTEL_GUC_MSG_TYPE_MASK | INTEL_GUC_MSG_CODE_MASK)) == \ - ((INTEL_GUC_MSG_TYPE_RESPONSE << INTEL_GUC_MSG_TYPE_SHIFT) | \ - (INTEL_GUC_RESPONSE_STATUS_SUCCESS << INTEL_GUC_MSG_CODE_SHIFT))) - /* This action will be programmed in C1BC - SOFT_SCRATCH_15_REG */ enum intel_guc_recv_message { INTEL_GUC_RECV_MSG_CRASH_DUMP_POSTED = BIT(1), diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c index c36d5eb5bbb9..ac0931f0374b 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c @@ -197,10 +197,8 @@ static bool guc_check_log_buf_overflow(struct intel_guc_log *log, static unsigned int guc_get_log_buffer_size(enum guc_log_buffer_type type) { switch (type) { - case GUC_ISR_LOG_BUFFER: - return ISR_BUFFER_SIZE; - case GUC_DPC_LOG_BUFFER: - return DPC_BUFFER_SIZE; + case GUC_DEBUG_LOG_BUFFER: + return DEBUG_BUFFER_SIZE; case GUC_CRASH_DUMP_LOG_BUFFER: return CRASH_BUFFER_SIZE; default: @@ -245,7 +243,7 @@ static void guc_read_update_log_buffer(struct intel_guc_log *log) src_data += PAGE_SIZE; dst_data += PAGE_SIZE; - for (type = GUC_ISR_LOG_BUFFER; type < GUC_MAX_LOG_BUFFER; type++) { + for (type = GUC_DEBUG_LOG_BUFFER; type < GUC_MAX_LOG_BUFFER; type++) { /* * Make a copy of the state structure, inside GuC log buffer * (which is uncached mapped), on the stack to avoid reading @@ -463,21 +461,16 @@ int intel_guc_log_create(struct intel_guc_log *log) * +===============================+ 00B * | Crash dump state header | * +-------------------------------+ 32B - * | DPC state header | + * | Debug state header | * +-------------------------------+ 64B - * | ISR state header | - * +-------------------------------+ 96B * | | * +===============================+ PAGE_SIZE (4KB) * | Crash Dump logs | * +===============================+ + CRASH_SIZE - * | DPC logs | - * +===============================+ + DPC_SIZE - * | ISR logs | - * +===============================+ + ISR_SIZE + * | Debug logs | + * +===============================+ + DEBUG_SIZE */ - guc_log_size = PAGE_SIZE + CRASH_BUFFER_SIZE + DPC_BUFFER_SIZE + - ISR_BUFFER_SIZE; + guc_log_size = PAGE_SIZE + CRASH_BUFFER_SIZE + DEBUG_BUFFER_SIZE; vma = intel_guc_allocate_vma(guc, guc_log_size); if (IS_ERR(vma)) { @@ -675,10 +668,8 @@ static const char * stringify_guc_log_type(enum guc_log_buffer_type type) { switch (type) { - case GUC_ISR_LOG_BUFFER: - return "ISR"; - case GUC_DPC_LOG_BUFFER: - return "DPC"; + case GUC_DEBUG_LOG_BUFFER: + return "DEBUG"; case GUC_CRASH_DUMP_LOG_BUFFER: return "CRASH"; default: @@ -708,7 +699,7 @@ void intel_guc_log_info(struct intel_guc_log *log, struct drm_printer *p) drm_printf(p, "\tRelay full count: %u\n", log->relay.full_count); - for (type = GUC_ISR_LOG_BUFFER; type < GUC_MAX_LOG_BUFFER; type++) { + for (type = GUC_DEBUG_LOG_BUFFER; type < GUC_MAX_LOG_BUFFER; type++) { drm_printf(p, "\t%s:\tflush count %10u, overflow count %10u\n", stringify_guc_log_type(type), log->stats[type].flush, diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h index 11fccd0b2294..ac1ee1d5ce10 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h @@ -17,12 +17,10 @@ struct intel_guc; #ifdef CONFIG_DRM_I915_DEBUG_GUC #define CRASH_BUFFER_SIZE SZ_2M -#define DPC_BUFFER_SIZE SZ_8M -#define ISR_BUFFER_SIZE SZ_8M +#define DEBUG_BUFFER_SIZE SZ_16M #else #define CRASH_BUFFER_SIZE SZ_8K -#define DPC_BUFFER_SIZE SZ_32K -#define ISR_BUFFER_SIZE SZ_32K +#define DEBUG_BUFFER_SIZE SZ_64K #endif /* diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.c new file mode 100644 index 000000000000..fc805d466d99 --- /dev/null +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.c @@ -0,0 +1,80 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2021 Intel Corporation + */ + +#include "intel_guc_rc.h" +#include "gt/intel_gt.h" +#include "i915_drv.h" + +static bool __guc_rc_supported(struct intel_guc *guc) +{ + /* GuC RC is unavailable for pre-Gen12 */ + return guc->submission_supported && + GRAPHICS_VER(guc_to_gt(guc)->i915) >= 12; +} + +static bool __guc_rc_selected(struct intel_guc *guc) +{ + if (!intel_guc_rc_is_supported(guc)) + return false; + + return guc->submission_selected; +} + +void intel_guc_rc_init_early(struct intel_guc *guc) +{ + guc->rc_supported = __guc_rc_supported(guc); + guc->rc_selected = __guc_rc_selected(guc); +} + +static int guc_action_control_gucrc(struct intel_guc *guc, bool enable) +{ + u32 rc_mode = enable ? INTEL_GUCRC_FIRMWARE_CONTROL : + INTEL_GUCRC_HOST_CONTROL; + u32 action[] = { + INTEL_GUC_ACTION_SETUP_PC_GUCRC, + rc_mode + }; + int ret; + + ret = intel_guc_send(guc, action, ARRAY_SIZE(action)); + ret = ret > 0 ? -EPROTO : ret; + + return ret; +} + +static int __guc_rc_control(struct intel_guc *guc, bool enable) +{ + struct intel_gt *gt = guc_to_gt(guc); + struct drm_device *drm = &guc_to_gt(guc)->i915->drm; + int ret; + + if (!intel_uc_uses_guc_rc(>->uc)) + return -EOPNOTSUPP; + + if (!intel_guc_is_ready(guc)) + return -EINVAL; + + ret = guc_action_control_gucrc(guc, enable); + if (ret) { + drm_err(drm, "Failed to %s GuC RC (%pe)\n", + enabledisable(enable), ERR_PTR(ret)); + return ret; + } + + drm_info(>->i915->drm, "GuC RC: %s\n", + enableddisabled(enable)); + + return 0; +} + +int intel_guc_rc_enable(struct intel_guc *guc) +{ + return __guc_rc_control(guc, true); +} + +int intel_guc_rc_disable(struct intel_guc *guc) +{ + return __guc_rc_control(guc, false); +} diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.h new file mode 100644 index 000000000000..57e86c337838 --- /dev/null +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_rc.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ + +#ifndef _INTEL_GUC_RC_H_ +#define _INTEL_GUC_RC_H_ + +#include "intel_guc_submission.h" + +void intel_guc_rc_init_early(struct intel_guc *guc); + +static inline bool intel_guc_rc_is_supported(struct intel_guc *guc) +{ + return guc->rc_supported; +} + +static inline bool intel_guc_rc_is_wanted(struct intel_guc *guc) +{ + return guc->submission_selected && intel_guc_rc_is_supported(guc); +} + +static inline bool intel_guc_rc_is_used(struct intel_guc *guc) +{ + return intel_guc_submission_is_used(guc) && intel_guc_rc_is_wanted(guc); +} + +int intel_guc_rc_enable(struct intel_guc *guc); +int intel_guc_rc_disable(struct intel_guc *guc); + +#endif diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c new file mode 100644 index 000000000000..65a3e7fdb2b2 --- /dev/null +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c @@ -0,0 +1,626 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2021 Intel Corporation + */ + +#include "i915_drv.h" +#include "intel_guc_slpc.h" +#include "gt/intel_gt.h" + +static inline struct intel_guc *slpc_to_guc(struct intel_guc_slpc *slpc) +{ + return container_of(slpc, struct intel_guc, slpc); +} + +static inline struct intel_gt *slpc_to_gt(struct intel_guc_slpc *slpc) +{ + return guc_to_gt(slpc_to_guc(slpc)); +} + +static inline struct drm_i915_private *slpc_to_i915(struct intel_guc_slpc *slpc) +{ + return slpc_to_gt(slpc)->i915; +} + +static bool __detect_slpc_supported(struct intel_guc *guc) +{ + /* GuC SLPC is unavailable for pre-Gen12 */ + return guc->submission_supported && + GRAPHICS_VER(guc_to_gt(guc)->i915) >= 12; +} + +static bool __guc_slpc_selected(struct intel_guc *guc) +{ + if (!intel_guc_slpc_is_supported(guc)) + return false; + + return guc->submission_selected; +} + +void intel_guc_slpc_init_early(struct intel_guc_slpc *slpc) +{ + struct intel_guc *guc = slpc_to_guc(slpc); + + slpc->supported = __detect_slpc_supported(guc); + slpc->selected = __guc_slpc_selected(guc); +} + +static void slpc_mem_set_param(struct slpc_shared_data *data, + u32 id, u32 value) +{ + GEM_BUG_ON(id >= SLPC_MAX_OVERRIDE_PARAMETERS); + /* + * When the flag bit is set, corresponding value will be read + * and applied by SLPC. + */ + data->override_params.bits[id >> 5] |= (1 << (id % 32)); + data->override_params.values[id] = value; +} + +static void slpc_mem_set_enabled(struct slpc_shared_data *data, + u8 enable_id, u8 disable_id) +{ + /* + * Enabling a param involves setting the enable_id + * to 1 and disable_id to 0. + */ + slpc_mem_set_param(data, enable_id, 1); + slpc_mem_set_param(data, disable_id, 0); +} + +static void slpc_mem_set_disabled(struct slpc_shared_data *data, + u8 enable_id, u8 disable_id) +{ + /* + * Disabling a param involves setting the enable_id + * to 0 and disable_id to 1. + */ + slpc_mem_set_param(data, disable_id, 1); + slpc_mem_set_param(data, enable_id, 0); +} + +int intel_guc_slpc_init(struct intel_guc_slpc *slpc) +{ + struct intel_guc *guc = slpc_to_guc(slpc); + struct drm_i915_private *i915 = slpc_to_i915(slpc); + u32 size = PAGE_ALIGN(sizeof(struct slpc_shared_data)); + int err; + + GEM_BUG_ON(slpc->vma); + + err = intel_guc_allocate_and_map_vma(guc, size, &slpc->vma, (void **)&slpc->vaddr); + if (unlikely(err)) { + drm_err(&i915->drm, + "Failed to allocate SLPC struct (err=%pe)\n", + ERR_PTR(err)); + return err; + } + + slpc->max_freq_softlimit = 0; + slpc->min_freq_softlimit = 0; + + return err; +} + +static u32 slpc_get_state(struct intel_guc_slpc *slpc) +{ + struct slpc_shared_data *data; + + GEM_BUG_ON(!slpc->vma); + + drm_clflush_virt_range(slpc->vaddr, sizeof(u32)); + data = slpc->vaddr; + + return data->header.global_state; +} + +static int guc_action_slpc_set_param(struct intel_guc *guc, u8 id, u32 value) +{ + u32 request[] = { + GUC_ACTION_HOST2GUC_PC_SLPC_REQUEST, + SLPC_EVENT(SLPC_EVENT_PARAMETER_SET, 2), + id, + value, + }; + int ret; + + ret = intel_guc_send(guc, request, ARRAY_SIZE(request)); + + return ret > 0 ? -EPROTO : ret; +} + +static int guc_action_slpc_unset_param(struct intel_guc *guc, u8 id) +{ + u32 request[] = { + GUC_ACTION_HOST2GUC_PC_SLPC_REQUEST, + SLPC_EVENT(SLPC_EVENT_PARAMETER_UNSET, 2), + id, + }; + + return intel_guc_send(guc, request, ARRAY_SIZE(request)); +} + +static bool slpc_is_running(struct intel_guc_slpc *slpc) +{ + return slpc_get_state(slpc) == SLPC_GLOBAL_STATE_RUNNING; +} + +static int guc_action_slpc_query(struct intel_guc *guc, u32 offset) +{ + u32 request[] = { + GUC_ACTION_HOST2GUC_PC_SLPC_REQUEST, + SLPC_EVENT(SLPC_EVENT_QUERY_TASK_STATE, 2), + offset, + 0, + }; + int ret; + + ret = intel_guc_send(guc, request, ARRAY_SIZE(request)); + + return ret > 0 ? -EPROTO : ret; +} + +static int slpc_query_task_state(struct intel_guc_slpc *slpc) +{ + struct intel_guc *guc = slpc_to_guc(slpc); + struct drm_i915_private *i915 = slpc_to_i915(slpc); + u32 offset = intel_guc_ggtt_offset(guc, slpc->vma); + int ret; + + ret = guc_action_slpc_query(guc, offset); + if (unlikely(ret)) + drm_err(&i915->drm, "Failed to query task state (%pe)\n", + ERR_PTR(ret)); + + drm_clflush_virt_range(slpc->vaddr, SLPC_PAGE_SIZE_BYTES); + + return ret; +} + +static int slpc_set_param(struct intel_guc_slpc *slpc, u8 id, u32 value) +{ + struct intel_guc *guc = slpc_to_guc(slpc); + struct drm_i915_private *i915 = slpc_to_i915(slpc); + int ret; + + GEM_BUG_ON(id >= SLPC_MAX_PARAM); + + ret = guc_action_slpc_set_param(guc, id, value); + if (ret) + drm_err(&i915->drm, "Failed to set param %d to %u (%pe)\n", + id, value, ERR_PTR(ret)); + + return ret; +} + +static int slpc_unset_param(struct intel_guc_slpc *slpc, + u8 id) +{ + struct intel_guc *guc = slpc_to_guc(slpc); + + GEM_BUG_ON(id >= SLPC_MAX_PARAM); + + return guc_action_slpc_unset_param(guc, id); +} + +static const char *slpc_global_state_to_string(enum slpc_global_state state) +{ + switch (state) { + case SLPC_GLOBAL_STATE_NOT_RUNNING: + return "not running"; + case SLPC_GLOBAL_STATE_INITIALIZING: + return "initializing"; + case SLPC_GLOBAL_STATE_RESETTING: + return "resetting"; + case SLPC_GLOBAL_STATE_RUNNING: + return "running"; + case SLPC_GLOBAL_STATE_SHUTTING_DOWN: + return "shutting down"; + case SLPC_GLOBAL_STATE_ERROR: + return "error"; + default: + return "unknown"; + } +} + +static const char *slpc_get_state_string(struct intel_guc_slpc *slpc) +{ + return slpc_global_state_to_string(slpc_get_state(slpc)); +} + +static int guc_action_slpc_reset(struct intel_guc *guc, u32 offset) +{ + u32 request[] = { + GUC_ACTION_HOST2GUC_PC_SLPC_REQUEST, + SLPC_EVENT(SLPC_EVENT_RESET, 2), + offset, + 0, + }; + int ret; + + ret = intel_guc_send(guc, request, ARRAY_SIZE(request)); + + return ret > 0 ? -EPROTO : ret; +} + +static int slpc_reset(struct intel_guc_slpc *slpc) +{ + struct drm_i915_private *i915 = slpc_to_i915(slpc); + struct intel_guc *guc = slpc_to_guc(slpc); + u32 offset = intel_guc_ggtt_offset(guc, slpc->vma); + int ret; + + ret = guc_action_slpc_reset(guc, offset); + + if (unlikely(ret < 0)) { + drm_err(&i915->drm, "SLPC reset action failed (%pe)\n", + ERR_PTR(ret)); + return ret; + } + + if (!ret) { + if (wait_for(slpc_is_running(slpc), SLPC_RESET_TIMEOUT_MS)) { + drm_err(&i915->drm, "SLPC not enabled! State = %s\n", + slpc_get_state_string(slpc)); + return -EIO; + } + } + + return 0; +} + +static u32 slpc_decode_min_freq(struct intel_guc_slpc *slpc) +{ + struct slpc_shared_data *data = slpc->vaddr; + + GEM_BUG_ON(!slpc->vma); + + return DIV_ROUND_CLOSEST(REG_FIELD_GET(SLPC_MIN_UNSLICE_FREQ_MASK, + data->task_state_data.freq) * + GT_FREQUENCY_MULTIPLIER, GEN9_FREQ_SCALER); +} + +static u32 slpc_decode_max_freq(struct intel_guc_slpc *slpc) +{ + struct slpc_shared_data *data = slpc->vaddr; + + GEM_BUG_ON(!slpc->vma); + + return DIV_ROUND_CLOSEST(REG_FIELD_GET(SLPC_MAX_UNSLICE_FREQ_MASK, + data->task_state_data.freq) * + GT_FREQUENCY_MULTIPLIER, GEN9_FREQ_SCALER); +} + +static void slpc_shared_data_reset(struct slpc_shared_data *data) +{ + memset(data, 0, sizeof(struct slpc_shared_data)); + + data->header.size = sizeof(struct slpc_shared_data); + + /* Enable only GTPERF task, disable others */ + slpc_mem_set_enabled(data, SLPC_PARAM_TASK_ENABLE_GTPERF, + SLPC_PARAM_TASK_DISABLE_GTPERF); + + slpc_mem_set_disabled(data, SLPC_PARAM_TASK_ENABLE_BALANCER, + SLPC_PARAM_TASK_DISABLE_BALANCER); + + slpc_mem_set_disabled(data, SLPC_PARAM_TASK_ENABLE_DCC, + SLPC_PARAM_TASK_DISABLE_DCC); +} + +/** + * intel_guc_slpc_set_max_freq() - Set max frequency limit for SLPC. + * @slpc: pointer to intel_guc_slpc. + * @val: frequency (MHz) + * + * This function will invoke GuC SLPC action to update the max frequency + * limit for unslice. + * + * Return: 0 on success, non-zero error code on failure. + */ +int intel_guc_slpc_set_max_freq(struct intel_guc_slpc *slpc, u32 val) +{ + struct drm_i915_private *i915 = slpc_to_i915(slpc); + intel_wakeref_t wakeref; + int ret; + + if (val < slpc->min_freq || + val > slpc->rp0_freq || + val < slpc->min_freq_softlimit) + return -EINVAL; + + with_intel_runtime_pm(&i915->runtime_pm, wakeref) { + ret = slpc_set_param(slpc, + SLPC_PARAM_GLOBAL_MAX_GT_UNSLICE_FREQ_MHZ, + val); + + /* Return standardized err code for sysfs calls */ + if (ret) + ret = -EIO; + } + + if (!ret) + slpc->max_freq_softlimit = val; + + return ret; +} + +/** + * intel_guc_slpc_get_max_freq() - Get max frequency limit for SLPC. + * @slpc: pointer to intel_guc_slpc. + * @val: pointer to val which will hold max frequency (MHz) + * + * This function will invoke GuC SLPC action to read the max frequency + * limit for unslice. + * + * Return: 0 on success, non-zero error code on failure. + */ +int intel_guc_slpc_get_max_freq(struct intel_guc_slpc *slpc, u32 *val) +{ + struct drm_i915_private *i915 = slpc_to_i915(slpc); + intel_wakeref_t wakeref; + int ret = 0; + + with_intel_runtime_pm(&i915->runtime_pm, wakeref) { + /* Force GuC to update task data */ + ret = slpc_query_task_state(slpc); + + if (!ret) + *val = slpc_decode_max_freq(slpc); + } + + return ret; +} + +/** + * intel_guc_slpc_set_min_freq() - Set min frequency limit for SLPC. + * @slpc: pointer to intel_guc_slpc. + * @val: frequency (MHz) + * + * This function will invoke GuC SLPC action to update the min unslice + * frequency. + * + * Return: 0 on success, non-zero error code on failure. + */ +int intel_guc_slpc_set_min_freq(struct intel_guc_slpc *slpc, u32 val) +{ + struct drm_i915_private *i915 = slpc_to_i915(slpc); + intel_wakeref_t wakeref; + int ret; + + if (val < slpc->min_freq || + val > slpc->rp0_freq || + val > slpc->max_freq_softlimit) + return -EINVAL; + + with_intel_runtime_pm(&i915->runtime_pm, wakeref) { + ret = slpc_set_param(slpc, + SLPC_PARAM_GLOBAL_MIN_GT_UNSLICE_FREQ_MHZ, + val); + + /* Return standardized err code for sysfs calls */ + if (ret) + ret = -EIO; + } + + if (!ret) + slpc->min_freq_softlimit = val; + + return ret; +} + +/** + * intel_guc_slpc_get_min_freq() - Get min frequency limit for SLPC. + * @slpc: pointer to intel_guc_slpc. + * @val: pointer to val which will hold min frequency (MHz) + * + * This function will invoke GuC SLPC action to read the min frequency + * limit for unslice. + * + * Return: 0 on success, non-zero error code on failure. + */ +int intel_guc_slpc_get_min_freq(struct intel_guc_slpc *slpc, u32 *val) +{ + struct drm_i915_private *i915 = slpc_to_i915(slpc); + intel_wakeref_t wakeref; + int ret = 0; + + with_intel_runtime_pm(&i915->runtime_pm, wakeref) { + /* Force GuC to update task data */ + ret = slpc_query_task_state(slpc); + + if (!ret) + *val = slpc_decode_min_freq(slpc); + } + + return ret; +} + +void intel_guc_pm_intrmsk_enable(struct intel_gt *gt) +{ + u32 pm_intrmsk_mbz = 0; + + /* + * Allow GuC to receive ARAT timer expiry event. + * This interrupt register is setup by RPS code + * when host based Turbo is enabled. + */ + pm_intrmsk_mbz |= ARAT_EXPIRED_INTRMSK; + + intel_uncore_rmw(gt->uncore, + GEN6_PMINTRMSK, pm_intrmsk_mbz, 0); +} + +static int slpc_set_softlimits(struct intel_guc_slpc *slpc) +{ + int ret = 0; + + /* + * Softlimits are initially equivalent to platform limits + * unless they have deviated from defaults, in which case, + * we retain the values and set min/max accordingly. + */ + if (!slpc->max_freq_softlimit) + slpc->max_freq_softlimit = slpc->rp0_freq; + else if (slpc->max_freq_softlimit != slpc->rp0_freq) + ret = intel_guc_slpc_set_max_freq(slpc, + slpc->max_freq_softlimit); + + if (unlikely(ret)) + return ret; + + if (!slpc->min_freq_softlimit) + slpc->min_freq_softlimit = slpc->min_freq; + else if (slpc->min_freq_softlimit != slpc->min_freq) + return intel_guc_slpc_set_min_freq(slpc, + slpc->min_freq_softlimit); + + return 0; +} + +static int slpc_ignore_eff_freq(struct intel_guc_slpc *slpc, bool ignore) +{ + int ret = 0; + + if (ignore) { + ret = slpc_set_param(slpc, + SLPC_PARAM_IGNORE_EFFICIENT_FREQUENCY, + ignore); + if (!ret) + return slpc_set_param(slpc, + SLPC_PARAM_GLOBAL_MIN_GT_UNSLICE_FREQ_MHZ, + slpc->min_freq); + } else { + ret = slpc_unset_param(slpc, + SLPC_PARAM_IGNORE_EFFICIENT_FREQUENCY); + if (!ret) + return slpc_unset_param(slpc, + SLPC_PARAM_GLOBAL_MIN_GT_UNSLICE_FREQ_MHZ); + } + + return ret; +} + +static int slpc_use_fused_rp0(struct intel_guc_slpc *slpc) +{ + /* Force SLPC to used platform rp0 */ + return slpc_set_param(slpc, + SLPC_PARAM_GLOBAL_MAX_GT_UNSLICE_FREQ_MHZ, + slpc->rp0_freq); +} + +static void slpc_get_rp_values(struct intel_guc_slpc *slpc) +{ + u32 rp_state_cap; + + rp_state_cap = intel_uncore_read(slpc_to_gt(slpc)->uncore, + GEN6_RP_STATE_CAP); + + slpc->rp0_freq = REG_FIELD_GET(RP0_CAP_MASK, rp_state_cap) * + GT_FREQUENCY_MULTIPLIER; + slpc->rp1_freq = REG_FIELD_GET(RP1_CAP_MASK, rp_state_cap) * + GT_FREQUENCY_MULTIPLIER; + slpc->min_freq = REG_FIELD_GET(RPN_CAP_MASK, rp_state_cap) * + GT_FREQUENCY_MULTIPLIER; +} + +/* + * intel_guc_slpc_enable() - Start SLPC + * @slpc: pointer to intel_guc_slpc. + * + * SLPC is enabled by setting up the shared data structure and + * sending reset event to GuC SLPC. Initial data is setup in + * intel_guc_slpc_init. Here we send the reset event. We do + * not currently need a slpc_disable since this is taken care + * of automatically when a reset/suspend occurs and the GuC + * CTB is destroyed. + * + * Return: 0 on success, non-zero error code on failure. + */ +int intel_guc_slpc_enable(struct intel_guc_slpc *slpc) +{ + struct drm_i915_private *i915 = slpc_to_i915(slpc); + int ret; + + GEM_BUG_ON(!slpc->vma); + + slpc_shared_data_reset(slpc->vaddr); + + ret = slpc_reset(slpc); + if (unlikely(ret < 0)) { + drm_err(&i915->drm, "SLPC Reset event returned (%pe)\n", + ERR_PTR(ret)); + return ret; + } + + ret = slpc_query_task_state(slpc); + if (unlikely(ret < 0)) + return ret; + + intel_guc_pm_intrmsk_enable(&i915->gt); + + slpc_get_rp_values(slpc); + + /* Ignore efficient freq and set min to platform min */ + ret = slpc_ignore_eff_freq(slpc, true); + if (unlikely(ret)) { + drm_err(&i915->drm, "Failed to set SLPC min to RPn (%pe)\n", + ERR_PTR(ret)); + return ret; + } + + /* Set SLPC max limit to RP0 */ + ret = slpc_use_fused_rp0(slpc); + if (unlikely(ret)) { + drm_err(&i915->drm, "Failed to set SLPC max to RP0 (%pe)\n", + ERR_PTR(ret)); + return ret; + } + + /* Revert SLPC min/max to softlimits if necessary */ + ret = slpc_set_softlimits(slpc); + if (unlikely(ret)) { + drm_err(&i915->drm, "Failed to set SLPC softlimits (%pe)\n", + ERR_PTR(ret)); + return ret; + } + + return 0; +} + +int intel_guc_slpc_print_info(struct intel_guc_slpc *slpc, struct drm_printer *p) +{ + struct drm_i915_private *i915 = slpc_to_i915(slpc); + struct slpc_shared_data *data = slpc->vaddr; + struct slpc_task_state_data *slpc_tasks; + intel_wakeref_t wakeref; + int ret = 0; + + GEM_BUG_ON(!slpc->vma); + + with_intel_runtime_pm(&i915->runtime_pm, wakeref) { + ret = slpc_query_task_state(slpc); + + if (!ret) { + slpc_tasks = &data->task_state_data; + + drm_printf(p, "\tSLPC state: %s\n", slpc_get_state_string(slpc)); + drm_printf(p, "\tGTPERF task active: %s\n", + yesno(slpc_tasks->status & SLPC_GTPERF_TASK_ENABLED)); + drm_printf(p, "\tMax freq: %u MHz\n", + slpc_decode_max_freq(slpc)); + drm_printf(p, "\tMin freq: %u MHz\n", + slpc_decode_min_freq(slpc)); + } + } + + return ret; +} + +void intel_guc_slpc_fini(struct intel_guc_slpc *slpc) +{ + if (!slpc->vma) + return; + + i915_vma_unpin_and_release(&slpc->vma, I915_VMA_RELEASE_MAP); +} diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h new file mode 100644 index 000000000000..e45054d5b9b4 --- /dev/null +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ + +#ifndef _INTEL_GUC_SLPC_H_ +#define _INTEL_GUC_SLPC_H_ + +#include "intel_guc_submission.h" +#include "intel_guc_slpc_types.h" + +struct intel_gt; +struct drm_printer; + +static inline bool intel_guc_slpc_is_supported(struct intel_guc *guc) +{ + return guc->slpc.supported; +} + +static inline bool intel_guc_slpc_is_wanted(struct intel_guc *guc) +{ + return guc->slpc.selected; +} + +static inline bool intel_guc_slpc_is_used(struct intel_guc *guc) +{ + return intel_guc_submission_is_used(guc) && intel_guc_slpc_is_wanted(guc); +} + +void intel_guc_slpc_init_early(struct intel_guc_slpc *slpc); + +int intel_guc_slpc_init(struct intel_guc_slpc *slpc); +int intel_guc_slpc_enable(struct intel_guc_slpc *slpc); +void intel_guc_slpc_fini(struct intel_guc_slpc *slpc); +int intel_guc_slpc_set_max_freq(struct intel_guc_slpc *slpc, u32 val); +int intel_guc_slpc_set_min_freq(struct intel_guc_slpc *slpc, u32 val); +int intel_guc_slpc_get_max_freq(struct intel_guc_slpc *slpc, u32 *val); +int intel_guc_slpc_get_min_freq(struct intel_guc_slpc *slpc, u32 *val); +int intel_guc_slpc_print_info(struct intel_guc_slpc *slpc, struct drm_printer *p); +void intel_guc_pm_intrmsk_enable(struct intel_gt *gt); + +#endif diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc_types.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc_types.h new file mode 100644 index 000000000000..41d13527666f --- /dev/null +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc_types.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ + +#ifndef _INTEL_GUC_SLPC_TYPES_H_ +#define _INTEL_GUC_SLPC_TYPES_H_ + +#include <linux/types.h> + +#define SLPC_RESET_TIMEOUT_MS 5 + +struct intel_guc_slpc { + struct i915_vma *vma; + struct slpc_shared_data *vaddr; + bool supported; + bool selected; + + /* platform frequency limits */ + u32 min_freq; + u32 rp0_freq; + u32 rp1_freq; + + /* frequency softlimits */ + u32 min_freq_softlimit; + u32 max_freq_softlimit; +}; + +#endif diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index 7c8ff9792f7b..87d8dc8f51b9 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -10,10 +10,13 @@ #include "gt/intel_breadcrumbs.h" #include "gt/intel_context.h" #include "gt/intel_engine_pm.h" +#include "gt/intel_engine_heartbeat.h" #include "gt/intel_gt.h" #include "gt/intel_gt_irq.h" #include "gt/intel_gt_pm.h" +#include "gt/intel_gt_requests.h" #include "gt/intel_lrc.h" +#include "gt/intel_lrc_reg.h" #include "gt/intel_mocs.h" #include "gt/intel_ring.h" @@ -58,244 +61,705 @@ * */ +/* GuC Virtual Engine */ +struct guc_virtual_engine { + struct intel_engine_cs base; + struct intel_context context; +}; + +static struct intel_context * +guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count); + #define GUC_REQUEST_SIZE 64 /* bytes */ -static inline struct i915_priolist *to_priolist(struct rb_node *rb) +/* + * Below is a set of functions which control the GuC scheduling state which do + * not require a lock as all state transitions are mutually exclusive. i.e. It + * is not possible for the context pinning code and submission, for the same + * context, to be executing simultaneously. We still need an atomic as it is + * possible for some of the bits to changing at the same time though. + */ +#define SCHED_STATE_NO_LOCK_ENABLED BIT(0) +#define SCHED_STATE_NO_LOCK_PENDING_ENABLE BIT(1) +#define SCHED_STATE_NO_LOCK_REGISTERED BIT(2) +static inline bool context_enabled(struct intel_context *ce) { - return rb_entry(rb, struct i915_priolist, node); + return (atomic_read(&ce->guc_sched_state_no_lock) & + SCHED_STATE_NO_LOCK_ENABLED); } -static struct guc_stage_desc *__get_stage_desc(struct intel_guc *guc, u32 id) +static inline void set_context_enabled(struct intel_context *ce) { - struct guc_stage_desc *base = guc->stage_desc_pool_vaddr; + atomic_or(SCHED_STATE_NO_LOCK_ENABLED, &ce->guc_sched_state_no_lock); +} - return &base[id]; +static inline void clr_context_enabled(struct intel_context *ce) +{ + atomic_and((u32)~SCHED_STATE_NO_LOCK_ENABLED, + &ce->guc_sched_state_no_lock); } -static int guc_stage_desc_pool_create(struct intel_guc *guc) +static inline bool context_pending_enable(struct intel_context *ce) { - u32 size = PAGE_ALIGN(sizeof(struct guc_stage_desc) * - GUC_MAX_STAGE_DESCRIPTORS); + return (atomic_read(&ce->guc_sched_state_no_lock) & + SCHED_STATE_NO_LOCK_PENDING_ENABLE); +} - return intel_guc_allocate_and_map_vma(guc, size, &guc->stage_desc_pool, - &guc->stage_desc_pool_vaddr); +static inline void set_context_pending_enable(struct intel_context *ce) +{ + atomic_or(SCHED_STATE_NO_LOCK_PENDING_ENABLE, + &ce->guc_sched_state_no_lock); +} + +static inline void clr_context_pending_enable(struct intel_context *ce) +{ + atomic_and((u32)~SCHED_STATE_NO_LOCK_PENDING_ENABLE, + &ce->guc_sched_state_no_lock); } -static void guc_stage_desc_pool_destroy(struct intel_guc *guc) +static inline bool context_registered(struct intel_context *ce) { - i915_vma_unpin_and_release(&guc->stage_desc_pool, I915_VMA_RELEASE_MAP); + return (atomic_read(&ce->guc_sched_state_no_lock) & + SCHED_STATE_NO_LOCK_REGISTERED); +} + +static inline void set_context_registered(struct intel_context *ce) +{ + atomic_or(SCHED_STATE_NO_LOCK_REGISTERED, + &ce->guc_sched_state_no_lock); +} + +static inline void clr_context_registered(struct intel_context *ce) +{ + atomic_and((u32)~SCHED_STATE_NO_LOCK_REGISTERED, + &ce->guc_sched_state_no_lock); } /* - * Initialise/clear the stage descriptor shared with the GuC firmware. - * - * This descriptor tells the GuC where (in GGTT space) to find the important - * data structures related to work submission (process descriptor, write queue, - * etc). + * Below is a set of functions which control the GuC scheduling state which + * require a lock, aside from the special case where the functions are called + * from guc_lrc_desc_pin(). In that case it isn't possible for any other code + * path to be executing on the context. */ -static void guc_stage_desc_init(struct intel_guc *guc) +#define SCHED_STATE_WAIT_FOR_DEREGISTER_TO_REGISTER BIT(0) +#define SCHED_STATE_DESTROYED BIT(1) +#define SCHED_STATE_PENDING_DISABLE BIT(2) +#define SCHED_STATE_BANNED BIT(3) +#define SCHED_STATE_BLOCKED_SHIFT 4 +#define SCHED_STATE_BLOCKED BIT(SCHED_STATE_BLOCKED_SHIFT) +#define SCHED_STATE_BLOCKED_MASK (0xfff << SCHED_STATE_BLOCKED_SHIFT) +static inline void init_sched_state(struct intel_context *ce) +{ + /* Only should be called from guc_lrc_desc_pin() */ + atomic_set(&ce->guc_sched_state_no_lock, 0); + ce->guc_state.sched_state = 0; +} + +static inline bool +context_wait_for_deregister_to_register(struct intel_context *ce) +{ + return ce->guc_state.sched_state & + SCHED_STATE_WAIT_FOR_DEREGISTER_TO_REGISTER; +} + +static inline void +set_context_wait_for_deregister_to_register(struct intel_context *ce) { - struct guc_stage_desc *desc; + /* Only should be called from guc_lrc_desc_pin() without lock */ + ce->guc_state.sched_state |= + SCHED_STATE_WAIT_FOR_DEREGISTER_TO_REGISTER; +} - /* we only use 1 stage desc, so hardcode it to 0 */ - desc = __get_stage_desc(guc, 0); - memset(desc, 0, sizeof(*desc)); +static inline void +clr_context_wait_for_deregister_to_register(struct intel_context *ce) +{ + lockdep_assert_held(&ce->guc_state.lock); + ce->guc_state.sched_state &= + ~SCHED_STATE_WAIT_FOR_DEREGISTER_TO_REGISTER; +} - desc->attribute = GUC_STAGE_DESC_ATTR_ACTIVE | - GUC_STAGE_DESC_ATTR_KERNEL; +static inline bool +context_destroyed(struct intel_context *ce) +{ + return ce->guc_state.sched_state & SCHED_STATE_DESTROYED; +} - desc->stage_id = 0; - desc->priority = GUC_CLIENT_PRIORITY_KMD_NORMAL; +static inline void +set_context_destroyed(struct intel_context *ce) +{ + lockdep_assert_held(&ce->guc_state.lock); + ce->guc_state.sched_state |= SCHED_STATE_DESTROYED; +} - desc->wq_size = GUC_WQ_SIZE; +static inline bool context_pending_disable(struct intel_context *ce) +{ + return ce->guc_state.sched_state & SCHED_STATE_PENDING_DISABLE; } -static void guc_stage_desc_fini(struct intel_guc *guc) +static inline void set_context_pending_disable(struct intel_context *ce) { - struct guc_stage_desc *desc; + lockdep_assert_held(&ce->guc_state.lock); + ce->guc_state.sched_state |= SCHED_STATE_PENDING_DISABLE; +} - desc = __get_stage_desc(guc, 0); - memset(desc, 0, sizeof(*desc)); +static inline void clr_context_pending_disable(struct intel_context *ce) +{ + lockdep_assert_held(&ce->guc_state.lock); + ce->guc_state.sched_state &= ~SCHED_STATE_PENDING_DISABLE; } -static void guc_add_request(struct intel_guc *guc, struct i915_request *rq) +static inline bool context_banned(struct intel_context *ce) { - /* Leaving stub as this function will be used in future patches */ + return ce->guc_state.sched_state & SCHED_STATE_BANNED; } -/* - * When we're doing submissions using regular execlists backend, writing to - * ELSP from CPU side is enough to make sure that writes to ringbuffer pages - * pinned in mappable aperture portion of GGTT are visible to command streamer. - * Writes done by GuC on our behalf are not guaranteeing such ordering, - * therefore, to ensure the flush, we're issuing a POSTING READ. - */ -static void flush_ggtt_writes(struct i915_vma *vma) +static inline void set_context_banned(struct intel_context *ce) { - if (i915_vma_is_map_and_fenceable(vma)) - intel_uncore_posting_read_fw(vma->vm->gt->uncore, - GUC_STATUS); + lockdep_assert_held(&ce->guc_state.lock); + ce->guc_state.sched_state |= SCHED_STATE_BANNED; } -static void guc_submit(struct intel_engine_cs *engine, - struct i915_request **out, - struct i915_request **end) +static inline void clr_context_banned(struct intel_context *ce) { - struct intel_guc *guc = &engine->gt->uc.guc; + lockdep_assert_held(&ce->guc_state.lock); + ce->guc_state.sched_state &= ~SCHED_STATE_BANNED; +} - do { - struct i915_request *rq = *out++; +static inline u32 context_blocked(struct intel_context *ce) +{ + return (ce->guc_state.sched_state & SCHED_STATE_BLOCKED_MASK) >> + SCHED_STATE_BLOCKED_SHIFT; +} - flush_ggtt_writes(rq->ring->vma); - guc_add_request(guc, rq); - } while (out != end); +static inline void incr_context_blocked(struct intel_context *ce) +{ + lockdep_assert_held(&ce->engine->sched_engine->lock); + lockdep_assert_held(&ce->guc_state.lock); + + ce->guc_state.sched_state += SCHED_STATE_BLOCKED; + + GEM_BUG_ON(!context_blocked(ce)); /* Overflow check */ } -static inline int rq_prio(const struct i915_request *rq) +static inline void decr_context_blocked(struct intel_context *ce) { - return rq->sched.attr.priority; + lockdep_assert_held(&ce->engine->sched_engine->lock); + lockdep_assert_held(&ce->guc_state.lock); + + GEM_BUG_ON(!context_blocked(ce)); /* Underflow check */ + + ce->guc_state.sched_state -= SCHED_STATE_BLOCKED; } -static struct i915_request *schedule_in(struct i915_request *rq, int idx) +static inline bool context_guc_id_invalid(struct intel_context *ce) { - trace_i915_request_in(rq, idx); + return ce->guc_id == GUC_INVALID_LRC_ID; +} + +static inline void set_context_guc_id_invalid(struct intel_context *ce) +{ + ce->guc_id = GUC_INVALID_LRC_ID; +} + +static inline struct intel_guc *ce_to_guc(struct intel_context *ce) +{ + return &ce->engine->gt->uc.guc; +} + +static inline struct i915_priolist *to_priolist(struct rb_node *rb) +{ + return rb_entry(rb, struct i915_priolist, node); +} + +static struct guc_lrc_desc *__get_lrc_desc(struct intel_guc *guc, u32 index) +{ + struct guc_lrc_desc *base = guc->lrc_desc_pool_vaddr; + + GEM_BUG_ON(index >= GUC_MAX_LRC_DESCRIPTORS); + + return &base[index]; +} + +static inline struct intel_context *__get_context(struct intel_guc *guc, u32 id) +{ + struct intel_context *ce = xa_load(&guc->context_lookup, id); + + GEM_BUG_ON(id >= GUC_MAX_LRC_DESCRIPTORS); + + return ce; +} + +static int guc_lrc_desc_pool_create(struct intel_guc *guc) +{ + u32 size; + int ret; + + size = PAGE_ALIGN(sizeof(struct guc_lrc_desc) * + GUC_MAX_LRC_DESCRIPTORS); + ret = intel_guc_allocate_and_map_vma(guc, size, &guc->lrc_desc_pool, + (void **)&guc->lrc_desc_pool_vaddr); + if (ret) + return ret; + + return 0; +} + +static void guc_lrc_desc_pool_destroy(struct intel_guc *guc) +{ + guc->lrc_desc_pool_vaddr = NULL; + i915_vma_unpin_and_release(&guc->lrc_desc_pool, I915_VMA_RELEASE_MAP); +} + +static inline bool guc_submission_initialized(struct intel_guc *guc) +{ + return !!guc->lrc_desc_pool_vaddr; +} + +static inline void reset_lrc_desc(struct intel_guc *guc, u32 id) +{ + if (likely(guc_submission_initialized(guc))) { + struct guc_lrc_desc *desc = __get_lrc_desc(guc, id); + unsigned long flags; + + memset(desc, 0, sizeof(*desc)); + + /* + * xarray API doesn't have xa_erase_irqsave wrapper, so calling + * the lower level functions directly. + */ + xa_lock_irqsave(&guc->context_lookup, flags); + __xa_erase(&guc->context_lookup, id); + xa_unlock_irqrestore(&guc->context_lookup, flags); + } +} + +static inline bool lrc_desc_registered(struct intel_guc *guc, u32 id) +{ + return __get_context(guc, id); +} + +static inline void set_lrc_desc_registered(struct intel_guc *guc, u32 id, + struct intel_context *ce) +{ + unsigned long flags; /* - * Currently we are not tracking the rq->context being inflight - * (ce->inflight = rq->engine). It is only used by the execlists - * backend at the moment, a similar counting strategy would be - * required if we generalise the inflight tracking. + * xarray API doesn't have xa_save_irqsave wrapper, so calling the + * lower level functions directly. */ + xa_lock_irqsave(&guc->context_lookup, flags); + __xa_store(&guc->context_lookup, id, ce, GFP_ATOMIC); + xa_unlock_irqrestore(&guc->context_lookup, flags); +} + +static int guc_submission_send_busy_loop(struct intel_guc *guc, + const u32 *action, + u32 len, + u32 g2h_len_dw, + bool loop) +{ + int err; + + err = intel_guc_send_busy_loop(guc, action, len, g2h_len_dw, loop); + + if (!err && g2h_len_dw) + atomic_inc(&guc->outstanding_submission_g2h); + + return err; +} + +int intel_guc_wait_for_pending_msg(struct intel_guc *guc, + atomic_t *wait_var, + bool interruptible, + long timeout) +{ + const int state = interruptible ? + TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE; + DEFINE_WAIT(wait); - __intel_gt_pm_get(rq->engine->gt); - return i915_request_get(rq); + might_sleep(); + GEM_BUG_ON(timeout < 0); + + if (!atomic_read(wait_var)) + return 0; + + if (!timeout) + return -ETIME; + + for (;;) { + prepare_to_wait(&guc->ct.wq, &wait, state); + + if (!atomic_read(wait_var)) + break; + + if (signal_pending_state(state, current)) { + timeout = -EINTR; + break; + } + + if (!timeout) { + timeout = -ETIME; + break; + } + + timeout = io_schedule_timeout(timeout); + } + finish_wait(&guc->ct.wq, &wait); + + return (timeout < 0) ? timeout : 0; } -static void schedule_out(struct i915_request *rq) +int intel_guc_wait_for_idle(struct intel_guc *guc, long timeout) { - trace_i915_request_out(rq); + if (!intel_uc_uses_guc_submission(&guc_to_gt(guc)->uc)) + return 0; - intel_gt_pm_put_async(rq->engine->gt); - i915_request_put(rq); + return intel_guc_wait_for_pending_msg(guc, + &guc->outstanding_submission_g2h, + true, timeout); } -static void __guc_dequeue(struct intel_engine_cs *engine) +static int guc_lrc_desc_pin(struct intel_context *ce, bool loop); + +static int guc_add_request(struct intel_guc *guc, struct i915_request *rq) { - struct intel_engine_execlists * const execlists = &engine->execlists; - struct i915_request **first = execlists->inflight; - struct i915_request ** const last_port = first + execlists->port_mask; - struct i915_request *last = first[0]; - struct i915_request **port; - bool submit = false; - struct rb_node *rb; + int err = 0; + struct intel_context *ce = rq->context; + u32 action[3]; + int len = 0; + u32 g2h_len_dw = 0; + bool enabled; - lockdep_assert_held(&engine->active.lock); + /* + * Corner case where requests were sitting in the priority list or a + * request resubmitted after the context was banned. + */ + if (unlikely(intel_context_is_banned(ce))) { + i915_request_put(i915_request_mark_eio(rq)); + intel_engine_signal_breadcrumbs(ce->engine); + goto out; + } - if (last) { - if (*++first) - return; + GEM_BUG_ON(!atomic_read(&ce->guc_id_ref)); + GEM_BUG_ON(context_guc_id_invalid(ce)); - last = NULL; + /* + * Corner case where the GuC firmware was blown away and reloaded while + * this context was pinned. + */ + if (unlikely(!lrc_desc_registered(guc, ce->guc_id))) { + err = guc_lrc_desc_pin(ce, false); + if (unlikely(err)) + goto out; } /* - * We write directly into the execlists->inflight queue and don't use - * the execlists->pending queue, as we don't have a distinct switch - * event. + * The request / context will be run on the hardware when scheduling + * gets enabled in the unblock. */ - port = first; - while ((rb = rb_first_cached(&execlists->queue))) { + if (unlikely(context_blocked(ce))) + goto out; + + enabled = context_enabled(ce); + + if (!enabled) { + action[len++] = INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_SET; + action[len++] = ce->guc_id; + action[len++] = GUC_CONTEXT_ENABLE; + set_context_pending_enable(ce); + intel_context_get(ce); + g2h_len_dw = G2H_LEN_DW_SCHED_CONTEXT_MODE_SET; + } else { + action[len++] = INTEL_GUC_ACTION_SCHED_CONTEXT; + action[len++] = ce->guc_id; + } + + err = intel_guc_send_nb(guc, action, len, g2h_len_dw); + if (!enabled && !err) { + trace_intel_context_sched_enable(ce); + atomic_inc(&guc->outstanding_submission_g2h); + set_context_enabled(ce); + } else if (!enabled) { + clr_context_pending_enable(ce); + intel_context_put(ce); + } + if (likely(!err)) + trace_i915_request_guc_submit(rq); + +out: + return err; +} + +static inline void guc_set_lrc_tail(struct i915_request *rq) +{ + rq->context->lrc_reg_state[CTX_RING_TAIL] = + intel_ring_set_tail(rq->ring, rq->tail); +} + +static inline int rq_prio(const struct i915_request *rq) +{ + return rq->sched.attr.priority; +} + +static int guc_dequeue_one_context(struct intel_guc *guc) +{ + struct i915_sched_engine * const sched_engine = guc->sched_engine; + struct i915_request *last = NULL; + bool submit = false; + struct rb_node *rb; + int ret; + + lockdep_assert_held(&sched_engine->lock); + + if (guc->stalled_request) { + submit = true; + last = guc->stalled_request; + goto resubmit; + } + + while ((rb = rb_first_cached(&sched_engine->queue))) { struct i915_priolist *p = to_priolist(rb); struct i915_request *rq, *rn; priolist_for_each_request_consume(rq, rn, p) { - if (last && rq->context != last->context) { - if (port == last_port) - goto done; - - *port = schedule_in(last, - port - execlists->inflight); - port++; - } + if (last && rq->context != last->context) + goto done; list_del_init(&rq->sched.link); + __i915_request_submit(rq); - submit = true; + + trace_i915_request_in(rq, 0); last = rq; + submit = true; } - rb_erase_cached(&p->node, &execlists->queue); + rb_erase_cached(&p->node, &sched_engine->queue); i915_priolist_free(p); } done: - execlists->queue_priority_hint = - rb ? to_priolist(rb)->priority : INT_MIN; if (submit) { - *port = schedule_in(last, port - execlists->inflight); - *++port = NULL; - guc_submit(engine, first, port); + guc_set_lrc_tail(last); +resubmit: + ret = guc_add_request(guc, last); + if (unlikely(ret == -EPIPE)) + goto deadlk; + else if (ret == -EBUSY) { + tasklet_schedule(&sched_engine->tasklet); + guc->stalled_request = last; + return false; + } } - execlists->active = execlists->inflight; + + guc->stalled_request = NULL; + return submit; + +deadlk: + sched_engine->tasklet.callback = NULL; + tasklet_disable_nosync(&sched_engine->tasklet); + return false; } static void guc_submission_tasklet(struct tasklet_struct *t) { - struct intel_engine_cs * const engine = - from_tasklet(engine, t, execlists.tasklet); - struct intel_engine_execlists * const execlists = &engine->execlists; - struct i915_request **port, *rq; + struct i915_sched_engine *sched_engine = + from_tasklet(sched_engine, t, tasklet); unsigned long flags; + bool loop; - spin_lock_irqsave(&engine->active.lock, flags); - - for (port = execlists->inflight; (rq = *port); port++) { - if (!i915_request_completed(rq)) - break; + spin_lock_irqsave(&sched_engine->lock, flags); - schedule_out(rq); - } - if (port != execlists->inflight) { - int idx = port - execlists->inflight; - int rem = ARRAY_SIZE(execlists->inflight) - idx; - memmove(execlists->inflight, port, rem * sizeof(*port)); - } + do { + loop = guc_dequeue_one_context(sched_engine->private_data); + } while (loop); - __guc_dequeue(engine); + i915_sched_engine_reset_on_empty(sched_engine); - spin_unlock_irqrestore(&engine->active.lock, flags); + spin_unlock_irqrestore(&sched_engine->lock, flags); } static void cs_irq_handler(struct intel_engine_cs *engine, u16 iir) { - if (iir & GT_RENDER_USER_INTERRUPT) { + if (iir & GT_RENDER_USER_INTERRUPT) intel_engine_signal_breadcrumbs(engine); - tasklet_hi_schedule(&engine->execlists.tasklet); +} + +static void __guc_context_destroy(struct intel_context *ce); +static void release_guc_id(struct intel_guc *guc, struct intel_context *ce); +static void guc_signal_context_fence(struct intel_context *ce); +static void guc_cancel_context_requests(struct intel_context *ce); +static void guc_blocked_fence_complete(struct intel_context *ce); + +static void scrub_guc_desc_for_outstanding_g2h(struct intel_guc *guc) +{ + struct intel_context *ce; + unsigned long index, flags; + bool pending_disable, pending_enable, deregister, destroyed, banned; + + xa_for_each(&guc->context_lookup, index, ce) { + /* Flush context */ + spin_lock_irqsave(&ce->guc_state.lock, flags); + spin_unlock_irqrestore(&ce->guc_state.lock, flags); + + /* + * Once we are at this point submission_disabled() is guaranteed + * to be visible to all callers who set the below flags (see above + * flush and flushes in reset_prepare). If submission_disabled() + * is set, the caller shouldn't set these flags. + */ + + destroyed = context_destroyed(ce); + pending_enable = context_pending_enable(ce); + pending_disable = context_pending_disable(ce); + deregister = context_wait_for_deregister_to_register(ce); + banned = context_banned(ce); + init_sched_state(ce); + + if (pending_enable || destroyed || deregister) { + atomic_dec(&guc->outstanding_submission_g2h); + if (deregister) + guc_signal_context_fence(ce); + if (destroyed) { + release_guc_id(guc, ce); + __guc_context_destroy(ce); + } + if (pending_enable || deregister) + intel_context_put(ce); + } + + /* Not mutualy exclusive with above if statement. */ + if (pending_disable) { + guc_signal_context_fence(ce); + if (banned) { + guc_cancel_context_requests(ce); + intel_engine_signal_breadcrumbs(ce->engine); + } + intel_context_sched_disable_unpin(ce); + atomic_dec(&guc->outstanding_submission_g2h); + spin_lock_irqsave(&ce->guc_state.lock, flags); + guc_blocked_fence_complete(ce); + spin_unlock_irqrestore(&ce->guc_state.lock, flags); + + intel_context_put(ce); + } } } -static void guc_reset_prepare(struct intel_engine_cs *engine) +static inline bool +submission_disabled(struct intel_guc *guc) +{ + struct i915_sched_engine * const sched_engine = guc->sched_engine; + + return unlikely(!sched_engine || + !__tasklet_is_enabled(&sched_engine->tasklet)); +} + +static void disable_submission(struct intel_guc *guc) { - struct intel_engine_execlists * const execlists = &engine->execlists; + struct i915_sched_engine * const sched_engine = guc->sched_engine; + + if (__tasklet_is_enabled(&sched_engine->tasklet)) { + GEM_BUG_ON(!guc->ct.enabled); + __tasklet_disable_sync_once(&sched_engine->tasklet); + sched_engine->tasklet.callback = NULL; + } +} + +static void enable_submission(struct intel_guc *guc) +{ + struct i915_sched_engine * const sched_engine = guc->sched_engine; + unsigned long flags; - ENGINE_TRACE(engine, "\n"); + spin_lock_irqsave(&guc->sched_engine->lock, flags); + sched_engine->tasklet.callback = guc_submission_tasklet; + wmb(); /* Make sure callback visible */ + if (!__tasklet_is_enabled(&sched_engine->tasklet) && + __tasklet_enable(&sched_engine->tasklet)) { + GEM_BUG_ON(!guc->ct.enabled); + + /* And kick in case we missed a new request submission. */ + tasklet_hi_schedule(&sched_engine->tasklet); + } + spin_unlock_irqrestore(&guc->sched_engine->lock, flags); +} + +static void guc_flush_submissions(struct intel_guc *guc) +{ + struct i915_sched_engine * const sched_engine = guc->sched_engine; + unsigned long flags; + + spin_lock_irqsave(&sched_engine->lock, flags); + spin_unlock_irqrestore(&sched_engine->lock, flags); +} + +void intel_guc_submission_reset_prepare(struct intel_guc *guc) +{ + int i; + + if (unlikely(!guc_submission_initialized(guc))) { + /* Reset called during driver load? GuC not yet initialised! */ + return; + } + + intel_gt_park_heartbeats(guc_to_gt(guc)); + disable_submission(guc); + guc->interrupts.disable(guc); + + /* Flush IRQ handler */ + spin_lock_irq(&guc_to_gt(guc)->irq_lock); + spin_unlock_irq(&guc_to_gt(guc)->irq_lock); + + guc_flush_submissions(guc); /* - * Prevent request submission to the hardware until we have - * completed the reset in i915_gem_reset_finish(). If a request - * is completed by one engine, it may then queue a request - * to a second via its execlists->tasklet *just* as we are - * calling engine->init_hw() and also writing the ELSP. - * Turning off the execlists->tasklet until the reset is over - * prevents the race. + * Handle any outstanding G2Hs before reset. Call IRQ handler directly + * each pass as interrupt have been disabled. We always scrub for + * outstanding G2H as it is possible for outstanding_submission_g2h to + * be incremented after the context state update. */ - __tasklet_disable_sync_once(&execlists->tasklet); + for (i = 0; i < 4 && atomic_read(&guc->outstanding_submission_g2h); ++i) { + intel_guc_to_host_event_handler(guc); +#define wait_for_reset(guc, wait_var) \ + intel_guc_wait_for_pending_msg(guc, wait_var, false, (HZ / 20)) + do { + wait_for_reset(guc, &guc->outstanding_submission_g2h); + } while (!list_empty(&guc->ct.requests.incoming)); + } + scrub_guc_desc_for_outstanding_g2h(guc); +} + +static struct intel_engine_cs * +guc_virtual_get_sibling(struct intel_engine_cs *ve, unsigned int sibling) +{ + struct intel_engine_cs *engine; + intel_engine_mask_t tmp, mask = ve->mask; + unsigned int num_siblings = 0; + + for_each_engine_masked(engine, ve->gt, mask, tmp) + if (num_siblings++ == sibling) + return engine; + + return NULL; +} + +static inline struct intel_engine_cs * +__context_to_physical_engine(struct intel_context *ce) +{ + struct intel_engine_cs *engine = ce->engine; + + if (intel_engine_is_virtual(engine)) + engine = guc_virtual_get_sibling(engine, 0); + + return engine; } -static void guc_reset_state(struct intel_context *ce, - struct intel_engine_cs *engine, - u32 head, - bool scrub) +static void guc_reset_state(struct intel_context *ce, u32 head, bool scrub) { + struct intel_engine_cs *engine = __context_to_physical_engine(ce); + + if (intel_context_is_banned(ce)) + return; + GEM_BUG_ON(!intel_context_is_pinned(ce)); /* @@ -313,37 +777,132 @@ static void guc_reset_state(struct intel_context *ce, lrc_update_regs(ce, engine, head); } -static void guc_reset_rewind(struct intel_engine_cs *engine, bool stalled) +static void guc_reset_nop(struct intel_engine_cs *engine) { - struct intel_engine_execlists * const execlists = &engine->execlists; - struct i915_request *rq; +} + +static void guc_rewind_nop(struct intel_engine_cs *engine, bool stalled) +{ +} + +static void +__unwind_incomplete_requests(struct intel_context *ce) +{ + struct i915_request *rq, *rn; + struct list_head *pl; + int prio = I915_PRIORITY_INVALID; + struct i915_sched_engine * const sched_engine = + ce->engine->sched_engine; unsigned long flags; - spin_lock_irqsave(&engine->active.lock, flags); + spin_lock_irqsave(&sched_engine->lock, flags); + spin_lock(&ce->guc_active.lock); + list_for_each_entry_safe(rq, rn, + &ce->guc_active.requests, + sched.link) { + if (i915_request_completed(rq)) + continue; - /* Push back any incomplete requests for replay after the reset. */ - rq = execlists_unwind_incomplete_requests(execlists); - if (!rq) - goto out_unlock; + list_del_init(&rq->sched.link); + spin_unlock(&ce->guc_active.lock); + + __i915_request_unsubmit(rq); + + /* Push the request back into the queue for later resubmission. */ + GEM_BUG_ON(rq_prio(rq) == I915_PRIORITY_INVALID); + if (rq_prio(rq) != prio) { + prio = rq_prio(rq); + pl = i915_sched_lookup_priolist(sched_engine, prio); + } + GEM_BUG_ON(i915_sched_engine_is_empty(sched_engine)); + + list_add_tail(&rq->sched.link, pl); + set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags); + + spin_lock(&ce->guc_active.lock); + } + spin_unlock(&ce->guc_active.lock); + spin_unlock_irqrestore(&sched_engine->lock, flags); +} + +static void __guc_reset_context(struct intel_context *ce, bool stalled) +{ + struct i915_request *rq; + u32 head; + + intel_context_get(ce); + + /* + * GuC will implicitly mark the context as non-schedulable + * when it sends the reset notification. Make sure our state + * reflects this change. The context will be marked enabled + * on resubmission. + */ + clr_context_enabled(ce); + + rq = intel_context_find_active_request(ce); + if (!rq) { + head = ce->ring->tail; + stalled = false; + goto out_replay; + } if (!i915_request_started(rq)) stalled = false; + GEM_BUG_ON(i915_active_is_idle(&ce->active)); + head = intel_ring_wrap(ce->ring, rq->head); __i915_request_reset(rq, stalled); - guc_reset_state(rq->context, engine, rq->head, stalled); -out_unlock: - spin_unlock_irqrestore(&engine->active.lock, flags); +out_replay: + guc_reset_state(ce, head, stalled); + __unwind_incomplete_requests(ce); + intel_context_put(ce); +} + +void intel_guc_submission_reset(struct intel_guc *guc, bool stalled) +{ + struct intel_context *ce; + unsigned long index; + + if (unlikely(!guc_submission_initialized(guc))) { + /* Reset called during driver load? GuC not yet initialised! */ + return; + } + + xa_for_each(&guc->context_lookup, index, ce) + if (intel_context_is_pinned(ce)) + __guc_reset_context(ce, stalled); + + /* GuC is blown away, drop all references to contexts */ + xa_destroy(&guc->context_lookup); } -static void guc_reset_cancel(struct intel_engine_cs *engine) +static void guc_cancel_context_requests(struct intel_context *ce) +{ + struct i915_sched_engine *sched_engine = ce_to_guc(ce)->sched_engine; + struct i915_request *rq; + unsigned long flags; + + /* Mark all executing requests as skipped. */ + spin_lock_irqsave(&sched_engine->lock, flags); + spin_lock(&ce->guc_active.lock); + list_for_each_entry(rq, &ce->guc_active.requests, sched.link) + i915_request_put(i915_request_mark_eio(rq)); + spin_unlock(&ce->guc_active.lock); + spin_unlock_irqrestore(&sched_engine->lock, flags); +} + +static void +guc_cancel_sched_engine_requests(struct i915_sched_engine *sched_engine) { - struct intel_engine_execlists * const execlists = &engine->execlists; struct i915_request *rq, *rn; struct rb_node *rb; unsigned long flags; - ENGINE_TRACE(engine, "\n"); + /* Can be called during boot if GuC fails to load */ + if (!sched_engine) + return; /* * Before we call engine->cancel_requests(), we should have exclusive @@ -359,47 +918,67 @@ static void guc_reset_cancel(struct intel_engine_cs *engine) * submission's irq state, we also wish to remind ourselves that * it is irq state.) */ - spin_lock_irqsave(&engine->active.lock, flags); - - /* Mark all executing requests as skipped. */ - list_for_each_entry(rq, &engine->active.requests, sched.link) { - i915_request_set_error_once(rq, -EIO); - i915_request_mark_complete(rq); - } + spin_lock_irqsave(&sched_engine->lock, flags); /* Flush the queued requests to the timeline list (for retiring). */ - while ((rb = rb_first_cached(&execlists->queue))) { + while ((rb = rb_first_cached(&sched_engine->queue))) { struct i915_priolist *p = to_priolist(rb); priolist_for_each_request_consume(rq, rn, p) { list_del_init(&rq->sched.link); + __i915_request_submit(rq); - dma_fence_set_error(&rq->fence, -EIO); - i915_request_mark_complete(rq); + + i915_request_put(i915_request_mark_eio(rq)); } - rb_erase_cached(&p->node, &execlists->queue); + rb_erase_cached(&p->node, &sched_engine->queue); i915_priolist_free(p); } /* Remaining _unready_ requests will be nop'ed when submitted */ - execlists->queue_priority_hint = INT_MIN; - execlists->queue = RB_ROOT_CACHED; + sched_engine->queue_priority_hint = INT_MIN; + sched_engine->queue = RB_ROOT_CACHED; - spin_unlock_irqrestore(&engine->active.lock, flags); + spin_unlock_irqrestore(&sched_engine->lock, flags); } -static void guc_reset_finish(struct intel_engine_cs *engine) +void intel_guc_submission_cancel_requests(struct intel_guc *guc) { - struct intel_engine_execlists * const execlists = &engine->execlists; + struct intel_context *ce; + unsigned long index; - if (__tasklet_enable(&execlists->tasklet)) - /* And kick in case we missed a new request submission. */ - tasklet_hi_schedule(&execlists->tasklet); + xa_for_each(&guc->context_lookup, index, ce) + if (intel_context_is_pinned(ce)) + guc_cancel_context_requests(ce); + + guc_cancel_sched_engine_requests(guc->sched_engine); - ENGINE_TRACE(engine, "depth->%d\n", - atomic_read(&execlists->tasklet.count)); + /* GuC is blown away, drop all references to contexts */ + xa_destroy(&guc->context_lookup); +} + +void intel_guc_submission_reset_finish(struct intel_guc *guc) +{ + /* Reset called during driver load or during wedge? */ + if (unlikely(!guc_submission_initialized(guc) || + test_bit(I915_WEDGED, &guc_to_gt(guc)->reset.flags))) { + return; + } + + /* + * Technically possible for either of these values to be non-zero here, + * but very unlikely + harmless. Regardless let's add a warn so we can + * see in CI if this happens frequently / a precursor to taking down the + * machine. + */ + GEM_WARN_ON(atomic_read(&guc->outstanding_submission_g2h)); + atomic_set(&guc->outstanding_submission_g2h, 0); + + intel_guc_global_policies_update(guc); + enable_submission(guc); + intel_gt_unpark_heartbeats(guc_to_gt(guc)); } /* @@ -410,43 +989,986 @@ int intel_guc_submission_init(struct intel_guc *guc) { int ret; - if (guc->stage_desc_pool) + if (guc->lrc_desc_pool) return 0; - ret = guc_stage_desc_pool_create(guc); + ret = guc_lrc_desc_pool_create(guc); if (ret) return ret; /* * Keep static analysers happy, let them know that we allocated the * vma after testing that it didn't exist earlier. */ - GEM_BUG_ON(!guc->stage_desc_pool); + GEM_BUG_ON(!guc->lrc_desc_pool); + + xa_init_flags(&guc->context_lookup, XA_FLAGS_LOCK_IRQ); + + spin_lock_init(&guc->contexts_lock); + INIT_LIST_HEAD(&guc->guc_id_list); + ida_init(&guc->guc_ids); return 0; } void intel_guc_submission_fini(struct intel_guc *guc) { - if (guc->stage_desc_pool) { - guc_stage_desc_pool_destroy(guc); + if (!guc->lrc_desc_pool) + return; + + guc_lrc_desc_pool_destroy(guc); + i915_sched_engine_put(guc->sched_engine); +} + +static inline void queue_request(struct i915_sched_engine *sched_engine, + struct i915_request *rq, + int prio) +{ + GEM_BUG_ON(!list_empty(&rq->sched.link)); + list_add_tail(&rq->sched.link, + i915_sched_lookup_priolist(sched_engine, prio)); + set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags); +} + +static int guc_bypass_tasklet_submit(struct intel_guc *guc, + struct i915_request *rq) +{ + int ret; + + __i915_request_submit(rq); + + trace_i915_request_in(rq, 0); + + guc_set_lrc_tail(rq); + ret = guc_add_request(guc, rq); + if (ret == -EBUSY) + guc->stalled_request = rq; + + if (unlikely(ret == -EPIPE)) + disable_submission(guc); + + return ret; +} + +static void guc_submit_request(struct i915_request *rq) +{ + struct i915_sched_engine *sched_engine = rq->engine->sched_engine; + struct intel_guc *guc = &rq->engine->gt->uc.guc; + unsigned long flags; + + /* Will be called from irq-context when using foreign fences. */ + spin_lock_irqsave(&sched_engine->lock, flags); + + if (submission_disabled(guc) || guc->stalled_request || + !i915_sched_engine_is_empty(sched_engine)) + queue_request(sched_engine, rq, rq_prio(rq)); + else if (guc_bypass_tasklet_submit(guc, rq) == -EBUSY) + tasklet_hi_schedule(&sched_engine->tasklet); + + spin_unlock_irqrestore(&sched_engine->lock, flags); +} + +static int new_guc_id(struct intel_guc *guc) +{ + return ida_simple_get(&guc->guc_ids, 0, + GUC_MAX_LRC_DESCRIPTORS, GFP_KERNEL | + __GFP_RETRY_MAYFAIL | __GFP_NOWARN); +} + +static void __release_guc_id(struct intel_guc *guc, struct intel_context *ce) +{ + if (!context_guc_id_invalid(ce)) { + ida_simple_remove(&guc->guc_ids, ce->guc_id); + reset_lrc_desc(guc, ce->guc_id); + set_context_guc_id_invalid(ce); } + if (!list_empty(&ce->guc_id_link)) + list_del_init(&ce->guc_id_link); } -static int guc_context_alloc(struct intel_context *ce) +static void release_guc_id(struct intel_guc *guc, struct intel_context *ce) { - return lrc_alloc(ce, ce->engine); + unsigned long flags; + + spin_lock_irqsave(&guc->contexts_lock, flags); + __release_guc_id(guc, ce); + spin_unlock_irqrestore(&guc->contexts_lock, flags); +} + +static int steal_guc_id(struct intel_guc *guc) +{ + struct intel_context *ce; + int guc_id; + + lockdep_assert_held(&guc->contexts_lock); + + if (!list_empty(&guc->guc_id_list)) { + ce = list_first_entry(&guc->guc_id_list, + struct intel_context, + guc_id_link); + + GEM_BUG_ON(atomic_read(&ce->guc_id_ref)); + GEM_BUG_ON(context_guc_id_invalid(ce)); + + list_del_init(&ce->guc_id_link); + guc_id = ce->guc_id; + clr_context_registered(ce); + set_context_guc_id_invalid(ce); + return guc_id; + } else { + return -EAGAIN; + } +} + +static int assign_guc_id(struct intel_guc *guc, u16 *out) +{ + int ret; + + lockdep_assert_held(&guc->contexts_lock); + + ret = new_guc_id(guc); + if (unlikely(ret < 0)) { + ret = steal_guc_id(guc); + if (ret < 0) + return ret; + } + + *out = ret; + return 0; +} + +#define PIN_GUC_ID_TRIES 4 +static int pin_guc_id(struct intel_guc *guc, struct intel_context *ce) +{ + int ret = 0; + unsigned long flags, tries = PIN_GUC_ID_TRIES; + + GEM_BUG_ON(atomic_read(&ce->guc_id_ref)); + +try_again: + spin_lock_irqsave(&guc->contexts_lock, flags); + + if (context_guc_id_invalid(ce)) { + ret = assign_guc_id(guc, &ce->guc_id); + if (ret) + goto out_unlock; + ret = 1; /* Indidcates newly assigned guc_id */ + } + if (!list_empty(&ce->guc_id_link)) + list_del_init(&ce->guc_id_link); + atomic_inc(&ce->guc_id_ref); + +out_unlock: + spin_unlock_irqrestore(&guc->contexts_lock, flags); + + /* + * -EAGAIN indicates no guc_ids are available, let's retire any + * outstanding requests to see if that frees up a guc_id. If the first + * retire didn't help, insert a sleep with the timeslice duration before + * attempting to retire more requests. Double the sleep period each + * subsequent pass before finally giving up. The sleep period has max of + * 100ms and minimum of 1ms. + */ + if (ret == -EAGAIN && --tries) { + if (PIN_GUC_ID_TRIES - tries > 1) { + unsigned int timeslice_shifted = + ce->engine->props.timeslice_duration_ms << + (PIN_GUC_ID_TRIES - tries - 2); + unsigned int max = min_t(unsigned int, 100, + timeslice_shifted); + + msleep(max_t(unsigned int, max, 1)); + } + intel_gt_retire_requests(guc_to_gt(guc)); + goto try_again; + } + + return ret; +} + +static void unpin_guc_id(struct intel_guc *guc, struct intel_context *ce) +{ + unsigned long flags; + + GEM_BUG_ON(atomic_read(&ce->guc_id_ref) < 0); + + if (unlikely(context_guc_id_invalid(ce))) + return; + + spin_lock_irqsave(&guc->contexts_lock, flags); + if (!context_guc_id_invalid(ce) && list_empty(&ce->guc_id_link) && + !atomic_read(&ce->guc_id_ref)) + list_add_tail(&ce->guc_id_link, &guc->guc_id_list); + spin_unlock_irqrestore(&guc->contexts_lock, flags); +} + +static int __guc_action_register_context(struct intel_guc *guc, + u32 guc_id, + u32 offset, + bool loop) +{ + u32 action[] = { + INTEL_GUC_ACTION_REGISTER_CONTEXT, + guc_id, + offset, + }; + + return guc_submission_send_busy_loop(guc, action, ARRAY_SIZE(action), + 0, loop); +} + +static int register_context(struct intel_context *ce, bool loop) +{ + struct intel_guc *guc = ce_to_guc(ce); + u32 offset = intel_guc_ggtt_offset(guc, guc->lrc_desc_pool) + + ce->guc_id * sizeof(struct guc_lrc_desc); + int ret; + + trace_intel_context_register(ce); + + ret = __guc_action_register_context(guc, ce->guc_id, offset, loop); + if (likely(!ret)) + set_context_registered(ce); + + return ret; +} + +static int __guc_action_deregister_context(struct intel_guc *guc, + u32 guc_id, + bool loop) +{ + u32 action[] = { + INTEL_GUC_ACTION_DEREGISTER_CONTEXT, + guc_id, + }; + + return guc_submission_send_busy_loop(guc, action, ARRAY_SIZE(action), + G2H_LEN_DW_DEREGISTER_CONTEXT, + loop); +} + +static int deregister_context(struct intel_context *ce, u32 guc_id, bool loop) +{ + struct intel_guc *guc = ce_to_guc(ce); + + trace_intel_context_deregister(ce); + + return __guc_action_deregister_context(guc, guc_id, loop); +} + +static intel_engine_mask_t adjust_engine_mask(u8 class, intel_engine_mask_t mask) +{ + switch (class) { + case RENDER_CLASS: + return mask >> RCS0; + case VIDEO_ENHANCEMENT_CLASS: + return mask >> VECS0; + case VIDEO_DECODE_CLASS: + return mask >> VCS0; + case COPY_ENGINE_CLASS: + return mask >> BCS0; + default: + MISSING_CASE(class); + return 0; + } +} + +static void guc_context_policy_init(struct intel_engine_cs *engine, + struct guc_lrc_desc *desc) +{ + desc->policy_flags = 0; + + if (engine->flags & I915_ENGINE_WANT_FORCED_PREEMPTION) + desc->policy_flags |= CONTEXT_POLICY_FLAG_PREEMPT_TO_IDLE; + + /* NB: For both of these, zero means disabled. */ + desc->execution_quantum = engine->props.timeslice_duration_ms * 1000; + desc->preemption_timeout = engine->props.preempt_timeout_ms * 1000; +} + +static inline u8 map_i915_prio_to_guc_prio(int prio); + +static int guc_lrc_desc_pin(struct intel_context *ce, bool loop) +{ + struct intel_engine_cs *engine = ce->engine; + struct intel_runtime_pm *runtime_pm = engine->uncore->rpm; + struct intel_guc *guc = &engine->gt->uc.guc; + u32 desc_idx = ce->guc_id; + struct guc_lrc_desc *desc; + const struct i915_gem_context *ctx; + int prio = I915_CONTEXT_DEFAULT_PRIORITY; + bool context_registered; + intel_wakeref_t wakeref; + int ret = 0; + + GEM_BUG_ON(!engine->mask); + + /* + * Ensure LRC + CT vmas are is same region as write barrier is done + * based on CT vma region. + */ + GEM_BUG_ON(i915_gem_object_is_lmem(guc->ct.vma->obj) != + i915_gem_object_is_lmem(ce->ring->vma->obj)); + + context_registered = lrc_desc_registered(guc, desc_idx); + + rcu_read_lock(); + ctx = rcu_dereference(ce->gem_context); + if (ctx) + prio = ctx->sched.priority; + rcu_read_unlock(); + + reset_lrc_desc(guc, desc_idx); + set_lrc_desc_registered(guc, desc_idx, ce); + + desc = __get_lrc_desc(guc, desc_idx); + desc->engine_class = engine_class_to_guc_class(engine->class); + desc->engine_submit_mask = adjust_engine_mask(engine->class, + engine->mask); + desc->hw_context_desc = ce->lrc.lrca; + ce->guc_prio = map_i915_prio_to_guc_prio(prio); + desc->priority = ce->guc_prio; + desc->context_flags = CONTEXT_REGISTRATION_FLAG_KMD; + guc_context_policy_init(engine, desc); + init_sched_state(ce); + + /* + * The context_lookup xarray is used to determine if the hardware + * context is currently registered. There are two cases in which it + * could be registered either the guc_id has been stolen from another + * context or the lrc descriptor address of this context has changed. In + * either case the context needs to be deregistered with the GuC before + * registering this context. + */ + if (context_registered) { + trace_intel_context_steal_guc_id(ce); + if (!loop) { + set_context_wait_for_deregister_to_register(ce); + intel_context_get(ce); + } else { + bool disabled; + unsigned long flags; + + /* Seal race with Reset */ + spin_lock_irqsave(&ce->guc_state.lock, flags); + disabled = submission_disabled(guc); + if (likely(!disabled)) { + set_context_wait_for_deregister_to_register(ce); + intel_context_get(ce); + } + spin_unlock_irqrestore(&ce->guc_state.lock, flags); + if (unlikely(disabled)) { + reset_lrc_desc(guc, desc_idx); + return 0; /* Will get registered later */ + } + } + + /* + * If stealing the guc_id, this ce has the same guc_id as the + * context whose guc_id was stolen. + */ + with_intel_runtime_pm(runtime_pm, wakeref) + ret = deregister_context(ce, ce->guc_id, loop); + if (unlikely(ret == -EBUSY)) { + clr_context_wait_for_deregister_to_register(ce); + intel_context_put(ce); + } else if (unlikely(ret == -ENODEV)) { + ret = 0; /* Will get registered later */ + } + } else { + with_intel_runtime_pm(runtime_pm, wakeref) + ret = register_context(ce, loop); + if (unlikely(ret == -EBUSY)) + reset_lrc_desc(guc, desc_idx); + else if (unlikely(ret == -ENODEV)) + ret = 0; /* Will get registered later */ + } + + return ret; +} + +static int __guc_context_pre_pin(struct intel_context *ce, + struct intel_engine_cs *engine, + struct i915_gem_ww_ctx *ww, + void **vaddr) +{ + return lrc_pre_pin(ce, engine, ww, vaddr); +} + +static int __guc_context_pin(struct intel_context *ce, + struct intel_engine_cs *engine, + void *vaddr) +{ + if (i915_ggtt_offset(ce->state) != + (ce->lrc.lrca & CTX_GTT_ADDRESS_MASK)) + set_bit(CONTEXT_LRCA_DIRTY, &ce->flags); + + /* + * GuC context gets pinned in guc_request_alloc. See that function for + * explaination of why. + */ + + return lrc_pin(ce, engine, vaddr); } static int guc_context_pre_pin(struct intel_context *ce, struct i915_gem_ww_ctx *ww, void **vaddr) { - return lrc_pre_pin(ce, ce->engine, ww, vaddr); + return __guc_context_pre_pin(ce, ce->engine, ww, vaddr); } static int guc_context_pin(struct intel_context *ce, void *vaddr) { - return lrc_pin(ce, ce->engine, vaddr); + return __guc_context_pin(ce, ce->engine, vaddr); +} + +static void guc_context_unpin(struct intel_context *ce) +{ + struct intel_guc *guc = ce_to_guc(ce); + + unpin_guc_id(guc, ce); + lrc_unpin(ce); +} + +static void guc_context_post_unpin(struct intel_context *ce) +{ + lrc_post_unpin(ce); +} + +static void __guc_context_sched_enable(struct intel_guc *guc, + struct intel_context *ce) +{ + u32 action[] = { + INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_SET, + ce->guc_id, + GUC_CONTEXT_ENABLE + }; + + trace_intel_context_sched_enable(ce); + + guc_submission_send_busy_loop(guc, action, ARRAY_SIZE(action), + G2H_LEN_DW_SCHED_CONTEXT_MODE_SET, true); +} + +static void __guc_context_sched_disable(struct intel_guc *guc, + struct intel_context *ce, + u16 guc_id) +{ + u32 action[] = { + INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_SET, + guc_id, /* ce->guc_id not stable */ + GUC_CONTEXT_DISABLE + }; + + GEM_BUG_ON(guc_id == GUC_INVALID_LRC_ID); + + trace_intel_context_sched_disable(ce); + + guc_submission_send_busy_loop(guc, action, ARRAY_SIZE(action), + G2H_LEN_DW_SCHED_CONTEXT_MODE_SET, true); +} + +static void guc_blocked_fence_complete(struct intel_context *ce) +{ + lockdep_assert_held(&ce->guc_state.lock); + + if (!i915_sw_fence_done(&ce->guc_blocked)) + i915_sw_fence_complete(&ce->guc_blocked); +} + +static void guc_blocked_fence_reinit(struct intel_context *ce) +{ + lockdep_assert_held(&ce->guc_state.lock); + GEM_BUG_ON(!i915_sw_fence_done(&ce->guc_blocked)); + + /* + * This fence is always complete unless a pending schedule disable is + * outstanding. We arm the fence here and complete it when we receive + * the pending schedule disable complete message. + */ + i915_sw_fence_fini(&ce->guc_blocked); + i915_sw_fence_reinit(&ce->guc_blocked); + i915_sw_fence_await(&ce->guc_blocked); + i915_sw_fence_commit(&ce->guc_blocked); +} + +static u16 prep_context_pending_disable(struct intel_context *ce) +{ + lockdep_assert_held(&ce->guc_state.lock); + + set_context_pending_disable(ce); + clr_context_enabled(ce); + guc_blocked_fence_reinit(ce); + intel_context_get(ce); + + return ce->guc_id; +} + +static struct i915_sw_fence *guc_context_block(struct intel_context *ce) +{ + struct intel_guc *guc = ce_to_guc(ce); + struct i915_sched_engine *sched_engine = ce->engine->sched_engine; + unsigned long flags; + struct intel_runtime_pm *runtime_pm = ce->engine->uncore->rpm; + intel_wakeref_t wakeref; + u16 guc_id; + bool enabled; + + spin_lock_irqsave(&ce->guc_state.lock, flags); + + /* + * Sync with submission path, increment before below changes to context + * state. + */ + spin_lock(&sched_engine->lock); + incr_context_blocked(ce); + spin_unlock(&sched_engine->lock); + + enabled = context_enabled(ce); + if (unlikely(!enabled || submission_disabled(guc))) { + if (enabled) + clr_context_enabled(ce); + spin_unlock_irqrestore(&ce->guc_state.lock, flags); + return &ce->guc_blocked; + } + + /* + * We add +2 here as the schedule disable complete CTB handler calls + * intel_context_sched_disable_unpin (-2 to pin_count). + */ + atomic_add(2, &ce->pin_count); + + guc_id = prep_context_pending_disable(ce); + + spin_unlock_irqrestore(&ce->guc_state.lock, flags); + + with_intel_runtime_pm(runtime_pm, wakeref) + __guc_context_sched_disable(guc, ce, guc_id); + + return &ce->guc_blocked; +} + +static void guc_context_unblock(struct intel_context *ce) +{ + struct intel_guc *guc = ce_to_guc(ce); + struct i915_sched_engine *sched_engine = ce->engine->sched_engine; + unsigned long flags; + struct intel_runtime_pm *runtime_pm = ce->engine->uncore->rpm; + intel_wakeref_t wakeref; + bool enable; + + GEM_BUG_ON(context_enabled(ce)); + + spin_lock_irqsave(&ce->guc_state.lock, flags); + + if (unlikely(submission_disabled(guc) || + !intel_context_is_pinned(ce) || + context_pending_disable(ce) || + context_blocked(ce) > 1)) { + enable = false; + } else { + enable = true; + set_context_pending_enable(ce); + set_context_enabled(ce); + intel_context_get(ce); + } + + /* + * Sync with submission path, decrement after above changes to context + * state. + */ + spin_lock(&sched_engine->lock); + decr_context_blocked(ce); + spin_unlock(&sched_engine->lock); + + spin_unlock_irqrestore(&ce->guc_state.lock, flags); + + if (enable) { + with_intel_runtime_pm(runtime_pm, wakeref) + __guc_context_sched_enable(guc, ce); + } +} + +static void guc_context_cancel_request(struct intel_context *ce, + struct i915_request *rq) +{ + if (i915_sw_fence_signaled(&rq->submit)) { + struct i915_sw_fence *fence = guc_context_block(ce); + + i915_sw_fence_wait(fence); + if (!i915_request_completed(rq)) { + __i915_request_skip(rq); + guc_reset_state(ce, intel_ring_wrap(ce->ring, rq->head), + true); + } + guc_context_unblock(ce); + } +} + +static void __guc_context_set_preemption_timeout(struct intel_guc *guc, + u16 guc_id, + u32 preemption_timeout) +{ + u32 action[] = { + INTEL_GUC_ACTION_SET_CONTEXT_PREEMPTION_TIMEOUT, + guc_id, + preemption_timeout + }; + + intel_guc_send_busy_loop(guc, action, ARRAY_SIZE(action), 0, true); +} + +static void guc_context_ban(struct intel_context *ce, struct i915_request *rq) +{ + struct intel_guc *guc = ce_to_guc(ce); + struct intel_runtime_pm *runtime_pm = + &ce->engine->gt->i915->runtime_pm; + intel_wakeref_t wakeref; + unsigned long flags; + + guc_flush_submissions(guc); + + spin_lock_irqsave(&ce->guc_state.lock, flags); + set_context_banned(ce); + + if (submission_disabled(guc) || + (!context_enabled(ce) && !context_pending_disable(ce))) { + spin_unlock_irqrestore(&ce->guc_state.lock, flags); + + guc_cancel_context_requests(ce); + intel_engine_signal_breadcrumbs(ce->engine); + } else if (!context_pending_disable(ce)) { + u16 guc_id; + + /* + * We add +2 here as the schedule disable complete CTB handler + * calls intel_context_sched_disable_unpin (-2 to pin_count). + */ + atomic_add(2, &ce->pin_count); + + guc_id = prep_context_pending_disable(ce); + spin_unlock_irqrestore(&ce->guc_state.lock, flags); + + /* + * In addition to disabling scheduling, set the preemption + * timeout to the minimum value (1 us) so the banned context + * gets kicked off the HW ASAP. + */ + with_intel_runtime_pm(runtime_pm, wakeref) { + __guc_context_set_preemption_timeout(guc, guc_id, 1); + __guc_context_sched_disable(guc, ce, guc_id); + } + } else { + if (!context_guc_id_invalid(ce)) + with_intel_runtime_pm(runtime_pm, wakeref) + __guc_context_set_preemption_timeout(guc, + ce->guc_id, + 1); + spin_unlock_irqrestore(&ce->guc_state.lock, flags); + } +} + +static void guc_context_sched_disable(struct intel_context *ce) +{ + struct intel_guc *guc = ce_to_guc(ce); + unsigned long flags; + struct intel_runtime_pm *runtime_pm = &ce->engine->gt->i915->runtime_pm; + intel_wakeref_t wakeref; + u16 guc_id; + bool enabled; + + if (submission_disabled(guc) || context_guc_id_invalid(ce) || + !lrc_desc_registered(guc, ce->guc_id)) { + clr_context_enabled(ce); + goto unpin; + } + + if (!context_enabled(ce)) + goto unpin; + + spin_lock_irqsave(&ce->guc_state.lock, flags); + + /* + * We have to check if the context has been disabled by another thread. + * We also have to check if the context has been pinned again as another + * pin operation is allowed to pass this function. Checking the pin + * count, within ce->guc_state.lock, synchronizes this function with + * guc_request_alloc ensuring a request doesn't slip through the + * 'context_pending_disable' fence. Checking within the spin lock (can't + * sleep) ensures another process doesn't pin this context and generate + * a request before we set the 'context_pending_disable' flag here. + */ + enabled = context_enabled(ce); + if (unlikely(!enabled || submission_disabled(guc))) { + if (enabled) + clr_context_enabled(ce); + spin_unlock_irqrestore(&ce->guc_state.lock, flags); + goto unpin; + } + if (unlikely(atomic_add_unless(&ce->pin_count, -2, 2))) { + spin_unlock_irqrestore(&ce->guc_state.lock, flags); + return; + } + guc_id = prep_context_pending_disable(ce); + + spin_unlock_irqrestore(&ce->guc_state.lock, flags); + + with_intel_runtime_pm(runtime_pm, wakeref) + __guc_context_sched_disable(guc, ce, guc_id); + + return; +unpin: + intel_context_sched_disable_unpin(ce); +} + +static inline void guc_lrc_desc_unpin(struct intel_context *ce) +{ + struct intel_guc *guc = ce_to_guc(ce); + + GEM_BUG_ON(!lrc_desc_registered(guc, ce->guc_id)); + GEM_BUG_ON(ce != __get_context(guc, ce->guc_id)); + GEM_BUG_ON(context_enabled(ce)); + + clr_context_registered(ce); + deregister_context(ce, ce->guc_id, true); +} + +static void __guc_context_destroy(struct intel_context *ce) +{ + GEM_BUG_ON(ce->guc_prio_count[GUC_CLIENT_PRIORITY_KMD_HIGH] || + ce->guc_prio_count[GUC_CLIENT_PRIORITY_HIGH] || + ce->guc_prio_count[GUC_CLIENT_PRIORITY_KMD_NORMAL] || + ce->guc_prio_count[GUC_CLIENT_PRIORITY_NORMAL]); + + lrc_fini(ce); + intel_context_fini(ce); + + if (intel_engine_is_virtual(ce->engine)) { + struct guc_virtual_engine *ve = + container_of(ce, typeof(*ve), context); + + if (ve->base.breadcrumbs) + intel_breadcrumbs_put(ve->base.breadcrumbs); + + kfree(ve); + } else { + intel_context_free(ce); + } +} + +static void guc_context_destroy(struct kref *kref) +{ + struct intel_context *ce = container_of(kref, typeof(*ce), ref); + struct intel_runtime_pm *runtime_pm = ce->engine->uncore->rpm; + struct intel_guc *guc = ce_to_guc(ce); + intel_wakeref_t wakeref; + unsigned long flags; + bool disabled; + + /* + * If the guc_id is invalid this context has been stolen and we can free + * it immediately. Also can be freed immediately if the context is not + * registered with the GuC or the GuC is in the middle of a reset. + */ + if (context_guc_id_invalid(ce)) { + __guc_context_destroy(ce); + return; + } else if (submission_disabled(guc) || + !lrc_desc_registered(guc, ce->guc_id)) { + release_guc_id(guc, ce); + __guc_context_destroy(ce); + return; + } + + /* + * We have to acquire the context spinlock and check guc_id again, if it + * is valid it hasn't been stolen and needs to be deregistered. We + * delete this context from the list of unpinned guc_ids available to + * steal to seal a race with guc_lrc_desc_pin(). When the G2H CTB + * returns indicating this context has been deregistered the guc_id is + * returned to the pool of available guc_ids. + */ + spin_lock_irqsave(&guc->contexts_lock, flags); + if (context_guc_id_invalid(ce)) { + spin_unlock_irqrestore(&guc->contexts_lock, flags); + __guc_context_destroy(ce); + return; + } + + if (!list_empty(&ce->guc_id_link)) + list_del_init(&ce->guc_id_link); + spin_unlock_irqrestore(&guc->contexts_lock, flags); + + /* Seal race with Reset */ + spin_lock_irqsave(&ce->guc_state.lock, flags); + disabled = submission_disabled(guc); + if (likely(!disabled)) + set_context_destroyed(ce); + spin_unlock_irqrestore(&ce->guc_state.lock, flags); + if (unlikely(disabled)) { + release_guc_id(guc, ce); + __guc_context_destroy(ce); + return; + } + + /* + * We defer GuC context deregistration until the context is destroyed + * in order to save on CTBs. With this optimization ideally we only need + * 1 CTB to register the context during the first pin and 1 CTB to + * deregister the context when the context is destroyed. Without this + * optimization, a CTB would be needed every pin & unpin. + * + * XXX: Need to acqiure the runtime wakeref as this can be triggered + * from context_free_worker when runtime wakeref is not held. + * guc_lrc_desc_unpin requires the runtime as a GuC register is written + * in H2G CTB to deregister the context. A future patch may defer this + * H2G CTB if the runtime wakeref is zero. + */ + with_intel_runtime_pm(runtime_pm, wakeref) + guc_lrc_desc_unpin(ce); +} + +static int guc_context_alloc(struct intel_context *ce) +{ + return lrc_alloc(ce, ce->engine); +} + +static void guc_context_set_prio(struct intel_guc *guc, + struct intel_context *ce, + u8 prio) +{ + u32 action[] = { + INTEL_GUC_ACTION_SET_CONTEXT_PRIORITY, + ce->guc_id, + prio, + }; + + GEM_BUG_ON(prio < GUC_CLIENT_PRIORITY_KMD_HIGH || + prio > GUC_CLIENT_PRIORITY_NORMAL); + + if (ce->guc_prio == prio || submission_disabled(guc) || + !context_registered(ce)) + return; + + guc_submission_send_busy_loop(guc, action, ARRAY_SIZE(action), 0, true); + + ce->guc_prio = prio; + trace_intel_context_set_prio(ce); +} + +static inline u8 map_i915_prio_to_guc_prio(int prio) +{ + if (prio == I915_PRIORITY_NORMAL) + return GUC_CLIENT_PRIORITY_KMD_NORMAL; + else if (prio < I915_PRIORITY_NORMAL) + return GUC_CLIENT_PRIORITY_NORMAL; + else if (prio < I915_PRIORITY_DISPLAY) + return GUC_CLIENT_PRIORITY_HIGH; + else + return GUC_CLIENT_PRIORITY_KMD_HIGH; +} + +static inline void add_context_inflight_prio(struct intel_context *ce, + u8 guc_prio) +{ + lockdep_assert_held(&ce->guc_active.lock); + GEM_BUG_ON(guc_prio >= ARRAY_SIZE(ce->guc_prio_count)); + + ++ce->guc_prio_count[guc_prio]; + + /* Overflow protection */ + GEM_WARN_ON(!ce->guc_prio_count[guc_prio]); +} + +static inline void sub_context_inflight_prio(struct intel_context *ce, + u8 guc_prio) +{ + lockdep_assert_held(&ce->guc_active.lock); + GEM_BUG_ON(guc_prio >= ARRAY_SIZE(ce->guc_prio_count)); + + /* Underflow protection */ + GEM_WARN_ON(!ce->guc_prio_count[guc_prio]); + + --ce->guc_prio_count[guc_prio]; +} + +static inline void update_context_prio(struct intel_context *ce) +{ + struct intel_guc *guc = &ce->engine->gt->uc.guc; + int i; + + BUILD_BUG_ON(GUC_CLIENT_PRIORITY_KMD_HIGH != 0); + BUILD_BUG_ON(GUC_CLIENT_PRIORITY_KMD_HIGH > GUC_CLIENT_PRIORITY_NORMAL); + + lockdep_assert_held(&ce->guc_active.lock); + + for (i = 0; i < ARRAY_SIZE(ce->guc_prio_count); ++i) { + if (ce->guc_prio_count[i]) { + guc_context_set_prio(guc, ce, i); + break; + } + } +} + +static inline bool new_guc_prio_higher(u8 old_guc_prio, u8 new_guc_prio) +{ + /* Lower value is higher priority */ + return new_guc_prio < old_guc_prio; +} + +static void add_to_context(struct i915_request *rq) +{ + struct intel_context *ce = rq->context; + u8 new_guc_prio = map_i915_prio_to_guc_prio(rq_prio(rq)); + + GEM_BUG_ON(rq->guc_prio == GUC_PRIO_FINI); + + spin_lock(&ce->guc_active.lock); + list_move_tail(&rq->sched.link, &ce->guc_active.requests); + + if (rq->guc_prio == GUC_PRIO_INIT) { + rq->guc_prio = new_guc_prio; + add_context_inflight_prio(ce, rq->guc_prio); + } else if (new_guc_prio_higher(rq->guc_prio, new_guc_prio)) { + sub_context_inflight_prio(ce, rq->guc_prio); + rq->guc_prio = new_guc_prio; + add_context_inflight_prio(ce, rq->guc_prio); + } + update_context_prio(ce); + + spin_unlock(&ce->guc_active.lock); +} + +static void guc_prio_fini(struct i915_request *rq, struct intel_context *ce) +{ + lockdep_assert_held(&ce->guc_active.lock); + + if (rq->guc_prio != GUC_PRIO_INIT && + rq->guc_prio != GUC_PRIO_FINI) { + sub_context_inflight_prio(ce, rq->guc_prio); + update_context_prio(ce); + } + rq->guc_prio = GUC_PRIO_FINI; +} + +static void remove_from_context(struct i915_request *rq) +{ + struct intel_context *ce = rq->context; + + spin_lock_irq(&ce->guc_active.lock); + + list_del_init(&rq->sched.link); + clear_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags); + + /* Prevent further __await_execution() registering a cb, then flush */ + set_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags); + + guc_prio_fini(rq, ce); + + spin_unlock_irq(&ce->guc_active.lock); + + atomic_dec(&ce->guc_id_ref); + i915_request_notify_execute_cb_imm(rq); } static const struct intel_context_ops guc_context_ops = { @@ -454,28 +1976,71 @@ static const struct intel_context_ops guc_context_ops = { .pre_pin = guc_context_pre_pin, .pin = guc_context_pin, - .unpin = lrc_unpin, - .post_unpin = lrc_post_unpin, + .unpin = guc_context_unpin, + .post_unpin = guc_context_post_unpin, + + .ban = guc_context_ban, + + .cancel_request = guc_context_cancel_request, .enter = intel_context_enter_engine, .exit = intel_context_exit_engine, + .sched_disable = guc_context_sched_disable, + .reset = lrc_reset, - .destroy = lrc_destroy, + .destroy = guc_context_destroy, + + .create_virtual = guc_create_virtual, }; -static int guc_request_alloc(struct i915_request *request) +static void __guc_signal_context_fence(struct intel_context *ce) { + struct i915_request *rq; + + lockdep_assert_held(&ce->guc_state.lock); + + if (!list_empty(&ce->guc_state.fences)) + trace_intel_context_fence_release(ce); + + list_for_each_entry(rq, &ce->guc_state.fences, guc_fence_link) + i915_sw_fence_complete(&rq->submit); + + INIT_LIST_HEAD(&ce->guc_state.fences); +} + +static void guc_signal_context_fence(struct intel_context *ce) +{ + unsigned long flags; + + spin_lock_irqsave(&ce->guc_state.lock, flags); + clr_context_wait_for_deregister_to_register(ce); + __guc_signal_context_fence(ce); + spin_unlock_irqrestore(&ce->guc_state.lock, flags); +} + +static bool context_needs_register(struct intel_context *ce, bool new_guc_id) +{ + return (new_guc_id || test_bit(CONTEXT_LRCA_DIRTY, &ce->flags) || + !lrc_desc_registered(ce_to_guc(ce), ce->guc_id)) && + !submission_disabled(ce_to_guc(ce)); +} + +static int guc_request_alloc(struct i915_request *rq) +{ + struct intel_context *ce = rq->context; + struct intel_guc *guc = ce_to_guc(ce); + unsigned long flags; int ret; - GEM_BUG_ON(!intel_context_is_pinned(request->context)); + GEM_BUG_ON(!intel_context_is_pinned(rq->context)); /* * Flush enough space to reduce the likelihood of waiting after * we start building the request - in which case we will just * have to repeat work. */ - request->reserved_space += GUC_REQUEST_SIZE; + rq->reserved_space += GUC_REQUEST_SIZE; /* * Note that after this point, we have committed to using @@ -486,40 +2051,232 @@ static int guc_request_alloc(struct i915_request *request) */ /* Unconditionally invalidate GPU caches and TLBs. */ - ret = request->engine->emit_flush(request, EMIT_INVALIDATE); + ret = rq->engine->emit_flush(rq, EMIT_INVALIDATE); if (ret) return ret; - request->reserved_space -= GUC_REQUEST_SIZE; + rq->reserved_space -= GUC_REQUEST_SIZE; + + /* + * Call pin_guc_id here rather than in the pinning step as with + * dma_resv, contexts can be repeatedly pinned / unpinned trashing the + * guc_ids and creating horrible race conditions. This is especially bad + * when guc_ids are being stolen due to over subscription. By the time + * this function is reached, it is guaranteed that the guc_id will be + * persistent until the generated request is retired. Thus, sealing these + * race conditions. It is still safe to fail here if guc_ids are + * exhausted and return -EAGAIN to the user indicating that they can try + * again in the future. + * + * There is no need for a lock here as the timeline mutex ensures at + * most one context can be executing this code path at once. The + * guc_id_ref is incremented once for every request in flight and + * decremented on each retire. When it is zero, a lock around the + * increment (in pin_guc_id) is needed to seal a race with unpin_guc_id. + */ + if (atomic_add_unless(&ce->guc_id_ref, 1, 0)) + goto out; + + ret = pin_guc_id(guc, ce); /* returns 1 if new guc_id assigned */ + if (unlikely(ret < 0)) + return ret; + if (context_needs_register(ce, !!ret)) { + ret = guc_lrc_desc_pin(ce, true); + if (unlikely(ret)) { /* unwind */ + if (ret == -EPIPE) { + disable_submission(guc); + goto out; /* GPU will be reset */ + } + atomic_dec(&ce->guc_id_ref); + unpin_guc_id(guc, ce); + return ret; + } + } + + clear_bit(CONTEXT_LRCA_DIRTY, &ce->flags); + +out: + /* + * We block all requests on this context if a G2H is pending for a + * schedule disable or context deregistration as the GuC will fail a + * schedule enable or context registration if either G2H is pending + * respectfully. Once a G2H returns, the fence is released that is + * blocking these requests (see guc_signal_context_fence). + * + * We can safely check the below fields outside of the lock as it isn't + * possible for these fields to transition from being clear to set but + * converse is possible, hence the need for the check within the lock. + */ + if (likely(!context_wait_for_deregister_to_register(ce) && + !context_pending_disable(ce))) + return 0; + + spin_lock_irqsave(&ce->guc_state.lock, flags); + if (context_wait_for_deregister_to_register(ce) || + context_pending_disable(ce)) { + i915_sw_fence_await(&rq->submit); + + list_add_tail(&rq->guc_fence_link, &ce->guc_state.fences); + } + spin_unlock_irqrestore(&ce->guc_state.lock, flags); + return 0; } -static inline void queue_request(struct intel_engine_cs *engine, - struct i915_request *rq, - int prio) +static int guc_virtual_context_pre_pin(struct intel_context *ce, + struct i915_gem_ww_ctx *ww, + void **vaddr) { - GEM_BUG_ON(!list_empty(&rq->sched.link)); - list_add_tail(&rq->sched.link, - i915_sched_lookup_priolist(engine, prio)); - set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags); + struct intel_engine_cs *engine = guc_virtual_get_sibling(ce->engine, 0); + + return __guc_context_pre_pin(ce, engine, ww, vaddr); } -static void guc_submit_request(struct i915_request *rq) +static int guc_virtual_context_pin(struct intel_context *ce, void *vaddr) { - struct intel_engine_cs *engine = rq->engine; - unsigned long flags; + struct intel_engine_cs *engine = guc_virtual_get_sibling(ce->engine, 0); - /* Will be called from irq-context when using foreign fences. */ - spin_lock_irqsave(&engine->active.lock, flags); + return __guc_context_pin(ce, engine, vaddr); +} - queue_request(engine, rq, rq_prio(rq)); +static void guc_virtual_context_enter(struct intel_context *ce) +{ + intel_engine_mask_t tmp, mask = ce->engine->mask; + struct intel_engine_cs *engine; - GEM_BUG_ON(RB_EMPTY_ROOT(&engine->execlists.queue.rb_root)); - GEM_BUG_ON(list_empty(&rq->sched.link)); + for_each_engine_masked(engine, ce->engine->gt, mask, tmp) + intel_engine_pm_get(engine); - tasklet_hi_schedule(&engine->execlists.tasklet); + intel_timeline_enter(ce->timeline); +} + +static void guc_virtual_context_exit(struct intel_context *ce) +{ + intel_engine_mask_t tmp, mask = ce->engine->mask; + struct intel_engine_cs *engine; - spin_unlock_irqrestore(&engine->active.lock, flags); + for_each_engine_masked(engine, ce->engine->gt, mask, tmp) + intel_engine_pm_put(engine); + + intel_timeline_exit(ce->timeline); +} + +static int guc_virtual_context_alloc(struct intel_context *ce) +{ + struct intel_engine_cs *engine = guc_virtual_get_sibling(ce->engine, 0); + + return lrc_alloc(ce, engine); +} + +static const struct intel_context_ops virtual_guc_context_ops = { + .alloc = guc_virtual_context_alloc, + + .pre_pin = guc_virtual_context_pre_pin, + .pin = guc_virtual_context_pin, + .unpin = guc_context_unpin, + .post_unpin = guc_context_post_unpin, + + .ban = guc_context_ban, + + .cancel_request = guc_context_cancel_request, + + .enter = guc_virtual_context_enter, + .exit = guc_virtual_context_exit, + + .sched_disable = guc_context_sched_disable, + + .destroy = guc_context_destroy, + + .get_sibling = guc_virtual_get_sibling, +}; + +static bool +guc_irq_enable_breadcrumbs(struct intel_breadcrumbs *b) +{ + struct intel_engine_cs *sibling; + intel_engine_mask_t tmp, mask = b->engine_mask; + bool result = false; + + for_each_engine_masked(sibling, b->irq_engine->gt, mask, tmp) + result |= intel_engine_irq_enable(sibling); + + return result; +} + +static void +guc_irq_disable_breadcrumbs(struct intel_breadcrumbs *b) +{ + struct intel_engine_cs *sibling; + intel_engine_mask_t tmp, mask = b->engine_mask; + + for_each_engine_masked(sibling, b->irq_engine->gt, mask, tmp) + intel_engine_irq_disable(sibling); +} + +static void guc_init_breadcrumbs(struct intel_engine_cs *engine) +{ + int i; + + /* + * In GuC submission mode we do not know which physical engine a request + * will be scheduled on, this creates a problem because the breadcrumb + * interrupt is per physical engine. To work around this we attach + * requests and direct all breadcrumb interrupts to the first instance + * of an engine per class. In addition all breadcrumb interrupts are + * enabled / disabled across an engine class in unison. + */ + for (i = 0; i < MAX_ENGINE_INSTANCE; ++i) { + struct intel_engine_cs *sibling = + engine->gt->engine_class[engine->class][i]; + + if (sibling) { + if (engine->breadcrumbs != sibling->breadcrumbs) { + intel_breadcrumbs_put(engine->breadcrumbs); + engine->breadcrumbs = + intel_breadcrumbs_get(sibling->breadcrumbs); + } + break; + } + } + + if (engine->breadcrumbs) { + engine->breadcrumbs->engine_mask |= engine->mask; + engine->breadcrumbs->irq_enable = guc_irq_enable_breadcrumbs; + engine->breadcrumbs->irq_disable = guc_irq_disable_breadcrumbs; + } +} + +static void guc_bump_inflight_request_prio(struct i915_request *rq, + int prio) +{ + struct intel_context *ce = rq->context; + u8 new_guc_prio = map_i915_prio_to_guc_prio(prio); + + /* Short circuit function */ + if (prio < I915_PRIORITY_NORMAL || + rq->guc_prio == GUC_PRIO_FINI || + (rq->guc_prio != GUC_PRIO_INIT && + !new_guc_prio_higher(rq->guc_prio, new_guc_prio))) + return; + + spin_lock(&ce->guc_active.lock); + if (rq->guc_prio != GUC_PRIO_FINI) { + if (rq->guc_prio != GUC_PRIO_INIT) + sub_context_inflight_prio(ce, rq->guc_prio); + rq->guc_prio = new_guc_prio; + add_context_inflight_prio(ce, rq->guc_prio); + update_context_prio(ce); + } + spin_unlock(&ce->guc_active.lock); +} + +static void guc_retire_inflight_request_prio(struct i915_request *rq) +{ + struct intel_context *ce = rq->context; + + spin_lock(&ce->guc_active.lock); + guc_prio_fini(rq, ce); + spin_unlock(&ce->guc_active.lock); } static void sanitize_hwsp(struct intel_engine_cs *engine) @@ -588,21 +2345,68 @@ static int guc_resume(struct intel_engine_cs *engine) return 0; } +static bool guc_sched_engine_disabled(struct i915_sched_engine *sched_engine) +{ + return !sched_engine->tasklet.callback; +} + static void guc_set_default_submission(struct intel_engine_cs *engine) { engine->submit_request = guc_submit_request; } +static inline void guc_kernel_context_pin(struct intel_guc *guc, + struct intel_context *ce) +{ + if (context_guc_id_invalid(ce)) + pin_guc_id(guc, ce); + guc_lrc_desc_pin(ce, true); +} + +static inline void guc_init_lrc_mapping(struct intel_guc *guc) +{ + struct intel_gt *gt = guc_to_gt(guc); + struct intel_engine_cs *engine; + enum intel_engine_id id; + + /* make sure all descriptors are clean... */ + xa_destroy(&guc->context_lookup); + + /* + * Some contexts might have been pinned before we enabled GuC + * submission, so we need to add them to the GuC bookeeping. + * Also, after a reset the of the GuC we want to make sure that the + * information shared with GuC is properly reset. The kernel LRCs are + * not attached to the gem_context, so they need to be added separately. + * + * Note: we purposefully do not check the return of guc_lrc_desc_pin, + * because that function can only fail if a reset is just starting. This + * is at the end of reset so presumably another reset isn't happening + * and even it did this code would be run again. + */ + + for_each_engine(engine, gt, id) + if (engine->kernel_context) + guc_kernel_context_pin(guc, engine->kernel_context); +} + static void guc_release(struct intel_engine_cs *engine) { engine->sanitize = NULL; /* no longer in control, nothing to sanitize */ - tasklet_kill(&engine->execlists.tasklet); - intel_engine_cleanup_common(engine); lrc_fini_wa_ctx(engine); } +static void virtual_guc_bump_serial(struct intel_engine_cs *engine) +{ + struct intel_engine_cs *e; + intel_engine_mask_t tmp, mask = engine->mask; + + for_each_engine_masked(e, engine->gt, mask, tmp) + e->serial++; +} + static void guc_default_vfuncs(struct intel_engine_cs *engine) { /* Default vfuncs which can be overridden by each engine. */ @@ -611,13 +2415,15 @@ static void guc_default_vfuncs(struct intel_engine_cs *engine) engine->cops = &guc_context_ops; engine->request_alloc = guc_request_alloc; + engine->add_active_request = add_to_context; + engine->remove_active_request = remove_from_context; - engine->schedule = i915_schedule; + engine->sched_engine->schedule = i915_schedule; - engine->reset.prepare = guc_reset_prepare; - engine->reset.rewind = guc_reset_rewind; - engine->reset.cancel = guc_reset_cancel; - engine->reset.finish = guc_reset_finish; + engine->reset.prepare = guc_reset_nop; + engine->reset.rewind = guc_rewind_nop; + engine->reset.cancel = guc_reset_nop; + engine->reset.finish = guc_reset_nop; engine->emit_flush = gen8_emit_flush_xcs; engine->emit_init_breadcrumb = gen8_emit_init_breadcrumb; @@ -629,13 +2435,13 @@ static void guc_default_vfuncs(struct intel_engine_cs *engine) engine->set_default_submission = guc_set_default_submission; engine->flags |= I915_ENGINE_HAS_PREEMPTION; + engine->flags |= I915_ENGINE_HAS_TIMESLICES; /* * TODO: GuC supports timeslicing and semaphores as well, but they're * handled by the firmware so some minor tweaks are required before * enabling. * - * engine->flags |= I915_ENGINE_HAS_TIMESLICES; * engine->flags |= I915_ENGINE_HAS_SEMAPHORES; */ @@ -666,9 +2472,21 @@ static inline void guc_default_irqs(struct intel_engine_cs *engine) intel_engine_set_irq_handler(engine, cs_irq_handler); } +static void guc_sched_engine_destroy(struct kref *kref) +{ + struct i915_sched_engine *sched_engine = + container_of(kref, typeof(*sched_engine), ref); + struct intel_guc *guc = sched_engine->private_data; + + guc->sched_engine = NULL; + tasklet_kill(&sched_engine->tasklet); /* flush the callback */ + kfree(sched_engine); +} + int intel_guc_submission_setup(struct intel_engine_cs *engine) { struct drm_i915_private *i915 = engine->i915; + struct intel_guc *guc = &engine->gt->uc.guc; /* * The setup relies on several assumptions (e.g. irqs always enabled) @@ -676,10 +2494,28 @@ int intel_guc_submission_setup(struct intel_engine_cs *engine) */ GEM_BUG_ON(GRAPHICS_VER(i915) < 11); - tasklet_setup(&engine->execlists.tasklet, guc_submission_tasklet); + if (!guc->sched_engine) { + guc->sched_engine = i915_sched_engine_create(ENGINE_VIRTUAL); + if (!guc->sched_engine) + return -ENOMEM; + + guc->sched_engine->schedule = i915_schedule; + guc->sched_engine->disabled = guc_sched_engine_disabled; + guc->sched_engine->private_data = guc; + guc->sched_engine->destroy = guc_sched_engine_destroy; + guc->sched_engine->bump_inflight_request_prio = + guc_bump_inflight_request_prio; + guc->sched_engine->retire_inflight_request_prio = + guc_retire_inflight_request_prio; + tasklet_setup(&guc->sched_engine->tasklet, + guc_submission_tasklet); + } + i915_sched_engine_put(engine->sched_engine); + engine->sched_engine = i915_sched_engine_get(guc->sched_engine); guc_default_vfuncs(engine); guc_default_irqs(engine); + guc_init_breadcrumbs(engine); if (engine->class == RENDER_CLASS) rcs_submission_override(engine); @@ -695,18 +2531,19 @@ int intel_guc_submission_setup(struct intel_engine_cs *engine) void intel_guc_submission_enable(struct intel_guc *guc) { - guc_stage_desc_init(guc); + guc_init_lrc_mapping(guc); } void intel_guc_submission_disable(struct intel_guc *guc) { - struct intel_gt *gt = guc_to_gt(guc); - - GEM_BUG_ON(gt->awake); /* GT should be parked first */ - /* Note: By the time we're here, GuC may have already been reset */ +} - guc_stage_desc_fini(guc); +static bool __guc_submission_supported(struct intel_guc *guc) +{ + /* GuC submission is unavailable for pre-Gen11 */ + return intel_guc_is_supported(guc) && + GRAPHICS_VER(guc_to_gt(guc)->i915) >= 11; } static bool __guc_submission_selected(struct intel_guc *guc) @@ -721,5 +2558,481 @@ static bool __guc_submission_selected(struct intel_guc *guc) void intel_guc_submission_init_early(struct intel_guc *guc) { + guc->submission_supported = __guc_submission_supported(guc); guc->submission_selected = __guc_submission_selected(guc); } + +static inline struct intel_context * +g2h_context_lookup(struct intel_guc *guc, u32 desc_idx) +{ + struct intel_context *ce; + + if (unlikely(desc_idx >= GUC_MAX_LRC_DESCRIPTORS)) { + drm_err(&guc_to_gt(guc)->i915->drm, + "Invalid desc_idx %u", desc_idx); + return NULL; + } + + ce = __get_context(guc, desc_idx); + if (unlikely(!ce)) { + drm_err(&guc_to_gt(guc)->i915->drm, + "Context is NULL, desc_idx %u", desc_idx); + return NULL; + } + + return ce; +} + +static void decr_outstanding_submission_g2h(struct intel_guc *guc) +{ + if (atomic_dec_and_test(&guc->outstanding_submission_g2h)) + wake_up_all(&guc->ct.wq); +} + +int intel_guc_deregister_done_process_msg(struct intel_guc *guc, + const u32 *msg, + u32 len) +{ + struct intel_context *ce; + u32 desc_idx = msg[0]; + + if (unlikely(len < 1)) { + drm_err(&guc_to_gt(guc)->i915->drm, "Invalid length %u", len); + return -EPROTO; + } + + ce = g2h_context_lookup(guc, desc_idx); + if (unlikely(!ce)) + return -EPROTO; + + trace_intel_context_deregister_done(ce); + + if (context_wait_for_deregister_to_register(ce)) { + struct intel_runtime_pm *runtime_pm = + &ce->engine->gt->i915->runtime_pm; + intel_wakeref_t wakeref; + + /* + * Previous owner of this guc_id has been deregistered, now safe + * register this context. + */ + with_intel_runtime_pm(runtime_pm, wakeref) + register_context(ce, true); + guc_signal_context_fence(ce); + intel_context_put(ce); + } else if (context_destroyed(ce)) { + /* Context has been destroyed */ + release_guc_id(guc, ce); + __guc_context_destroy(ce); + } + + decr_outstanding_submission_g2h(guc); + + return 0; +} + +int intel_guc_sched_done_process_msg(struct intel_guc *guc, + const u32 *msg, + u32 len) +{ + struct intel_context *ce; + unsigned long flags; + u32 desc_idx = msg[0]; + + if (unlikely(len < 2)) { + drm_err(&guc_to_gt(guc)->i915->drm, "Invalid length %u", len); + return -EPROTO; + } + + ce = g2h_context_lookup(guc, desc_idx); + if (unlikely(!ce)) + return -EPROTO; + + if (unlikely(context_destroyed(ce) || + (!context_pending_enable(ce) && + !context_pending_disable(ce)))) { + drm_err(&guc_to_gt(guc)->i915->drm, + "Bad context sched_state 0x%x, 0x%x, desc_idx %u", + atomic_read(&ce->guc_sched_state_no_lock), + ce->guc_state.sched_state, desc_idx); + return -EPROTO; + } + + trace_intel_context_sched_done(ce); + + if (context_pending_enable(ce)) { + clr_context_pending_enable(ce); + } else if (context_pending_disable(ce)) { + bool banned; + + /* + * Unpin must be done before __guc_signal_context_fence, + * otherwise a race exists between the requests getting + * submitted + retired before this unpin completes resulting in + * the pin_count going to zero and the context still being + * enabled. + */ + intel_context_sched_disable_unpin(ce); + + spin_lock_irqsave(&ce->guc_state.lock, flags); + banned = context_banned(ce); + clr_context_banned(ce); + clr_context_pending_disable(ce); + __guc_signal_context_fence(ce); + guc_blocked_fence_complete(ce); + spin_unlock_irqrestore(&ce->guc_state.lock, flags); + + if (banned) { + guc_cancel_context_requests(ce); + intel_engine_signal_breadcrumbs(ce->engine); + } + } + + decr_outstanding_submission_g2h(guc); + intel_context_put(ce); + + return 0; +} + +static void capture_error_state(struct intel_guc *guc, + struct intel_context *ce) +{ + struct intel_gt *gt = guc_to_gt(guc); + struct drm_i915_private *i915 = gt->i915; + struct intel_engine_cs *engine = __context_to_physical_engine(ce); + intel_wakeref_t wakeref; + + intel_engine_set_hung_context(engine, ce); + with_intel_runtime_pm(&i915->runtime_pm, wakeref) + i915_capture_error_state(gt, engine->mask); + atomic_inc(&i915->gpu_error.reset_engine_count[engine->uabi_class]); +} + +static void guc_context_replay(struct intel_context *ce) +{ + struct i915_sched_engine *sched_engine = ce->engine->sched_engine; + + __guc_reset_context(ce, true); + tasklet_hi_schedule(&sched_engine->tasklet); +} + +static void guc_handle_context_reset(struct intel_guc *guc, + struct intel_context *ce) +{ + trace_intel_context_reset(ce); + + if (likely(!intel_context_is_banned(ce))) { + capture_error_state(guc, ce); + guc_context_replay(ce); + } +} + +int intel_guc_context_reset_process_msg(struct intel_guc *guc, + const u32 *msg, u32 len) +{ + struct intel_context *ce; + int desc_idx; + + if (unlikely(len != 1)) { + drm_err(&guc_to_gt(guc)->i915->drm, "Invalid length %u", len); + return -EPROTO; + } + + desc_idx = msg[0]; + ce = g2h_context_lookup(guc, desc_idx); + if (unlikely(!ce)) + return -EPROTO; + + guc_handle_context_reset(guc, ce); + + return 0; +} + +static struct intel_engine_cs * +guc_lookup_engine(struct intel_guc *guc, u8 guc_class, u8 instance) +{ + struct intel_gt *gt = guc_to_gt(guc); + u8 engine_class = guc_class_to_engine_class(guc_class); + + /* Class index is checked in class converter */ + GEM_BUG_ON(instance > MAX_ENGINE_INSTANCE); + + return gt->engine_class[engine_class][instance]; +} + +int intel_guc_engine_failure_process_msg(struct intel_guc *guc, + const u32 *msg, u32 len) +{ + struct intel_engine_cs *engine; + u8 guc_class, instance; + u32 reason; + + if (unlikely(len != 3)) { + drm_err(&guc_to_gt(guc)->i915->drm, "Invalid length %u", len); + return -EPROTO; + } + + guc_class = msg[0]; + instance = msg[1]; + reason = msg[2]; + + engine = guc_lookup_engine(guc, guc_class, instance); + if (unlikely(!engine)) { + drm_err(&guc_to_gt(guc)->i915->drm, + "Invalid engine %d:%d", guc_class, instance); + return -EPROTO; + } + + intel_gt_handle_error(guc_to_gt(guc), engine->mask, + I915_ERROR_CAPTURE, + "GuC failed to reset %s (reason=0x%08x)\n", + engine->name, reason); + + return 0; +} + +void intel_guc_find_hung_context(struct intel_engine_cs *engine) +{ + struct intel_guc *guc = &engine->gt->uc.guc; + struct intel_context *ce; + struct i915_request *rq; + unsigned long index; + + /* Reset called during driver load? GuC not yet initialised! */ + if (unlikely(!guc_submission_initialized(guc))) + return; + + xa_for_each(&guc->context_lookup, index, ce) { + if (!intel_context_is_pinned(ce)) + continue; + + if (intel_engine_is_virtual(ce->engine)) { + if (!(ce->engine->mask & engine->mask)) + continue; + } else { + if (ce->engine != engine) + continue; + } + + list_for_each_entry(rq, &ce->guc_active.requests, sched.link) { + if (i915_test_request_state(rq) != I915_REQUEST_ACTIVE) + continue; + + intel_engine_set_hung_context(engine, ce); + + /* Can only cope with one hang at a time... */ + return; + } + } +} + +void intel_guc_dump_active_requests(struct intel_engine_cs *engine, + struct i915_request *hung_rq, + struct drm_printer *m) +{ + struct intel_guc *guc = &engine->gt->uc.guc; + struct intel_context *ce; + unsigned long index; + unsigned long flags; + + /* Reset called during driver load? GuC not yet initialised! */ + if (unlikely(!guc_submission_initialized(guc))) + return; + + xa_for_each(&guc->context_lookup, index, ce) { + if (!intel_context_is_pinned(ce)) + continue; + + if (intel_engine_is_virtual(ce->engine)) { + if (!(ce->engine->mask & engine->mask)) + continue; + } else { + if (ce->engine != engine) + continue; + } + + spin_lock_irqsave(&ce->guc_active.lock, flags); + intel_engine_dump_active_requests(&ce->guc_active.requests, + hung_rq, m); + spin_unlock_irqrestore(&ce->guc_active.lock, flags); + } +} + +void intel_guc_submission_print_info(struct intel_guc *guc, + struct drm_printer *p) +{ + struct i915_sched_engine *sched_engine = guc->sched_engine; + struct rb_node *rb; + unsigned long flags; + + if (!sched_engine) + return; + + drm_printf(p, "GuC Number Outstanding Submission G2H: %u\n", + atomic_read(&guc->outstanding_submission_g2h)); + drm_printf(p, "GuC tasklet count: %u\n\n", + atomic_read(&sched_engine->tasklet.count)); + + spin_lock_irqsave(&sched_engine->lock, flags); + drm_printf(p, "Requests in GuC submit tasklet:\n"); + for (rb = rb_first_cached(&sched_engine->queue); rb; rb = rb_next(rb)) { + struct i915_priolist *pl = to_priolist(rb); + struct i915_request *rq; + + priolist_for_each_request(rq, pl) + drm_printf(p, "guc_id=%u, seqno=%llu\n", + rq->context->guc_id, + rq->fence.seqno); + } + spin_unlock_irqrestore(&sched_engine->lock, flags); + drm_printf(p, "\n"); +} + +static inline void guc_log_context_priority(struct drm_printer *p, + struct intel_context *ce) +{ + int i; + + drm_printf(p, "\t\tPriority: %d\n", + ce->guc_prio); + drm_printf(p, "\t\tNumber Requests (lower index == higher priority)\n"); + for (i = GUC_CLIENT_PRIORITY_KMD_HIGH; + i < GUC_CLIENT_PRIORITY_NUM; ++i) { + drm_printf(p, "\t\tNumber requests in priority band[%d]: %d\n", + i, ce->guc_prio_count[i]); + } + drm_printf(p, "\n"); +} + +void intel_guc_submission_print_context_info(struct intel_guc *guc, + struct drm_printer *p) +{ + struct intel_context *ce; + unsigned long index; + + xa_for_each(&guc->context_lookup, index, ce) { + drm_printf(p, "GuC lrc descriptor %u:\n", ce->guc_id); + drm_printf(p, "\tHW Context Desc: 0x%08x\n", ce->lrc.lrca); + drm_printf(p, "\t\tLRC Head: Internal %u, Memory %u\n", + ce->ring->head, + ce->lrc_reg_state[CTX_RING_HEAD]); + drm_printf(p, "\t\tLRC Tail: Internal %u, Memory %u\n", + ce->ring->tail, + ce->lrc_reg_state[CTX_RING_TAIL]); + drm_printf(p, "\t\tContext Pin Count: %u\n", + atomic_read(&ce->pin_count)); + drm_printf(p, "\t\tGuC ID Ref Count: %u\n", + atomic_read(&ce->guc_id_ref)); + drm_printf(p, "\t\tSchedule State: 0x%x, 0x%x\n\n", + ce->guc_state.sched_state, + atomic_read(&ce->guc_sched_state_no_lock)); + + guc_log_context_priority(p, ce); + } +} + +static struct intel_context * +guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count) +{ + struct guc_virtual_engine *ve; + struct intel_guc *guc; + unsigned int n; + int err; + + ve = kzalloc(sizeof(*ve), GFP_KERNEL); + if (!ve) + return ERR_PTR(-ENOMEM); + + guc = &siblings[0]->gt->uc.guc; + + ve->base.i915 = siblings[0]->i915; + ve->base.gt = siblings[0]->gt; + ve->base.uncore = siblings[0]->uncore; + ve->base.id = -1; + + ve->base.uabi_class = I915_ENGINE_CLASS_INVALID; + ve->base.instance = I915_ENGINE_CLASS_INVALID_VIRTUAL; + ve->base.uabi_instance = I915_ENGINE_CLASS_INVALID_VIRTUAL; + ve->base.saturated = ALL_ENGINES; + + snprintf(ve->base.name, sizeof(ve->base.name), "virtual"); + + ve->base.sched_engine = i915_sched_engine_get(guc->sched_engine); + + ve->base.cops = &virtual_guc_context_ops; + ve->base.request_alloc = guc_request_alloc; + ve->base.bump_serial = virtual_guc_bump_serial; + + ve->base.submit_request = guc_submit_request; + + ve->base.flags = I915_ENGINE_IS_VIRTUAL; + + intel_context_init(&ve->context, &ve->base); + + for (n = 0; n < count; n++) { + struct intel_engine_cs *sibling = siblings[n]; + + GEM_BUG_ON(!is_power_of_2(sibling->mask)); + if (sibling->mask & ve->base.mask) { + DRM_DEBUG("duplicate %s entry in load balancer\n", + sibling->name); + err = -EINVAL; + goto err_put; + } + + ve->base.mask |= sibling->mask; + + if (n != 0 && ve->base.class != sibling->class) { + DRM_DEBUG("invalid mixing of engine class, sibling %d, already %d\n", + sibling->class, ve->base.class); + err = -EINVAL; + goto err_put; + } else if (n == 0) { + ve->base.class = sibling->class; + ve->base.uabi_class = sibling->uabi_class; + snprintf(ve->base.name, sizeof(ve->base.name), + "v%dx%d", ve->base.class, count); + ve->base.context_size = sibling->context_size; + + ve->base.add_active_request = + sibling->add_active_request; + ve->base.remove_active_request = + sibling->remove_active_request; + ve->base.emit_bb_start = sibling->emit_bb_start; + ve->base.emit_flush = sibling->emit_flush; + ve->base.emit_init_breadcrumb = + sibling->emit_init_breadcrumb; + ve->base.emit_fini_breadcrumb = + sibling->emit_fini_breadcrumb; + ve->base.emit_fini_breadcrumb_dw = + sibling->emit_fini_breadcrumb_dw; + ve->base.breadcrumbs = + intel_breadcrumbs_get(sibling->breadcrumbs); + + ve->base.flags |= sibling->flags; + + ve->base.props.timeslice_duration_ms = + sibling->props.timeslice_duration_ms; + ve->base.props.preempt_timeout_ms = + sibling->props.preempt_timeout_ms; + } + } + + return &ve->context; + +err_put: + intel_context_put(&ve->context); + return ERR_PTR(err); +} + +bool intel_guc_virtual_engine_has_heartbeat(const struct intel_engine_cs *ve) +{ + struct intel_engine_cs *engine; + intel_engine_mask_t tmp, mask = ve->mask; + + for_each_engine_masked(engine, ve->gt, mask, tmp) + if (READ_ONCE(engine->props.heartbeat_interval_ms)) + return true; + + return false; +} diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h index 3f7005018939..c7ef44fa0c36 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h @@ -10,6 +10,7 @@ #include "intel_guc.h" +struct drm_printer; struct intel_engine_cs; void intel_guc_submission_init_early(struct intel_guc *guc); @@ -20,11 +21,24 @@ void intel_guc_submission_fini(struct intel_guc *guc); int intel_guc_preempt_work_create(struct intel_guc *guc); void intel_guc_preempt_work_destroy(struct intel_guc *guc); int intel_guc_submission_setup(struct intel_engine_cs *engine); +void intel_guc_submission_print_info(struct intel_guc *guc, + struct drm_printer *p); +void intel_guc_submission_print_context_info(struct intel_guc *guc, + struct drm_printer *p); +void intel_guc_dump_active_requests(struct intel_engine_cs *engine, + struct i915_request *hung_rq, + struct drm_printer *m); + +bool intel_guc_virtual_engine_has_heartbeat(const struct intel_engine_cs *ve); + +int intel_guc_wait_for_pending_msg(struct intel_guc *guc, + atomic_t *wait_var, + bool interruptible, + long timeout); static inline bool intel_guc_submission_is_supported(struct intel_guc *guc) { - /* XXX: GuC submission is unavailable for now */ - return false; + return guc->submission_supported; } static inline bool intel_guc_submission_is_wanted(struct intel_guc *guc) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c index 6d8b9233214e..b104fb7607eb 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c @@ -34,8 +34,14 @@ static void uc_expand_default_options(struct intel_uc *uc) return; } - /* Default: enable HuC authentication only */ - i915->params.enable_guc = ENABLE_GUC_LOAD_HUC; + /* Intermediate platforms are HuC authentication only */ + if (IS_DG1(i915) || IS_ALDERLAKE_S(i915)) { + i915->params.enable_guc = ENABLE_GUC_LOAD_HUC; + return; + } + + /* Default: enable HuC authentication and GuC submission */ + i915->params.enable_guc = ENABLE_GUC_LOAD_HUC | ENABLE_GUC_SUBMISSION; } /* Reset GuC providing us with fresh state for both GuC and HuC. @@ -69,16 +75,18 @@ static void __confirm_options(struct intel_uc *uc) struct drm_i915_private *i915 = uc_to_gt(uc)->i915; drm_dbg(&i915->drm, - "enable_guc=%d (guc:%s submission:%s huc:%s)\n", + "enable_guc=%d (guc:%s submission:%s huc:%s slpc:%s)\n", i915->params.enable_guc, yesno(intel_uc_wants_guc(uc)), yesno(intel_uc_wants_guc_submission(uc)), - yesno(intel_uc_wants_huc(uc))); + yesno(intel_uc_wants_huc(uc)), + yesno(intel_uc_wants_guc_slpc(uc))); if (i915->params.enable_guc == 0) { GEM_BUG_ON(intel_uc_wants_guc(uc)); GEM_BUG_ON(intel_uc_wants_guc_submission(uc)); GEM_BUG_ON(intel_uc_wants_huc(uc)); + GEM_BUG_ON(intel_uc_wants_guc_slpc(uc)); return; } @@ -120,6 +128,11 @@ void intel_uc_init_early(struct intel_uc *uc) uc->ops = &uc_ops_off; } +void intel_uc_init_late(struct intel_uc *uc) +{ + intel_guc_init_late(&uc->guc); +} + void intel_uc_driver_late_release(struct intel_uc *uc) { } @@ -207,21 +220,6 @@ static void guc_handle_mmio_msg(struct intel_guc *guc) spin_unlock_irq(&guc->irq_lock); } -static void guc_reset_interrupts(struct intel_guc *guc) -{ - guc->interrupts.reset(guc); -} - -static void guc_enable_interrupts(struct intel_guc *guc) -{ - guc->interrupts.enable(guc); -} - -static void guc_disable_interrupts(struct intel_guc *guc) -{ - guc->interrupts.disable(guc); -} - static int guc_enable_communication(struct intel_guc *guc) { struct intel_gt *gt = guc_to_gt(guc); @@ -242,7 +240,7 @@ static int guc_enable_communication(struct intel_guc *guc) guc_get_mmio_msg(guc); guc_handle_mmio_msg(guc); - guc_enable_interrupts(guc); + intel_guc_enable_interrupts(guc); /* check for CT messages received before we enabled interrupts */ spin_lock_irq(>->irq_lock); @@ -265,7 +263,7 @@ static void guc_disable_communication(struct intel_guc *guc) */ guc_clear_mmio_msg(guc); - guc_disable_interrupts(guc); + intel_guc_disable_interrupts(guc); intel_guc_ct_disable(&guc->ct); @@ -323,9 +321,6 @@ static int __uc_init(struct intel_uc *uc) if (i915_inject_probe_failure(uc_to_gt(uc)->i915)) return -ENOMEM; - /* XXX: GuC submission is unavailable for now */ - GEM_BUG_ON(intel_uc_uses_guc_submission(uc)); - ret = intel_guc_init(guc); if (ret) return ret; @@ -463,7 +458,7 @@ static int __uc_init_hw(struct intel_uc *uc) if (ret) goto err_out; - guc_reset_interrupts(guc); + intel_guc_reset_interrupts(guc); /* WaEnableuKernelHeaderValidFix:skl */ /* WaEnableGuCBootHashCheckNotSet:skl,bxt,kbl */ @@ -505,12 +500,21 @@ static int __uc_init_hw(struct intel_uc *uc) if (intel_uc_uses_guc_submission(uc)) intel_guc_submission_enable(guc); + if (intel_uc_uses_guc_slpc(uc)) { + ret = intel_guc_slpc_enable(&guc->slpc); + if (ret) + goto err_submission; + } + drm_info(&i915->drm, "%s firmware %s version %u.%u %s:%s\n", intel_uc_fw_type_repr(INTEL_UC_FW_TYPE_GUC), guc->fw.path, guc->fw.major_ver_found, guc->fw.minor_ver_found, "submission", enableddisabled(intel_uc_uses_guc_submission(uc))); + drm_info(&i915->drm, "GuC SLPC: %s\n", + enableddisabled(intel_uc_uses_guc_slpc(uc))); + if (intel_uc_uses_huc(uc)) { drm_info(&i915->drm, "%s firmware %s version %u.%u %s:%s\n", intel_uc_fw_type_repr(INTEL_UC_FW_TYPE_HUC), @@ -525,6 +529,8 @@ static int __uc_init_hw(struct intel_uc *uc) /* * We've failed to load the firmware :( */ +err_submission: + intel_guc_submission_disable(guc); err_log_capture: __uc_capture_load_err_log(uc); err_out: @@ -565,23 +571,67 @@ void intel_uc_reset_prepare(struct intel_uc *uc) { struct intel_guc *guc = &uc->guc; - if (!intel_guc_is_ready(guc)) + uc->reset_in_progress = true; + + /* Nothing to do if GuC isn't supported */ + if (!intel_uc_supports_guc(uc)) return; + /* Firmware expected to be running when this function is called */ + if (!intel_guc_is_ready(guc)) + goto sanitize; + + if (intel_uc_uses_guc_submission(uc)) + intel_guc_submission_reset_prepare(guc); + +sanitize: __uc_sanitize(uc); } +void intel_uc_reset(struct intel_uc *uc, bool stalled) +{ + struct intel_guc *guc = &uc->guc; + + /* Firmware can not be running when this function is called */ + if (intel_uc_uses_guc_submission(uc)) + intel_guc_submission_reset(guc, stalled); +} + +void intel_uc_reset_finish(struct intel_uc *uc) +{ + struct intel_guc *guc = &uc->guc; + + uc->reset_in_progress = false; + + /* Firmware expected to be running when this function is called */ + if (intel_guc_is_fw_running(guc) && intel_uc_uses_guc_submission(uc)) + intel_guc_submission_reset_finish(guc); +} + +void intel_uc_cancel_requests(struct intel_uc *uc) +{ + struct intel_guc *guc = &uc->guc; + + /* Firmware can not be running when this function is called */ + if (intel_uc_uses_guc_submission(uc)) + intel_guc_submission_cancel_requests(guc); +} + void intel_uc_runtime_suspend(struct intel_uc *uc) { struct intel_guc *guc = &uc->guc; - int err; if (!intel_guc_is_ready(guc)) return; - err = intel_guc_suspend(guc); - if (err) - DRM_DEBUG_DRIVER("Failed to suspend GuC, err=%d", err); + /* + * Wait for any outstanding CTB before tearing down communication /w the + * GuC. + */ +#define OUTSTANDING_CTB_TIMEOUT_PERIOD (HZ / 5) + intel_guc_wait_for_pending_msg(guc, &guc->outstanding_submission_g2h, + false, OUTSTANDING_CTB_TIMEOUT_PERIOD); + GEM_WARN_ON(atomic_read(&guc->outstanding_submission_g2h)); guc_disable_communication(guc); } @@ -590,17 +640,22 @@ void intel_uc_suspend(struct intel_uc *uc) { struct intel_guc *guc = &uc->guc; intel_wakeref_t wakeref; + int err; if (!intel_guc_is_ready(guc)) return; - with_intel_runtime_pm(uc_to_gt(uc)->uncore->rpm, wakeref) - intel_uc_runtime_suspend(uc); + with_intel_runtime_pm(&uc_to_gt(uc)->i915->runtime_pm, wakeref) { + err = intel_guc_suspend(guc); + if (err) + DRM_DEBUG_DRIVER("Failed to suspend GuC, err=%d", err); + } } static int __uc_resume(struct intel_uc *uc, bool enable_communication) { struct intel_guc *guc = &uc->guc; + struct intel_gt *gt = guc_to_gt(guc); int err; if (!intel_guc_is_fw_running(guc)) @@ -612,6 +667,13 @@ static int __uc_resume(struct intel_uc *uc, bool enable_communication) if (enable_communication) guc_enable_communication(guc); + /* If we are only resuming GuC communication but not reloading + * GuC, we need to ensure the ARAT timer interrupt is enabled + * again. In case of GuC reload, it is enabled during SLPC enable. + */ + if (enable_communication && intel_uc_uses_guc_slpc(uc)) + intel_guc_pm_intrmsk_enable(gt); + err = intel_guc_resume(guc); if (err) { DRM_DEBUG_DRIVER("Failed to resume GuC, err=%d", err); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.h b/drivers/gpu/drm/i915/gt/uc/intel_uc.h index 9c954c589edf..866b462821c0 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.h @@ -7,7 +7,9 @@ #define _INTEL_UC_H_ #include "intel_guc.h" +#include "intel_guc_rc.h" #include "intel_guc_submission.h" +#include "intel_guc_slpc.h" #include "intel_huc.h" #include "i915_params.h" @@ -30,13 +32,19 @@ struct intel_uc { /* Snapshot of GuC log from last failed load */ struct drm_i915_gem_object *load_err_log; + + bool reset_in_progress; }; void intel_uc_init_early(struct intel_uc *uc); +void intel_uc_init_late(struct intel_uc *uc); void intel_uc_driver_late_release(struct intel_uc *uc); void intel_uc_driver_remove(struct intel_uc *uc); void intel_uc_init_mmio(struct intel_uc *uc); void intel_uc_reset_prepare(struct intel_uc *uc); +void intel_uc_reset(struct intel_uc *uc, bool stalled); +void intel_uc_reset_finish(struct intel_uc *uc); +void intel_uc_cancel_requests(struct intel_uc *uc); void intel_uc_suspend(struct intel_uc *uc); void intel_uc_runtime_suspend(struct intel_uc *uc); int intel_uc_resume(struct intel_uc *uc); @@ -77,10 +85,17 @@ __uc_state_checker(x, func, uses, used) uc_state_checkers(guc, guc); uc_state_checkers(huc, huc); uc_state_checkers(guc, guc_submission); +uc_state_checkers(guc, guc_slpc); +uc_state_checkers(guc, guc_rc); #undef uc_state_checkers #undef __uc_state_checker +static inline int intel_uc_wait_for_idle(struct intel_uc *uc, long timeout) +{ + return intel_guc_wait_for_idle(&uc->guc, timeout); +} + #define intel_uc_ops_function(_NAME, _OPS, _TYPE, _RET) \ static inline _TYPE intel_uc_##_NAME(struct intel_uc *uc) \ { \ diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c index df647c9a8d56..3a16d08608a5 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c @@ -48,19 +48,20 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw, * firmware as TGL. */ #define INTEL_UC_FIRMWARE_DEFS(fw_def, guc_def, huc_def) \ - fw_def(ALDERLAKE_S, 0, guc_def(tgl, 49, 0, 1), huc_def(tgl, 7, 5, 0)) \ - fw_def(ROCKETLAKE, 0, guc_def(tgl, 49, 0, 1), huc_def(tgl, 7, 5, 0)) \ - fw_def(TIGERLAKE, 0, guc_def(tgl, 49, 0, 1), huc_def(tgl, 7, 5, 0)) \ - fw_def(JASPERLAKE, 0, guc_def(ehl, 49, 0, 1), huc_def(ehl, 9, 0, 0)) \ - fw_def(ELKHARTLAKE, 0, guc_def(ehl, 49, 0, 1), huc_def(ehl, 9, 0, 0)) \ - fw_def(ICELAKE, 0, guc_def(icl, 49, 0, 1), huc_def(icl, 9, 0, 0)) \ - fw_def(COMETLAKE, 5, guc_def(cml, 49, 0, 1), huc_def(cml, 4, 0, 0)) \ - fw_def(COMETLAKE, 0, guc_def(kbl, 49, 0, 1), huc_def(kbl, 4, 0, 0)) \ - fw_def(COFFEELAKE, 0, guc_def(kbl, 49, 0, 1), huc_def(kbl, 4, 0, 0)) \ - fw_def(GEMINILAKE, 0, guc_def(glk, 49, 0, 1), huc_def(glk, 4, 0, 0)) \ - fw_def(KABYLAKE, 0, guc_def(kbl, 49, 0, 1), huc_def(kbl, 4, 0, 0)) \ - fw_def(BROXTON, 0, guc_def(bxt, 49, 0, 1), huc_def(bxt, 2, 0, 0)) \ - fw_def(SKYLAKE, 0, guc_def(skl, 49, 0, 1), huc_def(skl, 2, 0, 0)) + fw_def(ALDERLAKE_P, 0, guc_def(adlp, 62, 0, 3), huc_def(tgl, 7, 9, 3)) \ + fw_def(ALDERLAKE_S, 0, guc_def(tgl, 62, 0, 0), huc_def(tgl, 7, 9, 3)) \ + fw_def(ROCKETLAKE, 0, guc_def(tgl, 62, 0, 0), huc_def(tgl, 7, 9, 3)) \ + fw_def(TIGERLAKE, 0, guc_def(tgl, 62, 0, 0), huc_def(tgl, 7, 9, 3)) \ + fw_def(JASPERLAKE, 0, guc_def(ehl, 62, 0, 0), huc_def(ehl, 9, 0, 0)) \ + fw_def(ELKHARTLAKE, 0, guc_def(ehl, 62, 0, 0), huc_def(ehl, 9, 0, 0)) \ + fw_def(ICELAKE, 0, guc_def(icl, 62, 0, 0), huc_def(icl, 9, 0, 0)) \ + fw_def(COMETLAKE, 5, guc_def(cml, 62, 0, 0), huc_def(cml, 4, 0, 0)) \ + fw_def(COMETLAKE, 0, guc_def(kbl, 62, 0, 0), huc_def(kbl, 4, 0, 0)) \ + fw_def(COFFEELAKE, 0, guc_def(kbl, 62, 0, 0), huc_def(kbl, 4, 0, 0)) \ + fw_def(GEMINILAKE, 0, guc_def(glk, 62, 0, 0), huc_def(glk, 4, 0, 0)) \ + fw_def(KABYLAKE, 0, guc_def(kbl, 62, 0, 0), huc_def(kbl, 4, 0, 0)) \ + fw_def(BROXTON, 0, guc_def(bxt, 62, 0, 0), huc_def(bxt, 2, 0, 0)) \ + fw_def(SKYLAKE, 0, guc_def(skl, 62, 0, 0), huc_def(skl, 2, 0, 0)) #define __MAKE_UC_FW_PATH(prefix_, name_, major_, minor_, patch_) \ "i915/" \ |