From 2c2b0d880f1b4c01f30e14242977b82fa527342d Mon Sep 17 00:00:00 2001 From: Mukul Joshi Date: Thu, 23 Jul 2020 23:09:57 -0400 Subject: drm/amdkfd: Add thermal throttling SMI event Add support for reporting thermal throttling events through SMI. Also, add a counter to count the number of throttling interrupts observed and report the count in the SMI event message. Signed-off-by: Mukul Joshi Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- include/uapi/linux/kfd_ioctl.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index f738c3b53f4e..df6c7a43aadc 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -450,7 +450,8 @@ struct kfd_ioctl_import_dmabuf_args { * KFD SMI(System Management Interface) events */ /* Event type (defined by bitmask) */ -#define KFD_SMI_EVENT_VMFAULT 0x0000000000000001 +#define KFD_SMI_EVENT_VMFAULT 0x0000000000000001 +#define KFD_SMI_EVENT_THERMAL_THROTTLE 0x0000000000000002 struct kfd_ioctl_smi_events_args { __u32 gpuid; /* to KFD */ -- cgit v1.2.3 From 522ec6e0eed0ab0678e7d5b5bf00487dfe83f7ce Mon Sep 17 00:00:00 2001 From: Mukul Joshi Date: Thu, 30 Jul 2020 18:04:33 -0400 Subject: drm/amdkfd: Replace bitmask with event idx in SMI event msg Event bitmask is a 64-bit mask with only 1 bit set. Sending this event bitmask in KFD SMI event message is both wasteful of memory and potentially limiting to only 64 events. Instead send event index in SMI event message. Please note this change does not break the ABI for the two event types defined so far. The new index is identical to the mask used before. Signed-off-by: Mukul Joshi Suggested-by: Felix Kuehling Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c | 24 +++++++++++++----------- include/uapi/linux/kfd_ioctl.h | 10 +++++++--- 2 files changed, 20 insertions(+), 14 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c index 86c2c3e97944..4d4b6e3ab697 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c @@ -149,7 +149,7 @@ static int kfd_smi_ev_release(struct inode *inode, struct file *filep) return 0; } -static void add_event_to_kfifo(struct kfd_dev *dev, unsigned long long smi_event, +static void add_event_to_kfifo(struct kfd_dev *dev, unsigned int smi_event, char *event_msg, int len) { struct kfd_smi_client *client; @@ -157,14 +157,15 @@ static void add_event_to_kfifo(struct kfd_dev *dev, unsigned long long smi_event rcu_read_lock(); list_for_each_entry_rcu(client, &dev->smi_clients, list) { - if (!(READ_ONCE(client->events) & smi_event)) + if (!(READ_ONCE(client->events) & + KFD_SMI_EVENT_MASK_FROM_INDEX(smi_event))) continue; spin_lock(&client->lock); if (kfifo_avail(&client->fifo) >= len) { kfifo_in(&client->fifo, event_msg, len); wake_up_all(&client->wait_queue); } else { - pr_debug("smi_event(EventID: %llu): no space left\n", + pr_debug("smi_event(EventID: %u): no space left\n", smi_event); } spin_unlock(&client->lock); @@ -180,21 +181,21 @@ void kfd_smi_event_update_thermal_throttling(struct kfd_dev *dev, /* * ThermalThrottle msg = throttle_bitmask(8): * thermal_interrupt_count(16): - * 16 bytes event + 1 byte space + 8 byte throttle_bitmask + + * 1 byte event + 1 byte space + 8 byte throttle_bitmask + * 1 byte : + 16 byte thermal_interupt_counter + 1 byte \n + - * 1 byte \0 = 44 + * 1 byte \0 = 29 */ - char fifo_in[44]; + char fifo_in[29]; int len; if (list_empty(&dev->smi_clients)) return; - len = snprintf(fifo_in, 44, "%x %x:%llx\n", + len = snprintf(fifo_in, 29, "%x %x:%llx\n", KFD_SMI_EVENT_THERMAL_THROTTLE, throttle_bitmask, atomic64_read(&adev->smu.throttle_int_counter)); - add_event_to_kfifo(dev, KFD_SMI_EVENT_THERMAL_THROTTLE, fifo_in, len); + add_event_to_kfifo(dev, KFD_SMI_EVENT_THERMAL_THROTTLE, fifo_in, len); } void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid) @@ -202,9 +203,10 @@ void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid) struct amdgpu_device *adev = (struct amdgpu_device *)dev->kgd; struct amdgpu_task_info task_info; /* VmFault msg = (hex)uint32_pid(8) + :(1) + task name(16) = 25 */ - /* 16 bytes event + 1 byte space + 25 bytes msg + 1 byte \n = 43 + /* 1 byte event + 1 byte space + 25 bytes msg + 1 byte \n + + * 1 byte \0 = 29 */ - char fifo_in[43]; + char fifo_in[29]; int len; if (list_empty(&dev->smi_clients)) @@ -216,7 +218,7 @@ void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid) if (!task_info.pid) return; - len = snprintf(fifo_in, 43, "%x %x:%s\n", KFD_SMI_EVENT_VMFAULT, + len = snprintf(fifo_in, 29, "%x %x:%s\n", KFD_SMI_EVENT_VMFAULT, task_info.pid, task_info.task_name); add_event_to_kfifo(dev, KFD_SMI_EVENT_VMFAULT, fifo_in, len); diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index df6c7a43aadc..cb1f963a84e0 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -449,9 +449,13 @@ struct kfd_ioctl_import_dmabuf_args { /* * KFD SMI(System Management Interface) events */ -/* Event type (defined by bitmask) */ -#define KFD_SMI_EVENT_VMFAULT 0x0000000000000001 -#define KFD_SMI_EVENT_THERMAL_THROTTLE 0x0000000000000002 +enum kfd_smi_event { + KFD_SMI_EVENT_NONE = 0, /* not used */ + KFD_SMI_EVENT_VMFAULT = 1, /* event start counting at 1 */ + KFD_SMI_EVENT_THERMAL_THROTTLE = 2, +}; + +#define KFD_SMI_EVENT_MASK_FROM_INDEX(i) (1ULL << ((i) - 1)) struct kfd_ioctl_smi_events_args { __u32 gpuid; /* to KFD */ -- cgit v1.2.3 From 16c642ec3fe9a144fbe1e97dc56f13a6308f1381 Mon Sep 17 00:00:00 2001 From: Pierre-Eric Pelloux-Prayer Date: Thu, 30 Jul 2020 15:54:59 +0200 Subject: drm/amdgpu: new ids flag for tmz (v2) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Allows UMD to know if TMZ is supported and enabled. This commit also bumps KMS_DRIVER_MINOR because if we don't UMD can't tell if "ids_flags & AMDGPU_IDS_FLAGS_TMZ == 0" means "tmz is not enabled" or "tmz may be enabled but the kernel doesn't report it". v2: use amdgpu_is_tmz() and reworded commit message. Signed-off-by: Pierre-Eric Pelloux-Prayer Reviewed-by: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 3 ++- drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 2 ++ include/uapi/drm/amdgpu_drm.h | 1 + 3 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 5156c67ec67b..92d0368217a2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -88,9 +88,10 @@ * - 3.37.0 - L2 is invalidated before SDMA IBs, needed for correctness * - 3.38.0 - Add AMDGPU_IB_FLAG_EMIT_MEM_SYNC * - 3.39.0 - DMABUF implicit sync does a full pipeline sync + * - 3.40.0 - Add AMDGPU_IDS_FLAGS_TMZ */ #define KMS_DRIVER_MAJOR 3 -#define KMS_DRIVER_MINOR 39 +#define KMS_DRIVER_MINOR 40 #define KMS_DRIVER_PATCHLEVEL 0 int amdgpu_vram_limit = 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index e99ad031efd4..58580a48b648 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -737,6 +737,8 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file dev_info.ids_flags |= AMDGPU_IDS_FLAGS_FUSION; if (amdgpu_mcbp || amdgpu_sriov_vf(adev)) dev_info.ids_flags |= AMDGPU_IDS_FLAGS_PREEMPTION; + if (amdgpu_is_tmz(adev)) + dev_info.ids_flags |= AMDGPU_IDS_FLAGS_TMZ; vm_size = adev->vm_manager.max_pfn * AMDGPU_GPU_PAGE_SIZE; vm_size -= AMDGPU_VA_RESERVED_SIZE; diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index 3218576e109d..c5ff2b275fcd 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -673,6 +673,7 @@ struct drm_amdgpu_cs_chunk_data { */ #define AMDGPU_IDS_FLAGS_FUSION 0x1 #define AMDGPU_IDS_FLAGS_PREEMPTION 0x2 +#define AMDGPU_IDS_FLAGS_TMZ 0x4 /* indicate if acceleration can be working */ #define AMDGPU_INFO_ACCEL_WORKING 0x00 -- cgit v1.2.3 From e5b92773287c3eb3108a44785986a6c997866df8 Mon Sep 17 00:00:00 2001 From: Oleg Vasilev Date: Fri, 24 Apr 2020 18:20:51 +0530 Subject: drm: report dp downstream port type as a subconnector property MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently, downstream port type is only reported in debugfs. This information should be considered important since it reflects the actual physical connector type. Some userspace (e.g. window compositors) may want to show this info to a user. The 'subconnector' property is already utilized for DVI-I and TV-out for reporting connector subtype. The initial motivation for this feature came from i2c test [1]. It is supposed to be skipped on VGA connectors, but it cannot detect VGA over DP and fails instead. v2: - Ville: utilized drm_dp_is_branch() - Ville: implement DP 1.0 downstream type info - Replaced create_dp_properties with add_dp_subconnector_property - Added dp_set_subconnector_property helper v4: - Ville: add DP1.0 best assumption about subconnector - Ville: assume DVI is DVI-D - Ville: reuse Writeback enum value for Virtual subconnector - Renamed #defines: HDMI -> HDMIA, DP -> DisplayPort v5: rebase v6: - Jani Nikula: renamed a function name - Jani Nikula: addressed the issues with documentation [1]: https://bugs.freedesktop.org/show_bug.cgi?id=104097 Cc: Ville Syrjälä Cc: intel-gfx@lists.freedesktop.org Signed-off-by: Jeevan B Signed-off-by: Oleg Vasilev Reviewed-by: Emil Velikov Signed-off-by: Maarten Lankhorst Link: https://patchwork.freedesktop.org/patch/msgid/1587732655-17544-1-git-send-email-jeevan.b@intel.com --- drivers/gpu/drm/drm_connector.c | 49 ++++++++++++++++++++++++++-- drivers/gpu/drm/drm_dp_helper.c | 71 +++++++++++++++++++++++++++++++++++++++++ include/drm/drm_connector.h | 3 ++ include/drm/drm_dp_helper.h | 8 +++++ include/drm/drm_mode_config.h | 6 ++++ include/uapi/drm/drm_mode.h | 21 +++++++----- 6 files changed, 148 insertions(+), 10 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c index 00e40a26a800..3d48ad1c3682 100644 --- a/drivers/gpu/drm/drm_connector.c +++ b/drivers/gpu/drm/drm_connector.c @@ -850,7 +850,7 @@ static const struct drm_prop_enum_list drm_dvi_i_select_enum_list[] = { DRM_ENUM_NAME_FN(drm_get_dvi_i_select_name, drm_dvi_i_select_enum_list) static const struct drm_prop_enum_list drm_dvi_i_subconnector_enum_list[] = { - { DRM_MODE_SUBCONNECTOR_Unknown, "Unknown" }, /* DVI-I and TV-out */ + { DRM_MODE_SUBCONNECTOR_Unknown, "Unknown" }, /* DVI-I, TV-out and DP */ { DRM_MODE_SUBCONNECTOR_DVID, "DVI-D" }, /* DVI-I */ { DRM_MODE_SUBCONNECTOR_DVIA, "DVI-A" }, /* DVI-I */ }; @@ -867,7 +867,7 @@ static const struct drm_prop_enum_list drm_tv_select_enum_list[] = { DRM_ENUM_NAME_FN(drm_get_tv_select_name, drm_tv_select_enum_list) static const struct drm_prop_enum_list drm_tv_subconnector_enum_list[] = { - { DRM_MODE_SUBCONNECTOR_Unknown, "Unknown" }, /* DVI-I and TV-out */ + { DRM_MODE_SUBCONNECTOR_Unknown, "Unknown" }, /* DVI-I, TV-out and DP */ { DRM_MODE_SUBCONNECTOR_Composite, "Composite" }, /* TV-out */ { DRM_MODE_SUBCONNECTOR_SVIDEO, "SVIDEO" }, /* TV-out */ { DRM_MODE_SUBCONNECTOR_Component, "Component" }, /* TV-out */ @@ -876,6 +876,19 @@ static const struct drm_prop_enum_list drm_tv_subconnector_enum_list[] = { DRM_ENUM_NAME_FN(drm_get_tv_subconnector_name, drm_tv_subconnector_enum_list) +static const struct drm_prop_enum_list drm_dp_subconnector_enum_list[] = { + { DRM_MODE_SUBCONNECTOR_Unknown, "Unknown" }, /* DVI-I, TV-out and DP */ + { DRM_MODE_SUBCONNECTOR_VGA, "VGA" }, /* DP */ + { DRM_MODE_SUBCONNECTOR_DVID, "DVI-D" }, /* DP */ + { DRM_MODE_SUBCONNECTOR_HDMIA, "HDMI" }, /* DP */ + { DRM_MODE_SUBCONNECTOR_DisplayPort, "DP" }, /* DP */ + { DRM_MODE_SUBCONNECTOR_Wireless, "Wireless" }, /* DP */ + { DRM_MODE_SUBCONNECTOR_Native, "Native" }, /* DP */ +}; + +DRM_ENUM_NAME_FN(drm_get_dp_subconnector_name, + drm_dp_subconnector_enum_list) + static const struct drm_prop_enum_list hdmi_colorspaces[] = { /* For Default case, driver will set the colorspace */ { DRM_MODE_COLORIMETRY_DEFAULT, "Default" }, @@ -1217,6 +1230,14 @@ static const struct drm_prop_enum_list dp_colorspaces[] = { * can also expose this property to external outputs, in which case they * must support "None", which should be the default (since external screens * have a built-in scaler). + * + * subconnector: + * This property is used by DVI-I, TVout and DisplayPort to indicate different + * connector subtypes. Enum values more or less match with those from main + * connector types. + * For DVI-I and TVout there is also a matching property "select subconnector" + * allowing to switch between signal types. + * DP subconnector corresponds to a downstream port. */ int drm_connector_create_standard_properties(struct drm_device *dev) @@ -1305,6 +1326,30 @@ int drm_mode_create_dvi_i_properties(struct drm_device *dev) } EXPORT_SYMBOL(drm_mode_create_dvi_i_properties); +/** + * drm_connector_attach_dp_subconnector_property - create subconnector property for DP + * @connector: drm_connector to attach property + * + * Called by a driver when DP connector is created. + */ +void drm_connector_attach_dp_subconnector_property(struct drm_connector *connector) +{ + struct drm_mode_config *mode_config = &connector->dev->mode_config; + + if (!mode_config->dp_subconnector_property) + mode_config->dp_subconnector_property = + drm_property_create_enum(connector->dev, + DRM_MODE_PROP_IMMUTABLE, + "subconnector", + drm_dp_subconnector_enum_list, + ARRAY_SIZE(drm_dp_subconnector_enum_list)); + + drm_object_attach_property(&connector->base, + mode_config->dp_subconnector_property, + DRM_MODE_SUBCONNECTOR_Unknown); +} +EXPORT_SYMBOL(drm_connector_attach_dp_subconnector_property); + /** * DOC: HDMI connector properties * diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c index a3c82e726057..4c21cf69dad5 100644 --- a/drivers/gpu/drm/drm_dp_helper.c +++ b/drivers/gpu/drm/drm_dp_helper.c @@ -597,6 +597,77 @@ void drm_dp_downstream_debug(struct seq_file *m, } EXPORT_SYMBOL(drm_dp_downstream_debug); +/** + * drm_dp_subconnector_type() - get DP branch device type + * + */ +enum drm_mode_subconnector +drm_dp_subconnector_type(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4]) +{ + int type; + if (!drm_dp_is_branch(dpcd)) + return DRM_MODE_SUBCONNECTOR_Native; + /* DP 1.0 approach */ + if (dpcd[DP_DPCD_REV] == DP_DPCD_REV_10) { + type = dpcd[DP_DOWNSTREAMPORT_PRESENT] & + DP_DWN_STRM_PORT_TYPE_MASK; + + switch (type) { + case DP_DWN_STRM_PORT_TYPE_TMDS: + /* Can be HDMI or DVI-D, DVI-D is a safer option */ + return DRM_MODE_SUBCONNECTOR_DVID; + case DP_DWN_STRM_PORT_TYPE_ANALOG: + /* Can be VGA or DVI-A, VGA is more popular */ + return DRM_MODE_SUBCONNECTOR_VGA; + case DP_DWN_STRM_PORT_TYPE_DP: + return DRM_MODE_SUBCONNECTOR_DisplayPort; + case DP_DWN_STRM_PORT_TYPE_OTHER: + default: + return DRM_MODE_SUBCONNECTOR_Unknown; + } + } + type = port_cap[0] & DP_DS_PORT_TYPE_MASK; + + switch (type) { + case DP_DS_PORT_TYPE_DP: + case DP_DS_PORT_TYPE_DP_DUALMODE: + return DRM_MODE_SUBCONNECTOR_DisplayPort; + case DP_DS_PORT_TYPE_VGA: + return DRM_MODE_SUBCONNECTOR_VGA; + case DP_DS_PORT_TYPE_DVI: + return DRM_MODE_SUBCONNECTOR_DVID; + case DP_DS_PORT_TYPE_HDMI: + return DRM_MODE_SUBCONNECTOR_HDMIA; + case DP_DS_PORT_TYPE_WIRELESS: + return DRM_MODE_SUBCONNECTOR_Wireless; + case DP_DS_PORT_TYPE_NON_EDID: + default: + return DRM_MODE_SUBCONNECTOR_Unknown; + } +} +EXPORT_SYMBOL(drm_dp_subconnector_type); + +/** + * drm_mode_set_dp_subconnector_property - set subconnector for DP connector + * + * Called by a driver on every detect event. + */ +void drm_dp_set_subconnector_property(struct drm_connector *connector, + enum drm_connector_status status, + const u8 *dpcd, + const u8 port_cap[4]) +{ + enum drm_mode_subconnector subconnector = DRM_MODE_SUBCONNECTOR_Unknown; + + if (status == connector_status_connected) + subconnector = drm_dp_subconnector_type(dpcd, port_cap); + drm_object_property_set_value(&connector->base, + connector->dev->mode_config.dp_subconnector_property, + subconnector); +} +EXPORT_SYMBOL(drm_dp_set_subconnector_property); + /* * I2C-over-AUX implementation */ diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index af145608b5ed..928136556174 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -1604,10 +1604,13 @@ const char *drm_get_dvi_i_subconnector_name(int val); const char *drm_get_dvi_i_select_name(int val); const char *drm_get_tv_subconnector_name(int val); const char *drm_get_tv_select_name(int val); +const char *drm_get_dp_subconnector_name(int val); const char *drm_get_content_protection_name(int val); const char *drm_get_hdcp_content_type_name(int val); int drm_mode_create_dvi_i_properties(struct drm_device *dev); +void drm_connector_attach_dp_subconnector_property(struct drm_connector *connector); + int drm_mode_create_tv_margin_properties(struct drm_device *dev); int drm_mode_create_tv_properties(struct drm_device *dev, unsigned int num_modes, diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index e47dc22ebf50..5c2819924862 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -26,6 +26,7 @@ #include #include #include +#include /* * Unless otherwise noted, all values are from the DP 1.1a spec. Note that @@ -1619,6 +1620,13 @@ int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE], int drm_dp_downstream_id(struct drm_dp_aux *aux, char id[6]); void drm_dp_downstream_debug(struct seq_file *m, const u8 dpcd[DP_RECEIVER_CAP_SIZE], const u8 port_cap[4], struct drm_dp_aux *aux); +enum drm_mode_subconnector +drm_dp_subconnector_type(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4]); +void drm_dp_set_subconnector_property(struct drm_connector *connector, + enum drm_connector_status status, + const u8 *dpcd, + const u8 port_cap[4]); void drm_dp_remote_aux_init(struct drm_dp_aux *aux); void drm_dp_aux_init(struct drm_dp_aux *aux); diff --git a/include/drm/drm_mode_config.h b/include/drm/drm_mode_config.h index ffb9852a0638..f768c7cf7de3 100644 --- a/include/drm/drm_mode_config.h +++ b/include/drm/drm_mode_config.h @@ -680,6 +680,12 @@ struct drm_mode_config { */ struct drm_property *dvi_i_select_subconnector_property; + /** + * @dp_subconnector_property: Optional DP property to differentiate + * between different DP downstream port types. + */ + struct drm_property *dp_subconnector_property; + /** * @tv_subconnector_property: Optional TV property to differentiate * between different TV connector types. diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h index deea447e5f22..863eda048265 100644 --- a/include/uapi/drm/drm_mode.h +++ b/include/uapi/drm/drm_mode.h @@ -332,14 +332,19 @@ struct drm_mode_get_encoder { /* This is for connectors with multiple signal types. */ /* Try to match DRM_MODE_CONNECTOR_X as closely as possible. */ enum drm_mode_subconnector { - DRM_MODE_SUBCONNECTOR_Automatic = 0, - DRM_MODE_SUBCONNECTOR_Unknown = 0, - DRM_MODE_SUBCONNECTOR_DVID = 3, - DRM_MODE_SUBCONNECTOR_DVIA = 4, - DRM_MODE_SUBCONNECTOR_Composite = 5, - DRM_MODE_SUBCONNECTOR_SVIDEO = 6, - DRM_MODE_SUBCONNECTOR_Component = 8, - DRM_MODE_SUBCONNECTOR_SCART = 9, + DRM_MODE_SUBCONNECTOR_Automatic = 0, /* DVI-I, TV */ + DRM_MODE_SUBCONNECTOR_Unknown = 0, /* DVI-I, TV, DP */ + DRM_MODE_SUBCONNECTOR_VGA = 1, /* DP */ + DRM_MODE_SUBCONNECTOR_DVID = 3, /* DVI-I DP */ + DRM_MODE_SUBCONNECTOR_DVIA = 4, /* DVI-I */ + DRM_MODE_SUBCONNECTOR_Composite = 5, /* TV */ + DRM_MODE_SUBCONNECTOR_SVIDEO = 6, /* TV */ + DRM_MODE_SUBCONNECTOR_Component = 8, /* TV */ + DRM_MODE_SUBCONNECTOR_SCART = 9, /* TV */ + DRM_MODE_SUBCONNECTOR_DisplayPort = 10, /* DP */ + DRM_MODE_SUBCONNECTOR_HDMIA = 11, /* DP */ + DRM_MODE_SUBCONNECTOR_Native = 15, /* DP */ + DRM_MODE_SUBCONNECTOR_Wireless = 18, /* DP */ }; #define DRM_MODE_CONNECTOR_Unknown 0 -- cgit v1.2.3 From cda9edd02425d7902714c60a6f6e31881d2f2741 Mon Sep 17 00:00:00 2001 From: Lionel Landwerlin Date: Tue, 4 Aug 2020 11:59:53 +0300 Subject: drm/i915: introduce a mechanism to extend execbuf2 We're planning to use this for a couple of new feature where we need to provide additional parameters to execbuf. v2: Check for invalid flags in execbuffer2 (Lionel) v3: Rename I915_EXEC_EXT -> I915_EXEC_USE_EXTENSIONS (Chris) v4: Rebase Move array fence parsing in i915_gem_do_execbuffer() Signed-off-by: Lionel Landwerlin Reviewed-by: Daniel Vetter Reviewed-by: Chris Wilson Link: https://patchwork.freedesktop.org/patch/msgid/20200804085954.350343-2-lionel.g.landwerlin@intel.com Link: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/2901 Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 131 +++++++++++++++---------- include/uapi/drm/i915_drm.h | 25 ++++- 2 files changed, 102 insertions(+), 54 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index 6b4ec66cb558..09d2f955b11e 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -26,6 +26,7 @@ #include "i915_gem_ioctls.h" #include "i915_sw_fence_work.h" #include "i915_trace.h" +#include "i915_user_extensions.h" struct eb_vma { struct i915_vma *vma; @@ -281,6 +282,13 @@ struct i915_execbuffer { int lut_size; struct hlist_head *buckets; /** ht for relocation handles */ struct eb_vma_array *array; + + struct i915_eb_fence { + struct drm_syncobj *syncobj; /* Use with ptr_mask_bits() */ + } *fences; + u32 n_fences; + + u64 extension_flags; /** Available extensions parameters */ }; static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb) @@ -1622,7 +1630,8 @@ static int i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec) return -EINVAL; /* Kernel clipping was a DRI1 misfeature */ - if (!(exec->flags & I915_EXEC_FENCE_ARRAY)) { + if (!(exec->flags & (I915_EXEC_FENCE_ARRAY | + I915_EXEC_USE_EXTENSIONS))) { if (exec->num_cliprects || exec->cliprects_ptr) return -EINVAL; } @@ -2201,41 +2210,41 @@ eb_pin_engine(struct i915_execbuffer *eb, } static void -__free_fence_array(struct drm_syncobj **fences, unsigned int n) +__free_fence_array(struct i915_eb_fence *fences, unsigned int n) { while (n--) - drm_syncobj_put(ptr_mask_bits(fences[n], 2)); + drm_syncobj_put(ptr_mask_bits(fences[n].syncobj, 2)); kvfree(fences); } -static struct drm_syncobj ** +static int get_fence_array(struct drm_i915_gem_execbuffer2 *args, - struct drm_file *file) + struct i915_execbuffer *eb) { const unsigned long nfences = args->num_cliprects; struct drm_i915_gem_exec_fence __user *user; - struct drm_syncobj **fences; + struct i915_eb_fence *fences; unsigned long n; int err; if (!(args->flags & I915_EXEC_FENCE_ARRAY)) - return NULL; + return 0; /* Check multiplication overflow for access_ok() and kvmalloc_array() */ BUILD_BUG_ON(sizeof(size_t) > sizeof(unsigned long)); if (nfences > min_t(unsigned long, ULONG_MAX / sizeof(*user), SIZE_MAX / sizeof(*fences))) - return ERR_PTR(-EINVAL); + return -EINVAL; user = u64_to_user_ptr(args->cliprects_ptr); if (!access_ok(user, nfences * sizeof(*user))) - return ERR_PTR(-EFAULT); + return -EFAULT; fences = kvmalloc_array(nfences, sizeof(*fences), __GFP_NOWARN | GFP_KERNEL); if (!fences) - return ERR_PTR(-ENOMEM); + return -ENOMEM; for (n = 0; n < nfences; n++) { struct drm_i915_gem_exec_fence fence; @@ -2251,7 +2260,7 @@ get_fence_array(struct drm_i915_gem_execbuffer2 *args, goto err; } - syncobj = drm_syncobj_find(file, fence.handle); + syncobj = drm_syncobj_find(eb->file, fence.handle); if (!syncobj) { DRM_DEBUG("Invalid syncobj handle provided\n"); err = -ENOENT; @@ -2261,38 +2270,31 @@ get_fence_array(struct drm_i915_gem_execbuffer2 *args, BUILD_BUG_ON(~(ARCH_KMALLOC_MINALIGN - 1) & ~__I915_EXEC_FENCE_UNKNOWN_FLAGS); - fences[n] = ptr_pack_bits(syncobj, fence.flags, 2); + fences[n].syncobj = ptr_pack_bits(syncobj, fence.flags, 2); } - return fences; + eb->fences = fences; + eb->n_fences = nfences; + + return 0; err: __free_fence_array(fences, n); - return ERR_PTR(err); -} - -static void -put_fence_array(struct drm_i915_gem_execbuffer2 *args, - struct drm_syncobj **fences) -{ - if (fences) - __free_fence_array(fences, args->num_cliprects); + return err; } static int -await_fence_array(struct i915_execbuffer *eb, - struct drm_syncobj **fences) +await_fence_array(struct i915_execbuffer *eb) { - const unsigned int nfences = eb->args->num_cliprects; unsigned int n; int err; - for (n = 0; n < nfences; n++) { + for (n = 0; n < eb->n_fences; n++) { struct drm_syncobj *syncobj; struct dma_fence *fence; unsigned int flags; - syncobj = ptr_unpack_bits(fences[n], &flags, 2); + syncobj = ptr_unpack_bits(eb->fences[n].syncobj, &flags, 2); if (!(flags & I915_EXEC_FENCE_WAIT)) continue; @@ -2310,18 +2312,16 @@ await_fence_array(struct i915_execbuffer *eb, } static void -signal_fence_array(struct i915_execbuffer *eb, - struct drm_syncobj **fences) +signal_fence_array(struct i915_execbuffer *eb) { - const unsigned int nfences = eb->args->num_cliprects; struct dma_fence * const fence = &eb->request->fence; unsigned int n; - for (n = 0; n < nfences; n++) { + for (n = 0; n < eb->n_fences; n++) { struct drm_syncobj *syncobj; unsigned int flags; - syncobj = ptr_unpack_bits(fences[n], &flags, 2); + syncobj = ptr_unpack_bits(eb->fences[n].syncobj, &flags, 2); if (!(flags & I915_EXEC_FENCE_SIGNAL)) continue; @@ -2370,12 +2370,38 @@ static void eb_request_add(struct i915_execbuffer *eb) mutex_unlock(&tl->mutex); } +static const i915_user_extension_fn execbuf_extensions[] = { +}; + +static int +parse_execbuf2_extensions(struct drm_i915_gem_execbuffer2 *args, + struct i915_execbuffer *eb) +{ + eb->extension_flags = 0; + + if (!(args->flags & I915_EXEC_USE_EXTENSIONS)) + return 0; + + /* The execbuf2 extension mechanism reuses cliprects_ptr. So we cannot + * have another flag also using it at the same time. + */ + if (eb->args->flags & I915_EXEC_FENCE_ARRAY) + return -EINVAL; + + if (args->num_cliprects != 0) + return -EINVAL; + + return i915_user_extensions(u64_to_user_ptr(args->cliprects_ptr), + execbuf_extensions, + ARRAY_SIZE(execbuf_extensions), + eb); +} + static int i915_gem_do_execbuffer(struct drm_device *dev, struct drm_file *file, struct drm_i915_gem_execbuffer2 *args, - struct drm_i915_gem_exec_object2 *exec, - struct drm_syncobj **fences) + struct drm_i915_gem_exec_object2 *exec) { struct drm_i915_private *i915 = to_i915(dev); struct i915_execbuffer eb; @@ -2405,6 +2431,9 @@ i915_gem_do_execbuffer(struct drm_device *dev, eb.batch_len = args->batch_len; eb.trampoline = NULL; + eb.fences = NULL; + eb.n_fences = 0; + eb.batch_flags = 0; if (args->flags & I915_EXEC_SECURE) { if (INTEL_GEN(i915) >= 11) @@ -2441,10 +2470,18 @@ i915_gem_do_execbuffer(struct drm_device *dev, } } - err = eb_create(&eb); + err = parse_execbuf2_extensions(args, &eb); if (err) goto err_out_fence; + err = get_fence_array(args, &eb); + if (err) + goto err_arr_fence; + + err = eb_create(&eb); + if (err) + goto err_arr_fence; + GEM_BUG_ON(!eb.lut_size); err = eb_select_context(&eb); @@ -2539,8 +2576,8 @@ i915_gem_do_execbuffer(struct drm_device *dev, goto err_request; } - if (fences) { - err = await_fence_array(&eb, fences); + if (eb.n_fences) { + err = await_fence_array(&eb); if (err) goto err_request; } @@ -2571,8 +2608,8 @@ err_request: i915_request_get(eb.request); eb_request_add(&eb); - if (fences) - signal_fence_array(&eb, fences); + if (eb.n_fences) + signal_fence_array(&eb); if (out_fence) { if (err == 0) { @@ -2600,6 +2637,8 @@ err_context: i915_gem_context_put(eb.gem_context); err_destroy: eb_destroy(&eb); +err_arr_fence: + __free_fence_array(eb.fences, eb.n_fences); err_out_fence: if (out_fence_fd != -1) put_unused_fd(out_fence_fd); @@ -2699,7 +2738,7 @@ i915_gem_execbuffer_ioctl(struct drm_device *dev, void *data, exec2_list[i].flags = 0; } - err = i915_gem_do_execbuffer(dev, file, &exec2, exec2_list, NULL); + err = i915_gem_do_execbuffer(dev, file, &exec2, exec2_list); if (exec2.flags & __EXEC_HAS_RELOC) { struct drm_i915_gem_exec_object __user *user_exec_list = u64_to_user_ptr(args->buffers_ptr); @@ -2731,7 +2770,6 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data, struct drm_i915_private *i915 = to_i915(dev); struct drm_i915_gem_execbuffer2 *args = data; struct drm_i915_gem_exec_object2 *exec2_list; - struct drm_syncobj **fences = NULL; const size_t count = args->buffer_count; int err; @@ -2759,15 +2797,7 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data, return -EFAULT; } - if (args->flags & I915_EXEC_FENCE_ARRAY) { - fences = get_fence_array(args, file); - if (IS_ERR(fences)) { - kvfree(exec2_list); - return PTR_ERR(fences); - } - } - - err = i915_gem_do_execbuffer(dev, file, args, exec2_list, fences); + err = i915_gem_do_execbuffer(dev, file, args, exec2_list); /* * Now that we have begun execution of the batchbuffer, we ignore @@ -2808,7 +2838,6 @@ end:; } args->flags &= ~__I915_EXEC_UNKNOWN_FLAGS; - put_fence_array(args, fences); kvfree(exec2_list); return err; } diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 00546062e023..dcada8c3a693 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -1046,6 +1046,10 @@ struct drm_i915_gem_exec_fence { __u32 flags; }; +enum drm_i915_gem_execbuffer_ext { + DRM_I915_GEM_EXECBUFFER_EXT_MAX /* non-ABI */ +}; + struct drm_i915_gem_execbuffer2 { /** * List of gem_exec_object2 structs @@ -1062,8 +1066,14 @@ struct drm_i915_gem_execbuffer2 { __u32 num_cliprects; /** * This is a struct drm_clip_rect *cliprects if I915_EXEC_FENCE_ARRAY - * is not set. If I915_EXEC_FENCE_ARRAY is set, then this is a - * struct drm_i915_gem_exec_fence *fences. + * & I915_EXEC_USE_EXTENSIONS are not set. + * + * If I915_EXEC_FENCE_ARRAY is set, then this is a pointer to an array + * of struct drm_i915_gem_exec_fence and num_cliprects is the length + * of the array. + * + * If I915_EXEC_USE_EXTENSIONS is set, then this is a pointer to a + * single struct i915_user_extension and num_cliprects is 0. */ __u64 cliprects_ptr; #define I915_EXEC_RING_MASK (0x3f) @@ -1181,7 +1191,16 @@ struct drm_i915_gem_execbuffer2 { */ #define I915_EXEC_FENCE_SUBMIT (1 << 20) -#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_SUBMIT << 1)) +/* + * Setting I915_EXEC_USE_EXTENSIONS implies that + * drm_i915_gem_execbuffer2.cliprects_ptr is treated as a pointer to an linked + * list of i915_user_extension. Each i915_user_extension node is the base of a + * larger structure. The list of supported structures are listed in the + * drm_i915_gem_execbuffer_ext enum. + */ +#define I915_EXEC_USE_EXTENSIONS (1 << 21) + +#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_USE_EXTENSIONS << 1)) #define I915_EXEC_CONTEXT_ID_MASK (0xffffffff) #define i915_execbuffer2_set_context_id(eb2, context) \ -- cgit v1.2.3 From 13149e8bafc4657254831ba6c16ed8780aa64a06 Mon Sep 17 00:00:00 2001 From: Lionel Landwerlin Date: Tue, 4 Aug 2020 11:59:54 +0300 Subject: drm/i915: add syncobj timeline support Introduces a new parameters to execbuf so that we can specify syncobj handles as well as timeline points. v2: Reuse i915_user_extension_fn v3: Check that the chained extension is only present once (Chris) v4: Check that dma_fence_chain_find_seqno returns a non NULL fence (Lionel) v5: Use BIT_ULL (Chris) v6: Fix issue with already signaled timeline points, dma_fence_chain_find_seqno() setting fence to NULL (Chris) v7: Report ENOENT with invalid syncobj handle (Lionel) v8: Check for out of order timeline point insertion (Chris) v9: After explanations on https://lists.freedesktop.org/archives/dri-devel/2019-August/229287.html drop the ordering check from v8 (Lionel) v10: Set first extension enum item to 1 (Jason) v11: Rebase v12: Allow multiple extension nodes of timeline syncobj (Chris) Signed-off-by: Lionel Landwerlin Co-authored-by: Chris Wilson Reviewed-by: Daniel Vetter (v11) Reviewed-by: Chris Wilson Link: https://patchwork.freedesktop.org/patch/msgid/20200804085954.350343-3-lionel.g.landwerlin@intel.com Link: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/2901 Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 312 +++++++++++++++++++------ drivers/gpu/drm/i915/i915_drv.c | 3 +- drivers/gpu/drm/i915/i915_getparam.c | 1 + include/uapi/drm/i915_drm.h | 38 ++- 4 files changed, 279 insertions(+), 75 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index 09d2f955b11e..02b1630f513e 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -223,6 +223,13 @@ struct eb_vma_array { * the batchbuffer in trusted mode, otherwise the ioctl is rejected. */ +struct eb_fence { + struct drm_syncobj *syncobj; /* Use with ptr_mask_bits() */ + struct dma_fence *dma_fence; + u64 value; + struct dma_fence_chain *chain_fence; +}; + struct i915_execbuffer { struct drm_i915_private *i915; /** i915 backpointer */ struct drm_file *file; /** per-file lookup tables and limits */ @@ -283,12 +290,8 @@ struct i915_execbuffer { struct hlist_head *buckets; /** ht for relocation handles */ struct eb_vma_array *array; - struct i915_eb_fence { - struct drm_syncobj *syncobj; /* Use with ptr_mask_bits() */ - } *fences; - u32 n_fences; - - u64 extension_flags; /** Available extensions parameters */ + struct eb_fence *fences; + unsigned long num_fences; }; static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb) @@ -2210,77 +2213,222 @@ eb_pin_engine(struct i915_execbuffer *eb, } static void -__free_fence_array(struct i915_eb_fence *fences, unsigned int n) +__free_fence_array(struct eb_fence *fences, unsigned int n) { - while (n--) + while (n--) { drm_syncobj_put(ptr_mask_bits(fences[n].syncobj, 2)); + dma_fence_put(fences[n].dma_fence); + kfree(fences[n].chain_fence); + } kvfree(fences); } static int -get_fence_array(struct drm_i915_gem_execbuffer2 *args, - struct i915_execbuffer *eb) +add_timeline_fence_array(struct i915_execbuffer *eb, + const struct drm_i915_gem_execbuffer_ext_timeline_fences *timeline_fences) { - const unsigned long nfences = args->num_cliprects; - struct drm_i915_gem_exec_fence __user *user; - struct i915_eb_fence *fences; - unsigned long n; - int err; + struct drm_i915_gem_exec_fence __user *user_fences; + u64 __user *user_values; + struct eb_fence *f; + u64 nfences; + int err = 0; - if (!(args->flags & I915_EXEC_FENCE_ARRAY)) + nfences = timeline_fences->fence_count; + if (!nfences) return 0; /* Check multiplication overflow for access_ok() and kvmalloc_array() */ BUILD_BUG_ON(sizeof(size_t) > sizeof(unsigned long)); if (nfences > min_t(unsigned long, - ULONG_MAX / sizeof(*user), - SIZE_MAX / sizeof(*fences))) + ULONG_MAX / sizeof(*user_fences), + SIZE_MAX / sizeof(*f)) - eb->num_fences) return -EINVAL; - user = u64_to_user_ptr(args->cliprects_ptr); - if (!access_ok(user, nfences * sizeof(*user))) + user_fences = u64_to_user_ptr(timeline_fences->handles_ptr); + if (!access_ok(user_fences, nfences * sizeof(*user_fences))) + return -EFAULT; + + user_values = u64_to_user_ptr(timeline_fences->values_ptr); + if (!access_ok(user_values, nfences * sizeof(*user_values))) return -EFAULT; - fences = kvmalloc_array(nfences, sizeof(*fences), - __GFP_NOWARN | GFP_KERNEL); - if (!fences) + f = krealloc(eb->fences, + (eb->num_fences + nfences) * sizeof(*f), + __GFP_NOWARN | GFP_KERNEL); + if (!f) return -ENOMEM; - for (n = 0; n < nfences; n++) { - struct drm_i915_gem_exec_fence fence; + eb->fences = f; + f += eb->num_fences; + + BUILD_BUG_ON(~(ARCH_KMALLOC_MINALIGN - 1) & + ~__I915_EXEC_FENCE_UNKNOWN_FLAGS); + + while (nfences--) { + struct drm_i915_gem_exec_fence user_fence; struct drm_syncobj *syncobj; + struct dma_fence *fence = NULL; + u64 point; + + if (__copy_from_user(&user_fence, + user_fences++, + sizeof(user_fence))) + return -EFAULT; + + if (user_fence.flags & __I915_EXEC_FENCE_UNKNOWN_FLAGS) + return -EINVAL; + + if (__get_user(point, user_values++)) + return -EFAULT; + + syncobj = drm_syncobj_find(eb->file, user_fence.handle); + if (!syncobj) { + DRM_DEBUG("Invalid syncobj handle provided\n"); + return -ENOENT; + } + + fence = drm_syncobj_fence_get(syncobj); - if (__copy_from_user(&fence, user++, sizeof(fence))) { - err = -EFAULT; - goto err; + if (!fence && user_fence.flags && + !(user_fence.flags & I915_EXEC_FENCE_SIGNAL)) { + DRM_DEBUG("Syncobj handle has no fence\n"); + drm_syncobj_put(syncobj); + return -EINVAL; } - if (fence.flags & __I915_EXEC_FENCE_UNKNOWN_FLAGS) { - err = -EINVAL; - goto err; + if (fence) + err = dma_fence_chain_find_seqno(&fence, point); + + if (err && !(user_fence.flags & I915_EXEC_FENCE_SIGNAL)) { + DRM_DEBUG("Syncobj handle missing requested point %llu\n", point); + drm_syncobj_put(syncobj); + return err; + } + + /* + * A point might have been signaled already and + * garbage collected from the timeline. In this case + * just ignore the point and carry on. + */ + if (!fence && !(user_fence.flags & I915_EXEC_FENCE_SIGNAL)) { + drm_syncobj_put(syncobj); + continue; + } + + /* + * For timeline syncobjs we need to preallocate chains for + * later signaling. + */ + if (point != 0 && user_fence.flags & I915_EXEC_FENCE_SIGNAL) { + /* + * Waiting and signaling the same point (when point != + * 0) would break the timeline. + */ + if (user_fence.flags & I915_EXEC_FENCE_WAIT) { + DRM_DEBUG("Trying to wait & signal the same timeline point.\n"); + dma_fence_put(fence); + drm_syncobj_put(syncobj); + return -EINVAL; + } + + f->chain_fence = + kmalloc(sizeof(*f->chain_fence), + GFP_KERNEL); + if (!f->chain_fence) { + drm_syncobj_put(syncobj); + dma_fence_put(fence); + return -ENOMEM; + } + } else { + f->chain_fence = NULL; } - syncobj = drm_syncobj_find(eb->file, fence.handle); + f->syncobj = ptr_pack_bits(syncobj, user_fence.flags, 2); + f->dma_fence = fence; + f->value = point; + f++; + eb->num_fences++; + } + + return 0; +} + +static int add_fence_array(struct i915_execbuffer *eb) +{ + struct drm_i915_gem_execbuffer2 *args = eb->args; + struct drm_i915_gem_exec_fence __user *user; + unsigned long num_fences = args->num_cliprects; + struct eb_fence *f; + + if (!(args->flags & I915_EXEC_FENCE_ARRAY)) + return 0; + + if (!num_fences) + return 0; + + /* Check multiplication overflow for access_ok() and kvmalloc_array() */ + BUILD_BUG_ON(sizeof(size_t) > sizeof(unsigned long)); + if (num_fences > min_t(unsigned long, + ULONG_MAX / sizeof(*user), + SIZE_MAX / sizeof(*f) - eb->num_fences)) + return -EINVAL; + + user = u64_to_user_ptr(args->cliprects_ptr); + if (!access_ok(user, num_fences * sizeof(*user))) + return -EFAULT; + + f = krealloc(eb->fences, + (eb->num_fences + num_fences) * sizeof(*f), + __GFP_NOWARN | GFP_KERNEL); + if (!f) + return -ENOMEM; + + eb->fences = f; + f += eb->num_fences; + while (num_fences--) { + struct drm_i915_gem_exec_fence user_fence; + struct drm_syncobj *syncobj; + struct dma_fence *fence = NULL; + + if (__copy_from_user(&user_fence, user++, sizeof(user_fence))) + return -EFAULT; + + if (user_fence.flags & __I915_EXEC_FENCE_UNKNOWN_FLAGS) + return -EINVAL; + + syncobj = drm_syncobj_find(eb->file, user_fence.handle); if (!syncobj) { DRM_DEBUG("Invalid syncobj handle provided\n"); - err = -ENOENT; - goto err; + return -ENOENT; + } + + if (user_fence.flags & I915_EXEC_FENCE_WAIT) { + fence = drm_syncobj_fence_get(syncobj); + if (!fence) { + DRM_DEBUG("Syncobj handle has no fence\n"); + drm_syncobj_put(syncobj); + return -EINVAL; + } } BUILD_BUG_ON(~(ARCH_KMALLOC_MINALIGN - 1) & ~__I915_EXEC_FENCE_UNKNOWN_FLAGS); - fences[n].syncobj = ptr_pack_bits(syncobj, fence.flags, 2); + f->syncobj = ptr_pack_bits(syncobj, user_fence.flags, 2); + f->dma_fence = fence; + f->value = 0; + f->chain_fence = NULL; + f++; + eb->num_fences++; } - eb->fences = fences; - eb->n_fences = nfences; - return 0; +} -err: - __free_fence_array(fences, n); - return err; +static void put_fence_array(struct eb_fence *fences, int num_fences) +{ + if (fences) + __free_fence_array(fences, num_fences); } static int @@ -2289,21 +2437,17 @@ await_fence_array(struct i915_execbuffer *eb) unsigned int n; int err; - for (n = 0; n < eb->n_fences; n++) { + for (n = 0; n < eb->num_fences; n++) { struct drm_syncobj *syncobj; - struct dma_fence *fence; unsigned int flags; syncobj = ptr_unpack_bits(eb->fences[n].syncobj, &flags, 2); - if (!(flags & I915_EXEC_FENCE_WAIT)) - continue; - fence = drm_syncobj_fence_get(syncobj); - if (!fence) - return -EINVAL; + if (!eb->fences[n].dma_fence) + continue; - err = i915_request_await_dma_fence(eb->request, fence); - dma_fence_put(fence); + err = i915_request_await_dma_fence(eb->request, + eb->fences[n].dma_fence); if (err < 0) return err; } @@ -2311,13 +2455,12 @@ await_fence_array(struct i915_execbuffer *eb) return 0; } -static void -signal_fence_array(struct i915_execbuffer *eb) +static void signal_fence_array(const struct i915_execbuffer *eb) { struct dma_fence * const fence = &eb->request->fence; unsigned int n; - for (n = 0; n < eb->n_fences; n++) { + for (n = 0; n < eb->num_fences; n++) { struct drm_syncobj *syncobj; unsigned int flags; @@ -2325,10 +2468,34 @@ signal_fence_array(struct i915_execbuffer *eb) if (!(flags & I915_EXEC_FENCE_SIGNAL)) continue; - drm_syncobj_replace_fence(syncobj, fence); + if (eb->fences[n].chain_fence) { + drm_syncobj_add_point(syncobj, + eb->fences[n].chain_fence, + fence, + eb->fences[n].value); + /* + * The chain's ownership is transferred to the + * timeline. + */ + eb->fences[n].chain_fence = NULL; + } else { + drm_syncobj_replace_fence(syncobj, fence); + } } } +static int +parse_timeline_fences(struct i915_user_extension __user *ext, void *data) +{ + struct i915_execbuffer *eb = data; + struct drm_i915_gem_execbuffer_ext_timeline_fences timeline_fences; + + if (copy_from_user(&timeline_fences, ext, sizeof(timeline_fences))) + return -EFAULT; + + return add_timeline_fence_array(eb, &timeline_fences); +} + static void retire_requests(struct intel_timeline *tl, struct i915_request *end) { struct i915_request *rq, *rn; @@ -2371,14 +2538,13 @@ static void eb_request_add(struct i915_execbuffer *eb) } static const i915_user_extension_fn execbuf_extensions[] = { + [DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES] = parse_timeline_fences, }; static int parse_execbuf2_extensions(struct drm_i915_gem_execbuffer2 *args, struct i915_execbuffer *eb) { - eb->extension_flags = 0; - if (!(args->flags & I915_EXEC_USE_EXTENSIONS)) return 0; @@ -2432,7 +2598,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, eb.trampoline = NULL; eb.fences = NULL; - eb.n_fences = 0; + eb.num_fences = 0; eb.batch_flags = 0; if (args->flags & I915_EXEC_SECURE) { @@ -2451,14 +2617,24 @@ i915_gem_do_execbuffer(struct drm_device *dev, if (args->flags & I915_EXEC_IS_PINNED) eb.batch_flags |= I915_DISPATCH_PINNED; + err = parse_execbuf2_extensions(args, &eb); + if (err) + goto err_ext; + + err = add_fence_array(&eb); + if (err) + goto err_ext; + #define IN_FENCES (I915_EXEC_FENCE_IN | I915_EXEC_FENCE_SUBMIT) if (args->flags & IN_FENCES) { if ((args->flags & IN_FENCES) == IN_FENCES) return -EINVAL; in_fence = sync_file_get_fence(lower_32_bits(args->rsvd2)); - if (!in_fence) - return -EINVAL; + if (!in_fence) { + err = -EINVAL; + goto err_ext; + } } #undef IN_FENCES @@ -2470,17 +2646,9 @@ i915_gem_do_execbuffer(struct drm_device *dev, } } - err = parse_execbuf2_extensions(args, &eb); - if (err) - goto err_out_fence; - - err = get_fence_array(args, &eb); - if (err) - goto err_arr_fence; - err = eb_create(&eb); if (err) - goto err_arr_fence; + goto err_out_fence; GEM_BUG_ON(!eb.lut_size); @@ -2576,7 +2744,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, goto err_request; } - if (eb.n_fences) { + if (eb.fences) { err = await_fence_array(&eb); if (err) goto err_request; @@ -2608,7 +2776,7 @@ err_request: i915_request_get(eb.request); eb_request_add(&eb); - if (eb.n_fences) + if (eb.fences) signal_fence_array(&eb); if (out_fence) { @@ -2637,13 +2805,13 @@ err_context: i915_gem_context_put(eb.gem_context); err_destroy: eb_destroy(&eb); -err_arr_fence: - __free_fence_array(eb.fences, eb.n_fences); err_out_fence: if (out_fence_fd != -1) put_unused_fd(out_fence_fd); err_in_fence: dma_fence_put(in_fence); +err_ext: + put_fence_array(eb.fences, eb.num_fences); return err; } diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 5fd5af4bc855..2d10f6a2c042 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -1846,7 +1846,8 @@ static struct drm_driver driver = { */ .driver_features = DRIVER_GEM | - DRIVER_RENDER | DRIVER_MODESET | DRIVER_ATOMIC | DRIVER_SYNCOBJ, + DRIVER_RENDER | DRIVER_MODESET | DRIVER_ATOMIC | DRIVER_SYNCOBJ | + DRIVER_SYNCOBJ_TIMELINE, .release = i915_driver_release, .open = i915_driver_open, .lastclose = i915_driver_lastclose, diff --git a/drivers/gpu/drm/i915/i915_getparam.c b/drivers/gpu/drm/i915/i915_getparam.c index 421613219ae9..f96032c60a12 100644 --- a/drivers/gpu/drm/i915/i915_getparam.c +++ b/drivers/gpu/drm/i915/i915_getparam.c @@ -132,6 +132,7 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data, case I915_PARAM_HAS_EXEC_BATCH_FIRST: case I915_PARAM_HAS_EXEC_FENCE_ARRAY: case I915_PARAM_HAS_EXEC_SUBMIT_FENCE: + case I915_PARAM_HAS_EXEC_TIMELINE_FENCES: /* For the time being all of these are always true; * if some supported hardware does not have one of these * features this value needs to be provided from diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index dcada8c3a693..fa1f3d62f9a6 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -619,6 +619,12 @@ typedef struct drm_i915_irq_wait { */ #define I915_PARAM_PERF_REVISION 54 +/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of + * timeline syncobj through drm_i915_gem_execbuffer_ext_timeline_fences. See + * I915_EXEC_USE_EXTENSIONS. + */ +#define I915_PARAM_HAS_EXEC_TIMELINE_FENCES 55 + /* Must be kept compact -- no holes and well documented */ typedef struct drm_i915_getparam { @@ -1046,8 +1052,36 @@ struct drm_i915_gem_exec_fence { __u32 flags; }; -enum drm_i915_gem_execbuffer_ext { - DRM_I915_GEM_EXECBUFFER_EXT_MAX /* non-ABI */ +/** + * See drm_i915_gem_execbuffer_ext_timeline_fences. + */ +#define DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES 0 + +/** + * This structure describes an array of drm_syncobj and associated points for + * timeline variants of drm_syncobj. It is invalid to append this structure to + * the execbuf if I915_EXEC_FENCE_ARRAY is set. + */ +struct drm_i915_gem_execbuffer_ext_timeline_fences { + struct i915_user_extension base; + + /** + * Number of element in the handles_ptr & value_ptr arrays. + */ + __u64 fence_count; + + /** + * Pointer to an array of struct drm_i915_gem_exec_fence of length + * fence_count. + */ + __u64 handles_ptr; + + /** + * Pointer to an array of u64 values of length fence_count. Values + * must be 0 for a binary drm_syncobj. A Value of 0 for a timeline + * drm_syncobj is invalid as it turns a drm_syncobj into a binary one. + */ + __u64 values_ptr; }; struct drm_i915_gem_execbuffer2 { -- cgit v1.2.3 From 592d9fba33c275b72cb4dae99c187444daafcd33 Mon Sep 17 00:00:00 2001 From: David Stevens Date: Tue, 18 Aug 2020 16:13:42 +0900 Subject: virtio-gpu: add VIRTIO_GPU_F_RESOURCE_UUID feature This feature allows the guest to request a UUID from the host for a particular virtio_gpu resource. The UUID can then be shared with other virtio devices, to allow the other host devices to access the virtio_gpu's corresponding host resource. Signed-off-by: David Stevens Acked-by: Michael S. Tsirkin Link: http://patchwork.freedesktop.org/patch/msgid/20200818071343.3461203-3-stevensd@chromium.org Signed-off-by: Gerd Hoffmann --- include/uapi/linux/virtio_gpu.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/virtio_gpu.h b/include/uapi/linux/virtio_gpu.h index 0c85914d9369..9721d58b4d58 100644 --- a/include/uapi/linux/virtio_gpu.h +++ b/include/uapi/linux/virtio_gpu.h @@ -50,6 +50,10 @@ * VIRTIO_GPU_CMD_GET_EDID */ #define VIRTIO_GPU_F_EDID 1 +/* + * VIRTIO_GPU_CMD_RESOURCE_ASSIGN_UUID + */ +#define VIRTIO_GPU_F_RESOURCE_UUID 2 enum virtio_gpu_ctrl_type { VIRTIO_GPU_UNDEFINED = 0, @@ -66,6 +70,7 @@ enum virtio_gpu_ctrl_type { VIRTIO_GPU_CMD_GET_CAPSET_INFO, VIRTIO_GPU_CMD_GET_CAPSET, VIRTIO_GPU_CMD_GET_EDID, + VIRTIO_GPU_CMD_RESOURCE_ASSIGN_UUID, /* 3d commands */ VIRTIO_GPU_CMD_CTX_CREATE = 0x0200, @@ -87,6 +92,7 @@ enum virtio_gpu_ctrl_type { VIRTIO_GPU_RESP_OK_CAPSET_INFO, VIRTIO_GPU_RESP_OK_CAPSET, VIRTIO_GPU_RESP_OK_EDID, + VIRTIO_GPU_RESP_OK_RESOURCE_UUID, /* error responses */ VIRTIO_GPU_RESP_ERR_UNSPEC = 0x1200, @@ -340,4 +346,17 @@ enum virtio_gpu_formats { VIRTIO_GPU_FORMAT_R8G8B8X8_UNORM = 134, }; +/* VIRTIO_GPU_CMD_RESOURCE_ASSIGN_UUID */ +struct virtio_gpu_resource_assign_uuid { + struct virtio_gpu_ctrl_hdr hdr; + __le32 resource_id; + __le32 padding; +}; + +/* VIRTIO_GPU_RESP_OK_RESOURCE_UUID */ +struct virtio_gpu_resp_resource_uuid { + struct virtio_gpu_ctrl_hdr hdr; + __u8 uuid[16]; +}; + #endif -- cgit v1.2.3 From 55977744f9d862512a524fea93fc5226b09e76a9 Mon Sep 17 00:00:00 2001 From: Mukul Joshi Date: Fri, 28 Aug 2020 18:50:42 -0400 Subject: drm/amdkfd: Add GPU reset SMI event Add support for reporting GPU reset events through SMI. KFD would report both pre and post GPU reset events. Signed-off-by: Mukul Joshi Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_device.c | 4 ++++ drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 2 ++ drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c | 34 +++++++++++++++++++++++++++-- drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h | 1 + include/uapi/linux/kfd_ioctl.h | 2 ++ 5 files changed, 41 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index e1cd6599529f..0e71a0543f98 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -812,6 +812,8 @@ int kgd2kfd_pre_reset(struct kfd_dev *kfd) if (!kfd->init_complete) return 0; + kfd_smi_event_update_gpu_reset(kfd, false); + kfd->dqm->ops.pre_reset(kfd->dqm); kgd2kfd_suspend(kfd, false); @@ -840,6 +842,8 @@ int kgd2kfd_post_reset(struct kfd_dev *kfd) atomic_set(&kfd->sram_ecc_flag, 0); + kfd_smi_event_update_gpu_reset(kfd, true); + return 0; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index f14beb93acb4..023629f28495 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -312,6 +312,8 @@ struct kfd_dev { /* Clients watching SMI events */ struct list_head smi_clients; spinlock_t smi_lock; + + uint32_t reset_seq_num; }; enum kfd_mempool { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c index 4d4b6e3ab697..17d1736367ea 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c @@ -174,6 +174,36 @@ static void add_event_to_kfifo(struct kfd_dev *dev, unsigned int smi_event, rcu_read_unlock(); } +void kfd_smi_event_update_gpu_reset(struct kfd_dev *dev, bool post_reset) +{ + /* + * GpuReset msg = Reset seq number (incremented for + * every reset message sent before GPU reset). + * 1 byte event + 1 byte space + 8 bytes seq num + + * 1 byte \n + 1 byte \0 = 12 + */ + char fifo_in[12]; + int len; + unsigned int event; + + if (list_empty(&dev->smi_clients)) + return; + + memset(fifo_in, 0x0, sizeof(fifo_in)); + + if (post_reset) { + event = KFD_SMI_EVENT_GPU_POST_RESET; + } else { + event = KFD_SMI_EVENT_GPU_PRE_RESET; + ++(dev->reset_seq_num); + } + + len = snprintf(fifo_in, sizeof(fifo_in), "%x %x\n", event, + dev->reset_seq_num); + + add_event_to_kfifo(dev, event, fifo_in, len); +} + void kfd_smi_event_update_thermal_throttling(struct kfd_dev *dev, uint32_t throttle_bitmask) { @@ -191,7 +221,7 @@ void kfd_smi_event_update_thermal_throttling(struct kfd_dev *dev, if (list_empty(&dev->smi_clients)) return; - len = snprintf(fifo_in, 29, "%x %x:%llx\n", + len = snprintf(fifo_in, sizeof(fifo_in), "%x %x:%llx\n", KFD_SMI_EVENT_THERMAL_THROTTLE, throttle_bitmask, atomic64_read(&adev->smu.throttle_int_counter)); @@ -218,7 +248,7 @@ void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid) if (!task_info.pid) return; - len = snprintf(fifo_in, 29, "%x %x:%s\n", KFD_SMI_EVENT_VMFAULT, + len = snprintf(fifo_in, sizeof(fifo_in), "%x %x:%s\n", KFD_SMI_EVENT_VMFAULT, task_info.pid, task_info.task_name); add_event_to_kfifo(dev, KFD_SMI_EVENT_VMFAULT, fifo_in, len); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h index 15537b2cccb5..b9b0438202e2 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h @@ -27,5 +27,6 @@ int kfd_smi_event_open(struct kfd_dev *dev, uint32_t *fd); void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid); void kfd_smi_event_update_thermal_throttling(struct kfd_dev *dev, uint32_t throttle_bitmask); +void kfd_smi_event_update_gpu_reset(struct kfd_dev *dev, bool post_reset); #endif diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index cb1f963a84e0..8b7368bfbd84 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -453,6 +453,8 @@ enum kfd_smi_event { KFD_SMI_EVENT_NONE = 0, /* not used */ KFD_SMI_EVENT_VMFAULT = 1, /* event start counting at 1 */ KFD_SMI_EVENT_THERMAL_THROTTLE = 2, + KFD_SMI_EVENT_GPU_PRE_RESET = 3, + KFD_SMI_EVENT_GPU_POST_RESET = 4, }; #define KFD_SMI_EVENT_MASK_FROM_INDEX(i) (1ULL << ((i) - 1)) -- cgit v1.2.3 From 5dc1a0bcb758c343b873e8330ee986417f5a1727 Mon Sep 17 00:00:00 2001 From: Mukul Joshi Date: Fri, 28 Aug 2020 19:53:08 -0400 Subject: include/uapi/linux: Fix indentation in kfd_smi_event enum Replace spaces with Tabs to fix indentation in kfd_smi_event enum. Signed-off-by: Mukul Joshi Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- include/uapi/linux/kfd_ioctl.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 8b7368bfbd84..695b606da4b1 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -450,9 +450,9 @@ struct kfd_ioctl_import_dmabuf_args { * KFD SMI(System Management Interface) events */ enum kfd_smi_event { - KFD_SMI_EVENT_NONE = 0, /* not used */ - KFD_SMI_EVENT_VMFAULT = 1, /* event start counting at 1 */ - KFD_SMI_EVENT_THERMAL_THROTTLE = 2, + KFD_SMI_EVENT_NONE = 0, /* not used */ + KFD_SMI_EVENT_VMFAULT = 1, /* event start counting at 1 */ + KFD_SMI_EVENT_THERMAL_THROTTLE = 2, KFD_SMI_EVENT_GPU_PRE_RESET = 3, KFD_SMI_EVENT_GPU_POST_RESET = 4, }; -- cgit v1.2.3 From 0dd4ff93f4c8dba016ad79384007da4938cd54a1 Mon Sep 17 00:00:00 2001 From: Sebastien Boeuf Date: Wed, 19 Aug 2020 18:19:42 -0400 Subject: virtio: Implement get_shm_region for PCI transport On PCI the shm regions are found using capability entries; find a region by searching for the capability. Signed-off-by: Sebastien Boeuf Signed-off-by: Dr. David Alan Gilbert Signed-off-by: kbuild test robot Acked-by: Michael S. Tsirkin Cc: kvm@vger.kernel.org Cc: virtualization@lists.linux-foundation.org Cc: "Michael S. Tsirkin" Signed-off-by: Miklos Szeredi --- drivers/virtio/virtio_pci_modern.c | 95 ++++++++++++++++++++++++++++++++++++++ include/uapi/linux/virtio_pci.h | 11 ++++- 2 files changed, 105 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index 3e14e700b231..3d6ae5a5e252 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -444,6 +444,99 @@ static void del_vq(struct virtio_pci_vq_info *info) vring_del_virtqueue(vq); } +static int virtio_pci_find_shm_cap(struct pci_dev *dev, u8 required_id, + u8 *bar, u64 *offset, u64 *len) +{ + int pos; + + for (pos = pci_find_capability(dev, PCI_CAP_ID_VNDR); pos > 0; + pos = pci_find_next_capability(dev, pos, PCI_CAP_ID_VNDR)) { + u8 type, cap_len, id; + u32 tmp32; + u64 res_offset, res_length; + + pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap, + cfg_type), &type); + if (type != VIRTIO_PCI_CAP_SHARED_MEMORY_CFG) + continue; + + pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap, + cap_len), &cap_len); + if (cap_len != sizeof(struct virtio_pci_cap64)) { + dev_err(&dev->dev, "%s: shm cap with bad size offset:" + " %d size: %d\n", __func__, pos, cap_len); + continue; + } + + pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap, + id), &id); + if (id != required_id) + continue; + + /* Type, and ID match, looks good */ + pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap, + bar), bar); + + /* Read the lower 32bit of length and offset */ + pci_read_config_dword(dev, pos + offsetof(struct virtio_pci_cap, + offset), &tmp32); + res_offset = tmp32; + pci_read_config_dword(dev, pos + offsetof(struct virtio_pci_cap, + length), &tmp32); + res_length = tmp32; + + /* and now the top half */ + pci_read_config_dword(dev, + pos + offsetof(struct virtio_pci_cap64, + offset_hi), &tmp32); + res_offset |= ((u64)tmp32) << 32; + pci_read_config_dword(dev, + pos + offsetof(struct virtio_pci_cap64, + length_hi), &tmp32); + res_length |= ((u64)tmp32) << 32; + + *offset = res_offset; + *len = res_length; + + return pos; + } + return 0; +} + +static bool vp_get_shm_region(struct virtio_device *vdev, + struct virtio_shm_region *region, u8 id) +{ + struct virtio_pci_device *vp_dev = to_vp_device(vdev); + struct pci_dev *pci_dev = vp_dev->pci_dev; + u8 bar; + u64 offset, len; + phys_addr_t phys_addr; + size_t bar_len; + + if (!virtio_pci_find_shm_cap(pci_dev, id, &bar, &offset, &len)) + return false; + + phys_addr = pci_resource_start(pci_dev, bar); + bar_len = pci_resource_len(pci_dev, bar); + + if ((offset + len) < offset) { + dev_err(&pci_dev->dev, "%s: cap offset+len overflow detected\n", + __func__); + return false; + } + + if (offset + len > bar_len) { + dev_err(&pci_dev->dev, "%s: bar shorter than cap offset+len\n", + __func__); + return false; + } + + region->len = len; + region->addr = (u64) phys_addr + offset; + + return true; +} + static const struct virtio_config_ops virtio_pci_config_nodev_ops = { .get = NULL, .set = NULL, @@ -458,6 +551,7 @@ static const struct virtio_config_ops virtio_pci_config_nodev_ops = { .bus_name = vp_bus_name, .set_vq_affinity = vp_set_vq_affinity, .get_vq_affinity = vp_get_vq_affinity, + .get_shm_region = vp_get_shm_region, }; static const struct virtio_config_ops virtio_pci_config_ops = { @@ -474,6 +568,7 @@ static const struct virtio_config_ops virtio_pci_config_ops = { .bus_name = vp_bus_name, .set_vq_affinity = vp_set_vq_affinity, .get_vq_affinity = vp_get_vq_affinity, + .get_shm_region = vp_get_shm_region, }; /** diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h index 90007a1abcab..3a86f36d7e3d 100644 --- a/include/uapi/linux/virtio_pci.h +++ b/include/uapi/linux/virtio_pci.h @@ -113,6 +113,8 @@ #define VIRTIO_PCI_CAP_DEVICE_CFG 4 /* PCI configuration access */ #define VIRTIO_PCI_CAP_PCI_CFG 5 +/* Additional shared memory capability */ +#define VIRTIO_PCI_CAP_SHARED_MEMORY_CFG 8 /* This is the PCI capability header: */ struct virtio_pci_cap { @@ -121,11 +123,18 @@ struct virtio_pci_cap { __u8 cap_len; /* Generic PCI field: capability length */ __u8 cfg_type; /* Identifies the structure. */ __u8 bar; /* Where to find it. */ - __u8 padding[3]; /* Pad to full dword. */ + __u8 id; /* Multiple capabilities of the same type */ + __u8 padding[2]; /* Pad to full dword. */ __le32 offset; /* Offset within bar. */ __le32 length; /* Length of the structure, in bytes. */ }; +struct virtio_pci_cap64 { + struct virtio_pci_cap cap; + __le32 offset_hi; /* Most sig 32 bits of offset */ + __le32 length_hi; /* Most sig 32 bits of length */ +}; + struct virtio_pci_notify_cap { struct virtio_pci_cap cap; __le32 notify_off_multiplier; /* Multiplier for queue_notify_off. */ -- cgit v1.2.3 From 38e895487afc2ed42c11045853cbb3fa20b52b6e Mon Sep 17 00:00:00 2001 From: Sebastien Boeuf Date: Wed, 19 Aug 2020 18:19:43 -0400 Subject: virtio: Implement get_shm_region for MMIO transport On MMIO a new set of registers is defined for finding SHM regions. Add their definitions and use them to find the region. Signed-off-by: Sebastien Boeuf Cc: kvm@vger.kernel.org Cc: virtualization@lists.linux-foundation.org Cc: "Michael S. Tsirkin" Signed-off-by: Miklos Szeredi --- drivers/virtio/virtio_mmio.c | 31 +++++++++++++++++++++++++++++++ include/uapi/linux/virtio_mmio.h | 11 +++++++++++ 2 files changed, 42 insertions(+) (limited to 'include/uapi') diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c index 627ac0487494..238383ff1064 100644 --- a/drivers/virtio/virtio_mmio.c +++ b/drivers/virtio/virtio_mmio.c @@ -498,6 +498,36 @@ static const char *vm_bus_name(struct virtio_device *vdev) return vm_dev->pdev->name; } +static bool vm_get_shm_region(struct virtio_device *vdev, + struct virtio_shm_region *region, u8 id) +{ + struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev); + u64 len, addr; + + /* Select the region we're interested in */ + writel(id, vm_dev->base + VIRTIO_MMIO_SHM_SEL); + + /* Read the region size */ + len = (u64) readl(vm_dev->base + VIRTIO_MMIO_SHM_LEN_LOW); + len |= (u64) readl(vm_dev->base + VIRTIO_MMIO_SHM_LEN_HIGH) << 32; + + region->len = len; + + /* Check if region length is -1. If that's the case, the shared memory + * region does not exist and there is no need to proceed further. + */ + if (len == ~(u64)0) + return false; + + /* Read the region base address */ + addr = (u64) readl(vm_dev->base + VIRTIO_MMIO_SHM_BASE_LOW); + addr |= (u64) readl(vm_dev->base + VIRTIO_MMIO_SHM_BASE_HIGH) << 32; + + region->addr = addr; + + return true; +} + static const struct virtio_config_ops virtio_mmio_config_ops = { .get = vm_get, .set = vm_set, @@ -510,6 +540,7 @@ static const struct virtio_config_ops virtio_mmio_config_ops = { .get_features = vm_get_features, .finalize_features = vm_finalize_features, .bus_name = vm_bus_name, + .get_shm_region = vm_get_shm_region, }; diff --git a/include/uapi/linux/virtio_mmio.h b/include/uapi/linux/virtio_mmio.h index c4b09689ab64..0650f91bea6c 100644 --- a/include/uapi/linux/virtio_mmio.h +++ b/include/uapi/linux/virtio_mmio.h @@ -122,6 +122,17 @@ #define VIRTIO_MMIO_QUEUE_USED_LOW 0x0a0 #define VIRTIO_MMIO_QUEUE_USED_HIGH 0x0a4 +/* Shared memory region id */ +#define VIRTIO_MMIO_SHM_SEL 0x0ac + +/* Shared memory region length, 64 bits in two halves */ +#define VIRTIO_MMIO_SHM_LEN_LOW 0x0b0 +#define VIRTIO_MMIO_SHM_LEN_HIGH 0x0b4 + +/* Shared memory region base address, 64 bits in two halves */ +#define VIRTIO_MMIO_SHM_BASE_LOW 0x0b8 +#define VIRTIO_MMIO_SHM_BASE_HIGH 0x0bc + /* Configuration atomicity value */ #define VIRTIO_MMIO_CONFIG_GENERATION 0x0fc -- cgit v1.2.3