diff options
Diffstat (limited to 'include')
50 files changed, 1889 insertions, 60 deletions
diff --git a/include/drm/drm_atomic_helper.h b/include/drm/drm_atomic_helper.h index fea528aacfe2..9aa0a05aa072 100644 --- a/include/drm/drm_atomic_helper.h +++ b/include/drm/drm_atomic_helper.h @@ -96,6 +96,8 @@ void drm_atomic_helper_commit_modeset_enables(struct drm_device *dev, int drm_atomic_helper_prepare_planes(struct drm_device *dev, struct drm_atomic_state *state); +void drm_atomic_helper_unprepare_planes(struct drm_device *dev, + struct drm_atomic_state *state); #define DRM_PLANE_COMMIT_ACTIVE_ONLY BIT(0) #define DRM_PLANE_COMMIT_NO_DISABLE_AFTER_MODESET BIT(1) diff --git a/include/drm/drm_exec.h b/include/drm/drm_exec.h index b5bf0b6da791..f1a66c048721 100644 --- a/include/drm/drm_exec.h +++ b/include/drm/drm_exec.h @@ -135,7 +135,7 @@ static inline bool drm_exec_is_contended(struct drm_exec *exec) return !!exec->contended; } -void drm_exec_init(struct drm_exec *exec, uint32_t flags); +void drm_exec_init(struct drm_exec *exec, uint32_t flags, unsigned nr); void drm_exec_fini(struct drm_exec *exec); bool drm_exec_cleanup(struct drm_exec *exec); int drm_exec_lock_obj(struct drm_exec *exec, struct drm_gem_object *obj); diff --git a/include/drm/drm_gpuvm.h b/include/drm/drm_gpuvm.h index f3fdb810989a..9060f9fae6f1 100644 --- a/include/drm/drm_gpuvm.h +++ b/include/drm/drm_gpuvm.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/* SPDX-License-Identifier: GPL-2.0-only OR MIT */ #ifndef __DRM_GPUVM_H__ #define __DRM_GPUVM_H__ @@ -1018,6 +1018,16 @@ struct drm_gpuva_ops { list_for_each_entry_from_reverse(op, &(ops)->list, entry) /** + * drm_gpuva_for_each_op_reverse - iterator to walk over &drm_gpuva_ops in reverse + * @op: &drm_gpuva_op to assign in each iteration step + * @ops: &drm_gpuva_ops to walk + * + * This iterator walks over all ops within a given list of operations in reverse + */ +#define drm_gpuva_for_each_op_reverse(op, ops) \ + list_for_each_entry_reverse(op, &(ops)->list, entry) + +/** * drm_gpuva_first_op() - returns the first &drm_gpuva_op from &drm_gpuva_ops * @ops: the &drm_gpuva_ops to get the fist &drm_gpuva_op from */ diff --git a/include/drm/drm_mode_object.h b/include/drm/drm_mode_object.h index 912f1e415685..08d7a7f0188f 100644 --- a/include/drm/drm_mode_object.h +++ b/include/drm/drm_mode_object.h @@ -60,7 +60,7 @@ struct drm_mode_object { void (*free_cb)(struct kref *kref); }; -#define DRM_OBJECT_MAX_PROPERTY 24 +#define DRM_OBJECT_MAX_PROPERTY 64 /** * struct drm_object_properties - property tracking for &drm_mode_object */ diff --git a/include/drm/drm_plane.h b/include/drm/drm_plane.h index c6565a6f9324..641fe298052d 100644 --- a/include/drm/drm_plane.h +++ b/include/drm/drm_plane.h @@ -251,6 +251,13 @@ struct drm_plane_state { /** @state: backpointer to global drm_atomic_state */ struct drm_atomic_state *state; + + /** + * @color_mgmt_changed: Color management properties have changed. Used + * by the atomic helpers and drivers to steer the atomic commit control + * flow. + */ + bool color_mgmt_changed : 1; }; static inline struct drm_rect diff --git a/include/drm/drm_prime.h b/include/drm/drm_prime.h index a7abf9f3e697..2a1d01e5b56b 100644 --- a/include/drm/drm_prime.h +++ b/include/drm/drm_prime.h @@ -60,12 +60,19 @@ enum dma_data_direction; struct drm_device; struct drm_gem_object; +struct drm_file; /* core prime functions */ struct dma_buf *drm_gem_dmabuf_export(struct drm_device *dev, struct dma_buf_export_info *exp_info); void drm_gem_dmabuf_release(struct dma_buf *dma_buf); +int drm_gem_prime_fd_to_handle(struct drm_device *dev, + struct drm_file *file_priv, int prime_fd, uint32_t *handle); +int drm_gem_prime_handle_to_fd(struct drm_device *dev, + struct drm_file *file_priv, uint32_t handle, uint32_t flags, + int *prime_fd); + /* helper functions for exporting */ int drm_gem_map_attach(struct dma_buf *dma_buf, struct dma_buf_attachment *attach); diff --git a/include/drm/drm_property.h b/include/drm/drm_property.h index 65bc9710a470..082f29156b3e 100644 --- a/include/drm/drm_property.h +++ b/include/drm/drm_property.h @@ -279,6 +279,12 @@ struct drm_property_blob *drm_property_create_blob(struct drm_device *dev, const void *data); struct drm_property_blob *drm_property_lookup_blob(struct drm_device *dev, uint32_t id); +int drm_property_replace_blob_from_id(struct drm_device *dev, + struct drm_property_blob **blob, + uint64_t blob_id, + ssize_t expected_size, + ssize_t expected_elem_size, + bool *replaced); int drm_property_replace_global_blob(struct drm_device *dev, struct drm_property_blob **replace, size_t length, diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h index 1c9ea6ab3eb9..fcf1849aa47c 100644 --- a/include/drm/i915_pciids.h +++ b/include/drm/i915_pciids.h @@ -738,7 +738,8 @@ INTEL_DG2_G12_IDS(info) #define INTEL_ATS_M150_IDS(info) \ - INTEL_VGA_DEVICE(0x56C0, info) + INTEL_VGA_DEVICE(0x56C0, info), \ + INTEL_VGA_DEVICE(0x56C2, info) #define INTEL_ATS_M75_IDS(info) \ INTEL_VGA_DEVICE(0x56C1, info) diff --git a/include/drm/xe_pciids.h b/include/drm/xe_pciids.h new file mode 100644 index 000000000000..de1a344737bc --- /dev/null +++ b/include/drm/xe_pciids.h @@ -0,0 +1,190 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2022 Intel Corporation + */ + +#ifndef _XE_PCIIDS_H_ +#define _XE_PCIIDS_H_ + +/* + * Lists below can be turned into initializers for a struct pci_device_id + * by defining INTEL_VGA_DEVICE: + * + * #define INTEL_VGA_DEVICE(id, info) { \ + * 0x8086, id, \ + * ~0, ~0, \ + * 0x030000, 0xff0000, \ + * (unsigned long) info } + * + * And then calling like: + * + * XE_TGL_12_GT1_IDS(INTEL_VGA_DEVICE, ## __VA_ARGS__) + * + * To turn them into something else, just provide a different macro passed as + * first argument. + */ + +/* TGL */ +#define XE_TGL_GT1_IDS(MACRO__, ...) \ + MACRO__(0x9A60, ## __VA_ARGS__), \ + MACRO__(0x9A68, ## __VA_ARGS__), \ + MACRO__(0x9A70, ## __VA_ARGS__) + +#define XE_TGL_GT2_IDS(MACRO__, ...) \ + MACRO__(0x9A40, ## __VA_ARGS__), \ + MACRO__(0x9A49, ## __VA_ARGS__), \ + MACRO__(0x9A59, ## __VA_ARGS__), \ + MACRO__(0x9A78, ## __VA_ARGS__), \ + MACRO__(0x9AC0, ## __VA_ARGS__), \ + MACRO__(0x9AC9, ## __VA_ARGS__), \ + MACRO__(0x9AD9, ## __VA_ARGS__), \ + MACRO__(0x9AF8, ## __VA_ARGS__) + +#define XE_TGL_IDS(MACRO__, ...) \ + XE_TGL_GT1_IDS(MACRO__, ## __VA_ARGS__),\ + XE_TGL_GT2_IDS(MACRO__, ## __VA_ARGS__) + +/* RKL */ +#define XE_RKL_IDS(MACRO__, ...) \ + MACRO__(0x4C80, ## __VA_ARGS__), \ + MACRO__(0x4C8A, ## __VA_ARGS__), \ + MACRO__(0x4C8B, ## __VA_ARGS__), \ + MACRO__(0x4C8C, ## __VA_ARGS__), \ + MACRO__(0x4C90, ## __VA_ARGS__), \ + MACRO__(0x4C9A, ## __VA_ARGS__) + +/* DG1 */ +#define XE_DG1_IDS(MACRO__, ...) \ + MACRO__(0x4905, ## __VA_ARGS__), \ + MACRO__(0x4906, ## __VA_ARGS__), \ + MACRO__(0x4907, ## __VA_ARGS__), \ + MACRO__(0x4908, ## __VA_ARGS__), \ + MACRO__(0x4909, ## __VA_ARGS__) + +/* ADL-S */ +#define XE_ADLS_IDS(MACRO__, ...) \ + MACRO__(0x4680, ## __VA_ARGS__), \ + MACRO__(0x4682, ## __VA_ARGS__), \ + MACRO__(0x4688, ## __VA_ARGS__), \ + MACRO__(0x468A, ## __VA_ARGS__), \ + MACRO__(0x468B, ## __VA_ARGS__), \ + MACRO__(0x4690, ## __VA_ARGS__), \ + MACRO__(0x4692, ## __VA_ARGS__), \ + MACRO__(0x4693, ## __VA_ARGS__) + +/* ADL-P */ +#define XE_ADLP_IDS(MACRO__, ...) \ + MACRO__(0x46A0, ## __VA_ARGS__), \ + MACRO__(0x46A1, ## __VA_ARGS__), \ + MACRO__(0x46A2, ## __VA_ARGS__), \ + MACRO__(0x46A3, ## __VA_ARGS__), \ + MACRO__(0x46A6, ## __VA_ARGS__), \ + MACRO__(0x46A8, ## __VA_ARGS__), \ + MACRO__(0x46AA, ## __VA_ARGS__), \ + MACRO__(0x462A, ## __VA_ARGS__), \ + MACRO__(0x4626, ## __VA_ARGS__), \ + MACRO__(0x4628, ## __VA_ARGS__), \ + MACRO__(0x46B0, ## __VA_ARGS__), \ + MACRO__(0x46B1, ## __VA_ARGS__), \ + MACRO__(0x46B2, ## __VA_ARGS__), \ + MACRO__(0x46B3, ## __VA_ARGS__), \ + MACRO__(0x46C0, ## __VA_ARGS__), \ + MACRO__(0x46C1, ## __VA_ARGS__), \ + MACRO__(0x46C2, ## __VA_ARGS__), \ + MACRO__(0x46C3, ## __VA_ARGS__) + +/* ADL-N */ +#define XE_ADLN_IDS(MACRO__, ...) \ + MACRO__(0x46D0, ## __VA_ARGS__), \ + MACRO__(0x46D1, ## __VA_ARGS__), \ + MACRO__(0x46D2, ## __VA_ARGS__) + +/* RPL-S */ +#define XE_RPLS_IDS(MACRO__, ...) \ + MACRO__(0xA780, ## __VA_ARGS__), \ + MACRO__(0xA781, ## __VA_ARGS__), \ + MACRO__(0xA782, ## __VA_ARGS__), \ + MACRO__(0xA783, ## __VA_ARGS__), \ + MACRO__(0xA788, ## __VA_ARGS__), \ + MACRO__(0xA789, ## __VA_ARGS__), \ + MACRO__(0xA78A, ## __VA_ARGS__), \ + MACRO__(0xA78B, ## __VA_ARGS__) + +/* RPL-U */ +#define XE_RPLU_IDS(MACRO__, ...) \ + MACRO__(0xA721, ## __VA_ARGS__), \ + MACRO__(0xA7A1, ## __VA_ARGS__), \ + MACRO__(0xA7A9, ## __VA_ARGS__), \ + MACRO__(0xA7AC, ## __VA_ARGS__), \ + MACRO__(0xA7AD, ## __VA_ARGS__) + +/* RPL-P */ +#define XE_RPLP_IDS(MACRO__, ...) \ + XE_RPLU_IDS(MACRO__, ## __VA_ARGS__), \ + MACRO__(0xA720, ## __VA_ARGS__), \ + MACRO__(0xA7A0, ## __VA_ARGS__), \ + MACRO__(0xA7A8, ## __VA_ARGS__), \ + MACRO__(0xA7AA, ## __VA_ARGS__), \ + MACRO__(0xA7AB, ## __VA_ARGS__) + +/* DG2 */ +#define XE_DG2_G10_IDS(MACRO__, ...) \ + MACRO__(0x5690, ## __VA_ARGS__), \ + MACRO__(0x5691, ## __VA_ARGS__), \ + MACRO__(0x5692, ## __VA_ARGS__), \ + MACRO__(0x56A0, ## __VA_ARGS__), \ + MACRO__(0x56A1, ## __VA_ARGS__), \ + MACRO__(0x56A2, ## __VA_ARGS__) + +#define XE_DG2_G11_IDS(MACRO__, ...) \ + MACRO__(0x5693, ## __VA_ARGS__), \ + MACRO__(0x5694, ## __VA_ARGS__), \ + MACRO__(0x5695, ## __VA_ARGS__), \ + MACRO__(0x56A5, ## __VA_ARGS__), \ + MACRO__(0x56A6, ## __VA_ARGS__), \ + MACRO__(0x56B0, ## __VA_ARGS__), \ + MACRO__(0x56B1, ## __VA_ARGS__), \ + MACRO__(0x56BA, ## __VA_ARGS__), \ + MACRO__(0x56BB, ## __VA_ARGS__), \ + MACRO__(0x56BC, ## __VA_ARGS__), \ + MACRO__(0x56BD, ## __VA_ARGS__) + +#define XE_DG2_G12_IDS(MACRO__, ...) \ + MACRO__(0x5696, ## __VA_ARGS__), \ + MACRO__(0x5697, ## __VA_ARGS__), \ + MACRO__(0x56A3, ## __VA_ARGS__), \ + MACRO__(0x56A4, ## __VA_ARGS__), \ + MACRO__(0x56B2, ## __VA_ARGS__), \ + MACRO__(0x56B3, ## __VA_ARGS__) + +#define XE_DG2_IDS(MACRO__, ...) \ + XE_DG2_G10_IDS(MACRO__, ## __VA_ARGS__),\ + XE_DG2_G11_IDS(MACRO__, ## __VA_ARGS__),\ + XE_DG2_G12_IDS(MACRO__, ## __VA_ARGS__) + +#define XE_ATS_M150_IDS(MACRO__, ...) \ + MACRO__(0x56C0, ## __VA_ARGS__), \ + MACRO__(0x56C2, ## __VA_ARGS__) + +#define XE_ATS_M75_IDS(MACRO__, ...) \ + MACRO__(0x56C1, ## __VA_ARGS__) + +#define XE_ATS_M_IDS(MACRO__, ...) \ + XE_ATS_M150_IDS(MACRO__, ## __VA_ARGS__),\ + XE_ATS_M75_IDS(MACRO__, ## __VA_ARGS__) + +/* MTL / ARL */ +#define XE_MTL_IDS(MACRO__, ...) \ + MACRO__(0x7D40, ## __VA_ARGS__), \ + MACRO__(0x7D45, ## __VA_ARGS__), \ + MACRO__(0x7D55, ## __VA_ARGS__), \ + MACRO__(0x7D60, ## __VA_ARGS__), \ + MACRO__(0x7D67, ## __VA_ARGS__), \ + MACRO__(0x7DD5, ## __VA_ARGS__) + +#define XE_LNL_IDS(MACRO__, ...) \ + MACRO__(0x6420, ## __VA_ARGS__), \ + MACRO__(0x64A0, ## __VA_ARGS__), \ + MACRO__(0x64B0, ## __VA_ARGS__) + +#endif diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 54189e0e5f41..4db54e928b36 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -15,7 +15,6 @@ #include <linux/mod_devicetable.h> #include <linux/property.h> #include <linux/uuid.h> -#include <linux/fw_table.h> struct irq_domain; struct irq_domain_ops; @@ -25,22 +24,13 @@ struct irq_domain_ops; #endif #include <acpi/acpi.h> -#ifdef CONFIG_ACPI_TABLE_LIB -#define EXPORT_SYMBOL_ACPI_LIB(x) EXPORT_SYMBOL_NS_GPL(x, ACPI) -#define __init_or_acpilib -#define __initdata_or_acpilib -#else -#define EXPORT_SYMBOL_ACPI_LIB(x) -#define __init_or_acpilib __init -#define __initdata_or_acpilib __initdata -#endif - #ifdef CONFIG_ACPI #include <linux/list.h> #include <linux/dynamic_debug.h> #include <linux/module.h> #include <linux/mutex.h> +#include <linux/fw_table.h> #include <acpi/acpi_bus.h> #include <acpi/acpi_drivers.h> @@ -48,6 +38,16 @@ struct irq_domain_ops; #include <acpi/acpi_io.h> #include <asm/acpi.h> +#ifdef CONFIG_ACPI_TABLE_LIB +#define EXPORT_SYMBOL_ACPI_LIB(x) EXPORT_SYMBOL_NS_GPL(x, ACPI) +#define __init_or_acpilib +#define __initdata_or_acpilib +#else +#define EXPORT_SYMBOL_ACPI_LIB(x) +#define __init_or_acpilib __init +#define __initdata_or_acpilib __initdata +#endif + static inline acpi_handle acpi_device_handle(struct acpi_device *adev) { return adev ? adev->handle : NULL; diff --git a/include/linux/acpi_amd_wbrf.h b/include/linux/acpi_amd_wbrf.h new file mode 100644 index 000000000000..898f31d536d4 --- /dev/null +++ b/include/linux/acpi_amd_wbrf.h @@ -0,0 +1,91 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Wifi Band Exclusion Interface (AMD ACPI Implementation) + * Copyright (C) 2023 Advanced Micro Devices + */ + +#ifndef _ACPI_AMD_WBRF_H +#define _ACPI_AMD_WBRF_H + +#include <linux/device.h> +#include <linux/notifier.h> + +/* The maximum number of frequency band ranges */ +#define MAX_NUM_OF_WBRF_RANGES 11 + +/* Record actions */ +#define WBRF_RECORD_ADD 0x0 +#define WBRF_RECORD_REMOVE 0x1 + +/** + * struct freq_band_range - Wifi frequency band range definition + * @start: start frequency point (in Hz) + * @end: end frequency point (in Hz) + */ +struct freq_band_range { + u64 start; + u64 end; +}; + +/** + * struct wbrf_ranges_in_out - wbrf ranges info + * @num_of_ranges: total number of band ranges in this struct + * @band_list: array of Wifi band ranges + */ +struct wbrf_ranges_in_out { + u64 num_of_ranges; + struct freq_band_range band_list[MAX_NUM_OF_WBRF_RANGES]; +}; + +/** + * enum wbrf_notifier_actions - wbrf notifier actions index + * @WBRF_CHANGED: there was some frequency band updates. The consumers + * should retrieve the latest active frequency bands. + */ +enum wbrf_notifier_actions { + WBRF_CHANGED, +}; + +#if IS_ENABLED(CONFIG_AMD_WBRF) +bool acpi_amd_wbrf_supported_producer(struct device *dev); +int acpi_amd_wbrf_add_remove(struct device *dev, uint8_t action, struct wbrf_ranges_in_out *in); +bool acpi_amd_wbrf_supported_consumer(struct device *dev); +int amd_wbrf_retrieve_freq_band(struct device *dev, struct wbrf_ranges_in_out *out); +int amd_wbrf_register_notifier(struct notifier_block *nb); +int amd_wbrf_unregister_notifier(struct notifier_block *nb); +#else +static inline +bool acpi_amd_wbrf_supported_consumer(struct device *dev) +{ + return false; +} + +static inline +int acpi_amd_wbrf_add_remove(struct device *dev, uint8_t action, struct wbrf_ranges_in_out *in) +{ + return -ENODEV; +} + +static inline +bool acpi_amd_wbrf_supported_producer(struct device *dev) +{ + return false; +} +static inline +int amd_wbrf_retrieve_freq_band(struct device *dev, struct wbrf_ranges_in_out *out) +{ + return -ENODEV; +} +static inline +int amd_wbrf_register_notifier(struct notifier_block *nb) +{ + return -ENODEV; +} +static inline +int amd_wbrf_unregister_notifier(struct notifier_block *nb) +{ + return -ENODEV; +} +#endif /* CONFIG_AMD_WBRF */ + +#endif /* _ACPI_AMD_WBRF_H */ diff --git a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h index 446394f84606..6ad02ad9c7b4 100644 --- a/include/linux/amd-pstate.h +++ b/include/linux/amd-pstate.h @@ -70,6 +70,10 @@ struct amd_cpudata { u32 nominal_perf; u32 lowest_nonlinear_perf; u32 lowest_perf; + u32 min_limit_perf; + u32 max_limit_perf; + u32 min_limit_freq; + u32 max_limit_freq; u32 max_freq; u32 min_freq; diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index 1abedb5b2e48..3d0fde57ba90 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -209,6 +209,8 @@ bool ffa_device_is_valid(struct ffa_device *ffa_dev) { return false; } #define module_ffa_driver(__ffa_driver) \ module_driver(__ffa_driver, ffa_register, ffa_unregister) +extern struct bus_type ffa_bus_type; + /* FFA transport related */ struct ffa_partition_info { u16 id; diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index d5c5e59ddbd2..b29ebd53417d 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -49,9 +49,10 @@ struct block_device { bool bd_write_holder; bool bd_has_submit_bio; dev_t bd_dev; + struct inode *bd_inode; /* will die */ + atomic_t bd_openers; spinlock_t bd_size_lock; /* for bd_inode->i_size updates */ - struct inode * bd_inode; /* will die */ void * bd_claiming; void * bd_holder; const struct blk_holder_ops *bd_holder_ops; @@ -69,6 +70,7 @@ struct block_device { #ifdef CONFIG_FAIL_MAKE_REQUEST bool bd_make_it_fail; #endif + bool bd_ro_warned; /* * keep this out-of-line as it's both big and not needed in the fast * path diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 6762dac3ef76..cff5bb08820e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -3175,6 +3175,9 @@ enum bpf_text_poke_type { int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *addr1, void *addr2); +void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke, + struct bpf_prog *new, struct bpf_prog *old); + void *bpf_arch_text_copy(void *dst, void *src, size_t len); int bpf_arch_text_invalidate(void *dst, size_t len); diff --git a/include/linux/closure.h b/include/linux/closure.h index de7bb47d8a46..c554c6a08768 100644 --- a/include/linux/closure.h +++ b/include/linux/closure.h @@ -104,7 +104,7 @@ struct closure; struct closure_syncer; -typedef void (closure_fn) (struct closure *); +typedef void (closure_fn) (struct work_struct *); extern struct dentry *bcache_debug; struct closure_waitlist { @@ -254,7 +254,7 @@ static inline void closure_queue(struct closure *cl) INIT_WORK(&cl->work, cl->work.func); BUG_ON(!queue_work(wq, &cl->work)); } else - cl->fn(cl); + cl->fn(&cl->work); } /** @@ -309,6 +309,11 @@ static inline void closure_wake_up(struct closure_waitlist *list) __closure_wake_up(list); } +#define CLOSURE_CALLBACK(name) void name(struct work_struct *ws) +#define closure_type(name, type, member) \ + struct closure *cl = container_of(ws, struct closure, work); \ + type *name = container_of(cl, type, member) + /** * continue_at - jump to another function with barrier * diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index ea2d919fd9c7..c9c65b132c0f 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -171,6 +171,25 @@ ssize_t debugfs_write_file_bool(struct file *file, const char __user *user_buf, ssize_t debugfs_read_file_str(struct file *file, char __user *user_buf, size_t count, loff_t *ppos); +/** + * struct debugfs_cancellation - cancellation data + * @list: internal, for keeping track + * @cancel: callback to call + * @cancel_data: extra data for the callback to call + */ +struct debugfs_cancellation { + struct list_head list; + void (*cancel)(struct dentry *, void *); + void *cancel_data; +}; + +void __acquires(cancellation) +debugfs_enter_cancellation(struct file *file, + struct debugfs_cancellation *cancellation); +void __releases(cancellation) +debugfs_leave_cancellation(struct file *file, + struct debugfs_cancellation *cancellation); + #else #include <linux/err.h> diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index ebe78bd3d121..b3772edca2e6 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -499,6 +499,21 @@ static inline bool dma_fence_is_later(struct dma_fence *f1, } /** + * dma_fence_is_later_or_same - return true if f1 is later or same as f2 + * @f1: the first fence from the same context + * @f2: the second fence from the same context + * + * Returns true if f1 is chronologically later than f2 or the same fence. Both + * fences must be from the same context, since a seqno is not re-used across + * contexts. + */ +static inline bool dma_fence_is_later_or_same(struct dma_fence *f1, + struct dma_fence *f2) +{ + return f1 == f2 || dma_fence_is_later(f1, f2); +} + +/** * dma_fence_later - return the chronologically later fence * @f1: the first fence from the same context * @f2: the second fence from the same context diff --git a/include/linux/fw_table.h b/include/linux/fw_table.h index ff8fa58d5818..ca49947f0a77 100644 --- a/include/linux/fw_table.h +++ b/include/linux/fw_table.h @@ -25,9 +25,6 @@ struct acpi_subtable_proc { int count; }; -#include <linux/acpi.h> -#include <acpi/acpi.h> - union acpi_subtable_headers { struct acpi_subtable_header common; struct acpi_hmat_structure hmat; diff --git a/include/linux/habanalabs/cpucp_if.h b/include/linux/habanalabs/cpucp_if.h index 86ea7c63a0d2..f316c8d0f3fc 100644 --- a/include/linux/habanalabs/cpucp_if.h +++ b/include/linux/habanalabs/cpucp_if.h @@ -659,6 +659,12 @@ enum pq_init_status { * number (nonce) provided by the host to prevent replay attacks. * public key and certificate also provided as part of the FW response. * + * CPUCP_PACKET_INFO_SIGNED_GET - + * Get the device information signed by the Trusted Platform device. + * device info data is also hashed with some unique number (nonce) provided + * by the host to prevent replay attacks. public key and certificate also + * provided as part of the FW response. + * * CPUCP_PACKET_MONITOR_DUMP_GET - * Get monitors registers dump from the CpuCP kernel. * The CPU will put the registers dump in the a buffer allocated by the driver @@ -733,7 +739,7 @@ enum cpucp_packet_id { CPUCP_PACKET_ENGINE_CORE_ASID_SET, /* internal */ CPUCP_PACKET_RESERVED2, /* not used */ CPUCP_PACKET_SEC_ATTEST_GET, /* internal */ - CPUCP_PACKET_RESERVED3, /* not used */ + CPUCP_PACKET_INFO_SIGNED_GET, /* internal */ CPUCP_PACKET_RESERVED4, /* not used */ CPUCP_PACKET_MONITOR_DUMP_GET, /* debugfs */ CPUCP_PACKET_RESERVED5, /* not used */ diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 4cacc0e43b51..be20cff4ba73 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -454,7 +454,7 @@ static inline void memcpy_from_folio(char *to, struct folio *folio, memcpy(to, from, chunk); kunmap_local(from); - from += chunk; + to += chunk; offset += chunk; len -= chunk; } while (len > 0); diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index d3acecc5db4b..236ec7b63c54 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -1268,10 +1268,7 @@ static inline bool __vma_shareable_lock(struct vm_area_struct *vma) return (vma->vm_flags & VM_MAYSHARE) && vma->vm_private_data; } -static inline bool __vma_private_lock(struct vm_area_struct *vma) -{ - return (!(vma->vm_flags & VM_MAYSHARE)) && vma->vm_private_data; -} +bool __vma_private_lock(struct vm_area_struct *vma); /* * Safe version of huge_pte_offset() to check the locks. See comments diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 958771bac9c0..c2ac9e9e7ee9 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2830,12 +2830,14 @@ ieee80211_he_oper_size(const u8 *he_oper_ie) static inline const struct ieee80211_he_6ghz_oper * ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper) { - const u8 *ret = (const void *)&he_oper->optional; + const u8 *ret; u32 he_oper_params; if (!he_oper) return NULL; + ret = (const void *)&he_oper->optional; + he_oper_params = le32_to_cpu(he_oper->he_oper_params); if (!(he_oper_params & IEEE80211_HE_OPERATION_6GHZ_OP_INFO)) diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index d3009d56af0b..805bb635cdf5 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -340,6 +340,9 @@ struct io_ring_ctx { struct list_head io_buffers_cache; + /* deferred free list, protected by ->uring_lock */ + struct hlist_head io_buf_list; + /* Keep this last, we don't need it for the fast path */ struct wait_queue_head poll_wq; struct io_restriction restrictions; diff --git a/include/linux/iommu.h b/include/linux/iommu.h index ec289c1016f5..6291aa7b079b 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -845,6 +845,7 @@ static inline void dev_iommu_priv_set(struct device *dev, void *priv) dev->iommu->priv = priv; } +extern struct mutex iommu_probe_device_lock; int iommu_probe_device(struct device *dev); int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features f); diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index ab1da3142b06..0ff44d6633e3 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -139,7 +139,7 @@ static inline bool kprobe_ftrace(struct kprobe *p) * */ struct kretprobe_holder { - struct kretprobe *rp; + struct kretprobe __rcu *rp; struct objpool_head pool; }; @@ -197,10 +197,8 @@ extern int arch_trampoline_kprobe(struct kprobe *p); #ifdef CONFIG_KRETPROBE_ON_RETHOOK static nokprobe_inline struct kretprobe *get_kretprobe(struct kretprobe_instance *ri) { - RCU_LOCKDEP_WARN(!rcu_read_lock_any_held(), - "Kretprobe is accessed from instance under preemptive context"); - - return (struct kretprobe *)READ_ONCE(ri->node.rethook->data); + /* rethook::data is non-changed field, so that you can access it freely. */ + return (struct kretprobe *)ri->node.rethook->data; } static nokprobe_inline unsigned long get_kretprobe_retaddr(struct kretprobe_instance *ri) { @@ -245,10 +243,7 @@ unsigned long kretprobe_trampoline_handler(struct pt_regs *regs, static nokprobe_inline struct kretprobe *get_kretprobe(struct kretprobe_instance *ri) { - RCU_LOCKDEP_WARN(!rcu_read_lock_any_held(), - "Kretprobe is accessed from instance under preemptive context"); - - return READ_ONCE(ri->rph->rp); + return rcu_dereference_check(ri->rph->rp, rcu_read_lock_any_held()); } static nokprobe_inline unsigned long get_kretprobe_retaddr(struct kretprobe_instance *ri) diff --git a/include/linux/platform_data/x86/asus-wmi.h b/include/linux/platform_data/x86/asus-wmi.h index 63e630276499..ab1c7deff118 100644 --- a/include/linux/platform_data/x86/asus-wmi.h +++ b/include/linux/platform_data/x86/asus-wmi.h @@ -114,6 +114,9 @@ /* Charging mode - 1=Barrel, 2=USB */ #define ASUS_WMI_DEVID_CHARGE_MODE 0x0012006C +/* MCU powersave mode */ +#define ASUS_WMI_DEVID_MCU_POWERSAVE 0x001200E2 + /* epu is connected? 1 == true */ #define ASUS_WMI_DEVID_EGPU_CONNECTED 0x00090018 /* egpu on/off */ diff --git a/include/linux/rethook.h b/include/linux/rethook.h index ce69b2b7bc35..ba60962805f6 100644 --- a/include/linux/rethook.h +++ b/include/linux/rethook.h @@ -28,7 +28,12 @@ typedef void (*rethook_handler_t) (struct rethook_node *, void *, unsigned long, */ struct rethook { void *data; - rethook_handler_t handler; + /* + * To avoid sparse warnings, this uses a raw function pointer with + * __rcu, instead of rethook_handler_t. But this must be same as + * rethook_handler_t. + */ + void (__rcu *handler) (struct rethook_node *, void *, unsigned long, struct pt_regs *); struct objpool_head pool; struct rcu_head rcu; }; diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index c1637515a8a4..c953b8c0d2f4 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -106,6 +106,7 @@ struct sk_psock { struct mutex work_mutex; struct sk_psock_work_state work_state; struct delayed_work work; + struct sock *sk_pair; struct rcu_work rwork; }; diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 0b4658a7eceb..dee5ad6e48c5 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -175,6 +175,7 @@ struct stmmac_fpe_cfg { bool hs_enable; /* FPE handshake enable */ enum stmmac_fpe_state lp_fpe_state; /* Link Partner FPE state */ enum stmmac_fpe_state lo_fpe_state; /* Local station FPE state */ + u32 fpe_csr; /* MAC_FPE_CTRL_STS reg cache */ }; struct stmmac_safety_feature_cfg { diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 68f3d315d2e1..b646b574b060 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -169,7 +169,7 @@ struct tcp_request_sock { #ifdef CONFIG_TCP_AO u8 ao_keyid; u8 ao_rcv_next; - u8 maclen; + bool used_tcp_ao; #endif }; @@ -180,14 +180,10 @@ static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req) static inline bool tcp_rsk_used_ao(const struct request_sock *req) { - /* The real length of MAC is saved in the request socket, - * signing anything with zero-length makes no sense, so here is - * a little hack.. - */ #ifndef CONFIG_TCP_AO return false; #else - return tcp_rsk(req)->maclen != 0; + return tcp_rsk(req)->used_tcp_ao; #endif } diff --git a/include/linux/units.h b/include/linux/units.h index ff1bd6b5f5b3..45110daaf8d3 100644 --- a/include/linux/units.h +++ b/include/linux/units.h @@ -2,6 +2,7 @@ #ifndef _LINUX_UNITS_H #define _LINUX_UNITS_H +#include <linux/bits.h> #include <linux/math.h> /* Metric prefixes in accordance with Système international (d'unités) */ diff --git a/include/linux/usb/r8152.h b/include/linux/usb/r8152.h index 287e9d83fb8b..33a4c146dc19 100644 --- a/include/linux/usb/r8152.h +++ b/include/linux/usb/r8152.h @@ -30,6 +30,7 @@ #define VENDOR_ID_NVIDIA 0x0955 #define VENDOR_ID_TPLINK 0x2357 #define VENDOR_ID_DLINK 0x2001 +#define VENDOR_ID_ASUS 0x0b05 #if IS_REACHABLE(CONFIG_USB_RTL8152) extern u8 rtl8152_get_version(struct usb_interface *intf); diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 454e9295970c..a65b2513f8cd 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -289,16 +289,12 @@ void vfio_combine_iova_ranges(struct rb_root_cached *root, u32 cur_nodes, /* * External user API */ -#if IS_ENABLED(CONFIG_VFIO_GROUP) struct iommu_group *vfio_file_iommu_group(struct file *file); + +#if IS_ENABLED(CONFIG_VFIO_GROUP) bool vfio_file_is_group(struct file *file); bool vfio_file_has_dev(struct file *file, struct vfio_device *device); #else -static inline struct iommu_group *vfio_file_iommu_group(struct file *file) -{ - return NULL; -} - static inline bool vfio_file_is_group(struct file *file) { return false; diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 824c258143a3..49c4640027d8 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -75,6 +75,7 @@ struct unix_sock { }; #define unix_sk(ptr) container_of_const(ptr, struct unix_sock, sk) +#define unix_peer(sk) (unix_sk(sk)->peer) #define peer_wait peer_wq.wait diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index b137a33a1b68..4ecfb06c413d 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -9299,4 +9299,50 @@ bool cfg80211_valid_disable_subchannel_bitmap(u16 *bitmap, */ void cfg80211_links_removed(struct net_device *dev, u16 link_mask); +#ifdef CONFIG_CFG80211_DEBUGFS +/** + * wiphy_locked_debugfs_read - do a locked read in debugfs + * @wiphy: the wiphy to use + * @file: the file being read + * @buf: the buffer to fill and then read from + * @bufsize: size of the buffer + * @userbuf: the user buffer to copy to + * @count: read count + * @ppos: read position + * @handler: the read handler to call (under wiphy lock) + * @data: additional data to pass to the read handler + */ +ssize_t wiphy_locked_debugfs_read(struct wiphy *wiphy, struct file *file, + char *buf, size_t bufsize, + char __user *userbuf, size_t count, + loff_t *ppos, + ssize_t (*handler)(struct wiphy *wiphy, + struct file *file, + char *buf, + size_t bufsize, + void *data), + void *data); + +/** + * wiphy_locked_debugfs_write - do a locked write in debugfs + * @wiphy: the wiphy to use + * @file: the file being written to + * @buf: the buffer to copy the user data to + * @bufsize: size of the buffer + * @userbuf: the user buffer to copy from + * @count: read count + * @handler: the write handler to call (under wiphy lock) + * @data: additional data to pass to the write handler + */ +ssize_t wiphy_locked_debugfs_write(struct wiphy *wiphy, struct file *file, + char *buf, size_t bufsize, + const char __user *userbuf, size_t count, + ssize_t (*handler)(struct wiphy *wiphy, + struct file *file, + char *buf, + size_t count, + void *data), + void *data); +#endif + #endif /* __NET_CFG80211_H */ diff --git a/include/net/genetlink.h b/include/net/genetlink.h index e18a4c0d69ee..c53244f20437 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -12,10 +12,12 @@ * struct genl_multicast_group - generic netlink multicast group * @name: name of the multicast group, names are per-family * @flags: GENL_* flags (%GENL_ADMIN_PERM or %GENL_UNS_ADMIN_PERM) + * @cap_sys_admin: whether %CAP_SYS_ADMIN is required for binding */ struct genl_multicast_group { char name[GENL_NAMSIZ]; u8 flags; + u8 cap_sys_admin:1; }; struct genl_split_ops; diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 07022bb0d44d..0d28172193fa 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -162,7 +162,7 @@ struct neighbour { struct rcu_head rcu; struct net_device *dev; netdevice_tracker dev_tracker; - u8 primary_key[0]; + u8 primary_key[]; } __randomize_layout; struct neigh_ops { diff --git a/include/net/tcp.h b/include/net/tcp.h index d2f0736b76b8..144ba48bb07b 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1514,17 +1514,22 @@ static inline int tcp_full_space(const struct sock *sk) return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf)); } -static inline void tcp_adjust_rcv_ssthresh(struct sock *sk) +static inline void __tcp_adjust_rcv_ssthresh(struct sock *sk, u32 new_ssthresh) { int unused_mem = sk_unused_reserved_mem(sk); struct tcp_sock *tp = tcp_sk(sk); - tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss); + tp->rcv_ssthresh = min(tp->rcv_ssthresh, new_ssthresh); if (unused_mem) tp->rcv_ssthresh = max_t(u32, tp->rcv_ssthresh, tcp_win_from_space(sk, unused_mem)); } +static inline void tcp_adjust_rcv_ssthresh(struct sock *sk) +{ + __tcp_adjust_rcv_ssthresh(sk, 4U * tcp_sk(sk)->advmss); +} + void tcp_cleanup_rbuf(struct sock *sk, int copied); void __tcp_cleanup_rbuf(struct sock *sk, int copied); diff --git a/include/net/tcp_ao.h b/include/net/tcp_ao.h index b56be10838f0..647781080613 100644 --- a/include/net/tcp_ao.h +++ b/include/net/tcp_ao.h @@ -62,11 +62,17 @@ static inline int tcp_ao_maclen(const struct tcp_ao_key *key) return key->maclen; } +/* Use tcp_ao_len_aligned() for TCP header calculations */ static inline int tcp_ao_len(const struct tcp_ao_key *key) { return tcp_ao_maclen(key) + sizeof(struct tcp_ao_hdr); } +static inline int tcp_ao_len_aligned(const struct tcp_ao_key *key) +{ + return round_up(tcp_ao_len(key), 4); +} + static inline unsigned int tcp_ao_digest_size(struct tcp_ao_key *key) { return key->digest_size; diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h index 95896472a82b..565a85044541 100644 --- a/include/rdma/ib_umem.h +++ b/include/rdma/ib_umem.h @@ -77,6 +77,13 @@ static inline void __rdma_umem_block_iter_start(struct ib_block_iter *biter, { __rdma_block_iter_start(biter, umem->sgt_append.sgt.sgl, umem->sgt_append.sgt.nents, pgsz); + biter->__sg_advance = ib_umem_offset(umem) & ~(pgsz - 1); + biter->__sg_numblocks = ib_umem_num_dma_blocks(umem, pgsz); +} + +static inline bool __rdma_umem_block_iter_next(struct ib_block_iter *biter) +{ + return __rdma_block_iter_next(biter) && biter->__sg_numblocks--; } /** @@ -92,7 +99,7 @@ static inline void __rdma_umem_block_iter_start(struct ib_block_iter *biter, */ #define rdma_umem_for_each_dma_block(umem, biter, pgsz) \ for (__rdma_umem_block_iter_start(biter, umem, pgsz); \ - __rdma_block_iter_next(biter);) + __rdma_umem_block_iter_next(biter);) #ifdef CONFIG_INFINIBAND_USER_MEM diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index fb1a2d6b1969..b7b6b58dd348 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2850,6 +2850,7 @@ struct ib_block_iter { /* internal states */ struct scatterlist *__sg; /* sg holding the current aligned block */ dma_addr_t __dma_addr; /* unaligned DMA address of this block */ + size_t __sg_numblocks; /* ib_umem_num_dma_blocks() */ unsigned int __sg_nents; /* number of SG entries */ unsigned int __sg_advance; /* number of bytes to advance in sg in next step */ unsigned int __pg_bit; /* alignment of current block */ diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 10480eb582b2..5ec1e71a09de 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -167,19 +167,25 @@ struct scsi_device { * power state for system suspend/resume (suspend to RAM and * hibernation) operations. */ - bool manage_system_start_stop; + unsigned manage_system_start_stop:1; /* * If true, let the high-level device driver (sd) manage the device * power state for runtime device suspand and resume operations. */ - bool manage_runtime_start_stop; + unsigned manage_runtime_start_stop:1; /* * If true, let the high-level device driver (sd) manage the device * power state for system shutdown (power off) operations. */ - bool manage_shutdown; + unsigned manage_shutdown:1; + + /* + * If set and if the device is runtime suspended, ask the high-level + * device driver (sd) to force a runtime resume of the device. + */ + unsigned force_runtime_start_on_system_start:1; unsigned removable:1; unsigned changed:1; /* Data invalid due to media change */ diff --git a/include/sound/cs35l41.h b/include/sound/cs35l41.h index 043f8ac65dbf..68e053fe7340 100644 --- a/include/sound/cs35l41.h +++ b/include/sound/cs35l41.h @@ -906,6 +906,6 @@ int cs35l41_init_boost(struct device *dev, struct regmap *regmap, bool cs35l41_safe_reset(struct regmap *regmap, enum cs35l41_boost_type b_type); int cs35l41_mdsync_up(struct regmap *regmap); int cs35l41_global_enable(struct device *dev, struct regmap *regmap, enum cs35l41_boost_type b_type, - int enable, bool firmware_running); + int enable, struct cs_dsp *dsp); #endif /* __CS35L41_H */ diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h index aee3d40c96f0..7040e7ea80c7 100644 --- a/include/uapi/drm/drm_mode.h +++ b/include/uapi/drm/drm_mode.h @@ -846,6 +846,14 @@ struct drm_color_ctm { __u64 matrix[9]; }; +struct drm_color_ctm_3x4 { + /* + * Conversion matrix with 3x4 dimensions in S31.32 sign-magnitude + * (not two's complement!) format. + */ + __u64 matrix[12]; +}; + struct drm_color_lut { /* * Values are mapped linearly to 0.0 - 1.0 range, with 0x0 == 0.0 and diff --git a/include/uapi/drm/habanalabs_accel.h b/include/uapi/drm/habanalabs_accel.h index 347c7b62e60e..a512dc4cffd0 100644 --- a/include/uapi/drm/habanalabs_accel.h +++ b/include/uapi/drm/habanalabs_accel.h @@ -846,6 +846,7 @@ enum hl_server_type { #define HL_INFO_HW_ERR_EVENT 36 #define HL_INFO_FW_ERR_EVENT 37 #define HL_INFO_USER_ENGINE_ERR_EVENT 38 +#define HL_INFO_DEV_SIGNED 40 #define HL_INFO_VERSION_MAX_LEN 128 #define HL_INFO_CARD_NAME_MAX_LEN 16 @@ -1256,6 +1257,7 @@ struct hl_info_dev_memalloc_page_sizes { #define SEC_SIGNATURE_BUF_SZ 255 /* (256 - 1) 1 byte used for size */ #define SEC_PUB_DATA_BUF_SZ 510 /* (512 - 2) 2 bytes used for size */ #define SEC_CERTIFICATE_BUF_SZ 2046 /* (2048 - 2) 2 bytes used for size */ +#define SEC_DEV_INFO_BUF_SZ 5120 /* * struct hl_info_sec_attest - attestation report of the boot @@ -1290,6 +1292,32 @@ struct hl_info_sec_attest { __u8 pad0[2]; }; +/* + * struct hl_info_signed - device information signed by a secured device. + * @nonce: number only used once. random number provided by host. this also passed to the quote + * command as a qualifying data. + * @pub_data_len: length of the public data (bytes) + * @certificate_len: length of the certificate (bytes) + * @info_sig_len: length of the attestation signature (bytes) + * @public_data: public key info signed info data (outPublic + name + qualifiedName) + * @certificate: certificate for the signing key + * @info_sig: signature of the info + nonce data. + * @dev_info_len: length of device info (bytes) + * @dev_info: device info as byte array. + */ +struct hl_info_signed { + __u32 nonce; + __u16 pub_data_len; + __u16 certificate_len; + __u8 info_sig_len; + __u8 public_data[SEC_PUB_DATA_BUF_SZ]; + __u8 certificate[SEC_CERTIFICATE_BUF_SZ]; + __u8 info_sig[SEC_SIGNATURE_BUF_SZ]; + __u16 dev_info_len; + __u8 dev_info[SEC_DEV_INFO_BUF_SZ]; + __u8 pad[2]; +}; + /** * struct hl_page_fault_info - page fault information. * @timestamp: timestamp of page fault. diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h index 6c34272a13fd..d8a6b3472760 100644 --- a/include/uapi/drm/msm_drm.h +++ b/include/uapi/drm/msm_drm.h @@ -86,6 +86,7 @@ struct drm_msm_timespec { #define MSM_PARAM_CMDLINE 0x0d /* WO: override for task cmdline */ #define MSM_PARAM_VA_START 0x0e /* RO: start of valid GPU iova range */ #define MSM_PARAM_VA_SIZE 0x0f /* RO: size of valid GPU iova range (bytes) */ +#define MSM_PARAM_HIGHEST_BANK_BIT 0x10 /* RO */ /* For backwards compat. The original support for preemption was based on * a single ring per priority level so # of priority levels equals the # @@ -139,6 +140,8 @@ struct drm_msm_gem_new { #define MSM_INFO_GET_NAME 0x03 /* get debug name, returned by pointer */ #define MSM_INFO_SET_IOVA 0x04 /* set the iova, passed by value */ #define MSM_INFO_GET_FLAGS 0x05 /* get the MSM_BO_x flags */ +#define MSM_INFO_SET_METADATA 0x06 /* set userspace metadata */ +#define MSM_INFO_GET_METADATA 0x07 /* get userspace metadata */ struct drm_msm_gem_info { __u32 handle; /* in */ diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h new file mode 100644 index 000000000000..9fa3ae324731 --- /dev/null +++ b/include/uapi/drm/xe_drm.h @@ -0,0 +1,1347 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2023 Intel Corporation + */ + +#ifndef _UAPI_XE_DRM_H_ +#define _UAPI_XE_DRM_H_ + +#include "drm.h" + +#if defined(__cplusplus) +extern "C" { +#endif + +/* + * Please note that modifications to all structs defined here are + * subject to backwards-compatibility constraints. + * Sections in this file are organized as follows: + * 1. IOCTL definition + * 2. Extension definition and helper structs + * 3. IOCTL's Query structs in the order of the Query's entries. + * 4. The rest of IOCTL structs in the order of IOCTL declaration. + */ + +/** + * DOC: Xe Device Block Diagram + * + * The diagram below represents a high-level simplification of a discrete + * GPU supported by the Xe driver. It shows some device components which + * are necessary to understand this API, as well as how their relations + * to each other. This diagram does not represent real hardware:: + * + * ┌──────────────────────────────────────────────────────────────────┐ + * │ ┌──────────────────────────────────────────────────┐ ┌─────────┐ │ + * │ │ ┌───────────────────────┐ ┌─────┐ │ │ ┌─────┐ │ │ + * │ │ │ VRAM0 ├───┤ ... │ │ │ │VRAM1│ │ │ + * │ │ └───────────┬───────────┘ └─GT1─┘ │ │ └──┬──┘ │ │ + * │ │ ┌──────────────────┴───────────────────────────┐ │ │ ┌──┴──┐ │ │ + * │ │ │ ┌─────────────────────┐ ┌─────────────────┐ │ │ │ │ │ │ │ + * │ │ │ │ ┌──┐ ┌──┐ ┌──┐ ┌──┐ │ │ ┌─────┐ ┌─────┐ │ │ │ │ │ │ │ │ + * │ │ │ │ │EU│ │EU│ │EU│ │EU│ │ │ │RCS0 │ │BCS0 │ │ │ │ │ │ │ │ │ + * │ │ │ │ └──┘ └──┘ └──┘ └──┘ │ │ └─────┘ └─────┘ │ │ │ │ │ │ │ │ + * │ │ │ │ ┌──┐ ┌──┐ ┌──┐ ┌──┐ │ │ ┌─────┐ ┌─────┐ │ │ │ │ │ │ │ │ + * │ │ │ │ │EU│ │EU│ │EU│ │EU│ │ │ │VCS0 │ │VCS1 │ │ │ │ │ │ │ │ │ + * │ │ │ │ └──┘ └──┘ └──┘ └──┘ │ │ └─────┘ └─────┘ │ │ │ │ │ │ │ │ + * │ │ │ │ ┌──┐ ┌──┐ ┌──┐ ┌──┐ │ │ ┌─────┐ ┌─────┐ │ │ │ │ │ │ │ │ + * │ │ │ │ │EU│ │EU│ │EU│ │EU│ │ │ │VECS0│ │VECS1│ │ │ │ │ │ ... │ │ │ + * │ │ │ │ └──┘ └──┘ └──┘ └──┘ │ │ └─────┘ └─────┘ │ │ │ │ │ │ │ │ + * │ │ │ │ ┌──┐ ┌──┐ ┌──┐ ┌──┐ │ │ ┌─────┐ ┌─────┐ │ │ │ │ │ │ │ │ + * │ │ │ │ │EU│ │EU│ │EU│ │EU│ │ │ │CCS0 │ │CCS1 │ │ │ │ │ │ │ │ │ + * │ │ │ │ └──┘ └──┘ └──┘ └──┘ │ │ └─────┘ └─────┘ │ │ │ │ │ │ │ │ + * │ │ │ └─────────DSS─────────┘ │ ┌─────┐ ┌─────┐ │ │ │ │ │ │ │ │ + * │ │ │ │ │CCS2 │ │CCS3 │ │ │ │ │ │ │ │ │ + * │ │ │ ┌─────┐ ┌─────┐ ┌─────┐ │ └─────┘ └─────┘ │ │ │ │ │ │ │ │ + * │ │ │ │ ... │ │ ... │ │ ... │ │ │ │ │ │ │ │ │ │ + * │ │ │ └─DSS─┘ └─DSS─┘ └─DSS─┘ └─────Engines─────┘ │ │ │ │ │ │ │ + * │ │ └───────────────────────────GT0────────────────┘ │ │ └─GT2─┘ │ │ + * │ └────────────────────────────Tile0─────────────────┘ └─ Tile1──┘ │ + * └─────────────────────────────Device0───────┬──────────────────────┘ + * │ + * ───────────────────────┴────────── PCI bus + */ + +/** + * DOC: Xe uAPI Overview + * + * This section aims to describe the Xe's IOCTL entries, its structs, and other + * Xe related uAPI such as uevents and PMU (Platform Monitoring Unit) related + * entries and usage. + * + * List of supported IOCTLs: + * - &DRM_IOCTL_XE_DEVICE_QUERY + * - &DRM_IOCTL_XE_GEM_CREATE + * - &DRM_IOCTL_XE_GEM_MMAP_OFFSET + * - &DRM_IOCTL_XE_VM_CREATE + * - &DRM_IOCTL_XE_VM_DESTROY + * - &DRM_IOCTL_XE_VM_BIND + * - &DRM_IOCTL_XE_EXEC_QUEUE_CREATE + * - &DRM_IOCTL_XE_EXEC_QUEUE_DESTROY + * - &DRM_IOCTL_XE_EXEC_QUEUE_GET_PROPERTY + * - &DRM_IOCTL_XE_EXEC + * - &DRM_IOCTL_XE_WAIT_USER_FENCE + */ + +/* + * xe specific ioctls. + * + * The device specific ioctl range is [DRM_COMMAND_BASE, DRM_COMMAND_END) ie + * [0x40, 0xa0) (a0 is excluded). The numbers below are defined as offset + * against DRM_COMMAND_BASE and should be between [0x0, 0x60). + */ +#define DRM_XE_DEVICE_QUERY 0x00 +#define DRM_XE_GEM_CREATE 0x01 +#define DRM_XE_GEM_MMAP_OFFSET 0x02 +#define DRM_XE_VM_CREATE 0x03 +#define DRM_XE_VM_DESTROY 0x04 +#define DRM_XE_VM_BIND 0x05 +#define DRM_XE_EXEC_QUEUE_CREATE 0x06 +#define DRM_XE_EXEC_QUEUE_DESTROY 0x07 +#define DRM_XE_EXEC_QUEUE_GET_PROPERTY 0x08 +#define DRM_XE_EXEC 0x09 +#define DRM_XE_WAIT_USER_FENCE 0x0a +/* Must be kept compact -- no holes */ + +#define DRM_IOCTL_XE_DEVICE_QUERY DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_DEVICE_QUERY, struct drm_xe_device_query) +#define DRM_IOCTL_XE_GEM_CREATE DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_GEM_CREATE, struct drm_xe_gem_create) +#define DRM_IOCTL_XE_GEM_MMAP_OFFSET DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_GEM_MMAP_OFFSET, struct drm_xe_gem_mmap_offset) +#define DRM_IOCTL_XE_VM_CREATE DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_VM_CREATE, struct drm_xe_vm_create) +#define DRM_IOCTL_XE_VM_DESTROY DRM_IOW(DRM_COMMAND_BASE + DRM_XE_VM_DESTROY, struct drm_xe_vm_destroy) +#define DRM_IOCTL_XE_VM_BIND DRM_IOW(DRM_COMMAND_BASE + DRM_XE_VM_BIND, struct drm_xe_vm_bind) +#define DRM_IOCTL_XE_EXEC_QUEUE_CREATE DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_EXEC_QUEUE_CREATE, struct drm_xe_exec_queue_create) +#define DRM_IOCTL_XE_EXEC_QUEUE_DESTROY DRM_IOW(DRM_COMMAND_BASE + DRM_XE_EXEC_QUEUE_DESTROY, struct drm_xe_exec_queue_destroy) +#define DRM_IOCTL_XE_EXEC_QUEUE_GET_PROPERTY DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_EXEC_QUEUE_GET_PROPERTY, struct drm_xe_exec_queue_get_property) +#define DRM_IOCTL_XE_EXEC DRM_IOW(DRM_COMMAND_BASE + DRM_XE_EXEC, struct drm_xe_exec) +#define DRM_IOCTL_XE_WAIT_USER_FENCE DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_WAIT_USER_FENCE, struct drm_xe_wait_user_fence) + +/** + * DOC: Xe IOCTL Extensions + * + * Before detailing the IOCTLs and its structs, it is important to highlight + * that every IOCTL in Xe is extensible. + * + * Many interfaces need to grow over time. In most cases we can simply + * extend the struct and have userspace pass in more data. Another option, + * as demonstrated by Vulkan's approach to providing extensions for forward + * and backward compatibility, is to use a list of optional structs to + * provide those extra details. + * + * The key advantage to using an extension chain is that it allows us to + * redefine the interface more easily than an ever growing struct of + * increasing complexity, and for large parts of that interface to be + * entirely optional. The downside is more pointer chasing; chasing across + * the __user boundary with pointers encapsulated inside u64. + * + * Example chaining: + * + * .. code-block:: C + * + * struct drm_xe_user_extension ext3 { + * .next_extension = 0, // end + * .name = ..., + * }; + * struct drm_xe_user_extension ext2 { + * .next_extension = (uintptr_t)&ext3, + * .name = ..., + * }; + * struct drm_xe_user_extension ext1 { + * .next_extension = (uintptr_t)&ext2, + * .name = ..., + * }; + * + * Typically the struct drm_xe_user_extension would be embedded in some uAPI + * struct, and in this case we would feed it the head of the chain(i.e ext1), + * which would then apply all of the above extensions. +*/ + +/** + * struct drm_xe_user_extension - Base class for defining a chain of extensions + */ +struct drm_xe_user_extension { + /** + * @next_extension: + * + * Pointer to the next struct drm_xe_user_extension, or zero if the end. + */ + __u64 next_extension; + + /** + * @name: Name of the extension. + * + * Note that the name here is just some integer. + * + * Also note that the name space for this is not global for the whole + * driver, but rather its scope/meaning is limited to the specific piece + * of uAPI which has embedded the struct drm_xe_user_extension. + */ + __u32 name; + + /** + * @pad: MBZ + * + * All undefined bits must be zero. + */ + __u32 pad; +}; + +/** + * struct drm_xe_ext_set_property - Generic set property extension + * + * A generic struct that allows any of the Xe's IOCTL to be extended + * with a set_property operation. + */ +struct drm_xe_ext_set_property { + /** @base: base user extension */ + struct drm_xe_user_extension base; + + /** @property: property to set */ + __u32 property; + + /** @pad: MBZ */ + __u32 pad; + + /** @value: property value */ + __u64 value; + + /** @reserved: Reserved */ + __u64 reserved[2]; +}; + +/** + * struct drm_xe_engine_class_instance - instance of an engine class + * + * It is returned as part of the @drm_xe_engine, but it also is used as + * the input of engine selection for both @drm_xe_exec_queue_create and + * @drm_xe_query_engine_cycles + * + * The @engine_class can be: + * - %DRM_XE_ENGINE_CLASS_RENDER + * - %DRM_XE_ENGINE_CLASS_COPY + * - %DRM_XE_ENGINE_CLASS_VIDEO_DECODE + * - %DRM_XE_ENGINE_CLASS_VIDEO_ENHANCE + * - %DRM_XE_ENGINE_CLASS_COMPUTE + * - %DRM_XE_ENGINE_CLASS_VM_BIND - Kernel only classes (not actual + * hardware engine class). Used for creating ordered queues of VM + * bind operations. + */ +struct drm_xe_engine_class_instance { +#define DRM_XE_ENGINE_CLASS_RENDER 0 +#define DRM_XE_ENGINE_CLASS_COPY 1 +#define DRM_XE_ENGINE_CLASS_VIDEO_DECODE 2 +#define DRM_XE_ENGINE_CLASS_VIDEO_ENHANCE 3 +#define DRM_XE_ENGINE_CLASS_COMPUTE 4 +#define DRM_XE_ENGINE_CLASS_VM_BIND 5 + /** @engine_class: engine class id */ + __u16 engine_class; + /** @engine_instance: engine instance id */ + __u16 engine_instance; + /** @gt_id: Unique ID of this GT within the PCI Device */ + __u16 gt_id; + /** @pad: MBZ */ + __u16 pad; +}; + +/** + * struct drm_xe_engine - describe hardware engine + */ +struct drm_xe_engine { + /** @instance: The @drm_xe_engine_class_instance */ + struct drm_xe_engine_class_instance instance; + + /** @reserved: Reserved */ + __u64 reserved[3]; +}; + +/** + * struct drm_xe_query_engines - describe engines + * + * If a query is made with a struct @drm_xe_device_query where .query + * is equal to %DRM_XE_DEVICE_QUERY_ENGINES, then the reply uses an array of + * struct @drm_xe_query_engines in .data. + */ +struct drm_xe_query_engines { + /** @num_engines: number of engines returned in @engines */ + __u32 num_engines; + /** @pad: MBZ */ + __u32 pad; + /** @engines: The returned engines for this device */ + struct drm_xe_engine engines[]; +}; + +/** + * enum drm_xe_memory_class - Supported memory classes. + */ +enum drm_xe_memory_class { + /** @DRM_XE_MEM_REGION_CLASS_SYSMEM: Represents system memory. */ + DRM_XE_MEM_REGION_CLASS_SYSMEM = 0, + /** + * @DRM_XE_MEM_REGION_CLASS_VRAM: On discrete platforms, this + * represents the memory that is local to the device, which we + * call VRAM. Not valid on integrated platforms. + */ + DRM_XE_MEM_REGION_CLASS_VRAM +}; + +/** + * struct drm_xe_mem_region - Describes some region as known to + * the driver. + */ +struct drm_xe_mem_region { + /** + * @mem_class: The memory class describing this region. + * + * See enum drm_xe_memory_class for supported values. + */ + __u16 mem_class; + /** + * @instance: The unique ID for this region, which serves as the + * index in the placement bitmask used as argument for + * &DRM_IOCTL_XE_GEM_CREATE + */ + __u16 instance; + /** + * @min_page_size: Min page-size in bytes for this region. + * + * When the kernel allocates memory for this region, the + * underlying pages will be at least @min_page_size in size. + * Buffer objects with an allowable placement in this region must be + * created with a size aligned to this value. + * GPU virtual address mappings of (parts of) buffer objects that + * may be placed in this region must also have their GPU virtual + * address and range aligned to this value. + * Affected IOCTLS will return %-EINVAL if alignment restrictions are + * not met. + */ + __u32 min_page_size; + /** + * @total_size: The usable size in bytes for this region. + */ + __u64 total_size; + /** + * @used: Estimate of the memory used in bytes for this region. + * + * Requires CAP_PERFMON or CAP_SYS_ADMIN to get reliable + * accounting. Without this the value here will always equal + * zero. + */ + __u64 used; + /** + * @cpu_visible_size: How much of this region can be CPU + * accessed, in bytes. + * + * This will always be <= @total_size, and the remainder (if + * any) will not be CPU accessible. If the CPU accessible part + * is smaller than @total_size then this is referred to as a + * small BAR system. + * + * On systems without small BAR (full BAR), the probed_size will + * always equal the @total_size, since all of it will be CPU + * accessible. + * + * Note this is only tracked for DRM_XE_MEM_REGION_CLASS_VRAM + * regions (for other types the value here will always equal + * zero). + */ + __u64 cpu_visible_size; + /** + * @cpu_visible_used: Estimate of CPU visible memory used, in + * bytes. + * + * Requires CAP_PERFMON or CAP_SYS_ADMIN to get reliable + * accounting. Without this the value here will always equal + * zero. Note this is only currently tracked for + * DRM_XE_MEM_REGION_CLASS_VRAM regions (for other types the value + * here will always be zero). + */ + __u64 cpu_visible_used; + /** @reserved: Reserved */ + __u64 reserved[6]; +}; + +/** + * struct drm_xe_query_mem_regions - describe memory regions + * + * If a query is made with a struct drm_xe_device_query where .query + * is equal to DRM_XE_DEVICE_QUERY_MEM_REGIONS, then the reply uses + * struct drm_xe_query_mem_regions in .data. + */ +struct drm_xe_query_mem_regions { + /** @num_mem_regions: number of memory regions returned in @mem_regions */ + __u32 num_mem_regions; + /** @pad: MBZ */ + __u32 pad; + /** @mem_regions: The returned memory regions for this device */ + struct drm_xe_mem_region mem_regions[]; +}; + +/** + * struct drm_xe_query_config - describe the device configuration + * + * If a query is made with a struct drm_xe_device_query where .query + * is equal to DRM_XE_DEVICE_QUERY_CONFIG, then the reply uses + * struct drm_xe_query_config in .data. + * + * The index in @info can be: + * - %DRM_XE_QUERY_CONFIG_REV_AND_DEVICE_ID - Device ID (lower 16 bits) + * and the device revision (next 8 bits) + * - %DRM_XE_QUERY_CONFIG_FLAGS - Flags describing the device + * configuration, see list below + * + * - %DRM_XE_QUERY_CONFIG_FLAG_HAS_VRAM - Flag is set if the device + * has usable VRAM + * - %DRM_XE_QUERY_CONFIG_MIN_ALIGNMENT - Minimal memory alignment + * required by this device, typically SZ_4K or SZ_64K + * - %DRM_XE_QUERY_CONFIG_VA_BITS - Maximum bits of a virtual address + * - %DRM_XE_QUERY_CONFIG_MAX_EXEC_QUEUE_PRIORITY - Value of the highest + * available exec queue priority + */ +struct drm_xe_query_config { + /** @num_params: number of parameters returned in info */ + __u32 num_params; + + /** @pad: MBZ */ + __u32 pad; + +#define DRM_XE_QUERY_CONFIG_REV_AND_DEVICE_ID 0 +#define DRM_XE_QUERY_CONFIG_FLAGS 1 + #define DRM_XE_QUERY_CONFIG_FLAG_HAS_VRAM (1 << 0) +#define DRM_XE_QUERY_CONFIG_MIN_ALIGNMENT 2 +#define DRM_XE_QUERY_CONFIG_VA_BITS 3 +#define DRM_XE_QUERY_CONFIG_MAX_EXEC_QUEUE_PRIORITY 4 + /** @info: array of elements containing the config info */ + __u64 info[]; +}; + +/** + * struct drm_xe_gt - describe an individual GT. + * + * To be used with drm_xe_query_gt_list, which will return a list with all the + * existing GT individual descriptions. + * Graphics Technology (GT) is a subset of a GPU/tile that is responsible for + * implementing graphics and/or media operations. + * + * The index in @type can be: + * - %DRM_XE_QUERY_GT_TYPE_MAIN + * - %DRM_XE_QUERY_GT_TYPE_MEDIA + */ +struct drm_xe_gt { +#define DRM_XE_QUERY_GT_TYPE_MAIN 0 +#define DRM_XE_QUERY_GT_TYPE_MEDIA 1 + /** @type: GT type: Main or Media */ + __u16 type; + /** @tile_id: Tile ID where this GT lives (Information only) */ + __u16 tile_id; + /** @gt_id: Unique ID of this GT within the PCI Device */ + __u16 gt_id; + /** @pad: MBZ */ + __u16 pad[3]; + /** @reference_clock: A clock frequency for timestamp */ + __u32 reference_clock; + /** + * @near_mem_regions: Bit mask of instances from + * drm_xe_query_mem_regions that are nearest to the current engines + * of this GT. + * Each index in this mask refers directly to the struct + * drm_xe_query_mem_regions' instance, no assumptions should + * be made about order. The type of each region is described + * by struct drm_xe_query_mem_regions' mem_class. + */ + __u64 near_mem_regions; + /** + * @far_mem_regions: Bit mask of instances from + * drm_xe_query_mem_regions that are far from the engines of this GT. + * In general, they have extra indirections when compared to the + * @near_mem_regions. For a discrete device this could mean system + * memory and memory living in a different tile. + * Each index in this mask refers directly to the struct + * drm_xe_query_mem_regions' instance, no assumptions should + * be made about order. The type of each region is described + * by struct drm_xe_query_mem_regions' mem_class. + */ + __u64 far_mem_regions; + /** @reserved: Reserved */ + __u64 reserved[8]; +}; + +/** + * struct drm_xe_query_gt_list - A list with GT description items. + * + * If a query is made with a struct drm_xe_device_query where .query + * is equal to DRM_XE_DEVICE_QUERY_GT_LIST, then the reply uses struct + * drm_xe_query_gt_list in .data. + */ +struct drm_xe_query_gt_list { + /** @num_gt: number of GT items returned in gt_list */ + __u32 num_gt; + /** @pad: MBZ */ + __u32 pad; + /** @gt_list: The GT list returned for this device */ + struct drm_xe_gt gt_list[]; +}; + +/** + * struct drm_xe_query_topology_mask - describe the topology mask of a GT + * + * This is the hardware topology which reflects the internal physical + * structure of the GPU. + * + * If a query is made with a struct drm_xe_device_query where .query + * is equal to DRM_XE_DEVICE_QUERY_GT_TOPOLOGY, then the reply uses + * struct drm_xe_query_topology_mask in .data. + * + * The @type can be: + * - %DRM_XE_TOPO_DSS_GEOMETRY - To query the mask of Dual Sub Slices + * (DSS) available for geometry operations. For example a query response + * containing the following in mask: + * ``DSS_GEOMETRY ff ff ff ff 00 00 00 00`` + * means 32 DSS are available for geometry. + * - %DRM_XE_TOPO_DSS_COMPUTE - To query the mask of Dual Sub Slices + * (DSS) available for compute operations. For example a query response + * containing the following in mask: + * ``DSS_COMPUTE ff ff ff ff 00 00 00 00`` + * means 32 DSS are available for compute. + * - %DRM_XE_TOPO_EU_PER_DSS - To query the mask of Execution Units (EU) + * available per Dual Sub Slices (DSS). For example a query response + * containing the following in mask: + * ``EU_PER_DSS ff ff 00 00 00 00 00 00`` + * means each DSS has 16 EU. + */ +struct drm_xe_query_topology_mask { + /** @gt_id: GT ID the mask is associated with */ + __u16 gt_id; + +#define DRM_XE_TOPO_DSS_GEOMETRY (1 << 0) +#define DRM_XE_TOPO_DSS_COMPUTE (1 << 1) +#define DRM_XE_TOPO_EU_PER_DSS (1 << 2) + /** @type: type of mask */ + __u16 type; + + /** @num_bytes: number of bytes in requested mask */ + __u32 num_bytes; + + /** @mask: little-endian mask of @num_bytes */ + __u8 mask[]; +}; + +/** + * struct drm_xe_query_engine_cycles - correlate CPU and GPU timestamps + * + * If a query is made with a struct drm_xe_device_query where .query is equal to + * DRM_XE_DEVICE_QUERY_ENGINE_CYCLES, then the reply uses struct drm_xe_query_engine_cycles + * in .data. struct drm_xe_query_engine_cycles is allocated by the user and + * .data points to this allocated structure. + * + * The query returns the engine cycles, which along with GT's @reference_clock, + * can be used to calculate the engine timestamp. In addition the + * query returns a set of cpu timestamps that indicate when the command + * streamer cycle count was captured. + */ +struct drm_xe_query_engine_cycles { + /** + * @eci: This is input by the user and is the engine for which command + * streamer cycles is queried. + */ + struct drm_xe_engine_class_instance eci; + + /** + * @clockid: This is input by the user and is the reference clock id for + * CPU timestamp. For definition, see clock_gettime(2) and + * perf_event_open(2). Supported clock ids are CLOCK_MONOTONIC, + * CLOCK_MONOTONIC_RAW, CLOCK_REALTIME, CLOCK_BOOTTIME, CLOCK_TAI. + */ + __s32 clockid; + + /** @width: Width of the engine cycle counter in bits. */ + __u32 width; + + /** + * @engine_cycles: Engine cycles as read from its register + * at 0x358 offset. + */ + __u64 engine_cycles; + + /** + * @cpu_timestamp: CPU timestamp in ns. The timestamp is captured before + * reading the engine_cycles register using the reference clockid set by the + * user. + */ + __u64 cpu_timestamp; + + /** + * @cpu_delta: Time delta in ns captured around reading the lower dword + * of the engine_cycles register. + */ + __u64 cpu_delta; +}; + +/** + * struct drm_xe_device_query - Input of &DRM_IOCTL_XE_DEVICE_QUERY - main + * structure to query device information + * + * The user selects the type of data to query among DRM_XE_DEVICE_QUERY_* + * and sets the value in the query member. This determines the type of + * the structure provided by the driver in data, among struct drm_xe_query_*. + * + * The @query can be: + * - %DRM_XE_DEVICE_QUERY_ENGINES + * - %DRM_XE_DEVICE_QUERY_MEM_REGIONS + * - %DRM_XE_DEVICE_QUERY_CONFIG + * - %DRM_XE_DEVICE_QUERY_GT_LIST + * - %DRM_XE_DEVICE_QUERY_HWCONFIG - Query type to retrieve the hardware + * configuration of the device such as information on slices, memory, + * caches, and so on. It is provided as a table of key / value + * attributes. + * - %DRM_XE_DEVICE_QUERY_GT_TOPOLOGY + * - %DRM_XE_DEVICE_QUERY_ENGINE_CYCLES + * + * If size is set to 0, the driver fills it with the required size for + * the requested type of data to query. If size is equal to the required + * size, the queried information is copied into data. If size is set to + * a value different from 0 and different from the required size, the + * IOCTL call returns -EINVAL. + * + * For example the following code snippet allows retrieving and printing + * information about the device engines with DRM_XE_DEVICE_QUERY_ENGINES: + * + * .. code-block:: C + * + * struct drm_xe_query_engines *engines; + * struct drm_xe_device_query query = { + * .extensions = 0, + * .query = DRM_XE_DEVICE_QUERY_ENGINES, + * .size = 0, + * .data = 0, + * }; + * ioctl(fd, DRM_IOCTL_XE_DEVICE_QUERY, &query); + * engines = malloc(query.size); + * query.data = (uintptr_t)engines; + * ioctl(fd, DRM_IOCTL_XE_DEVICE_QUERY, &query); + * for (int i = 0; i < engines->num_engines; i++) { + * printf("Engine %d: %s\n", i, + * engines->engines[i].instance.engine_class == + * DRM_XE_ENGINE_CLASS_RENDER ? "RENDER": + * engines->engines[i].instance.engine_class == + * DRM_XE_ENGINE_CLASS_COPY ? "COPY": + * engines->engines[i].instance.engine_class == + * DRM_XE_ENGINE_CLASS_VIDEO_DECODE ? "VIDEO_DECODE": + * engines->engines[i].instance.engine_class == + * DRM_XE_ENGINE_CLASS_VIDEO_ENHANCE ? "VIDEO_ENHANCE": + * engines->engines[i].instance.engine_class == + * DRM_XE_ENGINE_CLASS_COMPUTE ? "COMPUTE": + * "UNKNOWN"); + * } + * free(engines); + */ +struct drm_xe_device_query { + /** @extensions: Pointer to the first extension struct, if any */ + __u64 extensions; + +#define DRM_XE_DEVICE_QUERY_ENGINES 0 +#define DRM_XE_DEVICE_QUERY_MEM_REGIONS 1 +#define DRM_XE_DEVICE_QUERY_CONFIG 2 +#define DRM_XE_DEVICE_QUERY_GT_LIST 3 +#define DRM_XE_DEVICE_QUERY_HWCONFIG 4 +#define DRM_XE_DEVICE_QUERY_GT_TOPOLOGY 5 +#define DRM_XE_DEVICE_QUERY_ENGINE_CYCLES 6 + /** @query: The type of data to query */ + __u32 query; + + /** @size: Size of the queried data */ + __u32 size; + + /** @data: Queried data is placed here */ + __u64 data; + + /** @reserved: Reserved */ + __u64 reserved[2]; +}; + +/** + * struct drm_xe_gem_create - Input of &DRM_IOCTL_XE_GEM_CREATE - A structure for + * gem creation + * + * The @flags can be: + * - %DRM_XE_GEM_CREATE_FLAG_DEFER_BACKING + * - %DRM_XE_GEM_CREATE_FLAG_SCANOUT + * - %DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM - When using VRAM as a + * possible placement, ensure that the corresponding VRAM allocation + * will always use the CPU accessible part of VRAM. This is important + * for small-bar systems (on full-bar systems this gets turned into a + * noop). + * Note1: System memory can be used as an extra placement if the kernel + * should spill the allocation to system memory, if space can't be made + * available in the CPU accessible part of VRAM (giving the same + * behaviour as the i915 interface, see + * I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS). + * Note2: For clear-color CCS surfaces the kernel needs to read the + * clear-color value stored in the buffer, and on discrete platforms we + * need to use VRAM for display surfaces, therefore the kernel requires + * setting this flag for such objects, otherwise an error is thrown on + * small-bar systems. + * + * @cpu_caching supports the following values: + * - %DRM_XE_GEM_CPU_CACHING_WB - Allocate the pages with write-back + * caching. On iGPU this can't be used for scanout surfaces. Currently + * not allowed for objects placed in VRAM. + * - %DRM_XE_GEM_CPU_CACHING_WC - Allocate the pages as write-combined. This + * is uncached. Scanout surfaces should likely use this. All objects + * that can be placed in VRAM must use this. + */ +struct drm_xe_gem_create { + /** @extensions: Pointer to the first extension struct, if any */ + __u64 extensions; + + /** + * @size: Size of the object to be created, must match region + * (system or vram) minimum alignment (&min_page_size). + */ + __u64 size; + + /** + * @placement: A mask of memory instances of where BO can be placed. + * Each index in this mask refers directly to the struct + * drm_xe_query_mem_regions' instance, no assumptions should + * be made about order. The type of each region is described + * by struct drm_xe_query_mem_regions' mem_class. + */ + __u32 placement; + +#define DRM_XE_GEM_CREATE_FLAG_DEFER_BACKING (1 << 0) +#define DRM_XE_GEM_CREATE_FLAG_SCANOUT (1 << 1) +#define DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM (1 << 2) + /** + * @flags: Flags, currently a mask of memory instances of where BO can + * be placed + */ + __u32 flags; + + /** + * @vm_id: Attached VM, if any + * + * If a VM is specified, this BO must: + * + * 1. Only ever be bound to that VM. + * 2. Cannot be exported as a PRIME fd. + */ + __u32 vm_id; + + /** + * @handle: Returned handle for the object. + * + * Object handles are nonzero. + */ + __u32 handle; + +#define DRM_XE_GEM_CPU_CACHING_WB 1 +#define DRM_XE_GEM_CPU_CACHING_WC 2 + /** + * @cpu_caching: The CPU caching mode to select for this object. If + * mmaping the object the mode selected here will also be used. + */ + __u16 cpu_caching; + /** @pad: MBZ */ + __u16 pad[3]; + + /** @reserved: Reserved */ + __u64 reserved[2]; +}; + +/** + * struct drm_xe_gem_mmap_offset - Input of &DRM_IOCTL_XE_GEM_MMAP_OFFSET + */ +struct drm_xe_gem_mmap_offset { + /** @extensions: Pointer to the first extension struct, if any */ + __u64 extensions; + + /** @handle: Handle for the object being mapped. */ + __u32 handle; + + /** @flags: Must be zero */ + __u32 flags; + + /** @offset: The fake offset to use for subsequent mmap call */ + __u64 offset; + + /** @reserved: Reserved */ + __u64 reserved[2]; +}; + +/** + * struct drm_xe_vm_create - Input of &DRM_IOCTL_XE_VM_CREATE + * + * The @flags can be: + * - %DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE + * - %DRM_XE_VM_CREATE_FLAG_LR_MODE - An LR, or Long Running VM accepts + * exec submissions to its exec_queues that don't have an upper time + * limit on the job execution time. But exec submissions to these + * don't allow any of the flags DRM_XE_SYNC_FLAG_SYNCOBJ, + * DRM_XE_SYNC_FLAG_TIMELINE_SYNCOBJ, DRM_XE_SYNC_FLAG_DMA_BUF, + * used as out-syncobjs, that is, together with DRM_XE_SYNC_FLAG_SIGNAL. + * LR VMs can be created in recoverable page-fault mode using + * DRM_XE_VM_CREATE_FLAG_FAULT_MODE, if the device supports it. + * If that flag is omitted, the UMD can not rely on the slightly + * different per-VM overcommit semantics that are enabled by + * DRM_XE_VM_CREATE_FLAG_FAULT_MODE (see below), but KMD may + * still enable recoverable pagefaults if supported by the device. + * - %DRM_XE_VM_CREATE_FLAG_FAULT_MODE - Requires also + * DRM_XE_VM_CREATE_FLAG_LR_MODE. It allows memory to be allocated on + * demand when accessed, and also allows per-VM overcommit of memory. + * The xe driver internally uses recoverable pagefaults to implement + * this. + */ +struct drm_xe_vm_create { + /** @extensions: Pointer to the first extension struct, if any */ + __u64 extensions; + +#define DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE (1 << 0) +#define DRM_XE_VM_CREATE_FLAG_LR_MODE (1 << 1) +#define DRM_XE_VM_CREATE_FLAG_FAULT_MODE (1 << 2) + /** @flags: Flags */ + __u32 flags; + + /** @vm_id: Returned VM ID */ + __u32 vm_id; + + /** @reserved: Reserved */ + __u64 reserved[2]; +}; + +/** + * struct drm_xe_vm_destroy - Input of &DRM_IOCTL_XE_VM_DESTROY + */ +struct drm_xe_vm_destroy { + /** @vm_id: VM ID */ + __u32 vm_id; + + /** @pad: MBZ */ + __u32 pad; + + /** @reserved: Reserved */ + __u64 reserved[2]; +}; + +/** + * struct drm_xe_vm_bind_op - run bind operations + * + * The @op can be: + * - %DRM_XE_VM_BIND_OP_MAP + * - %DRM_XE_VM_BIND_OP_UNMAP + * - %DRM_XE_VM_BIND_OP_MAP_USERPTR + * - %DRM_XE_VM_BIND_OP_UNMAP_ALL + * - %DRM_XE_VM_BIND_OP_PREFETCH + * + * and the @flags can be: + * - %DRM_XE_VM_BIND_FLAG_READONLY + * - %DRM_XE_VM_BIND_FLAG_ASYNC + * - %DRM_XE_VM_BIND_FLAG_IMMEDIATE - Valid on a faulting VM only, do the + * MAP operation immediately rather than deferring the MAP to the page + * fault handler. + * - %DRM_XE_VM_BIND_FLAG_NULL - When the NULL flag is set, the page + * tables are setup with a special bit which indicates writes are + * dropped and all reads return zero. In the future, the NULL flags + * will only be valid for DRM_XE_VM_BIND_OP_MAP operations, the BO + * handle MBZ, and the BO offset MBZ. This flag is intended to + * implement VK sparse bindings. + */ +struct drm_xe_vm_bind_op { + /** @extensions: Pointer to the first extension struct, if any */ + __u64 extensions; + + /** + * @obj: GEM object to operate on, MBZ for MAP_USERPTR, MBZ for UNMAP + */ + __u32 obj; + + /** + * @pat_index: The platform defined @pat_index to use for this mapping. + * The index basically maps to some predefined memory attributes, + * including things like caching, coherency, compression etc. The exact + * meaning of the pat_index is platform specific and defined in the + * Bspec and PRMs. When the KMD sets up the binding the index here is + * encoded into the ppGTT PTE. + * + * For coherency the @pat_index needs to be at least 1way coherent when + * drm_xe_gem_create.cpu_caching is DRM_XE_GEM_CPU_CACHING_WB. The KMD + * will extract the coherency mode from the @pat_index and reject if + * there is a mismatch (see note below for pre-MTL platforms). + * + * Note: On pre-MTL platforms there is only a caching mode and no + * explicit coherency mode, but on such hardware there is always a + * shared-LLC (or is dgpu) so all GT memory accesses are coherent with + * CPU caches even with the caching mode set as uncached. It's only the + * display engine that is incoherent (on dgpu it must be in VRAM which + * is always mapped as WC on the CPU). However to keep the uapi somewhat + * consistent with newer platforms the KMD groups the different cache + * levels into the following coherency buckets on all pre-MTL platforms: + * + * ppGTT UC -> COH_NONE + * ppGTT WC -> COH_NONE + * ppGTT WT -> COH_NONE + * ppGTT WB -> COH_AT_LEAST_1WAY + * + * In practice UC/WC/WT should only ever used for scanout surfaces on + * such platforms (or perhaps in general for dma-buf if shared with + * another device) since it is only the display engine that is actually + * incoherent. Everything else should typically use WB given that we + * have a shared-LLC. On MTL+ this completely changes and the HW + * defines the coherency mode as part of the @pat_index, where + * incoherent GT access is possible. + * + * Note: For userptr and externally imported dma-buf the kernel expects + * either 1WAY or 2WAY for the @pat_index. + * + * For DRM_XE_VM_BIND_FLAG_NULL bindings there are no KMD restrictions + * on the @pat_index. For such mappings there is no actual memory being + * mapped (the address in the PTE is invalid), so the various PAT memory + * attributes likely do not apply. Simply leaving as zero is one + * option (still a valid pat_index). + */ + __u16 pat_index; + + /** @pad: MBZ */ + __u16 pad; + + union { + /** + * @obj_offset: Offset into the object, MBZ for CLEAR_RANGE, + * ignored for unbind + */ + __u64 obj_offset; + + /** @userptr: user pointer to bind on */ + __u64 userptr; + }; + + /** + * @range: Number of bytes from the object to bind to addr, MBZ for UNMAP_ALL + */ + __u64 range; + + /** @addr: Address to operate on, MBZ for UNMAP_ALL */ + __u64 addr; + +#define DRM_XE_VM_BIND_OP_MAP 0x0 +#define DRM_XE_VM_BIND_OP_UNMAP 0x1 +#define DRM_XE_VM_BIND_OP_MAP_USERPTR 0x2 +#define DRM_XE_VM_BIND_OP_UNMAP_ALL 0x3 +#define DRM_XE_VM_BIND_OP_PREFETCH 0x4 + /** @op: Bind operation to perform */ + __u32 op; + +#define DRM_XE_VM_BIND_FLAG_READONLY (1 << 0) +#define DRM_XE_VM_BIND_FLAG_IMMEDIATE (1 << 1) +#define DRM_XE_VM_BIND_FLAG_NULL (1 << 2) + /** @flags: Bind flags */ + __u32 flags; + + /** + * @prefetch_mem_region_instance: Memory region to prefetch VMA to. + * It is a region instance, not a mask. + * To be used only with %DRM_XE_VM_BIND_OP_PREFETCH operation. + */ + __u32 prefetch_mem_region_instance; + + /** @pad2: MBZ */ + __u32 pad2; + + /** @reserved: Reserved */ + __u64 reserved[3]; +}; + +/** + * struct drm_xe_vm_bind - Input of &DRM_IOCTL_XE_VM_BIND + * + * Below is an example of a minimal use of @drm_xe_vm_bind to + * asynchronously bind the buffer `data` at address `BIND_ADDRESS` to + * illustrate `userptr`. It can be synchronized by using the example + * provided for @drm_xe_sync. + * + * .. code-block:: C + * + * data = aligned_alloc(ALIGNMENT, BO_SIZE); + * struct drm_xe_vm_bind bind = { + * .vm_id = vm, + * .num_binds = 1, + * .bind.obj = 0, + * .bind.obj_offset = to_user_pointer(data), + * .bind.range = BO_SIZE, + * .bind.addr = BIND_ADDRESS, + * .bind.op = DRM_XE_VM_BIND_OP_MAP_USERPTR, + * .bind.flags = 0, + * .num_syncs = 1, + * .syncs = &sync, + * .exec_queue_id = 0, + * }; + * ioctl(fd, DRM_IOCTL_XE_VM_BIND, &bind); + * + */ +struct drm_xe_vm_bind { + /** @extensions: Pointer to the first extension struct, if any */ + __u64 extensions; + + /** @vm_id: The ID of the VM to bind to */ + __u32 vm_id; + + /** + * @exec_queue_id: exec_queue_id, must be of class DRM_XE_ENGINE_CLASS_VM_BIND + * and exec queue must have same vm_id. If zero, the default VM bind engine + * is used. + */ + __u32 exec_queue_id; + + /** @pad: MBZ */ + __u32 pad; + + /** @num_binds: number of binds in this IOCTL */ + __u32 num_binds; + + union { + /** @bind: used if num_binds == 1 */ + struct drm_xe_vm_bind_op bind; + + /** + * @vector_of_binds: userptr to array of struct + * drm_xe_vm_bind_op if num_binds > 1 + */ + __u64 vector_of_binds; + }; + + /** @pad2: MBZ */ + __u32 pad2; + + /** @num_syncs: amount of syncs to wait on */ + __u32 num_syncs; + + /** @syncs: pointer to struct drm_xe_sync array */ + __u64 syncs; + + /** @reserved: Reserved */ + __u64 reserved[2]; +}; + +/** + * struct drm_xe_exec_queue_create - Input of &DRM_IOCTL_XE_EXEC_QUEUE_CREATE + * + * The example below shows how to use @drm_xe_exec_queue_create to create + * a simple exec_queue (no parallel submission) of class + * &DRM_XE_ENGINE_CLASS_RENDER. + * + * .. code-block:: C + * + * struct drm_xe_engine_class_instance instance = { + * .engine_class = DRM_XE_ENGINE_CLASS_RENDER, + * }; + * struct drm_xe_exec_queue_create exec_queue_create = { + * .extensions = 0, + * .vm_id = vm, + * .num_bb_per_exec = 1, + * .num_eng_per_bb = 1, + * .instances = to_user_pointer(&instance), + * }; + * ioctl(fd, DRM_IOCTL_XE_EXEC_QUEUE_CREATE, &exec_queue_create); + * + */ +struct drm_xe_exec_queue_create { +#define DRM_XE_EXEC_QUEUE_EXTENSION_SET_PROPERTY 0 +#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_PRIORITY 0 +#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_TIMESLICE 1 +#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_PREEMPTION_TIMEOUT 2 +#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_PERSISTENCE 3 +#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_JOB_TIMEOUT 4 +#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_TRIGGER 5 +#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_NOTIFY 6 +#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_GRANULARITY 7 +/* Monitor 128KB contiguous region with 4K sub-granularity */ +#define DRM_XE_ACC_GRANULARITY_128K 0 +/* Monitor 2MB contiguous region with 64KB sub-granularity */ +#define DRM_XE_ACC_GRANULARITY_2M 1 +/* Monitor 16MB contiguous region with 512KB sub-granularity */ +#define DRM_XE_ACC_GRANULARITY_16M 2 +/* Monitor 64MB contiguous region with 2M sub-granularity */ +#define DRM_XE_ACC_GRANULARITY_64M 3 + + /** @extensions: Pointer to the first extension struct, if any */ + __u64 extensions; + + /** @width: submission width (number BB per exec) for this exec queue */ + __u16 width; + + /** @num_placements: number of valid placements for this exec queue */ + __u16 num_placements; + + /** @vm_id: VM to use for this exec queue */ + __u32 vm_id; + + /** @flags: MBZ */ + __u32 flags; + + /** @exec_queue_id: Returned exec queue ID */ + __u32 exec_queue_id; + + /** + * @instances: user pointer to a 2-d array of struct + * drm_xe_engine_class_instance + * + * length = width (i) * num_placements (j) + * index = j + i * width + */ + __u64 instances; + + /** @reserved: Reserved */ + __u64 reserved[2]; +}; + +/** + * struct drm_xe_exec_queue_destroy - Input of &DRM_IOCTL_XE_EXEC_QUEUE_DESTROY + */ +struct drm_xe_exec_queue_destroy { + /** @exec_queue_id: Exec queue ID */ + __u32 exec_queue_id; + + /** @pad: MBZ */ + __u32 pad; + + /** @reserved: Reserved */ + __u64 reserved[2]; +}; + +/** + * struct drm_xe_exec_queue_get_property - Input of &DRM_IOCTL_XE_EXEC_QUEUE_GET_PROPERTY + * + * The @property can be: + * - %DRM_XE_EXEC_QUEUE_GET_PROPERTY_BAN + */ +struct drm_xe_exec_queue_get_property { + /** @extensions: Pointer to the first extension struct, if any */ + __u64 extensions; + + /** @exec_queue_id: Exec queue ID */ + __u32 exec_queue_id; + +#define DRM_XE_EXEC_QUEUE_GET_PROPERTY_BAN 0 + /** @property: property to get */ + __u32 property; + + /** @value: property value */ + __u64 value; + + /** @reserved: Reserved */ + __u64 reserved[2]; +}; + +/** + * struct drm_xe_sync - sync object + * + * The @type can be: + * - %DRM_XE_SYNC_TYPE_SYNCOBJ + * - %DRM_XE_SYNC_TYPE_TIMELINE_SYNCOBJ + * - %DRM_XE_SYNC_TYPE_USER_FENCE + * + * and the @flags can be: + * - %DRM_XE_SYNC_FLAG_SIGNAL + * + * A minimal use of @drm_xe_sync looks like this: + * + * .. code-block:: C + * + * struct drm_xe_sync sync = { + * .flags = DRM_XE_SYNC_FLAG_SIGNAL, + * .type = DRM_XE_SYNC_TYPE_SYNCOBJ, + * }; + * struct drm_syncobj_create syncobj_create = { 0 }; + * ioctl(fd, DRM_IOCTL_SYNCOBJ_CREATE, &syncobj_create); + * sync.handle = syncobj_create.handle; + * ... + * use of &sync in drm_xe_exec or drm_xe_vm_bind + * ... + * struct drm_syncobj_wait wait = { + * .handles = &sync.handle, + * .timeout_nsec = INT64_MAX, + * .count_handles = 1, + * .flags = 0, + * .first_signaled = 0, + * .pad = 0, + * }; + * ioctl(fd, DRM_IOCTL_SYNCOBJ_WAIT, &wait); + */ +struct drm_xe_sync { + /** @extensions: Pointer to the first extension struct, if any */ + __u64 extensions; + +#define DRM_XE_SYNC_TYPE_SYNCOBJ 0x0 +#define DRM_XE_SYNC_TYPE_TIMELINE_SYNCOBJ 0x1 +#define DRM_XE_SYNC_TYPE_USER_FENCE 0x2 + /** @type: Type of the this sync object */ + __u32 type; + +#define DRM_XE_SYNC_FLAG_SIGNAL (1 << 0) + /** @flags: Sync Flags */ + __u32 flags; + + union { + /** @handle: Handle for the object */ + __u32 handle; + + /** + * @addr: Address of user fence. When sync is passed in via exec + * IOCTL this is a GPU address in the VM. When sync passed in via + * VM bind IOCTL this is a user pointer. In either case, it is + * the users responsibility that this address is present and + * mapped when the user fence is signalled. Must be qword + * aligned. + */ + __u64 addr; + }; + + /** + * @timeline_value: Input for the timeline sync object. Needs to be + * different than 0 when used with %DRM_XE_SYNC_FLAG_TIMELINE_SYNCOBJ. + */ + __u64 timeline_value; + + /** @reserved: Reserved */ + __u64 reserved[2]; +}; + +/** + * struct drm_xe_exec - Input of &DRM_IOCTL_XE_EXEC + * + * This is an example to use @drm_xe_exec for execution of the object + * at BIND_ADDRESS (see example in @drm_xe_vm_bind) by an exec_queue + * (see example in @drm_xe_exec_queue_create). It can be synchronized + * by using the example provided for @drm_xe_sync. + * + * .. code-block:: C + * + * struct drm_xe_exec exec = { + * .exec_queue_id = exec_queue, + * .syncs = &sync, + * .num_syncs = 1, + * .address = BIND_ADDRESS, + * .num_batch_buffer = 1, + * }; + * ioctl(fd, DRM_IOCTL_XE_EXEC, &exec); + * + */ +struct drm_xe_exec { + /** @extensions: Pointer to the first extension struct, if any */ + __u64 extensions; + + /** @exec_queue_id: Exec queue ID for the batch buffer */ + __u32 exec_queue_id; + + /** @num_syncs: Amount of struct drm_xe_sync in array. */ + __u32 num_syncs; + + /** @syncs: Pointer to struct drm_xe_sync array. */ + __u64 syncs; + + /** + * @address: address of batch buffer if num_batch_buffer == 1 or an + * array of batch buffer addresses + */ + __u64 address; + + /** + * @num_batch_buffer: number of batch buffer in this exec, must match + * the width of the engine + */ + __u16 num_batch_buffer; + + /** @pad: MBZ */ + __u16 pad[3]; + + /** @reserved: Reserved */ + __u64 reserved[2]; +}; + +/** + * struct drm_xe_wait_user_fence - Input of &DRM_IOCTL_XE_WAIT_USER_FENCE + * + * Wait on user fence, XE will wake-up on every HW engine interrupt in the + * instances list and check if user fence is complete:: + * + * (*addr & MASK) OP (VALUE & MASK) + * + * Returns to user on user fence completion or timeout. + * + * The @op can be: + * - %DRM_XE_UFENCE_WAIT_OP_EQ + * - %DRM_XE_UFENCE_WAIT_OP_NEQ + * - %DRM_XE_UFENCE_WAIT_OP_GT + * - %DRM_XE_UFENCE_WAIT_OP_GTE + * - %DRM_XE_UFENCE_WAIT_OP_LT + * - %DRM_XE_UFENCE_WAIT_OP_LTE + * + * and the @flags can be: + * - %DRM_XE_UFENCE_WAIT_FLAG_ABSTIME + * - %DRM_XE_UFENCE_WAIT_FLAG_SOFT_OP + * + * The @mask values can be for example: + * - 0xffu for u8 + * - 0xffffu for u16 + * - 0xffffffffu for u32 + * - 0xffffffffffffffffu for u64 + */ +struct drm_xe_wait_user_fence { + /** @extensions: Pointer to the first extension struct, if any */ + __u64 extensions; + + /** + * @addr: user pointer address to wait on, must qword aligned + */ + __u64 addr; + +#define DRM_XE_UFENCE_WAIT_OP_EQ 0x0 +#define DRM_XE_UFENCE_WAIT_OP_NEQ 0x1 +#define DRM_XE_UFENCE_WAIT_OP_GT 0x2 +#define DRM_XE_UFENCE_WAIT_OP_GTE 0x3 +#define DRM_XE_UFENCE_WAIT_OP_LT 0x4 +#define DRM_XE_UFENCE_WAIT_OP_LTE 0x5 + /** @op: wait operation (type of comparison) */ + __u16 op; + +#define DRM_XE_UFENCE_WAIT_FLAG_ABSTIME (1 << 0) + /** @flags: wait flags */ + __u16 flags; + + /** @pad: MBZ */ + __u32 pad; + + /** @value: compare value */ + __u64 value; + + /** @mask: comparison mask */ + __u64 mask; + + /** + * @timeout: how long to wait before bailing, value in nanoseconds. + * Without DRM_XE_UFENCE_WAIT_FLAG_ABSTIME flag set (relative timeout) + * it contains timeout expressed in nanoseconds to wait (fence will + * expire at now() + timeout). + * When DRM_XE_UFENCE_WAIT_FLAG_ABSTIME flat is set (absolute timeout) wait + * will end at timeout (uses system MONOTONIC_CLOCK). + * Passing negative timeout leads to neverending wait. + * + * On relative timeout this value is updated with timeout left + * (for restarting the call in case of signal delivery). + * On absolute timeout this value stays intact (restarted call still + * expire at the same point of time). + */ + __s64 timeout; + + /** @exec_queue_id: exec_queue_id returned from xe_exec_queue_create_ioctl */ + __u32 exec_queue_id; + + /** @pad2: MBZ */ + __u32 pad2; + + /** @reserved: Reserved */ + __u64 reserved[2]; +}; + +#if defined(__cplusplus) +} +#endif + +#endif /* _UAPI_XE_DRM_H_ */ diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h index 5c6c4269f7ef..2ec6f35cda32 100644 --- a/include/uapi/linux/stddef.h +++ b/include/uapi/linux/stddef.h @@ -27,7 +27,7 @@ union { \ struct { MEMBERS } ATTRS; \ struct TAG { MEMBERS } ATTRS NAME; \ - } + } ATTRS #ifdef __cplusplus /* sizeof(struct{}) is 1 in C++, not 0, can't use C version of the macro. */ diff --git a/include/uapi/linux/v4l2-subdev.h b/include/uapi/linux/v4l2-subdev.h index 4a195b68f28f..b383c2fe0cf3 100644 --- a/include/uapi/linux/v4l2-subdev.h +++ b/include/uapi/linux/v4l2-subdev.h @@ -239,7 +239,7 @@ struct v4l2_subdev_routing { * set (which is the default), the 'stream' fields will be forced to 0 by the * kernel. */ - #define V4L2_SUBDEV_CLIENT_CAP_STREAMS (1U << 0) + #define V4L2_SUBDEV_CLIENT_CAP_STREAMS (1ULL << 0) /** * struct v4l2_subdev_client_capability - Capabilities of the client accessing |