From 4f18b9a6711adbc7c76993c734a94ee3f5c61791 Mon Sep 17 00:00:00 2001 From: Bas Nieuwenhuizen Date: Thu, 13 Apr 2023 16:22:53 +0200 Subject: drm/amdgpu: Add support for querying the max ibs in a submission. (v3) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This info would be used by radv to figure out when we need to split a submission into multiple submissions. radv currently has a limit of 192 which seems to work for most gfx submissions, but is way too high for e.g. compute or sdma. Userspace is available at https://gitlab.freedesktop.org/bnieuwenhuizen/mesa/-/commits/ib-rejection-v3 v3: Completely rewrote based on suggestion of making it a separate query. Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2498 Reviewed-by: Christian König Signed-off-by: Bas Nieuwenhuizen Signed-off-by: Alex Deucher --- include/uapi/drm/amdgpu_drm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index b6eb90df5d05..6981e59a9401 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -876,6 +876,8 @@ struct drm_amdgpu_cs_chunk_data { #define AMDGPU_INFO_VIDEO_CAPS_DECODE 0 /* Subquery id: Encode */ #define AMDGPU_INFO_VIDEO_CAPS_ENCODE 1 +/* Query the max number of IBs per gang per submission */ +#define AMDGPU_INFO_MAX_IBS 0x22 #define AMDGPU_INFO_MMR_SE_INDEX_SHIFT 0 #define AMDGPU_INFO_MMR_SE_INDEX_MASK 0xff -- cgit v1.2.3 From 043dc33f443fd7abaf3fe076897503ce3d5dbc26 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Thu, 9 Mar 2023 13:48:11 -0500 Subject: drm/amdgpu/UAPI: add new CS chunk for GFX shadow buffers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit For GFX11, the UMD needs to allocate some shadow buffers to be used for preemption. The UMD allocates the buffers and passes the GPU virtual address to the kernel since the kernel will program the packet that specified these addresses as part of its IB submission frame. v2: UMD passes shadow init to tell kernel when to initialize the shadow Reviewed-by: Christian König Signed-off-by: Alex Deucher --- include/uapi/drm/amdgpu_drm.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index 6981e59a9401..fc094653b13f 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -592,6 +592,7 @@ struct drm_amdgpu_gem_va { #define AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES 0x07 #define AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_WAIT 0x08 #define AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_SIGNAL 0x09 +#define AMDGPU_CHUNK_ID_CP_GFX_SHADOW 0x0a struct drm_amdgpu_cs_chunk { __u32 chunk_id; @@ -708,6 +709,15 @@ struct drm_amdgpu_cs_chunk_data { }; }; +#define AMDGPU_CS_CHUNK_CP_GFX_SHADOW_FLAGS_INIT_SHADOW 0x1 + +struct drm_amdgpu_cs_chunk_cp_gfx_shadow { + __u64 shadow_va; + __u64 csa_va; + __u64 gds_va; + __u64 flags; +}; + /* * Query h/w info: Flag that this is integrated (a.h.a. fusion) GPU * -- cgit v1.2.3 From edd9038000352ba846cba9dfb84d8c397c3b6499 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Thu, 9 Mar 2023 13:43:13 -0500 Subject: drm/amdgpu: add UAPI to query GFX shadow sizes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add UAPI to query the GFX shadow buffer requirements for preemption on GFX11. UMDs need to specify the shadow areas for preemption. v2: move into existing asic info query drop GDS as its use is determined by the UMD (Marek) v3: Update comments to note that alignment is base virtual alignment (Alex) Reviewed-by: Marek Olšák Signed-off-by: Alex Deucher --- include/uapi/drm/amdgpu_drm.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index fc094653b13f..cc78528c3b4b 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -1138,6 +1138,14 @@ struct drm_amdgpu_info_device { __u64 mall_size; /* AKA infinity cache */ /* high 32 bits of the rb pipes mask */ __u32 enabled_rb_pipes_mask_hi; + /* shadow area size for gfx11 */ + __u32 shadow_size; + /* shadow area base virtual alignment for gfx11 */ + __u32 shadow_alignment; + /* context save area size for gfx11 */ + __u32 csa_size; + /* context save area base virtual alignment for gfx11 */ + __u32 csa_alignment; }; struct drm_amdgpu_info_hw_ip { -- cgit v1.2.3 From 99e7e3b60080d913ff2f94943f4af1f1b76a1c06 Mon Sep 17 00:00:00 2001 From: Ville Syrjälä Date: Wed, 12 Apr 2023 01:29:26 +0300 Subject: drm/uapi: Document CTM matrix better MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Document in which order the CTM matrix elements are stored. Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20230411222931.15127-2-ville.syrjala@linux.intel.com Reviewed-by: Xaver Hugl Acked-by: Simon Ser --- include/uapi/drm/drm_mode.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h index 46becedf5b2f..43691058d28f 100644 --- a/include/uapi/drm/drm_mode.h +++ b/include/uapi/drm/drm_mode.h @@ -834,6 +834,11 @@ struct drm_color_ctm { /* * Conversion matrix in S31.32 sign-magnitude * (not two's complement!) format. + * + * out matrix in + * |R| |0 1 2| |R| + * |G| = |3 4 5| x |G| + * |B| |6 7 8| |B| */ __u64 matrix[9]; }; -- cgit v1.2.3 From a4bb75c4f19db711676e6bf6a278d932a5e7667b Mon Sep 17 00:00:00 2001 From: Jaroslav Kysela Date: Tue, 2 May 2023 13:55:36 +0200 Subject: ALSA: uapi: pcm: control the filling of the silence samples for drain Introduce SNDRV_PCM_INFO_PERFECT_DRAIN and SNDRV_PCM_HW_PARAMS_NO_DRAIN_SILENCE flags to fully control the filling of the silence samples in the drain ioctl. Actually, the configurable silencing is going to be implemented in the user space [1], but drivers (hardware) may not require this operation. Those flags do the bidirectional setup for this operation: 1) driver may notify the presence of the perfect drain 2) user space may not require the filling of the silence samples to inhibit clicks If we decide to move this operation to the kernel space in future, the SNDRV_PCM_INFO_PERFECT_DRAIN flag may handle this situation without double "silence" processing (user + kernel space). The ALSA API should be universal, so forcing the behaviour (modifying of the ring buffer with any samples) for the drain operation is not ideal. [1] https://lore.kernel.org/alsa-devel/20230502115010.986325-1-perex@perex.cz/ [ fixed a typo in comment by tiwai ] Signed-off-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20230502115536.986900-1-perex@perex.cz Signed-off-by: Takashi Iwai --- include/uapi/sound/asound.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h index 0aa955aa8246..6322823b5270 100644 --- a/include/uapi/sound/asound.h +++ b/include/uapi/sound/asound.h @@ -274,6 +274,7 @@ typedef int __bitwise snd_pcm_subformat_t; #define SNDRV_PCM_INFO_DOUBLE 0x00000004 /* Double buffering needed for PCM start/stop */ #define SNDRV_PCM_INFO_BATCH 0x00000010 /* double buffering */ #define SNDRV_PCM_INFO_SYNC_APPLPTR 0x00000020 /* need the explicit sync of appl_ptr update */ +#define SNDRV_PCM_INFO_PERFECT_DRAIN 0x00000040 /* silencing at the end of stream is not required */ #define SNDRV_PCM_INFO_INTERLEAVED 0x00000100 /* channels are interleaved */ #define SNDRV_PCM_INFO_NONINTERLEAVED 0x00000200 /* channels are not interleaved */ #define SNDRV_PCM_INFO_COMPLEX 0x00000400 /* complex frame organization (mmap only) */ @@ -383,6 +384,9 @@ typedef int snd_pcm_hw_param_t; #define SNDRV_PCM_HW_PARAMS_NORESAMPLE (1<<0) /* avoid rate resampling */ #define SNDRV_PCM_HW_PARAMS_EXPORT_BUFFER (1<<1) /* export buffer */ #define SNDRV_PCM_HW_PARAMS_NO_PERIOD_WAKEUP (1<<2) /* disable period wakeups */ +#define SNDRV_PCM_HW_PARAMS_NO_DRAIN_SILENCE (1<<3) /* suppress drain with the filling + * of the silence samples + */ struct snd_interval { unsigned int min, max; -- cgit v1.2.3 From 99afb7cc8c44578615200ea4806b183e1e35a81d Mon Sep 17 00:00:00 2001 From: Alan Previn Date: Thu, 11 May 2023 16:17:35 -0700 Subject: drm/i915/pxp: Add ARB session creation and cleanup Add MTL's function for ARB session creation using PXP firmware version 4.3 ABI structure format. While relooking at the ARB session creation flow in intel_pxp_start, let's address missing UAPI documentation. Without actually changing backward compatible behavior, update i915's drm-uapi comments that describe the possible error values when creating a context with I915_CONTEXT_PARAM_PROTECTED_CONTENT: Since the first merge of PXP support on ADL, i915 returns -ENXIO if a dependency such as firmware or component driver was yet to be loaded or returns -EIO if the creation attempt failed when requested by the PXP firmware (specific firmware error responses are reported in dmesg). Add MTL's function for ARB session invalidation but this reuses PXP firmware version 4.2 ABI structure format. For both cases, in the back-end gsccs functions for sending messages to the firmware inspect the GSC-CS-Mem-Header's pending-bit which means the GSC firmware is busy and we should retry. Given the last hw requirement, lets also update functions in front-end layer that wait for session creation or teardown completion to use new worst case timeout periods. Signed-off-by: Alan Previn Reviewed-by: Daniele Ceraolo Spurio Signed-off-by: Radhakrishna Sripada Link: https://patchwork.freedesktop.org/patch/msgid/20230511231738.1077674-6-alan.previn.teres.alexis@intel.com --- drivers/gpu/drm/i915/pxp/intel_pxp.c | 27 ++++- .../gpu/drm/i915/pxp/intel_pxp_cmd_interface_43.h | 21 ++++ drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.c | 130 +++++++++++++++++++++ drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.h | 12 +- drivers/gpu/drm/i915/pxp/intel_pxp_session.c | 11 +- include/uapi/drm/i915_drm.h | 15 +++ 6 files changed, 209 insertions(+), 7 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp.c b/drivers/gpu/drm/i915/pxp/intel_pxp.c index 8949d4be7882..b600d68de2a4 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp.c +++ b/drivers/gpu/drm/i915/pxp/intel_pxp.c @@ -291,6 +291,8 @@ static bool pxp_component_bound(struct intel_pxp *pxp) static int __pxp_global_teardown_final(struct intel_pxp *pxp) { + int timeout; + if (!pxp->arb_is_valid) return 0; /* @@ -300,7 +302,12 @@ static int __pxp_global_teardown_final(struct intel_pxp *pxp) intel_pxp_mark_termination_in_progress(pxp); intel_pxp_terminate(pxp, false); - if (!wait_for_completion_timeout(&pxp->termination, msecs_to_jiffies(250))) + if (HAS_ENGINE(pxp->ctrl_gt, GSC0)) + timeout = GSCFW_MAX_ROUND_TRIP_LATENCY_MS; + else + timeout = 250; + + if (!wait_for_completion_timeout(&pxp->termination, msecs_to_jiffies(timeout))) return -ETIMEDOUT; return 0; @@ -308,6 +315,8 @@ static int __pxp_global_teardown_final(struct intel_pxp *pxp) static int __pxp_global_teardown_restart(struct intel_pxp *pxp) { + int timeout; + if (pxp->arb_is_valid) return 0; /* @@ -316,7 +325,12 @@ static int __pxp_global_teardown_restart(struct intel_pxp *pxp) */ pxp_queue_termination(pxp); - if (!wait_for_completion_timeout(&pxp->termination, msecs_to_jiffies(250))) + if (HAS_ENGINE(pxp->ctrl_gt, GSC0)) + timeout = GSCFW_MAX_ROUND_TRIP_LATENCY_MS; + else + timeout = 250; + + if (!wait_for_completion_timeout(&pxp->termination, msecs_to_jiffies(timeout))) return -ETIMEDOUT; return 0; @@ -354,8 +368,13 @@ int intel_pxp_start(struct intel_pxp *pxp) if (!intel_pxp_is_enabled(pxp)) return -ENODEV; - if (wait_for(pxp_component_bound(pxp), 250)) - return -ENXIO; + if (HAS_ENGINE(pxp->ctrl_gt, GSC0)) { + if (wait_for(intel_pxp_gsccs_is_ready_for_sessions(pxp), 250)) + return -ENXIO; + } else { + if (wait_for(pxp_component_bound(pxp), 250)) + return -ENXIO; + } mutex_lock(&pxp->arb_mutex); diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_cmd_interface_43.h b/drivers/gpu/drm/i915/pxp/intel_pxp_cmd_interface_43.h index c65ada99e54f..09777719cd84 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_cmd_interface_43.h +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_cmd_interface_43.h @@ -11,6 +11,7 @@ /* PXP-Cmd-Op definitions */ #define PXP43_CMDID_START_HUC_AUTH 0x0000003A +#define PXP43_CMDID_INIT_SESSION 0x00000036 /* PXP-Packet sizes for MTL's GSCCS-HECI instruction */ #define PXP43_MAX_HECI_INOUT_SIZE (SZ_32K) @@ -26,4 +27,24 @@ struct pxp43_start_huc_auth_out { struct pxp_cmd_header header; } __packed; +/* PXP-Input-Packet: Init PXP session */ +struct pxp43_create_arb_in { + struct pxp_cmd_header header; + /* header.stream_id fields for vesion 4.3 of Init PXP session: */ + #define PXP43_INIT_SESSION_VALID BIT(0) + #define PXP43_INIT_SESSION_APPTYPE BIT(1) + #define PXP43_INIT_SESSION_APPID GENMASK(17, 2) + u32 protection_mode; + #define PXP43_INIT_SESSION_PROTECTION_ARB 0x2 + u32 sub_session_id; + u32 init_flags; + u32 rsvd[12]; +} __packed; + +/* PXP-Input-Packet: Init PXP session */ +struct pxp43_create_arb_out { + struct pxp_cmd_header header; + u32 rsvd[8]; +} __packed; + #endif /* __INTEL_PXP_FW_INTERFACE_43_H__ */ diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.c b/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.c index 16e3b73d0653..4bc276daca16 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.c +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.c @@ -6,13 +6,46 @@ #include "gem/i915_gem_internal.h" #include "gt/intel_context.h" +#include "gt/uc/intel_gsc_fw.h" #include "gt/uc/intel_gsc_uc_heci_cmd_submit.h" #include "i915_drv.h" +#include "intel_pxp_cmd_interface_42.h" #include "intel_pxp_cmd_interface_43.h" #include "intel_pxp_gsccs.h" #include "intel_pxp_types.h" +static bool +is_fw_err_platform_config(u32 type) +{ + switch (type) { + case PXP_STATUS_ERROR_API_VERSION: + case PXP_STATUS_PLATFCONFIG_KF1_NOVERIF: + case PXP_STATUS_PLATFCONFIG_KF1_BAD: + return true; + default: + break; + } + return false; +} + +static const char * +fw_err_to_string(u32 type) +{ + switch (type) { + case PXP_STATUS_ERROR_API_VERSION: + return "ERR_API_VERSION"; + case PXP_STATUS_NOT_READY: + return "ERR_NOT_READY"; + case PXP_STATUS_PLATFCONFIG_KF1_NOVERIF: + case PXP_STATUS_PLATFCONFIG_KF1_BAD: + return "ERR_PLATFORM_CONFIG"; + default: + break; + } + return NULL; +} + static int gsccs_send_message(struct intel_pxp *pxp, void *msg_in, size_t msg_in_size, @@ -152,6 +185,103 @@ gsccs_send_message_retry_complete(struct intel_pxp *pxp, return ret; } +bool intel_pxp_gsccs_is_ready_for_sessions(struct intel_pxp *pxp) +{ + /* + * GSC-fw loading, HuC-fw loading, HuC-fw authentication and + * GSC-proxy init flow (requiring an mei component driver) + * must all occur first before we can start requesting for PXP + * sessions. Checking for completion on HuC authentication and + * gsc-proxy init flow (the last set of dependencies that + * are out of order) will suffice. + */ + if (intel_huc_is_authenticated(&pxp->ctrl_gt->uc.huc) && + intel_gsc_uc_fw_proxy_init_done(&pxp->ctrl_gt->uc.gsc)) + return true; + + return false; +} + +int intel_pxp_gsccs_create_session(struct intel_pxp *pxp, + int arb_session_id) +{ + struct drm_i915_private *i915 = pxp->ctrl_gt->i915; + struct pxp43_create_arb_in msg_in = {0}; + struct pxp43_create_arb_out msg_out = {0}; + int ret; + + msg_in.header.api_version = PXP_APIVER(4, 3); + msg_in.header.command_id = PXP43_CMDID_INIT_SESSION; + msg_in.header.stream_id = (FIELD_PREP(PXP43_INIT_SESSION_APPID, arb_session_id) | + FIELD_PREP(PXP43_INIT_SESSION_VALID, 1) | + FIELD_PREP(PXP43_INIT_SESSION_APPTYPE, 0)); + msg_in.header.buffer_len = sizeof(msg_in) - sizeof(msg_in.header); + msg_in.protection_mode = PXP43_INIT_SESSION_PROTECTION_ARB; + + ret = gsccs_send_message_retry_complete(pxp, + &msg_in, sizeof(msg_in), + &msg_out, sizeof(msg_out), NULL); + if (ret) { + drm_err(&i915->drm, "Failed to init session %d, ret=[%d]\n", arb_session_id, ret); + } else if (msg_out.header.status != 0) { + if (is_fw_err_platform_config(msg_out.header.status)) { + drm_info_once(&i915->drm, + "PXP init-session-%d failed due to BIOS/SOC:0x%08x:%s\n", + arb_session_id, msg_out.header.status, + fw_err_to_string(msg_out.header.status)); + } else { + drm_dbg(&i915->drm, "PXP init-session-%d failed 0x%08x:%st:\n", + arb_session_id, msg_out.header.status, + fw_err_to_string(msg_out.header.status)); + drm_dbg(&i915->drm, " cmd-detail: ID=[0x%08x],API-Ver-[0x%08x]\n", + msg_in.header.command_id, msg_in.header.api_version); + } + } + + return ret; +} + +void intel_pxp_gsccs_end_arb_fw_session(struct intel_pxp *pxp, u32 session_id) +{ + struct drm_i915_private *i915 = pxp->ctrl_gt->i915; + struct pxp42_inv_stream_key_in msg_in = {0}; + struct pxp42_inv_stream_key_out msg_out = {0}; + int ret = 0; + + /* + * Stream key invalidation reuses the same version 4.2 input/output + * command format but firmware requires 4.3 API interaction + */ + msg_in.header.api_version = PXP_APIVER(4, 3); + msg_in.header.command_id = PXP42_CMDID_INVALIDATE_STREAM_KEY; + msg_in.header.buffer_len = sizeof(msg_in) - sizeof(msg_in.header); + + msg_in.header.stream_id = FIELD_PREP(PXP_CMDHDR_EXTDATA_SESSION_VALID, 1); + msg_in.header.stream_id |= FIELD_PREP(PXP_CMDHDR_EXTDATA_APP_TYPE, 0); + msg_in.header.stream_id |= FIELD_PREP(PXP_CMDHDR_EXTDATA_SESSION_ID, session_id); + + ret = gsccs_send_message_retry_complete(pxp, + &msg_in, sizeof(msg_in), + &msg_out, sizeof(msg_out), NULL); + if (ret) { + drm_err(&i915->drm, "Failed to inv-stream-key-%u, ret=[%d]\n", + session_id, ret); + } else if (msg_out.header.status != 0) { + if (is_fw_err_platform_config(msg_out.header.status)) { + drm_info_once(&i915->drm, + "PXP inv-stream-key-%u failed due to BIOS/SOC :0x%08x:%s\n", + session_id, msg_out.header.status, + fw_err_to_string(msg_out.header.status)); + } else { + drm_dbg(&i915->drm, "PXP inv-stream-key-%u failed 0x%08x:%s:\n", + session_id, msg_out.header.status, + fw_err_to_string(msg_out.header.status)); + drm_dbg(&i915->drm, " cmd-detail: ID=[0x%08x],API-Ver-[0x%08x]\n", + msg_in.header.command_id, msg_in.header.api_version); + } + } +} + static void gsccs_cleanup_fw_host_session_handle(struct intel_pxp *pxp) { diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.h b/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.h index bd1c028bc80f..298ad38e6c7d 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.h +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.h @@ -10,14 +10,22 @@ struct intel_pxp; -#define GSC_REPLY_LATENCY_MS 200 +#define GSC_REPLY_LATENCY_MS 210 +/* + * Max FW response time is 200ms, to which we add 10ms to account for overhead + * such as request preparation, GuC submission to hw and pipeline completion times. + */ #define GSC_PENDING_RETRY_MAXCOUNT 40 #define GSC_PENDING_RETRY_PAUSE_MS 50 +#define GSCFW_MAX_ROUND_TRIP_LATENCY_MS (GSC_PENDING_RETRY_MAXCOUNT * GSC_PENDING_RETRY_PAUSE_MS) #ifdef CONFIG_DRM_I915_PXP void intel_pxp_gsccs_fini(struct intel_pxp *pxp); int intel_pxp_gsccs_init(struct intel_pxp *pxp); +int intel_pxp_gsccs_create_session(struct intel_pxp *pxp, int arb_session_id); +void intel_pxp_gsccs_end_arb_fw_session(struct intel_pxp *pxp, u32 arb_session_id); + #else static inline void intel_pxp_gsccs_fini(struct intel_pxp *pxp) { @@ -30,4 +38,6 @@ static inline int intel_pxp_gsccs_init(struct intel_pxp *pxp) #endif +bool intel_pxp_gsccs_is_ready_for_sessions(struct intel_pxp *pxp); + #endif /*__INTEL_PXP_GSCCS_H__ */ diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_session.c b/drivers/gpu/drm/i915/pxp/intel_pxp_session.c index 7899079e17b0..e4d8242302c5 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_session.c +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_session.c @@ -7,6 +7,7 @@ #include "intel_pxp.h" #include "intel_pxp_cmd.h" +#include "intel_pxp_gsccs.h" #include "intel_pxp_session.h" #include "intel_pxp_tee.h" #include "intel_pxp_types.h" @@ -62,7 +63,10 @@ static int pxp_create_arb_session(struct intel_pxp *pxp) return -EEXIST; } - ret = intel_pxp_tee_cmd_create_arb_session(pxp, ARB_SESSION); + if (HAS_ENGINE(pxp->ctrl_gt, GSC0)) + ret = intel_pxp_gsccs_create_session(pxp, ARB_SESSION); + else + ret = intel_pxp_tee_cmd_create_arb_session(pxp, ARB_SESSION); if (ret) { drm_err(>->i915->drm, "tee cmd for arb session creation failed\n"); return ret; @@ -106,7 +110,10 @@ static int pxp_terminate_arb_session_and_global(struct intel_pxp *pxp) intel_uncore_write(gt->uncore, KCR_GLOBAL_TERMINATE(pxp->kcr_base), 1); - intel_pxp_tee_end_arb_fw_session(pxp, ARB_SESSION); + if (HAS_ENGINE(gt, GSC0)) + intel_pxp_gsccs_end_arb_fw_session(pxp, ARB_SESSION); + else + intel_pxp_tee_end_arb_fw_session(pxp, ARB_SESSION); return ret; } diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index dba7c5a5b25e..0aa3190e7654 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -2096,6 +2096,21 @@ struct drm_i915_gem_context_param { * * -ENODEV: feature not available * -EPERM: trying to mark a recoverable or not bannable context as protected + * -ENXIO: A dependency such as a component driver or firmware is not yet + * loaded so user space may need to attempt again. Depending on the + * device, this error may be reported if protected context creation is + * attempted very early after kernel start because the internal timeout + * waiting for such dependencies is not guaranteed to be larger than + * required (numbers differ depending on system and kernel config): + * - ADL/RPL: dependencies may take up to 3 seconds from kernel start + * while context creation internal timeout is 250 milisecs + * - MTL: dependencies may take up to 8 seconds from kernel start + * while context creation internal timeout is 250 milisecs + * NOTE: such dependencies happen once, so a subsequent call to create a + * protected context after a prior successful call will not experience + * such timeouts and will not return -ENXIO (unless the driver is reloaded, + * or, depending on the device, resumes from a suspended state). + * -EIO: The firmware did not succeed in creating the protected context. */ #define I915_CONTEXT_PARAM_PROTECTED_CONTENT 0xd /* Must be kept compact -- no holes and well documented */ -- cgit v1.2.3 From d1da138f245d4fb46b21d2ddb19504a2831d813f Mon Sep 17 00:00:00 2001 From: Alan Previn Date: Thu, 11 May 2023 16:17:36 -0700 Subject: drm/i915/uapi/pxp: Add a GET_PARAM for PXP Because of the additional firmware, component-driver and initialization depedencies required on MTL platform before a PXP context can be created, UMD calling for PXP creation as a way to get-caps can take a long time. An actual real world customer stack has seen this happen in the 4-to-8 second range after the kernel starts (which sees MESA's init appear in the middle of this range as the compositor comes up). To avoid unncessary delays experienced by the UMD for get-caps purposes, add a GET_PARAM for I915_PARAM_PXP_SUPPORT. However, some failures can still occur after all the depedencies are met (such as firmware init flow failure, bios configurations or SOC fusing not allowing PXP enablement). Those scenarios will only be known to user space when it attempts creating a PXP context and is documented in the GEM UAPI headers. While making this change, create a helper that is common to both GET_PARAM caller and intel_pxp_start since the latter does similar checks. Signed-off-by: Alan Previn Reviewed-by: Daniele Ceraolo Spurio Acked-by: Jordan Justen Signed-off-by: Radhakrishna Sripada Link: https://patchwork.freedesktop.org/patch/msgid/20230511231738.1077674-7-alan.previn.teres.alexis@intel.com --- drivers/gpu/drm/i915/i915_getparam.c | 7 +++++++ drivers/gpu/drm/i915/pxp/intel_pxp.c | 29 ++++++++++++++++++++++------- drivers/gpu/drm/i915/pxp/intel_pxp.h | 1 + include/uapi/drm/i915_drm.h | 19 +++++++++++++++++++ 4 files changed, 49 insertions(+), 7 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/i915/i915_getparam.c b/drivers/gpu/drm/i915/i915_getparam.c index 2238e096c957..6f11d7eaa91a 100644 --- a/drivers/gpu/drm/i915/i915_getparam.c +++ b/drivers/gpu/drm/i915/i915_getparam.c @@ -5,6 +5,8 @@ #include "gem/i915_gem_mman.h" #include "gt/intel_engine_user.h" +#include "pxp/intel_pxp.h" + #include "i915_cmd_parser.h" #include "i915_drv.h" #include "i915_getparam.h" @@ -102,6 +104,11 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data, if (value < 0) return value; break; + case I915_PARAM_PXP_STATUS: + value = intel_pxp_get_readiness_status(i915->pxp); + if (value < 0) + return value; + break; case I915_PARAM_MMAP_GTT_VERSION: /* Though we've started our numbering from 1, and so class all * earlier versions as 0, in effect their value is undefined as diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp.c b/drivers/gpu/drm/i915/pxp/intel_pxp.c index b600d68de2a4..f143eadbc253 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp.c +++ b/drivers/gpu/drm/i915/pxp/intel_pxp.c @@ -358,23 +358,38 @@ void intel_pxp_end(struct intel_pxp *pxp) } /* - * the arb session is restarted from the irq work when we receive the - * termination completion interrupt + * this helper is used by both intel_pxp_start and by + * the GET_PARAM IOCTL that user space calls. Thus, the + * return values here should match the UAPI spec. */ -int intel_pxp_start(struct intel_pxp *pxp) +int intel_pxp_get_readiness_status(struct intel_pxp *pxp) { - int ret = 0; - if (!intel_pxp_is_enabled(pxp)) return -ENODEV; if (HAS_ENGINE(pxp->ctrl_gt, GSC0)) { if (wait_for(intel_pxp_gsccs_is_ready_for_sessions(pxp), 250)) - return -ENXIO; + return 2; } else { if (wait_for(pxp_component_bound(pxp), 250)) - return -ENXIO; + return 2; } + return 1; +} + +/* + * the arb session is restarted from the irq work when we receive the + * termination completion interrupt + */ +int intel_pxp_start(struct intel_pxp *pxp) +{ + int ret = 0; + + ret = intel_pxp_get_readiness_status(pxp); + if (ret < 0) + return ret; + else if (ret > 1) + return -EIO; /* per UAPI spec, user may retry later */ mutex_lock(&pxp->arb_mutex); diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp.h b/drivers/gpu/drm/i915/pxp/intel_pxp.h index 3ded0890cd27..17e6dbc86b38 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp.h +++ b/drivers/gpu/drm/i915/pxp/intel_pxp.h @@ -26,6 +26,7 @@ void intel_pxp_fini_hw(struct intel_pxp *pxp); void intel_pxp_mark_termination_in_progress(struct intel_pxp *pxp); void intel_pxp_tee_end_arb_fw_session(struct intel_pxp *pxp, u32 arb_session_id); +int intel_pxp_get_readiness_status(struct intel_pxp *pxp); int intel_pxp_start(struct intel_pxp *pxp); void intel_pxp_end(struct intel_pxp *pxp); diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 0aa3190e7654..ba40855dbc93 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -771,6 +771,25 @@ typedef struct drm_i915_irq_wait { */ #define I915_PARAM_OA_TIMESTAMP_FREQUENCY 57 +/* + * Query the status of PXP support in i915. + * + * The query can fail in the following scenarios with the listed error codes: + * -ENODEV = PXP support is not available on the GPU device or in the + * kernel due to missing component drivers or kernel configs. + * + * If the IOCTL is successful, the returned parameter will be set to one of + * the following values: + * 1 = PXP feature is supported and is ready for use. + * 2 = PXP feature is supported but should be ready soon (pending + * initialization of non-i915 system dependencies). + * + * NOTE: When param is supported (positive return values), user space should + * still refer to the GEM PXP context-creation UAPI header specs to be + * aware of possible failure due to system state machine at the time. + */ +#define I915_PARAM_PXP_STATUS 58 + /* Must be kept compact -- no holes and well documented */ /** -- cgit v1.2.3 From eefca7ec514262aef08d0ef261552f2f604bd851 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 11 May 2023 11:49:50 -0400 Subject: net/handshake: Enable the SNI extension to work properly Enable the upper layer protocol to specify the SNI peername. This avoids the need for tlshd to use a DNS lookup, which can return a hostname that doesn't match the incoming certificate's SubjectName. Fixes: 2fd5532044a8 ("net/handshake: Add a kernel API for requesting a TLSv1.3 handshake") Reviewed-by: Simon Horman Signed-off-by: Chuck Lever Signed-off-by: David S. Miller --- Documentation/netlink/specs/handshake.yaml | 4 ++++ Documentation/networking/tls-handshake.rst | 5 +++++ include/net/handshake.h | 1 + include/uapi/linux/handshake.h | 1 + net/handshake/tlshd.c | 8 ++++++++ 5 files changed, 19 insertions(+) (limited to 'include/uapi') diff --git a/Documentation/netlink/specs/handshake.yaml b/Documentation/netlink/specs/handshake.yaml index 614f1a585511..6d89e30f5fd5 100644 --- a/Documentation/netlink/specs/handshake.yaml +++ b/Documentation/netlink/specs/handshake.yaml @@ -68,6 +68,9 @@ attribute-sets: type: nest nested-attributes: x509 multi-attr: true + - + name: peername + type: string - name: done attributes: @@ -105,6 +108,7 @@ operations: - auth-mode - peer-identity - certificate + - peername - name: done doc: Handler reports handshake completion diff --git a/Documentation/networking/tls-handshake.rst b/Documentation/networking/tls-handshake.rst index a2817a88e905..6f5ea1646a47 100644 --- a/Documentation/networking/tls-handshake.rst +++ b/Documentation/networking/tls-handshake.rst @@ -53,6 +53,7 @@ fills in a structure that contains the parameters of the request: struct socket *ta_sock; tls_done_func_t ta_done; void *ta_data; + const char *ta_peername; unsigned int ta_timeout_ms; key_serial_t ta_keyring; key_serial_t ta_my_cert; @@ -71,6 +72,10 @@ instantiated a struct file in sock->file. has completed. Further explanation of this function is in the "Handshake Completion" sesction below. +The consumer can provide a NUL-terminated hostname in the @ta_peername +field that is sent as part of ClientHello. If no peername is provided, +the DNS hostname associated with the server's IP address is used instead. + The consumer can fill in the @ta_timeout_ms field to force the servicing handshake agent to exit after a number of milliseconds. This enables the socket to be fully closed once both the kernel and the handshake agent diff --git a/include/net/handshake.h b/include/net/handshake.h index 3352b1ab43b3..2e26e436e85f 100644 --- a/include/net/handshake.h +++ b/include/net/handshake.h @@ -24,6 +24,7 @@ struct tls_handshake_args { struct socket *ta_sock; tls_done_func_t ta_done; void *ta_data; + const char *ta_peername; unsigned int ta_timeout_ms; key_serial_t ta_keyring; key_serial_t ta_my_cert; diff --git a/include/uapi/linux/handshake.h b/include/uapi/linux/handshake.h index 1de4d0b95325..3d7ea58778c9 100644 --- a/include/uapi/linux/handshake.h +++ b/include/uapi/linux/handshake.h @@ -44,6 +44,7 @@ enum { HANDSHAKE_A_ACCEPT_AUTH_MODE, HANDSHAKE_A_ACCEPT_PEER_IDENTITY, HANDSHAKE_A_ACCEPT_CERTIFICATE, + HANDSHAKE_A_ACCEPT_PEERNAME, __HANDSHAKE_A_ACCEPT_MAX, HANDSHAKE_A_ACCEPT_MAX = (__HANDSHAKE_A_ACCEPT_MAX - 1) diff --git a/net/handshake/tlshd.c b/net/handshake/tlshd.c index fcbeb63b4eb1..b735f5cced2f 100644 --- a/net/handshake/tlshd.c +++ b/net/handshake/tlshd.c @@ -31,6 +31,7 @@ struct tls_handshake_req { int th_type; unsigned int th_timeout_ms; int th_auth_mode; + const char *th_peername; key_serial_t th_keyring; key_serial_t th_certificate; key_serial_t th_privkey; @@ -48,6 +49,7 @@ tls_handshake_req_init(struct handshake_req *req, treq->th_timeout_ms = args->ta_timeout_ms; treq->th_consumer_done = args->ta_done; treq->th_consumer_data = args->ta_data; + treq->th_peername = args->ta_peername; treq->th_keyring = args->ta_keyring; treq->th_num_peerids = 0; treq->th_certificate = TLS_NO_CERT; @@ -214,6 +216,12 @@ static int tls_handshake_accept(struct handshake_req *req, ret = nla_put_u32(msg, HANDSHAKE_A_ACCEPT_MESSAGE_TYPE, treq->th_type); if (ret < 0) goto out_cancel; + if (treq->th_peername) { + ret = nla_put_string(msg, HANDSHAKE_A_ACCEPT_PEERNAME, + treq->th_peername); + if (ret < 0) + goto out_cancel; + } if (treq->th_timeout_ms) { ret = nla_put_u32(msg, HANDSHAKE_A_ACCEPT_TIMEOUT, treq->th_timeout_ms); if (ret < 0) -- cgit v1.2.3 From 69474a8a5837be63f13c6f60a7d622b98ed5c539 Mon Sep 17 00:00:00 2001 From: Vladimir Nikishkin Date: Fri, 12 May 2023 11:40:33 +0800 Subject: net: vxlan: Add nolocalbypass option to vxlan. If a packet needs to be encapsulated towards a local destination IP, the packet will undergo a "local bypass" and be injected into the Rx path as if it was received by the target VXLAN device without undergoing encapsulation. If such a device does not exist, the packet will be dropped. There are scenarios where we do not want to perform such a bypass, but instead want the packet to be encapsulated and locally received by a user space program for post-processing. To that end, add a new VXLAN device attribute that controls whether a "local bypass" is performed or not. Default to performing a bypass to maintain existing behavior. Signed-off-by: Vladimir Nikishkin Reviewed-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/vxlan/vxlan_core.c | 21 +++++++++++++++++++-- include/net/vxlan.h | 4 +++- include/uapi/linux/if_link.h | 1 + 3 files changed, 23 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 561fe1b314f5..78744549c1b3 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -2352,7 +2352,8 @@ static int encap_bypass_if_local(struct sk_buff *skb, struct net_device *dev, #endif /* Bypass encapsulation if the destination is local */ if (rt_flags & RTCF_LOCAL && - !(rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))) { + !(rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) && + vxlan->cfg.flags & VXLAN_F_LOCALBYPASS) { struct vxlan_dev *dst_vxlan; dst_release(dst); @@ -3172,6 +3173,7 @@ static void vxlan_raw_setup(struct net_device *dev) } static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = { + [IFLA_VXLAN_UNSPEC] = { .strict_start_type = IFLA_VXLAN_LOCALBYPASS }, [IFLA_VXLAN_ID] = { .type = NLA_U32 }, [IFLA_VXLAN_GROUP] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_VXLAN_GROUP6] = { .len = sizeof(struct in6_addr) }, @@ -3202,6 +3204,7 @@ static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = { [IFLA_VXLAN_TTL_INHERIT] = { .type = NLA_FLAG }, [IFLA_VXLAN_DF] = { .type = NLA_U8 }, [IFLA_VXLAN_VNIFILTER] = { .type = NLA_U8 }, + [IFLA_VXLAN_LOCALBYPASS] = NLA_POLICY_MAX(NLA_U8, 1), }; static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[], @@ -4011,6 +4014,17 @@ static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[], conf->flags |= VXLAN_F_UDP_ZERO_CSUM_TX; } + if (data[IFLA_VXLAN_LOCALBYPASS]) { + err = vxlan_nl2flag(conf, data, IFLA_VXLAN_LOCALBYPASS, + VXLAN_F_LOCALBYPASS, changelink, + true, extack); + if (err) + return err; + } else if (!changelink) { + /* default to local bypass on a new device */ + conf->flags |= VXLAN_F_LOCALBYPASS; + } + if (data[IFLA_VXLAN_UDP_ZERO_CSUM6_TX]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_UDP_ZERO_CSUM6_TX, VXLAN_F_UDP_ZERO_CSUM6_TX, changelink, @@ -4232,6 +4246,7 @@ static size_t vxlan_get_size(const struct net_device *dev) nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_ZERO_CSUM6_RX */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_REMCSUM_TX */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_REMCSUM_RX */ + nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_LOCALBYPASS */ 0; } @@ -4308,7 +4323,9 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev) nla_put_u8(skb, IFLA_VXLAN_REMCSUM_TX, !!(vxlan->cfg.flags & VXLAN_F_REMCSUM_TX)) || nla_put_u8(skb, IFLA_VXLAN_REMCSUM_RX, - !!(vxlan->cfg.flags & VXLAN_F_REMCSUM_RX))) + !!(vxlan->cfg.flags & VXLAN_F_REMCSUM_RX)) || + nla_put_u8(skb, IFLA_VXLAN_LOCALBYPASS, + !!(vxlan->cfg.flags & VXLAN_F_LOCALBYPASS))) goto nla_put_failure; if (nla_put(skb, IFLA_VXLAN_PORT_RANGE, sizeof(ports), &ports)) diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 20bd7d893e10..0be91ca78d3a 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -328,6 +328,7 @@ struct vxlan_dev { #define VXLAN_F_TTL_INHERIT 0x10000 #define VXLAN_F_VNIFILTER 0x20000 #define VXLAN_F_MDB 0x40000 +#define VXLAN_F_LOCALBYPASS 0x80000 /* Flags that are used in the receive path. These flags must match in * order for a socket to be shareable @@ -348,7 +349,8 @@ struct vxlan_dev { VXLAN_F_UDP_ZERO_CSUM6_TX | \ VXLAN_F_UDP_ZERO_CSUM6_RX | \ VXLAN_F_COLLECT_METADATA | \ - VXLAN_F_VNIFILTER) + VXLAN_F_VNIFILTER | \ + VXLAN_F_LOCALBYPASS) struct net_device *vxlan_dev_create(struct net *net, const char *name, u8 name_assign_type, struct vxlan_config *conf); diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 4ac1000b0ef2..0f6a0fe09bdb 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -828,6 +828,7 @@ enum { IFLA_VXLAN_TTL_INHERIT, IFLA_VXLAN_DF, IFLA_VXLAN_VNIFILTER, /* only applicable with COLLECT_METADATA mode */ + IFLA_VXLAN_LOCALBYPASS, __IFLA_VXLAN_MAX }; #define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1) -- cgit v1.2.3 From c7c12de893f808bd7c1215fe9056262295e5203b Mon Sep 17 00:00:00 2001 From: Juha-Pekka Heikkila Date: Sun, 14 May 2023 21:42:39 +0300 Subject: drm/fourcc: define Intel Meteorlake related ccs modifiers Add Tile4 type ccs modifiers with aux buffer needed for MTL Bspec: 49251, 49252, 49253 Cc: dri-devel@lists.freedesktop.org Cc: Jani Nikula Signed-off-by: Juha-Pekka Heikkila Reviewed-by: Matt Atwood Acked-by: Thomas Zimmermann Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/20230514184240.6184-1-juhapekka.heikkila@gmail.com --- include/uapi/drm/drm_fourcc.h | 43 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index de703c6be969..8db7fd3f743e 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -657,6 +657,49 @@ extern "C" { */ #define I915_FORMAT_MOD_4_TILED_DG2_RC_CCS_CC fourcc_mod_code(INTEL, 12) +/* + * Intel Color Control Surfaces (CCS) for display ver. 14 render compression. + * + * The main surface is tile4 and at plane index 0, the CCS is linear and + * at index 1. A 64B CCS cache line corresponds to an area of 4x1 tiles in + * main surface. In other words, 4 bits in CCS map to a main surface cache + * line pair. The main surface pitch is required to be a multiple of four + * tile4 widths. + */ +#define I915_FORMAT_MOD_4_TILED_MTL_RC_CCS fourcc_mod_code(INTEL, 13) + +/* + * Intel Color Control Surfaces (CCS) for display ver. 14 media compression + * + * The main surface is tile4 and at plane index 0, the CCS is linear and + * at index 1. A 64B CCS cache line corresponds to an area of 4x1 tiles in + * main surface. In other words, 4 bits in CCS map to a main surface cache + * line pair. The main surface pitch is required to be a multiple of four + * tile4 widths. For semi-planar formats like NV12, CCS planes follow the + * Y and UV planes i.e., planes 0 and 1 are used for Y and UV surfaces, + * planes 2 and 3 for the respective CCS. + */ +#define I915_FORMAT_MOD_4_TILED_MTL_MC_CCS fourcc_mod_code(INTEL, 14) + +/* + * Intel Color Control Surface with Clear Color (CCS) for display ver. 14 render + * compression. + * + * The main surface is tile4 and is at plane index 0 whereas CCS is linear + * and at index 1. The clear color is stored at index 2, and the pitch should + * be ignored. The clear color structure is 256 bits. The first 128 bits + * represents Raw Clear Color Red, Green, Blue and Alpha color each represented + * by 32 bits. The raw clear color is consumed by the 3d engine and generates + * the converted clear color of size 64 bits. The first 32 bits store the Lower + * Converted Clear Color value and the next 32 bits store the Higher Converted + * Clear Color value when applicable. The Converted Clear Color values are + * consumed by the DE. The last 64 bits are used to store Color Discard Enable + * and Depth Clear Value Valid which are ignored by the DE. A CCS cache line + * corresponds to an area of 4x1 tiles in the main surface. The main surface + * pitch is required to be a multiple of 4 tile widths. + */ +#define I915_FORMAT_MOD_4_TILED_MTL_RC_CCS_CC fourcc_mod_code(INTEL, 15) + /* * Tiled, NV12MT, grouped in 64 (pixels) x 32 (lines) -sized macroblocks * -- cgit v1.2.3 From 1298bc978afba0a507cedd0a91e53267ca152804 Mon Sep 17 00:00:00 2001 From: Oswald Buddenhagen Date: Sun, 14 May 2023 19:03:22 +0200 Subject: ALSA: emu10k1: enable bit-exact playback, part 1: DSP attenuation Fractional multiplication with the maximal value 2^31-1 causes some tiny distortion. Instead, we want to multiply with the full 2^31. The catch is of course that this cannot be represented in the DSP's signed 32 bit registers. One way to deal with this is to encode 1.0 as a negative number and special-case it. As a matter of fact, the SbLive! code path already contained such code, though the controls never actually exercised it. A more efficient approach is to use negative values, which actually extend to -2^31. Accordingly, for all the volume adjustments we now use the MAC1 instruction which negates the X operand. The range of the controls in highres mode is extended downwards, so -1 is the new zero/mute. At maximal excursion, real zero is not mute any more, but I don't think anyone will notice this behavior change. ;-) That also required making the min/max/values in the control structs signed. This technically changes the user space interface, but it seems implausible that someone would notice - the numbers were actually treated as if they were signed anyway (and in the actual mixer iface they _are_). And without this change, the min value didn't even make sense in the first place (and no-one noticed, because it was always 0). Tested-by: Jonathan Dowland Signed-off-by: Oswald Buddenhagen Link: https://lore.kernel.org/r/20230514170323.3408834-7-oswald.buddenhagen@gmx.de Signed-off-by: Takashi Iwai --- include/sound/emu10k1.h | 6 +-- include/uapi/sound/emu10k1.h | 8 +-- sound/pci/emu10k1/emufx.c | 119 ++++++++++++++++++++----------------------- 3 files changed, 64 insertions(+), 69 deletions(-) (limited to 'include/uapi') diff --git a/include/sound/emu10k1.h b/include/sound/emu10k1.h index e9b1729ade60..8e27f7074230 100644 --- a/include/sound/emu10k1.h +++ b/include/sound/emu10k1.h @@ -1508,9 +1508,9 @@ struct snd_emu10k1_fx8010_ctl { unsigned int vcount; unsigned int count; /* count of GPR (1..16) */ unsigned short gpr[32]; /* GPR number(s) */ - unsigned int value[32]; - unsigned int min; /* minimum range */ - unsigned int max; /* maximum range */ + int value[32]; + int min; /* minimum range */ + int max; /* maximum range */ unsigned int translation; /* translation type (EMU10K1_GPR_TRANSLATION*) */ struct snd_kcontrol *kcontrol; }; diff --git a/include/uapi/sound/emu10k1.h b/include/uapi/sound/emu10k1.h index c8e131d6da00..4c32a116e7ad 100644 --- a/include/uapi/sound/emu10k1.h +++ b/include/uapi/sound/emu10k1.h @@ -308,6 +308,8 @@ struct snd_emu10k1_fx8010_info { #define EMU10K1_GPR_TRANSLATION_BASS 2 #define EMU10K1_GPR_TRANSLATION_TREBLE 3 #define EMU10K1_GPR_TRANSLATION_ONOFF 4 +#define EMU10K1_GPR_TRANSLATION_NEGATE 5 +#define EMU10K1_GPR_TRANSLATION_NEG_TABLE100 6 enum emu10k1_ctl_elem_iface { EMU10K1_CTL_ELEM_IFACE_MIXER = 2, /* virtual mixer device */ @@ -328,9 +330,9 @@ struct snd_emu10k1_fx8010_control_gpr { unsigned int vcount; /* visible count */ unsigned int count; /* count of GPR (1..16) */ unsigned short gpr[32]; /* GPR number(s) */ - unsigned int value[32]; /* initial values */ - unsigned int min; /* minimum range */ - unsigned int max; /* maximum range */ + int value[32]; /* initial values */ + int min; /* minimum range */ + int max; /* maximum range */ unsigned int translation; /* translation type (EMU10K1_GPR_TRANSLATION*) */ const unsigned int *tlv; }; diff --git a/sound/pci/emu10k1/emufx.c b/sound/pci/emu10k1/emufx.c index 9c9ffba7e591..4c9d67e72ae5 100644 --- a/sound/pci/emu10k1/emufx.c +++ b/sound/pci/emu10k1/emufx.c @@ -332,7 +332,7 @@ static int snd_emu10k1_gpr_ctl_put(struct snd_kcontrol *kcontrol, struct snd_ctl struct snd_emu10k1 *emu = snd_kcontrol_chip(kcontrol); struct snd_emu10k1_fx8010_ctl *ctl = (struct snd_emu10k1_fx8010_ctl *) kcontrol->private_value; - unsigned int nval, val; + int nval, val; unsigned int i, j; int change = 0; @@ -349,9 +349,16 @@ static int snd_emu10k1_gpr_ctl_put(struct snd_kcontrol *kcontrol, struct snd_ctl case EMU10K1_GPR_TRANSLATION_NONE: snd_emu10k1_ptr_write(emu, emu->gpr_base + ctl->gpr[i], 0, val); break; + case EMU10K1_GPR_TRANSLATION_NEGATE: + snd_emu10k1_ptr_write(emu, emu->gpr_base + ctl->gpr[i], 0, ~val); + break; case EMU10K1_GPR_TRANSLATION_TABLE100: snd_emu10k1_ptr_write(emu, emu->gpr_base + ctl->gpr[i], 0, db_table[val]); break; + case EMU10K1_GPR_TRANSLATION_NEG_TABLE100: + snd_emu10k1_ptr_write(emu, emu->gpr_base + ctl->gpr[i], 0, + val == 100 ? 0x80000000 : -(int)db_table[val]); + break; case EMU10K1_GPR_TRANSLATION_BASS: if ((ctl->count % 5) != 0 || (ctl->count / 5) != ctl->vcount) { change = -EIO; @@ -771,8 +778,10 @@ static int snd_emu10k1_verify_controls(struct snd_emu10k1 *emu, } switch (gctl->translation) { case EMU10K1_GPR_TRANSLATION_NONE: + case EMU10K1_GPR_TRANSLATION_NEGATE: break; case EMU10K1_GPR_TRANSLATION_TABLE100: + case EMU10K1_GPR_TRANSLATION_NEG_TABLE100: if (gctl->min != 0 || gctl->max != 100) { err = -EINVAL; goto __error; @@ -1137,44 +1146,44 @@ static int snd_emu10k1_ipcm_peek(struct snd_emu10k1 *emu, static void snd_emu10k1_init_mono_control(struct snd_emu10k1_fx8010_control_gpr *ctl, - const char *name, int gpr, int defval) + const char *name, int gpr, int defval) { ctl->id.iface = (__force int)SNDRV_CTL_ELEM_IFACE_MIXER; strcpy(ctl->id.name, name); ctl->vcount = ctl->count = 1; if (high_res_gpr_volume) { - ctl->min = 0; + ctl->min = -1; ctl->max = 0x7fffffff; ctl->tlv = snd_emu10k1_db_linear; - ctl->translation = EMU10K1_GPR_TRANSLATION_NONE; - defval = defval * 0x7fffffffLL / 100; + ctl->translation = EMU10K1_GPR_TRANSLATION_NEGATE; + defval = defval * 0x80000000LL / 100 - 1; } else { ctl->min = 0; ctl->max = 100; ctl->tlv = snd_emu10k1_db_scale1; - ctl->translation = EMU10K1_GPR_TRANSLATION_TABLE100; + ctl->translation = EMU10K1_GPR_TRANSLATION_NEG_TABLE100; } ctl->gpr[0] = gpr + 0; ctl->value[0] = defval; } static void snd_emu10k1_init_stereo_control(struct snd_emu10k1_fx8010_control_gpr *ctl, - const char *name, int gpr, int defval) + const char *name, int gpr, int defval) { ctl->id.iface = (__force int)SNDRV_CTL_ELEM_IFACE_MIXER; strcpy(ctl->id.name, name); ctl->vcount = ctl->count = 2; if (high_res_gpr_volume) { - ctl->min = 0; + ctl->min = -1; ctl->max = 0x7fffffff; ctl->tlv = snd_emu10k1_db_linear; - ctl->translation = EMU10K1_GPR_TRANSLATION_NONE; - defval = defval * 0x7fffffffLL / 100; + ctl->translation = EMU10K1_GPR_TRANSLATION_NEGATE; + defval = defval * 0x80000000LL / 100 - 1; } else { ctl->min = 0; ctl->max = 100; ctl->tlv = snd_emu10k1_db_scale1; - ctl->translation = EMU10K1_GPR_TRANSLATION_TABLE100; + ctl->translation = EMU10K1_GPR_TRANSLATION_NEG_TABLE100; } ctl->gpr[0] = gpr + 0; ctl->value[0] = defval; ctl->gpr[1] = gpr + 1; ctl->value[1] = defval; @@ -1293,36 +1302,36 @@ static int _snd_emu10k1_audigy_init_efx(struct snd_emu10k1 *emu) #if 1 /* PCM front Playback Volume (independent from stereo mix) - * playback = 0 + ( gpr * FXBUS_PCM_LEFT_FRONT >> 31) - * where gpr contains attenuation from corresponding mixer control + * playback = -gpr * FXBUS_PCM_LEFT_FRONT >> 31 + * where gpr contains negated attenuation from corresponding mixer control * (snd_emu10k1_init_stereo_control) */ - A_OP(icode, &ptr, iMAC0, A_GPR(playback), A_C_00000000, A_GPR(gpr), A_FXBUS(FXBUS_PCM_LEFT_FRONT)); - A_OP(icode, &ptr, iMAC0, A_GPR(playback+1), A_C_00000000, A_GPR(gpr+1), A_FXBUS(FXBUS_PCM_RIGHT_FRONT)); + A_OP(icode, &ptr, iMAC1, A_GPR(playback), A_C_00000000, A_GPR(gpr), A_FXBUS(FXBUS_PCM_LEFT_FRONT)); + A_OP(icode, &ptr, iMAC1, A_GPR(playback+1), A_C_00000000, A_GPR(gpr+1), A_FXBUS(FXBUS_PCM_RIGHT_FRONT)); snd_emu10k1_init_stereo_control(&controls[nctl++], "PCM Front Playback Volume", gpr, 100); gpr += 2; /* PCM Surround Playback (independent from stereo mix) */ - A_OP(icode, &ptr, iMAC0, A_GPR(playback+2), A_C_00000000, A_GPR(gpr), A_FXBUS(FXBUS_PCM_LEFT_REAR)); - A_OP(icode, &ptr, iMAC0, A_GPR(playback+3), A_C_00000000, A_GPR(gpr+1), A_FXBUS(FXBUS_PCM_RIGHT_REAR)); + A_OP(icode, &ptr, iMAC1, A_GPR(playback+2), A_C_00000000, A_GPR(gpr), A_FXBUS(FXBUS_PCM_LEFT_REAR)); + A_OP(icode, &ptr, iMAC1, A_GPR(playback+3), A_C_00000000, A_GPR(gpr+1), A_FXBUS(FXBUS_PCM_RIGHT_REAR)); snd_emu10k1_init_stereo_control(&controls[nctl++], "PCM Surround Playback Volume", gpr, 100); gpr += 2; /* PCM Side Playback (independent from stereo mix) */ if (emu->card_capabilities->spk71) { - A_OP(icode, &ptr, iMAC0, A_GPR(playback+6), A_C_00000000, A_GPR(gpr), A_FXBUS(FXBUS_PCM_LEFT_SIDE)); - A_OP(icode, &ptr, iMAC0, A_GPR(playback+7), A_C_00000000, A_GPR(gpr+1), A_FXBUS(FXBUS_PCM_RIGHT_SIDE)); + A_OP(icode, &ptr, iMAC1, A_GPR(playback+6), A_C_00000000, A_GPR(gpr), A_FXBUS(FXBUS_PCM_LEFT_SIDE)); + A_OP(icode, &ptr, iMAC1, A_GPR(playback+7), A_C_00000000, A_GPR(gpr+1), A_FXBUS(FXBUS_PCM_RIGHT_SIDE)); snd_emu10k1_init_stereo_control(&controls[nctl++], "PCM Side Playback Volume", gpr, 100); gpr += 2; } /* PCM Center Playback (independent from stereo mix) */ - A_OP(icode, &ptr, iMAC0, A_GPR(playback+4), A_C_00000000, A_GPR(gpr), A_FXBUS(FXBUS_PCM_CENTER)); + A_OP(icode, &ptr, iMAC1, A_GPR(playback+4), A_C_00000000, A_GPR(gpr), A_FXBUS(FXBUS_PCM_CENTER)); snd_emu10k1_init_mono_control(&controls[nctl++], "PCM Center Playback Volume", gpr, 100); gpr++; /* PCM LFE Playback (independent from stereo mix) */ - A_OP(icode, &ptr, iMAC0, A_GPR(playback+5), A_C_00000000, A_GPR(gpr), A_FXBUS(FXBUS_PCM_LFE)); + A_OP(icode, &ptr, iMAC1, A_GPR(playback+5), A_C_00000000, A_GPR(gpr), A_FXBUS(FXBUS_PCM_LFE)); snd_emu10k1_init_mono_control(&controls[nctl++], "PCM LFE Playback Volume", gpr, 100); gpr++; @@ -1330,26 +1339,26 @@ static int _snd_emu10k1_audigy_init_efx(struct snd_emu10k1 *emu) * Stereo Mix */ /* Wave (PCM) Playback Volume (will be renamed later) */ - A_OP(icode, &ptr, iMAC0, A_GPR(stereo_mix), A_C_00000000, A_GPR(gpr), A_FXBUS(FXBUS_PCM_LEFT)); - A_OP(icode, &ptr, iMAC0, A_GPR(stereo_mix+1), A_C_00000000, A_GPR(gpr+1), A_FXBUS(FXBUS_PCM_RIGHT)); + A_OP(icode, &ptr, iMAC1, A_GPR(stereo_mix), A_C_00000000, A_GPR(gpr), A_FXBUS(FXBUS_PCM_LEFT)); + A_OP(icode, &ptr, iMAC1, A_GPR(stereo_mix+1), A_C_00000000, A_GPR(gpr+1), A_FXBUS(FXBUS_PCM_RIGHT)); snd_emu10k1_init_stereo_control(&controls[nctl++], "Wave Playback Volume", gpr, 100); gpr += 2; /* Synth Playback */ - A_OP(icode, &ptr, iMAC0, A_GPR(stereo_mix+0), A_GPR(stereo_mix+0), A_GPR(gpr), A_FXBUS(FXBUS_MIDI_LEFT)); - A_OP(icode, &ptr, iMAC0, A_GPR(stereo_mix+1), A_GPR(stereo_mix+1), A_GPR(gpr+1), A_FXBUS(FXBUS_MIDI_RIGHT)); + A_OP(icode, &ptr, iMAC1, A_GPR(stereo_mix+0), A_GPR(stereo_mix+0), A_GPR(gpr), A_FXBUS(FXBUS_MIDI_LEFT)); + A_OP(icode, &ptr, iMAC1, A_GPR(stereo_mix+1), A_GPR(stereo_mix+1), A_GPR(gpr+1), A_FXBUS(FXBUS_MIDI_RIGHT)); snd_emu10k1_init_stereo_control(&controls[nctl++], "Synth Playback Volume", gpr, 100); gpr += 2; /* Wave (PCM) Capture */ - A_OP(icode, &ptr, iMAC0, A_GPR(capture+0), A_C_00000000, A_GPR(gpr), A_FXBUS(FXBUS_PCM_LEFT)); - A_OP(icode, &ptr, iMAC0, A_GPR(capture+1), A_C_00000000, A_GPR(gpr+1), A_FXBUS(FXBUS_PCM_RIGHT)); + A_OP(icode, &ptr, iMAC1, A_GPR(capture+0), A_C_00000000, A_GPR(gpr), A_FXBUS(FXBUS_PCM_LEFT)); + A_OP(icode, &ptr, iMAC1, A_GPR(capture+1), A_C_00000000, A_GPR(gpr+1), A_FXBUS(FXBUS_PCM_RIGHT)); snd_emu10k1_init_stereo_control(&controls[nctl++], "PCM Capture Volume", gpr, 0); gpr += 2; /* Synth Capture */ - A_OP(icode, &ptr, iMAC0, A_GPR(capture+0), A_GPR(capture+0), A_GPR(gpr), A_FXBUS(FXBUS_MIDI_LEFT)); - A_OP(icode, &ptr, iMAC0, A_GPR(capture+1), A_GPR(capture+1), A_GPR(gpr+1), A_FXBUS(FXBUS_MIDI_RIGHT)); + A_OP(icode, &ptr, iMAC1, A_GPR(capture+0), A_GPR(capture+0), A_GPR(gpr), A_FXBUS(FXBUS_MIDI_LEFT)); + A_OP(icode, &ptr, iMAC1, A_GPR(capture+1), A_GPR(capture+1), A_GPR(gpr+1), A_FXBUS(FXBUS_MIDI_RIGHT)); snd_emu10k1_init_stereo_control(&controls[nctl++], "Synth Capture Volume", gpr, 0); gpr += 2; @@ -1357,23 +1366,23 @@ static int _snd_emu10k1_audigy_init_efx(struct snd_emu10k1 *emu) * inputs */ #define A_ADD_VOLUME_IN(var,vol,input) \ -A_OP(icode, &ptr, iMAC0, A_GPR(var), A_GPR(var), A_GPR(vol), A_EXTIN(input)) + A_OP(icode, &ptr, iMAC1, A_GPR(var), A_GPR(var), A_GPR(vol), A_EXTIN(input)) if (emu->card_capabilities->emu_model) { /* EMU1010 DSP 0 and DSP 1 Capture */ // The 24 MSB hold the actual value. We implicitly discard the 16 LSB. if (emu->card_capabilities->ca0108_chip) { // For unclear reasons, the EMU32IN cannot be the Y operand! - A_OP(icode, &ptr, iMAC0, A_GPR(capture+0), A_GPR(capture+0), A3_EMU32IN(0x0), A_GPR(gpr)); + A_OP(icode, &ptr, iMAC1, A_GPR(capture+0), A_GPR(capture+0), A3_EMU32IN(0x0), A_GPR(gpr)); // A3_EMU32IN(0) is delayed by one sample, so all other A3_EMU32IN channels // need to be delayed as well; we use an auxiliary register for that. - A_OP(icode, &ptr, iMAC0, A_GPR(capture+1), A_GPR(capture+1), A_GPR(gpr+2), A_GPR(gpr+1)); + A_OP(icode, &ptr, iMAC1, A_GPR(capture+1), A_GPR(capture+1), A_GPR(gpr+2), A_GPR(gpr+1)); A_OP(icode, &ptr, iACC3, A_GPR(gpr+2), A3_EMU32IN(0x1), A_C_00000000, A_C_00000000); } else { - A_OP(icode, &ptr, iMAC0, A_GPR(capture+0), A_GPR(capture+0), A_GPR(gpr), A_P16VIN(0x0)); + A_OP(icode, &ptr, iMAC1, A_GPR(capture+0), A_GPR(capture+0), A_P16VIN(0x0), A_GPR(gpr)); // A_P16VIN(0) is delayed by one sample, so all other A_P16VIN channels // need to be delayed as well; we use an auxiliary register for that. - A_OP(icode, &ptr, iMAC0, A_GPR(capture+1), A_GPR(capture+1), A_GPR(gpr+1), A_GPR(gpr+2)); + A_OP(icode, &ptr, iMAC1, A_GPR(capture+1), A_GPR(capture+1), A_GPR(gpr+2), A_GPR(gpr+1)); A_OP(icode, &ptr, iACC3, A_GPR(gpr+2), A_P16VIN(0x1), A_C_00000000, A_C_00000000); } snd_emu10k1_init_stereo_control(&controls[nctl++], "EMU Capture Volume", gpr, 0); @@ -1465,33 +1474,33 @@ A_OP(icode, &ptr, iMAC0, A_GPR(var), A_GPR(var), A_GPR(vol), A_EXTIN(input)) } /* Stereo Mix Front Playback Volume */ - A_OP(icode, &ptr, iMAC0, A_GPR(playback), A_GPR(playback), A_GPR(gpr), A_GPR(stereo_mix)); - A_OP(icode, &ptr, iMAC0, A_GPR(playback+1), A_GPR(playback+1), A_GPR(gpr+1), A_GPR(stereo_mix+1)); + A_OP(icode, &ptr, iMAC1, A_GPR(playback), A_GPR(playback), A_GPR(gpr), A_GPR(stereo_mix)); + A_OP(icode, &ptr, iMAC1, A_GPR(playback+1), A_GPR(playback+1), A_GPR(gpr+1), A_GPR(stereo_mix+1)); snd_emu10k1_init_stereo_control(&controls[nctl++], "Front Playback Volume", gpr, 100); gpr += 2; /* Stereo Mix Surround Playback */ - A_OP(icode, &ptr, iMAC0, A_GPR(playback+2), A_GPR(playback+2), A_GPR(gpr), A_GPR(stereo_mix)); - A_OP(icode, &ptr, iMAC0, A_GPR(playback+3), A_GPR(playback+3), A_GPR(gpr+1), A_GPR(stereo_mix+1)); + A_OP(icode, &ptr, iMAC1, A_GPR(playback+2), A_GPR(playback+2), A_GPR(gpr), A_GPR(stereo_mix)); + A_OP(icode, &ptr, iMAC1, A_GPR(playback+3), A_GPR(playback+3), A_GPR(gpr+1), A_GPR(stereo_mix+1)); snd_emu10k1_init_stereo_control(&controls[nctl++], "Surround Playback Volume", gpr, 0); gpr += 2; /* Stereo Mix Center Playback */ /* Center = sub = Left/2 + Right/2 */ A_OP(icode, &ptr, iINTERP, A_GPR(tmp), A_GPR(stereo_mix), A_C_40000000, A_GPR(stereo_mix+1)); - A_OP(icode, &ptr, iMAC0, A_GPR(playback+4), A_GPR(playback+4), A_GPR(gpr), A_GPR(tmp)); + A_OP(icode, &ptr, iMAC1, A_GPR(playback+4), A_GPR(playback+4), A_GPR(gpr), A_GPR(tmp)); snd_emu10k1_init_mono_control(&controls[nctl++], "Center Playback Volume", gpr, 0); gpr++; /* Stereo Mix LFE Playback */ - A_OP(icode, &ptr, iMAC0, A_GPR(playback+5), A_GPR(playback+5), A_GPR(gpr), A_GPR(tmp)); + A_OP(icode, &ptr, iMAC1, A_GPR(playback+5), A_GPR(playback+5), A_GPR(gpr), A_GPR(tmp)); snd_emu10k1_init_mono_control(&controls[nctl++], "LFE Playback Volume", gpr, 0); gpr++; if (emu->card_capabilities->spk71) { /* Stereo Mix Side Playback */ - A_OP(icode, &ptr, iMAC0, A_GPR(playback+6), A_GPR(playback+6), A_GPR(gpr), A_GPR(stereo_mix)); - A_OP(icode, &ptr, iMAC0, A_GPR(playback+7), A_GPR(playback+7), A_GPR(gpr+1), A_GPR(stereo_mix+1)); + A_OP(icode, &ptr, iMAC1, A_GPR(playback+6), A_GPR(playback+6), A_GPR(gpr), A_GPR(stereo_mix)); + A_OP(icode, &ptr, iMAC1, A_GPR(playback+7), A_GPR(playback+7), A_GPR(gpr+1), A_GPR(stereo_mix+1)); snd_emu10k1_init_stereo_control(&controls[nctl++], "Side Playback Volume", gpr, 0); gpr += 2; } @@ -1579,7 +1588,7 @@ A_OP(icode, &ptr, iMAC0, A_GPR(var), A_GPR(var), A_GPR(vol), A_EXTIN(input)) /* Master volume (will be renamed later) */ for (z = 0; z < 8; z++) - A_OP(icode, &ptr, iMAC0, A_GPR(playback+z), A_C_00000000, A_GPR(gpr), A_GPR(playback+z)); + A_OP(icode, &ptr, iMAC1, A_GPR(playback+z), A_C_00000000, A_GPR(gpr), A_GPR(playback+z)); snd_emu10k1_init_mono_control(&controls[nctl++], "Wave Master Playback Volume", gpr, 0); gpr++; @@ -1731,30 +1740,14 @@ __err_gpr: * initial DSP configuration for Emu10k1 */ -/* when volume = max, then copy only to avoid volume modification */ -/* with iMAC0 (negative values) */ +/* Volumes are in the [-2^31, 0] range, zero being mute. */ static void _volume(struct snd_emu10k1_fx8010_code *icode, u32 *ptr, u32 dst, u32 src, u32 vol) { - OP(icode, ptr, iMAC0, dst, C_00000000, src, vol); - OP(icode, ptr, iANDXOR, C_00000000, vol, C_ffffffff, C_7fffffff); - OP(icode, ptr, iSKIP, GPR_COND, GPR_COND, CC_REG_NONZERO, C_00000001); - OP(icode, ptr, iACC3, dst, src, C_00000000, C_00000000); + OP(icode, ptr, iMAC1, dst, C_00000000, src, vol); } static void _volume_add(struct snd_emu10k1_fx8010_code *icode, u32 *ptr, u32 dst, u32 src, u32 vol) { - OP(icode, ptr, iANDXOR, C_00000000, vol, C_ffffffff, C_7fffffff); - OP(icode, ptr, iSKIP, GPR_COND, GPR_COND, CC_REG_NONZERO, C_00000002); - OP(icode, ptr, iMACINT0, dst, dst, src, C_00000001); - OP(icode, ptr, iSKIP, C_00000000, C_7fffffff, C_7fffffff, C_00000001); - OP(icode, ptr, iMAC0, dst, dst, src, vol); -} -static void _volume_out(struct snd_emu10k1_fx8010_code *icode, u32 *ptr, u32 dst, u32 src, u32 vol) -{ - OP(icode, ptr, iANDXOR, C_00000000, vol, C_ffffffff, C_7fffffff); - OP(icode, ptr, iSKIP, GPR_COND, GPR_COND, CC_REG_NONZERO, C_00000002); - OP(icode, ptr, iACC3, dst, src, C_00000000, C_00000000); - OP(icode, ptr, iSKIP, C_00000000, C_7fffffff, C_7fffffff, C_00000001); - OP(icode, ptr, iMAC0, dst, C_00000000, src, vol); + OP(icode, ptr, iMAC1, dst, dst, src, vol); } #define VOLUME(icode, ptr, dst, src, vol) \ @@ -1766,7 +1759,7 @@ static void _volume_out(struct snd_emu10k1_fx8010_code *icode, u32 *ptr, u32 dst #define VOLUME_ADDIN(icode, ptr, dst, src, vol) \ _volume_add(icode, ptr, GPR(dst), EXTIN(src), GPR(vol)) #define VOLUME_OUT(icode, ptr, dst, src, vol) \ - _volume_out(icode, ptr, EXTOUT(dst), GPR(src), GPR(vol)) + _volume(icode, ptr, EXTOUT(dst), GPR(src), GPR(vol)) #define _SWITCH(icode, ptr, dst, src, sw) \ OP((icode), ptr, iMACINT0, dst, C_00000000, src, sw); #define SWITCH(icode, ptr, dst, src, sw) \ -- cgit v1.2.3 From 03d89a2de25bbc5c77e61a0cf77663978c4b6ea7 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 5 Nov 2021 17:20:54 -0600 Subject: io_uring: support for user allocated memory for rings/sqes Currently io_uring applications must call mmap(2) twice to map the rings themselves, and the sqes array. This works fine, but it does not support using huge pages to back the rings/sqes. Provide a way for the application to pass in pre-allocated memory for the rings/sqes, which can then suitably be allocated from shmfs or via mmap to get huge page support. Particularly for larger rings, this reduces the TLBs needed. If an application wishes to take advantage of that, it must pre-allocate the memory needed for the sq/cq ring, and the sqes. The former must be passed in via the io_uring_params->cq_off.user_data field, while the latter is passed in via the io_uring_params->sq_off.user_data field. Then it must set IORING_SETUP_NO_MMAP in the io_uring_params->flags field, and io_uring will then map the existing memory into the kernel for shared use. The application must not call mmap(2) to map rings as it otherwise would have, that will now fail with -EINVAL if this setup flag was used. The pages used for the rings and sqes must be contigious. The intent here is clearly that huge pages should be used, otherwise the normal setup procedure works fine as-is. The application may use one huge page for both the rings and sqes. Outside of those initialization changes, everything works like it did before. Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 10 ++++ include/uapi/linux/io_uring.h | 9 +++- io_uring/io_uring.c | 106 +++++++++++++++++++++++++++++++++++++---- 3 files changed, 114 insertions(+), 11 deletions(-) (limited to 'include/uapi') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 1b2a20a42413..f04ce513fadb 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -211,6 +211,16 @@ struct io_ring_ctx { unsigned int compat: 1; enum task_work_notify_mode notify_method; + + /* + * If IORING_SETUP_NO_MMAP is used, then the below holds + * the gup'ed pages for the two rings, and the sqes. + */ + unsigned short n_ring_pages; + unsigned short n_sqe_pages; + struct page **ring_pages; + struct page **sqe_pages; + struct io_rings *rings; struct task_struct *submitter_task; struct percpu_ref refs; diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 0716cb17e436..2edba9a274de 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -173,6 +173,11 @@ enum { */ #define IORING_SETUP_DEFER_TASKRUN (1U << 13) +/* + * Application provides the memory for the rings + */ +#define IORING_SETUP_NO_MMAP (1U << 14) + enum io_uring_op { IORING_OP_NOP, IORING_OP_READV, @@ -406,7 +411,7 @@ struct io_sqring_offsets { __u32 dropped; __u32 array; __u32 resv1; - __u64 resv2; + __u64 user_addr; }; /* @@ -425,7 +430,7 @@ struct io_cqring_offsets { __u32 cqes; __u32 flags; __u32 resv1; - __u64 resv2; + __u64 user_addr; }; /* diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 74433939a318..61379cf8e7f5 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2688,12 +2688,85 @@ static void io_mem_free(void *ptr) free_compound_page(page); } +static void io_pages_free(struct page ***pages, int npages) +{ + struct page **page_array; + int i; + + if (!pages) + return; + page_array = *pages; + for (i = 0; i < npages; i++) + unpin_user_page(page_array[i]); + kvfree(page_array); + *pages = NULL; +} + +static void *__io_uaddr_map(struct page ***pages, unsigned short *npages, + unsigned long uaddr, size_t size) +{ + struct page **page_array; + unsigned int nr_pages; + int ret; + + *npages = 0; + + if (uaddr & (PAGE_SIZE - 1) || !size) + return ERR_PTR(-EINVAL); + + nr_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; + if (nr_pages > USHRT_MAX) + return ERR_PTR(-EINVAL); + page_array = kvmalloc_array(nr_pages, sizeof(struct page *), GFP_KERNEL); + if (!page_array) + return ERR_PTR(-ENOMEM); + + ret = pin_user_pages_fast(uaddr, nr_pages, FOLL_WRITE | FOLL_LONGTERM, + page_array); + if (ret != nr_pages) { +err: + io_pages_free(&page_array, ret > 0 ? ret : 0); + return ret < 0 ? ERR_PTR(ret) : ERR_PTR(-EFAULT); + } + /* + * Should be a single page. If the ring is small enough that we can + * use a normal page, that is fine. If we need multiple pages, then + * userspace should use a huge page. That's the only way to guarantee + * that we get contigious memory, outside of just being lucky or + * (currently) having low memory fragmentation. + */ + if (page_array[0] != page_array[ret - 1]) + goto err; + *pages = page_array; + *npages = nr_pages; + return page_to_virt(page_array[0]); +} + +static void *io_rings_map(struct io_ring_ctx *ctx, unsigned long uaddr, + size_t size) +{ + return __io_uaddr_map(&ctx->ring_pages, &ctx->n_ring_pages, uaddr, + size); +} + +static void *io_sqes_map(struct io_ring_ctx *ctx, unsigned long uaddr, + size_t size) +{ + return __io_uaddr_map(&ctx->sqe_pages, &ctx->n_sqe_pages, uaddr, + size); +} + static void io_rings_free(struct io_ring_ctx *ctx) { - io_mem_free(ctx->rings); - io_mem_free(ctx->sq_sqes); - ctx->rings = NULL; - ctx->sq_sqes = NULL; + if (!(ctx->flags & IORING_SETUP_NO_MMAP)) { + io_mem_free(ctx->rings); + io_mem_free(ctx->sq_sqes); + ctx->rings = NULL; + ctx->sq_sqes = NULL; + } else { + io_pages_free(&ctx->ring_pages, ctx->n_ring_pages); + io_pages_free(&ctx->sqe_pages, ctx->n_sqe_pages); + } } static void *io_mem_alloc(size_t size) @@ -3338,6 +3411,10 @@ static void *io_uring_validate_mmap_request(struct file *file, struct page *page; void *ptr; + /* Don't allow mmap if the ring was setup without it */ + if (ctx->flags & IORING_SETUP_NO_MMAP) + return ERR_PTR(-EINVAL); + switch (offset & IORING_OFF_MMAP_MASK) { case IORING_OFF_SQ_RING: case IORING_OFF_CQ_RING: @@ -3673,7 +3750,11 @@ static __cold int io_allocate_scq_urings(struct io_ring_ctx *ctx, if (size == SIZE_MAX) return -EOVERFLOW; - rings = io_mem_alloc(size); + if (!(ctx->flags & IORING_SETUP_NO_MMAP)) + rings = io_mem_alloc(size); + else + rings = io_rings_map(ctx, p->cq_off.user_addr, size); + if (IS_ERR(rings)) return PTR_ERR(rings); @@ -3693,7 +3774,11 @@ static __cold int io_allocate_scq_urings(struct io_ring_ctx *ctx, return -EOVERFLOW; } - ptr = io_mem_alloc(size); + if (!(ctx->flags & IORING_SETUP_NO_MMAP)) + ptr = io_mem_alloc(size); + else + ptr = io_sqes_map(ctx, p->sq_off.user_addr, size); + if (IS_ERR(ptr)) { io_rings_free(ctx); return PTR_ERR(ptr); @@ -3885,7 +3970,8 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p, p->sq_off.dropped = offsetof(struct io_rings, sq_dropped); p->sq_off.array = (char *)ctx->sq_array - (char *)ctx->rings; p->sq_off.resv1 = 0; - p->sq_off.resv2 = 0; + if (!(ctx->flags & IORING_SETUP_NO_MMAP)) + p->sq_off.user_addr = 0; p->cq_off.head = offsetof(struct io_rings, cq.head); p->cq_off.tail = offsetof(struct io_rings, cq.tail); @@ -3895,7 +3981,8 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p, p->cq_off.cqes = offsetof(struct io_rings, cqes); p->cq_off.flags = offsetof(struct io_rings, cq_flags); p->cq_off.resv1 = 0; - p->cq_off.resv2 = 0; + if (!(ctx->flags & IORING_SETUP_NO_MMAP)) + p->cq_off.user_addr = 0; p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP | IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS | @@ -3961,7 +4048,8 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params) IORING_SETUP_R_DISABLED | IORING_SETUP_SUBMIT_ALL | IORING_SETUP_COOP_TASKRUN | IORING_SETUP_TASKRUN_FLAG | IORING_SETUP_SQE128 | IORING_SETUP_CQE32 | - IORING_SETUP_SINGLE_ISSUER | IORING_SETUP_DEFER_TASKRUN)) + IORING_SETUP_SINGLE_ISSUER | IORING_SETUP_DEFER_TASKRUN | + IORING_SETUP_NO_MMAP)) return -EINVAL; return io_uring_create(entries, &p, params); -- cgit v1.2.3 From 6e76ac595855db27bbdaef337173294a6fd6eb2c Mon Sep 17 00:00:00 2001 From: Josh Triplett Date: Sat, 29 Apr 2023 01:40:30 +0900 Subject: io_uring: Add io_uring_setup flag to pre-register ring fd and never install it With IORING_REGISTER_USE_REGISTERED_RING, an application can register the ring fd and use it via registered index rather than installed fd. This allows using a registered ring for everything *except* the initial mmap. With IORING_SETUP_NO_MMAP, io_uring_setup uses buffers allocated by the user, rather than requiring a subsequent mmap. The combination of the two allows a user to operate *entirely* via a registered ring fd, making it unnecessary to ever install the fd in the first place. So, add a flag IORING_SETUP_REGISTERED_FD_ONLY to make io_uring_setup register the fd and return a registered index, without installing the fd. This allows an application to avoid touching the fd table at all, and allows a library to never even momentarily install a file descriptor. This splits out an io_ring_add_registered_file helper from io_ring_add_registered_fd, for use by io_uring_setup. Signed-off-by: Josh Triplett Link: https://lore.kernel.org/r/bc8f431bada371c183b95a83399628b605e978a3.1682699803.git.josh@joshtriplett.org Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 7 +++++++ io_uring/io_uring.c | 37 ++++++++++++++++++++++--------------- io_uring/io_uring.h | 3 +++ io_uring/tctx.c | 31 ++++++++++++++++++++----------- 4 files changed, 52 insertions(+), 26 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 2edba9a274de..f222d263bc55 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -178,6 +178,13 @@ enum { */ #define IORING_SETUP_NO_MMAP (1U << 14) +/* + * Register the ring fd in itself for use with + * IORING_REGISTER_USE_REGISTERED_RING; return a registered fd index rather + * than an fd. + */ +#define IORING_SETUP_REGISTERED_FD_ONLY (1U << 15) + enum io_uring_op { IORING_OP_NOP, IORING_OP_READV, diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 61379cf8e7f5..dab09f568294 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -3788,19 +3788,13 @@ static __cold int io_allocate_scq_urings(struct io_ring_ctx *ctx, return 0; } -static int io_uring_install_fd(struct io_ring_ctx *ctx, struct file *file) +static int io_uring_install_fd(struct file *file) { - int ret, fd; + int fd; fd = get_unused_fd_flags(O_RDWR | O_CLOEXEC); if (fd < 0) return fd; - - ret = __io_uring_add_tctx_node(ctx); - if (ret) { - put_unused_fd(fd); - return ret; - } fd_install(fd, file); return fd; } @@ -3840,6 +3834,7 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p, struct io_uring_params __user *params) { struct io_ring_ctx *ctx; + struct io_uring_task *tctx; struct file *file; int ret; @@ -3851,6 +3846,10 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p, entries = IORING_MAX_ENTRIES; } + if ((p->flags & IORING_SETUP_REGISTERED_FD_ONLY) + && !(p->flags & IORING_SETUP_NO_MMAP)) + return -EINVAL; + /* * Use twice as many entries for the CQ ring. It's possible for the * application to drive a higher depth than the size of the SQ ring, @@ -4007,22 +4006,30 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p, goto err; } + ret = __io_uring_add_tctx_node(ctx); + if (ret) + goto err_fput; + tctx = current->io_uring; + /* * Install ring fd as the very last thing, so we don't risk someone * having closed it before we finish setup */ - ret = io_uring_install_fd(ctx, file); - if (ret < 0) { - /* fput will clean it up */ - fput(file); - return ret; - } + if (p->flags & IORING_SETUP_REGISTERED_FD_ONLY) + ret = io_ring_add_registered_file(tctx, file, 0, IO_RINGFD_REG_MAX); + else + ret = io_uring_install_fd(file); + if (ret < 0) + goto err_fput; trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags); return ret; err: io_ring_ctx_wait_and_kill(ctx); return ret; +err_fput: + fput(file); + return ret; } /* @@ -4049,7 +4056,7 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params) IORING_SETUP_COOP_TASKRUN | IORING_SETUP_TASKRUN_FLAG | IORING_SETUP_SQE128 | IORING_SETUP_CQE32 | IORING_SETUP_SINGLE_ISSUER | IORING_SETUP_DEFER_TASKRUN | - IORING_SETUP_NO_MMAP)) + IORING_SETUP_NO_MMAP | IORING_SETUP_REGISTERED_FD_ONLY)) return -EINVAL; return io_uring_create(entries, &p, params); diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h index 259bf798a390..9b8dfb3bb2b4 100644 --- a/io_uring/io_uring.h +++ b/io_uring/io_uring.h @@ -75,6 +75,9 @@ __cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd); int io_uring_alloc_task_context(struct task_struct *task, struct io_ring_ctx *ctx); +int io_ring_add_registered_file(struct io_uring_task *tctx, struct file *file, + int start, int end); + int io_poll_issue(struct io_kiocb *req, struct io_tw_state *ts); int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr); int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin); diff --git a/io_uring/tctx.c b/io_uring/tctx.c index 3a8d1dd97e1b..c043fe93a3f2 100644 --- a/io_uring/tctx.c +++ b/io_uring/tctx.c @@ -208,31 +208,40 @@ void io_uring_unreg_ringfd(void) } } -static int io_ring_add_registered_fd(struct io_uring_task *tctx, int fd, +int io_ring_add_registered_file(struct io_uring_task *tctx, struct file *file, int start, int end) { - struct file *file; int offset; - for (offset = start; offset < end; offset++) { offset = array_index_nospec(offset, IO_RINGFD_REG_MAX); if (tctx->registered_rings[offset]) continue; - file = fget(fd); - if (!file) { - return -EBADF; - } else if (!io_is_uring_fops(file)) { - fput(file); - return -EOPNOTSUPP; - } tctx->registered_rings[offset] = file; return offset; } - return -EBUSY; } +static int io_ring_add_registered_fd(struct io_uring_task *tctx, int fd, + int start, int end) +{ + struct file *file; + int offset; + + file = fget(fd); + if (!file) { + return -EBADF; + } else if (!io_is_uring_fops(file)) { + fput(file); + return -EOPNOTSUPP; + } + offset = io_ring_add_registered_file(tctx, file, start, end); + if (offset < 0) + fput(file); + return offset; +} + /* * Register a ring fd to avoid fdget/fdput for each io_uring_enter() * invocation. User passes in an array of struct io_uring_rsrc_update -- cgit v1.2.3 From b9f9a485fb0eb80b0e2b90410b28cbb9b0e85687 Mon Sep 17 00:00:00 2001 From: Jeremy Sowden Date: Tue, 9 May 2023 22:19:45 +0100 Subject: netfilter: nft_exthdr: add boolean DCCP option matching The xt_dccp iptables module supports the matching of DCCP packets based on the presence or absence of DCCP options. Extend nft_exthdr to add this functionality to nftables. Link: https://bugzilla.netfilter.org/show_bug.cgi?id=930 Signed-off-by: Jeremy Sowden Signed-off-by: Florian Westphal --- include/uapi/linux/netfilter/nf_tables.h | 2 + net/netfilter/nft_exthdr.c | 106 +++++++++++++++++++++++++++++++ 2 files changed, 108 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index c4d4d8e42dc8..e059dc2644df 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -859,12 +859,14 @@ enum nft_exthdr_flags { * @NFT_EXTHDR_OP_TCP: match against tcp options * @NFT_EXTHDR_OP_IPV4: match against ipv4 options * @NFT_EXTHDR_OP_SCTP: match against sctp chunks + * @NFT_EXTHDR_OP_DCCP: match against dccp otions */ enum nft_exthdr_op { NFT_EXTHDR_OP_IPV6, NFT_EXTHDR_OP_TCPOPT, NFT_EXTHDR_OP_IPV4, NFT_EXTHDR_OP_SCTP, + NFT_EXTHDR_OP_DCCP, __NFT_EXTHDR_OP_MAX }; #define NFT_EXTHDR_OP_MAX (__NFT_EXTHDR_OP_MAX - 1) diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index a54a7f772cec..671474e59817 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -406,6 +407,82 @@ err: regs->verdict.code = NFT_BREAK; } +static void nft_exthdr_dccp_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_exthdr *priv = nft_expr_priv(expr); + unsigned int thoff, dataoff, optoff, optlen, i; + u32 *dest = ®s->data[priv->dreg]; + const struct dccp_hdr *dh; + struct dccp_hdr _dh; + + if (pkt->tprot != IPPROTO_DCCP || pkt->fragoff) + goto err; + + thoff = nft_thoff(pkt); + + dh = skb_header_pointer(pkt->skb, thoff, sizeof(_dh), &_dh); + if (!dh) + goto err; + + dataoff = dh->dccph_doff * sizeof(u32); + optoff = __dccp_hdr_len(dh); + if (dataoff <= optoff) + goto err; + + optlen = dataoff - optoff; + + for (i = 0; i < optlen; ) { + /* Options 0 (DCCPO_PADDING) - 31 (DCCPO_MAX_RESERVED) are 1B in + * the length; the remaining options are at least 2B long. In + * all cases, the first byte contains the option type. In + * multi-byte options, the second byte contains the option + * length, which must be at least two: 1 for the type plus 1 for + * the length plus 0-253 for any following option data. We + * aren't interested in the option data, only the type and the + * length, so we don't need to read more than two bytes at a + * time. + */ + unsigned int buflen = optlen - i; + u8 buf[2], *bufp; + u8 type, len; + + if (buflen > sizeof(buf)) + buflen = sizeof(buf); + + bufp = skb_header_pointer(pkt->skb, thoff + optoff + i, buflen, + &buf); + if (!bufp) + goto err; + + type = bufp[0]; + + if (type == priv->type) { + *dest = 1; + return; + } + + if (type <= DCCPO_MAX_RESERVED) { + i++; + continue; + } + + if (buflen < 2) + goto err; + + len = bufp[1]; + + if (len < 2) + goto err; + + i += len; + } + +err: + *dest = 0; +} + static const struct nla_policy nft_exthdr_policy[NFTA_EXTHDR_MAX + 1] = { [NFTA_EXTHDR_DREG] = { .type = NLA_U32 }, [NFTA_EXTHDR_TYPE] = { .type = NLA_U8 }, @@ -557,6 +634,22 @@ static int nft_exthdr_ipv4_init(const struct nft_ctx *ctx, return 0; } +static int nft_exthdr_dccp_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_exthdr *priv = nft_expr_priv(expr); + int err = nft_exthdr_init(ctx, expr, tb); + + if (err < 0) + return err; + + if (!(priv->flags & NFT_EXTHDR_F_PRESENT)) + return -EOPNOTSUPP; + + return 0; +} + static int nft_exthdr_dump_common(struct sk_buff *skb, const struct nft_exthdr *priv) { if (nla_put_u8(skb, NFTA_EXTHDR_TYPE, priv->type)) @@ -686,6 +779,15 @@ static const struct nft_expr_ops nft_exthdr_sctp_ops = { .reduce = nft_exthdr_reduce, }; +static const struct nft_expr_ops nft_exthdr_dccp_ops = { + .type = &nft_exthdr_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_exthdr)), + .eval = nft_exthdr_dccp_eval, + .init = nft_exthdr_dccp_init, + .dump = nft_exthdr_dump, + .reduce = nft_exthdr_reduce, +}; + static const struct nft_expr_ops * nft_exthdr_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) @@ -720,6 +822,10 @@ nft_exthdr_select_ops(const struct nft_ctx *ctx, if (tb[NFTA_EXTHDR_DREG]) return &nft_exthdr_sctp_ops; break; + case NFT_EXTHDR_OP_DCCP: + if (tb[NFTA_EXTHDR_DREG]) + return &nft_exthdr_dccp_ops; + break; } return ERR_PTR(-EOPNOTSUPP); -- cgit v1.2.3 From 6ac392815628f317fcfdca1a39df00b9cc4ebc8b Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 3 May 2023 13:18:42 +0200 Subject: fs: allow to mount beneath top mount MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Various distributions are adding or are in the process of adding support for system extensions and in the future configuration extensions through various tools. A more detailed explanation on system and configuration extensions can be found on the manpage which is listed below at [1]. System extension images may – dynamically at runtime — extend the /usr/ and /opt/ directory hierarchies with additional files. This is particularly useful on immutable system images where a /usr/ and/or /opt/ hierarchy residing on a read-only file system shall be extended temporarily at runtime without making any persistent modifications. When one or more system extension images are activated, their /usr/ and /opt/ hierarchies are combined via overlayfs with the same hierarchies of the host OS, and the host /usr/ and /opt/ overmounted with it ("merging"). When they are deactivated, the mount point is disassembled — again revealing the unmodified original host version of the hierarchy ("unmerging"). Merging thus makes the extension's resources suddenly appear below the /usr/ and /opt/ hierarchies as if they were included in the base OS image itself. Unmerging makes them disappear again, leaving in place only the files that were shipped with the base OS image itself. System configuration images are similar but operate on directories containing system or service configuration. On nearly all modern distributions mount propagation plays a crucial role and the rootfs of the OS is a shared mount in a peer group (usually with peer group id 1): TARGET SOURCE FSTYPE PROPAGATION MNT_ID PARENT_ID / / ext4 shared:1 29 1 On such systems all services and containers run in a separate mount namespace and are pivot_root()ed into their rootfs. A separate mount namespace is almost always used as it is the minimal isolation mechanism services have. But usually they are even much more isolated up to the point where they almost become indistinguishable from containers. Mount propagation again plays a crucial role here. The rootfs of all these services is a slave mount to the peer group of the host rootfs. This is done so the service will receive mount propagation events from the host when certain files or directories are updated. In addition, the rootfs of each service, container, and sandbox is also a shared mount in its separate peer group: TARGET SOURCE FSTYPE PROPAGATION MNT_ID PARENT_ID / / ext4 shared:24 master:1 71 47 For people not too familiar with mount propagation, the master:1 means that this is a slave mount to peer group 1. Which as one can see is the host rootfs as indicated by shared:1 above. The shared:24 indicates that the service rootfs is a shared mount in a separate peer group with peer group id 24. A service may run other services. Such nested services will also have a rootfs mount that is a slave to the peer group of the outer service rootfs mount. For containers things are just slighly different. A container's rootfs isn't a slave to the service's or host rootfs' peer group. The rootfs mount of a container is simply a shared mount in its own peer group: TARGET SOURCE FSTYPE PROPAGATION MNT_ID PARENT_ID /home/ubuntu/debian-tree / ext4 shared:99 61 60 So whereas services are isolated OS components a container is treated like a separate world and mount propagation into it is restricted to a single well known mount that is a slave to the peer group of the shared mount /run on the host: TARGET SOURCE FSTYPE PROPAGATION MNT_ID PARENT_ID /propagate/debian-tree /run/host/incoming tmpfs master:5 71 68 Here, the master:5 indicates that this mount is a slave to the peer group with peer group id 5. This allows to propagate mounts into the container and served as a workaround for not being able to insert mounts into mount namespaces directly. But the new mount api does support inserting mounts directly. For the interested reader the blogpost in [2] might be worth reading where I explain the old and the new approach to inserting mounts into mount namespaces. Containers of course, can themselves be run as services. They often run full systems themselves which means they again run services and containers with the exact same propagation settings explained above. The whole system is designed so that it can be easily updated, including all services in various fine-grained ways without having to enter every single service's mount namespace which would be prohibitively expensive. The mount propagation layout has been carefully chosen so it is possible to propagate updates for system extensions and configurations from the host into all services. The simplest model to update the whole system is to mount on top of /usr, /opt, or /etc on the host. The new mount on /usr, /opt, or /etc will then propagate into every service. This works cleanly the first time. However, when the system is updated multiple times it becomes necessary to unmount the first update on /opt, /usr, /etc and then propagate the new update. But this means, there's an interval where the old base system is accessible. This has to be avoided to protect against downgrade attacks. The vfs already exposes a mechanism to userspace whereby mounts can be mounted beneath an existing mount. Such mounts are internally referred to as "tucked". The patch series exposes the ability to mount beneath a top mount through the new MOVE_MOUNT_BENEATH flag for the move_mount() system call. This allows userspace to seamlessly upgrade mounts. After this series the only thing that will have changed is that mounting beneath an existing mount can be done explicitly instead of just implicitly. Today, there are two scenarios where a mount can be mounted beneath an existing mount instead of on top of it: (1) When a service or container is started in a new mount namespace and pivot_root()s into its new rootfs. The way this is done is by mounting the new rootfs beneath the old rootfs: fd_newroot = open("/var/lib/machines/fedora", ...); fd_oldroot = open("/", ...); fchdir(fd_newroot); pivot_root(".", "."); After the pivot_root(".", ".") call the new rootfs is mounted beneath the old rootfs which can then be unmounted to reveal the underlying mount: fchdir(fd_oldroot); umount2(".", MNT_DETACH); Since pivot_root() moves the caller into a new rootfs no mounts must be propagated out of the new rootfs as a consequence of the pivot_root() call. Thus, the mounts cannot be shared. (2) When a mount is propagated to a mount that already has another mount mounted on the same dentry. The easiest example for this is to create a new mount namespace. The following commands will create a mount namespace where the rootfs mount / will be a slave to the peer group of the host rootfs / mount's peer group. IOW, it will receive propagation from the host: mount --make-shared / unshare --mount --propagation=slave Now a new mount on the /mnt dentry in that mount namespace is created. (As it can be confusing it should be spelled out that the tmpfs mount on the /mnt dentry that was just created doesn't propagate back to the host because the rootfs mount / of the mount namespace isn't a peer of the host rootfs.): mount -t tmpfs tmpfs /mnt TARGET SOURCE FSTYPE PROPAGATION └─/mnt tmpfs tmpfs Now another terminal in the host mount namespace can observe that the mount indeed hasn't propagated back to into the host mount namespace. A new mount can now be created on top of the /mnt dentry with the rootfs mount / as its parent: mount --bind /opt /mnt TARGET SOURCE FSTYPE PROPAGATION └─/mnt /dev/sda2[/opt] ext4 shared:1 The mount namespace that was created earlier can now observe that the bind mount created on the host has propagated into it: TARGET SOURCE FSTYPE PROPAGATION └─/mnt /dev/sda2[/opt] ext4 master:1 └─/mnt tmpfs tmpfs But instead of having been mounted on top of the tmpfs mount at the /mnt dentry the /opt mount has been mounted on top of the rootfs mount at the /mnt dentry. And the tmpfs mount has been remounted on top of the propagated /opt mount at the /opt dentry. So in other words, the propagated mount has been mounted beneath the preexisting mount in that mount namespace. Mount namespaces make this easy to illustrate but it's also easy to mount beneath an existing mount in the same mount namespace (The following example assumes a shared rootfs mount / with peer group id 1): mount --bind /opt /opt TARGET SOURCE FSTYPE MNT_ID PARENT_ID PROPAGATION └─/opt /dev/sda2[/opt] ext4 188 29 shared:1 If another mount is mounted on top of the /opt mount at the /opt dentry: mount --bind /tmp /opt The following clunky mount tree will result: TARGET SOURCE FSTYPE MNT_ID PARENT_ID PROPAGATION └─/opt /dev/sda2[/tmp] ext4 405 29 shared:1 └─/opt /dev/sda2[/opt] ext4 188 405 shared:1 └─/opt /dev/sda2[/tmp] ext4 404 188 shared:1 The /tmp mount is mounted beneath the /opt mount and another copy is mounted on top of the /opt mount. This happens because the rootfs / and the /opt mount are shared mounts in the same peer group. When the new /tmp mount is supposed to be mounted at the /opt dentry then the /tmp mount first propagates to the root mount at the /opt dentry. But there already is the /opt mount mounted at the /opt dentry. So the old /opt mount at the /opt dentry will be mounted on top of the new /tmp mount at the /tmp dentry, i.e. @opt->mnt_parent is @tmp and @opt->mnt_mountpoint is /tmp (Note that @opt->mnt_root is /opt which is what shows up as /opt under SOURCE). So again, a mount will be mounted beneath a preexisting mount. (Fwiw, a few iterations of mount --bind /opt /opt in a loop on a shared rootfs is a good example of what could be referred to as mount explosion.) The main point is that such mounts allows userspace to umount a top mount and reveal an underlying mount. So for example, umounting the tmpfs mount on /mnt that was created in example (1) using mount namespaces reveals the /opt mount which was mounted beneath it. In (2) where a mount was mounted beneath the top mount in the same mount namespace unmounting the top mount would unmount both the top mount and the mount beneath. In the process the original mount would be remounted on top of the rootfs mount / at the /opt dentry again. This again, is a result of mount propagation only this time it's umount propagation. However, this can be avoided by simply making the parent mount / of the @opt mount a private or slave mount. Then the top mount and the original mount can be unmounted to reveal the mount beneath. These two examples are fairly arcane and are merely added to make it clear how mount propagation has effects on current and future features. More common use-cases will just be things like: mount -t btrfs /dev/sdA /mnt mount -t xfs /dev/sdB --beneath /mnt umount /mnt after which we'll have updated from a btrfs filesystem to a xfs filesystem without ever revealing the underlying mountpoint. The crux is that the proposed mechanism already exists and that it is so powerful as to cover cases where mounts are supposed to be updated with new versions. Crucially, it offers an important flexibility. Namely that updates to a system may either be forced or can be delayed and the umount of the top mount be left to a service if it is a cooperative one. This adds a new flag to move_mount() that allows to explicitly move a beneath the top mount adhering to the following semantics: * Mounts cannot be mounted beneath the rootfs. This restriction encompasses the rootfs but also chroots via chroot() and pivot_root(). To mount a mount beneath the rootfs or a chroot, pivot_root() can be used as illustrated above. * The source mount must be a private mount to force the kernel to allocate a new, unused peer group id. This isn't a required restriction but a voluntary one. It avoids repeating a semantical quirk that already exists today. If bind mounts which already have a peer group id are inserted into mount trees that have the same peer group id this can cause a lot of mount propagation events to be generated (For example, consider running mount --bind /opt /opt in a loop where the parent mount is a shared mount.). * Avoid getting rid of the top mount in the kernel. Cooperative services need to be able to unmount the top mount themselves. This also avoids a good deal of additional complexity. The umount would have to be propagated which would be another rather expensive operation. So namespace_lock() and lock_mount_hash() would potentially have to be held for a long time for both a mount and umount propagation. That should be avoided. * The path to mount beneath must be mounted and attached. * The top mount and its parent must be in the caller's mount namespace and the caller must be able to mount in that mount namespace. * The caller must be able to unmount the top mount to prove that they could reveal the underlying mount. * The propagation tree is calculated based on the destination mount's parent mount and the destination mount's mountpoint on the parent mount. Of course, if the parent of the destination mount and the destination mount are shared mounts in the same peer group and the mountpoint of the new mount to be mounted is a subdir of their ->mnt_root then both will receive a mount of /opt. That's probably easier to understand with an example. Assuming a standard shared rootfs /: mount --bind /opt /opt mount --bind /tmp /opt will cause the same mount tree as: mount --bind /opt /opt mount --beneath /tmp /opt because both / and /opt are shared mounts/peers in the same peer group and the /opt dentry is a subdirectory of both the parent's and the child's ->mnt_root. If a mount tree like that is created it almost always is an accident or abuse of mount propagation. Realistically what most people probably mean in this scenarios is: mount --bind /opt /opt mount --make-private /opt mount --make-shared /opt This forces the allocation of a new separate peer group for the /opt mount. Aferwards a mount --bind or mount --beneath actually makes sense as the / and /opt mount belong to different peer groups. Before that it's likely just confusion about what the user wanted to achieve. * Refuse MOVE_MOUNT_BENEATH if: (1) the @mnt_from has been overmounted in between path resolution and acquiring @namespace_sem when locking @mnt_to. This avoids the proliferation of shadow mounts. (2) if @to_mnt is moved to a different mountpoint while acquiring @namespace_sem to lock @to_mnt. (3) if @to_mnt is unmounted while acquiring @namespace_sem to lock @to_mnt. (4) if the parent of the target mount propagates to the target mount at the same mountpoint. This would mean mounting @mnt_from on @mnt_to->mnt_parent and then propagating a copy @c of @mnt_from onto @mnt_to. This defeats the whole purpose of mounting @mnt_from beneath @mnt_to. (5) if the parent mount @mnt_to->mnt_parent propagates to @mnt_from at the same mountpoint. If @mnt_to->mnt_parent propagates to @mnt_from this would mean propagating a copy @c of @mnt_from on top of @mnt_from. Afterwards @mnt_from would be mounted on top of @mnt_to->mnt_parent and @mnt_to would be unmounted from @mnt->mnt_parent and remounted on @mnt_from. But since @c is already mounted on @mnt_from, @mnt_to would ultimately be remounted on top of @c. Afterwards, @mnt_from would be covered by a copy @c of @mnt_from and @c would be covered by @mnt_from itself. This defeats the whole purpose of mounting @mnt_from beneath @mnt_to. Cases (1) to (3) are required as they deal with races that would cause bugs or unexpected behavior for users. Cases (4) and (5) refuse semantical quirks that would not be a bug but would cause weird mount trees to be created. While they can already be created via other means (mount --bind /opt /opt x n) there's no reason to repeat past mistakes in new features. Link: https://man7.org/linux/man-pages/man8/systemd-sysext.8.html [1] Link: https://brauner.io/2023/02/28/mounting-into-mount-namespaces.html [2] Link: https://github.com/flatcar/sysext-bakery Link: https://fedoraproject.org/wiki/Changes/Unified_Kernel_Support_Phase_1 Link: https://fedoraproject.org/wiki/Changes/Unified_Kernel_Support_Phase_2 Link: https://github.com/systemd/systemd/pull/26013 Reviewed-by: Seth Forshee (DigitalOcean) Message-Id: <20230202-fs-move-mount-replace-v4-4-98f3d80d7eaa@kernel.org> Signed-off-by: Christian Brauner --- fs/namespace.c | 352 ++++++++++++++++++++++++++++++++++++++------- fs/pnode.c | 42 +++++- fs/pnode.h | 3 + include/uapi/linux/mount.h | 3 +- 4 files changed, 350 insertions(+), 50 deletions(-) (limited to 'include/uapi') diff --git a/fs/namespace.c b/fs/namespace.c index f91a60e6039d..382edc76aee7 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -926,6 +926,33 @@ void mnt_set_mountpoint(struct mount *mnt, hlist_add_head(&child_mnt->mnt_mp_list, &mp->m_list); } +/** + * mnt_set_mountpoint_beneath - mount a mount beneath another one + * + * @new_parent: the source mount + * @top_mnt: the mount beneath which @new_parent is mounted + * @new_mp: the new mountpoint of @top_mnt on @new_parent + * + * Remove @top_mnt from its current mountpoint @top_mnt->mnt_mp and + * parent @top_mnt->mnt_parent and mount it on top of @new_parent at + * @new_mp. And mount @new_parent on the old parent and old + * mountpoint of @top_mnt. + * + * Context: This function expects namespace_lock() and lock_mount_hash() + * to have been acquired in that order. + */ +static void mnt_set_mountpoint_beneath(struct mount *new_parent, + struct mount *top_mnt, + struct mountpoint *new_mp) +{ + struct mount *old_top_parent = top_mnt->mnt_parent; + struct mountpoint *old_top_mp = top_mnt->mnt_mp; + + mnt_set_mountpoint(old_top_parent, old_top_mp, new_parent); + mnt_change_mountpoint(new_parent, new_mp, top_mnt); +} + + static void __attach_mnt(struct mount *mnt, struct mount *parent) { hlist_add_head_rcu(&mnt->mnt_hash, @@ -933,15 +960,42 @@ static void __attach_mnt(struct mount *mnt, struct mount *parent) list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); } -/* - * vfsmount lock must be held for write +/** + * attach_mnt - mount a mount, attach to @mount_hashtable and parent's + * list of child mounts + * @parent: the parent + * @mnt: the new mount + * @mp: the new mountpoint + * @beneath: whether to mount @mnt beneath or on top of @parent + * + * If @beneath is false, mount @mnt at @mp on @parent. Then attach @mnt + * to @parent's child mount list and to @mount_hashtable. + * + * If @beneath is true, remove @mnt from its current parent and + * mountpoint and mount it on @mp on @parent, and mount @parent on the + * old parent and old mountpoint of @mnt. Finally, attach @parent to + * @mnt_hashtable and @parent->mnt_parent->mnt_mounts. + * + * Note, when __attach_mnt() is called @mnt->mnt_parent already points + * to the correct parent. + * + * Context: This function expects namespace_lock() and lock_mount_hash() + * to have been acquired in that order. */ -static void attach_mnt(struct mount *mnt, - struct mount *parent, - struct mountpoint *mp) +static void attach_mnt(struct mount *mnt, struct mount *parent, + struct mountpoint *mp, bool beneath) { - mnt_set_mountpoint(parent, mp, mnt); - __attach_mnt(mnt, parent); + if (beneath) + mnt_set_mountpoint_beneath(mnt, parent, mp); + else + mnt_set_mountpoint(parent, mp, mnt); + /* + * Note, @mnt->mnt_parent has to be used. If @mnt was mounted + * beneath @parent then @mnt will need to be attached to + * @parent's old parent, not @parent. IOW, @mnt->mnt_parent + * isn't the same mount as @parent. + */ + __attach_mnt(mnt, mnt->mnt_parent); } void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct mount *mnt) @@ -953,7 +1007,7 @@ void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct m hlist_del_init(&mnt->mnt_mp_list); hlist_del_init_rcu(&mnt->mnt_hash); - attach_mnt(mnt, parent, mp); + attach_mnt(mnt, parent, mp, false); put_mountpoint(old_mp); mnt_add_count(old_parent, -1); @@ -1954,7 +2008,7 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, goto out; lock_mount_hash(); list_add_tail(&q->mnt_list, &res->mnt_list); - attach_mnt(q, parent, p->mnt_mp); + attach_mnt(q, parent, p->mnt_mp, false); unlock_mount_hash(); } } @@ -2163,12 +2217,17 @@ int count_mounts(struct mnt_namespace *ns, struct mount *mnt) return 0; } -/* - * @source_mnt : mount tree to be attached - * @nd : place the mount tree @source_mnt is attached - * @parent_nd : if non-null, detach the source_mnt from its parent and - * store the parent mount and mountpoint dentry. - * (done when source_mnt is moved) +enum mnt_tree_flags_t { + MNT_TREE_MOVE = BIT(0), + MNT_TREE_BENEATH = BIT(1), +}; + +/** + * attach_recursive_mnt - attach a source mount tree + * @source_mnt: mount tree to be attached + * @top_mnt: mount that @source_mnt will be mounted on or mounted beneath + * @dest_mp: the mountpoint @source_mnt will be mounted at + * @flags: modify how @source_mnt is supposed to be attached * * NOTE: in the table below explains the semantics when a source mount * of a given type is attached to a destination mount of a given type. @@ -2225,22 +2284,28 @@ int count_mounts(struct mnt_namespace *ns, struct mount *mnt) * applied to each mount in the tree. * Must be called without spinlocks held, since this function can sleep * in allocations. + * + * Context: The function expects namespace_lock() to be held. + * Return: If @source_mnt was successfully attached 0 is returned. + * Otherwise a negative error code is returned. */ static int attach_recursive_mnt(struct mount *source_mnt, - struct mount *dest_mnt, - struct mountpoint *dest_mp, - bool moving) + struct mount *top_mnt, + struct mountpoint *dest_mp, + enum mnt_tree_flags_t flags) { struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns; HLIST_HEAD(tree_list); - struct mnt_namespace *ns = dest_mnt->mnt_ns; + struct mnt_namespace *ns = top_mnt->mnt_ns; struct mountpoint *smp; - struct mount *child, *p; + struct mount *child, *dest_mnt, *p; struct hlist_node *n; - int err; + int err = 0; + bool moving = flags & MNT_TREE_MOVE, beneath = flags & MNT_TREE_BENEATH; - /* Preallocate a mountpoint in case the new mounts need - * to be tucked under other mounts. + /* + * Preallocate a mountpoint in case the new mounts need to be + * mounted beneath mounts on the same mountpoint. */ smp = get_mountpoint(source_mnt->mnt.mnt_root); if (IS_ERR(smp)) @@ -2253,29 +2318,41 @@ static int attach_recursive_mnt(struct mount *source_mnt, goto out; } + if (beneath) + dest_mnt = top_mnt->mnt_parent; + else + dest_mnt = top_mnt; + if (IS_MNT_SHARED(dest_mnt)) { err = invent_group_ids(source_mnt, true); if (err) goto out; err = propagate_mnt(dest_mnt, dest_mp, source_mnt, &tree_list); - lock_mount_hash(); - if (err) - goto out_cleanup_ids; + } + lock_mount_hash(); + if (err) + goto out_cleanup_ids; + + if (IS_MNT_SHARED(dest_mnt)) { for (p = source_mnt; p; p = next_mnt(p, source_mnt)) set_mnt_shared(p); - } else { - lock_mount_hash(); } + if (moving) { + if (beneath) + dest_mp = smp; unhash_mnt(source_mnt); - attach_mnt(source_mnt, dest_mnt, dest_mp); + attach_mnt(source_mnt, top_mnt, dest_mp, beneath); touch_mnt_namespace(source_mnt->mnt_ns); } else { if (source_mnt->mnt_ns) { /* move from anon - the caller will destroy */ list_del_init(&source_mnt->mnt_ns->list); } - mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt); + if (beneath) + mnt_set_mountpoint_beneath(source_mnt, top_mnt, smp); + else + mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt); commit_tree(source_mnt); } @@ -2315,28 +2392,80 @@ static int attach_recursive_mnt(struct mount *source_mnt, return err; } -static struct mountpoint *lock_mount(struct path *path) +/** + * do_lock_mount - lock mount and mountpoint + * @path: target path + * @beneath: whether the intention is to mount beneath @path + * + * Follow the mount stack on @path until the top mount @mnt is found. If + * the initial @path->{mnt,dentry} is a mountpoint lookup the first + * mount stacked on top of it. Then simply follow @{mnt,mnt->mnt_root} + * until nothing is stacked on top of it anymore. + * + * Acquire the inode_lock() on the top mount's ->mnt_root to protect + * against concurrent removal of the new mountpoint from another mount + * namespace. + * + * If @beneath is requested, acquire inode_lock() on @mnt's mountpoint + * @mp on @mnt->mnt_parent must be acquired. This protects against a + * concurrent unlink of @mp->mnt_dentry from another mount namespace + * where @mnt doesn't have a child mount mounted @mp. A concurrent + * removal of @mnt->mnt_root doesn't matter as nothing will be mounted + * on top of it for @beneath. + * + * In addition, @beneath needs to make sure that @mnt hasn't been + * unmounted or moved from its current mountpoint in between dropping + * @mount_lock and acquiring @namespace_sem. For the !@beneath case @mnt + * being unmounted would be detected later by e.g., calling + * check_mnt(mnt) in the function it's called from. For the @beneath + * case however, it's useful to detect it directly in do_lock_mount(). + * If @mnt hasn't been unmounted then @mnt->mnt_mountpoint still points + * to @mnt->mnt_mp->m_dentry. But if @mnt has been unmounted it will + * point to @mnt->mnt_root and @mnt->mnt_mp will be NULL. + * + * Return: Either the target mountpoint on the top mount or the top + * mount's mountpoint. + */ +static struct mountpoint *do_lock_mount(struct path *path, bool beneath) { - struct vfsmount *mnt; + struct vfsmount *mnt = path->mnt; struct dentry *dentry; - struct mountpoint *mp; + struct mountpoint *mp = ERR_PTR(-ENOENT); for (;;) { - dentry = path->dentry; + struct mount *m; + + if (beneath) { + m = real_mount(mnt); + read_seqlock_excl(&mount_lock); + dentry = dget(m->mnt_mountpoint); + read_sequnlock_excl(&mount_lock); + } else { + dentry = path->dentry; + } + inode_lock(dentry->d_inode); if (unlikely(cant_mount(dentry))) { inode_unlock(dentry->d_inode); - return ERR_PTR(-ENOENT); + goto out; } namespace_lock(); + if (beneath && (!is_mounted(mnt) || m->mnt_mountpoint != dentry)) { + namespace_unlock(); + inode_unlock(dentry->d_inode); + goto out; + } + mnt = lookup_mnt(path); if (likely(!mnt)) break; namespace_unlock(); inode_unlock(dentry->d_inode); + if (beneath) + dput(dentry); path_put(path); path->mnt = mnt; path->dentry = dget(mnt->mnt_root); @@ -2348,9 +2477,18 @@ static struct mountpoint *lock_mount(struct path *path) inode_unlock(dentry->d_inode); } +out: + if (beneath) + dput(dentry); + return mp; } +static inline struct mountpoint *lock_mount(struct path *path) +{ + return do_lock_mount(path, false); +} + static void unlock_mount(struct mountpoint *where) { struct dentry *dentry = where->m_dentry; @@ -2372,7 +2510,7 @@ static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp) d_is_dir(mnt->mnt.mnt_root)) return -ENOTDIR; - return attach_recursive_mnt(mnt, p, mp, false); + return attach_recursive_mnt(mnt, p, mp, 0); } /* @@ -2854,7 +2992,110 @@ out: return err; } -static int do_move_mount(struct path *old_path, struct path *new_path) +/** + * path_overmounted - check if path is overmounted + * @path: path to check + * + * Check if path is overmounted, i.e., if there's a mount on top of + * @path->mnt with @path->dentry as mountpoint. + * + * Context: This function expects namespace_lock() to be held. + * Return: If path is overmounted true is returned, false if not. + */ +static inline bool path_overmounted(const struct path *path) +{ + rcu_read_lock(); + if (unlikely(__lookup_mnt(path->mnt, path->dentry))) { + rcu_read_unlock(); + return true; + } + rcu_read_unlock(); + return false; +} + +/** + * can_move_mount_beneath - check that we can mount beneath the top mount + * @from: mount to mount beneath + * @to: mount under which to mount + * + * - Make sure that @to->dentry is actually the root of a mount under + * which we can mount another mount. + * - Make sure that nothing can be mounted beneath the caller's current + * root or the rootfs of the namespace. + * - Make sure that the caller can unmount the topmost mount ensuring + * that the caller could reveal the underlying mountpoint. + * - Ensure that nothing has been mounted on top of @from before we + * grabbed @namespace_sem to avoid creating pointless shadow mounts. + * - Prevent mounting beneath a mount if the propagation relationship + * between the source mount, parent mount, and top mount would lead to + * nonsensical mount trees. + * + * Context: This function expects namespace_lock() to be held. + * Return: On success 0, and on error a negative error code is returned. + */ +static int can_move_mount_beneath(const struct path *from, + const struct path *to, + const struct mountpoint *mp) +{ + struct mount *mnt_from = real_mount(from->mnt), + *mnt_to = real_mount(to->mnt), + *parent_mnt_to = mnt_to->mnt_parent; + + if (!mnt_has_parent(mnt_to)) + return -EINVAL; + + if (!path_mounted(to)) + return -EINVAL; + + if (IS_MNT_LOCKED(mnt_to)) + return -EINVAL; + + /* Avoid creating shadow mounts during mount propagation. */ + if (path_overmounted(from)) + return -EINVAL; + + /* + * Mounting beneath the rootfs only makes sense when the + * semantics of pivot_root(".", ".") are used. + */ + if (&mnt_to->mnt == current->fs->root.mnt) + return -EINVAL; + if (parent_mnt_to == current->nsproxy->mnt_ns->root) + return -EINVAL; + + for (struct mount *p = mnt_from; mnt_has_parent(p); p = p->mnt_parent) + if (p == mnt_to) + return -EINVAL; + + /* + * If the parent mount propagates to the child mount this would + * mean mounting @mnt_from on @mnt_to->mnt_parent and then + * propagating a copy @c of @mnt_from on top of @mnt_to. This + * defeats the whole purpose of mounting beneath another mount. + */ + if (propagation_would_overmount(parent_mnt_to, mnt_to, mp)) + return -EINVAL; + + /* + * If @mnt_to->mnt_parent propagates to @mnt_from this would + * mean propagating a copy @c of @mnt_from on top of @mnt_from. + * Afterwards @mnt_from would be mounted on top of + * @mnt_to->mnt_parent and @mnt_to would be unmounted from + * @mnt->mnt_parent and remounted on @mnt_from. But since @c is + * already mounted on @mnt_from, @mnt_to would ultimately be + * remounted on top of @c. Afterwards, @mnt_from would be + * covered by a copy @c of @mnt_from and @c would be covered by + * @mnt_from itself. This defeats the whole purpose of mounting + * @mnt_from beneath @mnt_to. + */ + if (propagation_would_overmount(parent_mnt_to, mnt_from, mp)) + return -EINVAL; + + return 0; +} + +static int do_move_mount(struct path *old_path, struct path *new_path, + bool beneath) { struct mnt_namespace *ns; struct mount *p; @@ -2863,8 +3104,9 @@ static int do_move_mount(struct path *old_path, struct path *new_path) struct mountpoint *mp, *old_mp; int err; bool attached; + enum mnt_tree_flags_t flags = 0; - mp = lock_mount(new_path); + mp = do_lock_mount(new_path, beneath); if (IS_ERR(mp)) return PTR_ERR(mp); @@ -2872,6 +3114,8 @@ static int do_move_mount(struct path *old_path, struct path *new_path) p = real_mount(new_path->mnt); parent = old->mnt_parent; attached = mnt_has_parent(old); + if (attached) + flags |= MNT_TREE_MOVE; old_mp = old->mnt_mp; ns = old->mnt_ns; @@ -2902,6 +3146,17 @@ static int do_move_mount(struct path *old_path, struct path *new_path) */ if (attached && IS_MNT_SHARED(parent)) goto out; + + if (beneath) { + err = can_move_mount_beneath(old_path, new_path, mp); + if (err) + goto out; + + err = -EINVAL; + p = p->mnt_parent; + flags |= MNT_TREE_BENEATH; + } + /* * Don't move a mount tree containing unbindable mounts to a destination * mount which is shared. @@ -2915,8 +3170,7 @@ static int do_move_mount(struct path *old_path, struct path *new_path) if (p == old) goto out; - err = attach_recursive_mnt(old, real_mount(new_path->mnt), mp, - attached); + err = attach_recursive_mnt(old, real_mount(new_path->mnt), mp, flags); if (err) goto out; @@ -2948,7 +3202,7 @@ static int do_move_mount_old(struct path *path, const char *old_name) if (err) return err; - err = do_move_mount(&old_path, path); + err = do_move_mount(&old_path, path, false); path_put(&old_path); return err; } @@ -3114,13 +3368,10 @@ int finish_automount(struct vfsmount *m, const struct path *path) err = -ENOENT; goto discard_locked; } - rcu_read_lock(); - if (unlikely(__lookup_mnt(path->mnt, dentry))) { - rcu_read_unlock(); + if (path_overmounted(path)) { err = 0; goto discard_locked; } - rcu_read_unlock(); mp = get_mountpoint(dentry); if (IS_ERR(mp)) { err = PTR_ERR(mp); @@ -3812,6 +4063,10 @@ SYSCALL_DEFINE5(move_mount, if (flags & ~MOVE_MOUNT__MASK) return -EINVAL; + if ((flags & (MOVE_MOUNT_BENEATH | MOVE_MOUNT_SET_GROUP)) == + (MOVE_MOUNT_BENEATH | MOVE_MOUNT_SET_GROUP)) + return -EINVAL; + /* If someone gives a pathname, they aren't permitted to move * from an fd that requires unmount as we can't get at the flag * to clear it afterwards. @@ -3841,7 +4096,8 @@ SYSCALL_DEFINE5(move_mount, if (flags & MOVE_MOUNT_SET_GROUP) ret = do_set_group(&from_path, &to_path); else - ret = do_move_mount(&from_path, &to_path); + ret = do_move_mount(&from_path, &to_path, + (flags & MOVE_MOUNT_BENEATH)); out_to: path_put(&to_path); @@ -3974,9 +4230,9 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root, root_mnt->mnt.mnt_flags &= ~MNT_LOCKED; } /* mount old root on put_old */ - attach_mnt(root_mnt, old_mnt, old_mp); + attach_mnt(root_mnt, old_mnt, old_mp, false); /* mount new_root on / */ - attach_mnt(new_mnt, root_parent, root_mp); + attach_mnt(new_mnt, root_parent, root_mp, false); mnt_add_count(root_parent, -1); touch_mnt_namespace(current->nsproxy->mnt_ns); /* A moved mount should not expire automatically */ diff --git a/fs/pnode.c b/fs/pnode.c index 3cede8b18c8b..e4d0340393d5 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -216,7 +216,7 @@ static struct mount *next_group(struct mount *m, struct mount *origin) static struct mount *last_dest, *first_source, *last_source, *dest_master; static struct hlist_head *list; -static inline bool peers(struct mount *m1, struct mount *m2) +static inline bool peers(const struct mount *m1, const struct mount *m2) { return m1->mnt_group_id == m2->mnt_group_id && m1->mnt_group_id; } @@ -354,6 +354,46 @@ static inline int do_refcount_check(struct mount *mnt, int count) return mnt_get_count(mnt) > count; } +/** + * propagation_would_overmount - check whether propagation from @from + * would overmount @to + * @from: shared mount + * @to: mount to check + * @mp: future mountpoint of @to on @from + * + * If @from propagates mounts to @to, @from and @to must either be peers + * or one of the masters in the hierarchy of masters of @to must be a + * peer of @from. + * + * If the root of the @to mount is equal to the future mountpoint @mp of + * the @to mount on @from then @to will be overmounted by whatever is + * propagated to it. + * + * Context: This function expects namespace_lock() to be held and that + * @mp is stable. + * Return: If @from overmounts @to, true is returned, false if not. + */ +bool propagation_would_overmount(const struct mount *from, + const struct mount *to, + const struct mountpoint *mp) +{ + if (!IS_MNT_SHARED(from)) + return false; + + if (IS_MNT_NEW(to)) + return false; + + if (to->mnt.mnt_root != mp->m_dentry) + return false; + + for (const struct mount *m = to; m; m = m->mnt_master) { + if (peers(from, m)) + return true; + } + + return false; +} + /* * check if the mount 'mnt' can be unmounted successfully. * @mnt: the mount to be checked for unmount diff --git a/fs/pnode.h b/fs/pnode.h index 988f1aa9b02a..0b02a6393891 100644 --- a/fs/pnode.h +++ b/fs/pnode.h @@ -53,4 +53,7 @@ struct mount *copy_tree(struct mount *, struct dentry *, int); bool is_path_reachable(struct mount *, struct dentry *, const struct path *root); int count_mounts(struct mnt_namespace *ns, struct mount *mnt); +bool propagation_would_overmount(const struct mount *from, + const struct mount *to, + const struct mountpoint *mp); #endif /* _LINUX_PNODE_H */ diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h index 4d93967f8aea..8eb0d7b758d2 100644 --- a/include/uapi/linux/mount.h +++ b/include/uapi/linux/mount.h @@ -74,7 +74,8 @@ #define MOVE_MOUNT_T_AUTOMOUNTS 0x00000020 /* Follow automounts on to path */ #define MOVE_MOUNT_T_EMPTY_PATH 0x00000040 /* Empty to path permitted */ #define MOVE_MOUNT_SET_GROUP 0x00000100 /* Set sharing group instead */ -#define MOVE_MOUNT__MASK 0x00000177 +#define MOVE_MOUNT_BENEATH 0x00000200 /* Mount beneath top mount */ +#define MOVE_MOUNT__MASK 0x00000377 /* * fsopen() flags. -- cgit v1.2.3 From 62fe99cef94a5900cac3bf15fd03ee8baad1a99c Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 19 May 2023 14:50:29 +0800 Subject: ublk: add read()/write() support for ublk char device Support pread()/pwrite() on ublk char device for reading/writing request io buffer, so data copy between io request buffer and userspace buffer can be moved to ublk server from ublk driver. Then UBLK_F_NEED_GET_DATA becomes not necessary, so ublk server can allocate buffer without one extra round uring command communication for userspace to provide buffer. IO buffer can be located by iocb->ki_pos which encodes buffer offset, io tag and queue id info, and type of iocb->ki_pos is u64, so it is big enough for holding reasonable queue depth, nr_queues and max io buffer size. Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20230519065030.351216-7-ming.lei@redhat.com Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 151 ++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/ublk_cmd.h | 22 +++++- 2 files changed, 172 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 13523c37a165..ec40ac4f9af3 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -207,6 +207,23 @@ static unsigned int ublks_added; /* protected by ublk_ctl_mutex */ static struct miscdevice ublk_misc; +static inline unsigned ublk_pos_to_hwq(loff_t pos) +{ + return ((pos - UBLKSRV_IO_BUF_OFFSET) >> UBLK_QID_OFF) & + UBLK_QID_BITS_MASK; +} + +static inline unsigned ublk_pos_to_buf_off(loff_t pos) +{ + return (pos - UBLKSRV_IO_BUF_OFFSET) & UBLK_IO_BUF_BITS_MASK; +} + +static inline unsigned ublk_pos_to_tag(loff_t pos) +{ + return ((pos - UBLKSRV_IO_BUF_OFFSET) >> UBLK_TAG_OFF) & + UBLK_TAG_BITS_MASK; +} + static void ublk_dev_param_basic_apply(struct ublk_device *ub) { struct request_queue *q = ub->ub_disk->queue; @@ -1429,6 +1446,36 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd, return -EIOCBQUEUED; } +static inline struct request *__ublk_check_and_get_req(struct ublk_device *ub, + struct ublk_queue *ubq, int tag, size_t offset) +{ + struct request *req; + + if (!ublk_need_req_ref(ubq)) + return NULL; + + req = blk_mq_tag_to_rq(ub->tag_set.tags[ubq->q_id], tag); + if (!req) + return NULL; + + if (!ublk_get_req_ref(ubq, req)) + return NULL; + + if (unlikely(!blk_mq_request_started(req) || req->tag != tag)) + goto fail_put; + + if (!ublk_rq_has_data(req)) + goto fail_put; + + if (offset > blk_rq_bytes(req)) + goto fail_put; + + return req; +fail_put: + ublk_put_req_ref(ubq, req); + return NULL; +} + static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) { /* @@ -1446,11 +1493,112 @@ static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) return __ublk_ch_uring_cmd(cmd, issue_flags, &ub_cmd); } +static inline bool ublk_check_ubuf_dir(const struct request *req, + int ubuf_dir) +{ + /* copy ubuf to request pages */ + if (req_op(req) == REQ_OP_READ && ubuf_dir == ITER_SOURCE) + return true; + + /* copy request pages to ubuf */ + if (req_op(req) == REQ_OP_WRITE && ubuf_dir == ITER_DEST) + return true; + + return false; +} + +static struct request *ublk_check_and_get_req(struct kiocb *iocb, + struct iov_iter *iter, size_t *off, int dir) +{ + struct ublk_device *ub = iocb->ki_filp->private_data; + struct ublk_queue *ubq; + struct request *req; + size_t buf_off; + u16 tag, q_id; + + if (!ub) + return ERR_PTR(-EACCES); + + if (!user_backed_iter(iter)) + return ERR_PTR(-EACCES); + + if (ub->dev_info.state == UBLK_S_DEV_DEAD) + return ERR_PTR(-EACCES); + + tag = ublk_pos_to_tag(iocb->ki_pos); + q_id = ublk_pos_to_hwq(iocb->ki_pos); + buf_off = ublk_pos_to_buf_off(iocb->ki_pos); + + if (q_id >= ub->dev_info.nr_hw_queues) + return ERR_PTR(-EINVAL); + + ubq = ublk_get_queue(ub, q_id); + if (!ubq) + return ERR_PTR(-EINVAL); + + if (tag >= ubq->q_depth) + return ERR_PTR(-EINVAL); + + req = __ublk_check_and_get_req(ub, ubq, tag, buf_off); + if (!req) + return ERR_PTR(-EINVAL); + + if (!req->mq_hctx || !req->mq_hctx->driver_data) + goto fail; + + if (!ublk_check_ubuf_dir(req, dir)) + goto fail; + + *off = buf_off; + return req; +fail: + ublk_put_req_ref(ubq, req); + return ERR_PTR(-EACCES); +} + +static ssize_t ublk_ch_read_iter(struct kiocb *iocb, struct iov_iter *to) +{ + struct ublk_queue *ubq; + struct request *req; + size_t buf_off; + size_t ret; + + req = ublk_check_and_get_req(iocb, to, &buf_off, ITER_DEST); + if (IS_ERR(req)) + return PTR_ERR(req); + + ret = ublk_copy_user_pages(req, buf_off, to, ITER_DEST); + ubq = req->mq_hctx->driver_data; + ublk_put_req_ref(ubq, req); + + return ret; +} + +static ssize_t ublk_ch_write_iter(struct kiocb *iocb, struct iov_iter *from) +{ + struct ublk_queue *ubq; + struct request *req; + size_t buf_off; + size_t ret; + + req = ublk_check_and_get_req(iocb, from, &buf_off, ITER_SOURCE); + if (IS_ERR(req)) + return PTR_ERR(req); + + ret = ublk_copy_user_pages(req, buf_off, from, ITER_SOURCE); + ubq = req->mq_hctx->driver_data; + ublk_put_req_ref(ubq, req); + + return ret; +} + static const struct file_operations ublk_ch_fops = { .owner = THIS_MODULE, .open = ublk_ch_open, .release = ublk_ch_release, .llseek = no_llseek, + .read_iter = ublk_ch_read_iter, + .write_iter = ublk_ch_write_iter, .uring_cmd = ublk_ch_uring_cmd, .mmap = ublk_ch_mmap, }; @@ -2362,6 +2510,9 @@ static int __init ublk_init(void) { int ret; + BUILD_BUG_ON((u64)UBLKSRV_IO_BUF_OFFSET + + UBLKSRV_IO_BUF_TOTAL_SIZE < UBLKSRV_IO_BUF_OFFSET); + init_waitqueue_head(&ublk_idr_wq); ret = misc_register(&ublk_misc); diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 640bf687b94a..c0c1632c671e 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -93,9 +93,29 @@ #define UBLKSRV_CMD_BUF_OFFSET 0 #define UBLKSRV_IO_BUF_OFFSET 0x80000000 -/* tag bit is 12bit, so at most 4096 IOs for each queue */ +/* tag bit is 16bit, so far limit at most 4096 IOs for each queue */ #define UBLK_MAX_QUEUE_DEPTH 4096 +/* single IO buffer max size is 32MB */ +#define UBLK_IO_BUF_OFF 0 +#define UBLK_IO_BUF_BITS 25 +#define UBLK_IO_BUF_BITS_MASK ((1ULL << UBLK_IO_BUF_BITS) - 1) + +/* so at most 64K IOs for each queue */ +#define UBLK_TAG_OFF UBLK_IO_BUF_BITS +#define UBLK_TAG_BITS 16 +#define UBLK_TAG_BITS_MASK ((1ULL << UBLK_TAG_BITS) - 1) + +/* max 4096 queues */ +#define UBLK_QID_OFF (UBLK_TAG_OFF + UBLK_TAG_BITS) +#define UBLK_QID_BITS 12 +#define UBLK_QID_BITS_MASK ((1ULL << UBLK_QID_BITS) - 1) + +#define UBLK_MAX_NR_QUEUES (1U << UBLK_QID_BITS) + +#define UBLKSRV_IO_BUF_TOTAL_BITS (UBLK_QID_OFF + UBLK_QID_BITS) +#define UBLKSRV_IO_BUF_TOTAL_SIZE (1ULL << UBLKSRV_IO_BUF_TOTAL_BITS) + /* * zero copy requires 4k block size, and can remap ublk driver's io * request into ublksrv's vm space -- cgit v1.2.3 From 1172d5b8beca6b899deb9f7f2850e7e47ec16198 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 19 May 2023 14:50:30 +0800 Subject: ublk: support user copy Currently copy between io request buffer(pages) and userspace buffer is done inside ublk_map_io() or ublk_unmap_io(). This way performs very well in case of pre-allocated userspace io buffer. For dynamically allocated or external userspace backend io buffer, UBLK_F_NEED_GET_DATA is added for ublk server to provide buffer by one extra command communication for WRITE request. For READ, userspace simply provides buffer, but can't know when the buffer is done[1]. Add UBLK_F_USER_COPY by moving io data copy out of kernel by providing read()/write() on /dev/ublkcN, and simply let ublk server do the io data copy. This way makes both side cleaner, the cost is that one extra syscall for copy io data between request and backend buffer. With UBLK_F_USER_COPY, it actually becomes possible to run per-io zero copy now, such as, only do zero copy for big size IO, so it can be thought as one prep patch for supporting zero copy. Meantime zero copy still needs to expose read()/write() buffer for some corner case, such as passthrough IO. [1] READ buffer in UBLK_F_NEED_GET_DATA https://lore.kernel.org/linux-block/116d8a56-0881-56d3-9bcc-78ff3e1dc4e5@linux.alibaba.com/T/#m23bd4b8634c0a054e6797063167b469949a247bb ublksrv loop usercopy code: https://github.com/ming1/ubdsrv/commits/usercopy Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20230519065030.351216-8-ming.lei@redhat.com Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 58 +++++++++++++++++++++++++++++++++++-------- include/uapi/linux/ublk_cmd.h | 3 +++ 2 files changed, 50 insertions(+), 11 deletions(-) (limited to 'include/uapi') diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index ec40ac4f9af3..e00733b6fea8 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -55,7 +55,8 @@ | UBLK_F_USER_RECOVERY \ | UBLK_F_USER_RECOVERY_REISSUE \ | UBLK_F_UNPRIVILEGED_DEV \ - | UBLK_F_CMD_IOCTL_ENCODE) + | UBLK_F_CMD_IOCTL_ENCODE \ + | UBLK_F_USER_COPY) /* All UBLK_PARAM_TYPE_* should be included here */ #define UBLK_PARAM_TYPE_ALL (UBLK_PARAM_TYPE_BASIC | \ @@ -312,9 +313,18 @@ static int ublk_apply_params(struct ublk_device *ub) return 0; } +static inline bool ublk_support_user_copy(const struct ublk_queue *ubq) +{ + return ubq->flags & UBLK_F_USER_COPY; +} + static inline bool ublk_need_req_ref(const struct ublk_queue *ubq) { - return false; + /* + * read()/write() is involved in user copy, so request reference + * has to be grabbed + */ + return ublk_support_user_copy(ubq); } static inline void ublk_init_req_ref(const struct ublk_queue *ubq, @@ -591,6 +601,9 @@ static int ublk_map_io(const struct ublk_queue *ubq, const struct request *req, { const unsigned int rq_bytes = blk_rq_bytes(req); + if (ublk_support_user_copy(ubq)) + return rq_bytes; + /* * no zero copy, we delay copy WRITE request data into ublksrv * context and the big benefit is that pinning pages in current @@ -615,6 +628,9 @@ static int ublk_unmap_io(const struct ublk_queue *ubq, { const unsigned int rq_bytes = blk_rq_bytes(req); + if (ublk_support_user_copy(ubq)) + return rq_bytes; + if (ublk_need_unmap_req(req)) { struct iov_iter iter; struct iovec iov; @@ -1390,6 +1406,11 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd, ^ (_IOC_NR(cmd_op) == UBLK_IO_NEED_GET_DATA)) goto out; + if (ublk_support_user_copy(ubq) && ub_cmd->addr) { + ret = -EINVAL; + goto out; + } + ret = ublk_check_cmd_op(cmd_op); if (ret) goto out; @@ -1408,23 +1429,34 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd, */ if (io->flags & UBLK_IO_FLAG_OWNED_BY_SRV) goto out; - /* FETCH_RQ has to provide IO buffer if NEED GET DATA is not enabled */ - if (!ub_cmd->addr && !ublk_need_get_data(ubq)) - goto out; + + if (!ublk_support_user_copy(ubq)) { + /* + * FETCH_RQ has to provide IO buffer if NEED GET + * DATA is not enabled + */ + if (!ub_cmd->addr && !ublk_need_get_data(ubq)) + goto out; + } ublk_fill_io_cmd(io, cmd, ub_cmd->addr); ublk_mark_io_ready(ub, ubq); break; case UBLK_IO_COMMIT_AND_FETCH_REQ: req = blk_mq_tag_to_rq(ub->tag_set.tags[ub_cmd->q_id], tag); - /* - * COMMIT_AND_FETCH_REQ has to provide IO buffer if NEED GET DATA is - * not enabled or it is Read IO. - */ - if (!ub_cmd->addr && (!ublk_need_get_data(ubq) || req_op(req) == REQ_OP_READ)) - goto out; + if (!(io->flags & UBLK_IO_FLAG_OWNED_BY_SRV)) goto out; + + if (!ublk_support_user_copy(ubq)) { + /* + * COMMIT_AND_FETCH_REQ has to provide IO buffer if + * NEED GET DATA is not enabled or it is Read IO. + */ + if (!ub_cmd->addr && (!ublk_need_get_data(ubq) || + req_op(req) == REQ_OP_READ)) + goto out; + } ublk_fill_io_cmd(io, cmd, ub_cmd->addr); ublk_commit_completion(ub, ub_cmd); break; @@ -1996,6 +2028,10 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd) ub->dev_info.flags |= UBLK_F_CMD_IOCTL_ENCODE | UBLK_F_URING_CMD_COMP_IN_TASK; + /* GET_DATA isn't needed any more with USER_COPY */ + if (ub->dev_info.flags & UBLK_F_USER_COPY) + ub->dev_info.flags &= ~UBLK_F_NEED_GET_DATA; + /* We are not ready to support zero copy */ ub->dev_info.flags &= ~UBLK_F_SUPPORT_ZERO_COPY; diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index c0c1632c671e..54b5b0aeefca 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -165,6 +165,9 @@ /* use ioctl encoding for uring command */ #define UBLK_F_CMD_IOCTL_ENCODE (1UL << 6) +/* Copy between request and user buffer by pread()/pwrite() */ +#define UBLK_F_USER_COPY (1UL << 7) + /* device state */ #define UBLK_S_DEV_DEAD 0 #define UBLK_S_DEV_LIVE 1 -- cgit v1.2.3 From bc4be0a38b63b6d4d00a58b10e164f56049be2c2 Mon Sep 17 00:00:00 2001 From: Tvrtko Ursulin Date: Fri, 19 May 2023 08:49:45 -0700 Subject: drm/i915/pmu: Prepare for multi-tile non-engine counters Reserve some bits in the counter config namespace which will carry the tile id and prepare the code to handle this. No per tile counters have been added yet. v2: - Fix checkpatch issues - Use 4 bits for gt id in non-engine counters. Drop FIXME. - Set MAX GTs to 4. Drop FIXME. v3: (Ashutosh, Tvrtko) - Drop BUG_ON that would never fire - Make enable u64 - Pull in some code from next patch v4: Set I915_PMU_MAX_GTS to 2 (Tvrtko) v5: s/u64/u32 where needed (Ashutosh) Signed-off-by: Tvrtko Ursulin Signed-off-by: Umesh Nerlige Ramappa Reviewed-by: Ashutosh Dixit Link: https://patchwork.freedesktop.org/patch/msgid/20230519154946.3751971-7-umesh.nerlige.ramappa@intel.com --- drivers/gpu/drm/i915/i915_pmu.c | 146 +++++++++++++++++++++++++++++----------- drivers/gpu/drm/i915/i915_pmu.h | 9 ++- include/uapi/drm/i915_drm.h | 17 ++++- 3 files changed, 127 insertions(+), 45 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index ecb57a94143e..5cfc322e69b4 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -56,11 +56,21 @@ static bool is_engine_config(const u64 config) return config < __I915_PMU_OTHER(0); } +static unsigned int config_gt_id(const u64 config) +{ + return config >> __I915_PMU_GT_SHIFT; +} + +static u64 config_counter(const u64 config) +{ + return config & ~(~0ULL << __I915_PMU_GT_SHIFT); +} + static unsigned int other_bit(const u64 config) { unsigned int val; - switch (config) { + switch (config_counter(config)) { case I915_PMU_ACTUAL_FREQUENCY: val = __I915_PMU_ACTUAL_FREQUENCY_ENABLED; break; @@ -78,7 +88,9 @@ static unsigned int other_bit(const u64 config) return -1; } - return I915_ENGINE_SAMPLE_COUNT + val; + return I915_ENGINE_SAMPLE_COUNT + + config_gt_id(config) * __I915_PMU_TRACKED_EVENT_COUNT + + val; } static unsigned int config_bit(const u64 config) @@ -115,6 +127,18 @@ static unsigned int event_bit(struct perf_event *event) return config_bit(event->attr.config); } +static u32 frequency_enabled_mask(void) +{ + unsigned int i; + u32 mask = 0; + + for (i = 0; i < I915_PMU_MAX_GTS; i++) + mask |= config_mask(__I915_PMU_ACTUAL_FREQUENCY(i)) | + config_mask(__I915_PMU_REQUESTED_FREQUENCY(i)); + + return mask; +} + static bool pmu_needs_timer(struct i915_pmu *pmu, bool gpu_active) { struct drm_i915_private *i915 = container_of(pmu, typeof(*i915), pmu); @@ -131,9 +155,7 @@ static bool pmu_needs_timer(struct i915_pmu *pmu, bool gpu_active) * Mask out all the ones which do not need the timer, or in * other words keep all the ones that could need the timer. */ - enable &= config_mask(I915_PMU_ACTUAL_FREQUENCY) | - config_mask(I915_PMU_REQUESTED_FREQUENCY) | - ENGINE_SAMPLE_MASK; + enable &= frequency_enabled_mask() | ENGINE_SAMPLE_MASK; /* * When the GPU is idle per-engine counters do not need to be @@ -175,9 +197,37 @@ static inline s64 ktime_since_raw(const ktime_t kt) return ktime_to_ns(ktime_sub(ktime_get_raw(), kt)); } +static unsigned int +__sample_idx(struct i915_pmu *pmu, unsigned int gt_id, int sample) +{ + unsigned int idx = gt_id * __I915_NUM_PMU_SAMPLERS + sample; + + GEM_BUG_ON(idx >= ARRAY_SIZE(pmu->sample)); + + return idx; +} + +static u64 read_sample(struct i915_pmu *pmu, unsigned int gt_id, int sample) +{ + return pmu->sample[__sample_idx(pmu, gt_id, sample)].cur; +} + +static void +store_sample(struct i915_pmu *pmu, unsigned int gt_id, int sample, u64 val) +{ + pmu->sample[__sample_idx(pmu, gt_id, sample)].cur = val; +} + +static void +add_sample_mult(struct i915_pmu *pmu, unsigned int gt_id, int sample, u32 val, u32 mul) +{ + pmu->sample[__sample_idx(pmu, gt_id, sample)].cur += mul_u32_u32(val, mul); +} + static u64 get_rc6(struct intel_gt *gt) { struct drm_i915_private *i915 = gt->i915; + const unsigned int gt_id = gt->info.id; struct i915_pmu *pmu = &i915->pmu; unsigned long flags; bool awake = false; @@ -192,7 +242,7 @@ static u64 get_rc6(struct intel_gt *gt) spin_lock_irqsave(&pmu->lock, flags); if (awake) { - pmu->sample[__I915_SAMPLE_RC6].cur = val; + store_sample(pmu, gt_id, __I915_SAMPLE_RC6, val); } else { /* * We think we are runtime suspended. @@ -201,14 +251,14 @@ static u64 get_rc6(struct intel_gt *gt) * on top of the last known real value, as the approximated RC6 * counter value. */ - val = ktime_since_raw(pmu->sleep_last); - val += pmu->sample[__I915_SAMPLE_RC6].cur; + val = ktime_since_raw(pmu->sleep_last[gt_id]); + val += read_sample(pmu, gt_id, __I915_SAMPLE_RC6); } - if (val < pmu->sample[__I915_SAMPLE_RC6_LAST_REPORTED].cur) - val = pmu->sample[__I915_SAMPLE_RC6_LAST_REPORTED].cur; + if (val < read_sample(pmu, gt_id, __I915_SAMPLE_RC6_LAST_REPORTED)) + val = read_sample(pmu, gt_id, __I915_SAMPLE_RC6_LAST_REPORTED); else - pmu->sample[__I915_SAMPLE_RC6_LAST_REPORTED].cur = val; + store_sample(pmu, gt_id, __I915_SAMPLE_RC6_LAST_REPORTED, val); spin_unlock_irqrestore(&pmu->lock, flags); @@ -218,13 +268,20 @@ static u64 get_rc6(struct intel_gt *gt) static void init_rc6(struct i915_pmu *pmu) { struct drm_i915_private *i915 = container_of(pmu, typeof(*i915), pmu); - intel_wakeref_t wakeref; + struct intel_gt *gt; + unsigned int i; + + for_each_gt(gt, i915, i) { + intel_wakeref_t wakeref; + + with_intel_runtime_pm(gt->uncore->rpm, wakeref) { + u64 val = __get_rc6(gt); - with_intel_runtime_pm(to_gt(i915)->uncore->rpm, wakeref) { - pmu->sample[__I915_SAMPLE_RC6].cur = __get_rc6(to_gt(i915)); - pmu->sample[__I915_SAMPLE_RC6_LAST_REPORTED].cur = - pmu->sample[__I915_SAMPLE_RC6].cur; - pmu->sleep_last = ktime_get_raw(); + store_sample(pmu, i, __I915_SAMPLE_RC6, val); + store_sample(pmu, i, __I915_SAMPLE_RC6_LAST_REPORTED, + val); + pmu->sleep_last[i] = ktime_get_raw(); + } } } @@ -232,8 +289,8 @@ static void park_rc6(struct intel_gt *gt) { struct i915_pmu *pmu = >->i915->pmu; - pmu->sample[__I915_SAMPLE_RC6].cur = __get_rc6(gt); - pmu->sleep_last = ktime_get_raw(); + store_sample(pmu, gt->info.id, __I915_SAMPLE_RC6, __get_rc6(gt)); + pmu->sleep_last[gt->info.id] = ktime_get_raw(); } static void __i915_pmu_maybe_start_timer(struct i915_pmu *pmu) @@ -373,34 +430,30 @@ engines_sample(struct intel_gt *gt, unsigned int period_ns) } } -static void -add_sample_mult(struct i915_pmu_sample *sample, u32 val, u32 mul) -{ - sample->cur += mul_u32_u32(val, mul); -} - -static bool frequency_sampling_enabled(struct i915_pmu *pmu) +static bool +frequency_sampling_enabled(struct i915_pmu *pmu, unsigned int gt) { return pmu->enable & - (config_mask(I915_PMU_ACTUAL_FREQUENCY) | - config_mask(I915_PMU_REQUESTED_FREQUENCY)); + (config_mask(__I915_PMU_ACTUAL_FREQUENCY(gt)) | + config_mask(__I915_PMU_REQUESTED_FREQUENCY(gt))); } static void frequency_sample(struct intel_gt *gt, unsigned int period_ns) { struct drm_i915_private *i915 = gt->i915; + const unsigned int gt_id = gt->info.id; struct i915_pmu *pmu = &i915->pmu; struct intel_rps *rps = >->rps; - if (!frequency_sampling_enabled(pmu)) + if (!frequency_sampling_enabled(pmu, gt_id)) return; /* Report 0/0 (actual/requested) frequency while parked. */ if (!intel_gt_pm_get_if_awake(gt)) return; - if (pmu->enable & config_mask(I915_PMU_ACTUAL_FREQUENCY)) { + if (pmu->enable & config_mask(__I915_PMU_ACTUAL_FREQUENCY(gt_id))) { u32 val; /* @@ -416,12 +469,12 @@ frequency_sample(struct intel_gt *gt, unsigned int period_ns) if (!val) val = intel_gpu_freq(rps, rps->cur_freq); - add_sample_mult(&pmu->sample[__I915_SAMPLE_FREQ_ACT], + add_sample_mult(pmu, gt_id, __I915_SAMPLE_FREQ_ACT, val, period_ns / 1000); } - if (pmu->enable & config_mask(I915_PMU_REQUESTED_FREQUENCY)) { - add_sample_mult(&pmu->sample[__I915_SAMPLE_FREQ_REQ], + if (pmu->enable & config_mask(__I915_PMU_REQUESTED_FREQUENCY(gt_id))) { + add_sample_mult(pmu, gt_id, __I915_SAMPLE_FREQ_REQ, intel_rps_get_requested_frequency(rps), period_ns / 1000); } @@ -458,9 +511,7 @@ static enum hrtimer_restart i915_sample(struct hrtimer *hrtimer) continue; engines_sample(gt, period_ns); - - if (i == 0) /* FIXME */ - frequency_sample(gt, period_ns); + frequency_sample(gt, period_ns); } hrtimer_forward(hrtimer, now, ns_to_ktime(PERIOD)); @@ -502,7 +553,13 @@ config_status(struct drm_i915_private *i915, u64 config) { struct intel_gt *gt = to_gt(i915); - switch (config) { + unsigned int gt_id = config_gt_id(config); + unsigned int max_gt_id = HAS_EXTRA_GT_LIST(i915) ? 1 : 0; + + if (gt_id > max_gt_id) + return -ENOENT; + + switch (config_counter(config)) { case I915_PMU_ACTUAL_FREQUENCY: if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) /* Requires a mutex for sampling! */ @@ -513,6 +570,8 @@ config_status(struct drm_i915_private *i915, u64 config) return -ENODEV; break; case I915_PMU_INTERRUPTS: + if (gt_id) + return -ENOENT; break; case I915_PMU_RC6_RESIDENCY: if (!gt->rc6.supported) @@ -610,22 +669,27 @@ static u64 __i915_pmu_event_read(struct perf_event *event) val = engine->pmu.sample[sample].cur; } } else { - switch (event->attr.config) { + const unsigned int gt_id = config_gt_id(event->attr.config); + const u64 config = config_counter(event->attr.config); + + switch (config) { case I915_PMU_ACTUAL_FREQUENCY: val = - div_u64(pmu->sample[__I915_SAMPLE_FREQ_ACT].cur, + div_u64(read_sample(pmu, gt_id, + __I915_SAMPLE_FREQ_ACT), USEC_PER_SEC /* to MHz */); break; case I915_PMU_REQUESTED_FREQUENCY: val = - div_u64(pmu->sample[__I915_SAMPLE_FREQ_REQ].cur, + div_u64(read_sample(pmu, gt_id, + __I915_SAMPLE_FREQ_REQ), USEC_PER_SEC /* to MHz */); break; case I915_PMU_INTERRUPTS: val = READ_ONCE(pmu->irq_count); break; case I915_PMU_RC6_RESIDENCY: - val = get_rc6(to_gt(i915)); + val = get_rc6(i915->gt[gt_id]); break; case I915_PMU_SOFTWARE_GT_AWAKE_TIME: val = ktime_to_ns(intel_gt_get_awake_time(to_gt(i915))); diff --git a/drivers/gpu/drm/i915/i915_pmu.h b/drivers/gpu/drm/i915/i915_pmu.h index 3a811266ac6a..33d80fbaab8b 100644 --- a/drivers/gpu/drm/i915/i915_pmu.h +++ b/drivers/gpu/drm/i915/i915_pmu.h @@ -38,13 +38,16 @@ enum { __I915_NUM_PMU_SAMPLERS }; +#define I915_PMU_MAX_GTS 2 + /* * How many different events we track in the global PMU mask. * * It is also used to know to needed number of event reference counters. */ #define I915_PMU_MASK_BITS \ - (I915_ENGINE_SAMPLE_COUNT + __I915_PMU_TRACKED_EVENT_COUNT) + (I915_ENGINE_SAMPLE_COUNT + \ + I915_PMU_MAX_GTS * __I915_PMU_TRACKED_EVENT_COUNT) #define I915_ENGINE_SAMPLE_COUNT (I915_SAMPLE_SEMA + 1) @@ -124,11 +127,11 @@ struct i915_pmu { * Only global counters are held here, while the per-engine ones are in * struct intel_engine_cs. */ - struct i915_pmu_sample sample[__I915_NUM_PMU_SAMPLERS]; + struct i915_pmu_sample sample[I915_PMU_MAX_GTS * __I915_NUM_PMU_SAMPLERS]; /** * @sleep_last: Last time GT parked for RC6 estimation. */ - ktime_t sleep_last; + ktime_t sleep_last[I915_PMU_MAX_GTS]; /** * @irq_count: Number of interrupts * diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index ba40855dbc93..f31dfacde601 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -280,7 +280,16 @@ enum drm_i915_pmu_engine_sample { #define I915_PMU_ENGINE_SEMA(class, instance) \ __I915_PMU_ENGINE(class, instance, I915_SAMPLE_SEMA) -#define __I915_PMU_OTHER(x) (__I915_PMU_ENGINE(0xff, 0xff, 0xf) + 1 + (x)) +/* + * Top 4 bits of every non-engine counter are GT id. + */ +#define __I915_PMU_GT_SHIFT (60) + +#define ___I915_PMU_OTHER(gt, x) \ + (((__u64)__I915_PMU_ENGINE(0xff, 0xff, 0xf) + 1 + (x)) | \ + ((__u64)(gt) << __I915_PMU_GT_SHIFT)) + +#define __I915_PMU_OTHER(x) ___I915_PMU_OTHER(0, x) #define I915_PMU_ACTUAL_FREQUENCY __I915_PMU_OTHER(0) #define I915_PMU_REQUESTED_FREQUENCY __I915_PMU_OTHER(1) @@ -290,6 +299,12 @@ enum drm_i915_pmu_engine_sample { #define I915_PMU_LAST /* Deprecated - do not use */ I915_PMU_RC6_RESIDENCY +#define __I915_PMU_ACTUAL_FREQUENCY(gt) ___I915_PMU_OTHER(gt, 0) +#define __I915_PMU_REQUESTED_FREQUENCY(gt) ___I915_PMU_OTHER(gt, 1) +#define __I915_PMU_INTERRUPTS(gt) ___I915_PMU_OTHER(gt, 2) +#define __I915_PMU_RC6_RESIDENCY(gt) ___I915_PMU_OTHER(gt, 3) +#define __I915_PMU_SOFTWARE_GT_AWAKE_TIME(gt) ___I915_PMU_OTHER(gt, 4) + /* Each region is a minimum of 16k, and there are at most 255 of them. */ #define I915_NR_TEX_REGIONS 255 /* table size 2k - maximum due to use -- cgit v1.2.3 From e3a8a5b726bdd903de52bee6ba7c935c09d07ee8 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 23 May 2023 09:53:24 +0200 Subject: ALSA: rawmidi: UMP support This patch adds the support helpers for UMP (Universal MIDI Packet) in ALSA core. The basic design is that a rawmidi instance is assigned to each UMP Endpoint. A UMP Endpoint provides a UMP stream, typically bidirectional (but can be also uni-directional, too), which may hold up to 16 UMP Groups, where each UMP (input/output) Group corresponds to the traditional MIDI I/O Endpoint. Additionally, the ALSA UMP abstraction provides the multiple UMP Blocks that can be assigned to each UMP Endpoint. A UMP Block is a metadata to hold the UMP Group clusters, and can represent the functions assigned to each UMP Group. A typical implementation of UMP Block is the Group Terminal Blocks of USB MIDI 2.0 specification. For distinguishing from the legacy byte-stream MIDI device, a new device "umpC*D*" will be created, instead of the standard (MIDI 1.0) devices "midiC*D*". The UMP instance can be identified by the new rawmidi info bit SNDRV_RAWMIDI_INFO_UMP, too. A UMP rawmidi device reads/writes only in 4-bytes words alignment, stored in CPU native endianness. The transmit and receive functions take care of the input/out data alignment, and may return zero or aligned size, and the params ioctl may return -EINVAL when the given input/output buffer size isn't aligned. A few new UMP-specific ioctls are added for obtaining the new UMP endpoint and block information. As of this commit, no ALSA sequencer instance is attached to UMP devices yet. They will be supported by later patches. Along with those changes, the protocol version for rawmidi is bumped to 2.0.3. Reviewed-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20230523075358.9672-4-tiwai@suse.de Signed-off-by: Takashi Iwai --- include/sound/rawmidi.h | 8 ++ include/sound/ump.h | 118 +++++++++++++++++++++++ include/uapi/sound/asound.h | 57 ++++++++++- sound/core/Kconfig | 4 + sound/core/Makefile | 2 + sound/core/rawmidi.c | 139 ++++++++++++++++++-------- sound/core/rawmidi_compat.c | 4 + sound/core/ump.c | 230 ++++++++++++++++++++++++++++++++++++++++++++ 8 files changed, 521 insertions(+), 41 deletions(-) create mode 100644 include/sound/ump.h create mode 100644 sound/core/ump.c (limited to 'include/uapi') diff --git a/include/sound/rawmidi.h b/include/sound/rawmidi.h index 84413cfcdcb5..b8a230a7583b 100644 --- a/include/sound/rawmidi.h +++ b/include/sound/rawmidi.h @@ -63,6 +63,7 @@ struct snd_rawmidi_runtime { size_t avail_min; /* min avail for wakeup */ size_t avail; /* max used buffer for wakeup */ size_t xruns; /* over/underruns counter */ + size_t align; /* alignment (0 = byte stream, 3 = UMP) */ int buffer_ref; /* buffer reference count */ /* misc */ wait_queue_head_t sleep; @@ -148,6 +149,13 @@ int snd_rawmidi_new(struct snd_card *card, char *id, int device, void snd_rawmidi_set_ops(struct snd_rawmidi *rmidi, int stream, const struct snd_rawmidi_ops *ops); +/* internal */ +int snd_rawmidi_init(struct snd_rawmidi *rmidi, + struct snd_card *card, char *id, int device, + int output_count, int input_count, + unsigned int info_flags); +int snd_rawmidi_free(struct snd_rawmidi *rmidi); + /* callbacks */ int snd_rawmidi_receive(struct snd_rawmidi_substream *substream, diff --git a/include/sound/ump.h b/include/sound/ump.h new file mode 100644 index 000000000000..8a3ac97cd1d3 --- /dev/null +++ b/include/sound/ump.h @@ -0,0 +1,118 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Universal MIDI Packet (UMP) Support + */ +#ifndef __SOUND_UMP_H +#define __SOUND_UMP_H + +#include + +struct snd_ump_endpoint; +struct snd_ump_block; + +struct snd_ump_endpoint { + struct snd_rawmidi core; /* raw UMP access */ + + struct snd_ump_endpoint_info info; + + void *private_data; + void (*private_free)(struct snd_ump_endpoint *ump); + + struct list_head block_list; /* list of snd_ump_block objects */ +}; + +struct snd_ump_block { + struct snd_ump_block_info info; + struct snd_ump_endpoint *ump; + + void *private_data; + void (*private_free)(struct snd_ump_block *blk); + + struct list_head list; +}; + +#define rawmidi_to_ump(rmidi) container_of(rmidi, struct snd_ump_endpoint, core) + +int snd_ump_endpoint_new(struct snd_card *card, char *id, int device, + int output, int input, + struct snd_ump_endpoint **ump_ret); +int snd_ump_block_new(struct snd_ump_endpoint *ump, unsigned int blk, + unsigned int direction, unsigned int first_group, + unsigned int num_groups, struct snd_ump_block **blk_ret); + +/* + * Some definitions for UMP + */ + +/* MIDI 2.0 Message Type */ +enum { + UMP_MSG_TYPE_UTILITY = 0x00, + UMP_MSG_TYPE_SYSTEM = 0x01, + UMP_MSG_TYPE_MIDI1_CHANNEL_VOICE = 0x02, + UMP_MSG_TYPE_DATA = 0x03, + UMP_MSG_TYPE_MIDI2_CHANNEL_VOICE = 0x04, + UMP_MSG_TYPE_EXTENDED_DATA = 0x05, +}; + +/* MIDI 2.0 SysEx / Data Status; same values for both 7-bit and 8-bit SysEx */ +enum { + UMP_SYSEX_STATUS_SINGLE = 0, + UMP_SYSEX_STATUS_START = 1, + UMP_SYSEX_STATUS_CONTINUE = 2, + UMP_SYSEX_STATUS_END = 3, +}; + +/* + * Helpers for retrieving / filling bits from UMP + */ +/* get the message type (4bit) from a UMP packet (header) */ +static inline unsigned char ump_message_type(u32 data) +{ + return data >> 28; +} + +/* get the group number (0-based, 4bit) from a UMP packet (header) */ +static inline unsigned char ump_message_group(u32 data) +{ + return (data >> 24) & 0x0f; +} + +/* get the MIDI status code (4bit) from a UMP packet (header) */ +static inline unsigned char ump_message_status_code(u32 data) +{ + return (data >> 20) & 0x0f; +} + +/* get the MIDI channel number (0-based, 4bit) from a UMP packet (header) */ +static inline unsigned char ump_message_channel(u32 data) +{ + return (data >> 16) & 0x0f; +} + +/* get the MIDI status + channel combo byte (8bit) from a UMP packet (header) */ +static inline unsigned char ump_message_status_channel(u32 data) +{ + return (data >> 16) & 0xff; +} + +/* compose a UMP packet (header) from type, group and status values */ +static inline u32 ump_compose(unsigned char type, unsigned char group, + unsigned char status, unsigned char channel) +{ + return ((u32)type << 28) | ((u32)group << 24) | ((u32)status << 20) | + ((u32)channel << 16); +} + +/* get SysEx message status (for both 7 and 8bits) from a UMP packet (header) */ +static inline unsigned char ump_sysex_message_status(u32 data) +{ + return (data >> 20) & 0xf; +} + +/* get SysEx message length (for both 7 and 8bits) from a UMP packet (header) */ +static inline unsigned char ump_sysex_message_length(u32 data) +{ + return (data >> 16) & 0xf; +} + +#endif /* __SOUND_UMP_H */ diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h index 0aa955aa8246..b001df4b335e 100644 --- a/include/uapi/sound/asound.h +++ b/include/uapi/sound/asound.h @@ -708,7 +708,7 @@ enum { * Raw MIDI section - /dev/snd/midi?? */ -#define SNDRV_RAWMIDI_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 2) +#define SNDRV_RAWMIDI_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 3) enum { SNDRV_RAWMIDI_STREAM_OUTPUT = 0, @@ -719,6 +719,7 @@ enum { #define SNDRV_RAWMIDI_INFO_OUTPUT 0x00000001 #define SNDRV_RAWMIDI_INFO_INPUT 0x00000002 #define SNDRV_RAWMIDI_INFO_DUPLEX 0x00000004 +#define SNDRV_RAWMIDI_INFO_UMP 0x00000008 struct snd_rawmidi_info { unsigned int device; /* RO/WR (control): device number */ @@ -779,6 +780,57 @@ struct snd_rawmidi_status { }; #endif +/* UMP EP Protocol / JRTS capability bits */ +#define SNDRV_UMP_EP_INFO_PROTO_MIDI_MASK 0x0300 +#define SNDRV_UMP_EP_INFO_PROTO_MIDI1 0x0100 /* MIDI 1.0 */ +#define SNDRV_UMP_EP_INFO_PROTO_MIDI2 0x0200 /* MIDI 2.0 */ +#define SNDRV_UMP_EP_INFO_PROTO_JRTS_MASK 0x0003 +#define SNDRV_UMP_EP_INFO_PROTO_JRTS_TX 0x0001 /* JRTS Transmit */ +#define SNDRV_UMP_EP_INFO_PROTO_JRTS_RX 0x0002 /* JRTS Receive */ + +/* UMP Endpoint information */ +struct snd_ump_endpoint_info { + int card; /* card number */ + int device; /* device number */ + unsigned int flags; /* additional info */ + unsigned int protocol_caps; /* protocol capabilities */ + unsigned int protocol; /* current protocol */ + unsigned int num_blocks; /* # of function blocks */ + unsigned short version; /* UMP major/minor version */ + unsigned short padding[7]; + unsigned char name[128]; /* endpoint name string */ + unsigned char product_id[128]; /* unique product id string */ + unsigned char reserved[32]; +} __packed; + +/* UMP direction */ +#define SNDRV_UMP_DIR_INPUT 0x01 +#define SNDRV_UMP_DIR_OUTPUT 0x02 +#define SNDRV_UMP_DIR_BIDIRECTION 0x03 + +/* UMP block info flags */ +#define SNDRV_UMP_BLOCK_IS_MIDI1 (1U << 0) /* MIDI 1.0 port w/o restrict */ +#define SNDRV_UMP_BLOCK_IS_LOWSPEED (1U << 1) /* 31.25Kbps B/W MIDI1 port */ + +/* UMP groups and blocks */ +#define SNDRV_UMP_MAX_GROUPS 16 +#define SNDRV_UMP_MAX_BLOCKS 32 + +/* UMP Block information */ +struct snd_ump_block_info { + int card; /* card number */ + int device; /* device number */ + unsigned char block_id; /* block ID (R/W) */ + unsigned char direction; /* UMP direction */ + unsigned char active; /* Activeness */ + unsigned char first_group; /* first group ID */ + unsigned char num_groups; /* number of groups */ + unsigned char padding[3]; + unsigned int flags; /* various info flags */ + unsigned char name[128]; /* block name string */ + unsigned char reserved[32]; +} __packed; + #define SNDRV_RAWMIDI_IOCTL_PVERSION _IOR('W', 0x00, int) #define SNDRV_RAWMIDI_IOCTL_INFO _IOR('W', 0x01, struct snd_rawmidi_info) #define SNDRV_RAWMIDI_IOCTL_USER_PVERSION _IOW('W', 0x02, int) @@ -786,6 +838,9 @@ struct snd_rawmidi_status { #define SNDRV_RAWMIDI_IOCTL_STATUS _IOWR('W', 0x20, struct snd_rawmidi_status) #define SNDRV_RAWMIDI_IOCTL_DROP _IOW('W', 0x30, int) #define SNDRV_RAWMIDI_IOCTL_DRAIN _IOW('W', 0x31, int) +/* Additional ioctls for UMP rawmidi devices */ +#define SNDRV_UMP_IOCTL_ENDPOINT_INFO _IOR('W', 0x40, struct snd_ump_endpoint_info) +#define SNDRV_UMP_IOCTL_BLOCK_INFO _IOR('W', 0x41, struct snd_ump_block_info) /* * Timer section - /dev/snd/timer diff --git a/sound/core/Kconfig b/sound/core/Kconfig index 12990d9a4dff..eb1c6c930de9 100644 --- a/sound/core/Kconfig +++ b/sound/core/Kconfig @@ -26,6 +26,10 @@ config SND_RAWMIDI tristate select SND_SEQ_DEVICE if SND_SEQUENCER != n +config SND_UMP + tristate + select SND_RAWMIDI + config SND_COMPRESS_OFFLOAD tristate diff --git a/sound/core/Makefile b/sound/core/Makefile index 2762f03d9b7b..562a05edbc50 100644 --- a/sound/core/Makefile +++ b/sound/core/Makefile @@ -28,6 +28,7 @@ snd-pcm-dmaengine-objs := pcm_dmaengine.o snd-ctl-led-objs := control_led.o snd-rawmidi-objs := rawmidi.o +snd-ump-objs := ump.o snd-timer-objs := timer.o snd-hrtimer-objs := hrtimer.o snd-rtctimer-objs := rtctimer.o @@ -45,6 +46,7 @@ obj-$(CONFIG_SND_PCM) += snd-pcm.o obj-$(CONFIG_SND_DMAENGINE_PCM) += snd-pcm-dmaengine.o obj-$(CONFIG_SND_SEQ_DEVICE) += snd-seq-device.o obj-$(CONFIG_SND_RAWMIDI) += snd-rawmidi.o +obj-$(CONFIG_SND_UMP) += snd-ump.o obj-$(CONFIG_SND_OSSEMUL) += oss/ obj-$(CONFIG_SND_SEQUENCER) += seq/ diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index ab28cfc1fac8..6360e2239a63 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -21,6 +21,7 @@ #include #include #include +#include MODULE_AUTHOR("Jaroslav Kysela "); MODULE_DESCRIPTION("Midlevel RawMidi code for ALSA."); @@ -35,7 +36,6 @@ module_param_array(amidi_map, int, NULL, 0444); MODULE_PARM_DESC(amidi_map, "Raw MIDI device number assigned to 2nd OSS device."); #endif /* CONFIG_SND_OSSEMUL */ -static int snd_rawmidi_free(struct snd_rawmidi *rmidi); static int snd_rawmidi_dev_free(struct snd_device *device); static int snd_rawmidi_dev_register(struct snd_device *device); static int snd_rawmidi_dev_disconnect(struct snd_device *device); @@ -73,6 +73,9 @@ struct snd_rawmidi_status64 { #define SNDRV_RAWMIDI_IOCTL_STATUS64 _IOWR('W', 0x20, struct snd_rawmidi_status64) +#define rawmidi_is_ump(rmidi) \ + (IS_ENABLED(CONFIG_SND_UMP) && ((rmidi)->info_flags & SNDRV_RAWMIDI_INFO_UMP)) + static struct snd_rawmidi *snd_rawmidi_search(struct snd_card *card, int device) { struct snd_rawmidi *rawmidi; @@ -181,9 +184,23 @@ static int snd_rawmidi_runtime_create(struct snd_rawmidi_substream *substream) } runtime->appl_ptr = runtime->hw_ptr = 0; substream->runtime = runtime; + if (rawmidi_is_ump(substream->rmidi)) + runtime->align = 3; return 0; } +/* get the current alignment (either 0 or 3) */ +static inline int get_align(struct snd_rawmidi_runtime *runtime) +{ + if (IS_ENABLED(CONFIG_SND_UMP)) + return runtime->align; + else + return 0; +} + +/* get the trimmed size with the current alignment */ +#define get_aligned_size(runtime, size) ((size) & ~get_align(runtime)) + static int snd_rawmidi_runtime_free(struct snd_rawmidi_substream *substream) { struct snd_rawmidi_runtime *runtime = substream->runtime; @@ -721,6 +738,8 @@ static int resize_runtime_buffer(struct snd_rawmidi_substream *substream, return -EINVAL; if (params->avail_min < 1 || params->avail_min > params->buffer_size) return -EINVAL; + if (params->buffer_size & get_align(runtime)) + return -EINVAL; if (params->buffer_size != runtime->buffer_size) { newbuf = kvzalloc(params->buffer_size, GFP_KERNEL); if (!newbuf) @@ -1046,12 +1065,13 @@ static int receive_with_tstamp_framing(struct snd_rawmidi_substream *substream, struct snd_rawmidi_framing_tstamp frame = { .tv_sec = tstamp->tv_sec, .tv_nsec = tstamp->tv_nsec }; int orig_count = src_count; int frame_size = sizeof(struct snd_rawmidi_framing_tstamp); + int align = get_align(runtime); BUILD_BUG_ON(frame_size != 0x20); if (snd_BUG_ON((runtime->hw_ptr & 0x1f) != 0)) return -EINVAL; - while (src_count > 0) { + while (src_count > align) { if ((int)(runtime->buffer_size - runtime->avail) < frame_size) { runtime->xruns += src_count; break; @@ -1059,7 +1079,9 @@ static int receive_with_tstamp_framing(struct snd_rawmidi_substream *substream, if (src_count >= SNDRV_RAWMIDI_FRAMING_DATA_LENGTH) frame.length = SNDRV_RAWMIDI_FRAMING_DATA_LENGTH; else { - frame.length = src_count; + frame.length = get_aligned_size(runtime, src_count); + if (!frame.length) + break; memset(frame.data, 0, SNDRV_RAWMIDI_FRAMING_DATA_LENGTH); } memcpy(frame.data, buffer, frame.length); @@ -1123,6 +1145,10 @@ int snd_rawmidi_receive(struct snd_rawmidi_substream *substream, goto unlock; } + count = get_aligned_size(runtime, count); + if (!count) + goto unlock; + if (substream->framing == SNDRV_RAWMIDI_MODE_FRAMING_TSTAMP) { result = receive_with_tstamp_framing(substream, buffer, count, &ts64); } else if (count == 1) { /* special case, faster code */ @@ -1142,6 +1168,9 @@ int snd_rawmidi_receive(struct snd_rawmidi_substream *substream, count1 = count; if (count1 > (int)(runtime->buffer_size - runtime->avail)) count1 = runtime->buffer_size - runtime->avail; + count1 = get_aligned_size(runtime, count1); + if (!count1) + goto unlock; memcpy(runtime->buffer + runtime->hw_ptr, buffer, count1); runtime->hw_ptr += count1; runtime->hw_ptr %= runtime->buffer_size; @@ -1342,12 +1371,18 @@ static int __snd_rawmidi_transmit_peek(struct snd_rawmidi_substream *substream, count1 = count; if (count1 > (int)(runtime->buffer_size - runtime->avail)) count1 = runtime->buffer_size - runtime->avail; + count1 = get_aligned_size(runtime, count1); + if (!count1) + goto __skip; memcpy(buffer, runtime->buffer + runtime->hw_ptr, count1); count -= count1; result += count1; if (count > 0) { if (count > (int)(runtime->buffer_size - runtime->avail - count1)) count = runtime->buffer_size - runtime->avail - count1; + count = get_aligned_size(runtime, count); + if (!count) + goto __skip; memcpy(buffer + count1, runtime->buffer, count); result += count; } @@ -1404,6 +1439,7 @@ static int __snd_rawmidi_transmit_ack(struct snd_rawmidi_substream *substream, return -EINVAL; } snd_BUG_ON(runtime->avail + count > runtime->buffer_size); + count = get_aligned_size(runtime, count); runtime->hw_ptr += count; runtime->hw_ptr %= runtime->buffer_size; runtime->avail += count; @@ -1690,6 +1726,9 @@ static void snd_rawmidi_proc_info_read(struct snd_info_entry *entry, rmidi = entry->private_data; snd_iprintf(buffer, "%s\n\n", rmidi->name); + if (IS_ENABLED(CONFIG_SND_UMP)) + snd_iprintf(buffer, "Type: %s\n", + rawmidi_is_ump(rmidi) ? "UMP" : "Legacy"); mutex_lock(&rmidi->open_mutex); if (rmidi->info_flags & SNDRV_RAWMIDI_INFO_OUTPUT) { list_for_each_entry(substream, @@ -1800,25 +1839,12 @@ static void release_rawmidi_device(struct device *dev) kfree(container_of(dev, struct snd_rawmidi, dev)); } -/** - * snd_rawmidi_new - create a rawmidi instance - * @card: the card instance - * @id: the id string - * @device: the device index - * @output_count: the number of output streams - * @input_count: the number of input streams - * @rrawmidi: the pointer to store the new rawmidi instance - * - * Creates a new rawmidi instance. - * Use snd_rawmidi_set_ops() to set the operators to the new instance. - * - * Return: Zero if successful, or a negative error code on failure. - */ -int snd_rawmidi_new(struct snd_card *card, char *id, int device, - int output_count, int input_count, - struct snd_rawmidi **rrawmidi) +/* used for both rawmidi and ump */ +int snd_rawmidi_init(struct snd_rawmidi *rmidi, + struct snd_card *card, char *id, int device, + int output_count, int input_count, + unsigned int info_flags) { - struct snd_rawmidi *rmidi; int err; static const struct snd_device_ops ops = { .dev_free = snd_rawmidi_dev_free, @@ -1826,50 +1852,78 @@ int snd_rawmidi_new(struct snd_card *card, char *id, int device, .dev_disconnect = snd_rawmidi_dev_disconnect, }; - if (snd_BUG_ON(!card)) - return -ENXIO; - if (rrawmidi) - *rrawmidi = NULL; - rmidi = kzalloc(sizeof(*rmidi), GFP_KERNEL); - if (!rmidi) - return -ENOMEM; rmidi->card = card; rmidi->device = device; mutex_init(&rmidi->open_mutex); init_waitqueue_head(&rmidi->open_wait); INIT_LIST_HEAD(&rmidi->streams[SNDRV_RAWMIDI_STREAM_INPUT].substreams); INIT_LIST_HEAD(&rmidi->streams[SNDRV_RAWMIDI_STREAM_OUTPUT].substreams); + rmidi->info_flags = info_flags; if (id != NULL) strscpy(rmidi->id, id, sizeof(rmidi->id)); snd_device_initialize(&rmidi->dev, card); rmidi->dev.release = release_rawmidi_device; - dev_set_name(&rmidi->dev, "midiC%iD%i", card->number, device); + if (rawmidi_is_ump(rmidi)) + dev_set_name(&rmidi->dev, "umpC%iD%i", card->number, device); + else + dev_set_name(&rmidi->dev, "midiC%iD%i", card->number, device); err = snd_rawmidi_alloc_substreams(rmidi, &rmidi->streams[SNDRV_RAWMIDI_STREAM_INPUT], SNDRV_RAWMIDI_STREAM_INPUT, input_count); if (err < 0) - goto error; + return err; err = snd_rawmidi_alloc_substreams(rmidi, &rmidi->streams[SNDRV_RAWMIDI_STREAM_OUTPUT], SNDRV_RAWMIDI_STREAM_OUTPUT, output_count); if (err < 0) - goto error; + return err; err = snd_device_new(card, SNDRV_DEV_RAWMIDI, rmidi, &ops); if (err < 0) - goto error; + return err; + return 0; +} +EXPORT_SYMBOL_GPL(snd_rawmidi_init); + +/** + * snd_rawmidi_new - create a rawmidi instance + * @card: the card instance + * @id: the id string + * @device: the device index + * @output_count: the number of output streams + * @input_count: the number of input streams + * @rrawmidi: the pointer to store the new rawmidi instance + * + * Creates a new rawmidi instance. + * Use snd_rawmidi_set_ops() to set the operators to the new instance. + * + * Return: Zero if successful, or a negative error code on failure. + */ +int snd_rawmidi_new(struct snd_card *card, char *id, int device, + int output_count, int input_count, + struct snd_rawmidi **rrawmidi) +{ + struct snd_rawmidi *rmidi; + int err; + if (rrawmidi) + *rrawmidi = NULL; + rmidi = kzalloc(sizeof(*rmidi), GFP_KERNEL); + if (!rmidi) + return -ENOMEM; + err = snd_rawmidi_init(rmidi, card, id, device, + output_count, input_count, 0); + if (err < 0) { + snd_rawmidi_free(rmidi); + return err; + } if (rrawmidi) *rrawmidi = rmidi; return 0; - - error: - snd_rawmidi_free(rmidi); - return err; } EXPORT_SYMBOL(snd_rawmidi_new); @@ -1884,7 +1938,8 @@ static void snd_rawmidi_free_substreams(struct snd_rawmidi_str *stream) } } -static int snd_rawmidi_free(struct snd_rawmidi *rmidi) +/* called from ump.c, too */ +int snd_rawmidi_free(struct snd_rawmidi *rmidi) { if (!rmidi) return 0; @@ -1901,6 +1956,7 @@ static int snd_rawmidi_free(struct snd_rawmidi *rmidi) put_device(&rmidi->dev); return 0; } +EXPORT_SYMBOL_GPL(snd_rawmidi_free); static int snd_rawmidi_dev_free(struct snd_device *device) { @@ -1951,7 +2007,8 @@ static int snd_rawmidi_dev_register(struct snd_device *device) } #ifdef CONFIG_SND_OSSEMUL rmidi->ossreg = 0; - if ((int)rmidi->device == midi_map[rmidi->card->number]) { + if (!rawmidi_is_ump(rmidi) && + (int)rmidi->device == midi_map[rmidi->card->number]) { if (snd_register_oss_device(SNDRV_OSS_DEVICE_TYPE_MIDI, rmidi->card, 0, &snd_rawmidi_f_ops, rmidi) < 0) { @@ -1965,7 +2022,8 @@ static int snd_rawmidi_dev_register(struct snd_device *device) #endif } } - if ((int)rmidi->device == amidi_map[rmidi->card->number]) { + if (!rawmidi_is_ump(rmidi) && + (int)rmidi->device == amidi_map[rmidi->card->number]) { if (snd_register_oss_device(SNDRV_OSS_DEVICE_TYPE_MIDI, rmidi->card, 1, &snd_rawmidi_f_ops, rmidi) < 0) { @@ -1989,7 +2047,8 @@ static int snd_rawmidi_dev_register(struct snd_device *device) } rmidi->proc_entry = entry; #if IS_ENABLED(CONFIG_SND_SEQUENCER) - if (!rmidi->ops || !rmidi->ops->dev_register) { /* own registration mechanism */ + /* no own registration mechanism? */ + if (!rmidi->ops || !rmidi->ops->dev_register) { if (snd_seq_device_new(rmidi->card, rmidi->device, SNDRV_SEQ_DEV_ID_MIDISYNTH, 0, &rmidi->seq_dev) >= 0) { rmidi->seq_dev->private_data = rmidi; rmidi->seq_dev->private_free = snd_rawmidi_dev_seq_free; diff --git a/sound/core/rawmidi_compat.c b/sound/core/rawmidi_compat.c index 68a93443583c..b81b30d82f88 100644 --- a/sound/core/rawmidi_compat.c +++ b/sound/core/rawmidi_compat.c @@ -111,6 +111,10 @@ static long snd_rawmidi_ioctl_compat(struct file *file, unsigned int cmd, unsign case SNDRV_RAWMIDI_IOCTL_INFO: case SNDRV_RAWMIDI_IOCTL_DROP: case SNDRV_RAWMIDI_IOCTL_DRAIN: +#if IS_ENABLED(CONFIG_SND_UMP) + case SNDRV_UMP_IOCTL_ENDPOINT_INFO: + case SNDRV_UMP_IOCTL_BLOCK_INFO: +#endif return snd_rawmidi_ioctl(file, cmd, (unsigned long)argp); case SNDRV_RAWMIDI_IOCTL_PARAMS32: return snd_rawmidi_ioctl_params_compat(rfile, argp); diff --git a/sound/core/ump.c b/sound/core/ump.c new file mode 100644 index 000000000000..ee57ba1ee989 --- /dev/null +++ b/sound/core/ump.c @@ -0,0 +1,230 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Universal MIDI Packet (UMP) support + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#define ump_err(ump, fmt, args...) dev_err(&(ump)->core.dev, fmt, ##args) +#define ump_warn(ump, fmt, args...) dev_warn(&(ump)->core.dev, fmt, ##args) +#define ump_info(ump, fmt, args...) dev_info(&(ump)->core.dev, fmt, ##args) +#define ump_dbg(ump, fmt, args...) dev_dbg(&(ump)->core.dev, fmt, ##args) + +static int snd_ump_dev_register(struct snd_rawmidi *rmidi); +static int snd_ump_dev_unregister(struct snd_rawmidi *rmidi); +static long snd_ump_ioctl(struct snd_rawmidi *rmidi, unsigned int cmd, + void __user *argp); + +static const struct snd_rawmidi_global_ops snd_ump_rawmidi_ops = { + .dev_register = snd_ump_dev_register, + .dev_unregister = snd_ump_dev_unregister, + .ioctl = snd_ump_ioctl, +}; + +static void snd_ump_endpoint_free(struct snd_rawmidi *rmidi) +{ + struct snd_ump_endpoint *ump = rawmidi_to_ump(rmidi); + struct snd_ump_block *fb; + + while (!list_empty(&ump->block_list)) { + fb = list_first_entry(&ump->block_list, struct snd_ump_block, + list); + list_del(&fb->list); + if (fb->private_free) + fb->private_free(fb); + kfree(fb); + } + + if (ump->private_free) + ump->private_free(ump); +} + +/** + * snd_ump_endpoint_new - create a UMP Endpoint object + * @card: the card instance + * @id: the id string for rawmidi + * @device: the device index for rawmidi + * @output: 1 for enabling output + * @input: 1 for enabling input + * @ump_ret: the pointer to store the new UMP instance + * + * Creates a new UMP Endpoint object. A UMP Endpoint is tied with one rawmidi + * instance with one input and/or one output rawmidi stream (either uni- + * or bi-directional). A UMP Endpoint may contain one or multiple UMP Blocks + * that consist of one or multiple UMP Groups. + * + * Use snd_rawmidi_set_ops() to set the operators to the new instance. + * Unlike snd_rawmidi_new(), this function sets up the info_flags by itself + * depending on the given @output and @input. + * + * The device has SNDRV_RAWMIDI_INFO_UMP flag set and a different device + * file ("umpCxDx") than a standard MIDI 1.x device ("midiCxDx") is + * created. + * + * Return: Zero if successful, or a negative error code on failure. + */ +int snd_ump_endpoint_new(struct snd_card *card, char *id, int device, + int output, int input, + struct snd_ump_endpoint **ump_ret) +{ + unsigned int info_flags = SNDRV_RAWMIDI_INFO_UMP; + struct snd_ump_endpoint *ump; + int err; + + if (input) + info_flags |= SNDRV_RAWMIDI_INFO_INPUT; + if (output) + info_flags |= SNDRV_RAWMIDI_INFO_OUTPUT; + if (input && output) + info_flags |= SNDRV_RAWMIDI_INFO_DUPLEX; + + ump = kzalloc(sizeof(*ump), GFP_KERNEL); + if (!ump) + return -ENOMEM; + INIT_LIST_HEAD(&ump->block_list); + err = snd_rawmidi_init(&ump->core, card, id, device, + output, input, info_flags); + if (err < 0) { + snd_rawmidi_free(&ump->core); + return err; + } + + ump->info.card = card->number; + ump->info.device = device; + + ump->core.private_free = snd_ump_endpoint_free; + ump->core.ops = &snd_ump_rawmidi_ops; + + ump_dbg(ump, "Created a UMP EP #%d (%s)\n", device, id); + *ump_ret = ump; + return 0; +} +EXPORT_SYMBOL_GPL(snd_ump_endpoint_new); + +/* + * Device register / unregister hooks; + * do nothing, placeholders for avoiding the default rawmidi handling + */ +static int snd_ump_dev_register(struct snd_rawmidi *rmidi) +{ + return 0; +} + +static int snd_ump_dev_unregister(struct snd_rawmidi *rmidi) +{ + return 0; +} + +static struct snd_ump_block * +snd_ump_get_block(struct snd_ump_endpoint *ump, unsigned char id) +{ + struct snd_ump_block *fb; + + list_for_each_entry(fb, &ump->block_list, list) { + if (fb->info.block_id == id) + return fb; + } + return NULL; +} + +/** + * snd_ump_block_new - Create a UMP block + * @ump: UMP object + * @blk: block ID number to create + * @direction: direction (in/out/bidirection) + * @first_group: the first group ID (0-based) + * @num_groups: the number of groups in this block + * @blk_ret: the pointer to store the resultant block object + */ +int snd_ump_block_new(struct snd_ump_endpoint *ump, unsigned int blk, + unsigned int direction, unsigned int first_group, + unsigned int num_groups, struct snd_ump_block **blk_ret) +{ + struct snd_ump_block *fb, *p; + + if (blk < 0 || blk >= SNDRV_UMP_MAX_BLOCKS) + return -EINVAL; + + if (snd_ump_get_block(ump, blk)) + return -EBUSY; + + fb = kzalloc(sizeof(*fb), GFP_KERNEL); + if (!fb) + return -ENOMEM; + + fb->ump = ump; + fb->info.card = ump->info.card; + fb->info.device = ump->info.device; + fb->info.block_id = blk; + if (blk >= ump->info.num_blocks) + ump->info.num_blocks = blk + 1; + fb->info.direction = direction; + fb->info.active = 1; + fb->info.first_group = first_group; + fb->info.num_groups = num_groups; + /* fill the default name, may be overwritten to a better name */ + snprintf(fb->info.name, sizeof(fb->info.name), "Group %d-%d", + first_group + 1, first_group + num_groups); + + /* put the entry in the ordered list */ + list_for_each_entry(p, &ump->block_list, list) { + if (p->info.block_id > blk) { + list_add_tail(&fb->list, &p->list); + goto added; + } + } + list_add_tail(&fb->list, &ump->block_list); + + added: + ump_dbg(ump, "Created a UMP Block #%d (%s)\n", blk, fb->info.name); + *blk_ret = fb; + return 0; +} +EXPORT_SYMBOL_GPL(snd_ump_block_new); + +static int snd_ump_ioctl_block(struct snd_ump_endpoint *ump, + struct snd_ump_block_info __user *argp) +{ + struct snd_ump_block *fb; + unsigned char id; + + if (get_user(id, &argp->block_id)) + return -EFAULT; + fb = snd_ump_get_block(ump, id); + if (!fb) + return -ENOENT; + if (copy_to_user(argp, &fb->info, sizeof(fb->info))) + return -EFAULT; + return 0; +} + +/* + * Handle UMP-specific ioctls; called from snd_rawmidi_ioctl() + */ +static long snd_ump_ioctl(struct snd_rawmidi *rmidi, unsigned int cmd, + void __user *argp) +{ + struct snd_ump_endpoint *ump = rawmidi_to_ump(rmidi); + + switch (cmd) { + case SNDRV_UMP_IOCTL_ENDPOINT_INFO: + if (copy_to_user(argp, &ump->info, sizeof(ump->info))) + return -EFAULT; + return 0; + case SNDRV_UMP_IOCTL_BLOCK_INFO: + return snd_ump_ioctl_block(ump, argp); + default: + ump_dbg(ump, "rawmidi: unknown command = 0x%x\n", cmd); + return -ENOTTY; + } +} + +MODULE_DESCRIPTION("Universal MIDI Packet (UMP) Core Driver"); +MODULE_LICENSE("GPL"); -- cgit v1.2.3 From 127ae6f6dad2edb2201e27b7e6fa72994b537fad Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 23 May 2023 09:53:25 +0200 Subject: ALSA: rawmidi: Skip UMP devices at SNDRV_CTL_IOCTL_RAWMIDI_NEXT_DEVICE Applications may look for rawmidi devices with the ioctl SNDRV_CTL_IOCTL_RAWMIDI_NEXT_DEVICE. Returning a UMP device from this ioctl may confuse the existing applications that support only the legacy rawmidi. This patch changes the code to skip the UMP devices from the lookup for avoiding the confusion, and introduces a new ioctl to look for the UMP devices instead. Along with this change, bump the CTL protocol version to 2.0.9. Reviewed-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20230523075358.9672-5-tiwai@suse.de Signed-off-by: Takashi Iwai --- include/uapi/sound/asound.h | 3 ++- sound/core/rawmidi.c | 57 ++++++++++++++++++++++++++++----------------- 2 files changed, 38 insertions(+), 22 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h index b001df4b335e..1e4a21036109 100644 --- a/include/uapi/sound/asound.h +++ b/include/uapi/sound/asound.h @@ -1016,7 +1016,7 @@ struct snd_timer_tread { * * ****************************************************************************/ -#define SNDRV_CTL_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 8) +#define SNDRV_CTL_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 9) struct snd_ctl_card_info { int card; /* card number */ @@ -1177,6 +1177,7 @@ struct snd_ctl_tlv { #define SNDRV_CTL_IOCTL_RAWMIDI_NEXT_DEVICE _IOWR('U', 0x40, int) #define SNDRV_CTL_IOCTL_RAWMIDI_INFO _IOWR('U', 0x41, struct snd_rawmidi_info) #define SNDRV_CTL_IOCTL_RAWMIDI_PREFER_SUBDEVICE _IOW('U', 0x42, int) +#define SNDRV_CTL_IOCTL_UMP_NEXT_DEVICE _IOWR('U', 0x43, int) #define SNDRV_CTL_IOCTL_POWER _IOWR('U', 0xd0, int) #define SNDRV_CTL_IOCTL_POWER_STATE _IOR('U', 0xd1, int) diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index 6360e2239a63..9936ed282b85 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -1012,6 +1012,37 @@ static long snd_rawmidi_ioctl(struct file *file, unsigned int cmd, unsigned long return -ENOTTY; } +/* ioctl to find the next device; either legacy or UMP depending on @find_ump */ +static int snd_rawmidi_next_device(struct snd_card *card, int __user *argp, + bool find_ump) + +{ + struct snd_rawmidi *rmidi; + int device; + bool is_ump; + + if (get_user(device, argp)) + return -EFAULT; + if (device >= SNDRV_RAWMIDI_DEVICES) /* next device is -1 */ + device = SNDRV_RAWMIDI_DEVICES - 1; + mutex_lock(®ister_mutex); + device = device < 0 ? 0 : device + 1; + for (; device < SNDRV_RAWMIDI_DEVICES; device++) { + rmidi = snd_rawmidi_search(card, device); + if (!rmidi) + continue; + is_ump = rawmidi_is_ump(rmidi); + if (find_ump == is_ump) + break; + } + if (device == SNDRV_RAWMIDI_DEVICES) + device = -1; + mutex_unlock(®ister_mutex); + if (put_user(device, argp)) + return -EFAULT; + return 0; +} + static int snd_rawmidi_control_ioctl(struct snd_card *card, struct snd_ctl_file *control, unsigned int cmd, @@ -1021,27 +1052,11 @@ static int snd_rawmidi_control_ioctl(struct snd_card *card, switch (cmd) { case SNDRV_CTL_IOCTL_RAWMIDI_NEXT_DEVICE: - { - int device; - - if (get_user(device, (int __user *)argp)) - return -EFAULT; - if (device >= SNDRV_RAWMIDI_DEVICES) /* next device is -1 */ - device = SNDRV_RAWMIDI_DEVICES - 1; - mutex_lock(®ister_mutex); - device = device < 0 ? 0 : device + 1; - while (device < SNDRV_RAWMIDI_DEVICES) { - if (snd_rawmidi_search(card, device)) - break; - device++; - } - if (device == SNDRV_RAWMIDI_DEVICES) - device = -1; - mutex_unlock(®ister_mutex); - if (put_user(device, (int __user *)argp)) - return -EFAULT; - return 0; - } + return snd_rawmidi_next_device(card, argp, false); +#if IS_ENABLED(CONFIG_SND_UMP) + case SNDRV_CTL_IOCTL_UMP_NEXT_DEVICE: + return snd_rawmidi_next_device(card, argp, true); +#endif case SNDRV_CTL_IOCTL_RAWMIDI_PREFER_SUBDEVICE: { int val; -- cgit v1.2.3 From 30fc139260d46e9bdc06e46eec91e9ff61eb387e Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 23 May 2023 09:53:26 +0200 Subject: ALSA: ump: Add ioctls to inquiry UMP EP and Block info via control API It'd be convenient to have ioctls to inquiry the UMP Endpoint and UMP Block information directly via the control API without opening the rawmidi interface, just like SNDRV_CTL_IOCTL_RAWMIDI_INFO. This patch extends the rawmidi ioctl handler to support those; new ioctls, SNDRV_CTL_IOCTL_UMP_ENDPOINT_INFO and SNDRV_CTL_IOCTL_UMP_BLOCK_INFO, return the snd_ump_endpoint and snd_ump_block data that is specified by the device field, respectively. Suggested-by: Jaroslav Kysela Reviewed-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20230523075358.9672-6-tiwai@suse.de Signed-off-by: Takashi Iwai --- include/uapi/sound/asound.h | 2 ++ sound/core/rawmidi.c | 26 ++++++++++++++++++++++++++ 2 files changed, 28 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h index 1e4a21036109..5c5f41dd4001 100644 --- a/include/uapi/sound/asound.h +++ b/include/uapi/sound/asound.h @@ -1178,6 +1178,8 @@ struct snd_ctl_tlv { #define SNDRV_CTL_IOCTL_RAWMIDI_INFO _IOWR('U', 0x41, struct snd_rawmidi_info) #define SNDRV_CTL_IOCTL_RAWMIDI_PREFER_SUBDEVICE _IOW('U', 0x42, int) #define SNDRV_CTL_IOCTL_UMP_NEXT_DEVICE _IOWR('U', 0x43, int) +#define SNDRV_CTL_IOCTL_UMP_ENDPOINT_INFO _IOWR('U', 0x44, struct snd_ump_endpoint_info) +#define SNDRV_CTL_IOCTL_UMP_BLOCK_INFO _IOWR('U', 0x45, struct snd_ump_block_info) #define SNDRV_CTL_IOCTL_POWER _IOWR('U', 0xd0, int) #define SNDRV_CTL_IOCTL_POWER_STATE _IOR('U', 0xd1, int) diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index 9936ed282b85..ffb5b58105f4 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -1043,6 +1043,28 @@ static int snd_rawmidi_next_device(struct snd_card *card, int __user *argp, return 0; } +#if IS_ENABLED(CONFIG_SND_UMP) +/* inquiry of UMP endpoint and block info via control API */ +static int snd_rawmidi_call_ump_ioctl(struct snd_card *card, int cmd, + void __user *argp) +{ + struct snd_ump_endpoint_info __user *info = argp; + struct snd_rawmidi *rmidi; + int device, ret; + + if (get_user(device, &info->device)) + return -EFAULT; + mutex_lock(®ister_mutex); + rmidi = snd_rawmidi_search(card, device); + if (rmidi && rmidi->ops && rmidi->ops->ioctl) + ret = rmidi->ops->ioctl(rmidi, cmd, argp); + else + ret = -ENXIO; + mutex_unlock(®ister_mutex); + return ret; +} +#endif + static int snd_rawmidi_control_ioctl(struct snd_card *card, struct snd_ctl_file *control, unsigned int cmd, @@ -1056,6 +1078,10 @@ static int snd_rawmidi_control_ioctl(struct snd_card *card, #if IS_ENABLED(CONFIG_SND_UMP) case SNDRV_CTL_IOCTL_UMP_NEXT_DEVICE: return snd_rawmidi_next_device(card, argp, true); + case SNDRV_CTL_IOCTL_UMP_ENDPOINT_INFO: + return snd_rawmidi_call_ump_ioctl(card, SNDRV_UMP_IOCTL_ENDPOINT_INFO, argp); + case SNDRV_CTL_IOCTL_UMP_BLOCK_INFO: + return snd_rawmidi_call_ump_ioctl(card, SNDRV_UMP_IOCTL_BLOCK_INFO, argp); #endif case SNDRV_CTL_IOCTL_RAWMIDI_PREFER_SUBDEVICE: { -- cgit v1.2.3 From afb72505e4614a2ccefe3440d37dec3a2273c330 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 23 May 2023 09:53:45 +0200 Subject: ALSA: seq: Introduce SNDRV_SEQ_IOCTL_USER_PVERSION ioctl For the future extension of ALSA sequencer ABI, introduce a new ioctl SNDRV_SEQ_IOCTL_USER_PVERSION. This is similar like the ioctls used in PCM and other interfaces, for an application to specify its supporting ABI version. The use of this ioctl will be mandatory for the upcoming UMP support. Reviewed-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20230523075358.9672-25-tiwai@suse.de Signed-off-by: Takashi Iwai --- include/uapi/sound/asequencer.h | 1 + sound/core/seq/seq_clientmgr.c | 8 ++++++++ sound/core/seq/seq_clientmgr.h | 1 + sound/core/seq/seq_compat.c | 1 + 4 files changed, 11 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/sound/asequencer.h b/include/uapi/sound/asequencer.h index 00d2703e8fca..4a3c5a718bae 100644 --- a/include/uapi/sound/asequencer.h +++ b/include/uapi/sound/asequencer.h @@ -561,6 +561,7 @@ struct snd_seq_query_subs { #define SNDRV_SEQ_IOCTL_CLIENT_ID _IOR ('S', 0x01, int) #define SNDRV_SEQ_IOCTL_SYSTEM_INFO _IOWR('S', 0x02, struct snd_seq_system_info) #define SNDRV_SEQ_IOCTL_RUNNING_MODE _IOWR('S', 0x03, struct snd_seq_running_info) +#define SNDRV_SEQ_IOCTL_USER_PVERSION _IOW('S', 0x04, int) #define SNDRV_SEQ_IOCTL_GET_CLIENT_INFO _IOWR('S', 0x10, struct snd_seq_client_info) #define SNDRV_SEQ_IOCTL_SET_CLIENT_INFO _IOW ('S', 0x11, struct snd_seq_client_info) diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 0f26f20596d7..89a8d14df83b 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -1056,6 +1056,12 @@ static int snd_seq_ioctl_pversion(struct snd_seq_client *client, void *arg) return 0; } +static int snd_seq_ioctl_user_pversion(struct snd_seq_client *client, void *arg) +{ + client->user_pversion = *(unsigned int *)arg; + return 0; +} + static int snd_seq_ioctl_client_id(struct snd_seq_client *client, void *arg) { int *client_id = arg; @@ -1985,6 +1991,7 @@ static const struct ioctl_handler { int (*func)(struct snd_seq_client *client, void *arg); } ioctl_handlers[] = { { SNDRV_SEQ_IOCTL_PVERSION, snd_seq_ioctl_pversion }, + { SNDRV_SEQ_IOCTL_USER_PVERSION, snd_seq_ioctl_user_pversion }, { SNDRV_SEQ_IOCTL_CLIENT_ID, snd_seq_ioctl_client_id }, { SNDRV_SEQ_IOCTL_SYSTEM_INFO, snd_seq_ioctl_system_info }, { SNDRV_SEQ_IOCTL_RUNNING_MODE, snd_seq_ioctl_running_mode }, @@ -2125,6 +2132,7 @@ int snd_seq_create_kernel_client(struct snd_card *card, int client_index, client->accept_input = 1; client->accept_output = 1; client->data.kernel.card = card; + client->user_pversion = SNDRV_SEQ_VERSION; va_start(args, name_fmt); vsnprintf(client->name, sizeof(client->name), name_fmt, args); diff --git a/sound/core/seq/seq_clientmgr.h b/sound/core/seq/seq_clientmgr.h index f05704e45ab4..abe0ceadf3da 100644 --- a/sound/core/seq/seq_clientmgr.h +++ b/sound/core/seq/seq_clientmgr.h @@ -35,6 +35,7 @@ struct snd_seq_client { snd_seq_client_type_t type; unsigned int accept_input: 1, accept_output: 1; + unsigned int user_pversion; char name[64]; /* client name */ int number; /* client number */ unsigned int filter; /* filter flags */ diff --git a/sound/core/seq/seq_compat.c b/sound/core/seq/seq_compat.c index 54723566ce24..c0ce6236dc7f 100644 --- a/sound/core/seq/seq_compat.c +++ b/sound/core/seq/seq_compat.c @@ -81,6 +81,7 @@ static long snd_seq_ioctl_compat(struct file *file, unsigned int cmd, unsigned l switch (cmd) { case SNDRV_SEQ_IOCTL_PVERSION: + case SNDRV_SEQ_IOCTL_USER_PVERSION: case SNDRV_SEQ_IOCTL_CLIENT_ID: case SNDRV_SEQ_IOCTL_SYSTEM_INFO: case SNDRV_SEQ_IOCTL_GET_CLIENT_INFO: -- cgit v1.2.3 From 46397622a3fa8372b8fda0f04b33d16923b03b1b Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 23 May 2023 09:53:46 +0200 Subject: ALSA: seq: Add UMP support Starting from this commit, we add the basic support of UMP (Universal MIDI Packet) events on ALSA sequencer infrastructure. The biggest change here is that, for transferring UMP packets that are up to 128 bits, we extend the data payload of ALSA sequencer event record when the client is declared to support for the new UMP events. A new event flag bit, SNDRV_SEQ_EVENT_UMP, is defined and it shall be set for the UMP packet events that have the larger payload of 128 bits, defined as struct snd_seq_ump_event. For controlling the UMP feature enablement in kernel, a new Kconfig, CONFIG_SND_SEQ_UMP is introduced. The extended event for UMP is available only when this Kconfig item is set. Similarly, the size of the internal snd_seq_event_cell also increases (in 4 bytes) when the Kconfig item is set. (But the size increase is effective only for 32bit architectures; 64bit archs already have padding there.) Overall, when CONFIG_SND_SEQ_UMP isn't set, there is no change in the event and cell, keeping the old sizes. For applications that want to access the UMP packets, first of all, a sequencer client has to declare the user-protocol to match with the latest one via the new SNDRV_SEQ_IOCTL_USER_PVERSION; otherwise it's treated as if a legacy client without UMP support. Then the client can switch to the new UMP mode (MIDI 1.0 or MIDI 2.0) with a new field, midi_version, in snd_seq_client_info. When switched to UMP mode (midi_version = 1 or 2), the client can write the UMP events with SNDRV_SEQ_EVENT_UMP flag. For reads, the alignment size is changed from snd_seq_event (28 bytes) to snd_seq_ump_event (32 bytes). When a UMP sequencer event is delivered to a legacy sequencer client, it's ignored or handled as an error. Conceptually, ALSA sequencer client and port correspond to the UMP Endpoint and Group, respectively; each client may have multiple ports and each port has the fixed number (16) of channels, total up to 256 channels. As of this commit, ALSA sequencer core just sends and receives the UMP events as-is from/to clients. The automatic conversions between the legacy events and the new UMP events will be implemented in a later patch. Along with this commit, bump the sequencer protocol version to 1.0.3. Reviewed-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20230523075358.9672-26-tiwai@suse.de Signed-off-by: Takashi Iwai --- include/sound/asequencer.h | 4 ++ include/sound/seq_kernel.h | 8 +++ include/uapi/sound/asequencer.h | 53 +++++++++----- sound/core/seq/Kconfig | 7 ++ sound/core/seq/seq_clientmgr.c | 154 ++++++++++++++++++++++++++++------------ sound/core/seq/seq_clientmgr.h | 1 + sound/core/seq/seq_memory.c | 10 ++- sound/core/seq/seq_memory.h | 19 ++++- 8 files changed, 193 insertions(+), 63 deletions(-) (limited to 'include/uapi') diff --git a/include/sound/asequencer.h b/include/sound/asequencer.h index 18d4bc3ee0b7..ddbb6bf801bb 100644 --- a/include/sound/asequencer.h +++ b/include/sound/asequencer.h @@ -65,6 +65,10 @@ #define snd_seq_ev_is_abstime(ev) (snd_seq_ev_timemode_type(ev) == SNDRV_SEQ_TIME_MODE_ABS) #define snd_seq_ev_is_reltime(ev) (snd_seq_ev_timemode_type(ev) == SNDRV_SEQ_TIME_MODE_REL) +/* check whether the given event is a UMP event */ +#define snd_seq_ev_is_ump(ev) \ + (IS_ENABLED(CONFIG_SND_SEQ_UMP) && ((ev)->flags & SNDRV_SEQ_EVENT_UMP)) + /* queue sync port */ #define snd_seq_queue_sync_port(q) ((q) + 16) diff --git a/include/sound/seq_kernel.h b/include/sound/seq_kernel.h index 527e7f8ad661..c8621671fa70 100644 --- a/include/sound/seq_kernel.h +++ b/include/sound/seq_kernel.h @@ -75,6 +75,14 @@ int snd_seq_expand_var_event_at(const struct snd_seq_event *event, int count, int snd_seq_dump_var_event(const struct snd_seq_event *event, snd_seq_dump_func_t func, void *private_data); +/* size of the event packet; it can be greater than snd_seq_event size */ +static inline size_t snd_seq_event_packet_size(struct snd_seq_event *ev) +{ + if (snd_seq_ev_is_ump(ev)) + return sizeof(struct snd_seq_ump_event); + return sizeof(struct snd_seq_event); +} + /* interface for OSS emulation */ int snd_seq_set_queue_tempo(int client, struct snd_seq_queue_tempo *tempo); diff --git a/include/uapi/sound/asequencer.h b/include/uapi/sound/asequencer.h index 4a3c5a718bae..b87950cbfb79 100644 --- a/include/uapi/sound/asequencer.h +++ b/include/uapi/sound/asequencer.h @@ -10,7 +10,7 @@ #include /** version of the sequencer */ -#define SNDRV_SEQ_VERSION SNDRV_PROTOCOL_VERSION(1, 0, 2) +#define SNDRV_SEQ_VERSION SNDRV_PROTOCOL_VERSION(1, 0, 3) /** * definition of sequencer event types @@ -174,6 +174,7 @@ struct snd_seq_connect { #define SNDRV_SEQ_PRIORITY_HIGH (1<<4) /* event should be processed before others */ #define SNDRV_SEQ_PRIORITY_MASK (1<<4) +#define SNDRV_SEQ_EVENT_UMP (1<<5) /* event holds a UMP packet */ /* note event */ struct snd_seq_ev_note { @@ -252,6 +253,19 @@ struct snd_seq_ev_quote { struct snd_seq_event *event; /* quoted event */ } __attribute__((packed)); +union snd_seq_event_data { /* event data... */ + struct snd_seq_ev_note note; + struct snd_seq_ev_ctrl control; + struct snd_seq_ev_raw8 raw8; + struct snd_seq_ev_raw32 raw32; + struct snd_seq_ev_ext ext; + struct snd_seq_ev_queue_control queue; + union snd_seq_timestamp time; + struct snd_seq_addr addr; + struct snd_seq_connect connect; + struct snd_seq_result result; + struct snd_seq_ev_quote quote; +}; /* sequencer event */ struct snd_seq_event { @@ -262,25 +276,27 @@ struct snd_seq_event { unsigned char queue; /* schedule queue */ union snd_seq_timestamp time; /* schedule time */ - struct snd_seq_addr source; /* source address */ struct snd_seq_addr dest; /* destination address */ - union { /* event data... */ - struct snd_seq_ev_note note; - struct snd_seq_ev_ctrl control; - struct snd_seq_ev_raw8 raw8; - struct snd_seq_ev_raw32 raw32; - struct snd_seq_ev_ext ext; - struct snd_seq_ev_queue_control queue; - union snd_seq_timestamp time; - struct snd_seq_addr addr; - struct snd_seq_connect connect; - struct snd_seq_result result; - struct snd_seq_ev_quote quote; - } data; + union snd_seq_event_data data; }; + /* (compatible) event for UMP-capable clients */ +struct snd_seq_ump_event { + snd_seq_event_type_t type; /* event type */ + unsigned char flags; /* event flags */ + char tag; + unsigned char queue; /* schedule queue */ + union snd_seq_timestamp time; /* schedule time */ + struct snd_seq_addr source; /* source address */ + struct snd_seq_addr dest; /* destination address */ + + union { + union snd_seq_event_data data; + unsigned int ump[4]; + }; +}; /* * bounce event - stored as variable size data @@ -344,9 +360,14 @@ struct snd_seq_client_info { int event_lost; /* number of lost events */ int card; /* RO: card number[kernel] */ int pid; /* RO: pid[user] */ - char reserved[56]; /* for future use */ + unsigned int midi_version; /* MIDI version */ + char reserved[52]; /* for future use */ }; +/* MIDI version numbers in client info */ +#define SNDRV_SEQ_CLIENT_LEGACY_MIDI 0 /* Legacy client */ +#define SNDRV_SEQ_CLIENT_UMP_MIDI_1_0 1 /* UMP MIDI 1.0 */ +#define SNDRV_SEQ_CLIENT_UMP_MIDI_2_0 2 /* UMP MIDI 2.0 */ /* client pool size */ struct snd_seq_client_pool { diff --git a/sound/core/seq/Kconfig b/sound/core/seq/Kconfig index f84718a44980..c69d8beb09fa 100644 --- a/sound/core/seq/Kconfig +++ b/sound/core/seq/Kconfig @@ -60,4 +60,11 @@ config SND_SEQ_MIDI_EMUL config SND_SEQ_VIRMIDI tristate +config SND_SEQ_UMP + bool "Support for UMP events" + help + Say Y here to enable the support for handling UMP (Universal MIDI + Packet) events via ALSA sequencer infrastructure, which is an + essential feature for enabling MIDI 2.0 support. + endif # SND_SEQUENCER diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 89a8d14df83b..801d5eee21eb 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -387,6 +387,15 @@ static int snd_seq_release(struct inode *inode, struct file *file) return 0; } +static bool event_is_compatible(const struct snd_seq_client *client, + const struct snd_seq_event *ev) +{ + if (snd_seq_ev_is_ump(ev) && !client->midi_version) + return false; + if (snd_seq_ev_is_ump(ev) && snd_seq_ev_is_variable(ev)) + return false; + return true; +} /* handle client read() */ /* possible error values: @@ -400,6 +409,7 @@ static ssize_t snd_seq_read(struct file *file, char __user *buf, size_t count, { struct snd_seq_client *client = file->private_data; struct snd_seq_fifo *fifo; + size_t aligned_size; int err; long result = 0; struct snd_seq_event_cell *cell; @@ -431,43 +441,54 @@ static ssize_t snd_seq_read(struct file *file, char __user *buf, size_t count, err = 0; snd_seq_fifo_lock(fifo); + if (client->midi_version > 0) + aligned_size = sizeof(struct snd_seq_ump_event); + else + aligned_size = sizeof(struct snd_seq_event); + /* while data available in queue */ - while (count >= sizeof(struct snd_seq_event)) { + while (count >= aligned_size) { int nonblock; nonblock = (file->f_flags & O_NONBLOCK) || result > 0; err = snd_seq_fifo_cell_out(fifo, &cell, nonblock); if (err < 0) break; + if (!event_is_compatible(client, &cell->event)) { + snd_seq_cell_free(cell); + cell = NULL; + continue; + } if (snd_seq_ev_is_variable(&cell->event)) { - struct snd_seq_event tmpev; - tmpev = cell->event; + struct snd_seq_ump_event tmpev; + + memcpy(&tmpev, &cell->event, aligned_size); tmpev.data.ext.len &= ~SNDRV_SEQ_EXT_MASK; - if (copy_to_user(buf, &tmpev, sizeof(struct snd_seq_event))) { + if (copy_to_user(buf, &tmpev, aligned_size)) { err = -EFAULT; break; } - count -= sizeof(struct snd_seq_event); - buf += sizeof(struct snd_seq_event); + count -= aligned_size; + buf += aligned_size; err = snd_seq_expand_var_event(&cell->event, count, (char __force *)buf, 0, - sizeof(struct snd_seq_event)); + aligned_size); if (err < 0) break; result += err; count -= err; buf += err; } else { - if (copy_to_user(buf, &cell->event, sizeof(struct snd_seq_event))) { + if (copy_to_user(buf, &cell->event, aligned_size)) { err = -EFAULT; break; } - count -= sizeof(struct snd_seq_event); - buf += sizeof(struct snd_seq_event); + count -= aligned_size; + buf += aligned_size; } snd_seq_cell_free(cell); cell = NULL; /* to be sure */ - result += sizeof(struct snd_seq_event); + result += aligned_size; } if (err < 0) { @@ -665,15 +686,17 @@ static int deliver_to_subscribers(struct snd_seq_client *client, { struct snd_seq_subscribers *subs; int err, result = 0, num_ev = 0; - struct snd_seq_event event_saved; struct snd_seq_client_port *src_port; + union __snd_seq_event event_saved; + size_t saved_size; struct snd_seq_port_subs_info *grp; src_port = snd_seq_port_use_ptr(client, event->source.port); if (src_port == NULL) return -EINVAL; /* invalid source port */ /* save original event record */ - event_saved = *event; + saved_size = snd_seq_event_packet_size(event); + memcpy(&event_saved, event, saved_size); grp = &src_port->c_src; /* lock list */ @@ -700,14 +723,13 @@ static int deliver_to_subscribers(struct snd_seq_client *client, } num_ev++; /* restore original event record */ - *event = event_saved; + memcpy(event, &event_saved, saved_size); } if (atomic) read_unlock(&grp->list_lock); else up_read(&grp->list_mutex); - *event = event_saved; /* restore */ - snd_seq_port_unlock(src_port); + memcpy(event, &event_saved, saved_size); return (result < 0) ? result : num_ev; } @@ -769,7 +791,8 @@ int snd_seq_dispatch_event(struct snd_seq_event_cell *cell, int atomic, int hop) return -EINVAL; } - if (cell->event.type == SNDRV_SEQ_EVENT_NOTE) { + if (!snd_seq_ev_is_ump(&cell->event) && + cell->event.type == SNDRV_SEQ_EVENT_NOTE) { /* NOTE event: * the event cell is re-used as a NOTE-OFF event and * enqueued again. @@ -793,7 +816,7 @@ int snd_seq_dispatch_event(struct snd_seq_event_cell *cell, int atomic, int hop) /* add the duration time */ switch (ev->flags & SNDRV_SEQ_TIME_STAMP_MASK) { case SNDRV_SEQ_TIME_STAMP_TICK: - ev->time.tick += ev->data.note.duration; + cell->event.time.tick += ev->data.note.duration; break; case SNDRV_SEQ_TIME_STAMP_REAL: /* unit for duration is ms */ @@ -850,7 +873,8 @@ static int snd_seq_client_enqueue_event(struct snd_seq_client *client, /* direct event processing without enqueued */ if (snd_seq_ev_is_direct(event)) { - if (event->type == SNDRV_SEQ_EVENT_NOTE) + if (!snd_seq_ev_is_ump(event) && + event->type == SNDRV_SEQ_EVENT_NOTE) return -EINVAL; /* this event must be enqueued! */ return snd_seq_deliver_event(client, event, atomic, hop); } @@ -920,7 +944,8 @@ static ssize_t snd_seq_write(struct file *file, const char __user *buf, struct snd_seq_client *client = file->private_data; int written = 0, len; int err, handled; - struct snd_seq_event event; + union __snd_seq_event __event; + struct snd_seq_event *ev = &__event.legacy; if (!(snd_seq_file_flags(file) & SNDRV_SEQ_LFLG_OUTPUT)) return -ENXIO; @@ -946,49 +971,66 @@ static ssize_t snd_seq_write(struct file *file, const char __user *buf, err = -EINVAL; while (count >= sizeof(struct snd_seq_event)) { /* Read in the event header from the user */ - len = sizeof(event); - if (copy_from_user(&event, buf, len)) { + len = sizeof(struct snd_seq_event); + if (copy_from_user(ev, buf, len)) { err = -EFAULT; break; } - event.source.client = client->number; /* fill in client number */ + /* read in the rest bytes for UMP events */ + if (snd_seq_ev_is_ump(ev)) { + if (count < sizeof(struct snd_seq_ump_event)) + break; + if (copy_from_user((char *)ev + len, buf + len, + sizeof(struct snd_seq_ump_event) - len)) { + err = -EFAULT; + break; + } + len = sizeof(struct snd_seq_ump_event); + } + + ev->source.client = client->number; /* fill in client number */ /* Check for extension data length */ - if (check_event_type_and_length(&event)) { + if (check_event_type_and_length(ev)) { err = -EINVAL; break; } - /* check for special events */ - if (event.type == SNDRV_SEQ_EVENT_NONE) - goto __skip_event; - else if (snd_seq_ev_is_reserved(&event)) { + if (!event_is_compatible(client, ev)) { err = -EINVAL; break; } - if (snd_seq_ev_is_variable(&event)) { - int extlen = event.data.ext.len & ~SNDRV_SEQ_EXT_MASK; + /* check for special events */ + if (!snd_seq_ev_is_ump(ev)) { + if (ev->type == SNDRV_SEQ_EVENT_NONE) + goto __skip_event; + else if (snd_seq_ev_is_reserved(ev)) { + err = -EINVAL; + break; + } + } + + if (snd_seq_ev_is_variable(ev)) { + int extlen = ev->data.ext.len & ~SNDRV_SEQ_EXT_MASK; if ((size_t)(extlen + len) > count) { /* back out, will get an error this time or next */ err = -EINVAL; break; } /* set user space pointer */ - event.data.ext.len = extlen | SNDRV_SEQ_EXT_USRPTR; - event.data.ext.ptr = (char __force *)buf - + sizeof(struct snd_seq_event); + ev->data.ext.len = extlen | SNDRV_SEQ_EXT_USRPTR; + ev->data.ext.ptr = (char __force *)buf + len; len += extlen; /* increment data length */ } else { #ifdef CONFIG_COMPAT - if (client->convert32 && snd_seq_ev_is_varusr(&event)) { - void *ptr = (void __force *)compat_ptr(event.data.raw32.d[1]); - event.data.ext.ptr = ptr; - } + if (client->convert32 && snd_seq_ev_is_varusr(ev)) + ev->data.ext.ptr = + (void __force *)compat_ptr(ev->data.raw32.d[1]); #endif } /* ok, enqueue it */ - err = snd_seq_client_enqueue_event(client, &event, file, + err = snd_seq_client_enqueue_event(client, ev, file, !(file->f_flags & O_NONBLOCK), 0, 0, &client->ioctl_mutex); if (err < 0) @@ -1146,6 +1188,7 @@ static void get_client_info(struct snd_seq_client *cptr, else info->card = -1; + info->midi_version = cptr->midi_version; memset(info->reserved, 0, sizeof(info->reserved)); } @@ -1180,12 +1223,19 @@ static int snd_seq_ioctl_set_client_info(struct snd_seq_client *client, if (client->type != client_info->type) return -EINVAL; + /* check validity of midi_version field */ + if (client->user_pversion >= SNDRV_PROTOCOL_VERSION(1, 0, 3) && + client_info->midi_version > SNDRV_SEQ_CLIENT_UMP_MIDI_2_0) + return -EINVAL; + /* fill the info fields */ if (client_info->name[0]) strscpy(client->name, client_info->name, sizeof(client->name)); client->filter = client_info->filter; client->event_lost = client_info->event_lost; + if (client->user_pversion >= SNDRV_PROTOCOL_VERSION(1, 0, 3)) + client->midi_version = client_info->midi_version; memcpy(client->event_filter, client_info->event_filter, 32); return 0; @@ -2181,10 +2231,12 @@ int snd_seq_kernel_client_enqueue(int client, struct snd_seq_event *ev, if (snd_BUG_ON(!ev)) return -EINVAL; - if (ev->type == SNDRV_SEQ_EVENT_NONE) - return 0; /* ignore this */ - if (ev->type == SNDRV_SEQ_EVENT_KERNEL_ERROR) - return -EINVAL; /* quoted events can't be enqueued */ + if (!snd_seq_ev_is_ump(ev)) { + if (ev->type == SNDRV_SEQ_EVENT_NONE) + return 0; /* ignore this */ + if (ev->type == SNDRV_SEQ_EVENT_KERNEL_ERROR) + return -EINVAL; /* quoted events can't be enqueued */ + } /* fill in client number */ ev->source.client = client; @@ -2376,6 +2428,19 @@ static void snd_seq_info_dump_ports(struct snd_info_buffer *buffer, mutex_unlock(&client->ports_mutex); } +static const char *midi_version_string(unsigned int version) +{ + switch (version) { + case SNDRV_SEQ_CLIENT_LEGACY_MIDI: + return "Legacy"; + case SNDRV_SEQ_CLIENT_UMP_MIDI_1_0: + return "UMP MIDI1"; + case SNDRV_SEQ_CLIENT_UMP_MIDI_2_0: + return "UMP MIDI2"; + default: + return "Unknown"; + } +} /* exported to seq_info.c */ void snd_seq_info_clients_read(struct snd_info_entry *entry, @@ -2400,9 +2465,10 @@ void snd_seq_info_clients_read(struct snd_info_entry *entry, continue; } - snd_iprintf(buffer, "Client %3d : \"%s\" [%s]\n", + snd_iprintf(buffer, "Client %3d : \"%s\" [%s %s]\n", c, client->name, - client->type == USER_CLIENT ? "User" : "Kernel"); + client->type == USER_CLIENT ? "User" : "Kernel", + midi_version_string(client->midi_version)); snd_seq_info_dump_ports(buffer, client); if (snd_seq_write_pool_allocated(client)) { snd_iprintf(buffer, " Output pool :\n"); diff --git a/sound/core/seq/seq_clientmgr.h b/sound/core/seq/seq_clientmgr.h index abe0ceadf3da..5657f8091835 100644 --- a/sound/core/seq/seq_clientmgr.h +++ b/sound/core/seq/seq_clientmgr.h @@ -35,6 +35,7 @@ struct snd_seq_client { snd_seq_client_type_t type; unsigned int accept_input: 1, accept_output: 1; + unsigned int midi_version; unsigned int user_pversion; char name[64]; /* client name */ int number; /* client number */ diff --git a/sound/core/seq/seq_memory.c b/sound/core/seq/seq_memory.c index a8d2db439f86..174585bf59d2 100644 --- a/sound/core/seq/seq_memory.c +++ b/sound/core/seq/seq_memory.c @@ -340,6 +340,7 @@ int snd_seq_event_dup(struct snd_seq_pool *pool, struct snd_seq_event *event, int ncells, err; unsigned int extlen; struct snd_seq_event_cell *cell; + int size; *cellp = NULL; @@ -357,7 +358,12 @@ int snd_seq_event_dup(struct snd_seq_pool *pool, struct snd_seq_event *event, return err; /* copy the event */ - cell->event = *event; + size = snd_seq_event_packet_size(event); + memcpy(&cell->ump, event, size); +#if IS_ENABLED(CONFIG_SND_SEQ_UMP) + if (size < sizeof(cell->event)) + cell->ump.raw.extra = 0; +#endif /* decompose */ if (snd_seq_ev_is_variable(event)) { @@ -375,7 +381,7 @@ int snd_seq_event_dup(struct snd_seq_pool *pool, struct snd_seq_event *event, tail = NULL; while (ncells-- > 0) { - int size = sizeof(struct snd_seq_event); + size = sizeof(struct snd_seq_event); if (len < size) size = len; err = snd_seq_cell_alloc(pool, &tmp, nonblock, file, diff --git a/sound/core/seq/seq_memory.h b/sound/core/seq/seq_memory.h index 7d7ff80f915e..7f7a2c0b187d 100644 --- a/sound/core/seq/seq_memory.h +++ b/sound/core/seq/seq_memory.h @@ -11,9 +11,26 @@ struct snd_info_buffer; +/* aliasing for legacy and UMP event packet handling */ +union __snd_seq_event { + struct snd_seq_event legacy; +#if IS_ENABLED(CONFIG_SND_SEQ_UMP) + struct snd_seq_ump_event ump; +#endif + struct { + struct snd_seq_event event; +#if IS_ENABLED(CONFIG_SND_SEQ_UMP) + u32 extra; +#endif + } __packed raw; +}; + /* container for sequencer event (internal use) */ struct snd_seq_event_cell { - struct snd_seq_event event; + union { + struct snd_seq_event event; + union __snd_seq_event ump; + }; struct snd_seq_pool *pool; /* used pool */ struct snd_seq_event_cell *next; /* next cell */ }; -- cgit v1.2.3 From 74661932ac5ecb12e4378f41083be6ac17804e71 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 23 May 2023 09:53:47 +0200 Subject: ALSA: seq: Add port inactive flag This extends the ALSA sequencer port capability bit to indicate the "inactive" flag. When this flag is set, the port is essentially invisible, and doesn't appear in the port query ioctls, while the direct access and the connection to this port are still allowed. The active/inactive state can be flipped dynamically, so that it can be visible at any time later. This feature is introduced basically for UMP; some UMP Groups in a UMP Block may be unassigned, hence those are practically invisible. On ALSA sequencer, the corresponding sequencer ports will get this new "inactive" flag to indicate the invisible state. Reviewed-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20230523075358.9672-27-tiwai@suse.de Signed-off-by: Takashi Iwai --- include/uapi/sound/asequencer.h | 1 + sound/core/seq/seq_clientmgr.c | 2 ++ sound/core/seq/seq_ports.c | 4 ++++ 3 files changed, 7 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/sound/asequencer.h b/include/uapi/sound/asequencer.h index b87950cbfb79..c6ca6609790b 100644 --- a/include/uapi/sound/asequencer.h +++ b/include/uapi/sound/asequencer.h @@ -427,6 +427,7 @@ struct snd_seq_remove_events { #define SNDRV_SEQ_PORT_CAP_SUBS_READ (1<<5) /* allow read subscription */ #define SNDRV_SEQ_PORT_CAP_SUBS_WRITE (1<<6) /* allow write subscription */ #define SNDRV_SEQ_PORT_CAP_NO_EXPORT (1<<7) /* routing not allowed */ +#define SNDRV_SEQ_PORT_CAP_INACTIVE (1<<8) /* inactive port */ /* port type */ #define SNDRV_SEQ_PORT_TYPE_SPECIFIC (1<<0) /* hardware specific */ diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 801d5eee21eb..6508ce63f761 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -2416,6 +2416,8 @@ static void snd_seq_info_dump_ports(struct snd_info_buffer *buffer, mutex_lock(&client->ports_mutex); list_for_each_entry(p, &client->ports_list_head, list) { + if (p->capability & SNDRV_SEQ_PORT_CAP_INACTIVE) + continue; snd_iprintf(buffer, " Port %3d : \"%s\" (%c%c%c%c)\n", p->addr.port, p->name, FLAG_PERM_RD(p->capability), diff --git a/sound/core/seq/seq_ports.c b/sound/core/seq/seq_ports.c index 500b1a5a9679..42f4172d4766 100644 --- a/sound/core/seq/seq_ports.c +++ b/sound/core/seq/seq_ports.c @@ -69,11 +69,15 @@ struct snd_seq_client_port *snd_seq_port_query_nearest(struct snd_seq_client *cl { int num; struct snd_seq_client_port *port, *found; + bool check_inactive = (pinfo->capability & SNDRV_SEQ_PORT_CAP_INACTIVE); num = pinfo->addr.port; found = NULL; read_lock(&client->ports_lock); list_for_each_entry(port, &client->ports_list_head, list) { + if ((port->capability & SNDRV_SEQ_PORT_CAP_INACTIVE) && + !check_inactive) + continue; /* skip inactive ports */ if (port->addr.port < num) continue; if (port->addr.port == num) { -- cgit v1.2.3 From 177ccf811df4a893df339a72dc732bb26b66d055 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 23 May 2023 09:53:48 +0200 Subject: ALSA: seq: Support MIDI 2.0 UMP Endpoint port This is an extension to ALSA sequencer infrastructure to support the MIDI 2.0 UMP Endpoint port. It's a "catch-all" port that is supposed to be present for each UMP Endpoint. When this port is read via subscription, it sends any events from all ports (UMP Groups) found in the same client. A UMP Endpoint port can be created with the new capability bit SNDRV_SEQ_PORT_CAP_UMP_ENDPOINT. Although the port assignment isn't strictly defined, it should be the port number 0. Reviewed-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20230523075358.9672-28-tiwai@suse.de Signed-off-by: Takashi Iwai --- include/uapi/sound/asequencer.h | 1 + sound/core/seq/seq_clientmgr.c | 47 ++++++++++++++++++++++++++++++++++------- sound/core/seq/seq_clientmgr.h | 1 + 3 files changed, 41 insertions(+), 8 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/sound/asequencer.h b/include/uapi/sound/asequencer.h index c6ca6609790b..67532c46b115 100644 --- a/include/uapi/sound/asequencer.h +++ b/include/uapi/sound/asequencer.h @@ -428,6 +428,7 @@ struct snd_seq_remove_events { #define SNDRV_SEQ_PORT_CAP_SUBS_WRITE (1<<6) /* allow write subscription */ #define SNDRV_SEQ_PORT_CAP_NO_EXPORT (1<<7) /* routing not allowed */ #define SNDRV_SEQ_PORT_CAP_INACTIVE (1<<8) /* inactive port */ +#define SNDRV_SEQ_PORT_CAP_UMP_ENDPOINT (1<<9) /* MIDI 2.0 UMP Endpoint port */ /* port type */ #define SNDRV_SEQ_PORT_TYPE_SPECIFIC (1<<0) /* hardware specific */ diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 6508ce63f761..061b3e2bece1 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -239,6 +239,7 @@ static struct snd_seq_client *seq_create_client1(int client_index, int poolsize) mutex_init(&client->ports_mutex); INIT_LIST_HEAD(&client->ports_list_head); mutex_init(&client->ioctl_mutex); + client->ump_endpoint_port = -1; /* find free slot in the client table */ spin_lock_irq(&clients_lock); @@ -680,20 +681,17 @@ static int snd_seq_deliver_single_event(struct snd_seq_client *client, /* * send the event to all subscribers: */ -static int deliver_to_subscribers(struct snd_seq_client *client, - struct snd_seq_event *event, - int atomic, int hop) +static int __deliver_to_subscribers(struct snd_seq_client *client, + struct snd_seq_event *event, + struct snd_seq_client_port *src_port, + int atomic, int hop) { struct snd_seq_subscribers *subs; int err, result = 0, num_ev = 0; - struct snd_seq_client_port *src_port; union __snd_seq_event event_saved; size_t saved_size; struct snd_seq_port_subs_info *grp; - src_port = snd_seq_port_use_ptr(client, event->source.port); - if (src_port == NULL) - return -EINVAL; /* invalid source port */ /* save original event record */ saved_size = snd_seq_event_packet_size(event); memcpy(&event_saved, event, saved_size); @@ -733,6 +731,31 @@ static int deliver_to_subscribers(struct snd_seq_client *client, return (result < 0) ? result : num_ev; } +static int deliver_to_subscribers(struct snd_seq_client *client, + struct snd_seq_event *event, + int atomic, int hop) +{ + struct snd_seq_client_port *src_port; + int ret = 0, ret2; + + src_port = snd_seq_port_use_ptr(client, event->source.port); + if (src_port) { + ret = __deliver_to_subscribers(client, event, src_port, atomic, hop); + snd_seq_port_unlock(src_port); + } + + if (client->ump_endpoint_port < 0 || + event->source.port == client->ump_endpoint_port) + return ret; + + src_port = snd_seq_port_use_ptr(client, client->ump_endpoint_port); + if (!src_port) + return ret; + ret2 = __deliver_to_subscribers(client, event, src_port, atomic, hop); + snd_seq_port_unlock(src_port); + return ret2 < 0 ? ret2 : ret; +} + /* deliver an event to the destination port(s). * if the event is to subscribers or broadcast, the event is dispatched * to multiple targets. @@ -1257,6 +1280,9 @@ static int snd_seq_ioctl_create_port(struct snd_seq_client *client, void *arg) return -EPERM; if (client->type == USER_CLIENT && info->kernel) return -EINVAL; + if ((info->capability & SNDRV_SEQ_PORT_CAP_UMP_ENDPOINT) && + client->ump_endpoint_port >= 0) + return -EBUSY; if (info->flags & SNDRV_SEQ_PORT_FLG_GIVEN_PORT) port_idx = info->addr.port; @@ -1286,6 +1312,8 @@ static int snd_seq_ioctl_create_port(struct snd_seq_client *client, void *arg) info->addr = port->addr; snd_seq_set_port_info(port, info); + if (info->capability & SNDRV_SEQ_PORT_CAP_UMP_ENDPOINT) + client->ump_endpoint_port = port->addr.port; snd_seq_system_client_ev_port_start(port->addr.client, port->addr.port); snd_seq_port_unlock(port); @@ -1305,8 +1333,11 @@ static int snd_seq_ioctl_delete_port(struct snd_seq_client *client, void *arg) return -EPERM; err = snd_seq_delete_port(client, info->addr.port); - if (err >= 0) + if (err >= 0) { + if (client->ump_endpoint_port == info->addr.port) + client->ump_endpoint_port = -1; snd_seq_system_client_ev_port_exit(client->number, info->addr.port); + } return err; } diff --git a/sound/core/seq/seq_clientmgr.h b/sound/core/seq/seq_clientmgr.h index 5657f8091835..bb973d36ce78 100644 --- a/sound/core/seq/seq_clientmgr.h +++ b/sound/core/seq/seq_clientmgr.h @@ -50,6 +50,7 @@ struct snd_seq_client { struct mutex ports_mutex; struct mutex ioctl_mutex; int convert32; /* convert 32->64bit */ + int ump_endpoint_port; /* output pool */ struct snd_seq_pool *pool; /* memory pool for this client */ -- cgit v1.2.3 From ff166a9d19fab3d77f50e9413df046fb1d7c01cc Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 23 May 2023 09:53:49 +0200 Subject: ALSA: seq: Add port direction to snd_seq_port_info Add a new field "direction" to snd_seq_port_info for allowing a client to tell the expected direction of the port access. A port might still allow subscriptions for read/write (e.g. for MIDI-CI) even if the primary usage of the port is a single direction (either input or output only). This new "direction" field can help to indicate such cases. When the direction is unspecified at creating a port and the port has either read or write capability, the corresponding direction bits are set automatically as default. Reviewed-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20230523075358.9672-29-tiwai@suse.de Signed-off-by: Takashi Iwai --- include/uapi/sound/asequencer.h | 9 ++++++++- sound/core/seq/seq_clientmgr.c | 16 ++++++++++++++-- sound/core/seq/seq_dummy.c | 1 + sound/core/seq/seq_midi.c | 4 ++++ sound/core/seq/seq_ports.c | 13 +++++++++++++ sound/core/seq/seq_ports.h | 2 ++ sound/core/seq/seq_virmidi.c | 1 + 7 files changed, 43 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/sound/asequencer.h b/include/uapi/sound/asequencer.h index 67532c46b115..eae1e0b0bf37 100644 --- a/include/uapi/sound/asequencer.h +++ b/include/uapi/sound/asequencer.h @@ -455,6 +455,12 @@ struct snd_seq_remove_events { #define SNDRV_SEQ_PORT_FLG_TIMESTAMP (1<<1) #define SNDRV_SEQ_PORT_FLG_TIME_REAL (1<<2) +/* port direction */ +#define SNDRV_SEQ_PORT_DIR_UNKNOWN 0 +#define SNDRV_SEQ_PORT_DIR_INPUT 1 +#define SNDRV_SEQ_PORT_DIR_OUTPUT 2 +#define SNDRV_SEQ_PORT_DIR_BIDIRECTION 3 + struct snd_seq_port_info { struct snd_seq_addr addr; /* client/port numbers */ char name[64]; /* port name */ @@ -471,7 +477,8 @@ struct snd_seq_port_info { void *kernel; /* reserved for kernel use (must be NULL) */ unsigned int flags; /* misc. conditioning */ unsigned char time_queue; /* queue # for timestamping */ - char reserved[59]; /* for future use */ + unsigned char direction; /* port usage direction (r/w/bidir) */ + char reserved[58]; /* for future use */ }; diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 061b3e2bece1..33aa6c5c5c9e 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -2440,6 +2440,17 @@ static void snd_seq_info_dump_subscribers(struct snd_info_buffer *buffer, #define FLAG_PERM_DUPLEX(perm) ((perm) & SNDRV_SEQ_PORT_CAP_DUPLEX ? 'X' : '-') +static const char *port_direction_name(unsigned char dir) +{ + static const char *names[4] = { + "-", "In", "Out", "In/Out" + }; + + if (dir > SNDRV_SEQ_PORT_DIR_BIDIRECTION) + return "Invalid"; + return names[dir]; +} + static void snd_seq_info_dump_ports(struct snd_info_buffer *buffer, struct snd_seq_client *client) { @@ -2449,12 +2460,13 @@ static void snd_seq_info_dump_ports(struct snd_info_buffer *buffer, list_for_each_entry(p, &client->ports_list_head, list) { if (p->capability & SNDRV_SEQ_PORT_CAP_INACTIVE) continue; - snd_iprintf(buffer, " Port %3d : \"%s\" (%c%c%c%c)\n", + snd_iprintf(buffer, " Port %3d : \"%s\" (%c%c%c%c) [%s]\n", p->addr.port, p->name, FLAG_PERM_RD(p->capability), FLAG_PERM_WR(p->capability), FLAG_PERM_EX(p->capability), - FLAG_PERM_DUPLEX(p->capability)); + FLAG_PERM_DUPLEX(p->capability), + port_direction_name(p->direction)); snd_seq_info_dump_subscribers(buffer, &p->c_src, 1, " Connecting To: "); snd_seq_info_dump_subscribers(buffer, &p->c_dest, 0, " Connected From: "); } diff --git a/sound/core/seq/seq_dummy.c b/sound/core/seq/seq_dummy.c index 8c18d8c4177e..2e8844ee32ed 100644 --- a/sound/core/seq/seq_dummy.c +++ b/sound/core/seq/seq_dummy.c @@ -127,6 +127,7 @@ create_port(int idx, int type) pinfo.capability |= SNDRV_SEQ_PORT_CAP_WRITE | SNDRV_SEQ_PORT_CAP_SUBS_WRITE; if (duplex) pinfo.capability |= SNDRV_SEQ_PORT_CAP_DUPLEX; + pinfo.direction = SNDRV_SEQ_PORT_DIR_BIDIRECTION; pinfo.type = SNDRV_SEQ_PORT_TYPE_MIDI_GENERIC | SNDRV_SEQ_PORT_TYPE_SOFTWARE | SNDRV_SEQ_PORT_TYPE_PORT; diff --git a/sound/core/seq/seq_midi.c b/sound/core/seq/seq_midi.c index 2b5fff80de58..44302d98950e 100644 --- a/sound/core/seq/seq_midi.c +++ b/sound/core/seq/seq_midi.c @@ -367,6 +367,10 @@ snd_seq_midisynth_probe(struct device *_dev) if ((port->capability & (SNDRV_SEQ_PORT_CAP_WRITE|SNDRV_SEQ_PORT_CAP_READ)) == (SNDRV_SEQ_PORT_CAP_WRITE|SNDRV_SEQ_PORT_CAP_READ) && info->flags & SNDRV_RAWMIDI_INFO_DUPLEX) port->capability |= SNDRV_SEQ_PORT_CAP_DUPLEX; + if (port->capability & SNDRV_SEQ_PORT_CAP_READ) + port->direction |= SNDRV_SEQ_PORT_DIR_INPUT; + if (port->capability & SNDRV_SEQ_PORT_CAP_WRITE) + port->direction |= SNDRV_SEQ_PORT_DIR_OUTPUT; port->type = SNDRV_SEQ_PORT_TYPE_MIDI_GENERIC | SNDRV_SEQ_PORT_TYPE_HARDWARE | SNDRV_SEQ_PORT_TYPE_PORT; diff --git a/sound/core/seq/seq_ports.c b/sound/core/seq/seq_ports.c index 42f4172d4766..5574341f49eb 100644 --- a/sound/core/seq/seq_ports.c +++ b/sound/core/seq/seq_ports.c @@ -356,6 +356,16 @@ int snd_seq_set_port_info(struct snd_seq_client_port * port, port->time_real = (info->flags & SNDRV_SEQ_PORT_FLG_TIME_REAL) ? 1 : 0; port->time_queue = info->time_queue; + /* direction */ + port->direction = info->direction; + /* fill default port direction */ + if (!port->direction) { + if (info->capability & SNDRV_SEQ_PORT_CAP_READ) + port->direction |= SNDRV_SEQ_PORT_DIR_INPUT; + if (info->capability & SNDRV_SEQ_PORT_CAP_WRITE) + port->direction |= SNDRV_SEQ_PORT_DIR_OUTPUT; + } + return 0; } @@ -393,6 +403,9 @@ int snd_seq_get_port_info(struct snd_seq_client_port * port, info->time_queue = port->time_queue; } + /* direction */ + info->direction = port->direction; + return 0; } diff --git a/sound/core/seq/seq_ports.h b/sound/core/seq/seq_ports.h index 44f0e9e96bbf..dce733ab2398 100644 --- a/sound/core/seq/seq_ports.h +++ b/sound/core/seq/seq_ports.h @@ -72,6 +72,8 @@ struct snd_seq_client_port { int midi_voices; int synth_voices; + /* direction */ + unsigned char direction; }; struct snd_seq_client; diff --git a/sound/core/seq/seq_virmidi.c b/sound/core/seq/seq_virmidi.c index f5cae49500c8..1b9260108e48 100644 --- a/sound/core/seq/seq_virmidi.c +++ b/sound/core/seq/seq_virmidi.c @@ -385,6 +385,7 @@ static int snd_virmidi_dev_attach_seq(struct snd_virmidi_dev *rdev) pinfo->capability |= SNDRV_SEQ_PORT_CAP_WRITE | SNDRV_SEQ_PORT_CAP_SYNC_WRITE | SNDRV_SEQ_PORT_CAP_SUBS_WRITE; pinfo->capability |= SNDRV_SEQ_PORT_CAP_READ | SNDRV_SEQ_PORT_CAP_SYNC_READ | SNDRV_SEQ_PORT_CAP_SUBS_READ; pinfo->capability |= SNDRV_SEQ_PORT_CAP_DUPLEX; + pinfo->direction = SNDRV_SEQ_PORT_DIR_BIDIRECTION; pinfo->type = SNDRV_SEQ_PORT_TYPE_MIDI_GENERIC | SNDRV_SEQ_PORT_TYPE_SOFTWARE | SNDRV_SEQ_PORT_TYPE_PORT; -- cgit v1.2.3 From a3ca3b30800da0a334e2d6eb68d123ec8e2d2bf6 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 23 May 2023 09:53:50 +0200 Subject: ALSA: seq: Add UMP group number to snd_seq_port_info Add yet more new filed "ump_group" to snd_seq_port_info for specifying the associated UMP Group number for each sequencer port. This will be referred in the upcoming automatic UMP conversion in sequencer core. Reviewed-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20230523075358.9672-30-tiwai@suse.de Signed-off-by: Takashi Iwai --- include/uapi/sound/asequencer.h | 3 ++- sound/core/seq/seq_ports.c | 9 +++++++-- sound/core/seq/seq_ports.h | 3 ++- 3 files changed, 11 insertions(+), 4 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/sound/asequencer.h b/include/uapi/sound/asequencer.h index eae1e0b0bf37..2470eaa5edc5 100644 --- a/include/uapi/sound/asequencer.h +++ b/include/uapi/sound/asequencer.h @@ -478,7 +478,8 @@ struct snd_seq_port_info { unsigned int flags; /* misc. conditioning */ unsigned char time_queue; /* queue # for timestamping */ unsigned char direction; /* port usage direction (r/w/bidir) */ - char reserved[58]; /* for future use */ + unsigned char ump_group; /* 0 = UMP EP (no conversion), 1-16 = UMP group number */ + char reserved[57]; /* for future use */ }; diff --git a/sound/core/seq/seq_ports.c b/sound/core/seq/seq_ports.c index 5574341f49eb..9b80f8275026 100644 --- a/sound/core/seq/seq_ports.c +++ b/sound/core/seq/seq_ports.c @@ -356,8 +356,12 @@ int snd_seq_set_port_info(struct snd_seq_client_port * port, port->time_real = (info->flags & SNDRV_SEQ_PORT_FLG_TIME_REAL) ? 1 : 0; port->time_queue = info->time_queue; - /* direction */ + /* UMP direction and group */ port->direction = info->direction; + port->ump_group = info->ump_group; + if (port->ump_group > SNDRV_UMP_MAX_GROUPS) + port->ump_group = 0; + /* fill default port direction */ if (!port->direction) { if (info->capability & SNDRV_SEQ_PORT_CAP_READ) @@ -403,8 +407,9 @@ int snd_seq_get_port_info(struct snd_seq_client_port * port, info->time_queue = port->time_queue; } - /* direction */ + /* UMP direction and group */ info->direction = port->direction; + info->ump_group = port->ump_group; return 0; } diff --git a/sound/core/seq/seq_ports.h b/sound/core/seq/seq_ports.h index dce733ab2398..c6c138edceab 100644 --- a/sound/core/seq/seq_ports.h +++ b/sound/core/seq/seq_ports.h @@ -72,8 +72,9 @@ struct snd_seq_client_port { int midi_voices; int synth_voices; - /* direction */ + /* UMP direction and group */ unsigned char direction; + unsigned char ump_group; }; struct snd_seq_client; -- cgit v1.2.3 From 329ffe11a014834fdef9167c7ea24bd459829f86 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 23 May 2023 09:53:52 +0200 Subject: ALSA: seq: Allow suppressing UMP conversions A sequencer client like seq_dummy rather doesn't want to convert UMP events but receives / sends as is. Add a new event filter flag to suppress the automatic UMP conversion and applies accordingly. Reviewed-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20230523075358.9672-32-tiwai@suse.de Signed-off-by: Takashi Iwai --- include/uapi/sound/asequencer.h | 1 + sound/core/seq/seq_clientmgr.c | 18 ++++++++++-------- sound/core/seq/seq_dummy.c | 8 ++++++++ 3 files changed, 19 insertions(+), 8 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/sound/asequencer.h b/include/uapi/sound/asequencer.h index 2470eaa5edc5..c4632bd9d3a0 100644 --- a/include/uapi/sound/asequencer.h +++ b/include/uapi/sound/asequencer.h @@ -347,6 +347,7 @@ typedef int __bitwise snd_seq_client_type_t; #define SNDRV_SEQ_FILTER_BROADCAST (1U<<0) /* accept broadcast messages */ #define SNDRV_SEQ_FILTER_MULTICAST (1U<<1) /* accept multicast messages */ #define SNDRV_SEQ_FILTER_BOUNCE (1U<<2) /* accept bounce event in error */ +#define SNDRV_SEQ_FILTER_NO_CONVERT (1U<<30) /* don't convert UMP events */ #define SNDRV_SEQ_FILTER_USE_EVENT (1U<<31) /* use event filter */ struct snd_seq_client_info { diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 07b090f76b5f..3b1adcb1ccdd 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -671,14 +671,16 @@ static int snd_seq_deliver_single_event(struct snd_seq_client *client, dest_port->time_real); #if IS_ENABLED(CONFIG_SND_SEQ_UMP) - if (snd_seq_ev_is_ump(event)) { - result = snd_seq_deliver_from_ump(client, dest, dest_port, - event, atomic, hop); - goto __skip; - } else if (snd_seq_client_is_ump(dest)) { - result = snd_seq_deliver_to_ump(client, dest, dest_port, - event, atomic, hop); - goto __skip; + if (!(dest->filter & SNDRV_SEQ_FILTER_NO_CONVERT)) { + if (snd_seq_ev_is_ump(event)) { + result = snd_seq_deliver_from_ump(client, dest, dest_port, + event, atomic, hop); + goto __skip; + } else if (snd_seq_client_is_ump(dest)) { + result = snd_seq_deliver_to_ump(client, dest, dest_port, + event, atomic, hop); + goto __skip; + } } #endif /* CONFIG_SND_SEQ_UMP */ diff --git a/sound/core/seq/seq_dummy.c b/sound/core/seq/seq_dummy.c index 2e8844ee32ed..9308194b2d9a 100644 --- a/sound/core/seq/seq_dummy.c +++ b/sound/core/seq/seq_dummy.c @@ -152,6 +152,7 @@ static int __init register_client(void) { struct snd_seq_dummy_port *rec1, *rec2; + struct snd_seq_client *client; int i; if (ports < 1) { @@ -165,6 +166,13 @@ register_client(void) if (my_client < 0) return my_client; + /* don't convert events but just pass-through */ + client = snd_seq_kernel_client_get(my_client); + if (!client) + return -EINVAL; + client->filter = SNDRV_SEQ_FILTER_NO_CONVERT; + snd_seq_kernel_client_put(client); + /* create ports */ for (i = 0; i < ports; i++) { rec1 = create_port(i, 0); -- cgit v1.2.3 From 81fd444aa371261cd33f31d4ffd80faeeeab0cc9 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 23 May 2023 09:53:53 +0200 Subject: ALSA: seq: Bind UMP device This patch introduces a new ALSA sequencer client for the kernel UMP object, snd-seq-ump-client. It's a UMP version of snd-seq-midi driver, while this driver creates a sequencer client per UMP endpoint which contains (fixed) 16 ports. The UMP rawmidi device is opened in APPEND mode for output, so that multiple sequencer clients can share the same UMP endpoint, as well as the legacy UMP rawmidi devices that are opened in APPEND mode, too. For input, on the other hand, the incoming data is processed on the fly in the dedicated hook, hence it doesn't open a rawmidi device. The UMP packet group is updated upon delivery depending on the target sequencer port (which corresponds to the actual UMP group). Each sequencer port sets a new port type bit, SNDRV_SEQ_PORT_TYPE_MIDI_UMP, in addition to the other standard types for MIDI. Reviewed-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20230523075358.9672-33-tiwai@suse.de Signed-off-by: Takashi Iwai --- include/sound/seq_device.h | 1 + include/sound/ump.h | 15 +- include/uapi/sound/asequencer.h | 1 + sound/core/seq/Kconfig | 5 + sound/core/seq/Makefile | 2 + sound/core/seq/seq_ump_client.c | 389 ++++++++++++++++++++++++++++++++++++++++ sound/core/ump.c | 28 ++- 7 files changed, 439 insertions(+), 2 deletions(-) create mode 100644 sound/core/seq/seq_ump_client.c (limited to 'include/uapi') diff --git a/include/sound/seq_device.h b/include/sound/seq_device.h index 8899affe9155..dead74b022f4 100644 --- a/include/sound/seq_device.h +++ b/include/sound/seq_device.h @@ -78,5 +78,6 @@ void snd_seq_driver_unregister(struct snd_seq_driver *drv); */ #define SNDRV_SEQ_DEV_ID_MIDISYNTH "seq-midi" #define SNDRV_SEQ_DEV_ID_OPL3 "opl3-synth" +#define SNDRV_SEQ_DEV_ID_UMP "seq-ump-client" #endif /* __SOUND_SEQ_DEVICE_H */ diff --git a/include/sound/ump.h b/include/sound/ump.h index 45f4c9b673b5..e4fdf7cccf12 100644 --- a/include/sound/ump.h +++ b/include/sound/ump.h @@ -11,6 +11,7 @@ struct snd_ump_endpoint; struct snd_ump_block; struct snd_ump_ops; struct ump_cvt_to_ump; +struct snd_seq_ump_ops; struct snd_ump_endpoint { struct snd_rawmidi core; /* raw UMP access */ @@ -30,9 +31,9 @@ struct snd_ump_endpoint { int input_buf_head; int input_pending; -#if IS_ENABLED(CONFIG_SND_UMP_LEGACY_RAWMIDI) struct mutex open_mutex; +#if IS_ENABLED(CONFIG_SND_UMP_LEGACY_RAWMIDI) spinlock_t legacy_locks[2]; struct snd_rawmidi *legacy_rmidi; struct snd_rawmidi_substream *legacy_substreams[2][SNDRV_UMP_MAX_GROUPS]; @@ -42,6 +43,12 @@ struct snd_ump_endpoint { struct snd_rawmidi_file legacy_out_rfile; struct ump_cvt_to_ump *out_cvts; #endif + +#if IS_ENABLED(CONFIG_SND_SEQUENCER) + struct snd_seq_device *seq_dev; + const struct snd_seq_ump_ops *seq_ops; + void *seq_client; +#endif }; /* ops filled by UMP drivers */ @@ -52,6 +59,12 @@ struct snd_ump_ops { void (*drain)(struct snd_ump_endpoint *ump, int dir); }; +/* ops filled by sequencer binding */ +struct snd_seq_ump_ops { + void (*input_receive)(struct snd_ump_endpoint *ump, + const u32 *data, int words); +}; + struct snd_ump_block { struct snd_ump_block_info info; struct snd_ump_endpoint *ump; diff --git a/include/uapi/sound/asequencer.h b/include/uapi/sound/asequencer.h index c4632bd9d3a0..3fa6b17aa7a2 100644 --- a/include/uapi/sound/asequencer.h +++ b/include/uapi/sound/asequencer.h @@ -439,6 +439,7 @@ struct snd_seq_remove_events { #define SNDRV_SEQ_PORT_TYPE_MIDI_XG (1<<4) /* XG compatible device */ #define SNDRV_SEQ_PORT_TYPE_MIDI_MT32 (1<<5) /* MT-32 compatible device */ #define SNDRV_SEQ_PORT_TYPE_MIDI_GM2 (1<<6) /* General MIDI 2 compatible device */ +#define SNDRV_SEQ_PORT_TYPE_MIDI_UMP (1<<7) /* UMP */ /* other standards...*/ #define SNDRV_SEQ_PORT_TYPE_SYNTH (1<<10) /* Synth device (no MIDI compatible - direct wavetable) */ diff --git a/sound/core/seq/Kconfig b/sound/core/seq/Kconfig index f8336134153e..c14981daf943 100644 --- a/sound/core/seq/Kconfig +++ b/sound/core/seq/Kconfig @@ -62,6 +62,7 @@ config SND_SEQ_VIRMIDI config SND_SEQ_UMP bool "Support for UMP events" + default y if SND_SEQ_UMP_CLIENT help Say Y here to enable the support for handling UMP (Universal MIDI Packet) events via ALSA sequencer infrastructure, which is an @@ -69,4 +70,8 @@ config SND_SEQ_UMP It includes the automatic conversion of ALSA sequencer events among legacy and UMP clients. +config SND_SEQ_UMP_CLIENT + tristate + def_tristate SND_UMP + endif # SND_SEQUENCER diff --git a/sound/core/seq/Makefile b/sound/core/seq/Makefile index ba264a695643..990eec7c83ad 100644 --- a/sound/core/seq/Makefile +++ b/sound/core/seq/Makefile @@ -14,12 +14,14 @@ snd-seq-midi-emul-objs := seq_midi_emul.o snd-seq-midi-event-objs := seq_midi_event.o snd-seq-dummy-objs := seq_dummy.o snd-seq-virmidi-objs := seq_virmidi.o +snd-seq-ump-client-objs := seq_ump_client.o obj-$(CONFIG_SND_SEQUENCER) += snd-seq.o obj-$(CONFIG_SND_SEQUENCER_OSS) += oss/ obj-$(CONFIG_SND_SEQ_DUMMY) += snd-seq-dummy.o obj-$(CONFIG_SND_SEQ_MIDI) += snd-seq-midi.o +obj-$(CONFIG_SND_SEQ_UMP_CLIENT) += snd-seq-ump-client.o obj-$(CONFIG_SND_SEQ_MIDI_EMUL) += snd-seq-midi-emul.o obj-$(CONFIG_SND_SEQ_MIDI_EVENT) += snd-seq-midi-event.o obj-$(CONFIG_SND_SEQ_VIRMIDI) += snd-seq-virmidi.o diff --git a/sound/core/seq/seq_ump_client.c b/sound/core/seq/seq_ump_client.c new file mode 100644 index 000000000000..8d360655ff5d --- /dev/null +++ b/sound/core/seq/seq_ump_client.c @@ -0,0 +1,389 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* ALSA sequencer binding for UMP device */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "seq_clientmgr.h" + +struct seq_ump_client; +struct seq_ump_group; + +enum { + STR_IN = SNDRV_RAWMIDI_STREAM_INPUT, + STR_OUT = SNDRV_RAWMIDI_STREAM_OUTPUT +}; + +/* object per UMP group; corresponding to a sequencer port */ +struct seq_ump_group { + int group; /* group index (0-based) */ + unsigned int dir_bits; /* directions */ + bool active; /* activeness */ + char name[64]; /* seq port name */ +}; + +/* context for UMP input parsing, per EP */ +struct seq_ump_input_buffer { + unsigned char len; /* total length in words */ + unsigned char pending; /* pending words */ + unsigned char type; /* parsed UMP packet type */ + unsigned char group; /* parsed UMP packet group */ + u32 buf[4]; /* incoming UMP packet */ +}; + +/* sequencer client, per UMP EP (rawmidi) */ +struct seq_ump_client { + struct snd_ump_endpoint *ump; /* assigned endpoint */ + int seq_client; /* sequencer client id */ + int opened[2]; /* current opens for each direction */ + struct snd_rawmidi_file out_rfile; /* rawmidi for output */ + struct seq_ump_input_buffer input; /* input parser context */ + struct seq_ump_group groups[SNDRV_UMP_MAX_GROUPS]; /* table of groups */ +}; + +/* number of 32bit words for each UMP message type */ +static unsigned char ump_packet_words[0x10] = { + 1, 1, 1, 2, 2, 4, 1, 1, 2, 2, 2, 3, 3, 4, 4, 4 +}; + +/* conversion between UMP group and seq port; + * assume the port number is equal with UMP group number (1-based) + */ +static unsigned char ump_group_to_seq_port(unsigned char group) +{ + return group + 1; +} + +/* process the incoming rawmidi stream */ +static void seq_ump_input_receive(struct snd_ump_endpoint *ump, + const u32 *val, int words) +{ + struct seq_ump_client *client = ump->seq_client; + struct snd_seq_ump_event ev = {}; + + if (!client->opened[STR_IN]) + return; + + ev.source.port = ump_group_to_seq_port(ump_message_group(*val)); + ev.dest.client = SNDRV_SEQ_ADDRESS_SUBSCRIBERS; + ev.flags = SNDRV_SEQ_EVENT_UMP; + memcpy(ev.ump, val, words << 2); + snd_seq_kernel_client_dispatch(client->seq_client, + (struct snd_seq_event *)&ev, + true, 0); +} + +/* process an input sequencer event; only deal with UMP types */ +static int seq_ump_process_event(struct snd_seq_event *ev, int direct, + void *private_data, int atomic, int hop) +{ + struct seq_ump_client *client = private_data; + struct snd_rawmidi_substream *substream; + struct snd_seq_ump_event *ump_ev; + unsigned char type; + int len; + + substream = client->out_rfile.output; + if (!substream) + return -ENODEV; + if (!snd_seq_ev_is_ump(ev)) + return 0; /* invalid event, skip */ + ump_ev = (struct snd_seq_ump_event *)ev; + type = ump_message_type(ump_ev->ump[0]); + len = ump_packet_words[type]; + if (len > 4) + return 0; // invalid - skip + snd_rawmidi_kernel_write(substream, ev->data.raw8.d, len << 2); + return 0; +} + +/* open the rawmidi */ +static int seq_ump_client_open(struct seq_ump_client *client, int dir) +{ + struct snd_ump_endpoint *ump = client->ump; + int err = 0; + + mutex_lock(&ump->open_mutex); + if (dir == STR_OUT && !client->opened[dir]) { + err = snd_rawmidi_kernel_open(&ump->core, 0, + SNDRV_RAWMIDI_LFLG_OUTPUT | + SNDRV_RAWMIDI_LFLG_APPEND, + &client->out_rfile); + if (err < 0) + goto unlock; + } + client->opened[dir]++; + unlock: + mutex_unlock(&ump->open_mutex); + return err; +} + +/* close the rawmidi */ +static int seq_ump_client_close(struct seq_ump_client *client, int dir) +{ + struct snd_ump_endpoint *ump = client->ump; + + mutex_lock(&ump->open_mutex); + if (!--client->opened[dir]) + if (dir == STR_OUT) + snd_rawmidi_kernel_release(&client->out_rfile); + mutex_unlock(&ump->open_mutex); + return 0; +} + +/* sequencer subscription ops for each client */ +static int seq_ump_subscribe(void *pdata, struct snd_seq_port_subscribe *info) +{ + struct seq_ump_client *client = pdata; + + return seq_ump_client_open(client, STR_IN); +} + +static int seq_ump_unsubscribe(void *pdata, struct snd_seq_port_subscribe *info) +{ + struct seq_ump_client *client = pdata; + + return seq_ump_client_close(client, STR_IN); +} + +static int seq_ump_use(void *pdata, struct snd_seq_port_subscribe *info) +{ + struct seq_ump_client *client = pdata; + + return seq_ump_client_open(client, STR_OUT); +} + +static int seq_ump_unuse(void *pdata, struct snd_seq_port_subscribe *info) +{ + struct seq_ump_client *client = pdata; + + return seq_ump_client_close(client, STR_OUT); +} + +/* fill port_info from the given UMP EP and group info */ +static void fill_port_info(struct snd_seq_port_info *port, + struct seq_ump_client *client, + struct seq_ump_group *group) +{ + unsigned int rawmidi_info = client->ump->core.info_flags; + + port->addr.client = client->seq_client; + port->addr.port = ump_group_to_seq_port(group->group); + port->capability = 0; + if (rawmidi_info & SNDRV_RAWMIDI_INFO_OUTPUT) + port->capability |= SNDRV_SEQ_PORT_CAP_WRITE | + SNDRV_SEQ_PORT_CAP_SYNC_WRITE | + SNDRV_SEQ_PORT_CAP_SUBS_WRITE; + if (rawmidi_info & SNDRV_RAWMIDI_INFO_INPUT) + port->capability |= SNDRV_SEQ_PORT_CAP_READ | + SNDRV_SEQ_PORT_CAP_SYNC_READ | + SNDRV_SEQ_PORT_CAP_SUBS_READ; + if (rawmidi_info & SNDRV_RAWMIDI_INFO_DUPLEX) + port->capability |= SNDRV_SEQ_PORT_CAP_DUPLEX; + if (group->dir_bits & (1 << STR_IN)) + port->direction |= SNDRV_SEQ_PORT_DIR_INPUT; + if (group->dir_bits & (1 << STR_OUT)) + port->direction |= SNDRV_SEQ_PORT_DIR_OUTPUT; + port->ump_group = group->group + 1; + if (!group->active) + port->capability |= SNDRV_SEQ_PORT_CAP_INACTIVE; + port->type = SNDRV_SEQ_PORT_TYPE_MIDI_GENERIC | + SNDRV_SEQ_PORT_TYPE_MIDI_UMP | + SNDRV_SEQ_PORT_TYPE_HARDWARE | + SNDRV_SEQ_PORT_TYPE_PORT; + port->midi_channels = 16; + if (*group->name) + snprintf(port->name, sizeof(port->name), "Group %d (%s)", + group->group + 1, group->name); + else + sprintf(port->name, "Group %d", group->group + 1); +} + +/* create a new sequencer port per UMP group */ +static int seq_ump_group_init(struct seq_ump_client *client, int group_index) +{ + struct seq_ump_group *group = &client->groups[group_index]; + struct snd_seq_port_info *port; + struct snd_seq_port_callback pcallbacks; + int err; + + port = kzalloc(sizeof(*port), GFP_KERNEL); + if (!port) { + err = -ENOMEM; + goto error; + } + + fill_port_info(port, client, group); + port->flags = SNDRV_SEQ_PORT_FLG_GIVEN_PORT; + memset(&pcallbacks, 0, sizeof(pcallbacks)); + pcallbacks.owner = THIS_MODULE; + pcallbacks.private_data = client; + pcallbacks.subscribe = seq_ump_subscribe; + pcallbacks.unsubscribe = seq_ump_unsubscribe; + pcallbacks.use = seq_ump_use; + pcallbacks.unuse = seq_ump_unuse; + pcallbacks.event_input = seq_ump_process_event; + port->kernel = &pcallbacks; + err = snd_seq_kernel_client_ctl(client->seq_client, + SNDRV_SEQ_IOCTL_CREATE_PORT, + port); + error: + kfree(port); + return err; +} + +/* update dir_bits and active flag for all groups in the client */ +static void update_group_attrs(struct seq_ump_client *client) +{ + struct snd_ump_block *fb; + struct seq_ump_group *group; + int i; + + for (i = 0; i < SNDRV_UMP_MAX_GROUPS; i++) { + group = &client->groups[i]; + *group->name = 0; + group->dir_bits = 0; + group->active = 0; + group->group = i; + } + + list_for_each_entry(fb, &client->ump->block_list, list) { + if (fb->info.first_group < 0 || + fb->info.first_group + fb->info.num_groups > SNDRV_UMP_MAX_GROUPS) + break; + group = &client->groups[fb->info.first_group]; + for (i = 0; i < fb->info.num_groups; i++, group++) { + if (fb->info.active) + group->active = 1; + switch (fb->info.direction) { + case SNDRV_UMP_DIR_INPUT: + group->dir_bits |= (1 << STR_IN); + break; + case SNDRV_UMP_DIR_OUTPUT: + group->dir_bits |= (1 << STR_OUT); + break; + case SNDRV_UMP_DIR_BIDIRECTION: + group->dir_bits |= (1 << STR_OUT) | (1 << STR_IN); + break; + } + if (!*fb->info.name) + continue; + if (!*group->name) { + /* store the first matching name */ + strscpy(group->name, fb->info.name, + sizeof(group->name)); + } else { + /* when overlapping, concat names */ + strlcat(group->name, ", ", sizeof(group->name)); + strlcat(group->name, fb->info.name, + sizeof(group->name)); + } + } + } +} + +/* release the client resources */ +static void seq_ump_client_free(struct seq_ump_client *client) +{ + if (client->seq_client >= 0) + snd_seq_delete_kernel_client(client->seq_client); + + client->ump->seq_ops = NULL; + client->ump->seq_client = NULL; + + kfree(client); +} + +/* update the MIDI version for the given client */ +static void setup_client_midi_version(struct seq_ump_client *client) +{ + struct snd_seq_client *cptr; + + cptr = snd_seq_kernel_client_get(client->seq_client); + if (!cptr) + return; + if (client->ump->info.protocol & SNDRV_UMP_EP_INFO_PROTO_MIDI2) + cptr->midi_version = SNDRV_SEQ_CLIENT_UMP_MIDI_2_0; + else + cptr->midi_version = SNDRV_SEQ_CLIENT_UMP_MIDI_1_0; + snd_seq_kernel_client_put(cptr); +} + +static const struct snd_seq_ump_ops seq_ump_ops = { + .input_receive = seq_ump_input_receive, +}; + +/* create a sequencer client and ports for the given UMP endpoint */ +static int snd_seq_ump_probe(struct device *_dev) +{ + struct snd_seq_device *dev = to_seq_dev(_dev); + struct snd_ump_endpoint *ump = dev->private_data; + struct snd_card *card = dev->card; + struct seq_ump_client *client; + int p, err; + + client = kzalloc(sizeof(*client), GFP_KERNEL); + if (!client) + return -ENOMEM; + + client->ump = ump; + + client->seq_client = + snd_seq_create_kernel_client(card, ump->core.device, + ump->core.name); + if (client->seq_client < 0) { + err = client->seq_client; + goto error; + } + + setup_client_midi_version(client); + update_group_attrs(client); + + for (p = 0; p < SNDRV_UMP_MAX_GROUPS; p++) { + err = seq_ump_group_init(client, p); + if (err < 0) + goto error; + } + + ump->seq_client = client; + ump->seq_ops = &seq_ump_ops; + return 0; + + error: + seq_ump_client_free(client); + return err; +} + +/* remove a sequencer client */ +static int snd_seq_ump_remove(struct device *_dev) +{ + struct snd_seq_device *dev = to_seq_dev(_dev); + struct snd_ump_endpoint *ump = dev->private_data; + + if (ump->seq_client) + seq_ump_client_free(ump->seq_client); + return 0; +} + +static struct snd_seq_driver seq_ump_driver = { + .driver = { + .name = KBUILD_MODNAME, + .probe = snd_seq_ump_probe, + .remove = snd_seq_ump_remove, + }, + .id = SNDRV_SEQ_DEV_ID_UMP, + .argsize = 0, +}; + +module_snd_seq_driver(seq_ump_driver); + +MODULE_DESCRIPTION("ALSA sequencer client for UMP rawmidi"); +MODULE_LICENSE("GPL"); diff --git a/sound/core/ump.c b/sound/core/ump.c index cbe704b5d90d..69993cad6772 100644 --- a/sound/core/ump.c +++ b/sound/core/ump.c @@ -132,8 +132,8 @@ int snd_ump_endpoint_new(struct snd_card *card, char *id, int device, if (!ump) return -ENOMEM; INIT_LIST_HEAD(&ump->block_list); -#if IS_ENABLED(CONFIG_SND_UMP_LEGACY_RAWMIDI) mutex_init(&ump->open_mutex); +#if IS_ENABLED(CONFIG_SND_UMP_LEGACY_RAWMIDI) spin_lock_init(&ump->legacy_locks[0]); spin_lock_init(&ump->legacy_locks[1]); #endif @@ -166,8 +166,30 @@ EXPORT_SYMBOL_GPL(snd_ump_endpoint_new); * Device register / unregister hooks; * do nothing, placeholders for avoiding the default rawmidi handling */ + +#if IS_ENABLED(CONFIG_SND_SEQUENCER) +static void snd_ump_dev_seq_free(struct snd_seq_device *device) +{ + struct snd_ump_endpoint *ump = device->private_data; + + ump->seq_dev = NULL; +} +#endif + static int snd_ump_dev_register(struct snd_rawmidi *rmidi) { +#if IS_ENABLED(CONFIG_SND_SEQUENCER) + struct snd_ump_endpoint *ump = rawmidi_to_ump(rmidi); + int err; + + err = snd_seq_device_new(ump->core.card, ump->core.device, + SNDRV_SEQ_DEV_ID_UMP, 0, &ump->seq_dev); + if (err < 0) + return err; + ump->seq_dev->private_data = ump; + ump->seq_dev->private_free = snd_ump_dev_seq_free; + snd_device_register(ump->core.card, ump->seq_dev); +#endif return 0; } @@ -280,6 +302,10 @@ int snd_ump_receive(struct snd_ump_endpoint *ump, const u32 *buffer, int count) n = snd_ump_receive_ump_val(ump, *p++); if (!n) continue; +#if IS_ENABLED(CONFIG_SND_SEQUENCER) + if (ump->seq_ops) + ump->seq_ops->input_receive(ump, ump->input_buf, n); +#endif process_legacy_input(ump, ump->input_buf, n); } -- cgit v1.2.3 From d2d247e35eeea8331150d7708211a013aabccb5b Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 23 May 2023 09:53:55 +0200 Subject: ALSA: seq: Add ioctls for client UMP info query and setup Add new ioctls for sequencer clients to query and set the UMP endpoint and block information. As a sequencer client corresponds to a UMP Endpoint, one UMP Endpoint information can be assigned at most to a single sequencer client while multiple UMP block infos can be assigned by passing the type with the offset of block id (i.e. type = block_id + 1). For the kernel client, only SNDRV_SEQ_IOCTL_GET_CLIENT_UMP_INFO is allowed. Reviewed-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20230523075358.9672-35-tiwai@suse.de Signed-off-by: Takashi Iwai --- include/uapi/sound/asequencer.h | 14 +++++ sound/core/seq/seq_clientmgr.c | 120 +++++++++++++++++++++++++++++++++++++++- sound/core/seq/seq_clientmgr.h | 4 +- sound/core/seq/seq_compat.c | 2 + sound/core/seq/seq_ump_client.c | 15 +++++ 5 files changed, 153 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/sound/asequencer.h b/include/uapi/sound/asequencer.h index 3fa6b17aa7a2..c75f594f21e3 100644 --- a/include/uapi/sound/asequencer.h +++ b/include/uapi/sound/asequencer.h @@ -585,6 +585,18 @@ struct snd_seq_query_subs { char reserved[64]; /* for future use */ }; +/* + * UMP-specific information + */ +/* type of UMP info query */ +#define SNDRV_SEQ_CLIENT_UMP_INFO_ENDPOINT 0 +#define SNDRV_SEQ_CLIENT_UMP_INFO_BLOCK 1 + +struct snd_seq_client_ump_info { + int client; /* client number to inquire/set */ + int type; /* type to inquire/set */ + unsigned char info[512]; /* info (either UMP ep or block info) */ +} __packed; /* * IOCTL commands @@ -598,6 +610,8 @@ struct snd_seq_query_subs { #define SNDRV_SEQ_IOCTL_GET_CLIENT_INFO _IOWR('S', 0x10, struct snd_seq_client_info) #define SNDRV_SEQ_IOCTL_SET_CLIENT_INFO _IOW ('S', 0x11, struct snd_seq_client_info) +#define SNDRV_SEQ_IOCTL_GET_CLIENT_UMP_INFO _IOWR('S', 0x12, struct snd_seq_client_ump_info) +#define SNDRV_SEQ_IOCTL_SET_CLIENT_UMP_INFO _IOWR('S', 0x13, struct snd_seq_client_ump_info) #define SNDRV_SEQ_IOCTL_CREATE_PORT _IOWR('S', 0x20, struct snd_seq_port_info) #define SNDRV_SEQ_IOCTL_DELETE_PORT _IOW ('S', 0x21, struct snd_seq_port_info) diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 3b1adcb1ccdd..03ca78ea2cce 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -14,6 +14,7 @@ #include #include +#include #include "seq_clientmgr.h" #include "seq_memory.h" #include "seq_queue.h" @@ -71,6 +72,10 @@ static int snd_seq_deliver_single_event(struct snd_seq_client *client, struct snd_seq_event *event, int filter, int atomic, int hop); +#if IS_ENABLED(CONFIG_SND_SEQ_UMP) +static void free_ump_info(struct snd_seq_client *client); +#endif + /* */ static inline unsigned short snd_seq_file_flags(struct file *file) @@ -382,6 +387,9 @@ static int snd_seq_release(struct inode *inode, struct file *file) seq_free_client(client); if (client->data.user.fifo) snd_seq_fifo_delete(&client->data.user.fifo); +#if IS_ENABLED(CONFIG_SND_SEQ_UMP) + free_ump_info(client); +#endif put_pid(client->data.user.owner); kfree(client); } @@ -1282,7 +1290,6 @@ static int snd_seq_ioctl_set_client_info(struct snd_seq_client *client, if (client->user_pversion >= SNDRV_PROTOCOL_VERSION(1, 0, 3)) client->midi_version = client_info->midi_version; memcpy(client->event_filter, client_info->event_filter, 32); - return 0; } @@ -2087,6 +2094,108 @@ static int snd_seq_ioctl_query_next_port(struct snd_seq_client *client, return 0; } +#if IS_ENABLED(CONFIG_SND_SEQ_UMP) +#define NUM_UMP_INFOS (SNDRV_UMP_MAX_BLOCKS + 1) + +static void free_ump_info(struct snd_seq_client *client) +{ + int i; + + if (!client->ump_info) + return; + for (i = 0; i < NUM_UMP_INFOS; i++) + kfree(client->ump_info[i]); + kfree(client->ump_info); + client->ump_info = NULL; +} + +static void terminate_ump_info_strings(void *p, int type) +{ + if (type == SNDRV_SEQ_CLIENT_UMP_INFO_ENDPOINT) { + struct snd_ump_endpoint_info *ep = p; + ep->name[sizeof(ep->name) - 1] = 0; + } else { + struct snd_ump_block_info *bp = p; + bp->name[sizeof(bp->name) - 1] = 0; + } +} + +/* UMP-specific ioctls -- called directly without data copy */ +static int snd_seq_ioctl_client_ump_info(struct snd_seq_client *caller, + unsigned int cmd, + unsigned long arg) +{ + struct snd_seq_client_ump_info __user *argp = + (struct snd_seq_client_ump_info __user *)arg; + struct snd_seq_client *cptr; + int client, type, err = 0; + size_t size; + void *p; + + if (get_user(client, &argp->client) || get_user(type, &argp->type)) + return -EFAULT; + if (cmd == SNDRV_SEQ_IOCTL_SET_CLIENT_UMP_INFO && + caller->number != client) + return -EPERM; + if (type < 0 || type >= NUM_UMP_INFOS) + return -EINVAL; + if (type == SNDRV_SEQ_CLIENT_UMP_INFO_ENDPOINT) + size = sizeof(struct snd_ump_endpoint_info); + else + size = sizeof(struct snd_ump_block_info); + cptr = snd_seq_client_use_ptr(client); + if (!cptr) + return -ENOENT; + + mutex_lock(&cptr->ioctl_mutex); + if (!cptr->midi_version) { + err = -EBADFD; + goto error; + } + + if (cmd == SNDRV_SEQ_IOCTL_GET_CLIENT_UMP_INFO) { + if (!cptr->ump_info) + p = NULL; + else + p = cptr->ump_info[type]; + if (!p) { + err = -ENODEV; + goto error; + } + if (copy_to_user(argp->info, p, size)) { + err = -EFAULT; + goto error; + } + } else { + if (cptr->type != USER_CLIENT) { + err = -EBADFD; + goto error; + } + if (!cptr->ump_info) { + cptr->ump_info = kcalloc(NUM_UMP_INFOS, + sizeof(void *), GFP_KERNEL); + if (!cptr->ump_info) { + err = -ENOMEM; + goto error; + } + } + p = memdup_user(argp->info, size); + if (IS_ERR(p)) { + err = PTR_ERR(p); + goto error; + } + kfree(cptr->ump_info[type]); + terminate_ump_info_strings(p, type); + cptr->ump_info[type] = p; + } + + error: + mutex_unlock(&cptr->ioctl_mutex); + snd_seq_client_unlock(cptr); + return err; +} +#endif + /* -------------------------------------------------------- */ static const struct ioctl_handler { @@ -2157,6 +2266,15 @@ static long snd_seq_ioctl(struct file *file, unsigned int cmd, if (snd_BUG_ON(!client)) return -ENXIO; +#if IS_ENABLED(CONFIG_SND_SEQ_UMP) + /* exception - handling large data */ + switch (cmd) { + case SNDRV_SEQ_IOCTL_GET_CLIENT_UMP_INFO: + case SNDRV_SEQ_IOCTL_SET_CLIENT_UMP_INFO: + return snd_seq_ioctl_client_ump_info(client, cmd, arg); + } +#endif + for (handler = ioctl_handlers; handler->cmd > 0; ++handler) { if (handler->cmd == cmd) break; diff --git a/sound/core/seq/seq_clientmgr.h b/sound/core/seq/seq_clientmgr.h index 97762892ffab..be3fe555f233 100644 --- a/sound/core/seq/seq_clientmgr.h +++ b/sound/core/seq/seq_clientmgr.h @@ -12,7 +12,6 @@ #include "seq_ports.h" #include "seq_lock.h" - /* client manager */ struct snd_seq_user_client { @@ -59,6 +58,9 @@ struct snd_seq_client { struct snd_seq_user_client user; struct snd_seq_kernel_client kernel; } data; + + /* for UMP */ + void **ump_info; }; /* usage statistics */ diff --git a/sound/core/seq/seq_compat.c b/sound/core/seq/seq_compat.c index c0ce6236dc7f..1e35bf086a51 100644 --- a/sound/core/seq/seq_compat.c +++ b/sound/core/seq/seq_compat.c @@ -86,6 +86,8 @@ static long snd_seq_ioctl_compat(struct file *file, unsigned int cmd, unsigned l case SNDRV_SEQ_IOCTL_SYSTEM_INFO: case SNDRV_SEQ_IOCTL_GET_CLIENT_INFO: case SNDRV_SEQ_IOCTL_SET_CLIENT_INFO: + case SNDRV_SEQ_IOCTL_GET_CLIENT_UMP_INFO: + case SNDRV_SEQ_IOCTL_SET_CLIENT_UMP_INFO: case SNDRV_SEQ_IOCTL_SUBSCRIBE_PORT: case SNDRV_SEQ_IOCTL_UNSUBSCRIBE_PORT: case SNDRV_SEQ_IOCTL_CREATE_QUEUE: diff --git a/sound/core/seq/seq_ump_client.c b/sound/core/seq/seq_ump_client.c index 600b061ac8c3..e24833804094 100644 --- a/sound/core/seq/seq_ump_client.c +++ b/sound/core/seq/seq_ump_client.c @@ -47,6 +47,7 @@ struct seq_ump_client { struct snd_rawmidi_file out_rfile; /* rawmidi for output */ struct seq_ump_input_buffer input; /* input parser context */ struct seq_ump_group groups[SNDRV_UMP_MAX_GROUPS]; /* table of groups */ + void *ump_info[SNDRV_UMP_MAX_BLOCKS + 1]; /* shadow of seq client ump_info */ }; /* number of 32bit words for each UMP message type */ @@ -384,6 +385,8 @@ static int snd_seq_ump_probe(struct device *_dev) struct snd_ump_endpoint *ump = dev->private_data; struct snd_card *card = dev->card; struct seq_ump_client *client; + struct snd_ump_block *fb; + struct snd_seq_client *cptr; int p, err; client = kzalloc(sizeof(*client), GFP_KERNEL); @@ -400,6 +403,10 @@ static int snd_seq_ump_probe(struct device *_dev) goto error; } + client->ump_info[0] = &ump->info; + list_for_each_entry(fb, &ump->block_list, list) + client->ump_info[fb->info.block_id + 1] = &fb->info; + setup_client_midi_version(client); update_group_attrs(client); @@ -413,6 +420,14 @@ static int snd_seq_ump_probe(struct device *_dev) if (err < 0) goto error; + cptr = snd_seq_kernel_client_get(client->seq_client); + if (!cptr) { + err = -EINVAL; + goto error; + } + cptr->ump_info = client->ump_info; + snd_seq_kernel_client_put(cptr); + ump->seq_client = client; ump->seq_ops = &seq_ump_ops; return 0; -- cgit v1.2.3 From d2b706077792a366fac8c1db2f1b4406ad7da482 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 23 May 2023 09:53:57 +0200 Subject: ALSA: seq: Add UMP group filter Add a new filter bitmap for UMP groups for reducing the unnecessary read/write when the client is connected to UMP EP seq port. The new group_filter field contains the bitmap for the groups, i.e. when the bit is set, the corresponding group is filtered out and the messages to that group won't be delivered. The filter bitmap consists of each bit of 1-based UMP Group number. The bit 0 is reserved for the future use. Reviewed-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20230523075358.9672-37-tiwai@suse.de Signed-off-by: Takashi Iwai --- include/uapi/sound/asequencer.h | 3 ++- sound/core/seq/seq_clientmgr.c | 2 ++ sound/core/seq/seq_clientmgr.h | 1 + sound/core/seq/seq_ump_convert.c | 13 +++++++++++++ 4 files changed, 18 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/sound/asequencer.h b/include/uapi/sound/asequencer.h index c75f594f21e3..5e91243665d8 100644 --- a/include/uapi/sound/asequencer.h +++ b/include/uapi/sound/asequencer.h @@ -362,7 +362,8 @@ struct snd_seq_client_info { int card; /* RO: card number[kernel] */ int pid; /* RO: pid[user] */ unsigned int midi_version; /* MIDI version */ - char reserved[52]; /* for future use */ + unsigned int group_filter; /* UMP group filter bitmap (for 1-based Group indices) */ + char reserved[48]; /* for future use */ }; /* MIDI version numbers in client info */ diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 8cce8061ca55..948ae45e0cc3 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -1229,6 +1229,7 @@ static void get_client_info(struct snd_seq_client *cptr, info->filter = cptr->filter; info->event_lost = cptr->event_lost; memcpy(info->event_filter, cptr->event_filter, 32); + info->group_filter = cptr->group_filter; info->num_ports = cptr->num_ports; if (cptr->type == USER_CLIENT) @@ -1290,6 +1291,7 @@ static int snd_seq_ioctl_set_client_info(struct snd_seq_client *client, if (client->user_pversion >= SNDRV_PROTOCOL_VERSION(1, 0, 3)) client->midi_version = client_info->midi_version; memcpy(client->event_filter, client_info->event_filter, 32); + client->group_filter = client_info->group_filter; return 0; } diff --git a/sound/core/seq/seq_clientmgr.h b/sound/core/seq/seq_clientmgr.h index be3fe555f233..915b1017286e 100644 --- a/sound/core/seq/seq_clientmgr.h +++ b/sound/core/seq/seq_clientmgr.h @@ -40,6 +40,7 @@ struct snd_seq_client { int number; /* client number */ unsigned int filter; /* filter flags */ DECLARE_BITMAP(event_filter, 256); + unsigned short group_filter; snd_use_lock_t use_lock; int event_lost; /* ports */ diff --git a/sound/core/seq/seq_ump_convert.c b/sound/core/seq/seq_ump_convert.c index 433fe842947e..14ba6fed9dd1 100644 --- a/sound/core/seq/seq_ump_convert.c +++ b/sound/core/seq/seq_ump_convert.c @@ -527,6 +527,17 @@ static int deliver_with_group_convert(struct snd_seq_client *dest, atomic, hop); } +/* apply the UMP event filter; return true to skip the event */ +static bool ump_event_filtered(struct snd_seq_client *dest, + const struct snd_seq_ump_event *ev) +{ + unsigned char group; + + group = ump_message_group(ev->ump[0]); + /* check the bitmap for 1-based group number */ + return dest->group_filter & (1U << (group + 1)); +} + /* Convert from UMP packet and deliver */ int snd_seq_deliver_from_ump(struct snd_seq_client *source, struct snd_seq_client *dest, @@ -539,6 +550,8 @@ int snd_seq_deliver_from_ump(struct snd_seq_client *source, if (snd_seq_ev_is_variable(event)) return 0; // skip, no variable event for UMP, so far + if (ump_event_filtered(dest, ump_ev)) + return 0; // skip if group filter is set and matching type = ump_message_type(ump_ev->ump[0]); if (snd_seq_client_is_ump(dest)) { -- cgit v1.2.3 From cb8edce28073a906401c9e421eca7c99f3396da1 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 15 May 2023 16:48:06 -0700 Subject: bpf: Support O_PATH FDs in BPF_OBJ_PIN and BPF_OBJ_GET commands Current UAPI of BPF_OBJ_PIN and BPF_OBJ_GET commands of bpf() syscall forces users to specify pinning location as a string-based absolute or relative (to current working directory) path. This has various implications related to security (e.g., symlink-based attacks), forces BPF FS to be exposed in the file system, which can cause races with other applications. One of the feedbacks we got from folks working with containers heavily was that inability to use purely FD-based location specification was an unfortunate limitation and hindrance for BPF_OBJ_PIN and BPF_OBJ_GET commands. This patch closes this oversight, adding path_fd field to BPF_OBJ_PIN and BPF_OBJ_GET UAPI, following conventions established by *at() syscalls for dirfd + pathname combinations. This now allows interesting possibilities like working with detached BPF FS mount (e.g., to perform multiple pinnings without running a risk of someone interfering with them), and generally making pinning/getting more secure and not prone to any races and/or security attacks. This is demonstrated by a selftest added in subsequent patch that takes advantage of new mount APIs (fsopen, fsconfig, fsmount) to demonstrate creating detached BPF FS mount, pinning, and then getting BPF map out of it, all while never exposing this private instance of BPF FS to outside worlds. Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Reviewed-by: Christian Brauner Link: https://lore.kernel.org/bpf/20230523170013.728457-4-andrii@kernel.org --- include/linux/bpf.h | 4 ++-- include/uapi/linux/bpf.h | 10 ++++++++++ kernel/bpf/inode.c | 16 ++++++++-------- kernel/bpf/syscall.c | 25 ++++++++++++++++++++----- tools/include/uapi/linux/bpf.h | 10 ++++++++++ 5 files changed, 50 insertions(+), 15 deletions(-) (limited to 'include/uapi') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 36e4b2d8cca2..f58895830ada 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2077,8 +2077,8 @@ struct file *bpf_link_new_file(struct bpf_link *link, int *reserved_fd); struct bpf_link *bpf_link_get_from_fd(u32 ufd); struct bpf_link *bpf_link_get_curr_or_next(u32 *id); -int bpf_obj_pin_user(u32 ufd, const char __user *pathname); -int bpf_obj_get_user(const char __user *pathname, int flags); +int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname); +int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags); #define BPF_ITER_FUNC_PREFIX "bpf_iter_" #define DEFINE_BPF_ITER_FUNC(target, args...) \ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 1bb11a6ee667..9273c654743c 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1272,6 +1272,9 @@ enum { /* Create a map that will be registered/unregesitered by the backed bpf_link */ BPF_F_LINK = (1U << 13), + +/* Get path from provided FD in BPF_OBJ_PIN/BPF_OBJ_GET commands */ + BPF_F_PATH_FD = (1U << 14), }; /* Flags for BPF_PROG_QUERY. */ @@ -1420,6 +1423,13 @@ union bpf_attr { __aligned_u64 pathname; __u32 bpf_fd; __u32 file_flags; + /* Same as dirfd in openat() syscall; see openat(2) + * manpage for details of path FD and pathname semantics; + * path_fd should accompanied by BPF_F_PATH_FD flag set in + * file_flags field, otherwise it should be set to zero; + * if BPF_F_PATH_FD flag is not set, AT_FDCWD is assumed. + */ + __s32 path_fd; }; struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */ diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 329f27d5cacf..4174f76133df 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -435,7 +435,7 @@ static int bpf_iter_link_pin_kernel(struct dentry *parent, return ret; } -static int bpf_obj_do_pin(const char __user *pathname, void *raw, +static int bpf_obj_do_pin(int path_fd, const char __user *pathname, void *raw, enum bpf_type type) { struct dentry *dentry; @@ -444,7 +444,7 @@ static int bpf_obj_do_pin(const char __user *pathname, void *raw, umode_t mode; int ret; - dentry = user_path_create(AT_FDCWD, pathname, &path, 0); + dentry = user_path_create(path_fd, pathname, &path, 0); if (IS_ERR(dentry)) return PTR_ERR(dentry); @@ -477,7 +477,7 @@ out: return ret; } -int bpf_obj_pin_user(u32 ufd, const char __user *pathname) +int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname) { enum bpf_type type; void *raw; @@ -487,14 +487,14 @@ int bpf_obj_pin_user(u32 ufd, const char __user *pathname) if (IS_ERR(raw)) return PTR_ERR(raw); - ret = bpf_obj_do_pin(pathname, raw, type); + ret = bpf_obj_do_pin(path_fd, pathname, raw, type); if (ret != 0) bpf_any_put(raw, type); return ret; } -static void *bpf_obj_do_get(const char __user *pathname, +static void *bpf_obj_do_get(int path_fd, const char __user *pathname, enum bpf_type *type, int flags) { struct inode *inode; @@ -502,7 +502,7 @@ static void *bpf_obj_do_get(const char __user *pathname, void *raw; int ret; - ret = user_path_at(AT_FDCWD, pathname, LOOKUP_FOLLOW, &path); + ret = user_path_at(path_fd, pathname, LOOKUP_FOLLOW, &path); if (ret) return ERR_PTR(ret); @@ -526,7 +526,7 @@ out: return ERR_PTR(ret); } -int bpf_obj_get_user(const char __user *pathname, int flags) +int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags) { enum bpf_type type = BPF_TYPE_UNSPEC; int f_flags; @@ -537,7 +537,7 @@ int bpf_obj_get_user(const char __user *pathname, int flags) if (f_flags < 0) return f_flags; - raw = bpf_obj_do_get(pathname, &type, f_flags); + raw = bpf_obj_do_get(path_fd, pathname, &type, f_flags); if (IS_ERR(raw)) return PTR_ERR(raw); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index b2621089904b..c7f6807215e6 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2697,23 +2697,38 @@ free_prog: return err; } -#define BPF_OBJ_LAST_FIELD file_flags +#define BPF_OBJ_LAST_FIELD path_fd static int bpf_obj_pin(const union bpf_attr *attr) { - if (CHECK_ATTR(BPF_OBJ) || attr->file_flags != 0) + int path_fd; + + if (CHECK_ATTR(BPF_OBJ) || attr->file_flags & ~BPF_F_PATH_FD) + return -EINVAL; + + /* path_fd has to be accompanied by BPF_F_PATH_FD flag */ + if (!(attr->file_flags & BPF_F_PATH_FD) && attr->path_fd) return -EINVAL; - return bpf_obj_pin_user(attr->bpf_fd, u64_to_user_ptr(attr->pathname)); + path_fd = attr->file_flags & BPF_F_PATH_FD ? attr->path_fd : AT_FDCWD; + return bpf_obj_pin_user(attr->bpf_fd, path_fd, + u64_to_user_ptr(attr->pathname)); } static int bpf_obj_get(const union bpf_attr *attr) { + int path_fd; + if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0 || - attr->file_flags & ~BPF_OBJ_FLAG_MASK) + attr->file_flags & ~(BPF_OBJ_FLAG_MASK | BPF_F_PATH_FD)) + return -EINVAL; + + /* path_fd has to be accompanied by BPF_F_PATH_FD flag */ + if (!(attr->file_flags & BPF_F_PATH_FD) && attr->path_fd) return -EINVAL; - return bpf_obj_get_user(u64_to_user_ptr(attr->pathname), + path_fd = attr->file_flags & BPF_F_PATH_FD ? attr->path_fd : AT_FDCWD; + return bpf_obj_get_user(path_fd, u64_to_user_ptr(attr->pathname), attr->file_flags); } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 1bb11a6ee667..9273c654743c 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1272,6 +1272,9 @@ enum { /* Create a map that will be registered/unregesitered by the backed bpf_link */ BPF_F_LINK = (1U << 13), + +/* Get path from provided FD in BPF_OBJ_PIN/BPF_OBJ_GET commands */ + BPF_F_PATH_FD = (1U << 14), }; /* Flags for BPF_PROG_QUERY. */ @@ -1420,6 +1423,13 @@ union bpf_attr { __aligned_u64 pathname; __u32 bpf_fd; __u32 file_flags; + /* Same as dirfd in openat() syscall; see openat(2) + * manpage for details of path FD and pathname semantics; + * path_fd should accompanied by BPF_F_PATH_FD flag set in + * file_flags field, otherwise it should be set to zero; + * if BPF_F_PATH_FD flag is not set, AT_FDCWD is assumed. + */ + __s32 path_fd; }; struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */ -- cgit v1.2.3 From e9261467ae86a6544bb602a55a1eab52696e71e3 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Tue, 23 May 2023 11:15:48 +0100 Subject: net: mdio: add clause 73 to ethtool conversion helper Add a helper to convert a clause 73 advertisement to an ethtool bitmap. Reviewed-by: Andrew Lunn Signed-off-by: Russell King (Oracle) Signed-off-by: Jakub Kicinski --- include/linux/mdio.h | 39 +++++++++++++++++++++++++++++++++++++++ include/uapi/linux/mdio.h | 24 ++++++++++++++++++++++++ 2 files changed, 63 insertions(+) (limited to 'include/uapi') diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 27013d6bf24a..0670cc6e067c 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -486,6 +486,45 @@ static inline u32 linkmode_adv_to_mii_10base_t1_t(unsigned long *adv) return result; } +/** + * mii_c73_mod_linkmode - convert a Clause 73 advertisement to linkmodes + * @adv: linkmode advertisement setting + * @lpa: array of three u16s containing the advertisement + * + * Convert an IEEE 802.3 Clause 73 advertisement to ethtool link modes. + */ +static inline void mii_c73_mod_linkmode(unsigned long *adv, u16 *lpa) +{ + linkmode_mod_bit(ETHTOOL_LINK_MODE_Pause_BIT, + adv, lpa[0] & MDIO_AN_C73_0_PAUSE); + linkmode_mod_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, + adv, lpa[0] & MDIO_AN_C73_0_ASM_DIR); + linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, + adv, lpa[1] & MDIO_AN_C73_1_1000BASE_KX); + linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, + adv, lpa[1] & MDIO_AN_C73_1_10GBASE_KX4); + linkmode_mod_bit(ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT, + adv, lpa[1] & MDIO_AN_C73_1_40GBASE_KR4); + linkmode_mod_bit(ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT, + adv, lpa[1] & MDIO_AN_C73_1_40GBASE_CR4); + /* 100GBASE_CR10 and 100GBASE_KP4 not implemented */ + linkmode_mod_bit(ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, + adv, lpa[1] & MDIO_AN_C73_1_100GBASE_KR4); + linkmode_mod_bit(ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT, + adv, lpa[1] & MDIO_AN_C73_1_100GBASE_CR4); + /* 25GBASE_R_S not implemented */ + /* The 25GBASE_R bit can be used for 25Gbase KR or CR modes */ + linkmode_mod_bit(ETHTOOL_LINK_MODE_25000baseKR_Full_BIT, + adv, lpa[1] & MDIO_AN_C73_1_25GBASE_R); + linkmode_mod_bit(ETHTOOL_LINK_MODE_25000baseCR_Full_BIT, + adv, lpa[1] & MDIO_AN_C73_1_25GBASE_R); + linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseKR_Full_BIT, + adv, lpa[1] & MDIO_AN_C73_1_10GBASE_KR); + linkmode_mod_bit(ETHTOOL_LINK_MODE_2500baseX_Full_BIT, + adv, lpa[2] & MDIO_AN_C73_2_2500BASE_KX); + /* 5GBASE_KR not implemented */ +} + int __mdiobus_read(struct mii_bus *bus, int addr, u32 regnum); int __mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val); int __mdiobus_modify_changed(struct mii_bus *bus, int addr, u32 regnum, diff --git a/include/uapi/linux/mdio.h b/include/uapi/linux/mdio.h index 256b463e47a6..b826598d1e94 100644 --- a/include/uapi/linux/mdio.h +++ b/include/uapi/linux/mdio.h @@ -231,6 +231,30 @@ #define MDIO_PMA_EXTABLE_BT1 0x0800 /* BASE-T1 ability */ #define MDIO_PMA_EXTABLE_NBT 0x4000 /* 2.5/5GBASE-T ability */ +/* AN Clause 73 linkword */ +#define MDIO_AN_C73_0_S_MASK GENMASK(4, 0) +#define MDIO_AN_C73_0_E_MASK GENMASK(9, 5) +#define MDIO_AN_C73_0_PAUSE BIT(10) +#define MDIO_AN_C73_0_ASM_DIR BIT(11) +#define MDIO_AN_C73_0_C2 BIT(12) +#define MDIO_AN_C73_0_RF BIT(13) +#define MDIO_AN_C73_0_ACK BIT(14) +#define MDIO_AN_C73_0_NP BIT(15) +#define MDIO_AN_C73_1_T_MASK GENMASK(4, 0) +#define MDIO_AN_C73_1_1000BASE_KX BIT(5) +#define MDIO_AN_C73_1_10GBASE_KX4 BIT(6) +#define MDIO_AN_C73_1_10GBASE_KR BIT(7) +#define MDIO_AN_C73_1_40GBASE_KR4 BIT(8) +#define MDIO_AN_C73_1_40GBASE_CR4 BIT(9) +#define MDIO_AN_C73_1_100GBASE_CR10 BIT(10) +#define MDIO_AN_C73_1_100GBASE_KP4 BIT(11) +#define MDIO_AN_C73_1_100GBASE_KR4 BIT(12) +#define MDIO_AN_C73_1_100GBASE_CR4 BIT(13) +#define MDIO_AN_C73_1_25GBASE_R_S BIT(14) +#define MDIO_AN_C73_1_25GBASE_R BIT(15) +#define MDIO_AN_C73_2_2500BASE_KX BIT(0) +#define MDIO_AN_C73_2_5GBASE_KR BIT(1) + /* PHY XGXS lane state register. */ #define MDIO_PHYXS_LNSTAT_SYNC0 0x0001 #define MDIO_PHYXS_LNSTAT_SYNC1 0x0002 -- cgit v1.2.3 From 96b2b072ee62be8ae68c8ecf14854c4d0505a8f8 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Tue, 2 May 2023 15:48:16 +0300 Subject: exportfs: allow exporting non-decodeable file handles to userspace Some userspace programs use st_ino as a unique object identifier, even though inode numbers may be recycable. This issue has been addressed for NFS export long ago using the exportfs file handle API and the unique file handle identifiers are also exported to userspace via name_to_handle_at(2). fanotify also uses file handles to identify objects in events, but only for filesystems that support NFS export. Relax the requirement for NFS export support and allow more filesystems to export a unique object identifier via name_to_handle_at(2) with the flag AT_HANDLE_FID. A file handle requested with the AT_HANDLE_FID flag, may or may not be usable as an argument to open_by_handle_at(2). To allow filesystems to opt-in to supporting AT_HANDLE_FID, a struct export_operations is required, but even an empty struct is sufficient for encoding FIDs. Acked-by: Jeff Layton Acked-by: Chuck Lever Signed-off-by: Amir Goldstein Acked-by: Christian Brauner Signed-off-by: Jan Kara Message-Id: <20230502124817.3070545-4-amir73il@gmail.com> --- fs/fhandle.c | 22 ++++++++++++++-------- include/uapi/linux/fcntl.h | 5 +++++ 2 files changed, 19 insertions(+), 8 deletions(-) (limited to 'include/uapi') diff --git a/fs/fhandle.c b/fs/fhandle.c index f2bc27d1975e..4a635cf787fc 100644 --- a/fs/fhandle.c +++ b/fs/fhandle.c @@ -16,7 +16,7 @@ static long do_sys_name_to_handle(const struct path *path, struct file_handle __user *ufh, - int __user *mnt_id) + int __user *mnt_id, int fh_flags) { long retval; struct file_handle f_handle; @@ -24,11 +24,14 @@ static long do_sys_name_to_handle(const struct path *path, struct file_handle *handle = NULL; /* - * We need to make sure whether the file system - * support decoding of the file handle + * We need to make sure whether the file system support decoding of + * the file handle if decodeable file handle was requested. + * Otherwise, even empty export_operations are sufficient to opt-in + * to encoding FIDs. */ if (!path->dentry->d_sb->s_export_op || - !path->dentry->d_sb->s_export_op->fh_to_dentry) + (!(fh_flags & EXPORT_FH_FID) && + !path->dentry->d_sb->s_export_op->fh_to_dentry)) return -EOPNOTSUPP; if (copy_from_user(&f_handle, ufh, sizeof(struct file_handle))) @@ -45,10 +48,10 @@ static long do_sys_name_to_handle(const struct path *path, /* convert handle size to multiple of sizeof(u32) */ handle_dwords = f_handle.handle_bytes >> 2; - /* we ask for a non connected handle */ + /* we ask for a non connectable maybe decodeable file handle */ retval = exportfs_encode_fh(path->dentry, (struct fid *)handle->f_handle, - &handle_dwords, 0); + &handle_dwords, fh_flags); handle->handle_type = retval; /* convert handle size to bytes */ handle_bytes = handle_dwords * sizeof(u32); @@ -84,6 +87,7 @@ static long do_sys_name_to_handle(const struct path *path, * @handle: resulting file handle * @mnt_id: mount id of the file system containing the file * @flag: flag value to indicate whether to follow symlink or not + * and whether a decodable file handle is required. * * @handle->handle_size indicate the space available to store the * variable part of the file handle in bytes. If there is not @@ -96,17 +100,19 @@ SYSCALL_DEFINE5(name_to_handle_at, int, dfd, const char __user *, name, { struct path path; int lookup_flags; + int fh_flags; int err; - if ((flag & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0) + if (flag & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH | AT_HANDLE_FID)) return -EINVAL; lookup_flags = (flag & AT_SYMLINK_FOLLOW) ? LOOKUP_FOLLOW : 0; + fh_flags = (flag & AT_HANDLE_FID) ? EXPORT_FH_FID : 0; if (flag & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; err = user_path_at(dfd, name, lookup_flags, &path); if (!err) { - err = do_sys_name_to_handle(&path, handle, mnt_id); + err = do_sys_name_to_handle(&path, handle, mnt_id, fh_flags); path_put(&path); } return err; diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h index e8c07da58c9f..6c80f96049bd 100644 --- a/include/uapi/linux/fcntl.h +++ b/include/uapi/linux/fcntl.h @@ -112,4 +112,9 @@ #define AT_RECURSIVE 0x8000 /* Apply to the entire subtree */ +/* Flags for name_to_handle_at(2). We reuse AT_ flag space to save bits... */ +#define AT_HANDLE_FID AT_REMOVEDIR /* file handle is needed to + compare object identity and may not + be usable to open_by_handle_at(2) */ + #endif /* _UAPI_LINUX_FCNTL_H */ -- cgit v1.2.3 From a45baa079e2a6b7a5516354c6ff08702232384f5 Mon Sep 17 00:00:00 2001 From: Boerge Struempfel Date: Tue, 30 May 2023 16:16:37 +0200 Subject: spi: add SPI_MOSI_IDLE_LOW mode bit Some spi controller switch the mosi line to high, whenever they are idle. This may not be desired in all use cases. For example neopixel leds can get confused and flicker due to misinterpreting the idle state. Therefore, we introduce a new spi-mode bit, with which the idle behaviour can be overwritten on a per device basis. Signed-off-by: Boerge Struempfel Link: https://lore.kernel.org/r/20230530141641.1155691-2-boerge.struempfel@gmail.com Signed-off-by: Mark Brown --- include/uapi/linux/spi/spi.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/spi/spi.h b/include/uapi/linux/spi/spi.h index 9d5f58059703..ca56e477d161 100644 --- a/include/uapi/linux/spi/spi.h +++ b/include/uapi/linux/spi/spi.h @@ -28,6 +28,7 @@ #define SPI_RX_OCTAL _BITUL(14) /* receive with 8 wires */ #define SPI_3WIRE_HIZ _BITUL(15) /* high impedance turnaround */ #define SPI_RX_CPHA_FLIP _BITUL(16) /* flip CPHA on Rx only xfer */ +#define SPI_MOSI_IDLE_LOW _BITUL(17) /* leave mosi line low when idle */ /* * All the bits defined above should be covered by SPI_MODE_USER_MASK. @@ -37,6 +38,6 @@ * These bits must not overlap. A static assert check should make sure of that. * If adding extra bits, make sure to increase the bit index below as well. */ -#define SPI_MODE_USER_MASK (_BITUL(17) - 1) +#define SPI_MODE_USER_MASK (_BITUL(18) - 1) #endif /* _UAPI_SPI_H */ -- cgit v1.2.3 From e910c8e3aa02dc456e2f4c32cb479523c326b534 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 23 May 2023 10:19:35 +0200 Subject: autofs: use flexible array in ioctl structure Commit df8fc4e934c1 ("kbuild: Enable -fstrict-flex-arrays=3") introduced a warning for the autofs_dev_ioctl structure: In function 'check_name', inlined from 'validate_dev_ioctl' at fs/autofs/dev-ioctl.c:131:9, inlined from '_autofs_dev_ioctl' at fs/autofs/dev-ioctl.c:624:8: fs/autofs/dev-ioctl.c:33:14: error: 'strchr' reading 1 or more bytes from a region of size 0 [-Werror=stringop-overread] 33 | if (!strchr(name, '/')) | ^~~~~~~~~~~~~~~~~ In file included from include/linux/auto_dev-ioctl.h:10, from fs/autofs/autofs_i.h:10, from fs/autofs/dev-ioctl.c:14: include/uapi/linux/auto_dev-ioctl.h: In function '_autofs_dev_ioctl': include/uapi/linux/auto_dev-ioctl.h:112:14: note: source object 'path' of size 0 112 | char path[0]; | ^~~~ This is easily fixed by changing the gnu 0-length array into a c99 flexible array. Since this is a uapi structure, we have to be careful about possible regressions but this one should be fine as they are equivalent here. While it would break building with ancient gcc versions that predate c99, it helps building with --std=c99 and -Wpedantic builds in user space, as well as non-gnu compilers. This means we probably also want it fixed in stable kernels. Cc: stable@vger.kernel.org Cc: Kees Cook Cc: Gustavo A. R. Silva" Signed-off-by: Arnd Bergmann Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20230523081944.581710-1-arnd@kernel.org --- Documentation/filesystems/autofs-mount-control.rst | 2 +- Documentation/filesystems/autofs.rst | 2 +- include/uapi/linux/auto_dev-ioctl.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/Documentation/filesystems/autofs-mount-control.rst b/Documentation/filesystems/autofs-mount-control.rst index bf4b511cdbe8..b5a379d25c40 100644 --- a/Documentation/filesystems/autofs-mount-control.rst +++ b/Documentation/filesystems/autofs-mount-control.rst @@ -196,7 +196,7 @@ information and return operation results:: struct args_ismountpoint ismountpoint; }; - char path[0]; + char path[]; }; The ioctlfd field is a mount point file descriptor of an autofs mount diff --git a/Documentation/filesystems/autofs.rst b/Documentation/filesystems/autofs.rst index 4f490278d22f..3b6e38e646cd 100644 --- a/Documentation/filesystems/autofs.rst +++ b/Documentation/filesystems/autofs.rst @@ -467,7 +467,7 @@ Each ioctl is passed a pointer to an `autofs_dev_ioctl` structure:: struct args_ismountpoint ismountpoint; }; - char path[0]; + char path[]; }; For the **OPEN_MOUNT** and **IS_MOUNTPOINT** commands, the target diff --git a/include/uapi/linux/auto_dev-ioctl.h b/include/uapi/linux/auto_dev-ioctl.h index 62e625356dc8..08be539605fc 100644 --- a/include/uapi/linux/auto_dev-ioctl.h +++ b/include/uapi/linux/auto_dev-ioctl.h @@ -109,7 +109,7 @@ struct autofs_dev_ioctl { struct args_ismountpoint ismountpoint; }; - char path[0]; + char path[]; }; static inline void init_autofs_dev_ioctl(struct autofs_dev_ioctl *in) -- cgit v1.2.3 From 1a432018c0cdf51a77a2e134b19ba6cab4c29c89 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Mon, 29 May 2023 14:48:30 +0300 Subject: net/sched: flower: Allow matching on layer 2 miss Add the 'TCA_FLOWER_L2_MISS' netlink attribute that allows user space to match on packets that encountered a layer 2 miss. The miss indication is set as metadata in the tc skb extension by the bridge driver upon FDB or MDB lookup miss and dissected by the flow dissector to the 'FLOW_DISSECTOR_KEY_META' key. The use of this skb extension is guarded by the 'tc_skb_ext_tc' static key. As such, enable / disable this key when filters that match on layer 2 miss are added / deleted. Tested: # cat tc_skb_ext_tc.py #!/usr/bin/env -S drgn -s vmlinux refcount = prog["tc_skb_ext_tc"].key.enabled.counter.value_() print(f"tc_skb_ext_tc reference count is {refcount}") # ./tc_skb_ext_tc.py tc_skb_ext_tc reference count is 0 # tc filter add dev swp1 egress proto all handle 101 pref 1 flower src_mac 00:11:22:33:44:55 action drop # tc filter add dev swp1 egress proto all handle 102 pref 2 flower src_mac 00:11:22:33:44:55 l2_miss true action drop # tc filter add dev swp1 egress proto all handle 103 pref 3 flower src_mac 00:11:22:33:44:55 l2_miss false action drop # ./tc_skb_ext_tc.py tc_skb_ext_tc reference count is 2 # tc filter replace dev swp1 egress proto all handle 102 pref 2 flower src_mac 00:01:02:03:04:05 l2_miss false action drop # ./tc_skb_ext_tc.py tc_skb_ext_tc reference count is 2 # tc filter del dev swp1 egress proto all handle 103 pref 3 flower # tc filter del dev swp1 egress proto all handle 102 pref 2 flower # tc filter del dev swp1 egress proto all handle 101 pref 1 flower # ./tc_skb_ext_tc.py tc_skb_ext_tc reference count is 0 Signed-off-by: Ido Schimmel Reviewed-by: Nikolay Aleksandrov Signed-off-by: Jakub Kicinski --- include/uapi/linux/pkt_cls.h | 2 ++ net/sched/cls_flower.c | 30 ++++++++++++++++++++++++++++-- 2 files changed, 30 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 648a82f32666..00933dda7b10 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -594,6 +594,8 @@ enum { TCA_FLOWER_KEY_L2TPV3_SID, /* be32 */ + TCA_FLOWER_L2_MISS, /* u8 */ + __TCA_FLOWER_MAX, }; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 9dbc43388e57..04adcde9eb81 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -120,6 +120,7 @@ struct cls_fl_filter { u32 handle; u32 flags; u32 in_hw_count; + u8 needs_tc_skb_ext:1; struct rcu_work rwork; struct net_device *hw_dev; /* Flower classifier is unlocked, which means that its reference counter @@ -415,6 +416,8 @@ static struct cls_fl_head *fl_head_dereference(struct tcf_proto *tp) static void __fl_destroy_filter(struct cls_fl_filter *f) { + if (f->needs_tc_skb_ext) + tc_skb_ext_tc_disable(); tcf_exts_destroy(&f->exts); tcf_exts_put_net(&f->exts); kfree(f); @@ -615,7 +618,8 @@ static void *fl_get(struct tcf_proto *tp, u32 handle) } static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { - [TCA_FLOWER_UNSPEC] = { .type = NLA_UNSPEC }, + [TCA_FLOWER_UNSPEC] = { .strict_start_type = + TCA_FLOWER_L2_MISS }, [TCA_FLOWER_CLASSID] = { .type = NLA_U32 }, [TCA_FLOWER_INDEV] = { .type = NLA_STRING, .len = IFNAMSIZ }, @@ -720,7 +724,7 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_PPPOE_SID] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_PPP_PROTO] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_L2TPV3_SID] = { .type = NLA_U32 }, - + [TCA_FLOWER_L2_MISS] = NLA_POLICY_MAX(NLA_U8, 1), }; static const struct nla_policy @@ -1668,6 +1672,10 @@ static int fl_set_key(struct net *net, struct nlattr **tb, mask->meta.ingress_ifindex = 0xffffffff; } + fl_set_key_val(tb, &key->meta.l2_miss, TCA_FLOWER_L2_MISS, + &mask->meta.l2_miss, TCA_FLOWER_UNSPEC, + sizeof(key->meta.l2_miss)); + fl_set_key_val(tb, key->eth.dst, TCA_FLOWER_KEY_ETH_DST, mask->eth.dst, TCA_FLOWER_KEY_ETH_DST_MASK, sizeof(key->eth.dst)); @@ -2085,6 +2093,11 @@ errout_cleanup: return ret; } +static bool fl_needs_tc_skb_ext(const struct fl_flow_key *mask) +{ + return mask->meta.l2_miss; +} + static int fl_set_parms(struct net *net, struct tcf_proto *tp, struct cls_fl_filter *f, struct fl_flow_mask *mask, unsigned long base, struct nlattr **tb, @@ -2121,6 +2134,14 @@ static int fl_set_parms(struct net *net, struct tcf_proto *tp, return -EINVAL; } + /* Enable tc skb extension if filter matches on data extracted from + * this extension. + */ + if (fl_needs_tc_skb_ext(&mask->key)) { + f->needs_tc_skb_ext = 1; + tc_skb_ext_tc_enable(); + } + return 0; } @@ -3074,6 +3095,11 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net, goto nla_put_failure; } + if (fl_dump_key_val(skb, &key->meta.l2_miss, + TCA_FLOWER_L2_MISS, &mask->meta.l2_miss, + TCA_FLOWER_UNSPEC, sizeof(key->meta.l2_miss))) + goto nla_put_failure; + if (fl_dump_key_val(skb, key->eth.dst, TCA_FLOWER_KEY_ETH_DST, mask->eth.dst, TCA_FLOWER_KEY_ETH_DST_MASK, sizeof(key->eth.dst)) || -- cgit v1.2.3 From 6c1adb650c8d85c6cb471dbc900c2468f462995a Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 30 May 2023 12:19:46 +0300 Subject: net/sched: taprio: add netlink reporting for offload statistics counters Offloading drivers may report some additional statistics counters, some of them even suggested by 802.1Q, like TransmissionOverrun. In my opinion we don't have to limit ourselves to reporting counters only globally to the Qdisc/interface, especially if the device has more detailed reporting (per traffic class), since the more detailed info is valuable for debugging and can help identifying who is exceeding its time slot. But on the other hand, some devices may not be able to report both per TC and global stats. So we end up reporting both ways, and use the good old ethtool_put_stat() strategy to determine which statistics are supported by this NIC. Statistics which aren't set are simply not reported to netlink. For this reason, we need something dynamic (a nlattr nest) to be reported through TCA_STATS_APP, and not something daft like the fixed-size and inextensible struct tc_codel_xstats. A good model for xstats which are a nlattr nest rather than a fixed struct seems to be cake. # Global stats $ tc -s qdisc show dev eth0 root # Per-tc stats $ tc -s class show dev eth0 Signed-off-by: Vladimir Oltean Acked-by: Vinicius Costa Gomes Signed-off-by: David S. Miller --- include/net/pkt_sched.h | 47 ++++++++++++++++++++----- include/uapi/linux/pkt_sched.h | 10 ++++++ net/sched/sch_taprio.c | 78 +++++++++++++++++++++++++++++++++++++++++- 3 files changed, 126 insertions(+), 9 deletions(-) (limited to 'include/uapi') diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index f5fb11da357b..530d33adec88 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -188,6 +188,27 @@ struct tc_taprio_caps { enum tc_taprio_qopt_cmd { TAPRIO_CMD_REPLACE, TAPRIO_CMD_DESTROY, + TAPRIO_CMD_STATS, + TAPRIO_CMD_TC_STATS, +}; + +/** + * struct tc_taprio_qopt_stats - IEEE 802.1Qbv statistics + * @window_drops: Frames that were dropped because they were too large to be + * transmitted in any of the allotted time windows (open gates) for their + * traffic class. + * @tx_overruns: Frames still being transmitted by the MAC after the + * transmission gate associated with their traffic class has closed. + * Equivalent to `12.29.1.1.2 TransmissionOverrun` from 802.1Q-2018. + */ +struct tc_taprio_qopt_stats { + u64 window_drops; + u64 tx_overruns; +}; + +struct tc_taprio_qopt_tc_stats { + int tc; + struct tc_taprio_qopt_stats stats; }; struct tc_taprio_sched_entry { @@ -199,16 +220,26 @@ struct tc_taprio_sched_entry { }; struct tc_taprio_qopt_offload { - struct tc_mqprio_qopt_offload mqprio; - struct netlink_ext_ack *extack; enum tc_taprio_qopt_cmd cmd; - ktime_t base_time; - u64 cycle_time; - u64 cycle_time_extension; - u32 max_sdu[TC_MAX_QUEUE]; - size_t num_entries; - struct tc_taprio_sched_entry entries[]; + union { + /* TAPRIO_CMD_STATS */ + struct tc_taprio_qopt_stats stats; + /* TAPRIO_CMD_TC_STATS */ + struct tc_taprio_qopt_tc_stats tc_stats; + /* TAPRIO_CMD_REPLACE */ + struct { + struct tc_mqprio_qopt_offload mqprio; + struct netlink_ext_ack *extack; + ktime_t base_time; + u64 cycle_time; + u64 cycle_time_extension; + u32 max_sdu[TC_MAX_QUEUE]; + + size_t num_entries; + struct tc_taprio_sched_entry entries[]; + }; + }; }; #if IS_ENABLED(CONFIG_NET_SCH_TAPRIO) diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 51a7addc56c6..00f6ff0aff1f 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -1259,6 +1259,16 @@ enum { TCA_TAPRIO_TC_ENTRY_MAX = (__TCA_TAPRIO_TC_ENTRY_CNT - 1) }; +enum { + TCA_TAPRIO_OFFLOAD_STATS_PAD = 1, /* u64 */ + TCA_TAPRIO_OFFLOAD_STATS_WINDOW_DROPS, /* u64 */ + TCA_TAPRIO_OFFLOAD_STATS_TX_OVERRUNS, /* u64 */ + + /* add new constants above here */ + __TCA_TAPRIO_OFFLOAD_STATS_CNT, + TCA_TAPRIO_OFFLOAD_STATS_MAX = (__TCA_TAPRIO_OFFLOAD_STATS_CNT - 1) +}; + enum { TCA_TAPRIO_ATTR_UNSPEC, TCA_TAPRIO_ATTR_PRIOMAP, /* struct tc_mqprio_qopt */ diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 06bf4c6355a5..3c4c2c334878 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -27,6 +27,8 @@ #include #include +#define TAPRIO_STAT_NOT_SET (~0ULL) + #include "sch_mqprio_lib.h" static LIST_HEAD(taprio_list); @@ -2289,6 +2291,72 @@ nla_put_failure: return -EMSGSIZE; } +static int taprio_put_stat(struct sk_buff *skb, u64 val, u16 attrtype) +{ + if (val == TAPRIO_STAT_NOT_SET) + return 0; + if (nla_put_u64_64bit(skb, attrtype, val, TCA_TAPRIO_OFFLOAD_STATS_PAD)) + return -EMSGSIZE; + return 0; +} + +static int taprio_dump_xstats(struct Qdisc *sch, struct gnet_dump *d, + struct tc_taprio_qopt_offload *offload, + struct tc_taprio_qopt_stats *stats) +{ + struct net_device *dev = qdisc_dev(sch); + const struct net_device_ops *ops; + struct sk_buff *skb = d->skb; + struct nlattr *xstats; + int err; + + ops = qdisc_dev(sch)->netdev_ops; + + /* FIXME I could use qdisc_offload_dump_helper(), but that messes + * with sch->flags depending on whether the device reports taprio + * stats, and I'm not sure whether that's a good idea, considering + * that stats are optional to the offload itself + */ + if (!ops->ndo_setup_tc) + return 0; + + memset(stats, 0xff, sizeof(*stats)); + + err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TAPRIO, offload); + if (err == -EOPNOTSUPP) + return 0; + if (err) + return err; + + xstats = nla_nest_start(skb, TCA_STATS_APP); + if (!xstats) + goto err; + + if (taprio_put_stat(skb, stats->window_drops, + TCA_TAPRIO_OFFLOAD_STATS_WINDOW_DROPS) || + taprio_put_stat(skb, stats->tx_overruns, + TCA_TAPRIO_OFFLOAD_STATS_TX_OVERRUNS)) + goto err_cancel; + + nla_nest_end(skb, xstats); + + return 0; + +err_cancel: + nla_nest_cancel(skb, xstats); +err: + return -EMSGSIZE; +} + +static int taprio_dump_stats(struct Qdisc *sch, struct gnet_dump *d) +{ + struct tc_taprio_qopt_offload offload = { + .cmd = TAPRIO_CMD_STATS, + }; + + return taprio_dump_xstats(sch, d, &offload, &offload.stats); +} + static int taprio_dump(struct Qdisc *sch, struct sk_buff *skb) { struct taprio_sched *q = qdisc_priv(sch); @@ -2389,11 +2457,18 @@ static int taprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, { struct netdev_queue *dev_queue = taprio_queue_get(sch, cl); struct Qdisc *child = dev_queue->qdisc_sleeping; + struct tc_taprio_qopt_offload offload = { + .cmd = TAPRIO_CMD_TC_STATS, + .tc_stats = { + .tc = cl - 1, + }, + }; if (gnet_stats_copy_basic(d, NULL, &child->bstats, true) < 0 || qdisc_qstats_copy(d, child) < 0) return -1; - return 0; + + return taprio_dump_xstats(sch, d, &offload, &offload.tc_stats.stats); } static void taprio_walk(struct Qdisc *sch, struct qdisc_walker *arg) @@ -2440,6 +2515,7 @@ static struct Qdisc_ops taprio_qdisc_ops __read_mostly = { .dequeue = taprio_dequeue, .enqueue = taprio_enqueue, .dump = taprio_dump, + .dump_stats = taprio_dump_stats, .owner = THIS_MODULE, }; -- cgit v1.2.3 From 8ad77e72caae22a1ddcfd0c03f2884929e93b7a4 Mon Sep 17 00:00:00 2001 From: Louis DeLosSantos Date: Wed, 31 May 2023 15:38:48 -0400 Subject: bpf: Add table ID to bpf_fib_lookup BPF helper Add ability to specify routing table ID to the `bpf_fib_lookup` BPF helper. A new field `tbid` is added to `struct bpf_fib_lookup` used as parameters to the `bpf_fib_lookup` BPF helper. When the helper is called with the `BPF_FIB_LOOKUP_DIRECT` and `BPF_FIB_LOOKUP_TBID` flags the `tbid` field in `struct bpf_fib_lookup` will be used as the table ID for the fib lookup. If the `tbid` does not exist the fib lookup will fail with `BPF_FIB_LKUP_RET_NOT_FWDED`. The `tbid` field becomes a union over the vlan related output fields in `struct bpf_fib_lookup` and will be zeroed immediately after usage. This functionality is useful in containerized environments. For instance, if a CNI wants to dictate the next-hop for traffic leaving a container it can create a container-specific routing table and perform a fib lookup against this table in a "host-net-namespace-side" TC program. This functionality also allows `ip rule` like functionality at the TC layer, allowing an eBPF program to pick a routing table based on some aspect of the sk_buff. As a concrete use case, this feature will be used in Cilium's SRv6 L3VPN datapath. When egress traffic leaves a Pod an eBPF program attached by Cilium will determine which VRF the egress traffic should target, and then perform a FIB lookup in a specific table representing this VRF's FIB. Signed-off-by: Louis DeLosSantos Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20230505-bpf-add-tbid-fib-lookup-v2-1-0a31c22c748c@gmail.com --- include/uapi/linux/bpf.h | 21 ++++++++++++++++++--- net/core/filter.c | 14 +++++++++++++- tools/include/uapi/linux/bpf.h | 21 ++++++++++++++++++--- 3 files changed, 49 insertions(+), 7 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 9273c654743c..a7b5e91dd768 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3177,6 +3177,10 @@ union bpf_attr { * **BPF_FIB_LOOKUP_DIRECT** * Do a direct table lookup vs full lookup using FIB * rules. + * **BPF_FIB_LOOKUP_TBID** + * Used with BPF_FIB_LOOKUP_DIRECT. + * Use the routing table ID present in *params*->tbid + * for the fib lookup. * **BPF_FIB_LOOKUP_OUTPUT** * Perform lookup from an egress perspective (default is * ingress). @@ -6831,6 +6835,7 @@ enum { BPF_FIB_LOOKUP_DIRECT = (1U << 0), BPF_FIB_LOOKUP_OUTPUT = (1U << 1), BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2), + BPF_FIB_LOOKUP_TBID = (1U << 3), }; enum { @@ -6891,9 +6896,19 @@ struct bpf_fib_lookup { __u32 ipv6_dst[4]; /* in6_addr; network order */ }; - /* output */ - __be16 h_vlan_proto; - __be16 h_vlan_TCI; + union { + struct { + /* output */ + __be16 h_vlan_proto; + __be16 h_vlan_TCI; + }; + /* input: when accompanied with the + * 'BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_TBID` flags, a + * specific routing table to use for the fib lookup. + */ + __u32 tbid; + }; + __u8 smac[6]; /* ETH_ALEN */ __u8 dmac[6]; /* ETH_ALEN */ }; diff --git a/net/core/filter.c b/net/core/filter.c index 968139f4a1ac..d25d52854c21 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5803,6 +5803,12 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN; struct fib_table *tb; + if (flags & BPF_FIB_LOOKUP_TBID) { + tbid = params->tbid; + /* zero out for vlan output */ + params->tbid = 0; + } + tb = fib_get_table(net, tbid); if (unlikely(!tb)) return BPF_FIB_LKUP_RET_NOT_FWDED; @@ -5936,6 +5942,12 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN; struct fib6_table *tb; + if (flags & BPF_FIB_LOOKUP_TBID) { + tbid = params->tbid; + /* zero out for vlan output */ + params->tbid = 0; + } + tb = ipv6_stub->fib6_get_table(net, tbid); if (unlikely(!tb)) return BPF_FIB_LKUP_RET_NOT_FWDED; @@ -6008,7 +6020,7 @@ set_fwd_params: #endif #define BPF_FIB_LOOKUP_MASK (BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT | \ - BPF_FIB_LOOKUP_SKIP_NEIGH) + BPF_FIB_LOOKUP_SKIP_NEIGH | BPF_FIB_LOOKUP_TBID) BPF_CALL_4(bpf_xdp_fib_lookup, struct xdp_buff *, ctx, struct bpf_fib_lookup *, params, int, plen, u32, flags) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 9273c654743c..a7b5e91dd768 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3177,6 +3177,10 @@ union bpf_attr { * **BPF_FIB_LOOKUP_DIRECT** * Do a direct table lookup vs full lookup using FIB * rules. + * **BPF_FIB_LOOKUP_TBID** + * Used with BPF_FIB_LOOKUP_DIRECT. + * Use the routing table ID present in *params*->tbid + * for the fib lookup. * **BPF_FIB_LOOKUP_OUTPUT** * Perform lookup from an egress perspective (default is * ingress). @@ -6831,6 +6835,7 @@ enum { BPF_FIB_LOOKUP_DIRECT = (1U << 0), BPF_FIB_LOOKUP_OUTPUT = (1U << 1), BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2), + BPF_FIB_LOOKUP_TBID = (1U << 3), }; enum { @@ -6891,9 +6896,19 @@ struct bpf_fib_lookup { __u32 ipv6_dst[4]; /* in6_addr; network order */ }; - /* output */ - __be16 h_vlan_proto; - __be16 h_vlan_TCI; + union { + struct { + /* output */ + __be16 h_vlan_proto; + __be16 h_vlan_TCI; + }; + /* input: when accompanied with the + * 'BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_TBID` flags, a + * specific routing table to use for the fib lookup. + */ + __u32 tbid; + }; + __u8 smac[6]; /* ETH_ALEN */ __u8 dmac[6]; /* ETH_ALEN */ }; -- cgit v1.2.3 From b5bbc52fd01278642773818642288999a0236cb6 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Sat, 3 Jun 2023 12:06:01 +0800 Subject: ublk: add control command of UBLK_U_CMD_GET_FEATURES Add control command of UBLK_U_CMD_GET_FEATURES for returning driver's feature set or capability. This way can simplify userspace for maintaining compatibility because userspace doesn't need to send command to one device for querying driver feature set any more. Such as, with the queried feature set, userspace can choose to use: - UBLK_CMD_GET_DEV_INFO2 or UBLK_CMD_GET_DEV_INFO, - UBLK_U_CMD_* or UBLK_CMD_* Userspace code: https://github.com/ming1/ubdsrv/commits/features-cmd Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20230603040601.775227-1-ming.lei@redhat.com Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 21 +++++++++++++++++++++ include/uapi/linux/ublk_cmd.h | 8 ++++++++ 2 files changed, 29 insertions(+) (limited to 'include/uapi') diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 539eada32861..222a0341913f 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -2343,6 +2343,21 @@ static int ublk_ctrl_end_recovery(struct ublk_device *ub, return ret; } +static int ublk_ctrl_get_features(struct io_uring_cmd *cmd) +{ + const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe); + void __user *argp = (void __user *)(unsigned long)header->addr; + u64 features = UBLK_F_ALL & ~UBLK_F_SUPPORT_ZERO_COPY; + + if (header->len != UBLK_FEATURES_LEN || !header->addr) + return -EINVAL; + + if (copy_to_user(argp, &features, UBLK_FEATURES_LEN)) + return -EFAULT; + + return 0; +} + /* * All control commands are sent via /dev/ublk-control, so we have to check * the destination device's permission @@ -2423,6 +2438,7 @@ static int ublk_ctrl_uring_cmd_permission(struct ublk_device *ub, case UBLK_CMD_GET_DEV_INFO2: case UBLK_CMD_GET_QUEUE_AFFINITY: case UBLK_CMD_GET_PARAMS: + case (_IOC_NR(UBLK_U_CMD_GET_FEATURES)): mask = MAY_READ; break; case UBLK_CMD_START_DEV: @@ -2472,6 +2488,11 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, if (ret) goto out; + if (cmd_op == UBLK_U_CMD_GET_FEATURES) { + ret = ublk_ctrl_get_features(cmd); + goto out; + } + if (_IOC_NR(cmd_op) != UBLK_CMD_ADD_DEV) { ret = -ENODEV; ub = ublk_get_device_from_id(header->dev_id); diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 54b5b0aeefca..4b8558db90e1 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -47,6 +47,14 @@ _IOWR('u', UBLK_CMD_END_USER_RECOVERY, struct ublksrv_ctrl_cmd) #define UBLK_U_CMD_GET_DEV_INFO2 \ _IOR('u', UBLK_CMD_GET_DEV_INFO2, struct ublksrv_ctrl_cmd) +#define UBLK_U_CMD_GET_FEATURES \ + _IOR('u', 0x13, struct ublksrv_ctrl_cmd) + +/* + * 64bits are enough now, and it should be easy to extend in case of + * running out of feature flags + */ +#define UBLK_FEATURES_LEN 8 /* * IO commands, issued by ublk server, and handled by ublk driver. -- cgit v1.2.3 From 224d80c584d3016cb8d83d1c33914fdd3508aa8c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 31 May 2023 15:08:35 +0200 Subject: types: Introduce [us]128 Introduce [us]128 (when available). Unlike [us]64, ensure they are always naturally aligned. This also enables 128bit wide atomics (which require natural alignment) such as cmpxchg128(). Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Arnd Bergmann Reviewed-by: Mark Rutland Acked-by: Herbert Xu Tested-by: Mark Rutland Link: https://lore.kernel.org/r/20230531132323.385005581@infradead.org --- include/linux/types.h | 5 +++++ include/uapi/linux/types.h | 4 ++++ lib/crypto/curve25519-hacl64.c | 2 -- lib/crypto/poly1305-donna64.c | 2 -- 4 files changed, 9 insertions(+), 4 deletions(-) (limited to 'include/uapi') diff --git a/include/linux/types.h b/include/linux/types.h index 688fb943556a..becb8cd5916f 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -10,6 +10,11 @@ #define DECLARE_BITMAP(name,bits) \ unsigned long name[BITS_TO_LONGS(bits)] +#ifdef __SIZEOF_INT128__ +typedef __s128 s128; +typedef __u128 u128; +#endif + typedef u32 __kernel_dev_t; typedef __kernel_fd_set fd_set; diff --git a/include/uapi/linux/types.h b/include/uapi/linux/types.h index 308433be33c2..6375a0684052 100644 --- a/include/uapi/linux/types.h +++ b/include/uapi/linux/types.h @@ -13,6 +13,10 @@ #include +#ifdef __SIZEOF_INT128__ +typedef __signed__ __int128 __s128 __attribute__((aligned(16))); +typedef unsigned __int128 __u128 __attribute__((aligned(16))); +#endif /* * Below are truly Linux-specific types that should never collide with diff --git a/lib/crypto/curve25519-hacl64.c b/lib/crypto/curve25519-hacl64.c index 771d82dc5f14..c40e5d913234 100644 --- a/lib/crypto/curve25519-hacl64.c +++ b/lib/crypto/curve25519-hacl64.c @@ -14,8 +14,6 @@ #include #include -typedef __uint128_t u128; - static __always_inline u64 u64_eq_mask(u64 a, u64 b) { u64 x = a ^ b; diff --git a/lib/crypto/poly1305-donna64.c b/lib/crypto/poly1305-donna64.c index d34cf4053668..988702c9b3b2 100644 --- a/lib/crypto/poly1305-donna64.c +++ b/lib/crypto/poly1305-donna64.c @@ -10,8 +10,6 @@ #include #include -typedef __uint128_t u128; - void poly1305_core_setkey(struct poly1305_core_key *key, const u8 raw_key[POLY1305_BLOCK_SIZE]) { -- cgit v1.2.3 From 98d2722a85c4ad5f2baf2272cbb0fab67f797b69 Mon Sep 17 00:00:00 2001 From: Daniele Ceraolo Spurio Date: Wed, 31 May 2023 16:54:12 -0700 Subject: drm/i915/huc: differentiate the 2 steps of the MTL HuC auth flow Before we add the second step of the MTL HuC auth (via GSC), we need to have the ability to differentiate between them. To do so, the huc authentication check is duplicated for GuC and GSC auth, with GSC-enabled binaries being considered fully authenticated only after the GSC auth step. To report the difference between the 2 auth steps, a new case is added to the HuC getparam. This way, the clear media driver can start submitting before full auth, as partial auth is enough for those workloads. v2: fix authentication status check for DG2 v3: add a better comment at the top of the HuC file to explain the different approaches to load and auth (John) v4: update call to intel_huc_is_authenticated in the pxp code to check for GSC authentication v5: drop references to meu and esclamation mark in huc_auth print (John) Signed-off-by: Daniele Ceraolo Spurio Cc: Alan Previn Cc: John Harrison Reviewed-by: Alan Previn #v2 Reviewed-by: John Harrison Link: https://patchwork.freedesktop.org/patch/msgid/20230531235415.1467475-5-daniele.ceraolospurio@intel.com --- drivers/gpu/drm/i915/gt/uc/intel_huc.c | 111 ++++++++++++++++++++++------- drivers/gpu/drm/i915/gt/uc/intel_huc.h | 16 +++-- drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c | 4 +- drivers/gpu/drm/i915/i915_reg.h | 3 + drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.c | 2 +- include/uapi/drm/i915_drm.h | 3 +- 6 files changed, 104 insertions(+), 35 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c index b1e7a1e1bfa3..4c8592a281f2 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c @@ -10,6 +10,7 @@ #include "intel_huc.h" #include "intel_huc_print.h" #include "i915_drv.h" +#include "i915_reg.h" #include #include @@ -22,15 +23,23 @@ * capabilities by adding HuC specific commands to batch buffers. * * The kernel driver is only responsible for loading the HuC firmware and - * triggering its security authentication, which is performed by the GuC on - * older platforms and by the GSC on newer ones. For the GuC to correctly - * perform the authentication, the HuC binary must be loaded before the GuC one. + * triggering its security authentication. This is done differently depending + * on the platform: + * - older platforms (from Gen9 to most Gen12s): the load is performed via DMA + * and the authentication via GuC + * - DG2: load and authentication are both performed via GSC. + * - MTL and newer platforms: the load is performed via DMA (same as with + * not-DG2 older platforms), while the authentication is done in 2-steps, + * a first auth for clear-media workloads via GuC and a second one for all + * workloads via GSC. + * On platforms where the GuC does the authentication, to correctly do so the + * HuC binary must be loaded before the GuC one. * Loading the HuC is optional; however, not using the HuC might negatively * impact power usage and/or performance of media workloads, depending on the * use-cases. * HuC must be reloaded on events that cause the WOPCM to lose its contents - * (S3/S4, FLR); GuC-authenticated HuC must also be reloaded on GuC/GT reset, - * while GSC-managed HuC will survive that. + * (S3/S4, FLR); on older platforms the HuC must also be reloaded on GuC/GT + * reset, while on newer ones it will survive that. * * See https://github.com/intel/media-driver for the latest details on HuC * functionality. @@ -106,7 +115,7 @@ static enum hrtimer_restart huc_delayed_load_timer_callback(struct hrtimer *hrti { struct intel_huc *huc = container_of(hrtimer, struct intel_huc, delayed_load.timer); - if (!intel_huc_is_authenticated(huc)) { + if (!intel_huc_is_authenticated(huc, INTEL_HUC_AUTH_BY_GSC)) { if (huc->delayed_load.status == INTEL_HUC_WAITING_ON_GSC) huc_notice(huc, "timed out waiting for MEI GSC\n"); else if (huc->delayed_load.status == INTEL_HUC_WAITING_ON_PXP) @@ -124,7 +133,7 @@ static void huc_delayed_load_start(struct intel_huc *huc) { ktime_t delay; - GEM_BUG_ON(intel_huc_is_authenticated(huc)); + GEM_BUG_ON(intel_huc_is_authenticated(huc, INTEL_HUC_AUTH_BY_GSC)); /* * On resume we don't have to wait for MEI-GSC to be re-probed, but we @@ -284,13 +293,23 @@ void intel_huc_init_early(struct intel_huc *huc) } if (GRAPHICS_VER(i915) >= 11) { - huc->status.reg = GEN11_HUC_KERNEL_LOAD_INFO; - huc->status.mask = HUC_LOAD_SUCCESSFUL; - huc->status.value = HUC_LOAD_SUCCESSFUL; + huc->status[INTEL_HUC_AUTH_BY_GUC].reg = GEN11_HUC_KERNEL_LOAD_INFO; + huc->status[INTEL_HUC_AUTH_BY_GUC].mask = HUC_LOAD_SUCCESSFUL; + huc->status[INTEL_HUC_AUTH_BY_GUC].value = HUC_LOAD_SUCCESSFUL; } else { - huc->status.reg = HUC_STATUS2; - huc->status.mask = HUC_FW_VERIFIED; - huc->status.value = HUC_FW_VERIFIED; + huc->status[INTEL_HUC_AUTH_BY_GUC].reg = HUC_STATUS2; + huc->status[INTEL_HUC_AUTH_BY_GUC].mask = HUC_FW_VERIFIED; + huc->status[INTEL_HUC_AUTH_BY_GUC].value = HUC_FW_VERIFIED; + } + + if (IS_DG2(i915)) { + huc->status[INTEL_HUC_AUTH_BY_GSC].reg = GEN11_HUC_KERNEL_LOAD_INFO; + huc->status[INTEL_HUC_AUTH_BY_GSC].mask = HUC_LOAD_SUCCESSFUL; + huc->status[INTEL_HUC_AUTH_BY_GSC].value = HUC_LOAD_SUCCESSFUL; + } else { + huc->status[INTEL_HUC_AUTH_BY_GSC].reg = HECI_FWSTS5(MTL_GSC_HECI1_BASE); + huc->status[INTEL_HUC_AUTH_BY_GSC].mask = HECI_FWSTS5_HUC_AUTH_DONE; + huc->status[INTEL_HUC_AUTH_BY_GSC].value = HECI_FWSTS5_HUC_AUTH_DONE; } } @@ -397,28 +416,38 @@ void intel_huc_suspend(struct intel_huc *huc) delayed_huc_load_complete(huc); } -int intel_huc_wait_for_auth_complete(struct intel_huc *huc) +static const char *auth_mode_string(struct intel_huc *huc, + enum intel_huc_authentication_type type) +{ + bool partial = huc->fw.has_gsc_headers && type == INTEL_HUC_AUTH_BY_GUC; + + return partial ? "clear media" : "all workloads"; +} + +int intel_huc_wait_for_auth_complete(struct intel_huc *huc, + enum intel_huc_authentication_type type) { struct intel_gt *gt = huc_to_gt(huc); int ret; ret = __intel_wait_for_register(gt->uncore, - huc->status.reg, - huc->status.mask, - huc->status.value, + huc->status[type].reg, + huc->status[type].mask, + huc->status[type].value, 2, 50, NULL); /* mark the load process as complete even if the wait failed */ delayed_huc_load_complete(huc); if (ret) { - huc_err(huc, "firmware not verified %pe\n", ERR_PTR(ret)); + huc_err(huc, "firmware not verified for %s: %pe\n", + auth_mode_string(huc, type), ERR_PTR(ret)); intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_LOAD_FAIL); return ret; } intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_RUNNING); - huc_info(huc, "authenticated!\n"); + huc_info(huc, "authenticated for %s\n", auth_mode_string(huc, type)); return 0; } @@ -458,7 +487,7 @@ int intel_huc_auth(struct intel_huc *huc) } /* Check authentication status, it should be done by now */ - ret = intel_huc_wait_for_auth_complete(huc); + ret = intel_huc_wait_for_auth_complete(huc, INTEL_HUC_AUTH_BY_GUC); if (ret) goto fail; @@ -469,16 +498,29 @@ fail: return ret; } -bool intel_huc_is_authenticated(struct intel_huc *huc) +bool intel_huc_is_authenticated(struct intel_huc *huc, + enum intel_huc_authentication_type type) { struct intel_gt *gt = huc_to_gt(huc); intel_wakeref_t wakeref; u32 status = 0; with_intel_runtime_pm(gt->uncore->rpm, wakeref) - status = intel_uncore_read(gt->uncore, huc->status.reg); + status = intel_uncore_read(gt->uncore, huc->status[type].reg); - return (status & huc->status.mask) == huc->status.value; + return (status & huc->status[type].mask) == huc->status[type].value; +} + +static bool huc_is_fully_authenticated(struct intel_huc *huc) +{ + struct intel_uc_fw *huc_fw = &huc->fw; + + if (!huc_fw->has_gsc_headers) + return intel_huc_is_authenticated(huc, INTEL_HUC_AUTH_BY_GUC); + else if (intel_huc_is_loaded_by_gsc(huc) || HAS_ENGINE(huc_to_gt(huc), GSC0)) + return intel_huc_is_authenticated(huc, INTEL_HUC_AUTH_BY_GSC); + else + return false; } /** @@ -493,7 +535,9 @@ bool intel_huc_is_authenticated(struct intel_huc *huc) */ int intel_huc_check_status(struct intel_huc *huc) { - switch (__intel_uc_fw_status(&huc->fw)) { + struct intel_uc_fw *huc_fw = &huc->fw; + + switch (__intel_uc_fw_status(huc_fw)) { case INTEL_UC_FIRMWARE_NOT_SUPPORTED: return -ENODEV; case INTEL_UC_FIRMWARE_DISABLED: @@ -510,7 +554,17 @@ int intel_huc_check_status(struct intel_huc *huc) break; } - return intel_huc_is_authenticated(huc); + /* + * GSC-enabled binaries loaded via DMA are first partially + * authenticated by GuC and then fully authenticated by GSC + */ + if (huc_is_fully_authenticated(huc)) + return 1; /* full auth */ + else if (huc_fw->has_gsc_headers && !intel_huc_is_loaded_by_gsc(huc) && + intel_huc_is_authenticated(huc, INTEL_HUC_AUTH_BY_GUC)) + return 2; /* clear media only */ + else + return 0; } static bool huc_has_delayed_load(struct intel_huc *huc) @@ -524,7 +578,10 @@ void intel_huc_update_auth_status(struct intel_huc *huc) if (!intel_uc_fw_is_loadable(&huc->fw)) return; - if (intel_huc_is_authenticated(huc)) + if (!huc->fw.has_gsc_headers) + return; + + if (huc_is_fully_authenticated(huc)) intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_RUNNING); else if (huc_has_delayed_load(huc)) @@ -557,5 +614,5 @@ void intel_huc_load_status(struct intel_huc *huc, struct drm_printer *p) with_intel_runtime_pm(gt->uncore->rpm, wakeref) drm_printf(p, "HuC status: 0x%08x\n", - intel_uncore_read(gt->uncore, huc->status.reg)); + intel_uncore_read(gt->uncore, huc->status[INTEL_HUC_AUTH_BY_GUC].reg)); } diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.h b/drivers/gpu/drm/i915/gt/uc/intel_huc.h index 112f0dce4702..3f6aa7c37abc 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_huc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.h @@ -22,6 +22,12 @@ enum intel_huc_delayed_load_status { INTEL_HUC_DELAYED_LOAD_ERROR, }; +enum intel_huc_authentication_type { + INTEL_HUC_AUTH_BY_GUC = 0, + INTEL_HUC_AUTH_BY_GSC, + INTEL_HUC_AUTH_MAX_MODES +}; + struct intel_huc { /* Generic uC firmware management */ struct intel_uc_fw fw; @@ -31,7 +37,7 @@ struct intel_huc { i915_reg_t reg; u32 mask; u32 value; - } status; + } status[INTEL_HUC_AUTH_MAX_MODES]; struct { struct i915_sw_fence fence; @@ -49,10 +55,12 @@ int intel_huc_init(struct intel_huc *huc); void intel_huc_fini(struct intel_huc *huc); void intel_huc_suspend(struct intel_huc *huc); int intel_huc_auth(struct intel_huc *huc); -int intel_huc_wait_for_auth_complete(struct intel_huc *huc); +int intel_huc_wait_for_auth_complete(struct intel_huc *huc, + enum intel_huc_authentication_type type); +bool intel_huc_is_authenticated(struct intel_huc *huc, + enum intel_huc_authentication_type type); int intel_huc_check_status(struct intel_huc *huc); void intel_huc_update_auth_status(struct intel_huc *huc); -bool intel_huc_is_authenticated(struct intel_huc *huc); void intel_huc_register_gsc_notifier(struct intel_huc *huc, const struct bus_type *bus); void intel_huc_unregister_gsc_notifier(struct intel_huc *huc, const struct bus_type *bus); @@ -81,7 +89,7 @@ static inline bool intel_huc_is_loaded_by_gsc(const struct intel_huc *huc) static inline bool intel_huc_wait_required(struct intel_huc *huc) { return intel_huc_is_used(huc) && intel_huc_is_loaded_by_gsc(huc) && - !intel_huc_is_authenticated(huc); + !intel_huc_is_authenticated(huc, INTEL_HUC_AUTH_BY_GSC); } void intel_huc_load_status(struct intel_huc *huc, struct drm_printer *p); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c index 89a887d33b77..ac2ae5f5011e 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c @@ -161,7 +161,7 @@ int intel_huc_fw_load_and_auth_via_gsc(struct intel_huc *huc) * component gets re-bound and this function called again. If so, just * mark the HuC as loaded. */ - if (intel_huc_is_authenticated(huc)) { + if (intel_huc_is_authenticated(huc, INTEL_HUC_AUTH_BY_GSC)) { intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_RUNNING); return 0; } @@ -174,7 +174,7 @@ int intel_huc_fw_load_and_auth_via_gsc(struct intel_huc *huc) intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_TRANSFERRED); - return intel_huc_wait_for_auth_complete(huc); + return intel_huc_wait_for_auth_complete(huc, INTEL_HUC_AUTH_BY_GSC); } /** diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index c4197e31962e..e0fc0f588c45 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -941,6 +941,9 @@ #define HECI_H_GS1(base) _MMIO((base) + 0xc4c) #define HECI_H_GS1_ER_PREP REG_BIT(0) +#define HECI_FWSTS5(base) _MMIO((base) + 0xc68) +#define HECI_FWSTS5_HUC_AUTH_DONE (1 << 19) + #define HSW_GTT_CACHE_EN _MMIO(0x4024) #define GTT_CACHE_EN_ALL 0xF0007FFF #define GEN7_WR_WATERMARK _MMIO(0x4028) diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.c b/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.c index a217821eb0fb..f13890ec7db1 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.c +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.c @@ -196,7 +196,7 @@ bool intel_pxp_gsccs_is_ready_for_sessions(struct intel_pxp *pxp) * gsc-proxy init flow (the last set of dependencies that * are out of order) will suffice. */ - if (intel_huc_is_authenticated(&pxp->ctrl_gt->uc.huc) && + if (intel_huc_is_authenticated(&pxp->ctrl_gt->uc.huc, INTEL_HUC_AUTH_BY_GSC) && intel_gsc_uc_fw_proxy_init_done(&pxp->ctrl_gt->uc.gsc)) return true; diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index f31dfacde601..a1848e806059 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -674,7 +674,8 @@ typedef struct drm_i915_irq_wait { * If the IOCTL is successful, the returned parameter will be set to one of the * following values: * * 0 if HuC firmware load is not complete, - * * 1 if HuC firmware is authenticated and running. + * * 1 if HuC firmware is loaded and fully authenticated, + * * 2 if HuC firmware is loaded and authenticated for clear media only */ #define I915_PARAM_HUC_STATUS 42 -- cgit v1.2.3 From 6afc770048edc90405c444163de70b1cdfbb8b57 Mon Sep 17 00:00:00 2001 From: Tony Krowiak Date: Tue, 30 May 2023 18:35:36 -0400 Subject: s390/vfio-ap: realize the VFIO_DEVICE_GET_IRQ_INFO ioctl MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Realize the VFIO_DEVICE_GET_IRQ_INFO ioctl to retrieve the information for the VFIO device request IRQ. Signed-off-by: Tony Krowiak Acked-by: Alex Williamson Reviewed-by: Cédric Le Goater Reviewed-by: Matthew Rosato Tested-by: Matthew Rosato Link: https://lore.kernel.org/r/20230530223538.279198-2-akrowiak@linux.ibm.com Signed-off-by: Alexander Gordeev --- drivers/s390/crypto/vfio_ap_ops.c | 30 +++++++++++++++++++++++++++++- include/uapi/linux/vfio.h | 9 +++++++++ 2 files changed, 38 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c index cfbcb864ab63..35cd90eee937 100644 --- a/drivers/s390/crypto/vfio_ap_ops.c +++ b/drivers/s390/crypto/vfio_ap_ops.c @@ -1750,7 +1750,32 @@ static int vfio_ap_mdev_get_device_info(unsigned long arg) info.flags = VFIO_DEVICE_FLAGS_AP | VFIO_DEVICE_FLAGS_RESET; info.num_regions = 0; - info.num_irqs = 0; + info.num_irqs = VFIO_AP_NUM_IRQS; + + return copy_to_user((void __user *)arg, &info, minsz) ? -EFAULT : 0; +} + +static ssize_t vfio_ap_get_irq_info(unsigned long arg) +{ + unsigned long minsz; + struct vfio_irq_info info; + + minsz = offsetofend(struct vfio_irq_info, count); + + if (copy_from_user(&info, (void __user *)arg, minsz)) + return -EFAULT; + + if (info.argsz < minsz || info.index >= VFIO_AP_NUM_IRQS) + return -EINVAL; + + switch (info.index) { + case VFIO_AP_REQ_IRQ_INDEX: + info.count = 1; + info.flags = VFIO_IRQ_INFO_EVENTFD; + break; + default: + return -EINVAL; + } return copy_to_user((void __user *)arg, &info, minsz) ? -EFAULT : 0; } @@ -1770,6 +1795,9 @@ static ssize_t vfio_ap_mdev_ioctl(struct vfio_device *vdev, case VFIO_DEVICE_RESET: ret = vfio_ap_mdev_reset_queues(&matrix_mdev->qtable); break; + case VFIO_DEVICE_GET_IRQ_INFO: + ret = vfio_ap_get_irq_info(arg); + break; default: ret = -EOPNOTSUPP; break; diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 0552e8dcf0cb..b71276bd7f91 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -646,6 +646,15 @@ enum { VFIO_CCW_NUM_IRQS }; +/* + * The vfio-ap bus driver makes use of the following IRQ index mapping. + * Unimplemented IRQ types return a count of zero. + */ +enum { + VFIO_AP_REQ_IRQ_INDEX, + VFIO_AP_NUM_IRQS +}; + /** * VFIO_DEVICE_GET_PCI_HOT_RESET_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 12, * struct vfio_pci_hot_reset_info) -- cgit v1.2.3 From 55382134366e641e97cd83264c22c60c7dc10ccd Mon Sep 17 00:00:00 2001 From: "GONG, Ruiqi" Date: Fri, 2 Jun 2023 13:45:27 +0800 Subject: capability: erase checker warnings about struct __user_cap_data_struct Currently Sparse warns the following when compiling kernel/capability.c: kernel/capability.c:191:35: warning: incorrect type in argument 2 (different address spaces) kernel/capability.c:191:35: expected void const *from kernel/capability.c:191:35: got struct __user_cap_data_struct [noderef] __user * kernel/capability.c:168:14: warning: dereference of noderef expression ...... (multiple noderef warnings on different locations) kernel/capability.c:244:29: warning: incorrect type in argument 1 (different address spaces) kernel/capability.c:244:29: expected void *to kernel/capability.c:244:29: got struct __user_cap_data_struct [noderef] __user ( * )[2] kernel/capability.c:247:42: warning: dereference of noderef expression ...... (multiple noderef warnings on different locations) It seems that defining `struct __user_cap_data_struct` together with `cap_user_data_t` make Sparse believe that the struct is `noderef` as well. Separate their definitions to clarify their respective attributes. Signed-off-by: GONG, Ruiqi Acked-by: Serge Hallyn [PM: wrapped long lines in the description] Signed-off-by: Paul Moore --- include/uapi/linux/capability.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/capability.h b/include/uapi/linux/capability.h index 3d61a0ae055d..5bb906098697 100644 --- a/include/uapi/linux/capability.h +++ b/include/uapi/linux/capability.h @@ -41,11 +41,12 @@ typedef struct __user_cap_header_struct { int pid; } __user *cap_user_header_t; -typedef struct __user_cap_data_struct { +struct __user_cap_data_struct { __u32 effective; __u32 permitted; __u32 inheritable; -} __user *cap_user_data_t; +}; +typedef struct __user_cap_data_struct __user *cap_user_data_t; #define VFS_CAP_REVISION_MASK 0xFF000000 -- cgit v1.2.3 From 81b1b599dfd71c958418dad586fa72c8d30d1065 Mon Sep 17 00:00:00 2001 From: Fei Yang Date: Tue, 6 Jun 2023 12:00:42 +0200 Subject: drm/i915: Allow user to set cache at BO creation To comply with the design that buffer objects shall have immutable cache setting through out their life cycle, {set, get}_caching ioctl's are no longer supported from MTL onward. With that change caching policy can only be set at object creation time. The current code applies a default (platform dependent) cache setting for all objects. However this is not optimal for performance tuning. The patch extends the existing gem_create uAPI to let user set PAT index for the object at creation time. The new extension is platform independent, so UMD's can switch to using this extension for older platforms as well, while {set, get}_caching are still supported on these legacy paltforms for compatibility reason. However, since PAT index was not clearly defined for platforms prior to GEN12 (TGL), so we are limiting this externsion to GEN12+ platforms only. See ext_set_pat() in for the implementation details. The documentation related to the PAT/MOCS tables is currently available for Tiger Lake here: https://www.intel.com/content/www/us/en/docs/graphics-for-linux/developer-reference/1-0/tiger-lake.html The documentation for other platforms is currently being updated. BSpec: 45101 Mesa support has been submitted in this merge request: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22878 The media driver supprt has bin submitted in this merge request: https://github.com/intel/media-driver/pull/1680 The IGT test related to this change is igt@gem_create@create-ext-set-pat Signed-off-by: Fei Yang Cc: Chris Wilson Cc: Matt Roper Cc: Andi Shyti Reviewed-by: Andi Shyti Acked-by: Jordan Justen Tested-by: Jordan Justen Acked-by: Carl Zhang Tested-by: Lihao Gu Signed-off-by: Andi Shyti Acked-by: Tvrtko Ursulin Acked-by: Slawomir Milczarek Link: https://patchwork.freedesktop.org/patch/msgid/20230606100042.482345-2-andi.shyti@linux.intel.com --- drivers/gpu/drm/i915/gem/i915_gem_create.c | 40 +++++++++++++++++++++++++++++ drivers/gpu/drm/i915/gem/i915_gem_object.c | 6 +++++ include/uapi/drm/i915_drm.h | 41 ++++++++++++++++++++++++++++++ 3 files changed, 87 insertions(+) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/i915/gem/i915_gem_create.c b/drivers/gpu/drm/i915/gem/i915_gem_create.c index bfe1dbda4cb7..d24c0ce8805c 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_create.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_create.c @@ -245,6 +245,7 @@ struct create_ext { unsigned int n_placements; unsigned int placement_mask; unsigned long flags; + unsigned int pat_index; }; static void repr_placements(char *buf, size_t size, @@ -394,11 +395,43 @@ static int ext_set_protected(struct i915_user_extension __user *base, void *data return 0; } +static int ext_set_pat(struct i915_user_extension __user *base, void *data) +{ + struct create_ext *ext_data = data; + struct drm_i915_private *i915 = ext_data->i915; + struct drm_i915_gem_create_ext_set_pat ext; + unsigned int max_pat_index; + + BUILD_BUG_ON(sizeof(struct drm_i915_gem_create_ext_set_pat) != + offsetofend(struct drm_i915_gem_create_ext_set_pat, rsvd)); + + /* Limiting the extension only to Meteor Lake */ + if (!IS_METEORLAKE(i915)) + return -ENODEV; + + if (copy_from_user(&ext, base, sizeof(ext))) + return -EFAULT; + + max_pat_index = INTEL_INFO(i915)->max_pat_index; + + if (ext.pat_index > max_pat_index) { + drm_dbg(&i915->drm, "PAT index is invalid: %u\n", + ext.pat_index); + return -EINVAL; + } + + ext_data->pat_index = ext.pat_index; + + return 0; +} + static const i915_user_extension_fn create_extensions[] = { [I915_GEM_CREATE_EXT_MEMORY_REGIONS] = ext_set_placements, [I915_GEM_CREATE_EXT_PROTECTED_CONTENT] = ext_set_protected, + [I915_GEM_CREATE_EXT_SET_PAT] = ext_set_pat, }; +#define PAT_INDEX_NOT_SET 0xffff /** * i915_gem_create_ext_ioctl - Creates a new mm object and returns a handle to it. * @dev: drm device pointer @@ -418,6 +451,7 @@ i915_gem_create_ext_ioctl(struct drm_device *dev, void *data, if (args->flags & ~I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS) return -EINVAL; + ext_data.pat_index = PAT_INDEX_NOT_SET; ret = i915_user_extensions(u64_to_user_ptr(args->extensions), create_extensions, ARRAY_SIZE(create_extensions), @@ -454,5 +488,11 @@ i915_gem_create_ext_ioctl(struct drm_device *dev, void *data, if (IS_ERR(obj)) return PTR_ERR(obj); + if (ext_data.pat_index != PAT_INDEX_NOT_SET) { + i915_gem_object_set_pat_index(obj, ext_data.pat_index); + /* Mark pat_index is set by UMD */ + obj->pat_set_by_user = true; + } + return i915_gem_publish(obj, file, &args->size, &args->handle); } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c index 46a19b099ec8..97ac6fb37958 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c @@ -208,6 +208,12 @@ bool i915_gem_object_can_bypass_llc(struct drm_i915_gem_object *obj) if (!(obj->flags & I915_BO_ALLOC_USER)) return false; + /* + * Always flush cache for UMD objects at creation time. + */ + if (obj->pat_set_by_user) + return true; + /* * EHL and JSL add the 'Bypass LLC' MOCS entry, which should make it * possible for userspace to bypass the GTT caching bits set by the diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index a1848e806059..7000e5910a1d 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -3680,9 +3680,13 @@ struct drm_i915_gem_create_ext { * * For I915_GEM_CREATE_EXT_PROTECTED_CONTENT usage see * struct drm_i915_gem_create_ext_protected_content. + * + * For I915_GEM_CREATE_EXT_SET_PAT usage see + * struct drm_i915_gem_create_ext_set_pat. */ #define I915_GEM_CREATE_EXT_MEMORY_REGIONS 0 #define I915_GEM_CREATE_EXT_PROTECTED_CONTENT 1 +#define I915_GEM_CREATE_EXT_SET_PAT 2 __u64 extensions; }; @@ -3797,6 +3801,43 @@ struct drm_i915_gem_create_ext_protected_content { __u32 flags; }; +/** + * struct drm_i915_gem_create_ext_set_pat - The + * I915_GEM_CREATE_EXT_SET_PAT extension. + * + * If this extension is provided, the specified caching policy (PAT index) is + * applied to the buffer object. + * + * Below is an example on how to create an object with specific caching policy: + * + * .. code-block:: C + * + * struct drm_i915_gem_create_ext_set_pat set_pat_ext = { + * .base = { .name = I915_GEM_CREATE_EXT_SET_PAT }, + * .pat_index = 0, + * }; + * struct drm_i915_gem_create_ext create_ext = { + * .size = PAGE_SIZE, + * .extensions = (uintptr_t)&set_pat_ext, + * }; + * + * int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext); + * if (err) ... + */ +struct drm_i915_gem_create_ext_set_pat { + /** @base: Extension link. See struct i915_user_extension. */ + struct i915_user_extension base; + /** + * @pat_index: PAT index to be set + * PAT index is a bit field in Page Table Entry to control caching + * behaviors for GPU accesses. The definition of PAT index is + * platform dependent and can be found in hardware specifications, + */ + __u32 pat_index; + /** @rsvd: reserved for future use */ + __u32 rsvd; +}; + /* ID of the protected content session managed by i915 when PXP is active */ #define I915_PROTECTED_CONTENT_DEFAULT_SESSION 0xf -- cgit v1.2.3 From 3a41db531e5124adaa3a9ab9ca0c724aee85b10c Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 10 Mar 2023 18:45:41 +0200 Subject: pktcdvd: Get rid of custom printing macros We may use traditional dev_*() macros instead of custom ones provided by the driver. Signed-off-by: Andy Shevchenko Reviewed-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20230310164549.22133-2-andriy.shevchenko@linux.intel.com Signed-off-by: Jens Axboe --- drivers/block/pktcdvd.c | 247 ++++++++++++++++++++++--------------------- include/linux/pktcdvd.h | 1 - include/uapi/linux/pktcdvd.h | 1 + 3 files changed, 130 insertions(+), 119 deletions(-) (limited to 'include/uapi') diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 377f8b345352..a327cce67768 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -72,22 +72,6 @@ #define DRIVER_NAME "pktcdvd" -#define pkt_err(pd, fmt, ...) \ - pr_err("%s: " fmt, pd->name, ##__VA_ARGS__) -#define pkt_notice(pd, fmt, ...) \ - pr_notice("%s: " fmt, pd->name, ##__VA_ARGS__) -#define pkt_info(pd, fmt, ...) \ - pr_info("%s: " fmt, pd->name, ##__VA_ARGS__) - -#define pkt_dbg(level, pd, fmt, ...) \ -do { \ - if (level == 2 && PACKET_DEBUG >= 2) \ - pr_notice("%s: %s():" fmt, \ - pd->name, __func__, ##__VA_ARGS__); \ - else if (level == 1 && PACKET_DEBUG >= 1) \ - pr_notice("%s: " fmt, pd->name, ##__VA_ARGS__); \ -} while (0) - #define MAX_SPEED 0xffff static DEFINE_MUTEX(pktcdvd_mutex); @@ -319,7 +303,7 @@ static void pkt_sysfs_dev_new(struct pktcdvd_device *pd) if (class_is_registered(&class_pktcdvd)) { pd->dev = device_create_with_groups(&class_pktcdvd, NULL, MKDEV(0, 0), pd, pkt_groups, - "%s", pd->name); + "%s", pd->disk->disk_name); if (IS_ERR(pd->dev)) pd->dev = NULL; } @@ -350,7 +334,7 @@ static ssize_t device_map_show(const struct class *c, const struct class_attribu if (!pd) continue; n += sprintf(data+n, "%s %u:%u %u:%u\n", - pd->name, + pd->disk->disk_name, MAJOR(pd->pkt_dev), MINOR(pd->pkt_dev), MAJOR(pd->bdev->bd_dev), MINOR(pd->bdev->bd_dev)); @@ -450,7 +434,7 @@ static void pkt_debugfs_dev_new(struct pktcdvd_device *pd) { if (!pkt_debugfs_root) return; - pd->dfs_d_root = debugfs_create_dir(pd->name, pkt_debugfs_root); + pd->dfs_d_root = debugfs_create_dir(pd->disk->disk_name, pkt_debugfs_root); if (!pd->dfs_d_root) return; @@ -484,9 +468,11 @@ static void pkt_debugfs_cleanup(void) static void pkt_bio_finished(struct pktcdvd_device *pd) { + struct device *ddev = disk_to_dev(pd->disk); + BUG_ON(atomic_read(&pd->cdrw.pending_bios) <= 0); if (atomic_dec_and_test(&pd->cdrw.pending_bios)) { - pkt_dbg(2, pd, "queue empty\n"); + dev_dbg(ddev, "queue empty\n"); atomic_set(&pd->iosched.attention, 1); wake_up(&pd->wqueue); } @@ -717,15 +703,16 @@ static const char *sense_key_string(__u8 index) static void pkt_dump_sense(struct pktcdvd_device *pd, struct packet_command *cgc) { + struct device *ddev = disk_to_dev(pd->disk); struct scsi_sense_hdr *sshdr = cgc->sshdr; if (sshdr) - pkt_err(pd, "%*ph - sense %02x.%02x.%02x (%s)\n", + dev_err(ddev, "%*ph - sense %02x.%02x.%02x (%s)\n", CDROM_PACKET_SIZE, cgc->cmd, sshdr->sense_key, sshdr->asc, sshdr->ascq, sense_key_string(sshdr->sense_key)); else - pkt_err(pd, "%*ph - no sense\n", CDROM_PACKET_SIZE, cgc->cmd); + dev_err(ddev, "%*ph - no sense\n", CDROM_PACKET_SIZE, cgc->cmd); } /* @@ -809,6 +796,7 @@ static void pkt_queue_bio(struct pktcdvd_device *pd, struct bio *bio) */ static void pkt_iosched_process_queue(struct pktcdvd_device *pd) { + struct device *ddev = disk_to_dev(pd->disk); if (atomic_read(&pd->iosched.attention) == 0) return; @@ -836,7 +824,7 @@ static void pkt_iosched_process_queue(struct pktcdvd_device *pd) need_write_seek = 0; if (need_write_seek && reads_queued) { if (atomic_read(&pd->cdrw.pending_bios) > 0) { - pkt_dbg(2, pd, "write, waiting\n"); + dev_dbg(ddev, "write, waiting\n"); break; } pkt_flush_cache(pd); @@ -845,7 +833,7 @@ static void pkt_iosched_process_queue(struct pktcdvd_device *pd) } else { if (!reads_queued && writes_queued) { if (atomic_read(&pd->cdrw.pending_bios) > 0) { - pkt_dbg(2, pd, "read, waiting\n"); + dev_dbg(ddev, "read, waiting\n"); break; } pd->iosched.writing = 1; @@ -892,6 +880,8 @@ static void pkt_iosched_process_queue(struct pktcdvd_device *pd) */ static int pkt_set_segment_merging(struct pktcdvd_device *pd, struct request_queue *q) { + struct device *ddev = disk_to_dev(pd->disk); + if ((pd->settings.size << 9) / CD_FRAMESIZE <= queue_max_segments(q)) { /* @@ -908,7 +898,7 @@ static int pkt_set_segment_merging(struct pktcdvd_device *pd, struct request_que set_bit(PACKET_MERGE_SEGS, &pd->flags); return 0; } else { - pkt_err(pd, "cdrom max_phys_segments too small\n"); + dev_err(ddev, "cdrom max_phys_segments too small\n"); return -EIO; } } @@ -919,7 +909,7 @@ static void pkt_end_io_read(struct bio *bio) struct pktcdvd_device *pd = pkt->pd; BUG_ON(!pd); - pkt_dbg(2, pd, "bio=%p sec0=%llx sec=%llx err=%d\n", + dev_dbg(disk_to_dev(pd->disk), "bio=%p sec0=%llx sec=%llx err=%d\n", bio, (unsigned long long)pkt->sector, (unsigned long long)bio->bi_iter.bi_sector, bio->bi_status); @@ -939,7 +929,7 @@ static void pkt_end_io_packet_write(struct bio *bio) struct pktcdvd_device *pd = pkt->pd; BUG_ON(!pd); - pkt_dbg(2, pd, "id=%d, err=%d\n", pkt->id, bio->bi_status); + dev_dbg(disk_to_dev(pd->disk), "id=%d, err=%d\n", pkt->id, bio->bi_status); pd->stats.pkt_ended++; @@ -955,6 +945,7 @@ static void pkt_end_io_packet_write(struct bio *bio) */ static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt) { + struct device *ddev = disk_to_dev(pd->disk); int frames_read = 0; struct bio *bio; int f; @@ -983,8 +974,7 @@ static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt) spin_unlock(&pkt->lock); if (pkt->cache_valid) { - pkt_dbg(2, pd, "zone %llx cached\n", - (unsigned long long)pkt->sector); + dev_dbg(ddev, "zone %llx cached\n", (unsigned long long)pkt->sector); goto out_account; } @@ -1005,8 +995,8 @@ static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt) p = (f * CD_FRAMESIZE) / PAGE_SIZE; offset = (f * CD_FRAMESIZE) % PAGE_SIZE; - pkt_dbg(2, pd, "Adding frame %d, page:%p offs:%d\n", - f, pkt->pages[p], offset); + dev_dbg(ddev, "Adding frame %d, page:%p offs:%d\n", f, + pkt->pages[p], offset); if (!bio_add_page(bio, pkt->pages[p], CD_FRAMESIZE, offset)) BUG(); @@ -1016,8 +1006,8 @@ static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt) } out_account: - pkt_dbg(2, pd, "need %d frames for zone %llx\n", - frames_read, (unsigned long long)pkt->sector); + dev_dbg(ddev, "need %d frames for zone %llx\n", frames_read, + (unsigned long long)pkt->sector); pd->stats.pkt_started++; pd->stats.secs_rg += frames_read * (CD_FRAMESIZE >> 9); } @@ -1051,17 +1041,18 @@ static void pkt_put_packet_data(struct pktcdvd_device *pd, struct packet_data *p } } -static inline void pkt_set_state(struct packet_data *pkt, enum packet_data_state state) +static inline void pkt_set_state(struct device *ddev, struct packet_data *pkt, + enum packet_data_state state) { -#if PACKET_DEBUG > 1 static const char *state_name[] = { "IDLE", "WAITING", "READ_WAIT", "WRITE_WAIT", "RECOVERY", "FINISHED" }; enum packet_data_state old_state = pkt->state; - pkt_dbg(2, pd, "pkt %2d : s=%6llx %s -> %s\n", + + dev_dbg(ddev, "pkt %2d : s=%6llx %s -> %s\n", pkt->id, (unsigned long long)pkt->sector, state_name[old_state], state_name[state]); -#endif + pkt->state = state; } @@ -1071,6 +1062,7 @@ static inline void pkt_set_state(struct packet_data *pkt, enum packet_data_state */ static int pkt_handle_queue(struct pktcdvd_device *pd) { + struct device *ddev = disk_to_dev(pd->disk); struct packet_data *pkt, *p; struct bio *bio = NULL; sector_t zone = 0; /* Suppress gcc warning */ @@ -1080,7 +1072,7 @@ static int pkt_handle_queue(struct pktcdvd_device *pd) atomic_set(&pd->scan_queue, 0); if (list_empty(&pd->cdrw.pkt_free_list)) { - pkt_dbg(2, pd, "no pkt\n"); + dev_dbg(ddev, "no pkt\n"); return 0; } @@ -1117,7 +1109,7 @@ try_next_bio: } spin_unlock(&pd->lock); if (!bio) { - pkt_dbg(2, pd, "no bio\n"); + dev_dbg(ddev, "no bio\n"); return 0; } @@ -1133,12 +1125,13 @@ try_next_bio: * to this packet. */ spin_lock(&pd->lock); - pkt_dbg(2, pd, "looking for zone %llx\n", (unsigned long long)zone); + dev_dbg(ddev, "looking for zone %llx\n", (unsigned long long)zone); while ((node = pkt_rbtree_find(pd, zone)) != NULL) { + sector_t tmp = get_zone(node->bio->bi_iter.bi_sector, pd); + bio = node->bio; - pkt_dbg(2, pd, "found zone=%llx\n", (unsigned long long) - get_zone(bio->bi_iter.bi_sector, pd)); - if (get_zone(bio->bi_iter.bi_sector, pd) != zone) + dev_dbg(ddev, "found zone=%llx\n", (unsigned long long)tmp); + if (tmp != zone) break; pkt_rbtree_erase(pd, node); spin_lock(&pkt->lock); @@ -1157,7 +1150,7 @@ try_next_bio: spin_unlock(&pd->lock); pkt->sleep_time = max(PACKET_WAIT_TIME, 1); - pkt_set_state(pkt, PACKET_WAITING_STATE); + pkt_set_state(ddev, pkt, PACKET_WAITING_STATE); atomic_set(&pkt->run_sm, 1); spin_lock(&pd->cdrw.active_list_lock); @@ -1209,6 +1202,7 @@ static void bio_list_copy_data(struct bio *dst, struct bio *src) */ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt) { + struct device *ddev = disk_to_dev(pd->disk); int f; bio_init(pkt->w_bio, pd->bdev, pkt->w_bio->bi_inline_vecs, pkt->frames, @@ -1225,7 +1219,7 @@ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt) if (!bio_add_page(pkt->w_bio, page, CD_FRAMESIZE, offset)) BUG(); } - pkt_dbg(2, pd, "vcnt=%d\n", pkt->w_bio->bi_vcnt); + dev_dbg(ddev, "vcnt=%d\n", pkt->w_bio->bi_vcnt); /* * Fill-in bvec with data from orig_bios. @@ -1233,11 +1227,11 @@ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt) spin_lock(&pkt->lock); bio_list_copy_data(pkt->w_bio, pkt->orig_bios.head); - pkt_set_state(pkt, PACKET_WRITE_WAIT_STATE); + pkt_set_state(ddev, pkt, PACKET_WRITE_WAIT_STATE); spin_unlock(&pkt->lock); - pkt_dbg(2, pd, "Writing %d frames for zone %llx\n", - pkt->write_size, (unsigned long long)pkt->sector); + dev_dbg(ddev, "Writing %d frames for zone %llx\n", pkt->write_size, + (unsigned long long)pkt->sector); if (test_bit(PACKET_MERGE_SEGS, &pd->flags) || (pkt->write_size < pkt->frames)) pkt->cache_valid = 1; @@ -1265,7 +1259,9 @@ static void pkt_finish_packet(struct packet_data *pkt, blk_status_t status) static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data *pkt) { - pkt_dbg(2, pd, "pkt %d\n", pkt->id); + struct device *ddev = disk_to_dev(pd->disk); + + dev_dbg(ddev, "pkt %d\n", pkt->id); for (;;) { switch (pkt->state) { @@ -1275,7 +1271,7 @@ static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data pkt->sleep_time = 0; pkt_gather_data(pd, pkt); - pkt_set_state(pkt, PACKET_READ_WAIT_STATE); + pkt_set_state(ddev, pkt, PACKET_READ_WAIT_STATE); break; case PACKET_READ_WAIT_STATE: @@ -1283,7 +1279,7 @@ static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data return; if (atomic_read(&pkt->io_errors) > 0) { - pkt_set_state(pkt, PACKET_RECOVERY_STATE); + pkt_set_state(ddev, pkt, PACKET_RECOVERY_STATE); } else { pkt_start_write(pd, pkt); } @@ -1294,15 +1290,15 @@ static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data return; if (!pkt->w_bio->bi_status) { - pkt_set_state(pkt, PACKET_FINISHED_STATE); + pkt_set_state(ddev, pkt, PACKET_FINISHED_STATE); } else { - pkt_set_state(pkt, PACKET_RECOVERY_STATE); + pkt_set_state(ddev, pkt, PACKET_RECOVERY_STATE); } break; case PACKET_RECOVERY_STATE: - pkt_dbg(2, pd, "No recovery possible\n"); - pkt_set_state(pkt, PACKET_FINISHED_STATE); + dev_dbg(ddev, "No recovery possible\n"); + pkt_set_state(ddev, pkt, PACKET_FINISHED_STATE); break; case PACKET_FINISHED_STATE: @@ -1318,6 +1314,7 @@ static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data static void pkt_handle_packets(struct pktcdvd_device *pd) { + struct device *ddev = disk_to_dev(pd->disk); struct packet_data *pkt, *next; /* @@ -1338,7 +1335,7 @@ static void pkt_handle_packets(struct pktcdvd_device *pd) if (pkt->state == PACKET_FINISHED_STATE) { list_del(&pkt->list); pkt_put_packet_data(pd, pkt); - pkt_set_state(pkt, PACKET_IDLE_STATE); + pkt_set_state(ddev, pkt, PACKET_IDLE_STATE); atomic_set(&pd->scan_queue, 1); } } @@ -1367,7 +1364,9 @@ static void pkt_count_states(struct pktcdvd_device *pd, int *states) static int kcdrwd(void *foobar) { struct pktcdvd_device *pd = foobar; + struct device *ddev = disk_to_dev(pd->disk); struct packet_data *pkt; + int states[PACKET_NUM_STATES]; long min_sleep_time, residue; set_user_nice(current, MIN_NICE); @@ -1398,13 +1397,9 @@ static int kcdrwd(void *foobar) goto work_to_do; /* Otherwise, go to sleep */ - if (PACKET_DEBUG > 1) { - int states[PACKET_NUM_STATES]; - pkt_count_states(pd, states); - pkt_dbg(2, pd, "i:%d ow:%d rw:%d ww:%d rec:%d fin:%d\n", - states[0], states[1], states[2], - states[3], states[4], states[5]); - } + pkt_count_states(pd, states); + dev_dbg(ddev, "i:%d ow:%d rw:%d ww:%d rec:%d fin:%d\n", + states[0], states[1], states[2], states[3], states[4], states[5]); min_sleep_time = MAX_SCHEDULE_TIMEOUT; list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) { @@ -1412,9 +1407,9 @@ static int kcdrwd(void *foobar) min_sleep_time = pkt->sleep_time; } - pkt_dbg(2, pd, "sleeping\n"); + dev_dbg(ddev, "sleeping\n"); residue = schedule_timeout(min_sleep_time); - pkt_dbg(2, pd, "wake up\n"); + dev_dbg(ddev, "wake up\n"); /* make swsusp happy with our thread */ try_to_freeze(); @@ -1462,7 +1457,7 @@ work_to_do: static void pkt_print_settings(struct pktcdvd_device *pd) { - pkt_info(pd, "%s packets, %u blocks, Mode-%c disc\n", + dev_info(disk_to_dev(pd->disk), "%s packets, %u blocks, Mode-%c disc\n", pd->settings.fp ? "Fixed" : "Variable", pd->settings.size >> 2, pd->settings.block_mode == 8 ? '1' : '2'); @@ -1590,6 +1585,7 @@ static noinline_for_stack int pkt_get_last_written(struct pktcdvd_device *pd, */ static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd) { + struct device *ddev = disk_to_dev(pd->disk); struct packet_command cgc; struct scsi_sense_hdr sshdr; write_param_page *wp; @@ -1656,7 +1652,7 @@ static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd) /* * paranoia */ - pkt_err(pd, "write mode wrong %d\n", wp->data_block_type); + dev_err(ddev, "write mode wrong %d\n", wp->data_block_type); return 1; } wp->packet_size = cpu_to_be32(pd->settings.size >> 2); @@ -1677,6 +1673,8 @@ static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd) */ static int pkt_writable_track(struct pktcdvd_device *pd, track_information *ti) { + struct device *ddev = disk_to_dev(pd->disk); + switch (pd->mmc3_profile) { case 0x1a: /* DVD+RW */ case 0x12: /* DVD-RAM */ @@ -1701,7 +1699,7 @@ static int pkt_writable_track(struct pktcdvd_device *pd, track_information *ti) if (ti->rt == 1 && ti->blank == 0) return 1; - pkt_err(pd, "bad state %d-%d-%d\n", ti->rt, ti->blank, ti->packet); + dev_err(ddev, "bad state %d-%d-%d\n", ti->rt, ti->blank, ti->packet); return 0; } @@ -1710,6 +1708,8 @@ static int pkt_writable_track(struct pktcdvd_device *pd, track_information *ti) */ static int pkt_writable_disc(struct pktcdvd_device *pd, disc_information *di) { + struct device *ddev = disk_to_dev(pd->disk); + switch (pd->mmc3_profile) { case 0x0a: /* CD-RW */ case 0xffff: /* MMC3 not supported */ @@ -1719,8 +1719,7 @@ static int pkt_writable_disc(struct pktcdvd_device *pd, disc_information *di) case 0x12: /* DVD-RAM */ return 1; default: - pkt_dbg(2, pd, "Wrong disc profile (%x)\n", - pd->mmc3_profile); + dev_dbg(ddev, "Wrong disc profile (%x)\n", pd->mmc3_profile); return 0; } @@ -1729,22 +1728,22 @@ static int pkt_writable_disc(struct pktcdvd_device *pd, disc_information *di) * but i'm not sure, should we leave this to user apps? probably. */ if (di->disc_type == 0xff) { - pkt_notice(pd, "unknown disc - no track?\n"); + dev_notice(ddev, "unknown disc - no track?\n"); return 0; } if (di->disc_type != 0x20 && di->disc_type != 0) { - pkt_err(pd, "wrong disc type (%x)\n", di->disc_type); + dev_err(ddev, "wrong disc type (%x)\n", di->disc_type); return 0; } if (di->erasable == 0) { - pkt_notice(pd, "disc not erasable\n"); + dev_err(ddev, "disc not erasable\n"); return 0; } if (di->border_status == PACKET_SESSION_RESERVED) { - pkt_err(pd, "can't write to last track (reserved)\n"); + dev_err(ddev, "can't write to last track (reserved)\n"); return 0; } @@ -1753,6 +1752,7 @@ static int pkt_writable_disc(struct pktcdvd_device *pd, disc_information *di) static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd) { + struct device *ddev = disk_to_dev(pd->disk); struct packet_command cgc; unsigned char buf[12]; disc_information di; @@ -1770,7 +1770,7 @@ static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd) ret = pkt_get_disc_info(pd, &di); if (ret) { - pkt_err(pd, "failed get_disc\n"); + dev_err(ddev, "failed get_disc\n"); return ret; } @@ -1782,12 +1782,12 @@ static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd) track = 1; /* (di.last_track_msb << 8) | di.last_track_lsb; */ ret = pkt_get_track_info(pd, track, 1, &ti); if (ret) { - pkt_err(pd, "failed get_track\n"); + dev_err(ddev, "failed get_track\n"); return ret; } if (!pkt_writable_track(pd, &ti)) { - pkt_err(pd, "can't write to this track\n"); + dev_err(ddev, "can't write to this track\n"); return -EROFS; } @@ -1797,11 +1797,11 @@ static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd) */ pd->settings.size = be32_to_cpu(ti.fixed_packet_size) << 2; if (pd->settings.size == 0) { - pkt_notice(pd, "detected zero packet size!\n"); + dev_notice(ddev, "detected zero packet size!\n"); return -ENXIO; } if (pd->settings.size > PACKET_MAX_SECTORS) { - pkt_err(pd, "packet size is too big\n"); + dev_err(ddev, "packet size is too big\n"); return -EROFS; } pd->settings.fp = ti.fp; @@ -1843,7 +1843,7 @@ static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd) pd->settings.block_mode = PACKET_BLOCK_MODE2; break; default: - pkt_err(pd, "unknown data mode\n"); + dev_err(ddev, "unknown data mode\n"); return -EROFS; } return 0; @@ -1854,6 +1854,7 @@ static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd) */ static noinline_for_stack int pkt_write_caching(struct pktcdvd_device *pd) { + struct device *ddev = disk_to_dev(pd->disk); struct packet_command cgc; struct scsi_sense_hdr sshdr; unsigned char buf[64]; @@ -1883,10 +1884,10 @@ static noinline_for_stack int pkt_write_caching(struct pktcdvd_device *pd) cgc.buflen = cgc.cmd[8] = 2 + ((buf[0] << 8) | (buf[1] & 0xff)); ret = pkt_mode_select(pd, &cgc); if (ret) { - pkt_err(pd, "write caching control failed\n"); + dev_err(ddev, "write caching control failed\n"); pkt_dump_sense(pd, &cgc); } else if (!ret && set) - pkt_notice(pd, "enabled write caching\n"); + dev_notice(ddev, "enabled write caching\n"); return ret; } @@ -1967,6 +1968,7 @@ static char us_clv_to_speed[16] = { static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd, unsigned *speed) { + struct device *ddev = disk_to_dev(pd->disk); struct packet_command cgc; struct scsi_sense_hdr sshdr; unsigned char buf[64]; @@ -2001,11 +2003,11 @@ static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd, } if (!(buf[6] & 0x40)) { - pkt_notice(pd, "disc type is not CD-RW\n"); + dev_notice(ddev, "disc type is not CD-RW\n"); return 1; } if (!(buf[6] & 0x4)) { - pkt_notice(pd, "A1 values on media are not valid, maybe not CDRW?\n"); + dev_notice(ddev, "A1 values on media are not valid, maybe not CDRW?\n"); return 1; } @@ -2025,25 +2027,26 @@ static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd, *speed = us_clv_to_speed[sp]; break; default: - pkt_notice(pd, "unknown disc sub-type %d\n", st); + dev_notice(ddev, "unknown disc sub-type %d\n", st); return 1; } if (*speed) { - pkt_info(pd, "maximum media speed: %d\n", *speed); + dev_info(ddev, "maximum media speed: %d\n", *speed); return 0; } else { - pkt_notice(pd, "unknown speed %d for sub-type %d\n", sp, st); + dev_notice(ddev, "unknown speed %d for sub-type %d\n", sp, st); return 1; } } static noinline_for_stack int pkt_perform_opc(struct pktcdvd_device *pd) { + struct device *ddev = disk_to_dev(pd->disk); struct packet_command cgc; struct scsi_sense_hdr sshdr; int ret; - pkt_dbg(2, pd, "Performing OPC\n"); + dev_dbg(ddev, "Performing OPC\n"); init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE); cgc.sshdr = &sshdr; @@ -2058,18 +2061,19 @@ static noinline_for_stack int pkt_perform_opc(struct pktcdvd_device *pd) static int pkt_open_write(struct pktcdvd_device *pd) { + struct device *ddev = disk_to_dev(pd->disk); int ret; unsigned int write_speed, media_write_speed, read_speed; ret = pkt_probe_settings(pd); if (ret) { - pkt_dbg(2, pd, "failed probe\n"); + dev_dbg(ddev, "failed probe\n"); return ret; } ret = pkt_set_write_settings(pd); if (ret) { - pkt_dbg(1, pd, "failed saving write settings\n"); + dev_notice(ddev, "failed saving write settings\n"); return -EIO; } @@ -2082,30 +2086,29 @@ static int pkt_open_write(struct pktcdvd_device *pd) case 0x13: /* DVD-RW */ case 0x1a: /* DVD+RW */ case 0x12: /* DVD-RAM */ - pkt_dbg(1, pd, "write speed %ukB/s\n", write_speed); + dev_notice(ddev, "write speed %ukB/s\n", write_speed); break; default: ret = pkt_media_speed(pd, &media_write_speed); if (ret) media_write_speed = 16; write_speed = min(write_speed, media_write_speed * 177); - pkt_dbg(1, pd, "write speed %ux\n", write_speed / 176); + dev_notice(ddev, "write speed %ux\n", write_speed / 176); break; } read_speed = write_speed; ret = pkt_set_speed(pd, write_speed, read_speed); if (ret) { - pkt_dbg(1, pd, "couldn't set write speed\n"); + dev_notice(ddev, "couldn't set write speed\n"); return -EIO; } pd->write_speed = write_speed; pd->read_speed = read_speed; ret = pkt_perform_opc(pd); - if (ret) { - pkt_dbg(1, pd, "Optimum Power Calibration failed\n"); - } + if (ret) + dev_notice(ddev, "Optimum Power Calibration failed\n"); return 0; } @@ -2115,6 +2118,7 @@ static int pkt_open_write(struct pktcdvd_device *pd) */ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write) { + struct device *ddev = disk_to_dev(pd->disk); int ret; long lba; struct request_queue *q; @@ -2134,7 +2138,7 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write) ret = pkt_get_last_written(pd, &lba); if (ret) { - pkt_err(pd, "pkt_get_last_written failed\n"); + dev_err(ddev, "pkt_get_last_written failed\n"); goto out_putdev; } @@ -2163,11 +2167,11 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write) if (write) { if (!pkt_grow_pktlist(pd, CONFIG_CDROM_PKTCDVD_BUFFERS)) { - pkt_err(pd, "not enough memory for buffers\n"); + dev_err(ddev, "not enough memory for buffers\n"); ret = -ENOMEM; goto out_putdev; } - pkt_info(pd, "%lukB available on disc\n", lba << 1); + dev_info(ddev, "%lukB available on disc\n", lba << 1); } return 0; @@ -2184,8 +2188,10 @@ out: */ static void pkt_release_dev(struct pktcdvd_device *pd, int flush) { + struct device *ddev = disk_to_dev(pd->disk); + if (flush && pkt_flush_cache(pd)) - pkt_dbg(1, pd, "not flushing cache\n"); + dev_notice(ddev, "not flushing cache\n"); pkt_lock_door(pd, 0); @@ -2386,13 +2392,14 @@ static void pkt_make_request_write(struct request_queue *q, struct bio *bio) static void pkt_submit_bio(struct bio *bio) { struct pktcdvd_device *pd = bio->bi_bdev->bd_disk->queue->queuedata; + struct device *ddev = disk_to_dev(pd->disk); struct bio *split; bio = bio_split_to_limits(bio); if (!bio) return; - pkt_dbg(2, pd, "start = %6llx stop = %6llx\n", + dev_dbg(ddev, "start = %6llx stop = %6llx\n", (unsigned long long)bio->bi_iter.bi_sector, (unsigned long long)bio_end_sector(bio)); @@ -2405,13 +2412,13 @@ static void pkt_submit_bio(struct bio *bio) } if (!test_bit(PACKET_WRITABLE, &pd->flags)) { - pkt_notice(pd, "WRITE for ro device (%llu)\n", + dev_notice(ddev, "WRITE for ro device (%llu)\n", (unsigned long long)bio->bi_iter.bi_sector); goto end_io; } if (!bio->bi_iter.bi_size || (bio->bi_iter.bi_size % CD_FRAMESIZE)) { - pkt_err(pd, "wrong bio size\n"); + dev_err(ddev, "wrong bio size\n"); goto end_io; } @@ -2453,7 +2460,7 @@ static int pkt_seq_show(struct seq_file *m, void *p) char *msg; int states[PACKET_NUM_STATES]; - seq_printf(m, "Writer %s mapped to %pg:\n", pd->name, pd->bdev); + seq_printf(m, "Writer %s mapped to %pg:\n", pd->disk->disk_name, pd->bdev); seq_printf(m, "\nSettings:\n"); seq_printf(m, "\tpacket size:\t\t%dkB\n", pd->settings.size / 2); @@ -2509,12 +2516,13 @@ static int pkt_seq_show(struct seq_file *m, void *p) static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev) { + struct device *ddev = disk_to_dev(pd->disk); int i; struct block_device *bdev; struct scsi_device *sdev; if (pd->pkt_dev == dev) { - pkt_err(pd, "recursive setup not allowed\n"); + dev_err(ddev, "recursive setup not allowed\n"); return -EBUSY; } for (i = 0; i < MAX_WRITERS; i++) { @@ -2522,11 +2530,11 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev) if (!pd2) continue; if (pd2->bdev->bd_dev == dev) { - pkt_err(pd, "%pg already setup\n", pd2->bdev); + dev_err(ddev, "%pg already setup\n", pd2->bdev); return -EBUSY; } if (pd2->pkt_dev == dev) { - pkt_err(pd, "can't chain pktcdvd devices\n"); + dev_err(ddev, "can't chain pktcdvd devices\n"); return -EBUSY; } } @@ -2550,14 +2558,14 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev) pkt_init_queue(pd); atomic_set(&pd->cdrw.pending_bios, 0); - pd->cdrw.thread = kthread_run(kcdrwd, pd, "%s", pd->name); + pd->cdrw.thread = kthread_run(kcdrwd, pd, "%s", pd->disk->disk_name); if (IS_ERR(pd->cdrw.thread)) { - pkt_err(pd, "can't start kernel thread\n"); + dev_err(ddev, "can't start kernel thread\n"); goto out_mem; } - proc_create_single_data(pd->name, 0, pkt_proc, pkt_seq_show, pd); - pkt_dbg(1, pd, "writer mapped to %pg\n", bdev); + proc_create_single_data(pd->disk->disk_name, 0, pkt_proc, pkt_seq_show, pd); + dev_notice(ddev, "writer mapped to %pg\n", bdev); return 0; out_mem: @@ -2570,10 +2578,10 @@ out_mem: static int pkt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { struct pktcdvd_device *pd = bdev->bd_disk->private_data; + struct device *ddev = disk_to_dev(pd->disk); int ret; - pkt_dbg(2, pd, "cmd %x, dev %d:%d\n", - cmd, MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev)); + dev_dbg(ddev, "cmd %x, dev %d:%d\n", cmd, MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev)); mutex_lock(&pktcdvd_mutex); switch (cmd) { @@ -2599,7 +2607,7 @@ static int pkt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, ret = bdev->bd_disk->fops->ioctl(bdev, mode, cmd, arg); break; default: - pkt_dbg(2, pd, "Unknown ioctl (%x)\n", cmd); + dev_dbg(ddev, "Unknown ioctl (%x)\n", cmd); ret = -ENOTTY; } mutex_unlock(&pktcdvd_mutex); @@ -2677,7 +2685,6 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev) spin_lock_init(&pd->iosched.lock); bio_list_init(&pd->iosched.read_queue); bio_list_init(&pd->iosched.write_queue); - sprintf(pd->name, DRIVER_NAME"%d", idx); init_waitqueue_head(&pd->wqueue); pd->bio_queue = RB_ROOT; @@ -2694,7 +2701,7 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev) disk->minors = 1; disk->fops = &pktcdvd_ops; disk->flags = GENHD_FL_REMOVABLE | GENHD_FL_NO_PART; - strcpy(disk->disk_name, pd->name); + snprintf(disk->disk_name, sizeof(disk->disk_name), DRIVER_NAME"%d", idx); disk->private_data = pd; pd->pkt_dev = MKDEV(pktdev_major, idx); @@ -2736,6 +2743,7 @@ out_mutex: static int pkt_remove_dev(dev_t pkt_dev) { struct pktcdvd_device *pd; + struct device *ddev; int idx; int ret = 0; @@ -2756,6 +2764,9 @@ static int pkt_remove_dev(dev_t pkt_dev) ret = -EBUSY; goto out; } + + ddev = disk_to_dev(pd->disk); + if (!IS_ERR(pd->cdrw.thread)) kthread_stop(pd->cdrw.thread); @@ -2766,8 +2777,8 @@ static int pkt_remove_dev(dev_t pkt_dev) blkdev_put(pd->bdev, FMODE_READ | FMODE_NDELAY); - remove_proc_entry(pd->name, pkt_proc); - pkt_dbg(1, pd, "writer unmapped\n"); + remove_proc_entry(pd->disk->disk_name, pkt_proc); + dev_notice(ddev, "writer unmapped\n"); del_gendisk(pd->disk); put_disk(pd->disk); diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h index f9c5ac80d59b..80cb00db42a4 100644 --- a/include/linux/pktcdvd.h +++ b/include/linux/pktcdvd.h @@ -156,7 +156,6 @@ struct pktcdvd_device { struct block_device *bdev; /* dev attached */ dev_t pkt_dev; /* our dev */ - char name[20]; struct packet_settings settings; struct packet_stats stats; int refcnt; /* Open count */ diff --git a/include/uapi/linux/pktcdvd.h b/include/uapi/linux/pktcdvd.h index 6a5552dfd6af..987a3022dc5f 100644 --- a/include/uapi/linux/pktcdvd.h +++ b/include/uapi/linux/pktcdvd.h @@ -16,6 +16,7 @@ #include /* + * UNUSED: * 1 for normal debug messages, 2 is very verbose. 0 to turn it off. */ #define PACKET_DEBUG 1 -- cgit v1.2.3 From 92a3a9b1a3997cf67aca7874e7f61b102ea2f27c Mon Sep 17 00:00:00 2001 From: Dani Liberman Date: Thu, 20 Apr 2023 19:33:34 +0300 Subject: accel/habanalabs: add description to several info ioctls Several info ioctls may return success although no data retrieved. Signed-off-by: Dani Liberman Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- include/uapi/drm/habanalabs_accel.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/drm/habanalabs_accel.h b/include/uapi/drm/habanalabs_accel.h index d9ef1b151d04..e6436f3e8ea6 100644 --- a/include/uapi/drm/habanalabs_accel.h +++ b/include/uapi/drm/habanalabs_accel.h @@ -787,18 +787,28 @@ enum hl_server_type { * The address which accessing it caused the razwi. * Razwi initiator. * Razwi cause, was it a page fault or MMU access error. + * May return 0 even though no new data is available, in that case + * timestamp will be 0. * HL_INFO_DEV_MEM_ALLOC_PAGE_SIZES - Retrieve valid page sizes for device memory allocation * HL_INFO_SECURED_ATTESTATION - Retrieve attestation report of the boot. * HL_INFO_REGISTER_EVENTFD - Register eventfd for event notifications. * HL_INFO_UNREGISTER_EVENTFD - Unregister eventfd * HL_INFO_GET_EVENTS - Retrieve the last occurred events * HL_INFO_UNDEFINED_OPCODE_EVENT - Retrieve last undefined opcode error information. + * May return 0 even though no new data is available, in that case + * timestamp will be 0. * HL_INFO_ENGINE_STATUS - Retrieve the status of all the h/w engines in the asic. * HL_INFO_PAGE_FAULT_EVENT - Retrieve parameters of captured page fault. + * May return 0 even though no new data is available, in that case + * timestamp will be 0. * HL_INFO_USER_MAPPINGS - Retrieve user mappings, captured after page fault event. * HL_INFO_FW_GENERIC_REQ - Send generic request to FW. * HL_INFO_HW_ERR_EVENT - Retrieve information on the reported HW error. + * May return 0 even though no new data is available, in that case + * timestamp will be 0. * HL_INFO_FW_ERR_EVENT - Retrieve information on the reported FW error. + * May return 0 even though no new data is available, in that case + * timestamp will be 0. */ #define HL_INFO_HW_IP_INFO 0 #define HL_INFO_HW_EVENTS 1 -- cgit v1.2.3 From 489763af891d5dc35c0b64e18af284d6591286cf Mon Sep 17 00:00:00 2001 From: Pierre-Eric Pelloux-Prayer Date: Mon, 24 Apr 2023 19:25:32 +0200 Subject: drm/amdgpu: add new flag to AMDGPU_CTX_QUERY2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit OpenGL EXT_robustness extension expects the driver to stop reporting GUILTY_CONTEXT_RESET when the reset has completed and the GPU is ready to accept submission again. This commit adds a AMDGPU_CTX_QUERY2_FLAGS_RESET_IN_PROGRESS flag, that let the UMD know that the reset is still not finished. Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22290 Reviewed-by: Christian König Reviewed-by: André Almeida Signed-off-by: Pierre-Eric Pelloux-Prayer Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c | 3 +++ drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 3 ++- include/uapi/drm/amdgpu_drm.h | 2 ++ 3 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c index d2139ac12159..e1f642a3dc2f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -576,6 +576,9 @@ static int amdgpu_ctx_query2(struct amdgpu_device *adev, if (atomic_read(&ctx->guilty)) out->state.flags |= AMDGPU_CTX_QUERY2_FLAGS_GUILTY; + if (amdgpu_in_reset(adev)) + out->state.flags |= AMDGPU_CTX_QUERY2_FLAGS_RESET_IN_PROGRESS; + if (adev->ras_enabled && con) { /* Return the cached values in O(1), * and schedule delayed work to cache diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index b987022e11b4..45544ebe576e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -111,9 +111,10 @@ * tcp_cache_size, num_sqc_per_wgp, sqc_data_cache_size, sqc_inst_cache_size, * gl1c_cache_size, gl2c_cache_size, mall_size, enabled_rb_pipes_mask_hi * 3.53.0 - Support for GFX11 CP GFX shadowing + * 3.54.0 - Add AMDGPU_CTX_QUERY2_FLAGS_RESET_IN_PROGRESS support */ #define KMS_DRIVER_MAJOR 3 -#define KMS_DRIVER_MINOR 53 +#define KMS_DRIVER_MINOR 54 #define KMS_DRIVER_PATCHLEVEL 0 unsigned int amdgpu_vram_limit = UINT_MAX; diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index cc78528c3b4b..79b14828d542 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -245,6 +245,8 @@ union drm_amdgpu_bo_list { /* indicate some errors are detected by RAS */ #define AMDGPU_CTX_QUERY2_FLAGS_RAS_CE (1<<3) #define AMDGPU_CTX_QUERY2_FLAGS_RAS_UE (1<<4) +/* indicate that the reset hasn't completed yet */ +#define AMDGPU_CTX_QUERY2_FLAGS_RESET_IN_PROGRESS (1<<5) /* Context priority level */ #define AMDGPU_CTX_PRIORITY_UNSET -2048 -- cgit v1.2.3 From ef75a6ef37235e211bbdb17c25e5f79c55df1750 Mon Sep 17 00:00:00 2001 From: Rajneesh Bhardwaj Date: Thu, 3 Mar 2022 10:56:05 -0500 Subject: drm/amdkfd: Update coherence settings for svm ranges Recently introduced commit "drm/amdgpu: Set cache coherency for GC 9.4.3" did not update the settings applicable for svm ranges. Add the coherence settings for svm ranges for GFX IP 9.4.3. Reviewed-by: Amber Lin Signed-off-by: Rajneesh Bhardwaj Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 17 +++++++++++++++++ include/uapi/linux/kfd_ioctl.h | 2 ++ 2 files changed, 19 insertions(+) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 96ccff79902c..4b4f3bf8b823 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1159,6 +1159,7 @@ svm_range_get_pte_flags(struct amdgpu_device *adev, struct svm_range *prange, uint64_t pte_flags; bool snoop = (domain != SVM_RANGE_VRAM_DOMAIN); bool coherent = flags & KFD_IOCTL_SVM_FLAG_COHERENT; + bool uncached = flags & KFD_IOCTL_SVM_FLAG_UNCACHED; if (domain == SVM_RANGE_VRAM_DOMAIN) bo_adev = amdgpu_ttm_adev(prange->svm_bo->bo->tbo.bdev); @@ -1198,6 +1199,22 @@ svm_range_get_pte_flags(struct amdgpu_device *adev, struct svm_range *prange, AMDGPU_VM_MTYPE_UC : AMDGPU_VM_MTYPE_NC; } break; + case IP_VERSION(9, 4, 3): + //TODO: Need more work for handling multiple memory partitions + //e.g. NPS4. Current approch is only applicable without memory + //partitions. + snoop = true; + if (uncached) + mapping_flags |= AMDGPU_VM_MTYPE_UC; + /* local HBM region close to partition*/ + else if (bo_adev == adev) + mapping_flags |= AMDGPU_VM_MTYPE_RW; + /* local HBM region far from partition or remote XGMI GPU or + * system memory + */ + else + mapping_flags |= AMDGPU_VM_MTYPE_NC; + break; default: mapping_flags |= coherent ? AMDGPU_VM_MTYPE_UC : AMDGPU_VM_MTYPE_NC; diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 2da5c3ad71bd..2a9671e1ddb5 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -623,6 +623,8 @@ enum kfd_mmio_remap { #define KFD_IOCTL_SVM_FLAG_GPU_READ_MOSTLY 0x00000020 /* Keep GPU memory mapping always valid as if XNACK is disable */ #define KFD_IOCTL_SVM_FLAG_GPU_ALWAYS_MAPPED 0x00000040 +/* Uncached access to memory */ +#define KFD_IOCTL_SVM_FLAG_UNCACHED 0x00000080 /** * kfd_ioctl_svm_op - SVM ioctl operations -- cgit v1.2.3 From ba3c87fffb79311f54464288c66421d19c2c1234 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Fri, 2 Jun 2023 12:58:05 -0400 Subject: amd/amdkfd: drop unused KFD_IOCTL_SVM_FLAG_UNCACHED flag Was leftover from GC 9.4.3 bring up and is currently unused. Drop it for now. Cc: Philip.Yang@amd.com Cc: rajneesh.bhardwaj@amd.com Cc: Felix.Kuehling@amd.com Reviewed-by: Rajneesh Bhardwaj Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 2 +- include/uapi/linux/kfd_ioctl.h | 2 -- 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 615eab3f78c9..5ff1a5a89d96 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1154,7 +1154,7 @@ svm_range_get_pte_flags(struct kfd_node *node, uint64_t pte_flags; bool snoop = (domain != SVM_RANGE_VRAM_DOMAIN); bool coherent = flags & KFD_IOCTL_SVM_FLAG_COHERENT; - bool uncached = flags & KFD_IOCTL_SVM_FLAG_UNCACHED; + bool uncached = false; /*flags & KFD_IOCTL_SVM_FLAG_UNCACHED;*/ unsigned int mtype_local; if (domain == SVM_RANGE_VRAM_DOMAIN) diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 2a9671e1ddb5..2da5c3ad71bd 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -623,8 +623,6 @@ enum kfd_mmio_remap { #define KFD_IOCTL_SVM_FLAG_GPU_READ_MOSTLY 0x00000020 /* Keep GPU memory mapping always valid as if XNACK is disable */ #define KFD_IOCTL_SVM_FLAG_GPU_ALWAYS_MAPPED 0x00000040 -/* Uncached access to memory */ -#define KFD_IOCTL_SVM_FLAG_UNCACHED 0x00000080 /** * kfd_ioctl_svm_op - SVM ioctl operations -- cgit v1.2.3 From 4f98cf2baf9faee5b6f2f7889dad7c0f7686a787 Mon Sep 17 00:00:00 2001 From: Jonathan Kim Date: Wed, 2 Mar 2022 14:30:12 -0500 Subject: drm/amdkfd: add debug and runtime enable interface Introduce the GPU debug operations interface. For ROCm-GDB to extend the GNU Debugger's ability to inspect the AMD GPU instruction set, provide the necessary interface to allow the debugger to HW debug-mode set and query exceptions per HSA queue, process or device. The runtime_enable interface coordinates exception handling with the HSA runtime. Usage is available in the kern docs at uapi/linux/kfd_ioctl.h. Signed-off-by: Jonathan Kim Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 48 +++ include/uapi/linux/kfd_ioctl.h | 668 ++++++++++++++++++++++++++++++- 2 files changed, 715 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index a9efff94390b..00e34125987c 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -2729,6 +2729,48 @@ static int kfd_ioctl_criu(struct file *filep, struct kfd_process *p, void *data) return ret; } +static int kfd_ioctl_runtime_enable(struct file *filep, struct kfd_process *p, void *data) +{ + return 0; +} + +static int kfd_ioctl_set_debug_trap(struct file *filep, struct kfd_process *p, void *data) +{ + struct kfd_ioctl_dbg_trap_args *args = data; + int r = 0; + + if (sched_policy == KFD_SCHED_POLICY_NO_HWS) { + pr_err("Debugging does not support sched_policy %i", sched_policy); + return -EINVAL; + } + + switch (args->op) { + case KFD_IOC_DBG_TRAP_ENABLE: + case KFD_IOC_DBG_TRAP_DISABLE: + case KFD_IOC_DBG_TRAP_SEND_RUNTIME_EVENT: + case KFD_IOC_DBG_TRAP_SET_EXCEPTIONS_ENABLED: + case KFD_IOC_DBG_TRAP_SET_WAVE_LAUNCH_OVERRIDE: + case KFD_IOC_DBG_TRAP_SET_WAVE_LAUNCH_MODE: + case KFD_IOC_DBG_TRAP_SUSPEND_QUEUES: + case KFD_IOC_DBG_TRAP_RESUME_QUEUES: + case KFD_IOC_DBG_TRAP_SET_NODE_ADDRESS_WATCH: + case KFD_IOC_DBG_TRAP_CLEAR_NODE_ADDRESS_WATCH: + case KFD_IOC_DBG_TRAP_SET_FLAGS: + case KFD_IOC_DBG_TRAP_QUERY_DEBUG_EVENT: + case KFD_IOC_DBG_TRAP_QUERY_EXCEPTION_INFO: + case KFD_IOC_DBG_TRAP_GET_QUEUE_SNAPSHOT: + case KFD_IOC_DBG_TRAP_GET_DEVICE_SNAPSHOT: + pr_warn("Debugging not supported yet\n"); + r = -EACCES; + break; + default: + pr_err("Invalid option: %i\n", args->op); + r = -EINVAL; + } + + return r; +} + #define AMDKFD_IOCTL_DEF(ioctl, _func, _flags) \ [_IOC_NR(ioctl)] = {.cmd = ioctl, .func = _func, .flags = _flags, \ .cmd_drv = 0, .name = #ioctl} @@ -2841,6 +2883,12 @@ static const struct amdkfd_ioctl_desc amdkfd_ioctls[] = { AMDKFD_IOCTL_DEF(AMDKFD_IOC_EXPORT_DMABUF, kfd_ioctl_export_dmabuf, 0), + + AMDKFD_IOCTL_DEF(AMDKFD_IOC_RUNTIME_ENABLE, + kfd_ioctl_runtime_enable, 0), + + AMDKFD_IOCTL_DEF(AMDKFD_IOC_DBG_TRAP, + kfd_ioctl_set_debug_trap, 0), }; #define AMDKFD_CORE_IOCTL_COUNT ARRAY_SIZE(amdkfd_ioctls) diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 2da5c3ad71bd..32913d674d38 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -110,6 +110,32 @@ struct kfd_ioctl_get_available_memory_args { __u32 pad; }; +struct kfd_dbg_device_info_entry { + __u64 exception_status; + __u64 lds_base; + __u64 lds_limit; + __u64 scratch_base; + __u64 scratch_limit; + __u64 gpuvm_base; + __u64 gpuvm_limit; + __u32 gpu_id; + __u32 location_id; + __u32 vendor_id; + __u32 device_id; + __u32 revision_id; + __u32 subsystem_vendor_id; + __u32 subsystem_device_id; + __u32 fw_version; + __u32 gfx_target_version; + __u32 simd_count; + __u32 max_waves_per_simd; + __u32 array_count; + __u32 simd_arrays_per_engine; + __u32 num_xcc; + __u32 capability; + __u32 debug_prop; +}; + /* For kfd_ioctl_set_memory_policy_args.default_policy and alternate_policy */ #define KFD_IOC_CACHE_POLICY_COHERENT 0 #define KFD_IOC_CACHE_POLICY_NONCOHERENT 1 @@ -773,6 +799,640 @@ struct kfd_ioctl_set_xnack_mode_args { __s32 xnack_enabled; }; +/* Wave launch override modes */ +enum kfd_dbg_trap_override_mode { + KFD_DBG_TRAP_OVERRIDE_OR = 0, + KFD_DBG_TRAP_OVERRIDE_REPLACE = 1 +}; + +/* Wave launch overrides */ +enum kfd_dbg_trap_mask { + KFD_DBG_TRAP_MASK_FP_INVALID = 1, + KFD_DBG_TRAP_MASK_FP_INPUT_DENORMAL = 2, + KFD_DBG_TRAP_MASK_FP_DIVIDE_BY_ZERO = 4, + KFD_DBG_TRAP_MASK_FP_OVERFLOW = 8, + KFD_DBG_TRAP_MASK_FP_UNDERFLOW = 16, + KFD_DBG_TRAP_MASK_FP_INEXACT = 32, + KFD_DBG_TRAP_MASK_INT_DIVIDE_BY_ZERO = 64, + KFD_DBG_TRAP_MASK_DBG_ADDRESS_WATCH = 128, + KFD_DBG_TRAP_MASK_DBG_MEMORY_VIOLATION = 256, + KFD_DBG_TRAP_MASK_TRAP_ON_WAVE_START = (1 << 30), + KFD_DBG_TRAP_MASK_TRAP_ON_WAVE_END = (1 << 31) +}; + +/* Wave launch modes */ +enum kfd_dbg_trap_wave_launch_mode { + KFD_DBG_TRAP_WAVE_LAUNCH_MODE_NORMAL = 0, + KFD_DBG_TRAP_WAVE_LAUNCH_MODE_HALT = 1, + KFD_DBG_TRAP_WAVE_LAUNCH_MODE_DEBUG = 3 +}; + +/* Address watch modes */ +enum kfd_dbg_trap_address_watch_mode { + KFD_DBG_TRAP_ADDRESS_WATCH_MODE_READ = 0, + KFD_DBG_TRAP_ADDRESS_WATCH_MODE_NONREAD = 1, + KFD_DBG_TRAP_ADDRESS_WATCH_MODE_ATOMIC = 2, + KFD_DBG_TRAP_ADDRESS_WATCH_MODE_ALL = 3 +}; + +/* Additional wave settings */ +enum kfd_dbg_trap_flags { + KFD_DBG_TRAP_FLAG_SINGLE_MEM_OP = 1, +}; + +/* Trap exceptions */ +enum kfd_dbg_trap_exception_code { + EC_NONE = 0, + /* per queue */ + EC_QUEUE_WAVE_ABORT = 1, + EC_QUEUE_WAVE_TRAP = 2, + EC_QUEUE_WAVE_MATH_ERROR = 3, + EC_QUEUE_WAVE_ILLEGAL_INSTRUCTION = 4, + EC_QUEUE_WAVE_MEMORY_VIOLATION = 5, + EC_QUEUE_WAVE_APERTURE_VIOLATION = 6, + EC_QUEUE_PACKET_DISPATCH_DIM_INVALID = 16, + EC_QUEUE_PACKET_DISPATCH_GROUP_SEGMENT_SIZE_INVALID = 17, + EC_QUEUE_PACKET_DISPATCH_CODE_INVALID = 18, + EC_QUEUE_PACKET_RESERVED = 19, + EC_QUEUE_PACKET_UNSUPPORTED = 20, + EC_QUEUE_PACKET_DISPATCH_WORK_GROUP_SIZE_INVALID = 21, + EC_QUEUE_PACKET_DISPATCH_REGISTER_INVALID = 22, + EC_QUEUE_PACKET_VENDOR_UNSUPPORTED = 23, + EC_QUEUE_PREEMPTION_ERROR = 30, + EC_QUEUE_NEW = 31, + /* per device */ + EC_DEVICE_QUEUE_DELETE = 32, + EC_DEVICE_MEMORY_VIOLATION = 33, + EC_DEVICE_RAS_ERROR = 34, + EC_DEVICE_FATAL_HALT = 35, + EC_DEVICE_NEW = 36, + /* per process */ + EC_PROCESS_RUNTIME = 48, + EC_PROCESS_DEVICE_REMOVE = 49, + EC_MAX +}; + +/* Mask generated by ecode in kfd_dbg_trap_exception_code */ +#define KFD_EC_MASK(ecode) (1ULL << (ecode - 1)) + +/* Masks for exception code type checks below */ +#define KFD_EC_MASK_QUEUE (KFD_EC_MASK(EC_QUEUE_WAVE_ABORT) | \ + KFD_EC_MASK(EC_QUEUE_WAVE_TRAP) | \ + KFD_EC_MASK(EC_QUEUE_WAVE_MATH_ERROR) | \ + KFD_EC_MASK(EC_QUEUE_WAVE_ILLEGAL_INSTRUCTION) | \ + KFD_EC_MASK(EC_QUEUE_WAVE_MEMORY_VIOLATION) | \ + KFD_EC_MASK(EC_QUEUE_WAVE_APERTURE_VIOLATION) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_DIM_INVALID) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_GROUP_SEGMENT_SIZE_INVALID) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_CODE_INVALID) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_RESERVED) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_UNSUPPORTED) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_WORK_GROUP_SIZE_INVALID) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_REGISTER_INVALID) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_VENDOR_UNSUPPORTED) | \ + KFD_EC_MASK(EC_QUEUE_PREEMPTION_ERROR) | \ + KFD_EC_MASK(EC_QUEUE_NEW)) +#define KFD_EC_MASK_DEVICE (KFD_EC_MASK(EC_DEVICE_QUEUE_DELETE) | \ + KFD_EC_MASK(EC_DEVICE_RAS_ERROR) | \ + KFD_EC_MASK(EC_DEVICE_FATAL_HALT) | \ + KFD_EC_MASK(EC_DEVICE_MEMORY_VIOLATION) | \ + KFD_EC_MASK(EC_DEVICE_NEW)) +#define KFD_EC_MASK_PROCESS (KFD_EC_MASK(EC_PROCESS_RUNTIME) | \ + KFD_EC_MASK(EC_PROCESS_DEVICE_REMOVE)) + +/* Checks for exception code types for KFD search */ +#define KFD_DBG_EC_TYPE_IS_QUEUE(ecode) \ + (!!(KFD_EC_MASK(ecode) & KFD_EC_MASK_QUEUE)) +#define KFD_DBG_EC_TYPE_IS_DEVICE(ecode) \ + (!!(KFD_EC_MASK(ecode) & KFD_EC_MASK_DEVICE)) +#define KFD_DBG_EC_TYPE_IS_PROCESS(ecode) \ + (!!(KFD_EC_MASK(ecode) & KFD_EC_MASK_PROCESS)) + + +/* Runtime enable states */ +enum kfd_dbg_runtime_state { + DEBUG_RUNTIME_STATE_DISABLED = 0, + DEBUG_RUNTIME_STATE_ENABLED = 1, + DEBUG_RUNTIME_STATE_ENABLED_BUSY = 2, + DEBUG_RUNTIME_STATE_ENABLED_ERROR = 3 +}; + +/* Runtime enable status */ +struct kfd_runtime_info { + __u64 r_debug; + __u32 runtime_state; + __u32 ttmp_setup; +}; + +/* Enable modes for runtime enable */ +#define KFD_RUNTIME_ENABLE_MODE_ENABLE_MASK 1 +#define KFD_RUNTIME_ENABLE_MODE_TTMP_SAVE_MASK 2 + +/** + * kfd_ioctl_runtime_enable_args - Arguments for runtime enable + * + * Coordinates debug exception signalling and debug device enablement with runtime. + * + * @r_debug - pointer to user struct for sharing information between ROCr and the debuggger + * @mode_mask - mask to set mode + * KFD_RUNTIME_ENABLE_MODE_ENABLE_MASK - enable runtime for debugging, otherwise disable + * KFD_RUNTIME_ENABLE_MODE_TTMP_SAVE_MASK - enable trap temporary setup (ignore on disable) + * @capabilities_mask - mask to notify runtime on what KFD supports + * + * Return - 0 on SUCCESS. + * - EBUSY if runtime enable call already pending. + * - EEXIST if user queues already active prior to call. + * If process is debug enabled, runtime enable will enable debug devices and + * wait for debugger process to send runtime exception EC_PROCESS_RUNTIME + * to unblock - see kfd_ioctl_dbg_trap_args. + * + */ +struct kfd_ioctl_runtime_enable_args { + __u64 r_debug; + __u32 mode_mask; + __u32 capabilities_mask; +}; + +/* Queue information */ +struct kfd_queue_snapshot_entry { + __u64 exception_status; + __u64 ring_base_address; + __u64 write_pointer_address; + __u64 read_pointer_address; + __u64 ctx_save_restore_address; + __u32 queue_id; + __u32 gpu_id; + __u32 ring_size; + __u32 queue_type; + __u32 ctx_save_restore_area_size; + __u32 reserved; +}; + +/* Queue status return for suspend/resume */ +#define KFD_DBG_QUEUE_ERROR_BIT 30 +#define KFD_DBG_QUEUE_INVALID_BIT 31 +#define KFD_DBG_QUEUE_ERROR_MASK (1 << KFD_DBG_QUEUE_ERROR_BIT) +#define KFD_DBG_QUEUE_INVALID_MASK (1 << KFD_DBG_QUEUE_INVALID_BIT) + +/* Context save area header information */ +struct kfd_context_save_area_header { + struct { + __u32 control_stack_offset; + __u32 control_stack_size; + __u32 wave_state_offset; + __u32 wave_state_size; + } wave_state; + __u32 debug_offset; + __u32 debug_size; + __u64 err_payload_addr; + __u32 err_event_id; + __u32 reserved1; +}; + +/* + * Debug operations + * + * For specifics on usage and return values, see documentation per operation + * below. Otherwise, generic error returns apply: + * - ESRCH if the process to debug does not exist. + * + * - EINVAL (with KFD_IOC_DBG_TRAP_ENABLE exempt) if operation + * KFD_IOC_DBG_TRAP_ENABLE has not succeeded prior. + * Also returns this error if GPU hardware scheduling is not supported. + * + * - EPERM (with KFD_IOC_DBG_TRAP_DISABLE exempt) if target process is not + * PTRACE_ATTACHED. KFD_IOC_DBG_TRAP_DISABLE is exempt to allow + * clean up of debug mode as long as process is debug enabled. + * + * - EACCES if any DBG_HW_OP (debug hardware operation) is requested when + * AMDKFD_IOC_RUNTIME_ENABLE has not succeeded prior. + * + * - ENODEV if any GPU does not support debugging on a DBG_HW_OP call. + * + * - Other errors may be returned when a DBG_HW_OP occurs while the GPU + * is in a fatal state. + * + */ +enum kfd_dbg_trap_operations { + KFD_IOC_DBG_TRAP_ENABLE = 0, + KFD_IOC_DBG_TRAP_DISABLE = 1, + KFD_IOC_DBG_TRAP_SEND_RUNTIME_EVENT = 2, + KFD_IOC_DBG_TRAP_SET_EXCEPTIONS_ENABLED = 3, + KFD_IOC_DBG_TRAP_SET_WAVE_LAUNCH_OVERRIDE = 4, /* DBG_HW_OP */ + KFD_IOC_DBG_TRAP_SET_WAVE_LAUNCH_MODE = 5, /* DBG_HW_OP */ + KFD_IOC_DBG_TRAP_SUSPEND_QUEUES = 6, /* DBG_HW_OP */ + KFD_IOC_DBG_TRAP_RESUME_QUEUES = 7, /* DBG_HW_OP */ + KFD_IOC_DBG_TRAP_SET_NODE_ADDRESS_WATCH = 8, /* DBG_HW_OP */ + KFD_IOC_DBG_TRAP_CLEAR_NODE_ADDRESS_WATCH = 9, /* DBG_HW_OP */ + KFD_IOC_DBG_TRAP_SET_FLAGS = 10, + KFD_IOC_DBG_TRAP_QUERY_DEBUG_EVENT = 11, + KFD_IOC_DBG_TRAP_QUERY_EXCEPTION_INFO = 12, + KFD_IOC_DBG_TRAP_GET_QUEUE_SNAPSHOT = 13, + KFD_IOC_DBG_TRAP_GET_DEVICE_SNAPSHOT = 14 +}; + +/** + * kfd_ioctl_dbg_trap_enable_args + * + * Arguments for KFD_IOC_DBG_TRAP_ENABLE. + * + * Enables debug session for target process. Call @op KFD_IOC_DBG_TRAP_DISABLE in + * kfd_ioctl_dbg_trap_args to disable debug session. + * + * @exception_mask (IN) - exceptions to raise to the debugger + * @rinfo_ptr (IN) - pointer to runtime info buffer (see kfd_runtime_info) + * @rinfo_size (IN/OUT) - size of runtime info buffer in bytes + * @dbg_fd (IN) - fd the KFD will nofify the debugger with of raised + * exceptions set in exception_mask. + * + * Generic errors apply (see kfd_dbg_trap_operations). + * Return - 0 on SUCCESS. + * Copies KFD saved kfd_runtime_info to @rinfo_ptr on enable. + * Size of kfd_runtime saved by the KFD returned to @rinfo_size. + * - EBADF if KFD cannot get a reference to dbg_fd. + * - EFAULT if KFD cannot copy runtime info to rinfo_ptr. + * - EINVAL if target process is already debug enabled. + * + */ +struct kfd_ioctl_dbg_trap_enable_args { + __u64 exception_mask; + __u64 rinfo_ptr; + __u32 rinfo_size; + __u32 dbg_fd; +}; + +/** + * kfd_ioctl_dbg_trap_send_runtime_event_args + * + * + * Arguments for KFD_IOC_DBG_TRAP_SEND_RUNTIME_EVENT. + * Raises exceptions to runtime. + * + * @exception_mask (IN) - exceptions to raise to runtime + * @gpu_id (IN) - target device id + * @queue_id (IN) - target queue id + * + * Generic errors apply (see kfd_dbg_trap_operations). + * Return - 0 on SUCCESS. + * - ENODEV if gpu_id not found. + * If exception_mask contains EC_PROCESS_RUNTIME, unblocks pending + * AMDKFD_IOC_RUNTIME_ENABLE call - see kfd_ioctl_runtime_enable_args. + * All other exceptions are raised to runtime through err_payload_addr. + * See kfd_context_save_area_header. + */ +struct kfd_ioctl_dbg_trap_send_runtime_event_args { + __u64 exception_mask; + __u32 gpu_id; + __u32 queue_id; +}; + +/** + * kfd_ioctl_dbg_trap_set_exceptions_enabled_args + * + * Arguments for KFD_IOC_SET_EXCEPTIONS_ENABLED + * Set new exceptions to be raised to the debugger. + * + * @exception_mask (IN) - new exceptions to raise the debugger + * + * Generic errors apply (see kfd_dbg_trap_operations). + * Return - 0 on SUCCESS. + */ +struct kfd_ioctl_dbg_trap_set_exceptions_enabled_args { + __u64 exception_mask; +}; + +/** + * kfd_ioctl_dbg_trap_set_wave_launch_override_args + * + * Arguments for KFD_IOC_DBG_TRAP_SET_WAVE_LAUNCH_OVERRIDE + * Enable HW exceptions to raise trap. + * + * @override_mode (IN) - see kfd_dbg_trap_override_mode + * @enable_mask (IN/OUT) - reference kfd_dbg_trap_mask. + * IN is the override modes requested to be enabled. + * OUT is referenced in Return below. + * @support_request_mask (IN/OUT) - reference kfd_dbg_trap_mask. + * IN is the override modes requested for support check. + * OUT is referenced in Return below. + * + * Generic errors apply (see kfd_dbg_trap_operations). + * Return - 0 on SUCCESS. + * Previous enablement is returned in @enable_mask. + * Actual override support is returned in @support_request_mask. + * - EINVAL if override mode is not supported. + * - EACCES if trap support requested is not actually supported. + * i.e. enable_mask (IN) is not a subset of support_request_mask (OUT). + * Otherwise it is considered a generic error (see kfd_dbg_trap_operations). + */ +struct kfd_ioctl_dbg_trap_set_wave_launch_override_args { + __u32 override_mode; + __u32 enable_mask; + __u32 support_request_mask; + __u32 pad; +}; + +/** + * kfd_ioctl_dbg_trap_set_wave_launch_mode_args + * + * Arguments for KFD_IOC_DBG_TRAP_SET_WAVE_LAUNCH_MODE + * Set wave launch mode. + * + * @mode (IN) - see kfd_dbg_trap_wave_launch_mode + * + * Generic errors apply (see kfd_dbg_trap_operations). + * Return - 0 on SUCCESS. + */ +struct kfd_ioctl_dbg_trap_set_wave_launch_mode_args { + __u32 launch_mode; + __u32 pad; +}; + +/** + * kfd_ioctl_dbg_trap_suspend_queues_ags + * + * Arguments for KFD_IOC_DBG_TRAP_SUSPEND_QUEUES + * Suspend queues. + * + * @exception_mask (IN) - raised exceptions to clear + * @queue_array_ptr (IN) - pointer to array of queue ids (u32 per queue id) + * to suspend + * @num_queues (IN) - number of queues to suspend in @queue_array_ptr + * @grace_period (IN) - wave time allowance before preemption + * per 1K GPU clock cycle unit + * + * Generic errors apply (see kfd_dbg_trap_operations). + * Destruction of a suspended queue is blocked until the queue is + * resumed. This allows the debugger to access queue information and + * the its context save area without running into a race condition on + * queue destruction. + * Automatically copies per queue context save area header information + * into the save area base + * (see kfd_queue_snapshot_entry and kfd_context_save_area_header). + * + * Return - Number of queues suspended on SUCCESS. + * . KFD_DBG_QUEUE_ERROR_MASK and KFD_DBG_QUEUE_INVALID_MASK masked + * for each queue id in @queue_array_ptr array reports unsuccessful + * suspend reason. + * KFD_DBG_QUEUE_ERROR_MASK = HW failure. + * KFD_DBG_QUEUE_INVALID_MASK = queue does not exist, is new or + * is being destroyed. + */ +struct kfd_ioctl_dbg_trap_suspend_queues_args { + __u64 exception_mask; + __u64 queue_array_ptr; + __u32 num_queues; + __u32 grace_period; +}; + +/** + * kfd_ioctl_dbg_trap_resume_queues_args + * + * Arguments for KFD_IOC_DBG_TRAP_RESUME_QUEUES + * Resume queues. + * + * @queue_array_ptr (IN) - pointer to array of queue ids (u32 per queue id) + * to resume + * @num_queues (IN) - number of queues to resume in @queue_array_ptr + * + * Generic errors apply (see kfd_dbg_trap_operations). + * Return - Number of queues resumed on SUCCESS. + * KFD_DBG_QUEUE_ERROR_MASK and KFD_DBG_QUEUE_INVALID_MASK mask + * for each queue id in @queue_array_ptr array reports unsuccessful + * resume reason. + * KFD_DBG_QUEUE_ERROR_MASK = HW failure. + * KFD_DBG_QUEUE_INVALID_MASK = queue does not exist. + */ +struct kfd_ioctl_dbg_trap_resume_queues_args { + __u64 queue_array_ptr; + __u32 num_queues; + __u32 pad; +}; + +/** + * kfd_ioctl_dbg_trap_set_node_address_watch_args + * + * Arguments for KFD_IOC_DBG_TRAP_SET_NODE_ADDRESS_WATCH + * Sets address watch for device. + * + * @address (IN) - watch address to set + * @mode (IN) - see kfd_dbg_trap_address_watch_mode + * @mask (IN) - watch address mask + * @gpu_id (IN) - target gpu to set watch point + * @id (OUT) - watch id allocated + * + * Generic errors apply (see kfd_dbg_trap_operations). + * Return - 0 on SUCCESS. + * Allocated watch ID returned to @id. + * - ENODEV if gpu_id not found. + * - ENOMEM if watch IDs can be allocated + */ +struct kfd_ioctl_dbg_trap_set_node_address_watch_args { + __u64 address; + __u32 mode; + __u32 mask; + __u32 gpu_id; + __u32 id; +}; + +/** + * kfd_ioctl_dbg_trap_clear_node_address_watch_args + * + * Arguments for KFD_IOC_DBG_TRAP_CLEAR_NODE_ADDRESS_WATCH + * Clear address watch for device. + * + * @gpu_id (IN) - target device to clear watch point + * @id (IN) - allocated watch id to clear + * + * Generic errors apply (see kfd_dbg_trap_operations). + * Return - 0 on SUCCESS. + * - ENODEV if gpu_id not found. + * - EINVAL if watch ID has not been allocated. + */ +struct kfd_ioctl_dbg_trap_clear_node_address_watch_args { + __u32 gpu_id; + __u32 id; +}; + +/** + * kfd_ioctl_dbg_trap_set_flags_args + * + * Arguments for KFD_IOC_DBG_TRAP_SET_FLAGS + * Sets flags for wave behaviour. + * + * @flags (IN/OUT) - IN = flags to enable, OUT = flags previously enabled + * + * Generic errors apply (see kfd_dbg_trap_operations). + * Return - 0 on SUCCESS. + * - EACCESS if any debug device does not allow flag options. + */ +struct kfd_ioctl_dbg_trap_set_flags_args { + __u32 flags; + __u32 pad; +}; + +/** + * kfd_ioctl_dbg_trap_query_debug_event_args + * + * Arguments for KFD_IOC_DBG_TRAP_QUERY_DEBUG_EVENT + * + * Find one or more raised exceptions. This function can return multiple + * exceptions from a single queue or a single device with one call. To find + * all raised exceptions, this function must be called repeatedly until it + * returns -EAGAIN. Returned exceptions can optionally be cleared by + * setting the corresponding bit in the @exception_mask input parameter. + * However, clearing an exception prevents retrieving further information + * about it with KFD_IOC_DBG_TRAP_QUERY_EXCEPTION_INFO. + * + * @exception_mask (IN/OUT) - exception to clear (IN) and raised (OUT) + * @gpu_id (OUT) - gpu id of exceptions raised + * @queue_id (OUT) - queue id of exceptions raised + * + * Generic errors apply (see kfd_dbg_trap_operations). + * Return - 0 on raised exception found + * Raised exceptions found are returned in @exception mask + * with reported source id returned in @gpu_id or @queue_id. + * - EAGAIN if no raised exception has been found + */ +struct kfd_ioctl_dbg_trap_query_debug_event_args { + __u64 exception_mask; + __u32 gpu_id; + __u32 queue_id; +}; + +/** + * kfd_ioctl_dbg_trap_query_exception_info_args + * + * Arguments KFD_IOC_DBG_TRAP_QUERY_EXCEPTION_INFO + * Get additional info on raised exception. + * + * @info_ptr (IN) - pointer to exception info buffer to copy to + * @info_size (IN/OUT) - exception info buffer size (bytes) + * @source_id (IN) - target gpu or queue id + * @exception_code (IN) - target exception + * @clear_exception (IN) - clear raised @exception_code exception + * (0 = false, 1 = true) + * + * Generic errors apply (see kfd_dbg_trap_operations). + * Return - 0 on SUCCESS. + * If @exception_code is EC_DEVICE_MEMORY_VIOLATION, copy @info_size(OUT) + * bytes of memory exception data to @info_ptr. + * If @exception_code is EC_PROCESS_RUNTIME, copy saved + * kfd_runtime_info to @info_ptr. + * Actual required @info_ptr size (bytes) is returned in @info_size. + */ +struct kfd_ioctl_dbg_trap_query_exception_info_args { + __u64 info_ptr; + __u32 info_size; + __u32 source_id; + __u32 exception_code; + __u32 clear_exception; +}; + +/** + * kfd_ioctl_dbg_trap_get_queue_snapshot_args + * + * Arguments KFD_IOC_DBG_TRAP_GET_QUEUE_SNAPSHOT + * Get queue information. + * + * @exception_mask (IN) - exceptions raised to clear + * @snapshot_buf_ptr (IN) - queue snapshot entry buffer (see kfd_queue_snapshot_entry) + * @num_queues (IN/OUT) - number of queue snapshot entries + * The debugger specifies the size of the array allocated in @num_queues. + * KFD returns the number of queues that actually existed. If this is + * larger than the size specified by the debugger, KFD will not overflow + * the array allocated by the debugger. + * + * @entry_size (IN/OUT) - size per entry in bytes + * The debugger specifies sizeof(struct kfd_queue_snapshot_entry) in + * @entry_size. KFD returns the number of bytes actually populated per + * entry. The debugger should use the KFD_IOCTL_MINOR_VERSION to determine, + * which fields in struct kfd_queue_snapshot_entry are valid. This allows + * growing the ABI in a backwards compatible manner. + * Note that entry_size(IN) should still be used to stride the snapshot buffer in the + * event that it's larger than actual kfd_queue_snapshot_entry. + * + * Generic errors apply (see kfd_dbg_trap_operations). + * Return - 0 on SUCCESS. + * Copies @num_queues(IN) queue snapshot entries of size @entry_size(IN) + * into @snapshot_buf_ptr if @num_queues(IN) > 0. + * Otherwise return @num_queues(OUT) queue snapshot entries that exist. + */ +struct kfd_ioctl_dbg_trap_queue_snapshot_args { + __u64 exception_mask; + __u64 snapshot_buf_ptr; + __u32 num_queues; + __u32 entry_size; +}; + +/** + * kfd_ioctl_dbg_trap_get_device_snapshot_args + * + * Arguments for KFD_IOC_DBG_TRAP_GET_DEVICE_SNAPSHOT + * Get device information. + * + * @exception_mask (IN) - exceptions raised to clear + * @snapshot_buf_ptr (IN) - pointer to snapshot buffer (see kfd_dbg_device_info_entry) + * @num_devices (IN/OUT) - number of debug devices to snapshot + * The debugger specifies the size of the array allocated in @num_devices. + * KFD returns the number of devices that actually existed. If this is + * larger than the size specified by the debugger, KFD will not overflow + * the array allocated by the debugger. + * + * @entry_size (IN/OUT) - size per entry in bytes + * The debugger specifies sizeof(struct kfd_dbg_device_info_entry) in + * @entry_size. KFD returns the number of bytes actually populated. The + * debugger should use KFD_IOCTL_MINOR_VERSION to determine, which fields + * in struct kfd_dbg_device_info_entry are valid. This allows growing the + * ABI in a backwards compatible manner. + * Note that entry_size(IN) should still be used to stride the snapshot buffer in the + * event that it's larger than actual kfd_dbg_device_info_entry. + * + * Generic errors apply (see kfd_dbg_trap_operations). + * Return - 0 on SUCCESS. + * Copies @num_devices(IN) device snapshot entries of size @entry_size(IN) + * into @snapshot_buf_ptr if @num_devices(IN) > 0. + * Otherwise return @num_devices(OUT) queue snapshot entries that exist. + */ +struct kfd_ioctl_dbg_trap_device_snapshot_args { + __u64 exception_mask; + __u64 snapshot_buf_ptr; + __u32 num_devices; + __u32 entry_size; +}; + +/** + * kfd_ioctl_dbg_trap_args + * + * Arguments to debug target process. + * + * @pid - target process to debug + * @op - debug operation (see kfd_dbg_trap_operations) + * + * @op determines which union struct args to use. + * Refer to kern docs for each kfd_ioctl_dbg_trap_*_args struct. + */ +struct kfd_ioctl_dbg_trap_args { + __u32 pid; + __u32 op; + + union { + struct kfd_ioctl_dbg_trap_enable_args enable; + struct kfd_ioctl_dbg_trap_send_runtime_event_args send_runtime_event; + struct kfd_ioctl_dbg_trap_set_exceptions_enabled_args set_exceptions_enabled; + struct kfd_ioctl_dbg_trap_set_wave_launch_override_args launch_override; + struct kfd_ioctl_dbg_trap_set_wave_launch_mode_args launch_mode; + struct kfd_ioctl_dbg_trap_suspend_queues_args suspend_queues; + struct kfd_ioctl_dbg_trap_resume_queues_args resume_queues; + struct kfd_ioctl_dbg_trap_set_node_address_watch_args set_node_address_watch; + struct kfd_ioctl_dbg_trap_clear_node_address_watch_args clear_node_address_watch; + struct kfd_ioctl_dbg_trap_set_flags_args set_flags; + struct kfd_ioctl_dbg_trap_query_debug_event_args query_debug_event; + struct kfd_ioctl_dbg_trap_query_exception_info_args query_exception_info; + struct kfd_ioctl_dbg_trap_queue_snapshot_args queue_snapshot; + struct kfd_ioctl_dbg_trap_device_snapshot_args device_snapshot; + }; +}; + #define AMDKFD_IOCTL_BASE 'K' #define AMDKFD_IO(nr) _IO(AMDKFD_IOCTL_BASE, nr) #define AMDKFD_IOR(nr, type) _IOR(AMDKFD_IOCTL_BASE, nr, type) @@ -887,7 +1547,13 @@ struct kfd_ioctl_set_xnack_mode_args { #define AMDKFD_IOC_EXPORT_DMABUF \ AMDKFD_IOWR(0x24, struct kfd_ioctl_export_dmabuf_args) +#define AMDKFD_IOC_RUNTIME_ENABLE \ + AMDKFD_IOWR(0x25, struct kfd_ioctl_runtime_enable_args) + +#define AMDKFD_IOC_DBG_TRAP \ + AMDKFD_IOWR(0x26, struct kfd_ioctl_dbg_trap_args) + #define AMDKFD_COMMAND_START 0x01 -#define AMDKFD_COMMAND_END 0x25 +#define AMDKFD_COMMAND_END 0x27 #endif -- cgit v1.2.3 From d230f1bfe7a1977565ce1e2804ddb7b7a3d911ff Mon Sep 17 00:00:00 2001 From: Jonathan Kim Date: Fri, 25 Mar 2022 12:39:06 -0400 Subject: drm/amdkfd: display debug capabilities Expose debug capabilities in the KFD topology node's HSA capabilities and debug properties flags. Ensure correct capabilities are exposed based on firmware support. Flag definitions can be referenced in uapi/linux/kfd_sysfs.h. Signed-off-by: Jonathan Kim Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_topology.c | 101 ++++++++++++++++++++++++++++-- drivers/gpu/drm/amd/amdkfd/kfd_topology.h | 6 ++ include/uapi/linux/kfd_sysfs.h | 15 +++++ 3 files changed, 117 insertions(+), 5 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c index 8302d8967158..3def25b2bdbb 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c @@ -535,6 +535,8 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr, dev->gpu->kfd->mec_fw_version); sysfs_show_32bit_prop(buffer, offs, "capability", dev->node_props.capability); + sysfs_show_64bit_prop(buffer, offs, "debug_prop", + dev->node_props.debug_prop); sysfs_show_32bit_prop(buffer, offs, "sdma_fw_version", dev->gpu->kfd->sdma_fw_version); sysfs_show_64bit_prop(buffer, offs, "unique_id", @@ -1857,6 +1859,97 @@ err: return res; } +static void kfd_topology_set_dbg_firmware_support(struct kfd_topology_device *dev) +{ + bool firmware_supported = true; + + if (KFD_GC_VERSION(dev->gpu) >= IP_VERSION(11, 0, 0) && + KFD_GC_VERSION(dev->gpu) < IP_VERSION(12, 0, 0)) { + firmware_supported = + (dev->gpu->adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 9; + goto out; + } + + /* + * Note: Any unlisted devices here are assumed to support exception handling. + * Add additional checks here as needed. + */ + switch (KFD_GC_VERSION(dev->gpu)) { + case IP_VERSION(9, 0, 1): + firmware_supported = dev->gpu->kfd->mec_fw_version >= 459 + 32768; + break; + case IP_VERSION(9, 1, 0): + case IP_VERSION(9, 2, 1): + case IP_VERSION(9, 2, 2): + case IP_VERSION(9, 3, 0): + case IP_VERSION(9, 4, 0): + firmware_supported = dev->gpu->kfd->mec_fw_version >= 459; + break; + case IP_VERSION(9, 4, 1): + firmware_supported = dev->gpu->kfd->mec_fw_version >= 60; + break; + case IP_VERSION(9, 4, 2): + firmware_supported = dev->gpu->kfd->mec_fw_version >= 51; + break; + case IP_VERSION(10, 1, 10): + case IP_VERSION(10, 1, 2): + case IP_VERSION(10, 1, 1): + firmware_supported = dev->gpu->kfd->mec_fw_version >= 144; + break; + case IP_VERSION(10, 3, 0): + case IP_VERSION(10, 3, 2): + case IP_VERSION(10, 3, 1): + case IP_VERSION(10, 3, 4): + case IP_VERSION(10, 3, 5): + firmware_supported = dev->gpu->kfd->mec_fw_version >= 89; + break; + case IP_VERSION(10, 1, 3): + case IP_VERSION(10, 3, 3): + firmware_supported = false; + break; + default: + break; + } + +out: + if (firmware_supported) + dev->node_props.capability |= HSA_CAP_TRAP_DEBUG_FIRMWARE_SUPPORTED; +} + +static void kfd_topology_set_capabilities(struct kfd_topology_device *dev) +{ + dev->node_props.capability |= ((HSA_CAP_DOORBELL_TYPE_2_0 << + HSA_CAP_DOORBELL_TYPE_TOTALBITS_SHIFT) & + HSA_CAP_DOORBELL_TYPE_TOTALBITS_MASK); + + dev->node_props.capability |= HSA_CAP_TRAP_DEBUG_SUPPORT | + HSA_CAP_TRAP_DEBUG_WAVE_LAUNCH_TRAP_OVERRIDE_SUPPORTED | + HSA_CAP_TRAP_DEBUG_WAVE_LAUNCH_MODE_SUPPORTED; + + if (KFD_GC_VERSION(dev->gpu) < IP_VERSION(10, 0, 0)) { + dev->node_props.debug_prop |= HSA_DBG_WATCH_ADDR_MASK_LO_BIT_GFX9 | + HSA_DBG_WATCH_ADDR_MASK_HI_BIT; + + if (KFD_GC_VERSION(dev->gpu) < IP_VERSION(9, 4, 2)) + dev->node_props.debug_prop |= + HSA_DBG_DISPATCH_INFO_ALWAYS_VALID; + else + dev->node_props.capability |= + HSA_CAP_TRAP_DEBUG_PRECISE_MEMORY_OPERATIONS_SUPPORTED; + } else { + dev->node_props.debug_prop |= HSA_DBG_WATCH_ADDR_MASK_LO_BIT_GFX10 | + HSA_DBG_WATCH_ADDR_MASK_HI_BIT; + + if (KFD_GC_VERSION(dev->gpu) < IP_VERSION(11, 0, 0)) + dev->node_props.debug_prop |= HSA_DBG_DISPATCH_INFO_ALWAYS_VALID; + else + dev->node_props.capability |= + HSA_CAP_TRAP_DEBUG_PRECISE_MEMORY_OPERATIONS_SUPPORTED; + } + + kfd_topology_set_dbg_firmware_support(dev); +} + int kfd_topology_add_device(struct kfd_node *gpu) { uint32_t gpu_id; @@ -1967,13 +2060,11 @@ int kfd_topology_add_device(struct kfd_node *gpu) HSA_CAP_DOORBELL_TYPE_TOTALBITS_MASK); break; default: - if (KFD_GC_VERSION(dev->gpu) >= IP_VERSION(9, 0, 1)) - dev->node_props.capability |= ((HSA_CAP_DOORBELL_TYPE_2_0 << - HSA_CAP_DOORBELL_TYPE_TOTALBITS_SHIFT) & - HSA_CAP_DOORBELL_TYPE_TOTALBITS_MASK); - else + if (KFD_GC_VERSION(dev->gpu) < IP_VERSION(9, 0, 1)) WARN(1, "Unexpected ASIC family %u", dev->gpu->adev->asic_type); + else + kfd_topology_set_capabilities(dev); } /* diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h index 3b8afb6aba79..cba2cd5ed9d1 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h @@ -31,6 +31,11 @@ #define KFD_TOPOLOGY_PUBLIC_NAME_SIZE 32 +#define HSA_DBG_WATCH_ADDR_MASK_LO_BIT_GFX9 6 +#define HSA_DBG_WATCH_ADDR_MASK_LO_BIT_GFX10 7 +#define HSA_DBG_WATCH_ADDR_MASK_HI_BIT \ + (29 << HSA_DBG_WATCH_ADDR_MASK_HI_BIT_SHIFT) + struct kfd_node_properties { uint64_t hive_id; uint32_t cpu_cores_count; @@ -42,6 +47,7 @@ struct kfd_node_properties { uint32_t cpu_core_id_base; uint32_t simd_id_base; uint32_t capability; + uint64_t debug_prop; uint32_t max_waves_per_simd; uint32_t lds_size_in_kb; uint32_t gds_size_in_kb; diff --git a/include/uapi/linux/kfd_sysfs.h b/include/uapi/linux/kfd_sysfs.h index 3e330f368917..a51b7331e0b4 100644 --- a/include/uapi/linux/kfd_sysfs.h +++ b/include/uapi/linux/kfd_sysfs.h @@ -43,6 +43,11 @@ #define HSA_CAP_DOORBELL_TYPE_2_0 0x2 #define HSA_CAP_AQL_QUEUE_DOUBLE_MAP 0x00004000 +#define HSA_CAP_TRAP_DEBUG_SUPPORT 0x00008000 +#define HSA_CAP_TRAP_DEBUG_WAVE_LAUNCH_TRAP_OVERRIDE_SUPPORTED 0x00010000 +#define HSA_CAP_TRAP_DEBUG_WAVE_LAUNCH_MODE_SUPPORTED 0x00020000 +#define HSA_CAP_TRAP_DEBUG_PRECISE_MEMORY_OPERATIONS_SUPPORTED 0x00040000 + /* Old buggy user mode depends on this being 0 */ #define HSA_CAP_RESERVED_WAS_SRAM_EDCSUPPORTED 0x00080000 @@ -53,8 +58,18 @@ #define HSA_CAP_SRAM_EDCSUPPORTED 0x04000000 #define HSA_CAP_SVMAPI_SUPPORTED 0x08000000 #define HSA_CAP_FLAGS_COHERENTHOSTACCESS 0x10000000 +#define HSA_CAP_TRAP_DEBUG_FIRMWARE_SUPPORTED 0x20000000 #define HSA_CAP_RESERVED 0xe00f8000 +/* debug_prop bits in node properties */ +#define HSA_DBG_WATCH_ADDR_MASK_LO_BIT_MASK 0x0000000f +#define HSA_DBG_WATCH_ADDR_MASK_LO_BIT_SHIFT 0 +#define HSA_DBG_WATCH_ADDR_MASK_HI_BIT_MASK 0x000003f0 +#define HSA_DBG_WATCH_ADDR_MASK_HI_BIT_SHIFT 4 +#define HSA_DBG_DISPATCH_INFO_ALWAYS_VALID 0x00000400 +#define HSA_DBG_WATCHPOINTS_EXCLUSIVE 0x00000800 +#define HSA_DBG_RESERVED 0xfffffffffffff000ull + /* Heap types in memory properties */ #define HSA_MEM_HEAP_TYPE_SYSTEM 0 #define HSA_MEM_HEAP_TYPE_FB_PUBLIC 1 -- cgit v1.2.3 From a159afdad2f6b97e4d18549cff2b53d17e68a412 Mon Sep 17 00:00:00 2001 From: Jonathan Kim Date: Tue, 10 May 2022 12:51:26 -0400 Subject: drm/amdkfd: bump kfd ioctl minor version for debug api availability Bump the minor version to declare debugging capability is now available. Signed-off-by: Jonathan Kim Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 1 - include/uapi/linux/kfd_ioctl.h | 3 ++- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index f54ff5c3387d..cce2abe12e1b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -2984,7 +2984,6 @@ static int kfd_ioctl_set_debug_trap(struct file *filep, struct kfd_process *p, v if (!r) target->exception_enable_mask = args->enable.exception_mask; - pr_warn("Debug functions limited\n"); break; case KFD_IOC_DBG_TRAP_DISABLE: r = kfd_dbg_trap_disable(target); diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 32913d674d38..1781e7669982 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -38,9 +38,10 @@ * - 1.10 - Add SMI profiler event log * - 1.11 - Add unified memory for ctx save/restore area * - 1.12 - Add DMA buf export ioctl + * - 1.13 - Add debugger API */ #define KFD_IOCTL_MAJOR_VERSION 1 -#define KFD_IOCTL_MINOR_VERSION 12 +#define KFD_IOCTL_MINOR_VERSION 13 struct kfd_ioctl_get_version_args { __u32 major_version; /* from KFD */ -- cgit v1.2.3 From cf264e1329fb0307e044f7675849f9f38b44c11a Mon Sep 17 00:00:00 2001 From: Nhat Pham Date: Tue, 2 May 2023 18:36:07 -0700 Subject: cachestat: implement cachestat syscall There is currently no good way to query the page cache state of large file sets and directory trees. There is mincore(), but it scales poorly: the kernel writes out a lot of bitmap data that userspace has to aggregate, when the user really doesn not care about per-page information in that case. The user also needs to mmap and unmap each file as it goes along, which can be quite slow as well. Some use cases where this information could come in handy: * Allowing database to decide whether to perform an index scan or direct table queries based on the in-memory cache state of the index. * Visibility into the writeback algorithm, for performance issues diagnostic. * Workload-aware writeback pacing: estimating IO fulfilled by page cache (and IO to be done) within a range of a file, allowing for more frequent syncing when and where there is IO capacity, and batching when there is not. * Computing memory usage of large files/directory trees, analogous to the du tool for disk usage. More information about these use cases could be found in the following thread: https://lore.kernel.org/lkml/20230315170934.GA97793@cmpxchg.org/ This patch implements a new syscall that queries cache state of a file and summarizes the number of cached pages, number of dirty pages, number of pages marked for writeback, number of (recently) evicted pages, etc. in a given range. Currently, the syscall is only wired in for x86 architecture. NAME cachestat - query the page cache statistics of a file. SYNOPSIS #include struct cachestat_range { __u64 off; __u64 len; }; struct cachestat { __u64 nr_cache; __u64 nr_dirty; __u64 nr_writeback; __u64 nr_evicted; __u64 nr_recently_evicted; }; int cachestat(unsigned int fd, struct cachestat_range *cstat_range, struct cachestat *cstat, unsigned int flags); DESCRIPTION cachestat() queries the number of cached pages, number of dirty pages, number of pages marked for writeback, number of evicted pages, number of recently evicted pages, in the bytes range given by `off` and `len`. An evicted page is a page that is previously in the page cache but has been evicted since. A page is recently evicted if its last eviction was recent enough that its reentry to the cache would indicate that it is actively being used by the system, and that there is memory pressure on the system. These values are returned in a cachestat struct, whose address is given by the `cstat` argument. The `off` and `len` arguments must be non-negative integers. If `len` > 0, the queried range is [`off`, `off` + `len`]. If `len` == 0, we will query in the range from `off` to the end of the file. The `flags` argument is unused for now, but is included for future extensibility. User should pass 0 (i.e no flag specified). Currently, hugetlbfs is not supported. Because the status of a page can change after cachestat() checks it but before it returns to the application, the returned values may contain stale information. RETURN VALUE On success, cachestat returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EFAULT cstat or cstat_args points to an invalid address. EINVAL invalid flags. EBADF invalid file descriptor. EOPNOTSUPP file descriptor is of a hugetlbfs file [nphamcs@gmail.com: replace rounddown logic with the existing helper] Link: https://lkml.kernel.org/r/20230504022044.3675469-1-nphamcs@gmail.com Link: https://lkml.kernel.org/r/20230503013608.2431726-3-nphamcs@gmail.com Signed-off-by: Nhat Pham Acked-by: Johannes Weiner Cc: Brian Foster Cc: Matthew Wilcox (Oracle) Cc: Michael Kerrisk Signed-off-by: Andrew Morton --- arch/x86/entry/syscalls/syscall_32.tbl | 1 + arch/x86/entry/syscalls/syscall_64.tbl | 1 + include/linux/syscalls.h | 5 + include/uapi/asm-generic/unistd.h | 5 +- include/uapi/linux/mman.h | 14 +++ init/Kconfig | 10 ++ kernel/sys_ni.c | 1 + mm/filemap.c | 171 +++++++++++++++++++++++++++++++++ 8 files changed, 207 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 320480a8db4f..bc0a3c941b35 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -455,3 +455,4 @@ 448 i386 process_mrelease sys_process_mrelease 449 i386 futex_waitv sys_futex_waitv 450 i386 set_mempolicy_home_node sys_set_mempolicy_home_node +451 i386 cachestat sys_cachestat diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index c84d12608cd2..227538b0ce80 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -372,6 +372,7 @@ 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 common cachestat sys_cachestat # # Due to a historical design error, certain syscalls are numbered differently diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 33a0ee3bcb2e..6648c07c4381 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -72,6 +72,8 @@ struct open_how; struct mount_attr; struct landlock_ruleset_attr; enum landlock_rule_type; +struct cachestat_range; +struct cachestat; #include #include @@ -1058,6 +1060,9 @@ asmlinkage long sys_memfd_secret(unsigned int flags); asmlinkage long sys_set_mempolicy_home_node(unsigned long start, unsigned long len, unsigned long home_node, unsigned long flags); +asmlinkage long sys_cachestat(unsigned int fd, + struct cachestat_range __user *cstat_range, + struct cachestat __user *cstat, unsigned int flags); /* * Architecture-specific system calls diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 45fa180cc56a..cd639fae9086 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -886,8 +886,11 @@ __SYSCALL(__NR_futex_waitv, sys_futex_waitv) #define __NR_set_mempolicy_home_node 450 __SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node) +#define __NR_cachestat 451 +__SYSCALL(__NR_cachestat, sys_cachestat) + #undef __NR_syscalls -#define __NR_syscalls 451 +#define __NR_syscalls 452 /* * 32 bit systems traditionally used different diff --git a/include/uapi/linux/mman.h b/include/uapi/linux/mman.h index f55bc680b5b0..a246e11988d5 100644 --- a/include/uapi/linux/mman.h +++ b/include/uapi/linux/mman.h @@ -4,6 +4,7 @@ #include #include +#include #define MREMAP_MAYMOVE 1 #define MREMAP_FIXED 2 @@ -41,4 +42,17 @@ #define MAP_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB #define MAP_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB +struct cachestat_range { + __u64 off; + __u64 len; +}; + +struct cachestat { + __u64 nr_cache; + __u64 nr_dirty; + __u64 nr_writeback; + __u64 nr_evicted; + __u64 nr_recently_evicted; +}; + #endif /* _UAPI_LINUX_MMAN_H */ diff --git a/init/Kconfig b/init/Kconfig index 32c24950c4ce..f7f65af4ee12 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1771,6 +1771,16 @@ config RSEQ If unsure, say Y. +config CACHESTAT_SYSCALL + bool "Enable cachestat() system call" if EXPERT + default y + help + Enable the cachestat system call, which queries the page cache + statistics of a file (number of cached pages, dirty pages, + pages marked for writeback, (recently) evicted pages). + + If unsure say Y here. + config DEBUG_RSEQ default n bool "Enabled debugging of rseq() system call" if EXPERT diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 860b2dcf3ac4..04bfb1e4d377 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -299,6 +299,7 @@ COND_SYSCALL(set_mempolicy); COND_SYSCALL(migrate_pages); COND_SYSCALL(move_pages); COND_SYSCALL(set_mempolicy_home_node); +COND_SYSCALL(cachestat); COND_SYSCALL(perf_event_open); COND_SYSCALL(accept4); diff --git a/mm/filemap.c b/mm/filemap.c index b4c9bd368b7e..2d3d70c64dfd 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -58,6 +59,8 @@ #include +#include "swap.h" + /* * Shared mappings implemented 30.11.1994. It's not fully working yet, * though. @@ -4119,3 +4122,171 @@ bool filemap_release_folio(struct folio *folio, gfp_t gfp) return try_to_free_buffers(folio); } EXPORT_SYMBOL(filemap_release_folio); + +#ifdef CONFIG_CACHESTAT_SYSCALL +/** + * filemap_cachestat() - compute the page cache statistics of a mapping + * @mapping: The mapping to compute the statistics for. + * @first_index: The starting page cache index. + * @last_index: The final page index (inclusive). + * @cs: the cachestat struct to write the result to. + * + * This will query the page cache statistics of a mapping in the + * page range of [first_index, last_index] (inclusive). The statistics + * queried include: number of dirty pages, number of pages marked for + * writeback, and the number of (recently) evicted pages. + */ +static void filemap_cachestat(struct address_space *mapping, + pgoff_t first_index, pgoff_t last_index, struct cachestat *cs) +{ + XA_STATE(xas, &mapping->i_pages, first_index); + struct folio *folio; + + rcu_read_lock(); + xas_for_each(&xas, folio, last_index) { + unsigned long nr_pages; + pgoff_t folio_first_index, folio_last_index; + + if (xas_retry(&xas, folio)) + continue; + + if (xa_is_value(folio)) { + /* page is evicted */ + void *shadow = (void *)folio; + bool workingset; /* not used */ + int order = xa_get_order(xas.xa, xas.xa_index); + + nr_pages = 1 << order; + folio_first_index = round_down(xas.xa_index, 1 << order); + folio_last_index = folio_first_index + nr_pages - 1; + + /* Folios might straddle the range boundaries, only count covered pages */ + if (folio_first_index < first_index) + nr_pages -= first_index - folio_first_index; + + if (folio_last_index > last_index) + nr_pages -= folio_last_index - last_index; + + cs->nr_evicted += nr_pages; + +#ifdef CONFIG_SWAP /* implies CONFIG_MMU */ + if (shmem_mapping(mapping)) { + /* shmem file - in swap cache */ + swp_entry_t swp = radix_to_swp_entry(folio); + + shadow = get_shadow_from_swap_cache(swp); + } +#endif + if (workingset_test_recent(shadow, true, &workingset)) + cs->nr_recently_evicted += nr_pages; + + goto resched; + } + + nr_pages = folio_nr_pages(folio); + folio_first_index = folio_pgoff(folio); + folio_last_index = folio_first_index + nr_pages - 1; + + /* Folios might straddle the range boundaries, only count covered pages */ + if (folio_first_index < first_index) + nr_pages -= first_index - folio_first_index; + + if (folio_last_index > last_index) + nr_pages -= folio_last_index - last_index; + + /* page is in cache */ + cs->nr_cache += nr_pages; + + if (folio_test_dirty(folio)) + cs->nr_dirty += nr_pages; + + if (folio_test_writeback(folio)) + cs->nr_writeback += nr_pages; + +resched: + if (need_resched()) { + xas_pause(&xas); + cond_resched_rcu(); + } + } + rcu_read_unlock(); +} + +/* + * The cachestat(2) system call. + * + * cachestat() returns the page cache statistics of a file in the + * bytes range specified by `off` and `len`: number of cached pages, + * number of dirty pages, number of pages marked for writeback, + * number of evicted pages, and number of recently evicted pages. + * + * An evicted page is a page that is previously in the page cache + * but has been evicted since. A page is recently evicted if its last + * eviction was recent enough that its reentry to the cache would + * indicate that it is actively being used by the system, and that + * there is memory pressure on the system. + * + * `off` and `len` must be non-negative integers. If `len` > 0, + * the queried range is [`off`, `off` + `len`]. If `len` == 0, + * we will query in the range from `off` to the end of the file. + * + * The `flags` argument is unused for now, but is included for future + * extensibility. User should pass 0 (i.e no flag specified). + * + * Currently, hugetlbfs is not supported. + * + * Because the status of a page can change after cachestat() checks it + * but before it returns to the application, the returned values may + * contain stale information. + * + * return values: + * zero - success + * -EFAULT - cstat or cstat_range points to an illegal address + * -EINVAL - invalid flags + * -EBADF - invalid file descriptor + * -EOPNOTSUPP - file descriptor is of a hugetlbfs file + */ +SYSCALL_DEFINE4(cachestat, unsigned int, fd, + struct cachestat_range __user *, cstat_range, + struct cachestat __user *, cstat, unsigned int, flags) +{ + struct fd f = fdget(fd); + struct address_space *mapping; + struct cachestat_range csr; + struct cachestat cs; + pgoff_t first_index, last_index; + + if (!f.file) + return -EBADF; + + if (copy_from_user(&csr, cstat_range, + sizeof(struct cachestat_range))) { + fdput(f); + return -EFAULT; + } + + /* hugetlbfs is not supported */ + if (is_file_hugepages(f.file)) { + fdput(f); + return -EOPNOTSUPP; + } + + if (flags != 0) { + fdput(f); + return -EINVAL; + } + + first_index = csr.off >> PAGE_SHIFT; + last_index = + csr.len == 0 ? ULONG_MAX : (csr.off + csr.len - 1) >> PAGE_SHIFT; + memset(&cs, 0, sizeof(struct cachestat)); + mapping = f.file->f_mapping; + filemap_cachestat(mapping, first_index, last_index, &cs); + fdput(f); + + if (copy_to_user(cstat, &cs, sizeof(struct cachestat))) + return -EFAULT; + + return 0; +} +#endif /* CONFIG_CACHESTAT_SYSCALL */ -- cgit v1.2.3 From e069ba07e6c7af69e119316bc87ff44869095f49 Mon Sep 17 00:00:00 2001 From: Aaron Conole Date: Fri, 9 Jun 2023 09:59:55 -0400 Subject: net: openvswitch: add support for l4 symmetric hashing Since its introduction, the ovs module execute_hash action allowed hash algorithms other than the skb->l4_hash to be used. However, additional hash algorithms were not implemented. This means flows requiring different hash distributions weren't able to use the kernel datapath. Now, introduce support for symmetric hashing algorithm as an alternative hash supported by the ovs module using the flow dissector. Output of flow using l4_sym hash: recirc_id(0),in_port(3),eth(),eth_type(0x0800), ipv4(dst=64.0.0.0/192.0.0.0,proto=6,frag=no), packets:30473425, bytes:45902883702, used:0.000s, flags:SP., actions:hash(sym_l4(0)),recirc(0xd) Some performance testing with no GRO/GSO, two veths, single flow: hash(l4(0)): 4.35 GBits/s hash(l4_sym(0)): 4.24 GBits/s Signed-off-by: Aaron Conole Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 1 + net/openvswitch/actions.c | 12 ++++++++++-- net/openvswitch/flow_netlink.c | 2 ++ 3 files changed, 13 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index c5d62ee82567..e94870e77ee9 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -765,6 +765,7 @@ struct ovs_action_push_vlan { */ enum ovs_hash_alg { OVS_HASH_ALG_L4, + OVS_HASH_ALG_SYM_L4, }; /* diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 8074ea00d577..cab1e02b63e0 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -1073,8 +1073,16 @@ static void execute_hash(struct sk_buff *skb, struct sw_flow_key *key, struct ovs_action_hash *hash_act = nla_data(attr); u32 hash = 0; - /* OVS_HASH_ALG_L4 is the only possible hash algorithm. */ - hash = skb_get_hash(skb); + if (hash_act->hash_alg == OVS_HASH_ALG_L4) { + /* OVS_HASH_ALG_L4 hasing type. */ + hash = skb_get_hash(skb); + } else if (hash_act->hash_alg == OVS_HASH_ALG_SYM_L4) { + /* OVS_HASH_ALG_SYM_L4 hashing type. NOTE: this doesn't + * extend past an encapsulated header. + */ + hash = __skb_get_hash_symmetric(skb); + } + hash = jhash_1word(hash, hash_act->hash_basis); if (!hash) hash = 0x1; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index ead5418c126e..41116361433d 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -3221,6 +3221,8 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, switch (act_hash->hash_alg) { case OVS_HASH_ALG_L4: + fallthrough; + case OVS_HASH_ALG_SYM_L4: break; default: return -EINVAL; -- cgit v1.2.3 From 5e2ff6704a275be009be8979af17c52361b79b89 Mon Sep 17 00:00:00 2001 From: Alexander Mikhalitsyn Date: Thu, 8 Jun 2023 22:26:25 +0200 Subject: scm: add SO_PASSPIDFD and SCM_PIDFD Implement SCM_PIDFD, a new type of CMSG type analogical to SCM_CREDENTIALS, but it contains pidfd instead of plain pid, which allows programmers not to care about PID reuse problem. We mask SO_PASSPIDFD feature if CONFIG_UNIX is not builtin because it depends on a pidfd_prepare() API which is not exported to the kernel modules. Idea comes from UAPI kernel group: https://uapi-group.org/kernel-features/ Big thanks to Christian Brauner and Lennart Poettering for productive discussions about this. Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: Leon Romanovsky Cc: David Ahern Cc: Arnd Bergmann Cc: Kees Cook Cc: Christian Brauner Cc: Kuniyuki Iwashima Cc: Lennart Poettering Cc: Luca Boccassi Cc: linux-kernel@vger.kernel.org Cc: netdev@vger.kernel.org Cc: linux-arch@vger.kernel.org Tested-by: Luca Boccassi Reviewed-by: Kuniyuki Iwashima Reviewed-by: Christian Brauner Signed-off-by: Alexander Mikhalitsyn Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- arch/alpha/include/uapi/asm/socket.h | 2 ++ arch/mips/include/uapi/asm/socket.h | 2 ++ arch/parisc/include/uapi/asm/socket.h | 2 ++ arch/sparc/include/uapi/asm/socket.h | 2 ++ include/linux/net.h | 1 + include/linux/socket.h | 1 + include/net/scm.h | 39 +++++++++++++++++++++++++++++++-- include/uapi/asm-generic/socket.h | 2 ++ net/core/sock.c | 11 ++++++++++ net/mptcp/sockopt.c | 1 + net/unix/af_unix.c | 18 ++++++++++----- tools/include/uapi/asm-generic/socket.h | 2 ++ 12 files changed, 76 insertions(+), 7 deletions(-) (limited to 'include/uapi') diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index 739891b94136..ff310613ae64 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -137,6 +137,8 @@ #define SO_RCVMARK 75 +#define SO_PASSPIDFD 76 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 18f3d95ecfec..762dcb80e4ec 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -148,6 +148,8 @@ #define SO_RCVMARK 75 +#define SO_PASSPIDFD 76 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index f486d3dfb6bb..df16a3e16d64 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -129,6 +129,8 @@ #define SO_RCVMARK 0x4049 +#define SO_PASSPIDFD 0x404A + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 2fda57a3ea86..6e2847804fea 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -130,6 +130,8 @@ #define SO_RCVMARK 0x0054 +#define SO_PASSPIDFD 0x0055 + #if !defined(__KERNEL__) diff --git a/include/linux/net.h b/include/linux/net.h index 8defc8f1d82e..23324e9a2b3d 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -43,6 +43,7 @@ struct net; #define SOCK_PASSSEC 4 #define SOCK_SUPPORT_ZC 5 #define SOCK_CUSTOM_SOCKOPT 6 +#define SOCK_PASSPIDFD 7 #ifndef ARCH_HAS_SOCKET_TYPES /** diff --git a/include/linux/socket.h b/include/linux/socket.h index 3fd3436bc09f..58204700018a 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -177,6 +177,7 @@ static inline size_t msg_data_left(struct msghdr *msg) #define SCM_RIGHTS 0x01 /* rw: access rights (array of int) */ #define SCM_CREDENTIALS 0x02 /* rw: struct ucred */ #define SCM_SECURITY 0x03 /* rw: security label */ +#define SCM_PIDFD 0x04 /* ro: pidfd (int) */ struct ucred { __u32 pid; diff --git a/include/net/scm.h b/include/net/scm.h index 585adc1346bd..c67f765a165b 100644 --- a/include/net/scm.h +++ b/include/net/scm.h @@ -120,12 +120,44 @@ static inline bool scm_has_secdata(struct socket *sock) } #endif /* CONFIG_SECURITY_NETWORK */ +static __inline__ void scm_pidfd_recv(struct msghdr *msg, struct scm_cookie *scm) +{ + struct file *pidfd_file = NULL; + int pidfd; + + /* + * put_cmsg() doesn't return an error if CMSG is truncated, + * that's why we need to opencode these checks here. + */ + if ((msg->msg_controllen <= sizeof(struct cmsghdr)) || + (msg->msg_controllen - sizeof(struct cmsghdr)) < sizeof(int)) { + msg->msg_flags |= MSG_CTRUNC; + return; + } + + WARN_ON_ONCE(!scm->pid); + pidfd = pidfd_prepare(scm->pid, 0, &pidfd_file); + + if (put_cmsg(msg, SOL_SOCKET, SCM_PIDFD, sizeof(int), &pidfd)) { + if (pidfd_file) { + put_unused_fd(pidfd); + fput(pidfd_file); + } + + return; + } + + if (pidfd_file) + fd_install(pidfd, pidfd_file); +} + static __inline__ void scm_recv(struct socket *sock, struct msghdr *msg, struct scm_cookie *scm, int flags) { if (!msg->msg_control) { - if (test_bit(SOCK_PASSCRED, &sock->flags) || scm->fp || - scm_has_secdata(sock)) + if (test_bit(SOCK_PASSCRED, &sock->flags) || + test_bit(SOCK_PASSPIDFD, &sock->flags) || + scm->fp || scm_has_secdata(sock)) msg->msg_flags |= MSG_CTRUNC; scm_destroy(scm); return; @@ -141,6 +173,9 @@ static __inline__ void scm_recv(struct socket *sock, struct msghdr *msg, put_cmsg(msg, SOL_SOCKET, SCM_CREDENTIALS, sizeof(ucreds), &ucreds); } + if (test_bit(SOCK_PASSPIDFD, &sock->flags)) + scm_pidfd_recv(msg, scm); + scm_destroy_cred(scm); scm_passec(sock, msg, scm); diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 638230899e98..b76169fdb80b 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -132,6 +132,8 @@ #define SO_RCVMARK 75 +#define SO_PASSPIDFD 76 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) diff --git a/net/core/sock.c b/net/core/sock.c index 24f2761bdb1d..ed4eb4ba738b 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1246,6 +1246,13 @@ set_sndbuf: clear_bit(SOCK_PASSCRED, &sock->flags); break; + case SO_PASSPIDFD: + if (valbool) + set_bit(SOCK_PASSPIDFD, &sock->flags); + else + clear_bit(SOCK_PASSPIDFD, &sock->flags); + break; + case SO_TIMESTAMP_OLD: case SO_TIMESTAMP_NEW: case SO_TIMESTAMPNS_OLD: @@ -1732,6 +1739,10 @@ int sk_getsockopt(struct sock *sk, int level, int optname, v.val = !!test_bit(SOCK_PASSCRED, &sock->flags); break; + case SO_PASSPIDFD: + v.val = !!test_bit(SOCK_PASSPIDFD, &sock->flags); + break; + case SO_PEERCRED: { struct ucred peercred; diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index d4258869ac48..e172a5848b0d 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -355,6 +355,7 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname, case SO_BROADCAST: case SO_BSDCOMPAT: case SO_PASSCRED: + case SO_PASSPIDFD: case SO_PASSSEC: case SO_RXQ_OVFL: case SO_WIFI_STATUS: diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 653136d68b32..c46c2f5d860c 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1361,7 +1361,8 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr, if (err) goto out; - if (test_bit(SOCK_PASSCRED, &sock->flags) && + if ((test_bit(SOCK_PASSCRED, &sock->flags) || + test_bit(SOCK_PASSPIDFD, &sock->flags)) && !unix_sk(sk)->addr) { err = unix_autobind(sk); if (err) @@ -1469,7 +1470,8 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, if (err) goto out; - if (test_bit(SOCK_PASSCRED, &sock->flags) && !u->addr) { + if ((test_bit(SOCK_PASSCRED, &sock->flags) || + test_bit(SOCK_PASSPIDFD, &sock->flags)) && !u->addr) { err = unix_autobind(sk); if (err) goto out; @@ -1670,6 +1672,8 @@ static void unix_sock_inherit_flags(const struct socket *old, { if (test_bit(SOCK_PASSCRED, &old->flags)) set_bit(SOCK_PASSCRED, &new->flags); + if (test_bit(SOCK_PASSPIDFD, &old->flags)) + set_bit(SOCK_PASSPIDFD, &new->flags); if (test_bit(SOCK_PASSSEC, &old->flags)) set_bit(SOCK_PASSSEC, &new->flags); } @@ -1819,8 +1823,10 @@ static bool unix_passcred_enabled(const struct socket *sock, const struct sock *other) { return test_bit(SOCK_PASSCRED, &sock->flags) || + test_bit(SOCK_PASSPIDFD, &sock->flags) || !other->sk_socket || - test_bit(SOCK_PASSCRED, &other->sk_socket->flags); + test_bit(SOCK_PASSCRED, &other->sk_socket->flags) || + test_bit(SOCK_PASSPIDFD, &other->sk_socket->flags); } /* @@ -1904,7 +1910,8 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, goto out; } - if (test_bit(SOCK_PASSCRED, &sock->flags) && !u->addr) { + if ((test_bit(SOCK_PASSCRED, &sock->flags) || + test_bit(SOCK_PASSPIDFD, &sock->flags)) && !u->addr) { err = unix_autobind(sk); if (err) goto out; @@ -2718,7 +2725,8 @@ unlock: /* Never glue messages from different writers */ if (!unix_skb_scm_eq(skb, &scm)) break; - } else if (test_bit(SOCK_PASSCRED, &sock->flags)) { + } else if (test_bit(SOCK_PASSCRED, &sock->flags) || + test_bit(SOCK_PASSPIDFD, &sock->flags)) { /* Copy credentials */ scm_set_cred(&scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid); unix_set_secdata(&scm, skb); diff --git a/tools/include/uapi/asm-generic/socket.h b/tools/include/uapi/asm-generic/socket.h index 8756df13be50..fbbc4bf53ee3 100644 --- a/tools/include/uapi/asm-generic/socket.h +++ b/tools/include/uapi/asm-generic/socket.h @@ -121,6 +121,8 @@ #define SO_RCVMARK 75 +#define SO_PASSPIDFD 76 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) -- cgit v1.2.3 From 7b26952a91cf65ff1cc867a2382a8964d8c0ee7d Mon Sep 17 00:00:00 2001 From: Alexander Mikhalitsyn Date: Thu, 8 Jun 2023 22:26:26 +0200 Subject: net: core: add getsockopt SO_PEERPIDFD Add SO_PEERPIDFD which allows to get pidfd of peer socket holder pidfd. This thing is direct analog of SO_PEERCRED which allows to get plain PID. Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: Leon Romanovsky Cc: David Ahern Cc: Arnd Bergmann Cc: Kees Cook Cc: Christian Brauner Cc: Kuniyuki Iwashima Cc: Lennart Poettering Cc: Luca Boccassi Cc: Daniel Borkmann Cc: Stanislav Fomichev Cc: bpf@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: netdev@vger.kernel.org Cc: linux-arch@vger.kernel.org Reviewed-by: Christian Brauner Acked-by: Stanislav Fomichev Tested-by: Luca Boccassi Signed-off-by: Alexander Mikhalitsyn Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- arch/alpha/include/uapi/asm/socket.h | 1 + arch/mips/include/uapi/asm/socket.h | 1 + arch/parisc/include/uapi/asm/socket.h | 1 + arch/sparc/include/uapi/asm/socket.h | 1 + include/uapi/asm-generic/socket.h | 1 + net/core/sock.c | 33 +++++++++++++++++++++++++++++++++ net/unix/af_unix.c | 16 ++++++++++++++++ tools/include/uapi/asm-generic/socket.h | 1 + 8 files changed, 55 insertions(+) (limited to 'include/uapi') diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index ff310613ae64..e94f621903fe 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -138,6 +138,7 @@ #define SO_RCVMARK 75 #define SO_PASSPIDFD 76 +#define SO_PEERPIDFD 77 #if !defined(__KERNEL__) diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 762dcb80e4ec..60ebaed28a4c 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -149,6 +149,7 @@ #define SO_RCVMARK 75 #define SO_PASSPIDFD 76 +#define SO_PEERPIDFD 77 #if !defined(__KERNEL__) diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index df16a3e16d64..be264c2b1a11 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -130,6 +130,7 @@ #define SO_RCVMARK 0x4049 #define SO_PASSPIDFD 0x404A +#define SO_PEERPIDFD 0x404B #if !defined(__KERNEL__) diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 6e2847804fea..682da3714686 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -131,6 +131,7 @@ #define SO_RCVMARK 0x0054 #define SO_PASSPIDFD 0x0055 +#define SO_PEERPIDFD 0x0056 #if !defined(__KERNEL__) diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index b76169fdb80b..8ce8a39a1e5f 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -133,6 +133,7 @@ #define SO_RCVMARK 75 #define SO_PASSPIDFD 76 +#define SO_PEERPIDFD 77 #if !defined(__KERNEL__) diff --git a/net/core/sock.c b/net/core/sock.c index ed4eb4ba738b..ea66b1afadd0 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1758,6 +1758,39 @@ int sk_getsockopt(struct sock *sk, int level, int optname, goto lenout; } + case SO_PEERPIDFD: + { + struct pid *peer_pid; + struct file *pidfd_file = NULL; + int pidfd; + + if (len > sizeof(pidfd)) + len = sizeof(pidfd); + + spin_lock(&sk->sk_peer_lock); + peer_pid = get_pid(sk->sk_peer_pid); + spin_unlock(&sk->sk_peer_lock); + + if (!peer_pid) + return -ESRCH; + + pidfd = pidfd_prepare(peer_pid, 0, &pidfd_file); + put_pid(peer_pid); + if (pidfd < 0) + return pidfd; + + if (copy_to_sockptr(optval, &pidfd, len) || + copy_to_sockptr(optlen, &len, sizeof(int))) { + put_unused_fd(pidfd); + fput(pidfd_file); + + return -EFAULT; + } + + fd_install(pidfd, pidfd_file); + return 0; + } + case SO_PEERGROUPS: { const struct cred *cred; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index c46c2f5d860c..73c61a010b01 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -921,11 +921,26 @@ static void unix_unhash(struct sock *sk) */ } +static bool unix_bpf_bypass_getsockopt(int level, int optname) +{ + if (level == SOL_SOCKET) { + switch (optname) { + case SO_PEERPIDFD: + return true; + default: + return false; + } + } + + return false; +} + struct proto unix_dgram_proto = { .name = "UNIX", .owner = THIS_MODULE, .obj_size = sizeof(struct unix_sock), .close = unix_close, + .bpf_bypass_getsockopt = unix_bpf_bypass_getsockopt, #ifdef CONFIG_BPF_SYSCALL .psock_update_sk_prot = unix_dgram_bpf_update_proto, #endif @@ -937,6 +952,7 @@ struct proto unix_stream_proto = { .obj_size = sizeof(struct unix_sock), .close = unix_close, .unhash = unix_unhash, + .bpf_bypass_getsockopt = unix_bpf_bypass_getsockopt, #ifdef CONFIG_BPF_SYSCALL .psock_update_sk_prot = unix_stream_bpf_update_proto, #endif diff --git a/tools/include/uapi/asm-generic/socket.h b/tools/include/uapi/asm-generic/socket.h index fbbc4bf53ee3..54d9c8bf7c55 100644 --- a/tools/include/uapi/asm-generic/socket.h +++ b/tools/include/uapi/asm-generic/socket.h @@ -122,6 +122,7 @@ #define SO_RCVMARK 75 #define SO_PASSPIDFD 76 +#define SO_PEERPIDFD 77 #if !defined(__KERNEL__) -- cgit v1.2.3 From e375b8a045873cf5fb8bf61bf9a0ddfcd484243a Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 12 Jun 2023 10:10:45 +0200 Subject: ALSA: ump: Add more attributes to UMP EP and FB info Add a few more fields to snd_ump_endpoint_info and snd_ump_block_info that are added in the new v1.1 spec. Those are filled by the UMP Stream messages. The rawmidi protocol version is bumped to 2.0.4 to indicate those updates. Also, update the proc outputs to show the newly introduced fields. Link: https://lore.kernel.org/r/20230612081054.17200-2-tiwai@suse.de Signed-off-by: Takashi Iwai --- include/uapi/sound/asound.h | 18 +++++++++++++++--- sound/core/ump.c | 33 +++++++++++++++++++++++++++++++++ 2 files changed, 48 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h index 5c5f41dd4001..79ee48b2ed6d 100644 --- a/include/uapi/sound/asound.h +++ b/include/uapi/sound/asound.h @@ -708,7 +708,7 @@ enum { * Raw MIDI section - /dev/snd/midi?? */ -#define SNDRV_RAWMIDI_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 3) +#define SNDRV_RAWMIDI_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 4) enum { SNDRV_RAWMIDI_STREAM_OUTPUT = 0, @@ -797,7 +797,11 @@ struct snd_ump_endpoint_info { unsigned int protocol; /* current protocol */ unsigned int num_blocks; /* # of function blocks */ unsigned short version; /* UMP major/minor version */ - unsigned short padding[7]; + unsigned short family_id; /* MIDI device family ID */ + unsigned short model_id; /* MIDI family model ID */ + unsigned int manufacturer_id; /* MIDI manufacturer ID */ + unsigned char sw_revision[4]; /* software revision */ + unsigned short padding; unsigned char name[128]; /* endpoint name string */ unsigned char product_id[128]; /* unique product id string */ unsigned char reserved[32]; @@ -812,6 +816,12 @@ struct snd_ump_endpoint_info { #define SNDRV_UMP_BLOCK_IS_MIDI1 (1U << 0) /* MIDI 1.0 port w/o restrict */ #define SNDRV_UMP_BLOCK_IS_LOWSPEED (1U << 1) /* 31.25Kbps B/W MIDI1 port */ +/* UMP block user-interface hint */ +#define SNDRV_UMP_BLOCK_UI_HINT_UNKNOWN 0x00 +#define SNDRV_UMP_BLOCK_UI_HINT_RECEIVER 0x01 +#define SNDRV_UMP_BLOCK_UI_HINT_SENDER 0x02 +#define SNDRV_UMP_BLOCK_UI_HINT_BOTH 0x03 + /* UMP groups and blocks */ #define SNDRV_UMP_MAX_GROUPS 16 #define SNDRV_UMP_MAX_BLOCKS 32 @@ -825,7 +835,9 @@ struct snd_ump_block_info { unsigned char active; /* Activeness */ unsigned char first_group; /* first group ID */ unsigned char num_groups; /* number of groups */ - unsigned char padding[3]; + unsigned char midi_ci_version; /* MIDI-CI support version */ + unsigned char sysex8_streams; /* max number of sysex8 streams */ + unsigned char ui_hint; /* user interface hint */ unsigned int flags; /* various info flags */ unsigned char name[128]; /* block name string */ unsigned char reserved[32]; diff --git a/sound/core/ump.c b/sound/core/ump.c index 69993cad6772..839873fb0f33 100644 --- a/sound/core/ump.c +++ b/sound/core/ump.c @@ -448,6 +448,20 @@ static const char *ump_direction_string(int dir) } } +static const char *ump_ui_hint_string(int dir) +{ + switch (dir) { + case SNDRV_UMP_BLOCK_UI_HINT_RECEIVER: + return "receiver"; + case SNDRV_UMP_BLOCK_UI_HINT_SENDER: + return "sender"; + case SNDRV_UMP_BLOCK_UI_HINT_BOTH: + return "both"; + default: + return "unknown"; + } +} + /* Additional proc file output */ static void snd_ump_proc_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) @@ -461,6 +475,17 @@ static void snd_ump_proc_read(struct snd_info_entry *entry, snd_iprintf(buffer, "UMP Version: 0x%04x\n", ump->info.version); snd_iprintf(buffer, "Protocol Caps: 0x%08x\n", ump->info.protocol_caps); snd_iprintf(buffer, "Protocol: 0x%08x\n", ump->info.protocol); + if (ump->info.version) { + snd_iprintf(buffer, "Manufacturer ID: 0x%08x\n", + ump->info.manufacturer_id); + snd_iprintf(buffer, "Family ID: 0x%04x\n", ump->info.family_id); + snd_iprintf(buffer, "Model ID: 0x%04x\n", ump->info.model_id); + snd_iprintf(buffer, "SW Revision: 0x%02x%02x%02x%02x\n", + ump->info.sw_revision[0], + ump->info.sw_revision[1], + ump->info.sw_revision[2], + ump->info.sw_revision[3]); + } snd_iprintf(buffer, "Num Blocks: %d\n\n", ump->info.num_blocks); list_for_each_entry(fb, &ump->block_list, list) { @@ -476,6 +501,14 @@ static void snd_ump_proc_read(struct snd_info_entry *entry, snd_iprintf(buffer, " Is MIDI1: %s%s\n", (fb->info.flags & SNDRV_UMP_BLOCK_IS_MIDI1) ? "Yes" : "No", (fb->info.flags & SNDRV_UMP_BLOCK_IS_LOWSPEED) ? " (Low Speed)" : ""); + if (ump->info.version) { + snd_iprintf(buffer, " MIDI-CI Version: %d\n", + fb->info.midi_ci_version); + snd_iprintf(buffer, " Sysex8 Streams: %d\n", + fb->info.sysex8_streams); + snd_iprintf(buffer, " UI Hint: %s\n", + ump_ui_hint_string(fb->info.ui_hint)); + } snd_iprintf(buffer, "\n"); } } -- cgit v1.2.3 From 5437ac9bad639bb9112e1a749acbe4a143562cdc Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 12 Jun 2023 10:10:49 +0200 Subject: ALSA: seq: ump: Handle groupless messages The UMP Utility and Stream messages are "groupless", i.e. an incoming groupless packet should be sent only to the UMP EP port, and the event with the groupless message is sent to UMP EP as is without the group translation per port. Also, the former reserved bit 0 for the client group filter is now used for groupless events. When the bit 0 is set, the groupless events are filtered out and skipped. Link: https://lore.kernel.org/r/20230612081054.17200-6-tiwai@suse.de Signed-off-by: Takashi Iwai --- include/sound/ump.h | 3 +++ include/uapi/sound/asequencer.h | 5 ++++- sound/core/seq/seq_ump_client.c | 5 ++++- sound/core/seq/seq_ump_convert.c | 3 +++ 4 files changed, 14 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/sound/ump.h b/include/sound/ump.h index aef4748842d0..5b50a2fc0d79 100644 --- a/include/sound/ump.h +++ b/include/sound/ump.h @@ -255,4 +255,7 @@ static inline u32 ump_stream_compose(unsigned char status, unsigned short form) ((u32)status << 16); } +#define ump_is_groupless_msg(type) \ + ((type) == UMP_MSG_TYPE_UTILITY || (type) == UMP_MSG_TYPE_STREAM) + #endif /* __SOUND_UMP_H */ diff --git a/include/uapi/sound/asequencer.h b/include/uapi/sound/asequencer.h index 5e91243665d8..b5bc8604efe8 100644 --- a/include/uapi/sound/asequencer.h +++ b/include/uapi/sound/asequencer.h @@ -362,7 +362,10 @@ struct snd_seq_client_info { int card; /* RO: card number[kernel] */ int pid; /* RO: pid[user] */ unsigned int midi_version; /* MIDI version */ - unsigned int group_filter; /* UMP group filter bitmap (for 1-based Group indices) */ + unsigned int group_filter; /* UMP group filter bitmap + * (bit 0 = groupless messages, + * bit 1-16 = messages for groups 1-16) + */ char reserved[48]; /* for future use */ }; diff --git a/sound/core/seq/seq_ump_client.c b/sound/core/seq/seq_ump_client.c index e24833804094..7739fb3ebf34 100644 --- a/sound/core/seq/seq_ump_client.c +++ b/sound/core/seq/seq_ump_client.c @@ -73,7 +73,10 @@ static void seq_ump_input_receive(struct snd_ump_endpoint *ump, if (!client->opened[STR_IN]) return; - ev.source.port = ump_group_to_seq_port(ump_message_group(*val)); + if (ump_is_groupless_msg(ump_message_type(*val))) + ev.source.port = 0; /* UMP EP port */ + else + ev.source.port = ump_group_to_seq_port(ump_message_group(*val)); ev.dest.client = SNDRV_SEQ_ADDRESS_SUBSCRIBERS; ev.flags = SNDRV_SEQ_EVENT_UMP; memcpy(ev.ump, val, words << 2); diff --git a/sound/core/seq/seq_ump_convert.c b/sound/core/seq/seq_ump_convert.c index 14ba6fed9dd1..eb1d86ff6166 100644 --- a/sound/core/seq/seq_ump_convert.c +++ b/sound/core/seq/seq_ump_convert.c @@ -534,6 +534,8 @@ static bool ump_event_filtered(struct snd_seq_client *dest, unsigned char group; group = ump_message_group(ev->ump[0]); + if (ump_is_groupless_msg(ump_message_type(ev->ump[0]))) + return dest->group_filter & (1U << 0); /* check the bitmap for 1-based group number */ return dest->group_filter & (1U << (group + 1)); } @@ -565,6 +567,7 @@ int snd_seq_deliver_from_ump(struct snd_seq_client *source, event, atomic, hop); /* non-EP port and different group is set? */ if (dest_port->ump_group && + !ump_is_groupless_msg(type) && ump_message_group(*ump_ev->ump) + 1 != dest_port->ump_group) return deliver_with_group_convert(dest, dest_port, ump_ev, atomic, hop); -- cgit v1.2.3 From 01dfa8e969dbbc72fc4564e8d61c905c4f3a2352 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 12 Jun 2023 10:10:53 +0200 Subject: ALSA: ump: Add info flag bit for static blocks UMP v1.1 spec allows to inform whether the function blocks are static and not dynamically updated. Add a new flag bit to snd_ump_endpoint_info to reflect that attribute, too. The flag is set when a USB MIDI device is still in the old MIDI 2.0 without UMP 1.1 support. Then the driver falls back to GTBs, and they are supposed to be static-only. Link: https://lore.kernel.org/r/20230612081054.17200-10-tiwai@suse.de Signed-off-by: Takashi Iwai --- include/uapi/sound/asound.h | 3 +++ sound/core/ump.c | 11 +++++++++++ sound/usb/midi2.c | 2 ++ 3 files changed, 16 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h index 79ee48b2ed6d..4d1ac0797d56 100644 --- a/include/uapi/sound/asound.h +++ b/include/uapi/sound/asound.h @@ -780,6 +780,9 @@ struct snd_rawmidi_status { }; #endif +/* UMP EP info flags */ +#define SNDRV_UMP_EP_INFO_STATIC_BLOCKS 0x01 + /* UMP EP Protocol / JRTS capability bits */ #define SNDRV_UMP_EP_INFO_PROTO_MIDI_MASK 0x0300 #define SNDRV_UMP_EP_INFO_PROTO_MIDI1 0x0100 /* MIDI 1.0 */ diff --git a/sound/core/ump.c b/sound/core/ump.c index f364bb290d3a..a64dc2d8a129 100644 --- a/sound/core/ump.c +++ b/sound/core/ump.c @@ -490,6 +490,8 @@ static void snd_ump_proc_read(struct snd_info_entry *entry, ump->info.sw_revision[2], ump->info.sw_revision[3]); } + snd_iprintf(buffer, "Static Blocks: %s\n", + (ump->info.flags & SNDRV_UMP_EP_INFO_STATIC_BLOCKS) ? "Yes" : "No"); snd_iprintf(buffer, "Num Blocks: %d\n\n", ump->info.num_blocks); list_for_each_entry(fb, &ump->block_list, list) { @@ -608,6 +610,9 @@ static int ump_handle_ep_info_msg(struct snd_ump_endpoint *ump, ump->info.num_blocks = 1; } + if (buf->ep_info.static_function_block) + ump->info.flags |= SNDRV_UMP_EP_INFO_STATIC_BLOCKS; + ump->info.protocol_caps = (buf->ep_info.protocol << 8) | buf->ep_info.jrts; @@ -708,6 +713,12 @@ static bool is_fb_info_updated(struct snd_ump_endpoint *ump, { char tmpbuf[offsetof(struct snd_ump_block_info, name)]; + if (ump->info.flags & SNDRV_UMP_EP_INFO_STATIC_BLOCKS) { + ump_info(ump, "Skipping static FB info update (blk#%d)\n", + fb->info.block_id); + return 0; + } + memcpy(tmpbuf, &fb->info, sizeof(tmpbuf)); fill_fb_info(ump, (struct snd_ump_block_info *)tmpbuf, buf); return memcmp(&fb->info, tmpbuf, sizeof(tmpbuf)) != 0; diff --git a/sound/usb/midi2.c b/sound/usb/midi2.c index 13fa1978267a..ee2835741479 100644 --- a/sound/usb/midi2.c +++ b/sound/usb/midi2.c @@ -888,6 +888,8 @@ static int create_blocks_from_gtb(struct snd_usb_midi2_interface *umidi) /* Blocks have been already created? */ if (rmidi->ump_parsed || rmidi->ump->info.num_blocks) continue; + /* GTB is static-only */ + rmidi->ump->info.flags |= SNDRV_UMP_EP_INFO_STATIC_BLOCKS; /* loop over GTBs */ for (dir = 0; dir < 2; dir++) { if (!rmidi->eps[dir]) -- cgit v1.2.3 From 7cfffd5fed3e385010583840402f0bf66c4ed147 Mon Sep 17 00:00:00 2001 From: Zahari Doychev Date: Thu, 8 Jun 2023 12:56:47 +0200 Subject: net: flower: add support for matching cfm fields Add support to the tc flower classifier to match based on fields in CFM information elements like level and opcode. tc filter add dev ens6 ingress protocol 802.1q \ flower vlan_id 698 vlan_ethtype 0x8902 cfm mdl 5 op 46 \ action drop Signed-off-by: Zahari Doychev Reviewed-by: Simon Horman Reviewed-by: Ido Schimmel Signed-off-by: Jakub Kicinski --- include/uapi/linux/pkt_cls.h | 9 ++++ net/sched/cls_flower.c | 102 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 111 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 00933dda7b10..7865f5a9885b 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -596,6 +596,8 @@ enum { TCA_FLOWER_L2_MISS, /* u8 */ + TCA_FLOWER_KEY_CFM, /* nested */ + __TCA_FLOWER_MAX, }; @@ -704,6 +706,13 @@ enum { TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST = (1 << 1), }; +enum { + TCA_FLOWER_KEY_CFM_OPT_UNSPEC, + TCA_FLOWER_KEY_CFM_MD_LEVEL, + TCA_FLOWER_KEY_CFM_OPCODE, + TCA_FLOWER_KEY_CFM_OPT_MAX, +}; + #define TCA_FLOWER_MASK_FLAGS_RANGE (1 << 0) /* Range-based match */ /* Match-all classifier */ diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index e02ecabbb75c..56065cc5a661 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include @@ -71,6 +72,7 @@ struct fl_flow_key { struct flow_dissector_key_num_of_vlans num_of_vlans; struct flow_dissector_key_pppoe pppoe; struct flow_dissector_key_l2tpv3 l2tpv3; + struct flow_dissector_key_cfm cfm; } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */ struct fl_flow_mask_range { @@ -725,6 +727,7 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_PPP_PROTO] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_L2TPV3_SID] = { .type = NLA_U32 }, [TCA_FLOWER_L2_MISS] = NLA_POLICY_MAX(NLA_U8, 1), + [TCA_FLOWER_KEY_CFM] = { .type = NLA_NESTED }, }; static const struct nla_policy @@ -773,6 +776,12 @@ mpls_stack_entry_policy[TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX + 1] = { [TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL] = { .type = NLA_U32 }, }; +static const struct nla_policy cfm_opt_policy[TCA_FLOWER_KEY_CFM_OPT_MAX] = { + [TCA_FLOWER_KEY_CFM_MD_LEVEL] = NLA_POLICY_MAX(NLA_U8, + FLOW_DIS_CFM_MDL_MAX), + [TCA_FLOWER_KEY_CFM_OPCODE] = { .type = NLA_U8 }, +}; + static void fl_set_key_val(struct nlattr **tb, void *val, int val_type, void *mask, int mask_type, int len) @@ -1660,6 +1669,53 @@ static bool is_vlan_key(struct nlattr *tb, __be16 *ethertype, return false; } +static void fl_set_key_cfm_md_level(struct nlattr **tb, + struct fl_flow_key *key, + struct fl_flow_key *mask, + struct netlink_ext_ack *extack) +{ + u8 level; + + if (!tb[TCA_FLOWER_KEY_CFM_MD_LEVEL]) + return; + + level = nla_get_u8(tb[TCA_FLOWER_KEY_CFM_MD_LEVEL]); + key->cfm.mdl_ver = FIELD_PREP(FLOW_DIS_CFM_MDL_MASK, level); + mask->cfm.mdl_ver = FLOW_DIS_CFM_MDL_MASK; +} + +static void fl_set_key_cfm_opcode(struct nlattr **tb, + struct fl_flow_key *key, + struct fl_flow_key *mask, + struct netlink_ext_ack *extack) +{ + fl_set_key_val(tb, &key->cfm.opcode, TCA_FLOWER_KEY_CFM_OPCODE, + &mask->cfm.opcode, TCA_FLOWER_UNSPEC, + sizeof(key->cfm.opcode)); +} + +static int fl_set_key_cfm(struct nlattr **tb, + struct fl_flow_key *key, + struct fl_flow_key *mask, + struct netlink_ext_ack *extack) +{ + struct nlattr *nla_cfm_opt[TCA_FLOWER_KEY_CFM_OPT_MAX]; + int err; + + if (!tb[TCA_FLOWER_KEY_CFM]) + return 0; + + err = nla_parse_nested(nla_cfm_opt, TCA_FLOWER_KEY_CFM_OPT_MAX, + tb[TCA_FLOWER_KEY_CFM], cfm_opt_policy, extack); + if (err < 0) + return err; + + fl_set_key_cfm_opcode(nla_cfm_opt, key, mask, extack); + fl_set_key_cfm_md_level(nla_cfm_opt, key, mask, extack); + + return 0; +} + static int fl_set_key(struct net *net, struct nlattr **tb, struct fl_flow_key *key, struct fl_flow_key *mask, struct netlink_ext_ack *extack) @@ -1814,6 +1870,10 @@ static int fl_set_key(struct net *net, struct nlattr **tb, TCA_FLOWER_KEY_L2TPV3_SID, &mask->l2tpv3.session_id, TCA_FLOWER_UNSPEC, sizeof(key->l2tpv3.session_id)); + } else if (key->basic.n_proto == htons(ETH_P_CFM)) { + ret = fl_set_key_cfm(tb, key, mask, extack); + if (ret) + return ret; } if (key->basic.ip_proto == IPPROTO_TCP || @@ -1996,6 +2056,8 @@ static void fl_init_dissector(struct flow_dissector *dissector, FLOW_DISSECTOR_KEY_PPPOE, pppoe); FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_L2TPV3, l2tpv3); + FL_KEY_SET_IF_MASKED(mask, keys, cnt, + FLOW_DISSECTOR_KEY_CFM, cfm); skb_flow_dissector_init(dissector, keys, cnt); } @@ -3029,6 +3091,43 @@ nla_put_failure: return -EMSGSIZE; } +static int fl_dump_key_cfm(struct sk_buff *skb, + struct flow_dissector_key_cfm *key, + struct flow_dissector_key_cfm *mask) +{ + struct nlattr *opts; + int err; + u8 mdl; + + if (!memchr_inv(mask, 0, sizeof(*mask))) + return 0; + + opts = nla_nest_start(skb, TCA_FLOWER_KEY_CFM); + if (!opts) + return -EMSGSIZE; + + if (FIELD_GET(FLOW_DIS_CFM_MDL_MASK, mask->mdl_ver)) { + mdl = FIELD_GET(FLOW_DIS_CFM_MDL_MASK, key->mdl_ver); + err = nla_put_u8(skb, TCA_FLOWER_KEY_CFM_MD_LEVEL, mdl); + if (err) + goto err_cfm_opts; + } + + if (mask->opcode) { + err = nla_put_u8(skb, TCA_FLOWER_KEY_CFM_OPCODE, key->opcode); + if (err) + goto err_cfm_opts; + } + + nla_nest_end(skb, opts); + + return 0; + +err_cfm_opts: + nla_nest_cancel(skb, opts); + return err; +} + static int fl_dump_key_options(struct sk_buff *skb, int enc_opt_type, struct flow_dissector_key_enc_opts *enc_opts) { @@ -3316,6 +3415,9 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net, sizeof(key->hash.hash))) goto nla_put_failure; + if (fl_dump_key_cfm(skb, &key->cfm, &mask->cfm)) + goto nla_put_failure; + return 0; nla_put_failure: -- cgit v1.2.3 From 2ad66fcb2fded5359a676f7146cf442641d28307 Mon Sep 17 00:00:00 2001 From: Gilad Itzkovitch Date: Thu, 18 May 2023 12:07:23 +1200 Subject: wifi: cfg80211: S1G rate information and calculations Increase the size of S1G rate_info flags to support S1G and add flags for new S1G MCS and the supported bandwidths. Also, include S1G rate information to netlink STA rate message. Lastly, add rate calculation function for S1G MCS. Signed-off-by: Gilad Itzkovitch Link: https://lore.kernel.org/r/20230518000723.991912-1-gilad.itzkovitch@morsemicro.com Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 18 +++++-- include/uapi/linux/nl80211.h | 14 ++++++ net/wireless/nl80211.c | 23 +++++++++ net/wireless/util.c | 110 +++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 162 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 1b8619685bf6..5d04e7eed43d 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1702,6 +1702,7 @@ int cfg80211_check_station_change(struct wiphy *wiphy, * @RATE_INFO_FLAGS_EDMG: 60GHz MCS in EDMG mode * @RATE_INFO_FLAGS_EXTENDED_SC_DMG: 60GHz extended SC MCS * @RATE_INFO_FLAGS_EHT_MCS: EHT MCS information + * @RATE_INFO_FLAGS_S1G_MCS: MCS field filled with S1G MCS */ enum rate_info_flags { RATE_INFO_FLAGS_MCS = BIT(0), @@ -1712,6 +1713,7 @@ enum rate_info_flags { RATE_INFO_FLAGS_EDMG = BIT(5), RATE_INFO_FLAGS_EXTENDED_SC_DMG = BIT(6), RATE_INFO_FLAGS_EHT_MCS = BIT(7), + RATE_INFO_FLAGS_S1G_MCS = BIT(8), }; /** @@ -1728,6 +1730,11 @@ enum rate_info_flags { * @RATE_INFO_BW_HE_RU: bandwidth determined by HE RU allocation * @RATE_INFO_BW_320: 320 MHz bandwidth * @RATE_INFO_BW_EHT_RU: bandwidth determined by EHT RU allocation + * @RATE_INFO_BW_1: 1 MHz bandwidth + * @RATE_INFO_BW_2: 2 MHz bandwidth + * @RATE_INFO_BW_4: 4 MHz bandwidth + * @RATE_INFO_BW_8: 8 MHz bandwidth + * @RATE_INFO_BW_16: 16 MHz bandwidth */ enum rate_info_bw { RATE_INFO_BW_20 = 0, @@ -1739,6 +1746,11 @@ enum rate_info_bw { RATE_INFO_BW_HE_RU, RATE_INFO_BW_320, RATE_INFO_BW_EHT_RU, + RATE_INFO_BW_1, + RATE_INFO_BW_2, + RATE_INFO_BW_4, + RATE_INFO_BW_8, + RATE_INFO_BW_16, }; /** @@ -1747,8 +1759,8 @@ enum rate_info_bw { * Information about a receiving or transmitting bitrate * * @flags: bitflag of flags from &enum rate_info_flags - * @mcs: mcs index if struct describes an HT/VHT/HE rate * @legacy: bitrate in 100kbit/s for 802.11abg + * @mcs: mcs index if struct describes an HT/VHT/HE/EHT/S1G rate * @nss: number of streams (VHT & HE only) * @bw: bandwidth (from &enum rate_info_bw) * @he_gi: HE guard interval (from &enum nl80211_he_gi) @@ -1761,9 +1773,9 @@ enum rate_info_bw { * only valid if bw is %RATE_INFO_BW_EHT_RU) */ struct rate_info { - u8 flags; - u8 mcs; + u16 flags; u16 legacy; + u8 mcs; u8 nss; u8 bw; u8 he_gi; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index c59fec406da5..435c4ac5d9bf 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3667,6 +3667,13 @@ enum nl80211_eht_ru_alloc { * (u8, see &enum nl80211_eht_gi) * @NL80211_RATE_INFO_EHT_RU_ALLOC: EHT RU allocation, if not present then * non-OFDMA was used (u8, see &enum nl80211_eht_ru_alloc) + * @NL80211_RATE_INFO_S1G_MCS: S1G MCS index (u8, 0-10) + * @NL80211_RATE_INFO_S1G_NSS: S1G NSS value (u8, 1-4) + * @NL80211_RATE_INFO_1_MHZ_WIDTH: 1 MHz S1G rate + * @NL80211_RATE_INFO_2_MHZ_WIDTH: 2 MHz S1G rate + * @NL80211_RATE_INFO_4_MHZ_WIDTH: 4 MHz S1G rate + * @NL80211_RATE_INFO_8_MHZ_WIDTH: 8 MHz S1G rate + * @NL80211_RATE_INFO_16_MHZ_WIDTH: 16 MHz S1G rate * @__NL80211_RATE_INFO_AFTER_LAST: internal use */ enum nl80211_rate_info { @@ -3693,6 +3700,13 @@ enum nl80211_rate_info { NL80211_RATE_INFO_EHT_NSS, NL80211_RATE_INFO_EHT_GI, NL80211_RATE_INFO_EHT_RU_ALLOC, + NL80211_RATE_INFO_S1G_MCS, + NL80211_RATE_INFO_S1G_NSS, + NL80211_RATE_INFO_1_MHZ_WIDTH, + NL80211_RATE_INFO_2_MHZ_WIDTH, + NL80211_RATE_INFO_4_MHZ_WIDTH, + NL80211_RATE_INFO_8_MHZ_WIDTH, + NL80211_RATE_INFO_16_MHZ_WIDTH, /* keep last */ __NL80211_RATE_INFO_AFTER_LAST, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 772671b9bc42..f962765f7e0f 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -6368,12 +6368,27 @@ bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info, int attr) return false; switch (info->bw) { + case RATE_INFO_BW_1: + rate_flg = NL80211_RATE_INFO_1_MHZ_WIDTH; + break; + case RATE_INFO_BW_2: + rate_flg = NL80211_RATE_INFO_2_MHZ_WIDTH; + break; + case RATE_INFO_BW_4: + rate_flg = NL80211_RATE_INFO_4_MHZ_WIDTH; + break; case RATE_INFO_BW_5: rate_flg = NL80211_RATE_INFO_5_MHZ_WIDTH; break; + case RATE_INFO_BW_8: + rate_flg = NL80211_RATE_INFO_8_MHZ_WIDTH; + break; case RATE_INFO_BW_10: rate_flg = NL80211_RATE_INFO_10_MHZ_WIDTH; break; + case RATE_INFO_BW_16: + rate_flg = NL80211_RATE_INFO_16_MHZ_WIDTH; + break; default: WARN_ON(1); fallthrough; @@ -6432,6 +6447,14 @@ bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info, int attr) nla_put_u8(msg, NL80211_RATE_INFO_HE_RU_ALLOC, info->he_ru_alloc)) return false; + } else if (info->flags & RATE_INFO_FLAGS_S1G_MCS) { + if (nla_put_u8(msg, NL80211_RATE_INFO_S1G_MCS, info->mcs)) + return false; + if (nla_put_u8(msg, NL80211_RATE_INFO_S1G_NSS, info->nss)) + return false; + if (info->flags & RATE_INFO_FLAGS_SHORT_GI && + nla_put_flag(msg, NL80211_RATE_INFO_SHORT_GI)) + return false; } else if (info->flags & RATE_INFO_FLAGS_EHT_MCS) { if (nla_put_u8(msg, NL80211_RATE_INFO_EHT_MCS, info->mcs)) return false; diff --git a/net/wireless/util.c b/net/wireless/util.c index 3bc0c3072e78..610a867c14f7 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1646,6 +1646,114 @@ static u32 cfg80211_calculate_bitrate_eht(struct rate_info *rate) return result / 10000; } +static u32 cfg80211_calculate_bitrate_s1g(struct rate_info *rate) +{ + /* For 1, 2, 4, 8 and 16 MHz channels */ + static const u32 base[5][11] = { + { 300000, + 600000, + 900000, + 1200000, + 1800000, + 2400000, + 2700000, + 3000000, + 3600000, + 4000000, + /* MCS 10 supported in 1 MHz only */ + 150000, + }, + { 650000, + 1300000, + 1950000, + 2600000, + 3900000, + 5200000, + 5850000, + 6500000, + 7800000, + /* MCS 9 not valid */ + }, + { 1350000, + 2700000, + 4050000, + 5400000, + 8100000, + 10800000, + 12150000, + 13500000, + 16200000, + 18000000, + }, + { 2925000, + 5850000, + 8775000, + 11700000, + 17550000, + 23400000, + 26325000, + 29250000, + 35100000, + 39000000, + }, + { 8580000, + 11700000, + 17550000, + 23400000, + 35100000, + 46800000, + 52650000, + 58500000, + 70200000, + 78000000, + }, + }; + u32 bitrate; + /* default is 1 MHz index */ + int idx = 0; + + if (rate->mcs >= 11) + goto warn; + + switch (rate->bw) { + case RATE_INFO_BW_16: + idx = 4; + break; + case RATE_INFO_BW_8: + idx = 3; + break; + case RATE_INFO_BW_4: + idx = 2; + break; + case RATE_INFO_BW_2: + idx = 1; + break; + case RATE_INFO_BW_1: + idx = 0; + break; + case RATE_INFO_BW_5: + case RATE_INFO_BW_10: + case RATE_INFO_BW_20: + case RATE_INFO_BW_40: + case RATE_INFO_BW_80: + case RATE_INFO_BW_160: + default: + goto warn; + } + + bitrate = base[idx][rate->mcs]; + bitrate *= rate->nss; + + if (rate->flags & RATE_INFO_FLAGS_SHORT_GI) + bitrate = (bitrate / 9) * 10; + /* do NOT round down here */ + return (bitrate + 50000) / 100000; +warn: + WARN_ONCE(1, "invalid rate bw=%d, mcs=%d, nss=%d\n", + rate->bw, rate->mcs, rate->nss); + return 0; +} + u32 cfg80211_calculate_bitrate(struct rate_info *rate) { if (rate->flags & RATE_INFO_FLAGS_MCS) @@ -1662,6 +1770,8 @@ u32 cfg80211_calculate_bitrate(struct rate_info *rate) return cfg80211_calculate_bitrate_he(rate); if (rate->flags & RATE_INFO_FLAGS_EHT_MCS) return cfg80211_calculate_bitrate_eht(rate); + if (rate->flags & RATE_INFO_FLAGS_S1G_MCS) + return cfg80211_calculate_bitrate_s1g(rate); return rate->legacy; } -- cgit v1.2.3 From 6cf963edbbd3b279185e28e4864c9698ffaa23c3 Mon Sep 17 00:00:00 2001 From: Ilan Peer Date: Thu, 8 Jun 2023 16:36:10 +0300 Subject: wifi: cfg80211: Support association to AP MLD with disabled links An AP part of an AP MLD might be temporarily disabled, and might be enabled later. Such a link should be included in the association exchange, but should not be used until enabled. Extend the NL80211_CMD_ASSOCIATE to also indicate disabled links. Signed-off-by: Ilan Peer Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230608163202.c4c61ee4c4a5.I784ef4a0d619fc9120514b5615458fbef3b3684a@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 5 ++++- include/uapi/linux/nl80211.h | 7 ++++++- net/wireless/nl80211.c | 13 ++++++++++++- 3 files changed, 22 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 5d04e7eed43d..388f2a3851a2 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -7,7 +7,7 @@ * Copyright 2006-2010 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2021 Intel Corporation + * Copyright (C) 2018-2021, 2023 Intel Corporation */ #include @@ -2882,11 +2882,14 @@ struct cfg80211_auth_request { * if this is %NULL for a link, that link is not requested * @elems: extra elements for the per-STA profile for this link * @elems_len: length of the elements + * @disabled: If set this link should be included during association etc. but it + * should not be used until enabled by the AP MLD. */ struct cfg80211_assoc_link { struct cfg80211_bss *bss; const u8 *elems; size_t elems_len; + bool disabled; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 435c4ac5d9bf..03939bdb0e48 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -11,7 +11,7 @@ * Copyright 2008 Jouni Malinen * Copyright 2008 Colin McCabe * Copyright 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2022 Intel Corporation + * Copyright (C) 2018-2023 Intel Corporation * * Permission to use, copy, modify, and/or distribute this software for any * purpose with or without fee is hereby granted, provided that the above @@ -2805,6 +2805,9 @@ enum nl80211_commands { * index. If the userspace includes more RNR elements than number of * MBSSID elements then these will be added in every EMA beacon. * + * @NL80211_ATTR_MLO_LINK_DISABLED: Flag attribute indicating that the link is + * disabled. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3341,6 +3344,8 @@ enum nl80211_attrs { NL80211_ATTR_EMA_RNR_ELEMS, + NL80211_ATTR_MLO_LINK_DISABLED, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index f962765f7e0f..ec7d467cb096 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -5,7 +5,7 @@ * Copyright 2006-2010 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2022 Intel Corporation + * Copyright (C) 2018-2023 Intel Corporation */ #include @@ -816,6 +816,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_MAX_HW_TIMESTAMP_PEERS] = { .type = NLA_U16 }, [NL80211_ATTR_HW_TIMESTAMP_ENABLED] = { .type = NLA_FLAG }, [NL80211_ATTR_EMA_RNR_ELEMS] = { .type = NLA_NESTED }, + [NL80211_ATTR_MLO_LINK_DISABLED] = { .type = NLA_FLAG }, }; /* policy for the key attributes */ @@ -11138,6 +11139,9 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) goto free; } } + + req.links[link_id].disabled = + nla_get_flag(attrs[NL80211_ATTR_MLO_LINK_DISABLED]); } if (!req.links[req.link_id].bss) { @@ -11152,6 +11156,13 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) goto free; } + if (req.links[req.link_id].disabled) { + GENL_SET_ERR_MSG(info, + "cannot have assoc link disabled"); + err = -EINVAL; + goto free; + } + kfree(attrs); attrs = NULL; } else { -- cgit v1.2.3 From 2d8c9dcf7158060fcec9f891c0292ffdb4397523 Mon Sep 17 00:00:00 2001 From: Wen Yang Date: Thu, 15 Jun 2023 02:40:28 +0800 Subject: eventfd: add a uapi header for eventfd userspace APIs Create a uapi header include/uapi/linux/eventfd.h, move the associated flags to the uapi header, and include it from linux/eventfd.h. Suggested-by: Christian Brauner Signed-off-by: Wen Yang Reviewed-by: Matthew Wilcox (Oracle) Cc: Alexander Viro Cc: Jens Axboe Cc: Christian Brauner Cc: Christoph Hellwig Cc: Dylan Yudaken Cc: David Woodhouse Cc: Matthew Wilcox Cc: Eric Biggers Cc: linux-fsdevel@vger.kernel.org Cc: linux-kernel@vger.kernel.org Message-Id: Signed-off-by: Christian Brauner --- include/linux/eventfd.h | 6 +----- include/uapi/linux/eventfd.h | 11 +++++++++++ 2 files changed, 12 insertions(+), 5 deletions(-) create mode 100644 include/uapi/linux/eventfd.h (limited to 'include/uapi') diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index 98d31cdaca40..b9d83652c097 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -9,12 +9,12 @@ #ifndef _LINUX_EVENTFD_H #define _LINUX_EVENTFD_H -#include #include #include #include #include #include +#include /* * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining @@ -23,10 +23,6 @@ * from eventfd, in order to leave a free define-space for * shared O_* flags. */ -#define EFD_SEMAPHORE (1 << 0) -#define EFD_CLOEXEC O_CLOEXEC -#define EFD_NONBLOCK O_NONBLOCK - #define EFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK) #define EFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS | EFD_SEMAPHORE) diff --git a/include/uapi/linux/eventfd.h b/include/uapi/linux/eventfd.h new file mode 100644 index 000000000000..2eb9ab6c32f3 --- /dev/null +++ b/include/uapi/linux/eventfd.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_EVENTFD_H +#define _UAPI_LINUX_EVENTFD_H + +#include + +#define EFD_SEMAPHORE (1 << 0) +#define EFD_CLOEXEC O_CLOEXEC +#define EFD_NONBLOCK O_NONBLOCK + +#endif /* _UAPI_LINUX_EVENTFD_H */ -- cgit v1.2.3 From 6f582513ad15de729ee5c91dfef946f3c266a207 Mon Sep 17 00:00:00 2001 From: James Zhu Date: Wed, 17 May 2023 16:19:51 -0400 Subject: drm/amdkfd: add event age tracking Add event age tracking Signed-off-by: James Zhu Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- include/uapi/linux/kfd_ioctl.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 1781e7669982..93f1c0bc5caf 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -320,12 +320,20 @@ struct kfd_hsa_hw_exception_data { __u32 gpu_id; }; +/* hsa signal event data */ +struct kfd_hsa_signal_event_data { + __u64 last_event_age; /* to and from KFD */ +}; + /* Event data */ struct kfd_event_data { union { + /* From KFD */ struct kfd_hsa_memory_exception_data memory_exception_data; struct kfd_hsa_hw_exception_data hw_exception_data; - }; /* From KFD */ + /* To and From KFD */ + struct kfd_hsa_signal_event_data signal_event_data; + }; __u64 kfd_event_data_ext; /* pointer to an extension structure for future exception types */ __u32 event_id; /* to KFD */ -- cgit v1.2.3 From d297eedf83f5af96751c0da1e4355c19244a55a2 Mon Sep 17 00:00:00 2001 From: James Zhu Date: Wed, 7 Jun 2023 13:27:40 -0400 Subject: drm/amdkfd: bump kfd ioctl minor version for event age availability Bump the minor version to declare event age tracking feature is now available. In kernel amdgpu driver, kfd_wait_on_events is used to support user space signal event wait function. For multiple threads waiting on same event scenery, race condition could occur since some threads after checking signal condition, before calling kfd_wait_on_events, the event interrupt could be fired and wake up other thread which are sleeping on this event. Then those threads could fall into sleep without waking up again. Adding event age tracking in both kernel and user mode, will help avoiding this race condition. Proposed ROCT-Thunk-Interface: https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface/commit/efdbf6cfbc026bd68ac3c35d00dacf84370eb81e https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface/commit/1820ae0a2db85b6f584611dc0cde1a00e7c22915 Proposed ROCR-Runtime: https://github.com/RadeonOpenCompute/ROCR-Runtime/compare/master...zhums:ROCR-Runtime:new_event_wait_review https://github.com/RadeonOpenCompute/ROCR-Runtime/commit/e1f5bdb88eb882ac798aeca2c00ea3fbb2dba459 https://github.com/RadeonOpenCompute/ROCR-Runtime/commit/7d26afd14107b5c2a754c1a3f415d89f3aabb503 Signed-off-by: James Zhu 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 93f1c0bc5caf..eeb2fdcbdcb7 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -39,9 +39,10 @@ * - 1.11 - Add unified memory for ctx save/restore area * - 1.12 - Add DMA buf export ioctl * - 1.13 - Add debugger API + * - 1.14 - Update kfd_event_data */ #define KFD_IOCTL_MAJOR_VERSION 1 -#define KFD_IOCTL_MINOR_VERSION 13 +#define KFD_IOCTL_MINOR_VERSION 14 struct kfd_ioctl_get_version_args { __u32 major_version; /* from KFD */ -- cgit v1.2.3 From 065563b20a664a6575dc158688dfb0e121c25b38 Mon Sep 17 00:00:00 2001 From: Veerendranath Jakkam Date: Fri, 17 Mar 2023 19:51:53 +0530 Subject: wifi: cfg80211/nl80211: Add support to indicate STA MLD setup links removal STA MLD setup links may get removed if AP MLD remove the corresponding affiliated APs with Multi-Link reconfiguration as described in P802.11be_D3.0, section 35.3.6.2.2 Removing affiliated APs. Currently, there is no support to notify such operation to cfg80211 and userspace. Add support for the drivers to indicate STA MLD setup links removal to cfg80211 and notify the same to userspace. Upon receiving such indication from the driver, clear the MLO links information of the removed links in the WDEV. Signed-off-by: Veerendranath Jakkam Link: https://lore.kernel.org/r/20230317142153.237900-1-quic_vjakkam@quicinc.com [rename function and attribute, fix kernel-doc] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 13 ++++++++ include/uapi/linux/nl80211.h | 7 +++++ net/wireless/core.h | 1 + net/wireless/nl80211.c | 70 ++++++++++++++++++++++++++++++++++++++++++++ net/wireless/sme.c | 15 ++++++++++ net/wireless/trace.h | 15 ++++++++++ 6 files changed, 121 insertions(+) (limited to 'include/uapi') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 9972de114d73..3a736f9286b0 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -9205,4 +9205,17 @@ static inline int cfg80211_color_change_notify(struct net_device *dev) bool cfg80211_valid_disable_subchannel_bitmap(u16 *bitmap, const struct cfg80211_chan_def *chandef); +/** + * cfg80211_links_removed - Notify about removed STA MLD setup links. + * @dev: network device. + * @link_mask: BIT mask of removed STA MLD setup link IDs. + * + * Inform cfg80211 and the userspace about removed STA MLD setup links due to + * AP MLD removing the corresponding affiliated APs with Multi-Link + * reconfiguration. Note that it's not valid to remove all links, in this + * case disconnect instead. + * Also note that the wdev mutex must be held. + */ +void cfg80211_links_removed(struct net_device *dev, u16 link_mask); + #endif /* __NET_CFG80211_H */ diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 03939bdb0e48..3190d34269ef 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1309,6 +1309,11 @@ * The number of peers that HW timestamping can be enabled for concurrently * is indicated by %NL80211_ATTR_MAX_HW_TIMESTAMP_PEERS. * + * @NL80211_CMD_LINKS_REMOVED: Notify userspace about the removal of STA MLD + * setup links due to AP MLD removing the corresponding affiliated APs with + * Multi-Link reconfiguration. %NL80211_ATTR_MLO_LINKS is used to provide + * information about the removed STA MLD setup links. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -1562,6 +1567,8 @@ enum nl80211_commands { NL80211_CMD_SET_HW_TIMESTAMP, + NL80211_CMD_LINKS_REMOVED, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ diff --git a/net/wireless/core.h b/net/wireless/core.h index 291c6d83d56f..8a807b609ef7 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -576,5 +576,6 @@ void cfg80211_remove_link(struct wireless_dev *wdev, unsigned int link_id); void cfg80211_remove_links(struct wireless_dev *wdev); int cfg80211_remove_virtual_intf(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev); +void cfg80211_wdev_release_link_bsses(struct wireless_dev *wdev, u16 link_mask); #endif /* __NET_WIRELESS_CORE_H */ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 7b547aeb52f1..0da2e6a2a7ea 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -18288,6 +18288,76 @@ void nl80211_send_disconnected(struct cfg80211_registered_device *rdev, nlmsg_free(msg); } +void cfg80211_links_removed(struct net_device *dev, u16 link_mask) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct wiphy *wiphy = wdev->wiphy; + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); + struct sk_buff *msg; + struct nlattr *links; + void *hdr; + + ASSERT_WDEV_LOCK(wdev); + trace_cfg80211_links_removed(dev, link_mask); + + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION && + wdev->iftype != NL80211_IFTYPE_P2P_CLIENT)) + return; + + if (WARN_ON(!wdev->valid_links || !link_mask || + (wdev->valid_links & link_mask) != link_mask || + wdev->valid_links == link_mask)) + return; + + cfg80211_wdev_release_link_bsses(wdev, link_mask); + wdev->valid_links &= ~link_mask; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_LINKS_REMOVED); + if (!hdr) { + nlmsg_free(msg); + return; + } + + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex)) + goto nla_put_failure; + + links = nla_nest_start(msg, NL80211_ATTR_MLO_LINKS); + if (!links) + goto nla_put_failure; + + while (link_mask) { + struct nlattr *link; + int link_id = __ffs(link_mask); + + link = nla_nest_start(msg, link_id + 1); + if (!link) + goto nla_put_failure; + + if (nla_put_u8(msg, NL80211_ATTR_MLO_LINK_ID, link_id)) + goto nla_put_failure; + + nla_nest_end(msg, link); + link_mask &= ~(1 << link_id); + } + + nla_nest_end(msg, links); + + genlmsg_end(msg, hdr); + + genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0, + NL80211_MCGRP_MLME, GFP_KERNEL); + return; + + nla_put_failure: + nlmsg_free(msg); +} +EXPORT_SYMBOL(cfg80211_links_removed); + void nl80211_send_ibss_bssid(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *bssid, gfp_t gfp) diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 247369004aaa..9bba233b5a6e 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -491,6 +491,21 @@ static void cfg80211_wdev_release_bsses(struct wireless_dev *wdev) } } +void cfg80211_wdev_release_link_bsses(struct wireless_dev *wdev, u16 link_mask) +{ + unsigned int link; + + for_each_valid_link(wdev, link) { + if (!wdev->links[link].client.current_bss || + !(link_mask & BIT(link))) + continue; + cfg80211_unhold_bss(wdev->links[link].client.current_bss); + cfg80211_put_bss(wdev->wiphy, + &wdev->links[link].client.current_bss->pub); + wdev->links[link].client.current_bss = NULL; + } +} + static int cfg80211_sme_get_conn_ies(struct wireless_dev *wdev, const u8 *ies, size_t ies_len, const u8 **out_ies, size_t *out_ies_len) diff --git a/net/wireless/trace.h b/net/wireless/trace.h index e63990b81249..617c0d0dfa96 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -3966,6 +3966,21 @@ TRACE_EVENT(rdev_set_hw_timestamp, __entry->enable) ); +TRACE_EVENT(cfg80211_links_removed, + TP_PROTO(struct net_device *netdev, u16 link_mask), + TP_ARGS(netdev, link_mask), + TP_STRUCT__entry( + NETDEV_ENTRY + __field(u16, link_mask) + ), + TP_fast_assign( + NETDEV_ASSIGN; + __entry->link_mask = link_mask; + ), + TP_printk(NETDEV_PR_FMT ", link_mask:%u", NETDEV_PR_ARG, + __entry->link_mask) +); + #endif /* !__RDEV_OPS_TRACE || TRACE_HEADER_MULTI_READ */ #undef TRACE_INCLUDE_PATH -- cgit v1.2.3 From c3b60ab7a4dff6e6e608e685b70ddc3d6b2aca81 Mon Sep 17 00:00:00 2001 From: Rahul Rameshbabu Date: Mon, 12 Jun 2023 14:14:56 -0700 Subject: ptp: Add .getmaxphase callback to ptp_clock_info Enables advertisement of the maximum offset supported by the phase control functionality of PHCs. The callback is used to return an error if an offset not supported by the PHC is used in ADJ_OFFSET. The ioctls PTP_CLOCK_GETCAPS and PTP_CLOCK_GETCAPS2 now advertise the maximum offset a PHC's phase control functionality is capable of supporting. Introduce new sysfs node, max_phase_adjustment. Cc: Jakub Kicinski Cc: Shuah Khan Cc: Richard Cochran Cc: Maciek Machnikowski Signed-off-by: Rahul Rameshbabu Acked-by: Richard Cochran Signed-off-by: David S. Miller --- drivers/ptp/ptp_chardev.c | 5 ++++- drivers/ptp/ptp_clock.c | 4 ++++ drivers/ptp/ptp_sysfs.c | 12 ++++++++++++ include/linux/ptp_clock_kernel.h | 5 +++++ include/uapi/linux/ptp_clock.h | 3 ++- tools/testing/selftests/ptp/testptp.c | 6 ++++-- 6 files changed, 31 insertions(+), 4 deletions(-) (limited to 'include/uapi') diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c index af3bc65c4595..362bf756e6b7 100644 --- a/drivers/ptp/ptp_chardev.c +++ b/drivers/ptp/ptp_chardev.c @@ -136,7 +136,10 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg) caps.pps = ptp->info->pps; caps.n_pins = ptp->info->n_pins; caps.cross_timestamping = ptp->info->getcrosststamp != NULL; - caps.adjust_phase = ptp->info->adjphase != NULL; + caps.adjust_phase = ptp->info->adjphase != NULL && + ptp->info->getmaxphase != NULL; + if (caps.adjust_phase) + caps.max_phase_adj = ptp->info->getmaxphase(ptp->info); if (copy_to_user((void __user *)arg, &caps, sizeof(caps))) err = -EFAULT; break; diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index 790f9250b381..80f74e38c2da 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -135,11 +135,15 @@ static int ptp_clock_adjtime(struct posix_clock *pc, struct __kernel_timex *tx) ptp->dialed_frequency = tx->freq; } else if (tx->modes & ADJ_OFFSET) { if (ops->adjphase) { + s32 max_phase_adj = ops->getmaxphase(ops); s32 offset = tx->offset; if (!(tx->modes & ADJ_NANO)) offset *= NSEC_PER_USEC; + if (offset > max_phase_adj || offset < -max_phase_adj) + return -ERANGE; + err = ops->adjphase(ops, offset); } } else if (tx->modes == 0) { diff --git a/drivers/ptp/ptp_sysfs.c b/drivers/ptp/ptp_sysfs.c index f30b0a439470..77219cdcd683 100644 --- a/drivers/ptp/ptp_sysfs.c +++ b/drivers/ptp/ptp_sysfs.c @@ -18,6 +18,17 @@ static ssize_t clock_name_show(struct device *dev, } static DEVICE_ATTR_RO(clock_name); +static ssize_t max_phase_adjustment_show(struct device *dev, + struct device_attribute *attr, + char *page) +{ + struct ptp_clock *ptp = dev_get_drvdata(dev); + + return snprintf(page, PAGE_SIZE - 1, "%d\n", + ptp->info->getmaxphase(ptp->info)); +} +static DEVICE_ATTR_RO(max_phase_adjustment); + #define PTP_SHOW_INT(name, var) \ static ssize_t var##_show(struct device *dev, \ struct device_attribute *attr, char *page) \ @@ -309,6 +320,7 @@ static struct attribute *ptp_attrs[] = { &dev_attr_clock_name.attr, &dev_attr_max_adjustment.attr, + &dev_attr_max_phase_adjustment.attr, &dev_attr_n_alarms.attr, &dev_attr_n_external_timestamps.attr, &dev_attr_n_periodic_outputs.attr, diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index f8e8443a8b35..1ef4e0f9bd2a 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -82,6 +82,10 @@ struct ptp_system_timestamp { * parameter delta: PHC servo phase adjustment target * in nanoseconds. * + * @getmaxphase: Advertises maximum offset that can be provided + * to the hardware clock's phase control functionality + * through adjphase. + * * @adjtime: Shifts the time of the hardware clock. * parameter delta: Desired change in nanoseconds. * @@ -171,6 +175,7 @@ struct ptp_clock_info { struct ptp_pin_desc *pin_config; int (*adjfine)(struct ptp_clock_info *ptp, long scaled_ppm); int (*adjphase)(struct ptp_clock_info *ptp, s32 phase); + s32 (*getmaxphase)(struct ptp_clock_info *ptp); int (*adjtime)(struct ptp_clock_info *ptp, s64 delta); int (*gettime64)(struct ptp_clock_info *ptp, struct timespec64 *ts); int (*gettimex64)(struct ptp_clock_info *ptp, struct timespec64 *ts, diff --git a/include/uapi/linux/ptp_clock.h b/include/uapi/linux/ptp_clock.h index 1d108d597f66..05cc35fc94ac 100644 --- a/include/uapi/linux/ptp_clock.h +++ b/include/uapi/linux/ptp_clock.h @@ -95,7 +95,8 @@ struct ptp_clock_caps { int cross_timestamping; /* Whether the clock supports adjust phase */ int adjust_phase; - int rsv[12]; /* Reserved for future use. */ + int max_phase_adj; /* Maximum phase adjustment in nanoseconds. */ + int rsv[11]; /* Reserved for future use. */ }; struct ptp_extts_request { diff --git a/tools/testing/selftests/ptp/testptp.c b/tools/testing/selftests/ptp/testptp.c index cc535f76db99..e9438a1862ad 100644 --- a/tools/testing/selftests/ptp/testptp.c +++ b/tools/testing/selftests/ptp/testptp.c @@ -292,7 +292,8 @@ int main(int argc, char *argv[]) " %d pulse per second\n" " %d programmable pins\n" " %d cross timestamping\n" - " %d adjust_phase\n", + " %d adjust_phase\n" + " %d maximum phase adjustment (ns)\n", caps.max_adj, caps.n_alarm, caps.n_ext_ts, @@ -300,7 +301,8 @@ int main(int argc, char *argv[]) caps.pps, caps.n_pins, caps.cross_timestamping, - caps.adjust_phase); + caps.adjust_phase, + caps.max_phase_adj); } } -- cgit v1.2.3 From 95a55437dc49fb3342c82e61f5472a71c63d9ed0 Mon Sep 17 00:00:00 2001 From: Michael Schmitz Date: Wed, 21 Jun 2023 08:17:24 +1200 Subject: block: change all __u32 annotations to __be32 in affs_hardblocks.h The Amiga partition parser module uses signed int for partition sector address and count, which will overflow for disks larger than 1 TB. Use u64 as type for sector address and size to allow using disks up to 2 TB without LBD support, and disks larger than 2 TB with LBD. The RBD format allows to specify disk sizes up to 2^128 bytes (though native OS limitations reduce this somewhat, to max 2^68 bytes), so check for u64 overflow carefully to protect against overflowing sector_t. This bug was reported originally in 2012, and the fix was created by the RDB author, Joanne Dow . A patch had been discussed and reviewed on linux-m68k at that time but never officially submitted (now resubmitted as patch 1 of this series). Patch 3 (this series) adds additional error checking and warning messages. One of the error checks now makes use of the previously unused rdb_CylBlocks field, which causes a 'sparse' warning (cast to restricted __be32). Annotate all 32 bit fields in affs_hardblocks.h as __be32, as the on-disk format of RDB and partition blocks is always big endian. Reported-by: Martin Steigerwald Closes: https://bugzilla.kernel.org/show_bug.cgi?id=43511 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Message-ID: <201206192146.09327.Martin@lichtvoll.de> Cc: # 5.2 Signed-off-by: Michael Schmitz Reviewed-by: Christoph Hellwig Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230620201725.7020-3-schmitzmic@gmail.com Signed-off-by: Jens Axboe --- include/uapi/linux/affs_hardblocks.h | 68 ++++++++++++++++++------------------ 1 file changed, 34 insertions(+), 34 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/affs_hardblocks.h b/include/uapi/linux/affs_hardblocks.h index 5e2fb8481252..a5aff2eb5f70 100644 --- a/include/uapi/linux/affs_hardblocks.h +++ b/include/uapi/linux/affs_hardblocks.h @@ -7,42 +7,42 @@ /* Just the needed definitions for the RDB of an Amiga HD. */ struct RigidDiskBlock { - __u32 rdb_ID; + __be32 rdb_ID; __be32 rdb_SummedLongs; - __s32 rdb_ChkSum; - __u32 rdb_HostID; + __be32 rdb_ChkSum; + __be32 rdb_HostID; __be32 rdb_BlockBytes; - __u32 rdb_Flags; - __u32 rdb_BadBlockList; + __be32 rdb_Flags; + __be32 rdb_BadBlockList; __be32 rdb_PartitionList; - __u32 rdb_FileSysHeaderList; - __u32 rdb_DriveInit; - __u32 rdb_Reserved1[6]; - __u32 rdb_Cylinders; - __u32 rdb_Sectors; - __u32 rdb_Heads; - __u32 rdb_Interleave; - __u32 rdb_Park; - __u32 rdb_Reserved2[3]; - __u32 rdb_WritePreComp; - __u32 rdb_ReducedWrite; - __u32 rdb_StepRate; - __u32 rdb_Reserved3[5]; - __u32 rdb_RDBBlocksLo; - __u32 rdb_RDBBlocksHi; - __u32 rdb_LoCylinder; - __u32 rdb_HiCylinder; - __u32 rdb_CylBlocks; - __u32 rdb_AutoParkSeconds; - __u32 rdb_HighRDSKBlock; - __u32 rdb_Reserved4; + __be32 rdb_FileSysHeaderList; + __be32 rdb_DriveInit; + __be32 rdb_Reserved1[6]; + __be32 rdb_Cylinders; + __be32 rdb_Sectors; + __be32 rdb_Heads; + __be32 rdb_Interleave; + __be32 rdb_Park; + __be32 rdb_Reserved2[3]; + __be32 rdb_WritePreComp; + __be32 rdb_ReducedWrite; + __be32 rdb_StepRate; + __be32 rdb_Reserved3[5]; + __be32 rdb_RDBBlocksLo; + __be32 rdb_RDBBlocksHi; + __be32 rdb_LoCylinder; + __be32 rdb_HiCylinder; + __be32 rdb_CylBlocks; + __be32 rdb_AutoParkSeconds; + __be32 rdb_HighRDSKBlock; + __be32 rdb_Reserved4; char rdb_DiskVendor[8]; char rdb_DiskProduct[16]; char rdb_DiskRevision[4]; char rdb_ControllerVendor[8]; char rdb_ControllerProduct[16]; char rdb_ControllerRevision[4]; - __u32 rdb_Reserved5[10]; + __be32 rdb_Reserved5[10]; }; #define IDNAME_RIGIDDISK 0x5244534B /* "RDSK" */ @@ -50,16 +50,16 @@ struct RigidDiskBlock { struct PartitionBlock { __be32 pb_ID; __be32 pb_SummedLongs; - __s32 pb_ChkSum; - __u32 pb_HostID; + __be32 pb_ChkSum; + __be32 pb_HostID; __be32 pb_Next; - __u32 pb_Flags; - __u32 pb_Reserved1[2]; - __u32 pb_DevFlags; + __be32 pb_Flags; + __be32 pb_Reserved1[2]; + __be32 pb_DevFlags; __u8 pb_DriveName[32]; - __u32 pb_Reserved2[15]; + __be32 pb_Reserved2[15]; __be32 pb_Environment[17]; - __u32 pb_EReserved[15]; + __be32 pb_EReserved[15]; }; #define IDNAME_PARTITION 0x50415254 /* "PART" */ -- cgit v1.2.3 From 6c5b9a3296e146cc74b1d006c6a546ea92534ade Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 19 Jun 2023 16:26:53 +0300 Subject: wifi: nl80211/reg: add no-EHT regulatory flag This just propagates to the channel flags, like no-HE and similar other flags before it. Signed-off-by: Johannes Berg Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230619161906.74ce2983aed8.Ifa343ba89c11760491daad5aee5a81209d5735a7@changeid Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 2 ++ net/wireless/reg.c | 4 +++- 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 3190d34269ef..88eb85c63029 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -4450,6 +4450,7 @@ enum nl80211_sched_scan_match_attr { * @NL80211_RRF_NO_160MHZ: 160MHz operation not allowed * @NL80211_RRF_NO_HE: HE operation not allowed * @NL80211_RRF_NO_320MHZ: 320MHz operation not allowed + * @NL80211_RRF_NO_EHT: EHT operation not allowed */ enum nl80211_reg_rule_flags { NL80211_RRF_NO_OFDM = 1<<0, @@ -4469,6 +4470,7 @@ enum nl80211_reg_rule_flags { NL80211_RRF_NO_160MHZ = 1<<16, NL80211_RRF_NO_HE = 1<<17, NL80211_RRF_NO_320MHZ = 1<<18, + NL80211_RRF_NO_EHT = 1<<19, }; #define NL80211_RRF_PASSIVE_SCAN NL80211_RRF_NO_IR diff --git a/net/wireless/reg.c b/net/wireless/reg.c index f9e03850d71b..0317cf9da307 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -5,7 +5,7 @@ * Copyright 2008-2011 Luis R. Rodriguez * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2017 Intel Deutschland GmbH - * Copyright (C) 2018 - 2022 Intel Corporation + * Copyright (C) 2018 - 2023 Intel Corporation * * Permission to use, copy, modify, and/or distribute this software for any * purpose with or without fee is hereby granted, provided that the above @@ -1587,6 +1587,8 @@ static u32 map_regdom_flags(u32 rd_flags) channel_flags |= IEEE80211_CHAN_NO_HE; if (rd_flags & NL80211_RRF_NO_320MHZ) channel_flags |= IEEE80211_CHAN_NO_320MHZ; + if (rd_flags & NL80211_RRF_NO_EHT) + channel_flags |= IEEE80211_CHAN_NO_EHT; return channel_flags; } -- cgit v1.2.3 From 360da60d6c6edb9740de7a8e6d8969d62ceff956 Mon Sep 17 00:00:00 2001 From: Selvin Xavier Date: Tue, 13 Jun 2023 11:12:23 -0700 Subject: RDMA/bnxt_re: Enable low latency push Introduce driver specific uapi functionalites. Added a alloc_page functionality for user library to allocate specific pages. Currently added support for allocating write combine pages for push functinality. This interface shall be extended for other page allocations. Allocate a WC page using the uapi hook for enabling the low latency push in Gen P5 adapters for small packets. This is supported only for the user space QPs. Link: https://lore.kernel.org/r/1686679943-17117-8-git-send-email-selvin.xavier@broadcom.com Signed-off-by: Selvin Xavier Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/bnxt_re/bnxt_re.h | 3 + drivers/infiniband/hw/bnxt_re/ib_verbs.c | 148 ++++++++++++++++++++++++++++++ drivers/infiniband/hw/bnxt_re/ib_verbs.h | 4 + drivers/infiniband/hw/bnxt_re/main.c | 20 +++- drivers/infiniband/hw/bnxt_re/qplib_res.c | 3 + drivers/infiniband/hw/bnxt_re/qplib_res.h | 3 +- include/uapi/rdma/bnxt_re-abi.h | 27 ++++++ 7 files changed, 204 insertions(+), 4 deletions(-) (limited to 'include/uapi') diff --git a/drivers/infiniband/hw/bnxt_re/bnxt_re.h b/drivers/infiniband/hw/bnxt_re/bnxt_re.h index f34fb87e3b77..9e278d23eb82 100644 --- a/drivers/infiniband/hw/bnxt_re/bnxt_re.h +++ b/drivers/infiniband/hw/bnxt_re/bnxt_re.h @@ -39,6 +39,7 @@ #ifndef __BNXT_RE_H__ #define __BNXT_RE_H__ +#include #include "hw_counters.h" #define ROCE_DRV_MODULE_NAME "bnxt_re" @@ -189,4 +190,6 @@ static inline struct device *rdev_to_dev(struct bnxt_re_dev *rdev) return &rdev->ibdev.dev; return NULL; } + +extern const struct uapi_definition bnxt_re_uapi_defs[]; #endif diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index 8e3b45d9e656..a936e0d474f9 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -61,6 +61,15 @@ #include "bnxt_re.h" #include "ib_verbs.h" + +#include +#include + +#include + +#define UVERBS_MODULE_NAME bnxt_re +#include + #include static int __from_ib_access_flags(int iflags) @@ -546,6 +555,7 @@ bnxt_re_mmap_entry_insert(struct bnxt_re_ucontext *uctx, u64 mem_offset, entry->mem_offset = mem_offset; entry->mmap_flag = mmap_flag; + entry->uctx = uctx; switch (mmap_flag) { case BNXT_RE_MMAP_SH_PAGE: @@ -553,6 +563,7 @@ bnxt_re_mmap_entry_insert(struct bnxt_re_ucontext *uctx, u64 mem_offset, &entry->rdma_entry, PAGE_SIZE, 0); break; case BNXT_RE_MMAP_UC_DB: + case BNXT_RE_MMAP_WC_DB: ret = rdma_user_mmap_entry_insert(&uctx->ib_uctx, &entry->rdma_entry, PAGE_SIZE); break; @@ -4056,6 +4067,9 @@ int bnxt_re_alloc_ucontext(struct ib_ucontext *ctx, struct ib_udata *udata) resp.comp_mask |= BNXT_RE_UCNTX_CMASK_HAVE_MODE; resp.mode = rdev->chip_ctx->modes.wqe_mode; + if (rdev->chip_ctx->modes.db_push) + resp.comp_mask |= BNXT_RE_UCNTX_CMASK_WC_DPI_ENABLED; + entry = bnxt_re_mmap_entry_insert(uctx, 0, BNXT_RE_MMAP_SH_PAGE, NULL); if (!entry) { rc = -ENOMEM; @@ -4119,6 +4133,12 @@ int bnxt_re_mmap(struct ib_ucontext *ib_uctx, struct vm_area_struct *vma) rdma_entry); switch (bnxt_entry->mmap_flag) { + case BNXT_RE_MMAP_WC_DB: + pfn = bnxt_entry->mem_offset >> PAGE_SHIFT; + ret = rdma_user_mmap_io(ib_uctx, vma, pfn, PAGE_SIZE, + pgprot_writecombine(vma->vm_page_prot), + rdma_entry); + break; case BNXT_RE_MMAP_UC_DB: pfn = bnxt_entry->mem_offset >> PAGE_SHIFT; ret = rdma_user_mmap_io(ib_uctx, vma, pfn, PAGE_SIZE, @@ -4146,3 +4166,131 @@ void bnxt_re_mmap_free(struct rdma_user_mmap_entry *rdma_entry) kfree(bnxt_entry); } + +static int UVERBS_HANDLER(BNXT_RE_METHOD_ALLOC_PAGE)(struct uverbs_attr_bundle *attrs) +{ + struct ib_uobject *uobj = uverbs_attr_get_uobject(attrs, BNXT_RE_ALLOC_PAGE_HANDLE); + enum bnxt_re_alloc_page_type alloc_type; + struct bnxt_re_user_mmap_entry *entry; + enum bnxt_re_mmap_flag mmap_flag; + struct bnxt_qplib_chip_ctx *cctx; + struct bnxt_re_ucontext *uctx; + struct bnxt_re_dev *rdev; + u64 mmap_offset; + u32 length; + u32 dpi; + u64 dbr; + int err; + + uctx = container_of(ib_uverbs_get_ucontext(attrs), struct bnxt_re_ucontext, ib_uctx); + if (IS_ERR(uctx)) + return PTR_ERR(uctx); + + err = uverbs_get_const(&alloc_type, attrs, BNXT_RE_ALLOC_PAGE_TYPE); + if (err) + return err; + + rdev = uctx->rdev; + cctx = rdev->chip_ctx; + + switch (alloc_type) { + case BNXT_RE_ALLOC_WC_PAGE: + if (cctx->modes.db_push) { + if (bnxt_qplib_alloc_dpi(&rdev->qplib_res, &uctx->wcdpi, + uctx, BNXT_QPLIB_DPI_TYPE_WC)) + return -ENOMEM; + length = PAGE_SIZE; + dpi = uctx->wcdpi.dpi; + dbr = (u64)uctx->wcdpi.umdbr; + mmap_flag = BNXT_RE_MMAP_WC_DB; + } else { + return -EINVAL; + } + + break; + + default: + return -EOPNOTSUPP; + } + + entry = bnxt_re_mmap_entry_insert(uctx, dbr, mmap_flag, &mmap_offset); + if (IS_ERR(entry)) + return PTR_ERR(entry); + + uobj->object = entry; + uverbs_finalize_uobj_create(attrs, BNXT_RE_ALLOC_PAGE_HANDLE); + err = uverbs_copy_to(attrs, BNXT_RE_ALLOC_PAGE_MMAP_OFFSET, + &mmap_offset, sizeof(mmap_offset)); + if (err) + return err; + + err = uverbs_copy_to(attrs, BNXT_RE_ALLOC_PAGE_MMAP_LENGTH, + &length, sizeof(length)); + if (err) + return err; + + err = uverbs_copy_to(attrs, BNXT_RE_ALLOC_PAGE_DPI, + &dpi, sizeof(length)); + if (err) + return err; + + return 0; +} + +static int alloc_page_obj_cleanup(struct ib_uobject *uobject, + enum rdma_remove_reason why, + struct uverbs_attr_bundle *attrs) +{ + struct bnxt_re_user_mmap_entry *entry = uobject->object; + struct bnxt_re_ucontext *uctx = entry->uctx; + + switch (entry->mmap_flag) { + case BNXT_RE_MMAP_WC_DB: + if (uctx && uctx->wcdpi.dbr) { + struct bnxt_re_dev *rdev = uctx->rdev; + + bnxt_qplib_dealloc_dpi(&rdev->qplib_res, &uctx->wcdpi); + uctx->wcdpi.dbr = NULL; + } + break; + default: + goto exit; + } + rdma_user_mmap_entry_remove(&entry->rdma_entry); +exit: + return 0; +} + +DECLARE_UVERBS_NAMED_METHOD(BNXT_RE_METHOD_ALLOC_PAGE, + UVERBS_ATTR_IDR(BNXT_RE_ALLOC_PAGE_HANDLE, + BNXT_RE_OBJECT_ALLOC_PAGE, + UVERBS_ACCESS_NEW, + UA_MANDATORY), + UVERBS_ATTR_CONST_IN(BNXT_RE_ALLOC_PAGE_TYPE, + enum bnxt_re_alloc_page_type, + UA_MANDATORY), + UVERBS_ATTR_PTR_OUT(BNXT_RE_ALLOC_PAGE_MMAP_OFFSET, + UVERBS_ATTR_TYPE(u64), + UA_MANDATORY), + UVERBS_ATTR_PTR_OUT(BNXT_RE_ALLOC_PAGE_MMAP_LENGTH, + UVERBS_ATTR_TYPE(u32), + UA_MANDATORY), + UVERBS_ATTR_PTR_OUT(BNXT_RE_ALLOC_PAGE_DPI, + UVERBS_ATTR_TYPE(u32), + UA_MANDATORY)); + +DECLARE_UVERBS_NAMED_METHOD_DESTROY(BNXT_RE_METHOD_DESTROY_PAGE, + UVERBS_ATTR_IDR(BNXT_RE_DESTROY_PAGE_HANDLE, + BNXT_RE_OBJECT_ALLOC_PAGE, + UVERBS_ACCESS_DESTROY, + UA_MANDATORY)); + +DECLARE_UVERBS_NAMED_OBJECT(BNXT_RE_OBJECT_ALLOC_PAGE, + UVERBS_TYPE_ALLOC_IDR(alloc_page_obj_cleanup), + &UVERBS_METHOD(BNXT_RE_METHOD_ALLOC_PAGE), + &UVERBS_METHOD(BNXT_RE_METHOD_DESTROY_PAGE)); + +const struct uapi_definition bnxt_re_uapi_defs[] = { + UAPI_DEF_CHAIN_OBJ_TREE_NAMED(BNXT_RE_OBJECT_ALLOC_PAGE), + {} +}; diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.h b/drivers/infiniband/hw/bnxt_re/ib_verbs.h index dcd31aefad4c..32d9e9d09791 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.h +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.h @@ -61,6 +61,7 @@ struct bnxt_re_pd { struct bnxt_qplib_pd qplib_pd; struct bnxt_re_fence_data fence; struct rdma_user_mmap_entry *pd_db_mmap; + struct rdma_user_mmap_entry *pd_wcdb_mmap; }; struct bnxt_re_ah { @@ -135,6 +136,7 @@ struct bnxt_re_ucontext { struct ib_ucontext ib_uctx; struct bnxt_re_dev *rdev; struct bnxt_qplib_dpi dpi; + struct bnxt_qplib_dpi wcdpi; void *shpg; spinlock_t sh_lock; /* protect shpg */ struct rdma_user_mmap_entry *shpage_mmap; @@ -143,10 +145,12 @@ struct bnxt_re_ucontext { enum bnxt_re_mmap_flag { BNXT_RE_MMAP_SH_PAGE, BNXT_RE_MMAP_UC_DB, + BNXT_RE_MMAP_WC_DB, }; struct bnxt_re_user_mmap_entry { struct rdma_user_mmap_entry rdma_entry; + struct bnxt_re_ucontext *uctx; u64 mem_offset; u8 mmap_flag; }; diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index 0c681134dd57..0816cf2a0b38 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -66,6 +66,7 @@ #include #include "bnxt.h" #include "hw_counters.h" +#include "ib_verbs.h" static char version[] = BNXT_RE_DESC "\n"; @@ -117,6 +118,10 @@ static void bnxt_re_set_db_offset(struct bnxt_re_dev *rdev) * in such cases and DB-push will be disabled. */ barlen = pci_resource_len(res->pdev, RCFW_DBR_PCI_BAR_REGION); + if (cctx->modes.db_push && l2db_len && en_dev->l2_db_size != barlen) { + res->dpi_tbl.wcreg.offset = en_dev->l2_db_size; + dev_info(rdev_to_dev(rdev), "Low latency framework is enabled\n"); + } } static void bnxt_re_set_drv_mode(struct bnxt_re_dev *rdev, u8 mode) @@ -395,8 +400,7 @@ static int bnxt_re_hwrm_qcfg(struct bnxt_re_dev *rdev, u32 *db_len, int rc; memset(&fw_msg, 0, sizeof(fw_msg)); - bnxt_re_init_hwrm_hdr(rdev, (void *)&req, - HWRM_FUNC_QCFG, -1, -1); + bnxt_re_init_hwrm_hdr((void *)&req, HWRM_FUNC_QCFG); req.fid = cpu_to_le16(0xffff); bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp, sizeof(resp), DFLT_HWRM_CMD_TIMEOUT); @@ -416,13 +420,20 @@ int bnxt_re_hwrm_qcaps(struct bnxt_re_dev *rdev) struct hwrm_func_qcaps_input req = {}; struct bnxt_qplib_chip_ctx *cctx; struct bnxt_fw_msg fw_msg = {}; + int rc; cctx = rdev->chip_ctx; bnxt_re_init_hwrm_hdr((void *)&req, HWRM_FUNC_QCAPS); req.fid = cpu_to_le16(0xffff); bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp, sizeof(resp), DFLT_HWRM_CMD_TIMEOUT); - return bnxt_send_msg(en_dev, &fw_msg); + + rc = bnxt_send_msg(en_dev, &fw_msg); + if (rc) + return rc; + cctx->modes.db_push = le32_to_cpu(resp.flags) & FUNC_QCAPS_RESP_FLAGS_WCB_PUSH_MODE; + + return 0; } static int bnxt_re_net_ring_free(struct bnxt_re_dev *rdev, @@ -669,6 +680,9 @@ static int bnxt_re_register_ib(struct bnxt_re_dev *rdev) ibdev->dev.parent = &rdev->en_dev->pdev->dev; ibdev->local_dma_lkey = BNXT_QPLIB_RSVD_LKEY; + if (IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS)) + ibdev->driver_def = bnxt_re_uapi_defs; + ib_set_device_ops(ibdev, &bnxt_re_dev_ops); ret = ib_device_set_netdev(&rdev->ibdev, rdev->netdev, 1); if (ret) diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.c b/drivers/infiniband/hw/bnxt_re/qplib_res.c index e1cbe594e56b..174db831b888 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_res.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c @@ -740,6 +740,9 @@ int bnxt_qplib_alloc_dpi(struct bnxt_qplib_res *res, dpi->dbr = dpit->priv_db; dpi->dpi = dpi->bit; break; + case BNXT_QPLIB_DPI_TYPE_WC: + dpi->dbr = ioremap_wc(umaddr, PAGE_SIZE); + break; default: dpi->dbr = ioremap(umaddr, PAGE_SIZE); break; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.h b/drivers/infiniband/hw/bnxt_re/qplib_res.h index 398a469d8377..d850a553821e 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_res.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_res.h @@ -47,7 +47,7 @@ extern const struct bnxt_qplib_gid bnxt_qplib_gid_zero; struct bnxt_qplib_drv_modes { u8 wqe_mode; - /* Other modes to follow here */ + bool db_push; }; struct bnxt_qplib_chip_ctx { @@ -194,6 +194,7 @@ struct bnxt_qplib_sgid_tbl { enum { BNXT_QPLIB_DPI_TYPE_KERNEL = 0, BNXT_QPLIB_DPI_TYPE_UC = 1, + BNXT_QPLIB_DPI_TYPE_WC = 2 }; struct bnxt_qplib_dpi { diff --git a/include/uapi/rdma/bnxt_re-abi.h b/include/uapi/rdma/bnxt_re-abi.h index c4e90775da0c..8a2a1d4f6b29 100644 --- a/include/uapi/rdma/bnxt_re-abi.h +++ b/include/uapi/rdma/bnxt_re-abi.h @@ -41,6 +41,7 @@ #define __BNXT_RE_UVERBS_ABI_H__ #include +#include #define BNXT_RE_ABI_VERSION 1 @@ -51,6 +52,7 @@ enum { BNXT_RE_UCNTX_CMASK_HAVE_CCTX = 0x1ULL, BNXT_RE_UCNTX_CMASK_HAVE_MODE = 0x02ULL, + BNXT_RE_UCNTX_CMASK_WC_DPI_ENABLED = 0x04ULL, }; enum bnxt_re_wqe_mode { @@ -127,4 +129,29 @@ enum bnxt_re_shpg_offt { BNXT_RE_END_RESV_OFFT = 0xFF0 }; +enum bnxt_re_objects { + BNXT_RE_OBJECT_ALLOC_PAGE = (1U << UVERBS_ID_NS_SHIFT), +}; + +enum bnxt_re_alloc_page_type { + BNXT_RE_ALLOC_WC_PAGE = 0, +}; + +enum bnxt_re_var_alloc_page_attrs { + BNXT_RE_ALLOC_PAGE_HANDLE = (1U << UVERBS_ID_NS_SHIFT), + BNXT_RE_ALLOC_PAGE_TYPE, + BNXT_RE_ALLOC_PAGE_DPI, + BNXT_RE_ALLOC_PAGE_MMAP_OFFSET, + BNXT_RE_ALLOC_PAGE_MMAP_LENGTH, +}; + +enum bnxt_re_alloc_page_attrs { + BNXT_RE_DESTROY_PAGE_HANDLE = (1U << UVERBS_ID_NS_SHIFT), +}; + +enum bnxt_re_alloc_page_methods { + BNXT_RE_METHOD_ALLOC_PAGE = (1U << UVERBS_ID_NS_SHIFT), + BNXT_RE_METHOD_DESTROY_PAGE, +}; + #endif /* __BNXT_RE_UVERBS_ABI_H__*/ -- cgit v1.2.3 From 38967f424b5be79c4c676712e5640d846efd07e3 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 20 Jun 2023 18:30:15 +0200 Subject: mptcp: track some aggregate data counters Currently there are no data transfer counters accounting for all the subflows used by a given MPTCP socket. The user-space can compute such figures aggregating the subflow info, but that is inaccurate if any subflow is closed before the MPTCP socket itself. Add the new counters in the MPTCP socket itself and expose them via the existing diag and sockopt. While touching mptcp_diag_fill_info(), acquire the relevant locks before fetching the msk data, to ensure better data consistency Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/385 Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Signed-off-by: Jakub Kicinski --- include/uapi/linux/mptcp.h | 5 +++++ net/mptcp/options.c | 10 ++++++++-- net/mptcp/protocol.c | 11 ++++++++++- net/mptcp/protocol.h | 4 ++++ net/mptcp/sockopt.c | 25 ++++++++++++++++++++----- 5 files changed, 47 insertions(+), 8 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 32af2d278cb4..a124be6ebbba 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -123,6 +123,11 @@ struct mptcp_info { __u8 mptcpi_local_addr_used; __u8 mptcpi_local_addr_max; __u8 mptcpi_csum_enabled; + __u32 mptcpi_retransmits; + __u64 mptcpi_bytes_retrans; + __u64 mptcpi_bytes_sent; + __u64 mptcpi_bytes_received; + __u64 mptcpi_bytes_acked; }; /* diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 4bdcd2b326bd..c254accb14de 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -1026,6 +1026,12 @@ u64 __mptcp_expand_seq(u64 old_seq, u64 cur_seq) return cur_seq; } +static void __mptcp_snd_una_update(struct mptcp_sock *msk, u64 new_snd_una) +{ + msk->bytes_acked += new_snd_una - msk->snd_una; + msk->snd_una = new_snd_una; +} + static void ack_update_msk(struct mptcp_sock *msk, struct sock *ssk, struct mptcp_options_received *mp_opt) @@ -1057,7 +1063,7 @@ static void ack_update_msk(struct mptcp_sock *msk, __mptcp_check_push(sk, ssk); if (after64(new_snd_una, old_snd_una)) { - msk->snd_una = new_snd_una; + __mptcp_snd_una_update(msk, new_snd_una); __mptcp_data_acked(sk); } mptcp_data_unlock(sk); @@ -1123,7 +1129,7 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) /* on fallback we just need to ignore the msk-level snd_una, as * this is really plain TCP */ - msk->snd_una = READ_ONCE(msk->snd_nxt); + __mptcp_snd_una_update(msk, READ_ONCE(msk->snd_nxt)); __mptcp_data_acked(subflow->conn); mptcp_data_unlock(subflow->conn); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 9c756d675d4d..d5b8e488bce1 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -377,6 +377,7 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, if (MPTCP_SKB_CB(skb)->map_seq == msk->ack_seq) { /* in sequence */ + msk->bytes_received += copy_len; WRITE_ONCE(msk->ack_seq, msk->ack_seq + copy_len); tail = skb_peek_tail(&sk->sk_receive_queue); if (tail && mptcp_try_coalesce(sk, tail, skb)) @@ -760,6 +761,7 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk) MPTCP_SKB_CB(skb)->map_seq += delta; __skb_queue_tail(&sk->sk_receive_queue, skb); } + msk->bytes_received += end_seq - msk->ack_seq; msk->ack_seq = end_seq; moved = true; } @@ -1531,8 +1533,10 @@ static void mptcp_update_post_push(struct mptcp_sock *msk, * that has been handed to the subflow for transmission * and skip update in case it was old dfrag. */ - if (likely(after64(snd_nxt_new, msk->snd_nxt))) + if (likely(after64(snd_nxt_new, msk->snd_nxt))) { + msk->bytes_sent += snd_nxt_new - msk->snd_nxt; msk->snd_nxt = snd_nxt_new; + } } void mptcp_check_and_set_pending(struct sock *sk) @@ -2590,6 +2594,7 @@ static void __mptcp_retrans(struct sock *sk) } if (copied) { dfrag->already_sent = max(dfrag->already_sent, info.sent); + msk->bytes_retrans += copied; tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle, info.size_goal); WRITE_ONCE(msk->allow_infinite_fallback, false); @@ -3102,6 +3107,10 @@ static int mptcp_disconnect(struct sock *sk, int flags) WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk))); mptcp_pm_data_reset(msk); mptcp_ca_reset(sk); + msk->bytes_acked = 0; + msk->bytes_received = 0; + msk->bytes_sent = 0; + msk->bytes_retrans = 0; WRITE_ONCE(sk->sk_shutdown, 0); sk_error_report(sk); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 47b46602870e..27adfcc5aaa2 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -262,10 +262,13 @@ struct mptcp_sock { u64 local_key; u64 remote_key; u64 write_seq; + u64 bytes_sent; u64 snd_nxt; + u64 bytes_received; u64 ack_seq; atomic64_t rcv_wnd_sent; u64 rcv_data_fin_seq; + u64 bytes_retrans; int rmem_fwd_alloc; struct sock *last_snd; int snd_burst; @@ -274,6 +277,7 @@ struct mptcp_sock { * recovery related fields are under data_lock * protection */ + u64 bytes_acked; u64 snd_una; u64 wnd_end; unsigned long timer_ival; diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index e172a5848b0d..fa5055d5b029 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -889,7 +889,9 @@ out: void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info) { + struct sock *sk = (struct sock *)msk; u32 flags = 0; + bool slow; memset(info, 0, sizeof(*info)); @@ -898,6 +900,9 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info) info->mptcpi_add_addr_accepted = READ_ONCE(msk->pm.add_addr_accepted); info->mptcpi_local_addr_used = READ_ONCE(msk->pm.local_addr_used); + if (inet_sk_state_load(sk) == TCP_LISTEN) + return; + /* The following limits only make sense for the in-kernel PM */ if (mptcp_pm_is_kernel(msk)) { info->mptcpi_subflows_max = @@ -915,11 +920,21 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info) if (READ_ONCE(msk->can_ack)) flags |= MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED; info->mptcpi_flags = flags; - info->mptcpi_token = READ_ONCE(msk->token); - info->mptcpi_write_seq = READ_ONCE(msk->write_seq); - info->mptcpi_snd_una = READ_ONCE(msk->snd_una); - info->mptcpi_rcv_nxt = READ_ONCE(msk->ack_seq); - info->mptcpi_csum_enabled = READ_ONCE(msk->csum_enabled); + mptcp_data_lock(sk); + info->mptcpi_snd_una = msk->snd_una; + info->mptcpi_rcv_nxt = msk->ack_seq; + info->mptcpi_bytes_acked = msk->bytes_acked; + mptcp_data_unlock(sk); + + slow = lock_sock_fast(sk); + info->mptcpi_csum_enabled = msk->csum_enabled; + info->mptcpi_token = msk->token; + info->mptcpi_write_seq = msk->write_seq; + info->mptcpi_retransmits = inet_csk(sk)->icsk_retransmits; + info->mptcpi_bytes_sent = msk->bytes_sent; + info->mptcpi_bytes_received = msk->bytes_received; + info->mptcpi_bytes_retrans = msk->bytes_retrans; + unlock_sock_fast(sk, slow); } EXPORT_SYMBOL_GPL(mptcp_diag_fill_info); -- cgit v1.2.3 From 492432074e4fce4f8880213bf009b47adbf94a3a Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 20 Jun 2023 18:30:18 +0200 Subject: mptcp: introduce MPTCP_FULL_INFO getsockopt Some user-space applications want to monitor the subflows utilization. Dumping the per subflow tcp_info is not enough, as the PM could close and re-create the subflows under-the-hood, fooling the accounting. Even checking the src/dst addresses used by each subflow could not be enough, because new subflows could re-use the same address/port of the just closed one. This patch introduces a new socket option, allow dumping all the relevant information all-at-once (everything, everywhere...), in a consistent manner. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/388 Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Signed-off-by: Jakub Kicinski --- include/uapi/linux/mptcp.h | 24 +++++++++ net/mptcp/sockopt.c | 127 ++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 149 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index a124be6ebbba..ee9c49f949a2 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -249,9 +249,33 @@ struct mptcp_subflow_addrs { }; }; +struct mptcp_subflow_info { + __u32 id; + struct mptcp_subflow_addrs addrs; +}; + +struct mptcp_full_info { + __u32 size_tcpinfo_kernel; /* must be 0, set by kernel */ + __u32 size_tcpinfo_user; + __u32 size_sfinfo_kernel; /* must be 0, set by kernel */ + __u32 size_sfinfo_user; + __u32 num_subflows; /* must be 0, set by kernel (real subflow count) */ + __u32 size_arrays_user; /* max subflows that userspace is interested in; + * the buffers at subflow_info/tcp_info + * are respectively at least: + * size_arrays * size_sfinfo_user + * size_arrays * size_tcpinfo_user + * bytes wide + */ + __aligned_u64 subflow_info; + __aligned_u64 tcp_info; + struct mptcp_info mptcp_info; +}; + /* MPTCP socket options */ #define MPTCP_INFO 1 #define MPTCP_TCPINFO 2 #define MPTCP_SUBFLOW_ADDRS 3 +#define MPTCP_FULL_INFO 4 #endif /* _UAPI_MPTCP_H */ diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index fa5055d5b029..63f7a09335c5 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -14,7 +14,8 @@ #include #include "protocol.h" -#define MIN_INFO_OPTLEN_SIZE 16 +#define MIN_INFO_OPTLEN_SIZE 16 +#define MIN_FULL_INFO_OPTLEN_SIZE 40 static struct sock *__mptcp_tcp_fallback(struct mptcp_sock *msk) { @@ -981,7 +982,8 @@ static int mptcp_put_subflow_data(struct mptcp_subflow_data *sfd, } static int mptcp_get_subflow_data(struct mptcp_subflow_data *sfd, - char __user *optval, int __user *optlen) + char __user *optval, + int __user *optlen) { int len, copylen; @@ -1162,6 +1164,125 @@ static int mptcp_getsockopt_subflow_addrs(struct mptcp_sock *msk, char __user *o return 0; } +static int mptcp_get_full_info(struct mptcp_full_info *mfi, + char __user *optval, + int __user *optlen) +{ + int len; + + BUILD_BUG_ON(offsetof(struct mptcp_full_info, mptcp_info) != + MIN_FULL_INFO_OPTLEN_SIZE); + + if (get_user(len, optlen)) + return -EFAULT; + + if (len < MIN_FULL_INFO_OPTLEN_SIZE) + return -EINVAL; + + memset(mfi, 0, sizeof(*mfi)); + if (copy_from_user(mfi, optval, MIN_FULL_INFO_OPTLEN_SIZE)) + return -EFAULT; + + if (mfi->size_tcpinfo_kernel || + mfi->size_sfinfo_kernel || + mfi->num_subflows) + return -EINVAL; + + if (mfi->size_sfinfo_user > INT_MAX || + mfi->size_tcpinfo_user > INT_MAX) + return -EINVAL; + + return len - MIN_FULL_INFO_OPTLEN_SIZE; +} + +static int mptcp_put_full_info(struct mptcp_full_info *mfi, + char __user *optval, + u32 copylen, + int __user *optlen) +{ + copylen += MIN_FULL_INFO_OPTLEN_SIZE; + if (put_user(copylen, optlen)) + return -EFAULT; + + if (copy_to_user(optval, mfi, copylen)) + return -EFAULT; + return 0; +} + +static int mptcp_getsockopt_full_info(struct mptcp_sock *msk, char __user *optval, + int __user *optlen) +{ + unsigned int sfcount = 0, copylen = 0; + struct mptcp_subflow_context *subflow; + struct sock *sk = (struct sock *)msk; + void __user *tcpinfoptr, *sfinfoptr; + struct mptcp_full_info mfi; + int len; + + len = mptcp_get_full_info(&mfi, optval, optlen); + if (len < 0) + return len; + + /* don't bother filling the mptcp info if there is not enough + * user-space-provided storage + */ + if (len > 0) { + mptcp_diag_fill_info(msk, &mfi.mptcp_info); + copylen += min_t(unsigned int, len, sizeof(struct mptcp_info)); + } + + mfi.size_tcpinfo_kernel = sizeof(struct tcp_info); + mfi.size_tcpinfo_user = min_t(unsigned int, mfi.size_tcpinfo_user, + sizeof(struct tcp_info)); + sfinfoptr = u64_to_user_ptr(mfi.subflow_info); + mfi.size_sfinfo_kernel = sizeof(struct mptcp_subflow_info); + mfi.size_sfinfo_user = min_t(unsigned int, mfi.size_sfinfo_user, + sizeof(struct mptcp_subflow_info)); + tcpinfoptr = u64_to_user_ptr(mfi.tcp_info); + + lock_sock(sk); + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + struct mptcp_subflow_info sfinfo; + struct tcp_info tcp_info; + + if (sfcount++ >= mfi.size_arrays_user) + continue; + + /* fetch addr/tcp_info only if the user space buffers + * are wide enough + */ + memset(&sfinfo, 0, sizeof(sfinfo)); + sfinfo.id = subflow->subflow_id; + if (mfi.size_sfinfo_user > + offsetof(struct mptcp_subflow_info, addrs)) + mptcp_get_sub_addrs(ssk, &sfinfo.addrs); + if (copy_to_user(sfinfoptr, &sfinfo, mfi.size_sfinfo_user)) + goto fail_release; + + if (mfi.size_tcpinfo_user) { + tcp_get_info(ssk, &tcp_info); + if (copy_to_user(tcpinfoptr, &tcp_info, + mfi.size_tcpinfo_user)) + goto fail_release; + } + + tcpinfoptr += mfi.size_tcpinfo_user; + sfinfoptr += mfi.size_sfinfo_user; + } + release_sock(sk); + + mfi.num_subflows = sfcount; + if (mptcp_put_full_info(&mfi, optval, copylen, optlen)) + return -EFAULT; + + return 0; + +fail_release: + release_sock(sk); + return -EFAULT; +} + static int mptcp_put_int_option(struct mptcp_sock *msk, char __user *optval, int __user *optlen, int val) { @@ -1235,6 +1356,8 @@ static int mptcp_getsockopt_sol_mptcp(struct mptcp_sock *msk, int optname, switch (optname) { case MPTCP_INFO: return mptcp_getsockopt_info(msk, optval, optlen); + case MPTCP_FULL_INFO: + return mptcp_getsockopt_full_info(msk, optval, optlen); case MPTCP_TCPINFO: return mptcp_getsockopt_tcpinfo(msk, optval, optlen); case MPTCP_SUBFLOW_ADDRS: -- cgit v1.2.3 From 735d86a8aaf660e2a5fd5d711ee05fa817e8d567 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Fri, 9 Jun 2023 14:10:51 +0200 Subject: can: uapi: move CAN_RAW_FILTER_MAX definition to raw.h CAN_RAW_FILTER_MAX is only relevant for CAN_RAW sockets and used in linux/can/raw.c or in userspace applications that include the raw.h file anyway. Signed-off-by: Oliver Hartkopp Link: https://lore.kernel.org/all/20230609121051.9631-1-socketcan@hartkopp.net Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/can.h | 1 - include/uapi/linux/can/raw.h | 2 ++ 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/can.h b/include/uapi/linux/can.h index dd645ea72306..939db2388208 100644 --- a/include/uapi/linux/can.h +++ b/include/uapi/linux/can.h @@ -285,6 +285,5 @@ struct can_filter { }; #define CAN_INV_FILTER 0x20000000U /* to be set in can_filter.can_id */ -#define CAN_RAW_FILTER_MAX 512 /* maximum number of can_filter set via setsockopt() */ #endif /* !_UAPI_CAN_H */ diff --git a/include/uapi/linux/can/raw.h b/include/uapi/linux/can/raw.h index ff12f525c37c..31622c9b7988 100644 --- a/include/uapi/linux/can/raw.h +++ b/include/uapi/linux/can/raw.h @@ -49,6 +49,8 @@ #include #define SOL_CAN_RAW (SOL_CAN_BASE + CAN_RAW) +#define CAN_RAW_FILTER_MAX 512 /* maximum number of can_filter set via setsockopt() */ + enum { SCM_CAN_RAW_ERRQUEUE = 1, }; -- cgit v1.2.3 From 0b3d412798a4763aaf39213a279e453e1fddc81d Mon Sep 17 00:00:00 2001 From: Baruch Siach Date: Fri, 23 Jun 2023 08:50:11 +0300 Subject: elf: correct note name comment NT_PRFPREG note is named "CORE". Correct the comment accordingly. Fixes: 00e19ceec80b ("ELF: Add ELF program property parsing support") Signed-off-by: Baruch Siach Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/455b22b986de4d3bc6d9bfd522378e442943de5f.1687499411.git.baruch@tkos.co.il --- include/uapi/linux/elf.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index ac3da855fb19..4d1c8d46e7f0 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -372,7 +372,8 @@ typedef struct elf64_shdr { * Notes used in ET_CORE. Architectures export some of the arch register sets * using the corresponding note types via the PTRACE_GETREGSET and * PTRACE_SETREGSET requests. - * The note name for all these is "LINUX". + * The note name for these types is "LINUX", except NT_PRFPREG that is named + * "CORE". */ #define NT_PRSTATUS 1 #define NT_PRFPREG 2 -- cgit v1.2.3 From 079cd633219d7298d087cd115c17682264244c18 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Thu, 15 Jun 2023 16:31:40 +0200 Subject: netfilter: nf_tables: Introduce NFT_MSG_GETSETELEM_RESET Analogous to NFT_MSG_GETOBJ_RESET, but for set elements with a timeout or attached stateful expressions like counters or quotas - reset them all at once. Respect a per element timeout value if present to reset the 'expires' value to. Signed-off-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 2 + net/netfilter/nf_tables_api.c | 68 ++++++++++++++++++++++---------- 2 files changed, 50 insertions(+), 20 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index e059dc2644df..8466c2a9938f 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -105,6 +105,7 @@ enum nft_verdicts { * @NFT_MSG_DESTROYSETELEM: destroy a set element (enum nft_set_elem_attributes) * @NFT_MSG_DESTROYOBJ: destroy a stateful object (enum nft_object_attributes) * @NFT_MSG_DESTROYFLOWTABLE: destroy flow table (enum nft_flowtable_attributes) + * @NFT_MSG_GETSETELEM_RESET: get set elements and reset attached stateful expressions (enum nft_set_elem_attributes) */ enum nf_tables_msg_types { NFT_MSG_NEWTABLE, @@ -140,6 +141,7 @@ enum nf_tables_msg_types { NFT_MSG_DESTROYSETELEM, NFT_MSG_DESTROYOBJ, NFT_MSG_DESTROYFLOWTABLE, + NFT_MSG_GETSETELEM_RESET, NFT_MSG_MAX, }; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index dfd441ff1e3e..30fd62224df9 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5229,7 +5229,8 @@ static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX + static int nft_set_elem_expr_dump(struct sk_buff *skb, const struct nft_set *set, - const struct nft_set_ext *ext) + const struct nft_set_ext *ext, + bool reset) { struct nft_set_elem_expr *elem_expr; u32 size, num_exprs = 0; @@ -5242,7 +5243,7 @@ static int nft_set_elem_expr_dump(struct sk_buff *skb, if (num_exprs == 1) { expr = nft_setelem_expr_at(elem_expr, 0); - if (nft_expr_dump(skb, NFTA_SET_ELEM_EXPR, expr, false) < 0) + if (nft_expr_dump(skb, NFTA_SET_ELEM_EXPR, expr, reset) < 0) return -1; return 0; @@ -5253,7 +5254,7 @@ static int nft_set_elem_expr_dump(struct sk_buff *skb, nft_setelem_expr_foreach(expr, elem_expr, size) { expr = nft_setelem_expr_at(elem_expr, size); - if (nft_expr_dump(skb, NFTA_LIST_ELEM, expr, false) < 0) + if (nft_expr_dump(skb, NFTA_LIST_ELEM, expr, reset) < 0) goto nla_put_failure; } nla_nest_end(skb, nest); @@ -5266,11 +5267,13 @@ nla_put_failure: static int nf_tables_fill_setelem(struct sk_buff *skb, const struct nft_set *set, - const struct nft_set_elem *elem) + const struct nft_set_elem *elem, + bool reset) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; + u64 timeout = 0; nest = nla_nest_start_noflag(skb, NFTA_LIST_ELEM); if (nest == NULL) @@ -5293,7 +5296,7 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, goto nla_put_failure; if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPRESSIONS) && - nft_set_elem_expr_dump(skb, set, ext)) + nft_set_elem_expr_dump(skb, set, ext, reset)) goto nla_put_failure; if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF) && @@ -5306,11 +5309,15 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, htonl(*nft_set_ext_flags(ext)))) goto nla_put_failure; - if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) && - nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT, - nf_jiffies64_to_msecs(*nft_set_ext_timeout(ext)), - NFTA_SET_ELEM_PAD)) - goto nla_put_failure; + if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT)) { + timeout = *nft_set_ext_timeout(ext); + if (nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT, + nf_jiffies64_to_msecs(timeout), + NFTA_SET_ELEM_PAD)) + goto nla_put_failure; + } else if (set->flags & NFT_SET_TIMEOUT) { + timeout = READ_ONCE(set->timeout); + } if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) { u64 expires, now = get_jiffies_64(); @@ -5325,6 +5332,9 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, nf_jiffies64_to_msecs(expires), NFTA_SET_ELEM_PAD)) goto nla_put_failure; + + if (reset) + *nft_set_ext_expiration(ext) = now + timeout; } if (nft_set_ext_exists(ext, NFT_SET_EXT_USERDATA)) { @@ -5348,6 +5358,7 @@ struct nft_set_dump_args { const struct netlink_callback *cb; struct nft_set_iter iter; struct sk_buff *skb; + bool reset; }; static int nf_tables_dump_setelem(const struct nft_ctx *ctx, @@ -5358,7 +5369,7 @@ static int nf_tables_dump_setelem(const struct nft_ctx *ctx, struct nft_set_dump_args *args; args = container_of(iter, struct nft_set_dump_args, iter); - return nf_tables_fill_setelem(args->skb, set, elem); + return nf_tables_fill_setelem(args->skb, set, elem, args->reset); } struct nft_set_dump_ctx { @@ -5367,7 +5378,7 @@ struct nft_set_dump_ctx { }; static int nft_set_catchall_dump(struct net *net, struct sk_buff *skb, - const struct nft_set *set) + const struct nft_set *set, bool reset) { struct nft_set_elem_catchall *catchall; u8 genmask = nft_genmask_cur(net); @@ -5382,7 +5393,7 @@ static int nft_set_catchall_dump(struct net *net, struct sk_buff *skb, continue; elem.priv = catchall->elem; - ret = nf_tables_fill_setelem(skb, set, &elem); + ret = nf_tables_fill_setelem(skb, set, &elem, reset); break; } @@ -5400,6 +5411,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) bool set_found = false; struct nlmsghdr *nlh; struct nlattr *nest; + bool reset = false; u32 portid, seq; int event; @@ -5447,8 +5459,12 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) if (nest == NULL) goto nla_put_failure; + if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) == NFT_MSG_GETSETELEM_RESET) + reset = true; + args.cb = cb; args.skb = skb; + args.reset = reset; args.iter.genmask = nft_genmask_cur(net); args.iter.skip = cb->args[0]; args.iter.count = 0; @@ -5457,7 +5473,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) set->ops->walk(&dump_ctx->ctx, set, &args.iter); if (!args.iter.err && args.iter.count == cb->args[0]) - args.iter.err = nft_set_catchall_dump(net, skb, set); + args.iter.err = nft_set_catchall_dump(net, skb, set, reset); rcu_read_unlock(); nla_nest_end(skb, nest); @@ -5495,7 +5511,8 @@ static int nf_tables_fill_setelem_info(struct sk_buff *skb, const struct nft_ctx *ctx, u32 seq, u32 portid, int event, u16 flags, const struct nft_set *set, - const struct nft_set_elem *elem) + const struct nft_set_elem *elem, + bool reset) { struct nlmsghdr *nlh; struct nlattr *nest; @@ -5516,7 +5533,7 @@ static int nf_tables_fill_setelem_info(struct sk_buff *skb, if (nest == NULL) goto nla_put_failure; - err = nf_tables_fill_setelem(skb, set, elem); + err = nf_tables_fill_setelem(skb, set, elem, reset); if (err < 0) goto nla_put_failure; @@ -5622,7 +5639,7 @@ static int nft_setelem_get(struct nft_ctx *ctx, struct nft_set *set, } static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set, - const struct nlattr *attr) + const struct nlattr *attr, bool reset) { struct nlattr *nla[NFTA_SET_ELEM_MAX + 1]; struct nft_set_elem elem; @@ -5666,7 +5683,8 @@ static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set, return err; err = nf_tables_fill_setelem_info(skb, ctx, ctx->seq, ctx->portid, - NFT_MSG_NEWSETELEM, 0, set, &elem); + NFT_MSG_NEWSETELEM, 0, set, &elem, + reset); if (err < 0) goto err_fill_setelem; @@ -5690,6 +5708,7 @@ static int nf_tables_getsetelem(struct sk_buff *skb, struct nft_set *set; struct nlattr *attr; struct nft_ctx ctx; + bool reset = false; int rem, err = 0; table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family, @@ -5724,8 +5743,11 @@ static int nf_tables_getsetelem(struct sk_buff *skb, if (!nla[NFTA_SET_ELEM_LIST_ELEMENTS]) return -EINVAL; + if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_GETSETELEM_RESET) + reset = true; + nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { - err = nft_get_set_elem(&ctx, set, attr); + err = nft_get_set_elem(&ctx, set, attr, reset); if (err < 0) { NL_SET_BAD_ATTR(extack, attr); break; @@ -5758,7 +5780,7 @@ static void nf_tables_setelem_notify(const struct nft_ctx *ctx, flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); err = nf_tables_fill_setelem_info(skb, ctx, 0, portid, event, flags, - set, elem); + set, elem, false); if (err < 0) { kfree_skb(skb); goto err; @@ -8715,6 +8737,12 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .attr_count = NFTA_SET_ELEM_LIST_MAX, .policy = nft_set_elem_list_policy, }, + [NFT_MSG_GETSETELEM_RESET] = { + .call = nf_tables_getsetelem, + .type = NFNL_CB_RCU, + .attr_count = NFTA_SET_ELEM_LIST_MAX, + .policy = nft_set_elem_list_policy, + }, [NFT_MSG_DELSETELEM] = { .call = nf_tables_delsetelem, .type = NFNL_CB_BATCH, -- cgit v1.2.3