From c787f1baa5031c22cbe20af17b2ee36ad32957ea Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 7 Apr 2023 15:05:34 -0500 Subject: block: Add PR callouts for read keys and reservation Add callouts for reading keys and reservations. This allows LIO to support the READ_KEYS and READ_RESERVATION commands so it can export devices to VMs for software like windows clustering. Signed-off-by: Mike Christie Link: https://lore.kernel.org/r/20230407200551.12660-2-michael.christie@oracle.com Reviewed-by: Chaitanya Kulkarni Reviewed-by: Christoph Hellwig Reviewed-by: Bart Van Assche Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- include/linux/pr.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pr.h b/include/linux/pr.h index 94ceec713afe..3003daec28a5 100644 --- a/include/linux/pr.h +++ b/include/linux/pr.h @@ -4,6 +4,18 @@ #include +struct pr_keys { + u32 generation; + u32 num_keys; + u64 keys[]; +}; + +struct pr_held_reservation { + u64 key; + u32 generation; + enum pr_type type; +}; + struct pr_ops { int (*pr_register)(struct block_device *bdev, u64 old_key, u64 new_key, u32 flags); @@ -14,6 +26,19 @@ struct pr_ops { int (*pr_preempt)(struct block_device *bdev, u64 old_key, u64 new_key, enum pr_type type, bool abort); int (*pr_clear)(struct block_device *bdev, u64 key); + /* + * pr_read_keys - Read the registered keys and return them in the + * pr_keys->keys array. The keys array will have been allocated at the + * end of the pr_keys struct, and pr_keys->num_keys must be set to the + * number of keys the array can hold. If there are more than can fit + * in the array, success will still be returned and pr_keys->num_keys + * will reflect the total number of keys the device contains, so the + * caller can retry with a larger array. + */ + int (*pr_read_keys)(struct block_device *bdev, + struct pr_keys *keys_info); + int (*pr_read_reservation)(struct block_device *bdev, + struct pr_held_reservation *rsv); }; #endif /* LINUX_PR_H */ -- cgit v1.2.3 From 7ba150834b840f6f5cdd07ca69a4ccf39df59a66 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 7 Apr 2023 15:05:35 -0500 Subject: block: Rename BLK_STS_NEXUS to BLK_STS_RESV_CONFLICT BLK_STS_NEXUS is used for NVMe/SCSI reservation conflicts and DASD's locking feature which works similar to NVMe/SCSI reservations where a host can get a lock on a device and when the lock is taken it will get failures. This patch renames BLK_STS_NEXUS so it better reflects this type of use. Signed-off-by: Mike Christie Link: https://lore.kernel.org/r/20230407200551.12660-3-michael.christie@oracle.com Acked-by: Stefan Haberland Reviewed-by: Bart Van Assche Reviewed-by: Chaitanya Kulkarni Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- block/blk-core.c | 2 +- drivers/nvme/host/core.c | 2 +- drivers/s390/block/dasd.c | 7 ++++++- drivers/scsi/scsi_lib.c | 2 +- include/linux/blk_types.h | 4 ++-- 5 files changed, 11 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/block/blk-core.c b/block/blk-core.c index 9e5e0277a4d9..ff8fb7a49389 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -155,7 +155,7 @@ static const struct { [BLK_STS_NOSPC] = { -ENOSPC, "critical space allocation" }, [BLK_STS_TRANSPORT] = { -ENOLINK, "recoverable transport" }, [BLK_STS_TARGET] = { -EREMOTEIO, "critical target" }, - [BLK_STS_NEXUS] = { -EBADE, "critical nexus" }, + [BLK_STS_RESV_CONFLICT] = { -EBADE, "reservation conflict" }, [BLK_STS_MEDIUM] = { -ENODATA, "critical medium" }, [BLK_STS_PROTECTION] = { -EILSEQ, "protection" }, [BLK_STS_RESOURCE] = { -ENOMEM, "kernel resource" }, diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index c2730b116dc6..535a26ceb205 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -279,7 +279,7 @@ static blk_status_t nvme_error_status(u16 status) case NVME_SC_INVALID_PI: return BLK_STS_PROTECTION; case NVME_SC_RESERVATION_CONFLICT: - return BLK_STS_NEXUS; + return BLK_STS_RESV_CONFLICT; case NVME_SC_HOST_PATH_ERROR: return BLK_STS_TRANSPORT; case NVME_SC_ZONE_TOO_MANY_ACTIVE: diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index a9c2a8d76c45..ca0df87fa8f4 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -2723,7 +2723,12 @@ static void __dasd_cleanup_cqr(struct dasd_ccw_req *cqr) else if (status == 0) { switch (cqr->intrc) { case -EPERM: - error = BLK_STS_NEXUS; + /* + * DASD doesn't implement SCSI/NVMe reservations, but it + * implements a locking scheme similar to them. We + * return this error when we no longer have the lock. + */ + error = BLK_STS_RESV_CONFLICT; break; case -ENOLINK: error = BLK_STS_TRANSPORT; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index b7c569a42aa4..e1468483ac7e 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -599,7 +599,7 @@ static blk_status_t scsi_result_to_blk_status(int result) case SCSIML_STAT_OK: break; case SCSIML_STAT_RESV_CONFLICT: - return BLK_STS_NEXUS; + return BLK_STS_RESV_CONFLICT; case SCSIML_STAT_NOSPC: return BLK_STS_NOSPC; case SCSIML_STAT_MED_ERROR: diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 99be590f952f..2b2452086a2f 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -96,7 +96,7 @@ typedef u16 blk_short_t; #define BLK_STS_NOSPC ((__force blk_status_t)3) #define BLK_STS_TRANSPORT ((__force blk_status_t)4) #define BLK_STS_TARGET ((__force blk_status_t)5) -#define BLK_STS_NEXUS ((__force blk_status_t)6) +#define BLK_STS_RESV_CONFLICT ((__force blk_status_t)6) #define BLK_STS_MEDIUM ((__force blk_status_t)7) #define BLK_STS_PROTECTION ((__force blk_status_t)8) #define BLK_STS_RESOURCE ((__force blk_status_t)9) @@ -184,7 +184,7 @@ static inline bool blk_path_error(blk_status_t error) case BLK_STS_NOTSUPP: case BLK_STS_NOSPC: case BLK_STS_TARGET: - case BLK_STS_NEXUS: + case BLK_STS_RESV_CONFLICT: case BLK_STS_MEDIUM: case BLK_STS_PROTECTION: return false; -- cgit v1.2.3 From f2bf2e7e2d526116aab942aaf1b71a949a570ba6 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 7 Apr 2023 15:05:40 -0500 Subject: nvme: Fix reservation status related structs This fixes the following issues with the reservation status structs: 1. resv10 is bytes 23:10 so it should be 14 bytes. 2. regctl_ds only supports 64 bit host IDs. These are not currently used, but will be in this patchset which adds support for the reservation report command. Signed-off-by: Mike Christie Link: https://lore.kernel.org/r/20230407200551.12660-8-michael.christie@oracle.com Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- include/linux/nvme.h | 38 ++++++++++++++++++++++++++++++-------- 1 file changed, 30 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 4fad4aa245fb..57b5b2b8d95b 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -759,20 +759,42 @@ enum { NVME_LBART_ATTRIB_HIDE = 1 << 1, }; +struct nvme_registered_ctrl { + __le16 cntlid; + __u8 rcsts; + __u8 rsvd3[5]; + __le64 hostid; + __le64 rkey; +}; + struct nvme_reservation_status { __le32 gen; __u8 rtype; __u8 regctl[2]; __u8 resv5[2]; __u8 ptpls; - __u8 resv10[13]; - struct { - __le16 cntlid; - __u8 rcsts; - __u8 resv3[5]; - __le64 hostid; - __le64 rkey; - } regctl_ds[]; + __u8 resv10[14]; + struct nvme_registered_ctrl regctl_ds[]; +}; + +struct nvme_registered_ctrl_ext { + __le16 cntlid; + __u8 rcsts; + __u8 rsvd3[5]; + __le64 rkey; + __u8 hostid[16]; + __u8 rsvd32[32]; +}; + +struct nvme_reservation_status_ext { + __le32 gen; + __u8 rtype; + __u8 regctl[2]; + __u8 resv5[2]; + __u8 ptpls; + __u8 resv10[14]; + __u8 rsvd24[40]; + struct nvme_registered_ctrl_ext regctl_eds[]; }; enum nvme_async_event_type { -- cgit v1.2.3 From 5fd96a4e15de8442915a912233d800c56f49001d Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 7 Apr 2023 15:05:44 -0500 Subject: nvme: Add pr_ops read_keys support This patch adds support for the pr_ops read_keys callout by calling the NVMe Reservation Report helper, then parsing that info to get the controller's registered keys. Because the callout is only used in the kernel where the callers, like LIO, do not know about controller/host IDs, the callout just returns the registered keys which is required by the SCSI PR in READ KEYS command. Signed-off-by: Mike Christie Link: https://lore.kernel.org/r/20230407200551.12660-12-michael.christie@oracle.com Reviewed-by: Chaitanya Kulkarni Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- drivers/nvme/host/pr.c | 69 ++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/nvme.h | 4 +++ 2 files changed, 73 insertions(+) (limited to 'include/linux') diff --git a/drivers/nvme/host/pr.c b/drivers/nvme/host/pr.c index cd93d2e5b340..0ee656404437 100644 --- a/drivers/nvme/host/pr.c +++ b/drivers/nvme/host/pr.c @@ -154,10 +154,79 @@ static int nvme_pr_release(struct block_device *bdev, u64 key, enum pr_type type return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_release); } +static int nvme_pr_resv_report(struct block_device *bdev, void *data, + u32 data_len, bool *eds) +{ + struct nvme_command c = { }; + int ret; + + c.common.opcode = nvme_cmd_resv_report; + c.common.cdw10 = cpu_to_le32(nvme_bytes_to_numd(data_len)); + c.common.cdw11 = cpu_to_le32(NVME_EXTENDED_DATA_STRUCT); + *eds = true; + +retry: + ret = nvme_send_pr_command(bdev, &c, data, data_len); + if (ret == NVME_SC_HOST_ID_INCONSIST && + c.common.cdw11 == cpu_to_le32(NVME_EXTENDED_DATA_STRUCT)) { + c.common.cdw11 = 0; + *eds = false; + goto retry; + } + + if (ret < 0) + return ret; + + return nvme_sc_to_pr_err(ret); +} + +static int nvme_pr_read_keys(struct block_device *bdev, + struct pr_keys *keys_info) +{ + u32 rse_len, num_keys = keys_info->num_keys; + struct nvme_reservation_status_ext *rse; + int ret, i; + bool eds; + + /* + * Assume we are using 128-bit host IDs and allocate a buffer large + * enough to get enough keys to fill the return keys buffer. + */ + rse_len = struct_size(rse, regctl_eds, num_keys); + rse = kzalloc(rse_len, GFP_KERNEL); + if (!rse) + return -ENOMEM; + + ret = nvme_pr_resv_report(bdev, rse, rse_len, &eds); + if (ret) + goto free_rse; + + keys_info->generation = le32_to_cpu(rse->gen); + keys_info->num_keys = get_unaligned_le16(&rse->regctl); + + num_keys = min(num_keys, keys_info->num_keys); + for (i = 0; i < num_keys; i++) { + if (eds) { + keys_info->keys[i] = + le64_to_cpu(rse->regctl_eds[i].rkey); + } else { + struct nvme_reservation_status *rs; + + rs = (struct nvme_reservation_status *)rse; + keys_info->keys[i] = le64_to_cpu(rs->regctl_ds[i].rkey); + } + } + +free_rse: + kfree(rse); + return ret; +} + const struct pr_ops nvme_pr_ops = { .pr_register = nvme_pr_register, .pr_reserve = nvme_pr_reserve, .pr_release = nvme_pr_release, .pr_preempt = nvme_pr_preempt, .pr_clear = nvme_pr_clear, + .pr_read_keys = nvme_pr_read_keys, }; diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 57b5b2b8d95b..a617e250d629 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -759,6 +759,10 @@ enum { NVME_LBART_ATTRIB_HIDE = 1 << 1, }; +enum nvme_eds { + NVME_EXTENDED_DATA_STRUCT = 0x1, +}; + struct nvme_registered_ctrl { __le16 cntlid; __u8 rcsts; -- cgit v1.2.3 From be1a7cd2d0ed028ffdd60c65e3734e2a1d8b17df Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 7 Apr 2023 15:05:45 -0500 Subject: nvme: Add a nvme_pr_type enum The next patch adds support to report the reservation type, so we need to be able to convert from the NVMe PR value we get from the device to the linux block layer PR value that will be returned to callers. To prepare for that, this patch adds a nvme_pr_type enum and renames the nvme_pr_type function. Signed-off-by: Mike Christie Link: https://lore.kernel.org/r/20230407200551.12660-13-michael.christie@oracle.com Reviewed-by: Chaitanya Kulkarni Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- drivers/nvme/host/pr.c | 24 ++++++++++++------------ include/linux/nvme.h | 9 +++++++++ 2 files changed, 21 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/nvme/host/pr.c b/drivers/nvme/host/pr.c index 0ee656404437..732c56b417c2 100644 --- a/drivers/nvme/host/pr.c +++ b/drivers/nvme/host/pr.c @@ -9,24 +9,24 @@ #include "nvme.h" -static char nvme_pr_type(enum pr_type type) +static enum nvme_pr_type nvme_pr_type_from_blk(enum pr_type type) { switch (type) { case PR_WRITE_EXCLUSIVE: - return 1; + return NVME_PR_WRITE_EXCLUSIVE; case PR_EXCLUSIVE_ACCESS: - return 2; + return NVME_PR_EXCLUSIVE_ACCESS; case PR_WRITE_EXCLUSIVE_REG_ONLY: - return 3; + return NVME_PR_WRITE_EXCLUSIVE_REG_ONLY; case PR_EXCLUSIVE_ACCESS_REG_ONLY: - return 4; + return NVME_PR_EXCLUSIVE_ACCESS_REG_ONLY; case PR_WRITE_EXCLUSIVE_ALL_REGS: - return 5; + return NVME_PR_WRITE_EXCLUSIVE_ALL_REGS; case PR_EXCLUSIVE_ACCESS_ALL_REGS: - return 6; - default: - return 0; + return NVME_PR_EXCLUSIVE_ACCESS_ALL_REGS; } + + return 0; } static int nvme_send_ns_head_pr_command(struct block_device *bdev, @@ -127,7 +127,7 @@ static int nvme_pr_reserve(struct block_device *bdev, u64 key, if (flags & ~PR_FL_IGNORE_KEY) return -EOPNOTSUPP; - cdw10 = nvme_pr_type(type) << 8; + cdw10 = nvme_pr_type_from_blk(type) << 8; cdw10 |= ((flags & PR_FL_IGNORE_KEY) ? 1 << 3 : 0); return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_acquire); } @@ -135,7 +135,7 @@ static int nvme_pr_reserve(struct block_device *bdev, u64 key, static int nvme_pr_preempt(struct block_device *bdev, u64 old, u64 new, enum pr_type type, bool abort) { - u32 cdw10 = nvme_pr_type(type) << 8 | (abort ? 2 : 1); + u32 cdw10 = nvme_pr_type_from_blk(type) << 8 | (abort ? 2 : 1); return nvme_pr_command(bdev, cdw10, old, new, nvme_cmd_resv_acquire); } @@ -149,7 +149,7 @@ static int nvme_pr_clear(struct block_device *bdev, u64 key) static int nvme_pr_release(struct block_device *bdev, u64 key, enum pr_type type) { - u32 cdw10 = nvme_pr_type(type) << 8 | (key ? 0 : 1 << 3); + u32 cdw10 = nvme_pr_type_from_blk(type) << 8 | (key ? 0 : 1 << 3); return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_release); } diff --git a/include/linux/nvme.h b/include/linux/nvme.h index a617e250d629..4013abb86642 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -759,6 +759,15 @@ enum { NVME_LBART_ATTRIB_HIDE = 1 << 1, }; +enum nvme_pr_type { + NVME_PR_WRITE_EXCLUSIVE = 1, + NVME_PR_EXCLUSIVE_ACCESS = 2, + NVME_PR_WRITE_EXCLUSIVE_REG_ONLY = 3, + NVME_PR_EXCLUSIVE_ACCESS_REG_ONLY = 4, + NVME_PR_WRITE_EXCLUSIVE_ALL_REGS = 5, + NVME_PR_EXCLUSIVE_ACCESS_ALL_REGS = 6, +}; + enum nvme_eds { NVME_EXTENDED_DATA_STRUCT = 0x1, }; -- cgit v1.2.3 From 5fbcc6708fe32ef80122cd2a59ddca9d18b24d6e Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Thu, 6 Apr 2023 15:21:06 +0200 Subject: video/aperture: Drop primary argument With the preceding patches it's become defunct. Also I'm about to add a different boolean argument, so it's better to keep the confusion down to the absolute minimum. v2: Since the hypervfb patch got droppped (it's only a pci device for gen1 vm, not for gen2) there is one leftover user in an actual driver left to touch. v4: - fixes to commit message - fix Daniel's S-o-b address v5: - add back an S-o-b tag with Daniel's Intel address Signed-off-by: Daniel Vetter Signed-off-by: Daniel Vetter Signed-off-by: Thomas Zimmermann Cc: Thomas Zimmermann Cc: Javier Martinez Canillas Cc: Helge Deller Cc: linux-fbdev@vger.kernel.org Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: "K. Y. Srinivasan" Cc: Haiyang Zhang Cc: Wei Liu Cc: Dexuan Cui Cc: linux-hyperv@vger.kernel.org Reviewed-by: Javier Martinez Canillas Link: https://patchwork.freedesktop.org/patch/msgid/20230406132109.32050-7-tzimmermann@suse.de --- drivers/gpu/drm/drm_aperture.c | 2 +- drivers/video/aperture.c | 7 +++---- drivers/video/fbdev/hyperv_fb.c | 2 +- include/linux/aperture.h | 9 ++++----- 4 files changed, 9 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/drm_aperture.c b/drivers/gpu/drm/drm_aperture.c index 697cffbfd603..5729f3bb4398 100644 --- a/drivers/gpu/drm/drm_aperture.c +++ b/drivers/gpu/drm/drm_aperture.c @@ -168,7 +168,7 @@ EXPORT_SYMBOL(devm_aperture_acquire_from_firmware); int drm_aperture_remove_conflicting_framebuffers(resource_size_t base, resource_size_t size, const struct drm_driver *req_driver) { - return aperture_remove_conflicting_devices(base, size, false, req_driver->name); + return aperture_remove_conflicting_devices(base, size, req_driver->name); } EXPORT_SYMBOL(drm_aperture_remove_conflicting_framebuffers); diff --git a/drivers/video/aperture.c b/drivers/video/aperture.c index b378cd1d44d0..a0945027e0df 100644 --- a/drivers/video/aperture.c +++ b/drivers/video/aperture.c @@ -43,7 +43,7 @@ * base = mem->start; * size = resource_size(mem); * - * ret = aperture_remove_conflicting_devices(base, size, false, "example"); + * ret = aperture_remove_conflicting_devices(base, size, "example"); * if (ret) * return ret; * @@ -274,7 +274,6 @@ static void aperture_detach_devices(resource_size_t base, resource_size_t size) * aperture_remove_conflicting_devices - remove devices in the given range * @base: the aperture's base address in physical memory * @size: aperture size in bytes - * @primary: also kick vga16fb if present; only relevant for VGA devices * @name: a descriptive name of the requesting driver * * This function removes devices that own apertures within @base and @size. @@ -283,7 +282,7 @@ static void aperture_detach_devices(resource_size_t base, resource_size_t size) * 0 on success, or a negative errno code otherwise */ int aperture_remove_conflicting_devices(resource_size_t base, resource_size_t size, - bool primary, const char *name) + const char *name) { /* * If a driver asked to unregister a platform device registered by @@ -329,7 +328,7 @@ int aperture_remove_conflicting_pci_devices(struct pci_dev *pdev, const char *na base = pci_resource_start(pdev, bar); size = pci_resource_len(pdev, bar); - ret = aperture_remove_conflicting_devices(base, size, primary, name); + ret = aperture_remove_conflicting_devices(base, size, name); if (ret) return ret; } diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c index ec3f6cf05f8c..54f433e09ab8 100644 --- a/drivers/video/fbdev/hyperv_fb.c +++ b/drivers/video/fbdev/hyperv_fb.c @@ -1073,7 +1073,7 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info) info->screen_size = dio_fb_size; getmem_done: - aperture_remove_conflicting_devices(base, size, false, KBUILD_MODNAME); + aperture_remove_conflicting_devices(base, size, KBUILD_MODNAME); if (gen2vm) { /* framebuffer is reallocated, clear screen_info to avoid misuse from kexec */ diff --git a/include/linux/aperture.h b/include/linux/aperture.h index 442f15a57cad..7248727753be 100644 --- a/include/linux/aperture.h +++ b/include/linux/aperture.h @@ -14,7 +14,7 @@ int devm_aperture_acquire_for_platform_device(struct platform_device *pdev, resource_size_t size); int aperture_remove_conflicting_devices(resource_size_t base, resource_size_t size, - bool primary, const char *name); + const char *name); int aperture_remove_conflicting_pci_devices(struct pci_dev *pdev, const char *name); #else @@ -26,7 +26,7 @@ static inline int devm_aperture_acquire_for_platform_device(struct platform_devi } static inline int aperture_remove_conflicting_devices(resource_size_t base, resource_size_t size, - bool primary, const char *name) + const char *name) { return 0; } @@ -39,7 +39,6 @@ static inline int aperture_remove_conflicting_pci_devices(struct pci_dev *pdev, /** * aperture_remove_all_conflicting_devices - remove all existing framebuffers - * @primary: also kick vga16fb if present; only relevant for VGA devices * @name: a descriptive name of the requesting driver * * This function removes all graphics device drivers. Use this function on systems @@ -48,9 +47,9 @@ static inline int aperture_remove_conflicting_pci_devices(struct pci_dev *pdev, * Returns: * 0 on success, or a negative errno code otherwise */ -static inline int aperture_remove_all_conflicting_devices(bool primary, const char *name) +static inline int aperture_remove_all_conflicting_devices(const char *name) { - return aperture_remove_conflicting_devices(0, (resource_size_t)-1, primary, name); + return aperture_remove_conflicting_devices(0, (resource_size_t)-1, name); } #endif -- cgit v1.2.3 From 116b1c5a364bcbdc40be64d4f3ec9dbc32e264dd Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Thu, 6 Apr 2023 15:21:09 +0200 Subject: video/aperture: Provide a VGA helper for gma500 and internal use The hardware for gma500 is different from the rest, as it uses stolen framebuffer memory that is not available via PCI BAR. The regular PCI removal helper cannot detect the framebuffer, while the non-PCI helper misses possible conflicting VGA devices (i.e., a framebuffer or text console). Gma500 therefore calls both helpers to catch all cases. It's confusing as it implies that there's something about the PCI device that requires ownership management. The relationship between the PCI device and the VGA devices is non-obvious. At worst, readers might assume that calling two functions for clearing aperture ownership is a bug in the driver. Hence, move the PCI removal helper's code for VGA functionality into a separate function and call this function from gma500. Documents the purpose of each call to aperture helpers. The change contains comments and example code form the discussion at [1]. v5: * fix grammar in gma500 comment (Javier) Signed-off-by: Thomas Zimmermann Link: https://patchwork.kernel.org/project/dri-devel/patch/20230404201842.567344-1-daniel.vetter@ffwll.ch/ # 1 Reviewed-by: Javier Martinez Canillas Link: https://patchwork.freedesktop.org/patch/msgid/20230406132109.32050-10-tzimmermann@suse.de --- drivers/gpu/drm/gma500/psb_drv.c | 48 +++++++++++++++++++++++---------- drivers/video/aperture.c | 58 +++++++++++++++++++++++++++------------- include/linux/aperture.h | 7 +++++ 3 files changed, 81 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c index 4bb06a89e48d..8b64f61ffaf9 100644 --- a/drivers/gpu/drm/gma500/psb_drv.c +++ b/drivers/gpu/drm/gma500/psb_drv.c @@ -7,6 +7,7 @@ * **************************************************************************/ +#include #include #include #include @@ -19,7 +20,6 @@ #include #include -#include #include #include #include @@ -414,25 +414,45 @@ out_err: return ret; } -static int psb_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) +/* + * Hardware for gma500 is a hybrid device, which both acts as a PCI + * device (for legacy vga functionality) but also more like an + * integrated display on a SoC where the framebuffer simply + * resides in main memory and not in a special PCI bar (that + * internally redirects to a stolen range of main memory) like all + * other integrated PCI display devices implement it. + * + * To catch all cases we need to remove conflicting firmware devices + * for the stolen system memory and for the VGA functionality. As we + * currently cannot easily find the framebuffer's location in stolen + * memory, we remove all framebuffers here. + * + * TODO: Refactor psb_driver_load() to map vdc_reg earlier. Then + * we might be able to read the framebuffer range from the + * device. + */ +static int gma_remove_conflicting_framebuffers(struct pci_dev *pdev, + const struct drm_driver *req_driver) { - struct drm_psb_private *dev_priv; - struct drm_device *dev; + resource_size_t base = 0; + resource_size_t size = U32_MAX; /* 4 GiB HW limit */ + const char *name = req_driver->name; int ret; - /* - * We cannot yet easily find the framebuffer's location in memory. So - * remove all framebuffers here. Note that we still want the pci special - * handling to kick out vgacon. - * - * TODO: Refactor psb_driver_load() to map vdc_reg earlier. Then we - * might be able to read the framebuffer range from the device. - */ - ret = drm_aperture_remove_framebuffers(&driver); + ret = aperture_remove_conflicting_devices(base, size, name); if (ret) return ret; - ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &driver); + return __aperture_remove_legacy_vga_devices(pdev); +} + +static int psb_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) +{ + struct drm_psb_private *dev_priv; + struct drm_device *dev; + int ret; + + ret = gma_remove_conflicting_framebuffers(pdev, &driver); if (ret) return ret; diff --git a/drivers/video/aperture.c b/drivers/video/aperture.c index fa71f8257eed..561be8feca96 100644 --- a/drivers/video/aperture.c +++ b/drivers/video/aperture.c @@ -301,6 +301,37 @@ int aperture_remove_conflicting_devices(resource_size_t base, resource_size_t si } EXPORT_SYMBOL(aperture_remove_conflicting_devices); +/** + * __aperture_remove_legacy_vga_devices - remove legacy VGA devices of a PCI devices + * @pdev: PCI device + * + * This function removes VGA devices provided by @pdev, such as a VGA + * framebuffer or a console. This is useful if you have a VGA-compatible + * PCI graphics device with framebuffers in non-BAR locations. Drivers + * should acquire ownership of those memory areas and afterwards call + * this helper to release remaining VGA devices. + * + * If your hardware has its framebuffers accessible via PCI BARS, use + * aperture_remove_conflicting_pci_devices() instead. The function will + * release any VGA devices automatically. + * + * WARNING: Apparently we must remove graphics drivers before calling + * this helper. Otherwise the vga fbdev driver falls over if + * we have vgacon configured. + * + * Returns: + * 0 on success, or a negative errno code otherwise + */ +int __aperture_remove_legacy_vga_devices(struct pci_dev *pdev) +{ + /* VGA framebuffer */ + aperture_detach_devices(VGA_FB_PHYS_BASE, VGA_FB_PHYS_SIZE); + + /* VGA textmode console */ + return vga_remove_vgacon(pdev); +} +EXPORT_SYMBOL(__aperture_remove_legacy_vga_devices); + /** * aperture_remove_conflicting_pci_devices - remove existing framebuffers for PCI devices * @pdev: PCI device @@ -317,7 +348,7 @@ int aperture_remove_conflicting_pci_devices(struct pci_dev *pdev, const char *na { bool primary = false; resource_size_t base, size; - int bar, ret; + int bar, ret = 0; if (pdev == vga_default_device()) primary = true; @@ -334,24 +365,15 @@ int aperture_remove_conflicting_pci_devices(struct pci_dev *pdev, const char *na aperture_detach_devices(base, size); } - if (primary) { - /* - * If this is the primary adapter, there could be a VGA device - * that consumes the VGA framebuffer I/O range. Remove this - * device as well. - */ - aperture_detach_devices(VGA_FB_PHYS_BASE, VGA_FB_PHYS_SIZE); - - /* - * WARNING: Apparently we must kick fbdev drivers before vgacon, - * otherwise the vga fbdev driver falls over. - */ - ret = vga_remove_vgacon(pdev); - if (ret) - return ret; - } + /* + * If this is the primary adapter, there could be a VGA device + * that consumes the VGA framebuffer I/O range. Remove this + * device as well. + */ + if (primary) + ret = __aperture_remove_legacy_vga_devices(pdev); - return 0; + return ret; } EXPORT_SYMBOL(aperture_remove_conflicting_pci_devices); diff --git a/include/linux/aperture.h b/include/linux/aperture.h index 7248727753be..1a9a88b11584 100644 --- a/include/linux/aperture.h +++ b/include/linux/aperture.h @@ -16,6 +16,8 @@ int devm_aperture_acquire_for_platform_device(struct platform_device *pdev, int aperture_remove_conflicting_devices(resource_size_t base, resource_size_t size, const char *name); +int __aperture_remove_legacy_vga_devices(struct pci_dev *pdev); + int aperture_remove_conflicting_pci_devices(struct pci_dev *pdev, const char *name); #else static inline int devm_aperture_acquire_for_platform_device(struct platform_device *pdev, @@ -31,6 +33,11 @@ static inline int aperture_remove_conflicting_devices(resource_size_t base, reso return 0; } +static inline int __aperture_remove_legacy_vga_devices(struct pci_dev *pdev) +{ + return 0; +} + static inline int aperture_remove_conflicting_pci_devices(struct pci_dev *pdev, const char *name) { return 0; -- cgit v1.2.3 From 26662d7347a058ca497792c4b22ac91cc415cbf6 Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Thu, 20 Apr 2023 00:14:12 -0700 Subject: bpf: Add bpf_dynptr_size bpf_dynptr_size returns the number of usable bytes in a dynptr. Signed-off-by: Joanne Koong Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20230420071414.570108-4-joannelkoong@gmail.com --- include/linux/bpf.h | 2 +- kernel/bpf/helpers.c | 15 ++++++++++++--- kernel/trace/bpf_trace.c | 4 ++-- 3 files changed, 15 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e53ceee1df37..456f33b9d205 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1197,7 +1197,7 @@ enum bpf_dynptr_type { }; int bpf_dynptr_check_size(u32 size); -u32 bpf_dynptr_get_size(const struct bpf_dynptr_kern *ptr); +u32 __bpf_dynptr_size(const struct bpf_dynptr_kern *ptr); #ifdef CONFIG_BPF_JIT int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr); diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index a683b3e71a28..c465e97733b9 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1443,7 +1443,7 @@ static enum bpf_dynptr_type bpf_dynptr_get_type(const struct bpf_dynptr_kern *pt return (ptr->size & ~(DYNPTR_RDONLY_BIT)) >> DYNPTR_TYPE_SHIFT; } -u32 bpf_dynptr_get_size(const struct bpf_dynptr_kern *ptr) +u32 __bpf_dynptr_size(const struct bpf_dynptr_kern *ptr) { return ptr->size & DYNPTR_SIZE_MASK; } @@ -1476,7 +1476,7 @@ void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr) static int bpf_dynptr_check_off_len(const struct bpf_dynptr_kern *ptr, u32 offset, u32 len) { - u32 size = bpf_dynptr_get_size(ptr); + u32 size = __bpf_dynptr_size(ptr); if (len > size || offset > size - len) return -E2BIG; @@ -2311,7 +2311,7 @@ __bpf_kfunc int bpf_dynptr_adjust(struct bpf_dynptr_kern *ptr, u32 start, u32 en if (!ptr->data || start > end) return -EINVAL; - size = bpf_dynptr_get_size(ptr); + size = __bpf_dynptr_size(ptr); if (start > size || end > size) return -ERANGE; @@ -2335,6 +2335,14 @@ __bpf_kfunc bool bpf_dynptr_is_rdonly(struct bpf_dynptr_kern *ptr) return __bpf_dynptr_is_rdonly(ptr); } +__bpf_kfunc __u32 bpf_dynptr_size(const struct bpf_dynptr_kern *ptr) +{ + if (!ptr->data) + return -EINVAL; + + return __bpf_dynptr_size(ptr); +} + __bpf_kfunc void *bpf_cast_to_kern_ctx(void *obj) { return obj; @@ -2410,6 +2418,7 @@ BTF_ID_FLAGS(func, bpf_iter_num_destroy, KF_ITER_DESTROY) BTF_ID_FLAGS(func, bpf_dynptr_adjust) BTF_ID_FLAGS(func, bpf_dynptr_is_null) BTF_ID_FLAGS(func, bpf_dynptr_is_rdonly) +BTF_ID_FLAGS(func, bpf_dynptr_size) BTF_SET8_END(common_btf_ids) static const struct btf_kfunc_id_set common_kfunc_set = { diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index bcf91bc7bf71..8deb22a99abe 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1349,9 +1349,9 @@ __bpf_kfunc int bpf_verify_pkcs7_signature(struct bpf_dynptr_kern *data_ptr, } return verify_pkcs7_signature(data_ptr->data, - bpf_dynptr_get_size(data_ptr), + __bpf_dynptr_size(data_ptr), sig_ptr->data, - bpf_dynptr_get_size(sig_ptr), + __bpf_dynptr_size(sig_ptr), trusted_keyring->key, VERIFYING_UNSPECIFIED_SIGNATURE, NULL, NULL); -- cgit v1.2.3 From 7b9c13dd4d0ebbe89dfd7e1ecd09696037622101 Mon Sep 17 00:00:00 2001 From: Michał Mirosław Date: Mon, 1 May 2023 17:39:45 -0700 Subject: Input: i8042 - add missing include MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit include uses ENODEV when included with !IS_ENABLED(CONFIG_SERIO_I8042) and so need to include it. Signed-off-by: Michał Mirosław Link: https://lore.kernel.org/r/49fd4d400d1ab62095e5ed75a6637f883c0d071b.1682795105.git.mirq-linux@rere.qmqm.pl Signed-off-by: Dmitry Torokhov --- include/linux/i8042.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/i8042.h b/include/linux/i8042.h index 0261e2fb3636..95b07f8b77fe 100644 --- a/include/linux/i8042.h +++ b/include/linux/i8042.h @@ -3,6 +3,7 @@ #define _LINUX_I8042_H +#include #include /* -- cgit v1.2.3 From 0cce06ba859a515bd06224085d3addb870608b6d Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 25 Apr 2023 17:03:13 +0200 Subject: debugobjects,locking: Annotate debug_object_fill_pool() wait type violation There is an explicit wait-type violation in debug_object_fill_pool() for PREEMPT_RT=n kernels which allows them to more easily fill the object pool and reduce the chance of allocation failures. Lockdep's wait-type checks are designed to check the PREEMPT_RT locking rules even for PREEMPT_RT=n kernels and object to this, so create a lockdep annotation to allow this to stand. Specifically, create a 'lock' type that overrides the inner wait-type while it is held -- allowing one to temporarily raise it, such that the violation is hidden. Reported-by: Vlastimil Babka Reported-by: Qi Zheng Signed-off-by: Peter Zijlstra (Intel) Tested-by: Qi Zheng Link: https://lkml.kernel.org/r/20230429100614.GA1489784@hirez.programming.kicks-ass.net --- include/linux/lockdep.h | 14 ++++++++++++++ include/linux/lockdep_types.h | 1 + kernel/locking/lockdep.c | 28 +++++++++++++++++++++------- lib/debugobjects.c | 15 +++++++++++++-- 4 files changed, 49 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 1023f349af71..a3329fb49b33 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -339,6 +339,16 @@ extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie); #define lockdep_repin_lock(l,c) lock_repin_lock(&(l)->dep_map, (c)) #define lockdep_unpin_lock(l,c) lock_unpin_lock(&(l)->dep_map, (c)) +/* + * Must use lock_map_aquire_try() with override maps to avoid + * lockdep thinking they participate in the block chain. + */ +#define DEFINE_WAIT_OVERRIDE_MAP(_name, _wait_type) \ + struct lockdep_map _name = { \ + .name = #_name "-wait-type-override", \ + .wait_type_inner = _wait_type, \ + .lock_type = LD_LOCK_WAIT_OVERRIDE, } + #else /* !CONFIG_LOCKDEP */ static inline void lockdep_init_task(struct task_struct *task) @@ -427,6 +437,9 @@ extern int lockdep_is_held(const void *); #define lockdep_repin_lock(l, c) do { (void)(l); (void)(c); } while (0) #define lockdep_unpin_lock(l, c) do { (void)(l); (void)(c); } while (0) +#define DEFINE_WAIT_OVERRIDE_MAP(_name, _wait_type) \ + struct lockdep_map __maybe_unused _name = {} + #endif /* !LOCKDEP */ enum xhlock_context_t { @@ -551,6 +564,7 @@ do { \ #define rwsem_release(l, i) lock_release(l, i) #define lock_map_acquire(l) lock_acquire_exclusive(l, 0, 0, NULL, _THIS_IP_) +#define lock_map_acquire_try(l) lock_acquire_exclusive(l, 0, 1, NULL, _THIS_IP_) #define lock_map_acquire_read(l) lock_acquire_shared_recursive(l, 0, 0, NULL, _THIS_IP_) #define lock_map_acquire_tryread(l) lock_acquire_shared_recursive(l, 0, 1, NULL, _THIS_IP_) #define lock_map_release(l) lock_release(l, _THIS_IP_) diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h index d22430840b53..59f4fb1626ea 100644 --- a/include/linux/lockdep_types.h +++ b/include/linux/lockdep_types.h @@ -33,6 +33,7 @@ enum lockdep_wait_type { enum lockdep_lock_type { LD_LOCK_NORMAL = 0, /* normal, catch all */ LD_LOCK_PERCPU, /* percpu */ + LD_LOCK_WAIT_OVERRIDE, /* annotation */ LD_LOCK_MAX, }; diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 50d4863974e7..62ef295e07e6 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -2253,6 +2253,9 @@ static inline bool usage_match(struct lock_list *entry, void *mask) static inline bool usage_skip(struct lock_list *entry, void *mask) { + if (entry->class->lock_type == LD_LOCK_NORMAL) + return false; + /* * Skip local_lock() for irq inversion detection. * @@ -2279,14 +2282,16 @@ static inline bool usage_skip(struct lock_list *entry, void *mask) * As a result, we will skip local_lock(), when we search for irq * inversion bugs. */ - if (entry->class->lock_type == LD_LOCK_PERCPU) { - if (DEBUG_LOCKS_WARN_ON(entry->class->wait_type_inner < LD_WAIT_CONFIG)) - return false; + if (entry->class->lock_type == LD_LOCK_PERCPU && + DEBUG_LOCKS_WARN_ON(entry->class->wait_type_inner < LD_WAIT_CONFIG)) + return false; - return true; - } + /* + * Skip WAIT_OVERRIDE for irq inversion detection -- it's not actually + * a lock and only used to override the wait_type. + */ - return false; + return true; } /* @@ -4752,7 +4757,8 @@ static int check_wait_context(struct task_struct *curr, struct held_lock *next) for (; depth < curr->lockdep_depth; depth++) { struct held_lock *prev = curr->held_locks + depth; - u8 prev_inner = hlock_class(prev)->wait_type_inner; + struct lock_class *class = hlock_class(prev); + u8 prev_inner = class->wait_type_inner; if (prev_inner) { /* @@ -4762,6 +4768,14 @@ static int check_wait_context(struct task_struct *curr, struct held_lock *next) * Also due to trylocks. */ curr_inner = min(curr_inner, prev_inner); + + /* + * Allow override for annotations -- this is typically + * only valid/needed for code that only exists when + * CONFIG_PREEMPT_RT=n. + */ + if (unlikely(class->lock_type == LD_LOCK_WAIT_OVERRIDE)) + curr_inner = prev_inner; } } diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 003edc5ebd67..826c617b10a7 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -591,10 +591,21 @@ static void debug_objects_fill_pool(void) { /* * On RT enabled kernels the pool refill must happen in preemptible - * context: + * context -- for !RT kernels we rely on the fact that spinlock_t and + * raw_spinlock_t are basically the same type and this lock-type + * inversion works just fine. */ - if (!IS_ENABLED(CONFIG_PREEMPT_RT) || preemptible()) + if (!IS_ENABLED(CONFIG_PREEMPT_RT) || preemptible()) { + /* + * Annotate away the spinlock_t inside raw_spinlock_t warning + * by temporarily raising the wait-type to WAIT_SLEEP, matching + * the preemptible() condition above. + */ + static DEFINE_WAIT_OVERRIDE_MAP(fill_pool_map, LD_WAIT_SLEEP); + lock_map_acquire_try(&fill_pool_map); fill_pool(); + lock_map_release(&fill_pool_map); + } } static void -- cgit v1.2.3 From 407958a0e980b9e1842ab87b5a1040521e1e24e9 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 4 May 2023 21:33:10 -0700 Subject: bpf: encapsulate precision backtracking bookkeeping Add struct backtrack_state and straightforward API around it to keep track of register and stack masks used and maintained during precision backtracking process. Having this logic separately allow to keep high-level backtracking algorithm cleaner, but also it sets us up to cleanly keep track of register and stack masks per frame, allowing (with some further logic adjustments) to perform precision backpropagation across multiple frames (i.e., subprog calls). Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20230505043317.3629845-4-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 14 +++ kernel/bpf/verifier.c | 249 +++++++++++++++++++++++++++++++------------ 2 files changed, 196 insertions(+), 67 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 3dd29a53b711..33f541366f4e 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -238,6 +238,10 @@ enum bpf_stack_slot_type { #define BPF_REG_SIZE 8 /* size of eBPF register in bytes */ +#define BPF_REGMASK_ARGS ((1 << BPF_REG_1) | (1 << BPF_REG_2) | \ + (1 << BPF_REG_3) | (1 << BPF_REG_4) | \ + (1 << BPF_REG_5)) + #define BPF_DYNPTR_SIZE sizeof(struct bpf_dynptr_kern) #define BPF_DYNPTR_NR_SLOTS (BPF_DYNPTR_SIZE / BPF_REG_SIZE) @@ -541,6 +545,15 @@ struct bpf_subprog_info { bool is_async_cb; }; +struct bpf_verifier_env; + +struct backtrack_state { + struct bpf_verifier_env *env; + u32 frame; + u32 reg_masks[MAX_CALL_FRAMES]; + u64 stack_masks[MAX_CALL_FRAMES]; +}; + /* single container for all structs * one verifier_env per bpf_check() call */ @@ -578,6 +591,7 @@ struct bpf_verifier_env { int *insn_stack; int cur_stack; } cfg; + struct backtrack_state bt; u32 pass_cnt; /* number of times do_check() was called */ u32 subprog_cnt; /* number of instructions analyzed by the verifier */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index da8a5834f2ca..9b2e571250e1 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1296,6 +1296,12 @@ static bool is_spilled_reg(const struct bpf_stack_state *stack) return stack->slot_type[BPF_REG_SIZE - 1] == STACK_SPILL; } +static bool is_spilled_scalar_reg(const struct bpf_stack_state *stack) +{ + return stack->slot_type[BPF_REG_SIZE - 1] == STACK_SPILL && + stack->spilled_ptr.type == SCALAR_VALUE; +} + static void scrub_spilled_slot(u8 *stype) { if (*stype != STACK_INVALID) @@ -3186,12 +3192,128 @@ static const char *disasm_kfunc_name(void *data, const struct bpf_insn *insn) return btf_name_by_offset(desc_btf, func->name_off); } +static inline void bt_init(struct backtrack_state *bt, u32 frame) +{ + bt->frame = frame; +} + +static inline void bt_reset(struct backtrack_state *bt) +{ + struct bpf_verifier_env *env = bt->env; + + memset(bt, 0, sizeof(*bt)); + bt->env = env; +} + +static inline u32 bt_empty(struct backtrack_state *bt) +{ + u64 mask = 0; + int i; + + for (i = 0; i <= bt->frame; i++) + mask |= bt->reg_masks[i] | bt->stack_masks[i]; + + return mask == 0; +} + +static inline int bt_subprog_enter(struct backtrack_state *bt) +{ + if (bt->frame == MAX_CALL_FRAMES - 1) { + verbose(bt->env, "BUG subprog enter from frame %d\n", bt->frame); + WARN_ONCE(1, "verifier backtracking bug"); + return -EFAULT; + } + bt->frame++; + return 0; +} + +static inline int bt_subprog_exit(struct backtrack_state *bt) +{ + if (bt->frame == 0) { + verbose(bt->env, "BUG subprog exit from frame 0\n"); + WARN_ONCE(1, "verifier backtracking bug"); + return -EFAULT; + } + bt->frame--; + return 0; +} + +static inline void bt_set_frame_reg(struct backtrack_state *bt, u32 frame, u32 reg) +{ + bt->reg_masks[frame] |= 1 << reg; +} + +static inline void bt_clear_frame_reg(struct backtrack_state *bt, u32 frame, u32 reg) +{ + bt->reg_masks[frame] &= ~(1 << reg); +} + +static inline void bt_set_reg(struct backtrack_state *bt, u32 reg) +{ + bt_set_frame_reg(bt, bt->frame, reg); +} + +static inline void bt_clear_reg(struct backtrack_state *bt, u32 reg) +{ + bt_clear_frame_reg(bt, bt->frame, reg); +} + +static inline void bt_set_frame_slot(struct backtrack_state *bt, u32 frame, u32 slot) +{ + bt->stack_masks[frame] |= 1ull << slot; +} + +static inline void bt_clear_frame_slot(struct backtrack_state *bt, u32 frame, u32 slot) +{ + bt->stack_masks[frame] &= ~(1ull << slot); +} + +static inline void bt_set_slot(struct backtrack_state *bt, u32 slot) +{ + bt_set_frame_slot(bt, bt->frame, slot); +} + +static inline void bt_clear_slot(struct backtrack_state *bt, u32 slot) +{ + bt_clear_frame_slot(bt, bt->frame, slot); +} + +static inline u32 bt_frame_reg_mask(struct backtrack_state *bt, u32 frame) +{ + return bt->reg_masks[frame]; +} + +static inline u32 bt_reg_mask(struct backtrack_state *bt) +{ + return bt->reg_masks[bt->frame]; +} + +static inline u64 bt_frame_stack_mask(struct backtrack_state *bt, u32 frame) +{ + return bt->stack_masks[frame]; +} + +static inline u64 bt_stack_mask(struct backtrack_state *bt) +{ + return bt->stack_masks[bt->frame]; +} + +static inline bool bt_is_reg_set(struct backtrack_state *bt, u32 reg) +{ + return bt->reg_masks[bt->frame] & (1 << reg); +} + +static inline bool bt_is_slot_set(struct backtrack_state *bt, u32 slot) +{ + return bt->stack_masks[bt->frame] & (1ull << slot); +} + /* For given verifier state backtrack_insn() is called from the last insn to * the first insn. Its purpose is to compute a bitmask of registers and * stack slots that needs precision in the parent verifier state. */ static int backtrack_insn(struct bpf_verifier_env *env, int idx, - u32 *reg_mask, u64 *stack_mask) + struct backtrack_state *bt) { const struct bpf_insn_cbs cbs = { .cb_call = disasm_kfunc_name, @@ -3202,20 +3324,20 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, u8 class = BPF_CLASS(insn->code); u8 opcode = BPF_OP(insn->code); u8 mode = BPF_MODE(insn->code); - u32 dreg = 1u << insn->dst_reg; - u32 sreg = 1u << insn->src_reg; + u32 dreg = insn->dst_reg; + u32 sreg = insn->src_reg; u32 spi; if (insn->code == 0) return 0; if (env->log.level & BPF_LOG_LEVEL2) { - verbose(env, "regs=%x stack=%llx before ", *reg_mask, *stack_mask); + verbose(env, "regs=%x stack=%llx before ", bt_reg_mask(bt), bt_stack_mask(bt)); verbose(env, "%d: ", idx); print_bpf_insn(&cbs, insn, env->allow_ptr_leaks); } if (class == BPF_ALU || class == BPF_ALU64) { - if (!(*reg_mask & dreg)) + if (!bt_is_reg_set(bt, dreg)) return 0; if (opcode == BPF_MOV) { if (BPF_SRC(insn->code) == BPF_X) { @@ -3223,8 +3345,8 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, * dreg needs precision after this insn * sreg needs precision before this insn */ - *reg_mask &= ~dreg; - *reg_mask |= sreg; + bt_clear_reg(bt, dreg); + bt_set_reg(bt, sreg); } else { /* dreg = K * dreg needs precision after this insn. @@ -3232,7 +3354,7 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, * as precise=true in this verifier state. * No further markings in parent are necessary */ - *reg_mask &= ~dreg; + bt_clear_reg(bt, dreg); } } else { if (BPF_SRC(insn->code) == BPF_X) { @@ -3240,15 +3362,15 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, * both dreg and sreg need precision * before this insn */ - *reg_mask |= sreg; + bt_set_reg(bt, sreg); } /* else dreg += K * dreg still needs precision before this insn */ } } else if (class == BPF_LDX) { - if (!(*reg_mask & dreg)) + if (!bt_is_reg_set(bt, dreg)) return 0; - *reg_mask &= ~dreg; + bt_clear_reg(bt, dreg); /* scalars can only be spilled into stack w/o losing precision. * Load from any other memory can be zero extended. @@ -3269,9 +3391,9 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; } - *stack_mask |= 1ull << spi; + bt_set_slot(bt, spi); } else if (class == BPF_STX || class == BPF_ST) { - if (*reg_mask & dreg) + if (bt_is_reg_set(bt, dreg)) /* stx & st shouldn't be using _scalar_ dst_reg * to access memory. It means backtracking * encountered a case of pointer subtraction. @@ -3286,11 +3408,11 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; } - if (!(*stack_mask & (1ull << spi))) + if (!bt_is_slot_set(bt, spi)) return 0; - *stack_mask &= ~(1ull << spi); + bt_clear_slot(bt, spi); if (class == BPF_STX) - *reg_mask |= sreg; + bt_set_reg(bt, sreg); } else if (class == BPF_JMP || class == BPF_JMP32) { if (opcode == BPF_CALL) { if (insn->src_reg == BPF_PSEUDO_CALL) @@ -3307,19 +3429,19 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL && insn->imm == 0) return -ENOTSUPP; /* regular helper call sets R0 */ - *reg_mask &= ~1; - if (*reg_mask & 0x3f) { + bt_clear_reg(bt, BPF_REG_0); + if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) { /* if backtracing was looking for registers R1-R5 * they should have been found already. */ - verbose(env, "BUG regs %x\n", *reg_mask); + verbose(env, "BUG regs %x\n", bt_reg_mask(bt)); WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; } } else if (opcode == BPF_EXIT) { return -ENOTSUPP; } else if (BPF_SRC(insn->code) == BPF_X) { - if (!(*reg_mask & (dreg | sreg))) + if (!bt_is_reg_set(bt, dreg) && !bt_is_reg_set(bt, sreg)) return 0; /* dreg sreg * Both dreg and sreg need precision before @@ -3327,7 +3449,8 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, * before it would be equally necessary to * propagate it to dreg. */ - *reg_mask |= (sreg | dreg); + bt_set_reg(bt, dreg); + bt_set_reg(bt, sreg); /* else dreg K * Only dreg still needs precision before * this insn, so for the K-based conditional @@ -3335,9 +3458,9 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, */ } } else if (class == BPF_LD) { - if (!(*reg_mask & dreg)) + if (!bt_is_reg_set(bt, dreg)) return 0; - *reg_mask &= ~dreg; + bt_clear_reg(bt, dreg); /* It's ld_imm64 or ld_abs or ld_ind. * For ld_imm64 no further tracking of precision * into parent is necessary @@ -3550,20 +3673,21 @@ static void mark_all_scalars_imprecise(struct bpf_verifier_env *env, struct bpf_ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int regno, int spi) { + struct backtrack_state *bt = &env->bt; struct bpf_verifier_state *st = env->cur_state; int first_idx = st->first_insn_idx; int last_idx = env->insn_idx; struct bpf_func_state *func; struct bpf_reg_state *reg; - u32 reg_mask = regno >= 0 ? 1u << regno : 0; - u64 stack_mask = spi >= 0 ? 1ull << spi : 0; bool skip_first = true; - bool new_marks = false; int i, err; if (!env->bpf_capable) return 0; + /* set frame number from which we are starting to backtrack */ + bt_init(bt, frame); + /* Do sanity checks against current state of register and/or stack * slot, but don't set precise flag in current state, as precision * tracking in the current state is unnecessary. @@ -3575,26 +3699,17 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r WARN_ONCE(1, "backtracing misuse"); return -EFAULT; } - new_marks = true; + bt_set_reg(bt, regno); } while (spi >= 0) { - if (!is_spilled_reg(&func->stack[spi])) { - stack_mask = 0; + if (!is_spilled_scalar_reg(&func->stack[spi])) break; - } - reg = &func->stack[spi].spilled_ptr; - if (reg->type != SCALAR_VALUE) { - stack_mask = 0; - break; - } - new_marks = true; + bt_set_slot(bt, spi); break; } - if (!new_marks) - return 0; - if (!reg_mask && !stack_mask) + if (bt_empty(bt)) return 0; for (;;) { @@ -3613,12 +3728,13 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r if (st->curframe == 0 && st->frame[0]->subprogno > 0 && st->frame[0]->callsite == BPF_MAIN_FUNC && - stack_mask == 0 && (reg_mask & ~0x3e) == 0) { - bitmap_from_u64(mask, reg_mask); + bt_stack_mask(bt) == 0 && + (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) == 0) { + bitmap_from_u64(mask, bt_reg_mask(bt)); for_each_set_bit(i, mask, 32) { reg = &st->frame[0]->regs[i]; if (reg->type != SCALAR_VALUE) { - reg_mask &= ~(1u << i); + bt_clear_reg(bt, i); continue; } reg->precise = true; @@ -3626,8 +3742,8 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r return 0; } - verbose(env, "BUG backtracing func entry subprog %d reg_mask %x stack_mask %llx\n", - st->frame[0]->subprogno, reg_mask, stack_mask); + verbose(env, "BUG backtracking func entry subprog %d reg_mask %x stack_mask %llx\n", + st->frame[0]->subprogno, bt_reg_mask(bt), bt_stack_mask(bt)); WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; } @@ -3637,15 +3753,16 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r err = 0; skip_first = false; } else { - err = backtrack_insn(env, i, ®_mask, &stack_mask); + err = backtrack_insn(env, i, bt); } if (err == -ENOTSUPP) { mark_all_scalars_precise(env, st); + bt_reset(bt); return 0; } else if (err) { return err; } - if (!reg_mask && !stack_mask) + if (bt_empty(bt)) /* Found assignment(s) into tracked register in this state. * Since this state is already marked, just return. * Nothing to be tracked further in the parent state. @@ -3670,21 +3787,21 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r if (!st) break; - new_marks = false; func = st->frame[frame]; - bitmap_from_u64(mask, reg_mask); + bitmap_from_u64(mask, bt_reg_mask(bt)); for_each_set_bit(i, mask, 32) { reg = &func->regs[i]; if (reg->type != SCALAR_VALUE) { - reg_mask &= ~(1u << i); + bt_clear_reg(bt, i); continue; } - if (!reg->precise) - new_marks = true; - reg->precise = true; + if (reg->precise) + bt_clear_reg(bt, i); + else + reg->precise = true; } - bitmap_from_u64(mask, stack_mask); + bitmap_from_u64(mask, bt_stack_mask(bt)); for_each_set_bit(i, mask, 64) { if (i >= func->allocated_stack / BPF_REG_SIZE) { /* the sequence of instructions: @@ -3701,32 +3818,28 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r * In such case fallback to conservative. */ mark_all_scalars_precise(env, st); + bt_reset(bt); return 0; } - if (!is_spilled_reg(&func->stack[i])) { - stack_mask &= ~(1ull << i); + if (!is_spilled_scalar_reg(&func->stack[i])) { + bt_clear_slot(bt, i); continue; } reg = &func->stack[i].spilled_ptr; - if (reg->type != SCALAR_VALUE) { - stack_mask &= ~(1ull << i); - continue; - } - if (!reg->precise) - new_marks = true; - reg->precise = true; + if (reg->precise) + bt_clear_slot(bt, i); + else + reg->precise = true; } if (env->log.level & BPF_LOG_LEVEL2) { verbose(env, "parent %s regs=%x stack=%llx marks:", - new_marks ? "didn't have" : "already had", - reg_mask, stack_mask); + !bt_empty(bt) ? "didn't have" : "already had", + bt_reg_mask(bt), bt_stack_mask(bt)); print_verifier_state(env, func, true); } - if (!reg_mask && !stack_mask) - break; - if (!new_marks) + if (bt_empty(bt)) break; last_idx = st->last_insn_idx; @@ -18872,6 +18985,8 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 if (!env) return -ENOMEM; + env->bt.env = env; + len = (*prog)->len; env->insn_aux_data = vzalloc(array_size(sizeof(struct bpf_insn_aux_data), len)); -- cgit v1.2.3 From d9439c21a9e4769bfd83a03ab39056164d44ac31 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 4 May 2023 21:33:11 -0700 Subject: bpf: improve precision backtrack logging Add helper to format register and stack masks in more human-readable format. Adjust logging a bit during backtrack propagation and especially during forcing precision fallback logic to make it clearer what's going on (with log_level=2, of course), and also start reporting affected frame depth. This is in preparation for having more than one active frame later when precision propagation between subprog calls is added. Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20230505043317.3629845-5-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 13 ++- kernel/bpf/verifier.c | 72 +++++++++++++++-- tools/testing/selftests/bpf/verifier/precise.c | 106 +++++++++++++------------ 3 files changed, 128 insertions(+), 63 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 33f541366f4e..5b11a3b0fec0 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -18,8 +18,11 @@ * that converting umax_value to int cannot overflow. */ #define BPF_MAX_VAR_SIZ (1 << 29) -/* size of type_str_buf in bpf_verifier. */ -#define TYPE_STR_BUF_LEN 128 +/* size of tmp_str_buf in bpf_verifier. + * we need at least 306 bytes to fit full stack mask representation + * (in the "-8,-16,...,-512" form) + */ +#define TMP_STR_BUF_LEN 320 /* Liveness marks, used for registers and spilled-regs (in stack slots). * Read marks propagate upwards until they find a write mark; they record that @@ -620,8 +623,10 @@ struct bpf_verifier_env { /* Same as scratched_regs but for stack slots */ u64 scratched_stack_slots; u64 prev_log_pos, prev_insn_print_pos; - /* buffer used in reg_type_str() to generate reg_type string */ - char type_str_buf[TYPE_STR_BUF_LEN]; + /* buffer used to generate temporary string representations, + * e.g., in reg_type_str() to generate reg_type string + */ + char tmp_str_buf[TMP_STR_BUF_LEN]; }; __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log, diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 9b2e571250e1..5412c8c8511d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -605,9 +605,9 @@ static const char *reg_type_str(struct bpf_verifier_env *env, type & PTR_TRUSTED ? "trusted_" : "" ); - snprintf(env->type_str_buf, TYPE_STR_BUF_LEN, "%s%s%s", + snprintf(env->tmp_str_buf, TMP_STR_BUF_LEN, "%s%s%s", prefix, str[base_type(type)], postfix); - return env->type_str_buf; + return env->tmp_str_buf; } static char slot_type_char[] = { @@ -3308,6 +3308,45 @@ static inline bool bt_is_slot_set(struct backtrack_state *bt, u32 slot) return bt->stack_masks[bt->frame] & (1ull << slot); } +/* format registers bitmask, e.g., "r0,r2,r4" for 0x15 mask */ +static void fmt_reg_mask(char *buf, ssize_t buf_sz, u32 reg_mask) +{ + DECLARE_BITMAP(mask, 64); + bool first = true; + int i, n; + + buf[0] = '\0'; + + bitmap_from_u64(mask, reg_mask); + for_each_set_bit(i, mask, 32) { + n = snprintf(buf, buf_sz, "%sr%d", first ? "" : ",", i); + first = false; + buf += n; + buf_sz -= n; + if (buf_sz < 0) + break; + } +} +/* format stack slots bitmask, e.g., "-8,-24,-40" for 0x15 mask */ +static void fmt_stack_mask(char *buf, ssize_t buf_sz, u64 stack_mask) +{ + DECLARE_BITMAP(mask, 64); + bool first = true; + int i, n; + + buf[0] = '\0'; + + bitmap_from_u64(mask, stack_mask); + for_each_set_bit(i, mask, 64) { + n = snprintf(buf, buf_sz, "%s%d", first ? "" : ",", -(i + 1) * 8); + first = false; + buf += n; + buf_sz -= n; + if (buf_sz < 0) + break; + } +} + /* For given verifier state backtrack_insn() is called from the last insn to * the first insn. Its purpose is to compute a bitmask of registers and * stack slots that needs precision in the parent verifier state. @@ -3331,7 +3370,11 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, if (insn->code == 0) return 0; if (env->log.level & BPF_LOG_LEVEL2) { - verbose(env, "regs=%x stack=%llx before ", bt_reg_mask(bt), bt_stack_mask(bt)); + fmt_reg_mask(env->tmp_str_buf, TMP_STR_BUF_LEN, bt_reg_mask(bt)); + verbose(env, "mark_precise: frame%d: regs=%s ", + bt->frame, env->tmp_str_buf); + fmt_stack_mask(env->tmp_str_buf, TMP_STR_BUF_LEN, bt_stack_mask(bt)); + verbose(env, "stack=%s before ", env->tmp_str_buf); verbose(env, "%d: ", idx); print_bpf_insn(&cbs, insn, env->allow_ptr_leaks); } @@ -3531,6 +3574,11 @@ static void mark_all_scalars_precise(struct bpf_verifier_env *env, struct bpf_reg_state *reg; int i, j; + if (env->log.level & BPF_LOG_LEVEL2) { + verbose(env, "mark_precise: frame%d: falling back to forcing all scalars precise\n", + st->curframe); + } + /* big hammer: mark all scalars precise in this path. * pop_stack may still get !precise scalars. * We also skip current state and go straight to first parent state, @@ -3542,17 +3590,25 @@ static void mark_all_scalars_precise(struct bpf_verifier_env *env, func = st->frame[i]; for (j = 0; j < BPF_REG_FP; j++) { reg = &func->regs[j]; - if (reg->type != SCALAR_VALUE) + if (reg->type != SCALAR_VALUE || reg->precise) continue; reg->precise = true; + if (env->log.level & BPF_LOG_LEVEL2) { + verbose(env, "force_precise: frame%d: forcing r%d to be precise\n", + i, j); + } } for (j = 0; j < func->allocated_stack / BPF_REG_SIZE; j++) { if (!is_spilled_reg(&func->stack[j])) continue; reg = &func->stack[j].spilled_ptr; - if (reg->type != SCALAR_VALUE) + if (reg->type != SCALAR_VALUE || reg->precise) continue; reg->precise = true; + if (env->log.level & BPF_LOG_LEVEL2) { + verbose(env, "force_precise: frame%d: forcing fp%d to be precise\n", + i, -(j + 1) * 8); + } } } } @@ -3716,8 +3772,10 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r DECLARE_BITMAP(mask, 64); u32 history = st->jmp_history_cnt; - if (env->log.level & BPF_LOG_LEVEL2) - verbose(env, "last_idx %d first_idx %d\n", last_idx, first_idx); + if (env->log.level & BPF_LOG_LEVEL2) { + verbose(env, "mark_precise: frame%d: last_idx %d first_idx %d\n", + bt->frame, last_idx, first_idx); + } if (last_idx < 0) { /* we are at the entry into subprog, which diff --git a/tools/testing/selftests/bpf/verifier/precise.c b/tools/testing/selftests/bpf/verifier/precise.c index 8f0340eed696..a22fabd404ed 100644 --- a/tools/testing/selftests/bpf/verifier/precise.c +++ b/tools/testing/selftests/bpf/verifier/precise.c @@ -38,25 +38,24 @@ .fixup_map_array_48b = { 1 }, .result = VERBOSE_ACCEPT, .errstr = - "26: (85) call bpf_probe_read_kernel#113\ - last_idx 26 first_idx 20\ - regs=4 stack=0 before 25\ - regs=4 stack=0 before 24\ - regs=4 stack=0 before 23\ - regs=4 stack=0 before 22\ - regs=4 stack=0 before 20\ - parent didn't have regs=4 stack=0 marks\ - last_idx 19 first_idx 10\ - regs=4 stack=0 before 19\ - regs=200 stack=0 before 18\ - regs=300 stack=0 before 17\ - regs=201 stack=0 before 15\ - regs=201 stack=0 before 14\ - regs=200 stack=0 before 13\ - regs=200 stack=0 before 12\ - regs=200 stack=0 before 11\ - regs=200 stack=0 before 10\ - parent already had regs=0 stack=0 marks", + "mark_precise: frame0: last_idx 26 first_idx 20\ + mark_precise: frame0: regs=r2 stack= before 25\ + mark_precise: frame0: regs=r2 stack= before 24\ + mark_precise: frame0: regs=r2 stack= before 23\ + mark_precise: frame0: regs=r2 stack= before 22\ + mark_precise: frame0: regs=r2 stack= before 20\ + parent didn't have regs=4 stack=0 marks:\ + mark_precise: frame0: last_idx 19 first_idx 10\ + mark_precise: frame0: regs=r2 stack= before 19\ + mark_precise: frame0: regs=r9 stack= before 18\ + mark_precise: frame0: regs=r8,r9 stack= before 17\ + mark_precise: frame0: regs=r0,r9 stack= before 15\ + mark_precise: frame0: regs=r0,r9 stack= before 14\ + mark_precise: frame0: regs=r9 stack= before 13\ + mark_precise: frame0: regs=r9 stack= before 12\ + mark_precise: frame0: regs=r9 stack= before 11\ + mark_precise: frame0: regs=r9 stack= before 10\ + parent already had regs=0 stack=0 marks:", }, { "precise: test 2", @@ -100,20 +99,20 @@ .flags = BPF_F_TEST_STATE_FREQ, .errstr = "26: (85) call bpf_probe_read_kernel#113\ - last_idx 26 first_idx 22\ - regs=4 stack=0 before 25\ - regs=4 stack=0 before 24\ - regs=4 stack=0 before 23\ - regs=4 stack=0 before 22\ - parent didn't have regs=4 stack=0 marks\ - last_idx 20 first_idx 20\ - regs=4 stack=0 before 20\ - parent didn't have regs=4 stack=0 marks\ - last_idx 19 first_idx 17\ - regs=4 stack=0 before 19\ - regs=200 stack=0 before 18\ - regs=300 stack=0 before 17\ - parent already had regs=0 stack=0 marks", + mark_precise: frame0: last_idx 26 first_idx 22\ + mark_precise: frame0: regs=r2 stack= before 25\ + mark_precise: frame0: regs=r2 stack= before 24\ + mark_precise: frame0: regs=r2 stack= before 23\ + mark_precise: frame0: regs=r2 stack= before 22\ + parent didn't have regs=4 stack=0 marks:\ + mark_precise: frame0: last_idx 20 first_idx 20\ + mark_precise: frame0: regs=r2 stack= before 20\ + parent didn't have regs=4 stack=0 marks:\ + mark_precise: frame0: last_idx 19 first_idx 17\ + mark_precise: frame0: regs=r2 stack= before 19\ + mark_precise: frame0: regs=r9 stack= before 18\ + mark_precise: frame0: regs=r8,r9 stack= before 17\ + parent already had regs=0 stack=0 marks:", }, { "precise: cross frame pruning", @@ -153,15 +152,15 @@ }, .prog_type = BPF_PROG_TYPE_XDP, .flags = BPF_F_TEST_STATE_FREQ, - .errstr = "5: (2d) if r4 > r0 goto pc+0\ - last_idx 5 first_idx 5\ - parent didn't have regs=10 stack=0 marks\ - last_idx 4 first_idx 2\ - regs=10 stack=0 before 4\ - regs=10 stack=0 before 3\ - regs=0 stack=1 before 2\ - last_idx 5 first_idx 5\ - parent didn't have regs=1 stack=0 marks", + .errstr = "mark_precise: frame0: last_idx 5 first_idx 5\ + parent didn't have regs=10 stack=0 marks:\ + mark_precise: frame0: last_idx 4 first_idx 2\ + mark_precise: frame0: regs=r4 stack= before 4\ + mark_precise: frame0: regs=r4 stack= before 3\ + mark_precise: frame0: regs= stack=-8 before 2\ + mark_precise: frame0: falling back to forcing all scalars precise\ + mark_precise: frame0: last_idx 5 first_idx 5\ + parent didn't have regs=1 stack=0 marks:", .result = VERBOSE_ACCEPT, .retval = -1, }, @@ -179,16 +178,19 @@ }, .prog_type = BPF_PROG_TYPE_XDP, .flags = BPF_F_TEST_STATE_FREQ, - .errstr = "last_idx 6 first_idx 6\ - parent didn't have regs=10 stack=0 marks\ - last_idx 5 first_idx 3\ - regs=10 stack=0 before 5\ - regs=10 stack=0 before 4\ - regs=0 stack=1 before 3\ - last_idx 6 first_idx 6\ - parent didn't have regs=1 stack=0 marks\ - last_idx 5 first_idx 3\ - regs=1 stack=0 before 5", + .errstr = "mark_precise: frame0: last_idx 6 first_idx 6\ + parent didn't have regs=10 stack=0 marks:\ + mark_precise: frame0: last_idx 5 first_idx 3\ + mark_precise: frame0: regs=r4 stack= before 5\ + mark_precise: frame0: regs=r4 stack= before 4\ + mark_precise: frame0: regs= stack=-8 before 3\ + mark_precise: frame0: falling back to forcing all scalars precise\ + force_precise: frame0: forcing r0 to be precise\ + force_precise: frame0: forcing r0 to be precise\ + mark_precise: frame0: last_idx 6 first_idx 6\ + parent didn't have regs=1 stack=0 marks:\ + mark_precise: frame0: last_idx 5 first_idx 3\ + mark_precise: frame0: regs=r0 stack= before 5", .result = VERBOSE_ACCEPT, .retval = -1, }, -- cgit v1.2.3 From 3bda08b63670c39be390fcb00e7718775508e673 Mon Sep 17 00:00:00 2001 From: Daniel Rosenberg Date: Fri, 5 May 2023 18:31:30 -0700 Subject: bpf: Allow NULL buffers in bpf_dynptr_slice(_rw) bpf_dynptr_slice(_rw) uses a user provided buffer if it can not provide a pointer to a block of contiguous memory. This buffer is unused in the case of local dynptrs, and may be unused in other cases as well. There is no need to require the buffer, as the kfunc can just return NULL if it was needed and not provided. This adds another kfunc annotation, __opt, which combines with __sz and __szk to allow the buffer associated with the size to be NULL. If the buffer is NULL, the verifier does not check that the buffer is of sufficient size. Signed-off-by: Daniel Rosenberg Link: https://lore.kernel.org/r/20230506013134.2492210-2-drosen@google.com Signed-off-by: Alexei Starovoitov --- Documentation/bpf/kfuncs.rst | 23 ++++++++++++++++++++++- include/linux/skbuff.h | 2 +- kernel/bpf/helpers.c | 30 ++++++++++++++++++------------ kernel/bpf/verifier.c | 17 +++++++++++++---- 4 files changed, 54 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/Documentation/bpf/kfuncs.rst b/Documentation/bpf/kfuncs.rst index ea2516374d92..7a3d9de5f315 100644 --- a/Documentation/bpf/kfuncs.rst +++ b/Documentation/bpf/kfuncs.rst @@ -100,7 +100,7 @@ Hence, whenever a constant scalar argument is accepted by a kfunc which is not a size parameter, and the value of the constant matters for program safety, __k suffix should be used. -2.2.2 __uninit Annotation +2.2.3 __uninit Annotation ------------------------- This annotation is used to indicate that the argument will be treated as @@ -117,6 +117,27 @@ Here, the dynptr will be treated as an uninitialized dynptr. Without this annotation, the verifier will reject the program if the dynptr passed in is not initialized. +2.2.4 __opt Annotation +------------------------- + +This annotation is used to indicate that the buffer associated with an __sz or __szk +argument may be null. If the function is passed a nullptr in place of the buffer, +the verifier will not check that length is appropriate for the buffer. The kfunc is +responsible for checking if this buffer is null before using it. + +An example is given below:: + + __bpf_kfunc void *bpf_dynptr_slice(..., void *buffer__opt, u32 buffer__szk) + { + ... + } + +Here, the buffer may be null. If buffer is not null, it at least of size buffer_szk. +Either way, the returned buffer is either NULL, or of size buffer_szk. Without this +annotation, the verifier will reject the program if a null pointer is passed in with +a nonzero size. + + .. _BPF_kfunc_nodef: 2.3 Using an existing kernel function diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 738776ab8838..8ddb4af1a501 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4033,7 +4033,7 @@ __skb_header_pointer(const struct sk_buff *skb, int offset, int len, if (likely(hlen - offset >= len)) return (void *)data + offset; - if (!skb || unlikely(skb_copy_bits(skb, offset, buffer, len) < 0)) + if (!skb || !buffer || unlikely(skb_copy_bits(skb, offset, buffer, len) < 0)) return NULL; return buffer; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index a128fe0ab2d0..4ef4c4f8a355 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -2190,13 +2190,15 @@ __bpf_kfunc struct task_struct *bpf_task_from_pid(s32 pid) * bpf_dynptr_slice() - Obtain a read-only pointer to the dynptr data. * @ptr: The dynptr whose data slice to retrieve * @offset: Offset into the dynptr - * @buffer: User-provided buffer to copy contents into - * @buffer__szk: Size (in bytes) of the buffer. This is the length of the - * requested slice. This must be a constant. + * @buffer__opt: User-provided buffer to copy contents into. May be NULL + * @buffer__szk: Size (in bytes) of the buffer if present. This is the + * length of the requested slice. This must be a constant. * * For non-skb and non-xdp type dynptrs, there is no difference between * bpf_dynptr_slice and bpf_dynptr_data. * + * If buffer__opt is NULL, the call will fail if buffer_opt was needed. + * * If the intention is to write to the data slice, please use * bpf_dynptr_slice_rdwr. * @@ -2213,7 +2215,7 @@ __bpf_kfunc struct task_struct *bpf_task_from_pid(s32 pid) * direct pointer) */ __bpf_kfunc void *bpf_dynptr_slice(const struct bpf_dynptr_kern *ptr, u32 offset, - void *buffer, u32 buffer__szk) + void *buffer__opt, u32 buffer__szk) { enum bpf_dynptr_type type; u32 len = buffer__szk; @@ -2233,15 +2235,17 @@ __bpf_kfunc void *bpf_dynptr_slice(const struct bpf_dynptr_kern *ptr, u32 offset case BPF_DYNPTR_TYPE_RINGBUF: return ptr->data + ptr->offset + offset; case BPF_DYNPTR_TYPE_SKB: - return skb_header_pointer(ptr->data, ptr->offset + offset, len, buffer); + return skb_header_pointer(ptr->data, ptr->offset + offset, len, buffer__opt); case BPF_DYNPTR_TYPE_XDP: { void *xdp_ptr = bpf_xdp_pointer(ptr->data, ptr->offset + offset, len); if (xdp_ptr) return xdp_ptr; - bpf_xdp_copy_buf(ptr->data, ptr->offset + offset, buffer, len, false); - return buffer; + if (!buffer__opt) + return NULL; + bpf_xdp_copy_buf(ptr->data, ptr->offset + offset, buffer__opt, len, false); + return buffer__opt; } default: WARN_ONCE(true, "unknown dynptr type %d\n", type); @@ -2253,13 +2257,15 @@ __bpf_kfunc void *bpf_dynptr_slice(const struct bpf_dynptr_kern *ptr, u32 offset * bpf_dynptr_slice_rdwr() - Obtain a writable pointer to the dynptr data. * @ptr: The dynptr whose data slice to retrieve * @offset: Offset into the dynptr - * @buffer: User-provided buffer to copy contents into - * @buffer__szk: Size (in bytes) of the buffer. This is the length of the - * requested slice. This must be a constant. + * @buffer__opt: User-provided buffer to copy contents into. May be NULL + * @buffer__szk: Size (in bytes) of the buffer if present. This is the + * length of the requested slice. This must be a constant. * * For non-skb and non-xdp type dynptrs, there is no difference between * bpf_dynptr_slice and bpf_dynptr_data. * + * If buffer__opt is NULL, the call will fail if buffer_opt was needed. + * * The returned pointer is writable and may point to either directly the dynptr * data at the requested offset or to the buffer if unable to obtain a direct * data pointer to (example: the requested slice is to the paged area of an skb @@ -2290,7 +2296,7 @@ __bpf_kfunc void *bpf_dynptr_slice(const struct bpf_dynptr_kern *ptr, u32 offset * direct pointer) */ __bpf_kfunc void *bpf_dynptr_slice_rdwr(const struct bpf_dynptr_kern *ptr, u32 offset, - void *buffer, u32 buffer__szk) + void *buffer__opt, u32 buffer__szk) { if (!ptr->data || __bpf_dynptr_is_rdonly(ptr)) return NULL; @@ -2317,7 +2323,7 @@ __bpf_kfunc void *bpf_dynptr_slice_rdwr(const struct bpf_dynptr_kern *ptr, u32 o * will be copied out into the buffer and the user will need to call * bpf_dynptr_write() to commit changes. */ - return bpf_dynptr_slice(ptr, offset, buffer, buffer__szk); + return bpf_dynptr_slice(ptr, offset, buffer__opt, buffer__szk); } __bpf_kfunc int bpf_dynptr_adjust(struct bpf_dynptr_kern *ptr, u32 start, u32 end) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 0fa96581eb77..7e6bbae9db81 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -9743,6 +9743,11 @@ static bool is_kfunc_arg_const_mem_size(const struct btf *btf, return __kfunc_param_match_suffix(btf, arg, "__szk"); } +static bool is_kfunc_arg_optional(const struct btf *btf, const struct btf_param *arg) +{ + return __kfunc_param_match_suffix(btf, arg, "__opt"); +} + static bool is_kfunc_arg_constant(const struct btf *btf, const struct btf_param *arg) { return __kfunc_param_match_suffix(btf, arg, "__k"); @@ -10830,13 +10835,17 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ break; case KF_ARG_PTR_TO_MEM_SIZE: { + struct bpf_reg_state *buff_reg = ®s[regno]; + const struct btf_param *buff_arg = &args[i]; struct bpf_reg_state *size_reg = ®s[regno + 1]; const struct btf_param *size_arg = &args[i + 1]; - ret = check_kfunc_mem_size_reg(env, size_reg, regno + 1); - if (ret < 0) { - verbose(env, "arg#%d arg#%d memory, len pair leads to invalid memory access\n", i, i + 1); - return ret; + if (!register_is_null(buff_reg) || !is_kfunc_arg_optional(meta->btf, buff_arg)) { + ret = check_kfunc_mem_size_reg(env, size_reg, regno + 1); + if (ret < 0) { + verbose(env, "arg#%d arg#%d memory, len pair leads to invalid memory access\n", i, i + 1); + return ret; + } } if (is_kfunc_arg_const_mem_size(meta->btf, size_arg, size_reg)) { -- cgit v1.2.3 From 69da5aa99ea67e86d3461fb281eadc952cc2914f Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Fri, 7 Apr 2023 07:47:33 -0400 Subject: regmap-irq: Drop map from handle_mask_sync() parameters Remove the map parameter from the struct regmap_irq_chip callback handle_mask_sync() because it can be passed via the irq_drv_data parameter instead. The gpio-104-dio-48e driver is the only consumer of this callback and is thus updated accordingly. Reviewed-by: Linus Walleij chip->num_regs; i++) { if (d->mask_base) { if (d->chip->handle_mask_sync) - d->chip->handle_mask_sync(d->map, i, - d->mask_buf_def[i], + d->chip->handle_mask_sync(i, d->mask_buf_def[i], d->mask_buf[i], d->chip->irq_drv_data); else { @@ -920,7 +919,7 @@ int regmap_add_irq_chip_fwnode(struct fwnode_handle *fwnode, if (d->mask_base) { if (chip->handle_mask_sync) { - ret = chip->handle_mask_sync(d->map, i, + ret = chip->handle_mask_sync(i, d->mask_buf_def[i], d->mask_buf[i], chip->irq_drv_data); diff --git a/drivers/gpio/gpio-104-dio-48e.c b/drivers/gpio/gpio-104-dio-48e.c index 63dce9532e97..8ff5f4ff5958 100644 --- a/drivers/gpio/gpio-104-dio-48e.c +++ b/drivers/gpio/gpio-104-dio-48e.c @@ -110,7 +110,7 @@ struct dio48e_gpio { unsigned int irq_mask; }; -static int dio48e_handle_mask_sync(struct regmap *const map, const int index, +static int dio48e_handle_mask_sync(const int index, const unsigned int mask_buf_def, const unsigned int mask_buf, void *const irq_drv_data) diff --git a/include/linux/regmap.h b/include/linux/regmap.h index c2b9cc5db824..f820bd44d16f 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -1658,8 +1658,7 @@ struct regmap_irq_chip { int (*handle_pre_irq)(void *irq_drv_data); int (*handle_post_irq)(void *irq_drv_data); - int (*handle_mask_sync)(struct regmap *map, int index, - unsigned int mask_buf_def, + int (*handle_mask_sync)(int index, unsigned int mask_buf_def, unsigned int mask_buf, void *irq_drv_data); int (*set_type_virt)(unsigned int **buf, unsigned int type, unsigned long hwirq, int reg); -- cgit v1.2.3 From d1a7718ee8dbcc488d3243d52e19c755123e0024 Mon Sep 17 00:00:00 2001 From: Jaewon Kim Date: Tue, 2 May 2023 15:28:11 +0900 Subject: spi: s3c64xx: change polling mode to optional Previously, Polling mode was supported as quirk for SOC without DMA. To provide more flexible support for polling mode, it changed to polling mode when the 'dmas' property is not present in the devicetree, rather than using a quirk. Signed-off-by: Jaewon Kim #define MAX_SPI_PORTS 12 -#define S3C64XX_SPI_QUIRK_POLL (1 << 0) #define S3C64XX_SPI_QUIRK_CS_AUTO (1 << 1) #define AUTOSUSPEND_TIMEOUT 2000 @@ -116,7 +115,7 @@ #define S3C64XX_SPI_TRAILCNT S3C64XX_SPI_MAX_TRAILCNT #define msecs_to_loops(t) (loops_per_jiffy / 1000 * HZ * t) -#define is_polling(x) (x->port_conf->quirks & S3C64XX_SPI_QUIRK_POLL) +#define is_polling(x) (x->cntrlr_info->polling) #define RXBUSY (1<<2) #define TXBUSY (1<<3) @@ -1068,6 +1067,7 @@ static struct s3c64xx_spi_info *s3c64xx_spi_parse_dt(struct device *dev) } sci->no_cs = of_property_read_bool(dev->of_node, "no-cs-readback"); + sci->polling = !of_property_present(dev->of_node, "dmas"); return sci; } diff --git a/include/linux/platform_data/spi-s3c64xx.h b/include/linux/platform_data/spi-s3c64xx.h index 3101152ce449..1d6e6c424fc6 100644 --- a/include/linux/platform_data/spi-s3c64xx.h +++ b/include/linux/platform_data/spi-s3c64xx.h @@ -36,6 +36,7 @@ struct s3c64xx_spi_info { int src_clk_nr; int num_cs; bool no_cs; + bool polling; int (*cfg_gpio)(void); }; -- cgit v1.2.3 From 0d6d062ca27ec7ef547712d34dcfcfb952bcef53 Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Thu, 4 May 2023 16:30:00 +0530 Subject: perf/core: Rework forwarding of {task|cpu}-clock events Currently, PERF_TYPE_SOFTWARE is treated specially since task-clock and cpu-clock events are interfaced through it but internally gets forwarded to their own pmus. Rework this by overwriting event->attr.type in perf_swevent_init() which will cause perf_init_event() to retry with updated type and event will automatically get forwarded to right pmu. With the change, SW pmu no longer needs to be treated specially and can be included in 'pmu_idr' list. Suggested-by: Peter Zijlstra Signed-off-by: Ravi Bangoria Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20230504110003.2548-2-ravi.bangoria@amd.com --- include/linux/perf_event.h | 10 ++++++ kernel/events/core.c | 77 ++++++++++++++++++++++++---------------------- 2 files changed, 51 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index d5628a7b5eaa..bf4f346d6d70 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -295,6 +295,8 @@ struct perf_event_pmu_context; struct perf_output_handle; +#define PMU_NULL_DEV ((void *)(~0UL)) + /** * struct pmu - generic performance monitoring unit */ @@ -827,6 +829,14 @@ struct perf_event { void *security; #endif struct list_head sb_list; + + /* + * Certain events gets forwarded to another pmu internally by over- + * writing kernel copy of event->attr.type without user being aware + * of it. event->orig_type contains original 'type' requested by + * user. + */ + __u32 orig_type; #endif /* CONFIG_PERF_EVENTS */ }; diff --git a/kernel/events/core.c b/kernel/events/core.c index 68baa8194d9f..c01bbe93e291 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6647,7 +6647,7 @@ static void perf_sigtrap(struct perf_event *event) return; send_sig_perf((void __user *)event->pending_addr, - event->attr.type, event->attr.sig_data); + event->orig_type, event->attr.sig_data); } /* @@ -9951,6 +9951,9 @@ static void sw_perf_event_destroy(struct perf_event *event) swevent_hlist_put(); } +static struct pmu perf_cpu_clock; /* fwd declaration */ +static struct pmu perf_task_clock; + static int perf_swevent_init(struct perf_event *event) { u64 event_id = event->attr.config; @@ -9966,7 +9969,10 @@ static int perf_swevent_init(struct perf_event *event) switch (event_id) { case PERF_COUNT_SW_CPU_CLOCK: + event->attr.type = perf_cpu_clock.type; + return -ENOENT; case PERF_COUNT_SW_TASK_CLOCK: + event->attr.type = perf_task_clock.type; return -ENOENT; default: @@ -11086,7 +11092,7 @@ static void cpu_clock_event_read(struct perf_event *event) static int cpu_clock_event_init(struct perf_event *event) { - if (event->attr.type != PERF_TYPE_SOFTWARE) + if (event->attr.type != perf_cpu_clock.type) return -ENOENT; if (event->attr.config != PERF_COUNT_SW_CPU_CLOCK) @@ -11107,6 +11113,7 @@ static struct pmu perf_cpu_clock = { .task_ctx_nr = perf_sw_context, .capabilities = PERF_PMU_CAP_NO_NMI, + .dev = PMU_NULL_DEV, .event_init = cpu_clock_event_init, .add = cpu_clock_event_add, @@ -11167,7 +11174,7 @@ static void task_clock_event_read(struct perf_event *event) static int task_clock_event_init(struct perf_event *event) { - if (event->attr.type != PERF_TYPE_SOFTWARE) + if (event->attr.type != perf_task_clock.type) return -ENOENT; if (event->attr.config != PERF_COUNT_SW_TASK_CLOCK) @@ -11188,6 +11195,7 @@ static struct pmu perf_task_clock = { .task_ctx_nr = perf_sw_context, .capabilities = PERF_PMU_CAP_NO_NMI, + .dev = PMU_NULL_DEV, .event_init = task_clock_event_init, .add = task_clock_event_add, @@ -11415,31 +11423,31 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type) goto unlock; pmu->type = -1; - if (!name) - goto skip_type; + if (WARN_ONCE(!name, "Can not register anonymous pmu.\n")) { + ret = -EINVAL; + goto free_pdc; + } + pmu->name = name; - if (type != PERF_TYPE_SOFTWARE) { - if (type >= 0) - max = type; + if (type >= 0) + max = type; - ret = idr_alloc(&pmu_idr, pmu, max, 0, GFP_KERNEL); - if (ret < 0) - goto free_pdc; + ret = idr_alloc(&pmu_idr, pmu, max, 0, GFP_KERNEL); + if (ret < 0) + goto free_pdc; - WARN_ON(type >= 0 && ret != type); + WARN_ON(type >= 0 && ret != type); - type = ret; - } + type = ret; pmu->type = type; - if (pmu_bus_running) { + if (pmu_bus_running && !pmu->dev) { ret = pmu_dev_alloc(pmu); if (ret) goto free_idr; } -skip_type: ret = -ENOMEM; pmu->cpu_pmu_context = alloc_percpu(struct perf_cpu_pmu_context); if (!pmu->cpu_pmu_context) @@ -11481,16 +11489,7 @@ skip_type: if (!pmu->event_idx) pmu->event_idx = perf_event_idx_default; - /* - * Ensure the TYPE_SOFTWARE PMUs are at the head of the list, - * since these cannot be in the IDR. This way the linear search - * is fast, provided a valid software event is provided. - */ - if (type == PERF_TYPE_SOFTWARE || !name) - list_add_rcu(&pmu->entry, &pmus); - else - list_add_tail_rcu(&pmu->entry, &pmus); - + list_add_rcu(&pmu->entry, &pmus); atomic_set(&pmu->exclusive_cnt, 0); ret = 0; unlock: @@ -11499,12 +11498,13 @@ unlock: return ret; free_dev: - device_del(pmu->dev); - put_device(pmu->dev); + if (pmu->dev && pmu->dev != PMU_NULL_DEV) { + device_del(pmu->dev); + put_device(pmu->dev); + } free_idr: - if (pmu->type != PERF_TYPE_SOFTWARE) - idr_remove(&pmu_idr, pmu->type); + idr_remove(&pmu_idr, pmu->type); free_pdc: free_percpu(pmu->pmu_disable_count); @@ -11525,9 +11525,8 @@ void perf_pmu_unregister(struct pmu *pmu) synchronize_rcu(); free_percpu(pmu->pmu_disable_count); - if (pmu->type != PERF_TYPE_SOFTWARE) - idr_remove(&pmu_idr, pmu->type); - if (pmu_bus_running) { + idr_remove(&pmu_idr, pmu->type); + if (pmu_bus_running && pmu->dev && pmu->dev != PMU_NULL_DEV) { if (pmu->nr_addr_filters) device_remove_file(pmu->dev, &dev_attr_nr_addr_filters); device_del(pmu->dev); @@ -11601,6 +11600,12 @@ static struct pmu *perf_init_event(struct perf_event *event) idx = srcu_read_lock(&pmus_srcu); + /* + * Save original type before calling pmu->event_init() since certain + * pmus overwrites event->attr.type to forward event to another pmu. + */ + event->orig_type = event->attr.type; + /* Try parent's PMU first: */ if (event->parent && event->parent->pmu) { pmu = event->parent->pmu; @@ -13640,8 +13645,8 @@ void __init perf_event_init(void) perf_event_init_all_cpus(); init_srcu_struct(&pmus_srcu); perf_pmu_register(&perf_swevent, "software", PERF_TYPE_SOFTWARE); - perf_pmu_register(&perf_cpu_clock, NULL, -1); - perf_pmu_register(&perf_task_clock, NULL, -1); + perf_pmu_register(&perf_cpu_clock, "cpu_clock", -1); + perf_pmu_register(&perf_task_clock, "task_clock", -1); perf_tp_register(); perf_event_init_cpu(smp_processor_id()); register_reboot_notifier(&perf_reboot_notifier); @@ -13684,7 +13689,7 @@ static int __init perf_event_sysfs_init(void) goto unlock; list_for_each_entry(pmu, &pmus, entry) { - if (!pmu->name || pmu->type < 0) + if (pmu->dev) continue; ret = pmu_dev_alloc(pmu); -- cgit v1.2.3 From ca528cc501896a808dc79c3c0544369d23b331c8 Mon Sep 17 00:00:00 2001 From: Ricardo Neri Date: Thu, 6 Apr 2023 13:31:45 -0700 Subject: sched/topology: Remove SHARED_CHILD from ASYM_PACKING Only x86 and Power7 use ASYM_PACKING. They use it differently. Power7 has cores of equal priority, but the SMT siblings of a core have different priorities. Parent scheduling domains do not need (nor have) the ASYM_PACKING flag. SHARED_CHILD is not needed. Using SHARED_PARENT would cause the topology debug code to complain. X86 has cores of different priority, but all the SMT siblings of the core have equal priority. It needs ASYM_PACKING at the MC level, but not at the SMT level (it also needs it at upper levels if they have scheduling groups of different priority). Removing ASYM_PACKING from the SMT domain causes the topology debug code to complain. Remove SHARED_CHILD for now. We still need a topology check that satisfies both architectures. Suggested-by: Valentin Schneider Signed-off-by: Ricardo Neri Signed-off-by: Peter Zijlstra (Intel) Tested-by: Zhang Rui Link: https://lore.kernel.org/r/20230406203148.19182-10-ricardo.neri-calderon@linux.intel.com --- include/linux/sched/sd_flags.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h index 57bde66d95f7..fad77b5172e2 100644 --- a/include/linux/sched/sd_flags.h +++ b/include/linux/sched/sd_flags.h @@ -132,12 +132,9 @@ SD_FLAG(SD_SERIALIZE, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS) /* * Place busy tasks earlier in the domain * - * SHARED_CHILD: Usually set on the SMT level. Technically could be set further - * up, but currently assumed to be set from the base domain - * upwards (see update_top_cache_domain()). * NEEDS_GROUPS: Load balancing flag. */ -SD_FLAG(SD_ASYM_PACKING, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS) +SD_FLAG(SD_ASYM_PACKING, SDF_NEEDS_GROUPS) /* * Prefer to place tasks in a sibling domain -- cgit v1.2.3 From 6121cd9ef911432b14c2a17aefaf8cd2f3cfcdff Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Fri, 28 Apr 2023 14:24:51 +0200 Subject: fbdev: Move I/O read and write code into helper functions Move the existing I/O read and write code for I/O memory into the new helpers fb_cfb_read() and fb_cfb_write(). Make them the default fp_ops. No functional changes. In the near term, the new functions will be useful to the DRM subsystem, which currently provides it's own implementation. It can then use the shared code. In the longer term, it might make sense to revise the I/O helper's default status and make them opt-in by the driver. Systems that don't use them would not contain the code any longer. v2: * add detailed commit message (Javier) * rename fb_cfb_() to fb_io_() (Geert) * add fixes that got lost while moving the code (Geert) Signed-off-by: Thomas Zimmermann Tested-by: Sui Jingfeng Reviewed-by: Javier Martinez Canillas Acked-by: Helge Deller Reviewed-by: Sam Ravnborg Link: https://patchwork.freedesktop.org/patch/msgid/20230428122452.4856-19-tzimmermann@suse.de --- drivers/video/fbdev/core/Makefile | 2 +- drivers/video/fbdev/core/fb_io_fops.c | 133 ++++++++++++++++++++++++++++++++++ drivers/video/fbdev/core/fbmem.c | 118 +----------------------------- include/linux/fb.h | 10 +++ 4 files changed, 146 insertions(+), 117 deletions(-) create mode 100644 drivers/video/fbdev/core/fb_io_fops.c (limited to 'include/linux') diff --git a/drivers/video/fbdev/core/Makefile b/drivers/video/fbdev/core/Makefile index 08fabce76b74..8f0060160ffb 100644 --- a/drivers/video/fbdev/core/Makefile +++ b/drivers/video/fbdev/core/Makefile @@ -2,7 +2,7 @@ obj-$(CONFIG_FB_NOTIFY) += fb_notify.o obj-$(CONFIG_FB) += fb.o fb-y := fbmem.o fbmon.o fbcmap.o fbsysfs.o \ - modedb.o fbcvt.o fb_cmdline.o + modedb.o fbcvt.o fb_cmdline.o fb_io_fops.o fb-$(CONFIG_FB_DEFERRED_IO) += fb_defio.o ifeq ($(CONFIG_FRAMEBUFFER_CONSOLE),y) diff --git a/drivers/video/fbdev/core/fb_io_fops.c b/drivers/video/fbdev/core/fb_io_fops.c new file mode 100644 index 000000000000..f5299d50f33b --- /dev/null +++ b/drivers/video/fbdev/core/fb_io_fops.c @@ -0,0 +1,133 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include + +ssize_t fb_io_read(struct fb_info *info, char __user *buf, size_t count, loff_t *ppos) +{ + unsigned long p = *ppos; + u8 *buffer, *dst; + u8 __iomem *src; + int c, cnt = 0, err = 0; + unsigned long total_size, trailing; + + if (!info->screen_base) + return -ENODEV; + + total_size = info->screen_size; + + if (total_size == 0) + total_size = info->fix.smem_len; + + if (p >= total_size) + return 0; + + if (count >= total_size) + count = total_size; + + if (count + p > total_size) + count = total_size - p; + + buffer = kmalloc((count > PAGE_SIZE) ? PAGE_SIZE : count, + GFP_KERNEL); + if (!buffer) + return -ENOMEM; + + src = (u8 __iomem *) (info->screen_base + p); + + if (info->fbops->fb_sync) + info->fbops->fb_sync(info); + + while (count) { + c = (count > PAGE_SIZE) ? PAGE_SIZE : count; + dst = buffer; + fb_memcpy_fromfb(dst, src, c); + dst += c; + src += c; + + trailing = copy_to_user(buf, buffer, c); + if (trailing == c) { + err = -EFAULT; + break; + } + c -= trailing; + + *ppos += c; + buf += c; + cnt += c; + count -= c; + } + + kfree(buffer); + + return cnt ? cnt : err; +} +EXPORT_SYMBOL(fb_io_read); + +ssize_t fb_io_write(struct fb_info *info, const char __user *buf, size_t count, loff_t *ppos) +{ + unsigned long p = *ppos; + u8 *buffer, *src; + u8 __iomem *dst; + int c, cnt = 0, err = 0; + unsigned long total_size, trailing; + + if (!info->screen_base) + return -ENODEV; + + total_size = info->screen_size; + + if (total_size == 0) + total_size = info->fix.smem_len; + + if (p > total_size) + return -EFBIG; + + if (count > total_size) { + err = -EFBIG; + count = total_size; + } + + if (count + p > total_size) { + if (!err) + err = -ENOSPC; + + count = total_size - p; + } + + buffer = kmalloc((count > PAGE_SIZE) ? PAGE_SIZE : count, + GFP_KERNEL); + if (!buffer) + return -ENOMEM; + + dst = (u8 __iomem *) (info->screen_base + p); + + if (info->fbops->fb_sync) + info->fbops->fb_sync(info); + + while (count) { + c = (count > PAGE_SIZE) ? PAGE_SIZE : count; + src = buffer; + + trailing = copy_from_user(src, buf, c); + if (trailing == c) { + err = -EFAULT; + break; + } + c -= trailing; + + fb_memcpy_tofb(dst, src, c); + dst += c; + src += c; + *ppos += c; + buf += c; + cnt += c; + count -= c; + } + + kfree(buffer); + + return (cnt) ? cnt : err; +} +EXPORT_SYMBOL(fb_io_write); diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index bf5a0780457e..63af40831d7d 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -761,12 +761,7 @@ static struct fb_info *file_fb_info(struct file *file) static ssize_t fb_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { - unsigned long p = *ppos; struct fb_info *info = file_fb_info(file); - u8 *buffer, *dst; - u8 __iomem *src; - int c, cnt = 0, err = 0; - unsigned long total_size, trailing; if (!info) return -ENODEV; @@ -777,67 +772,13 @@ fb_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) if (info->fbops->fb_read) return info->fbops->fb_read(info, buf, count, ppos); - if (!info->screen_base) - return -ENODEV; - - total_size = info->screen_size; - - if (total_size == 0) - total_size = info->fix.smem_len; - - if (p >= total_size) - return 0; - - if (count >= total_size) - count = total_size; - - if (count + p > total_size) - count = total_size - p; - - buffer = kmalloc((count > PAGE_SIZE) ? PAGE_SIZE : count, - GFP_KERNEL); - if (!buffer) - return -ENOMEM; - - src = (u8 __iomem *) (info->screen_base + p); - - if (info->fbops->fb_sync) - info->fbops->fb_sync(info); - - while (count) { - c = (count > PAGE_SIZE) ? PAGE_SIZE : count; - dst = buffer; - fb_memcpy_fromfb(dst, src, c); - dst += c; - src += c; - - trailing = copy_to_user(buf, buffer, c); - if (trailing == c) { - err = -EFAULT; - break; - } - c -= trailing; - - *ppos += c; - buf += c; - cnt += c; - count -= c; - } - - kfree(buffer); - - return cnt ? cnt : err; + return fb_io_read(info, buf, count, ppos); } static ssize_t fb_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - unsigned long p = *ppos; struct fb_info *info = file_fb_info(file); - u8 *buffer, *src; - u8 __iomem *dst; - int c, cnt = 0, err = 0; - unsigned long total_size, trailing; if (!info) return -ENODEV; @@ -848,62 +789,7 @@ fb_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) if (info->fbops->fb_write) return info->fbops->fb_write(info, buf, count, ppos); - if (!info->screen_base) - return -ENODEV; - - total_size = info->screen_size; - - if (total_size == 0) - total_size = info->fix.smem_len; - - if (p > total_size) - return -EFBIG; - - if (count > total_size) { - err = -EFBIG; - count = total_size; - } - - if (count + p > total_size) { - if (!err) - err = -ENOSPC; - - count = total_size - p; - } - - buffer = kmalloc((count > PAGE_SIZE) ? PAGE_SIZE : count, - GFP_KERNEL); - if (!buffer) - return -ENOMEM; - - dst = (u8 __iomem *) (info->screen_base + p); - - if (info->fbops->fb_sync) - info->fbops->fb_sync(info); - - while (count) { - c = (count > PAGE_SIZE) ? PAGE_SIZE : count; - src = buffer; - - trailing = copy_from_user(src, buf, c); - if (trailing == c) { - err = -EFAULT; - break; - } - c -= trailing; - - fb_memcpy_tofb(dst, src, c); - dst += c; - src += c; - *ppos += c; - buf += c; - cnt += c; - count -= c; - } - - kfree(buffer); - - return (cnt) ? cnt : err; + return fb_io_write(info, buf, count, ppos); } int diff --git a/include/linux/fb.h b/include/linux/fb.h index 08cb47da71f8..ec978a4969a9 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -576,9 +576,19 @@ struct fb_info { extern int fb_set_var(struct fb_info *info, struct fb_var_screeninfo *var); extern int fb_pan_display(struct fb_info *info, struct fb_var_screeninfo *var); extern int fb_blank(struct fb_info *info, int blank); + +/* + * Drawing operations where framebuffer is in I/O memory + */ + extern void cfb_fillrect(struct fb_info *info, const struct fb_fillrect *rect); extern void cfb_copyarea(struct fb_info *info, const struct fb_copyarea *area); extern void cfb_imageblit(struct fb_info *info, const struct fb_image *image); +extern ssize_t fb_io_read(struct fb_info *info, char __user *buf, + size_t count, loff_t *ppos); +extern ssize_t fb_io_write(struct fb_info *info, const char __user *buf, + size_t count, loff_t *ppos); + /* * Drawing operations where framebuffer is in system RAM */ -- cgit v1.2.3 From c00bc80462afc7963f449d7f21d896d2f629cacc Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 15 Apr 2023 20:23:34 +0200 Subject: power: supply: bq27xxx: Fix poll_interval handling and races on remove Before this patch bq27xxx_battery_teardown() was setting poll_interval = 0 to avoid bq27xxx_battery_update() requeuing the delayed_work item. There are 2 problems with this: 1. If the driver is unbound through sysfs, rather then the module being rmmod-ed, this changes poll_interval unexpectedly 2. This is racy, after it being set poll_interval could be changed before bq27xxx_battery_update() checks it through /sys/module/bq27xxx_battery/parameters/poll_interval Fix this by added a removed attribute to struct bq27xxx_device_info and using that instead of setting poll_interval to 0. There also is another poll_interval related race on remove(), writing /sys/module/bq27xxx_battery/parameters/poll_interval will requeue the delayed_work item for all devices on the bq27xxx_battery_devices list and the device being removed was only removed from that list after cancelling the delayed_work item. Fix this by moving the removal from the bq27xxx_battery_devices list to before cancelling the delayed_work item. Fixes: 8cfaaa811894 ("bq27x00_battery: Fix OOPS caused by unregistring bq27x00 driver") Signed-off-by: Hans de Goede Signed-off-by: Sebastian Reichel --- drivers/power/supply/bq27xxx_battery.c | 22 +++++++++------------- include/linux/power/bq27xxx_battery.h | 1 + 2 files changed, 10 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index 79aedf83cc8d..7411f1cf741b 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -1801,7 +1801,7 @@ static void bq27xxx_battery_update_unlocked(struct bq27xxx_device_info *di) di->last_update = jiffies; - if (poll_interval > 0) + if (!di->removed && poll_interval > 0) mod_delayed_work(system_wq, &di->work, poll_interval * HZ); } @@ -2132,22 +2132,18 @@ EXPORT_SYMBOL_GPL(bq27xxx_battery_setup); void bq27xxx_battery_teardown(struct bq27xxx_device_info *di) { - /* - * power_supply_unregister call bq27xxx_battery_get_property which - * call bq27xxx_battery_poll. - * Make sure that bq27xxx_battery_poll will not call - * schedule_delayed_work again after unregister (which cause OOPS). - */ - poll_interval = 0; - - cancel_delayed_work_sync(&di->work); - - power_supply_unregister(di->bat); - mutex_lock(&bq27xxx_list_lock); list_del(&di->list); mutex_unlock(&bq27xxx_list_lock); + /* Set removed to avoid bq27xxx_battery_update() re-queuing the work */ + mutex_lock(&di->lock); + di->removed = true; + mutex_unlock(&di->lock); + + cancel_delayed_work_sync(&di->work); + + power_supply_unregister(di->bat); mutex_destroy(&di->lock); } EXPORT_SYMBOL_GPL(bq27xxx_battery_teardown); diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index a1aa68141d0b..e3322dad9c85 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -68,6 +68,7 @@ struct bq27xxx_device_info { struct bq27xxx_access_methods bus; struct bq27xxx_reg_cache cache; int charge_design_full; + bool removed; unsigned long last_update; struct delayed_work work; struct power_supply *bat; -- cgit v1.2.3 From 939a116142012926e25de0ea6b7e2f8d86a5f1b6 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 15 Apr 2023 20:23:37 +0200 Subject: power: supply: bq27xxx: Ensure power_supply_changed() is called on current sign changes On gauges where the current register is signed, there is no charging flag in the flags register. So only checking flags will not result in power_supply_changed() getting called when e.g. a charger is plugged in and the current sign changes from negative (discharging) to positive (charging). This causes userspace's notion of the status to lag until userspace does a poll. And when a power_supply_leds.c LED trigger is used to indicate charging status with a LED, this LED will lag until the capacity percentage changes, which may take many minutes (because the LED trigger only is updated on power_supply_changed() calls). Fix this by calling bq27xxx_battery_current_and_status() on gauges with a signed current register and checking if the status has changed. Fixes: 297a533b3e62 ("bq27x00: Cache battery registers") Signed-off-by: Hans de Goede Signed-off-by: Sebastian Reichel --- drivers/power/supply/bq27xxx_battery.c | 13 ++++++++++++- include/linux/power/bq27xxx_battery.h | 3 +++ 2 files changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index 8f2995e9850a..f98b51ce19b5 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -1836,6 +1836,7 @@ static int bq27xxx_battery_current_and_status( static void bq27xxx_battery_update_unlocked(struct bq27xxx_device_info *di) { + union power_supply_propval status = di->last_status; struct bq27xxx_reg_cache cache = {0, }; bool has_singe_flag = di->opts & BQ27XXX_O_ZERO; @@ -1860,14 +1861,24 @@ static void bq27xxx_battery_update_unlocked(struct bq27xxx_device_info *di) if (di->regs[BQ27XXX_REG_CYCT] != INVALID_REG_ADDR) cache.cycle_count = bq27xxx_battery_read_cyct(di); + /* + * On gauges with signed current reporting the current must be + * checked to detect charging <-> discharging status changes. + */ + if (!(di->opts & BQ27XXX_O_ZERO)) + bq27xxx_battery_current_and_status(di, NULL, &status, &cache); + /* We only have to read charge design full once */ if (di->charge_design_full <= 0) di->charge_design_full = bq27xxx_battery_read_dcap(di); } if ((di->cache.capacity != cache.capacity) || - (di->cache.flags != cache.flags)) + (di->cache.flags != cache.flags) || + (di->last_status.intval != status.intval)) { + di->last_status.intval = status.intval; power_supply_changed(di->bat); + } if (memcmp(&di->cache, &cache, sizeof(cache)) != 0) di->cache = cache; diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index e3322dad9c85..7c8d65414a70 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -2,6 +2,8 @@ #ifndef __LINUX_BQ27X00_BATTERY_H__ #define __LINUX_BQ27X00_BATTERY_H__ +#include + enum bq27xxx_chip { BQ27000 = 1, /* bq27000, bq27200 */ BQ27010, /* bq27010, bq27210 */ @@ -70,6 +72,7 @@ struct bq27xxx_device_info { int charge_design_full; bool removed; unsigned long last_update; + union power_supply_propval last_status; struct delayed_work work; struct power_supply *bat; struct list_head list; -- cgit v1.2.3 From 19b8766459c41c6f318f8a548cc1c66dffd18363 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Thu, 20 Apr 2023 16:06:03 +0100 Subject: firmware: arm_ffa: Fix FFA device names for logical partitions Each physical partition can provide multiple services each with UUID. Each such service can be presented as logical partition with a unique combination of VM ID and UUID. The number of distinct UUID in a system will be less than or equal to the number of logical partitions. However, currently it fails to register more than one logical partition or service within a physical partition as the device name contains only VM ID while both VM ID and UUID are maintained in the partition information. The kernel complains with the below message: | sysfs: cannot create duplicate filename '/devices/arm-ffa-8001' | CPU: 1 PID: 1 Comm: swapper/0 Not tainted 6.3.0-rc7 #8 | Hardware name: FVP Base RevC (DT) | Call trace: | dump_backtrace+0xf8/0x118 | show_stack+0x18/0x24 | dump_stack_lvl+0x50/0x68 | dump_stack+0x18/0x24 | sysfs_create_dir_ns+0xe0/0x13c | kobject_add_internal+0x220/0x3d4 | kobject_add+0x94/0x100 | device_add+0x144/0x5d8 | device_register+0x20/0x30 | ffa_device_register+0x88/0xd8 | ffa_setup_partitions+0x108/0x1b8 | ffa_init+0x2ec/0x3a4 | do_one_initcall+0xcc/0x240 | do_initcall_level+0x8c/0xac | do_initcalls+0x54/0x94 | do_basic_setup+0x1c/0x28 | kernel_init_freeable+0x100/0x16c | kernel_init+0x20/0x1a0 | ret_from_fork+0x10/0x20 | kobject_add_internal failed for arm-ffa-8001 with -EEXIST, don't try to | register things with the same name in the same directory. | arm_ffa arm-ffa: unable to register device arm-ffa-8001 err=-17 | ARM FF-A: ffa_setup_partitions: failed to register partition ID 0x8001 By virtue of being random enough to avoid collisions when generated in a distributed system, there is no way to compress UUID keys to the number of bits required to identify each. We can eliminate '-' in the name but it is not worth eliminating 4 bytes and add unnecessary logic for doing that. Also v1.0 doesn't provide the UUID of the partitions which makes it hard to use the same for the device name. So to keep it simple, let us alloc an ID using ida_alloc() and append the same to "arm-ffa" to make up a unique device name. Also stash the id value in ffa_dev to help freeing the ID later when the device is destroyed. Fixes: e781858488b9 ("firmware: arm_ffa: Add initial FFA bus support for device enumeration") Reported-by: Lucian Paul-Trifu Link: https://lore.kernel.org/r/20230419-ffa_fixes_6-4-v2-3-d9108e43a176@arm.com Signed-off-by: Sudeep Holla --- drivers/firmware/arm_ffa/bus.c | 16 +++++++++++++--- include/linux/arm_ffa.h | 1 + 2 files changed, 14 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/firmware/arm_ffa/bus.c b/drivers/firmware/arm_ffa/bus.c index 36bd5423c2f0..2b8bfcd010f5 100644 --- a/drivers/firmware/arm_ffa/bus.c +++ b/drivers/firmware/arm_ffa/bus.c @@ -15,6 +15,8 @@ #include "common.h" +static DEFINE_IDA(ffa_bus_id); + static int ffa_device_match(struct device *dev, struct device_driver *drv) { const struct ffa_device_id *id_table; @@ -131,6 +133,7 @@ static void ffa_release_device(struct device *dev) { struct ffa_device *ffa_dev = to_ffa_dev(dev); + ida_free(&ffa_bus_id, ffa_dev->id); kfree(ffa_dev); } @@ -171,18 +174,24 @@ bool ffa_device_is_valid(struct ffa_device *ffa_dev) struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id, const struct ffa_ops *ops) { - int ret; + int id, ret; struct device *dev; struct ffa_device *ffa_dev; + id = ida_alloc_min(&ffa_bus_id, 1, GFP_KERNEL); + if (id < 0) + return NULL; + ffa_dev = kzalloc(sizeof(*ffa_dev), GFP_KERNEL); - if (!ffa_dev) + if (!ffa_dev) { + ida_free(&ffa_bus_id, id); return NULL; + } dev = &ffa_dev->dev; dev->bus = &ffa_bus_type; dev->release = ffa_release_device; - dev_set_name(&ffa_dev->dev, "arm-ffa-%04x", vm_id); + dev_set_name(&ffa_dev->dev, "arm-ffa-%d", id); ffa_dev->vm_id = vm_id; ffa_dev->ops = ops; @@ -218,4 +227,5 @@ void arm_ffa_bus_exit(void) { ffa_devices_unregister(); bus_unregister(&ffa_bus_type); + ida_destroy(&ffa_bus_id); } diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index c87aeecaa9b2..583fe3b49a49 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -96,6 +96,7 @@ /* FFA Bus/Device/Driver related */ struct ffa_device { + u32 id; int vm_id; bool mode_32bit; uuid_t uuid; -- cgit v1.2.3 From 111cd11bbc54850f24191c52ff217da88a5e639b Mon Sep 17 00:00:00 2001 From: Juri Lelli Date: Mon, 8 May 2023 09:58:50 +0200 Subject: sched/cpuset: Bring back cpuset_mutex Turns out percpu_cpuset_rwsem - commit 1243dc518c9d ("cgroup/cpuset: Convert cpuset_mutex to percpu_rwsem") - wasn't such a brilliant idea, as it has been reported to cause slowdowns in workloads that need to change cpuset configuration frequently and it is also not implementing priority inheritance (which causes troubles with realtime workloads). Convert percpu_cpuset_rwsem back to regular cpuset_mutex. Also grab it only for SCHED_DEADLINE tasks (other policies don't care about stable cpusets anyway). Signed-off-by: Juri Lelli Reviewed-by: Waiman Long Signed-off-by: Tejun Heo --- include/linux/cpuset.h | 8 +-- kernel/cgroup/cpuset.c | 159 +++++++++++++++++++++++++------------------------ kernel/sched/core.c | 22 ++++--- 3 files changed, 99 insertions(+), 90 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 980b76a1237e..f90e6325d707 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -71,8 +71,8 @@ extern void cpuset_init_smp(void); extern void cpuset_force_rebuild(void); extern void cpuset_update_active_cpus(void); extern void cpuset_wait_for_hotplug(void); -extern void cpuset_read_lock(void); -extern void cpuset_read_unlock(void); +extern void cpuset_lock(void); +extern void cpuset_unlock(void); extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); extern bool cpuset_cpus_allowed_fallback(struct task_struct *p); extern nodemask_t cpuset_mems_allowed(struct task_struct *p); @@ -189,8 +189,8 @@ static inline void cpuset_update_active_cpus(void) static inline void cpuset_wait_for_hotplug(void) { } -static inline void cpuset_read_lock(void) { } -static inline void cpuset_read_unlock(void) { } +static inline void cpuset_lock(void) { } +static inline void cpuset_unlock(void) { } static inline void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 428ab46291e2..041c0809adaf 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -366,22 +366,23 @@ static struct cpuset top_cpuset = { if (is_cpuset_online(((des_cs) = css_cs((pos_css))))) /* - * There are two global locks guarding cpuset structures - cpuset_rwsem and + * There are two global locks guarding cpuset structures - cpuset_mutex and * callback_lock. We also require taking task_lock() when dereferencing a * task's cpuset pointer. See "The task_lock() exception", at the end of this - * comment. The cpuset code uses only cpuset_rwsem write lock. Other - * kernel subsystems can use cpuset_read_lock()/cpuset_read_unlock() to - * prevent change to cpuset structures. + * comment. The cpuset code uses only cpuset_mutex. Other kernel subsystems + * can use cpuset_lock()/cpuset_unlock() to prevent change to cpuset + * structures. Note that cpuset_mutex needs to be a mutex as it is used in + * paths that rely on priority inheritance (e.g. scheduler - on RT) for + * correctness. * * A task must hold both locks to modify cpusets. If a task holds - * cpuset_rwsem, it blocks others wanting that rwsem, ensuring that it - * is the only task able to also acquire callback_lock and be able to - * modify cpusets. It can perform various checks on the cpuset structure - * first, knowing nothing will change. It can also allocate memory while - * just holding cpuset_rwsem. While it is performing these checks, various - * callback routines can briefly acquire callback_lock to query cpusets. - * Once it is ready to make the changes, it takes callback_lock, blocking - * everyone else. + * cpuset_mutex, it blocks others, ensuring that it is the only task able to + * also acquire callback_lock and be able to modify cpusets. It can perform + * various checks on the cpuset structure first, knowing nothing will change. + * It can also allocate memory while just holding cpuset_mutex. While it is + * performing these checks, various callback routines can briefly acquire + * callback_lock to query cpusets. Once it is ready to make the changes, it + * takes callback_lock, blocking everyone else. * * Calls to the kernel memory allocator can not be made while holding * callback_lock, as that would risk double tripping on callback_lock @@ -403,16 +404,16 @@ static struct cpuset top_cpuset = { * guidelines for accessing subsystem state in kernel/cgroup.c */ -DEFINE_STATIC_PERCPU_RWSEM(cpuset_rwsem); +static DEFINE_MUTEX(cpuset_mutex); -void cpuset_read_lock(void) +void cpuset_lock(void) { - percpu_down_read(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); } -void cpuset_read_unlock(void) +void cpuset_unlock(void) { - percpu_up_read(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); } static DEFINE_SPINLOCK(callback_lock); @@ -496,7 +497,7 @@ static inline bool partition_is_populated(struct cpuset *cs, * One way or another, we guarantee to return some non-empty subset * of cpu_online_mask. * - * Call with callback_lock or cpuset_rwsem held. + * Call with callback_lock or cpuset_mutex held. */ static void guarantee_online_cpus(struct task_struct *tsk, struct cpumask *pmask) @@ -538,7 +539,7 @@ out_unlock: * One way or another, we guarantee to return some non-empty subset * of node_states[N_MEMORY]. * - * Call with callback_lock or cpuset_rwsem held. + * Call with callback_lock or cpuset_mutex held. */ static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask) { @@ -550,7 +551,7 @@ static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask) /* * update task's spread flag if cpuset's page/slab spread flag is set * - * Call with callback_lock or cpuset_rwsem held. The check can be skipped + * Call with callback_lock or cpuset_mutex held. The check can be skipped * if on default hierarchy. */ static void cpuset_update_task_spread_flags(struct cpuset *cs, @@ -575,7 +576,7 @@ static void cpuset_update_task_spread_flags(struct cpuset *cs, * * One cpuset is a subset of another if all its allowed CPUs and * Memory Nodes are a subset of the other, and its exclusive flags - * are only set if the other's are set. Call holding cpuset_rwsem. + * are only set if the other's are set. Call holding cpuset_mutex. */ static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q) @@ -713,7 +714,7 @@ out: * If we replaced the flag and mask values of the current cpuset * (cur) with those values in the trial cpuset (trial), would * our various subset and exclusive rules still be valid? Presumes - * cpuset_rwsem held. + * cpuset_mutex held. * * 'cur' is the address of an actual, in-use cpuset. Operations * such as list traversal that depend on the actual address of the @@ -829,7 +830,7 @@ static void update_domain_attr_tree(struct sched_domain_attr *dattr, rcu_read_unlock(); } -/* Must be called with cpuset_rwsem held. */ +/* Must be called with cpuset_mutex held. */ static inline int nr_cpusets(void) { /* jump label reference count + the top-level cpuset */ @@ -855,7 +856,7 @@ static inline int nr_cpusets(void) * domains when operating in the severe memory shortage situations * that could cause allocation failures below. * - * Must be called with cpuset_rwsem held. + * Must be called with cpuset_mutex held. * * The three key local variables below are: * cp - cpuset pointer, used (together with pos_css) to perform a @@ -1084,7 +1085,7 @@ static void dl_rebuild_rd_accounting(void) struct cpuset *cs = NULL; struct cgroup_subsys_state *pos_css; - percpu_rwsem_assert_held(&cpuset_rwsem); + lockdep_assert_held(&cpuset_mutex); lockdep_assert_cpus_held(); lockdep_assert_held(&sched_domains_mutex); @@ -1134,7 +1135,7 @@ partition_and_rebuild_sched_domains(int ndoms_new, cpumask_var_t doms_new[], * 'cpus' is removed, then call this routine to rebuild the * scheduler's dynamic sched domains. * - * Call with cpuset_rwsem held. Takes cpus_read_lock(). + * Call with cpuset_mutex held. Takes cpus_read_lock(). */ static void rebuild_sched_domains_locked(void) { @@ -1145,7 +1146,7 @@ static void rebuild_sched_domains_locked(void) int ndoms; lockdep_assert_cpus_held(); - percpu_rwsem_assert_held(&cpuset_rwsem); + lockdep_assert_held(&cpuset_mutex); /* * If we have raced with CPU hotplug, return early to avoid @@ -1196,9 +1197,9 @@ static void rebuild_sched_domains_locked(void) void rebuild_sched_domains(void) { cpus_read_lock(); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); rebuild_sched_domains_locked(); - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); cpus_read_unlock(); } @@ -1208,7 +1209,7 @@ void rebuild_sched_domains(void) * @new_cpus: the temp variable for the new effective_cpus mask * * Iterate through each task of @cs updating its cpus_allowed to the - * effective cpuset's. As this function is called with cpuset_rwsem held, + * effective cpuset's. As this function is called with cpuset_mutex held, * cpuset membership stays stable. For top_cpuset, task_cpu_possible_mask() * is used instead of effective_cpus to make sure all offline CPUs are also * included as hotplug code won't update cpumasks for tasks in top_cpuset. @@ -1322,7 +1323,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, int old_prs, new_prs; int part_error = PERR_NONE; /* Partition error? */ - percpu_rwsem_assert_held(&cpuset_rwsem); + lockdep_assert_held(&cpuset_mutex); /* * The parent must be a partition root. @@ -1545,7 +1546,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, * * On legacy hierarchy, effective_cpus will be the same with cpu_allowed. * - * Called with cpuset_rwsem held + * Called with cpuset_mutex held */ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp, bool force) @@ -1705,7 +1706,7 @@ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs, struct cpuset *sibling; struct cgroup_subsys_state *pos_css; - percpu_rwsem_assert_held(&cpuset_rwsem); + lockdep_assert_held(&cpuset_mutex); /* * Check all its siblings and call update_cpumasks_hier() @@ -1955,12 +1956,12 @@ static void *cpuset_being_rebound; * @cs: the cpuset in which each task's mems_allowed mask needs to be changed * * Iterate through each task of @cs updating its mems_allowed to the - * effective cpuset's. As this function is called with cpuset_rwsem held, + * effective cpuset's. As this function is called with cpuset_mutex held, * cpuset membership stays stable. */ static void update_tasks_nodemask(struct cpuset *cs) { - static nodemask_t newmems; /* protected by cpuset_rwsem */ + static nodemask_t newmems; /* protected by cpuset_mutex */ struct css_task_iter it; struct task_struct *task; @@ -1973,7 +1974,7 @@ static void update_tasks_nodemask(struct cpuset *cs) * take while holding tasklist_lock. Forks can happen - the * mpol_dup() cpuset_being_rebound check will catch such forks, * and rebind their vma mempolicies too. Because we still hold - * the global cpuset_rwsem, we know that no other rebind effort + * the global cpuset_mutex, we know that no other rebind effort * will be contending for the global variable cpuset_being_rebound. * It's ok if we rebind the same mm twice; mpol_rebind_mm() * is idempotent. Also migrate pages in each mm to new nodes. @@ -2019,7 +2020,7 @@ static void update_tasks_nodemask(struct cpuset *cs) * * On legacy hierarchy, effective_mems will be the same with mems_allowed. * - * Called with cpuset_rwsem held + * Called with cpuset_mutex held */ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems) { @@ -2072,7 +2073,7 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems) * mempolicies and if the cpuset is marked 'memory_migrate', * migrate the tasks pages to the new memory. * - * Call with cpuset_rwsem held. May take callback_lock during call. + * Call with cpuset_mutex held. May take callback_lock during call. * Will take tasklist_lock, scan tasklist for tasks in cpuset cs, * lock each such tasks mm->mmap_lock, scan its vma's and rebind * their mempolicies to the cpusets new mems_allowed. @@ -2164,7 +2165,7 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val) * @cs: the cpuset in which each task's spread flags needs to be changed * * Iterate through each task of @cs updating its spread flags. As this - * function is called with cpuset_rwsem held, cpuset membership stays + * function is called with cpuset_mutex held, cpuset membership stays * stable. */ static void update_tasks_flags(struct cpuset *cs) @@ -2184,7 +2185,7 @@ static void update_tasks_flags(struct cpuset *cs) * cs: the cpuset to update * turning_on: whether the flag is being set or cleared * - * Call with cpuset_rwsem held. + * Call with cpuset_mutex held. */ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, @@ -2234,7 +2235,7 @@ out: * @new_prs: new partition root state * Return: 0 if successful, != 0 if error * - * Call with cpuset_rwsem held. + * Call with cpuset_mutex held. */ static int update_prstate(struct cpuset *cs, int new_prs) { @@ -2472,7 +2473,7 @@ static int cpuset_can_attach_check(struct cpuset *cs) return 0; } -/* Called by cgroups to determine if a cpuset is usable; cpuset_rwsem held */ +/* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */ static int cpuset_can_attach(struct cgroup_taskset *tset) { struct cgroup_subsys_state *css; @@ -2484,7 +2485,7 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css)); cs = css_cs(css); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); /* Check to see if task is allowed in the cpuset */ ret = cpuset_can_attach_check(cs); @@ -2506,7 +2507,7 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) */ cs->attach_in_progress++; out_unlock: - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); return ret; } @@ -2518,15 +2519,15 @@ static void cpuset_cancel_attach(struct cgroup_taskset *tset) cgroup_taskset_first(tset, &css); cs = css_cs(css); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); cs->attach_in_progress--; if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); } /* - * Protected by cpuset_rwsem. cpus_attach is used only by cpuset_attach_task() + * Protected by cpuset_mutex. cpus_attach is used only by cpuset_attach_task() * but we can't allocate it dynamically there. Define it global and * allocate from cpuset_init(). */ @@ -2535,7 +2536,7 @@ static nodemask_t cpuset_attach_nodemask_to; static void cpuset_attach_task(struct cpuset *cs, struct task_struct *task) { - percpu_rwsem_assert_held(&cpuset_rwsem); + lockdep_assert_held(&cpuset_mutex); if (cs != &top_cpuset) guarantee_online_cpus(task, cpus_attach); @@ -2565,7 +2566,7 @@ static void cpuset_attach(struct cgroup_taskset *tset) cs = css_cs(css); lockdep_assert_cpus_held(); /* see cgroup_attach_lock() */ - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); cpus_updated = !cpumask_equal(cs->effective_cpus, oldcs->effective_cpus); mems_updated = !nodes_equal(cs->effective_mems, oldcs->effective_mems); @@ -2626,7 +2627,7 @@ out: if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); } /* The various types of files and directories in a cpuset file system */ @@ -2658,7 +2659,7 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, int retval = 0; cpus_read_lock(); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) { retval = -ENODEV; goto out_unlock; @@ -2694,7 +2695,7 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, break; } out_unlock: - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); cpus_read_unlock(); return retval; } @@ -2707,7 +2708,7 @@ static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, int retval = -ENODEV; cpus_read_lock(); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) goto out_unlock; @@ -2720,7 +2721,7 @@ static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, break; } out_unlock: - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); cpus_read_unlock(); return retval; } @@ -2753,7 +2754,7 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, * operation like this one can lead to a deadlock through kernfs * active_ref protection. Let's break the protection. Losing the * protection is okay as we check whether @cs is online after - * grabbing cpuset_rwsem anyway. This only happens on the legacy + * grabbing cpuset_mutex anyway. This only happens on the legacy * hierarchies. */ css_get(&cs->css); @@ -2761,7 +2762,7 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, flush_work(&cpuset_hotplug_work); cpus_read_lock(); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) goto out_unlock; @@ -2785,7 +2786,7 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, free_cpuset(trialcs); out_unlock: - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); cpus_read_unlock(); kernfs_unbreak_active_protection(of->kn); css_put(&cs->css); @@ -2933,13 +2934,13 @@ static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf, css_get(&cs->css); cpus_read_lock(); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) goto out_unlock; retval = update_prstate(cs, val); out_unlock: - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); cpus_read_unlock(); css_put(&cs->css); return retval ?: nbytes; @@ -3156,7 +3157,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) return 0; cpus_read_lock(); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); set_bit(CS_ONLINE, &cs->flags); if (is_spread_page(parent)) @@ -3207,7 +3208,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) cpumask_copy(cs->effective_cpus, parent->cpus_allowed); spin_unlock_irq(&callback_lock); out_unlock: - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); cpus_read_unlock(); return 0; } @@ -3228,7 +3229,7 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css) struct cpuset *cs = css_cs(css); cpus_read_lock(); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); if (is_partition_valid(cs)) update_prstate(cs, 0); @@ -3247,7 +3248,7 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css) cpuset_dec(); clear_bit(CS_ONLINE, &cs->flags); - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); cpus_read_unlock(); } @@ -3260,7 +3261,7 @@ static void cpuset_css_free(struct cgroup_subsys_state *css) static void cpuset_bind(struct cgroup_subsys_state *root_css) { - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); spin_lock_irq(&callback_lock); if (is_in_v2_mode()) { @@ -3273,7 +3274,7 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css) } spin_unlock_irq(&callback_lock); - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); } /* @@ -3294,7 +3295,7 @@ static int cpuset_can_fork(struct task_struct *task, struct css_set *cset) return 0; lockdep_assert_held(&cgroup_mutex); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); /* Check to see if task is allowed in the cpuset */ ret = cpuset_can_attach_check(cs); @@ -3315,7 +3316,7 @@ static int cpuset_can_fork(struct task_struct *task, struct css_set *cset) */ cs->attach_in_progress++; out_unlock: - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); return ret; } @@ -3331,11 +3332,11 @@ static void cpuset_cancel_fork(struct task_struct *task, struct css_set *cset) if (same_cs) return; - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); cs->attach_in_progress--; if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); } /* @@ -3363,7 +3364,7 @@ static void cpuset_fork(struct task_struct *task) } /* CLONE_INTO_CGROUP */ - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); guarantee_online_mems(cs, &cpuset_attach_nodemask_to); cpuset_attach_task(cs, task); @@ -3371,7 +3372,7 @@ static void cpuset_fork(struct task_struct *task) if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); } struct cgroup_subsys cpuset_cgrp_subsys = { @@ -3472,7 +3473,7 @@ hotplug_update_tasks_legacy(struct cpuset *cs, is_empty = cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed); - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); /* * Move tasks to the nearest ancestor with execution resources, @@ -3482,7 +3483,7 @@ hotplug_update_tasks_legacy(struct cpuset *cs, if (is_empty) remove_tasks_in_empty_cpuset(cs); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); } static void @@ -3533,14 +3534,14 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) retry: wait_event(cpuset_attach_wq, cs->attach_in_progress == 0); - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); /* * We have raced with task attaching. We wait until attaching * is finished, so we won't attach a task to an empty cpuset. */ if (cs->attach_in_progress) { - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); goto retry; } @@ -3637,7 +3638,7 @@ update_tasks: cpus_updated, mems_updated); unlock: - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); } /** @@ -3667,7 +3668,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work) if (on_dfl && !alloc_cpumasks(NULL, &tmp)) ptmp = &tmp; - percpu_down_write(&cpuset_rwsem); + mutex_lock(&cpuset_mutex); /* fetch the available cpus/mems and find out which changed how */ cpumask_copy(&new_cpus, cpu_active_mask); @@ -3724,7 +3725,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work) update_tasks_nodemask(&top_cpuset); } - percpu_up_write(&cpuset_rwsem); + mutex_unlock(&cpuset_mutex); /* if cpus or mems changed, we need to propagate to descendants */ if (cpus_updated || mems_updated) { @@ -4155,7 +4156,7 @@ void __cpuset_memory_pressure_bump(void) * - Used for /proc//cpuset. * - No need to task_lock(tsk) on this tsk->cpuset reference, as it * doesn't really matter if tsk->cpuset changes after we read it, - * and we take cpuset_rwsem, keeping cpuset_attach() from changing it + * and we take cpuset_mutex, keeping cpuset_attach() from changing it * anyway. */ int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 944c3ae39861..d826bec1c522 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7590,6 +7590,7 @@ static int __sched_setscheduler(struct task_struct *p, int reset_on_fork; int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK; struct rq *rq; + bool cpuset_locked = false; /* The pi code expects interrupts enabled */ BUG_ON(pi && in_interrupt()); @@ -7639,8 +7640,14 @@ recheck: return retval; } - if (pi) - cpuset_read_lock(); + /* + * SCHED_DEADLINE bandwidth accounting relies on stable cpusets + * information. + */ + if (dl_policy(policy) || dl_policy(p->policy)) { + cpuset_locked = true; + cpuset_lock(); + } /* * Make sure no PI-waiters arrive (or leave) while we are @@ -7716,8 +7723,8 @@ change: if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { policy = oldpolicy = -1; task_rq_unlock(rq, p, &rf); - if (pi) - cpuset_read_unlock(); + if (cpuset_locked) + cpuset_unlock(); goto recheck; } @@ -7784,7 +7791,8 @@ change: task_rq_unlock(rq, p, &rf); if (pi) { - cpuset_read_unlock(); + if (cpuset_locked) + cpuset_unlock(); rt_mutex_adjust_pi(p); } @@ -7796,8 +7804,8 @@ change: unlock: task_rq_unlock(rq, p, &rf); - if (pi) - cpuset_read_unlock(); + if (cpuset_locked) + cpuset_unlock(); return retval; } -- cgit v1.2.3 From 6c24849f5515e4966d94fa5279bdff4acf2e9489 Mon Sep 17 00:00:00 2001 From: Juri Lelli Date: Mon, 8 May 2023 09:58:51 +0200 Subject: sched/cpuset: Keep track of SCHED_DEADLINE task in cpusets Qais reported that iterating over all tasks when rebuilding root domains for finding out which ones are DEADLINE and need their bandwidth correctly restored on such root domains can be a costly operation (10+ ms delays on suspend-resume). To fix the problem keep track of the number of DEADLINE tasks belonging to each cpuset and then use this information (followup patch) to only perform the above iteration if DEADLINE tasks are actually present in the cpuset for which a corresponding root domain is being rebuilt. Reported-by: Qais Yousef Link: https://lore.kernel.org/lkml/20230206221428.2125324-1-qyousef@layalina.io/ Signed-off-by: Juri Lelli Reviewed-by: Waiman Long Signed-off-by: Tejun Heo --- include/linux/cpuset.h | 4 ++++ kernel/cgroup/cgroup.c | 4 ++++ kernel/cgroup/cpuset.c | 25 +++++++++++++++++++++++++ kernel/sched/deadline.c | 14 ++++++++++++++ 4 files changed, 47 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index f90e6325d707..d629094fac6e 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -71,6 +71,8 @@ extern void cpuset_init_smp(void); extern void cpuset_force_rebuild(void); extern void cpuset_update_active_cpus(void); extern void cpuset_wait_for_hotplug(void); +extern void inc_dl_tasks_cs(struct task_struct *task); +extern void dec_dl_tasks_cs(struct task_struct *task); extern void cpuset_lock(void); extern void cpuset_unlock(void); extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); @@ -189,6 +191,8 @@ static inline void cpuset_update_active_cpus(void) static inline void cpuset_wait_for_hotplug(void) { } +static inline void inc_dl_tasks_cs(struct task_struct *task) { } +static inline void dec_dl_tasks_cs(struct task_struct *task) { } static inline void cpuset_lock(void) { } static inline void cpuset_unlock(void) { } diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 625d7483951c..9d809191a54f 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -57,6 +57,7 @@ #include #include #include +#include #include #include @@ -6683,6 +6684,9 @@ void cgroup_exit(struct task_struct *tsk) list_add_tail(&tsk->cg_list, &cset->dying_tasks); cset->nr_tasks--; + if (dl_task(tsk)) + dec_dl_tasks_cs(tsk); + WARN_ON_ONCE(cgroup_task_frozen(tsk)); if (unlikely(!(tsk->flags & PF_KTHREAD) && test_bit(CGRP_FREEZE, &task_dfl_cgroup(tsk)->flags))) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 041c0809adaf..ca195ff8b298 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -193,6 +193,12 @@ struct cpuset { int use_parent_ecpus; int child_ecpus_count; + /* + * number of SCHED_DEADLINE tasks attached to this cpuset, so that we + * know when to rebuild associated root domain bandwidth information. + */ + int nr_deadline_tasks; + /* Invalid partition error code, not lock protected */ enum prs_errcode prs_err; @@ -245,6 +251,20 @@ static inline struct cpuset *parent_cs(struct cpuset *cs) return css_cs(cs->css.parent); } +void inc_dl_tasks_cs(struct task_struct *p) +{ + struct cpuset *cs = task_cs(p); + + cs->nr_deadline_tasks++; +} + +void dec_dl_tasks_cs(struct task_struct *p) +{ + struct cpuset *cs = task_cs(p); + + cs->nr_deadline_tasks--; +} + /* bits in struct cpuset flags field */ typedef enum { CS_ONLINE, @@ -2499,6 +2519,11 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) ret = security_task_setscheduler(task); if (ret) goto out_unlock; + + if (dl_task(task)) { + cs->nr_deadline_tasks++; + cpuset_attach_old_cs->nr_deadline_tasks--; + } } /* diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 5a9a4b81c972..e11de074a6fd 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -16,6 +16,8 @@ * Fabio Checconi */ +#include + /* * Default limits for DL period; on the top end we guard against small util * tasks still getting ridiculously long effective runtimes, on the bottom end we @@ -2596,6 +2598,12 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p) if (task_on_rq_queued(p) && p->dl.dl_runtime) task_non_contending(p); + /* + * In case a task is setscheduled out from SCHED_DEADLINE we need to + * keep track of that on its cpuset (for correct bandwidth tracking). + */ + dec_dl_tasks_cs(p); + if (!task_on_rq_queued(p)) { /* * Inactive timer is armed. However, p is leaving DEADLINE and @@ -2636,6 +2644,12 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p) if (hrtimer_try_to_cancel(&p->dl.inactive_timer) == 1) put_task_struct(p); + /* + * In case a task is setscheduled to SCHED_DEADLINE we need to keep + * track of that on its cpuset (for correct bandwidth tracking). + */ + inc_dl_tasks_cs(p); + /* If p is not queued we will update its parameters at next wakeup. */ if (!task_on_rq_queued(p)) { add_rq_bw(&p->dl, &rq->dl); -- cgit v1.2.3 From 85989106feb734437e2d598b639991b9185a43a6 Mon Sep 17 00:00:00 2001 From: Dietmar Eggemann Date: Mon, 8 May 2023 09:58:53 +0200 Subject: sched/deadline: Create DL BW alloc, free & check overflow interface While moving a set of tasks between exclusive cpusets, cpuset_can_attach() -> task_can_attach() calls dl_cpu_busy(..., p) for DL BW overflow checking and per-task DL BW allocation on the destination root_domain for the DL tasks in this set. This approach has the issue of not freeing already allocated DL BW in the following error cases: (1) The set of tasks includes multiple DL tasks and DL BW overflow checking fails for one of the subsequent DL tasks. (2) Another controller next to the cpuset controller which is attached to the same cgroup fails in its can_attach(). To address this problem rework dl_cpu_busy(): (1) Split it into dl_bw_check_overflow() & dl_bw_alloc() and add a dedicated dl_bw_free(). (2) dl_bw_alloc() & dl_bw_free() take a `u64 dl_bw` parameter instead of a `struct task_struct *p` used in dl_cpu_busy(). This allows to allocate DL BW for a set of tasks too rather than only for a single task. Signed-off-by: Dietmar Eggemann Signed-off-by: Juri Lelli Signed-off-by: Tejun Heo --- include/linux/sched.h | 2 ++ kernel/sched/core.c | 4 ++-- kernel/sched/deadline.c | 53 +++++++++++++++++++++++++++++++++++++------------ kernel/sched/sched.h | 2 +- 4 files changed, 45 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index eed5d65b8d1f..0bee06542450 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1853,6 +1853,8 @@ current_restore_flags(unsigned long orig_flags, unsigned long flags) extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial); extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_effective_cpus); +extern int dl_bw_alloc(int cpu, u64 dl_bw); +extern void dl_bw_free(int cpu, u64 dl_bw); #ifdef CONFIG_SMP extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask); extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d826bec1c522..df659892d7d5 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -9319,7 +9319,7 @@ int task_can_attach(struct task_struct *p, if (unlikely(cpu >= nr_cpu_ids)) return -EINVAL; - ret = dl_cpu_busy(cpu, p); + ret = dl_bw_alloc(cpu, p->dl.dl_bw); } out: @@ -9604,7 +9604,7 @@ static void cpuset_cpu_active(void) static int cpuset_cpu_inactive(unsigned int cpu) { if (!cpuhp_tasks_frozen) { - int ret = dl_cpu_busy(cpu, NULL); + int ret = dl_bw_check_overflow(cpu); if (ret) return ret; diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index e11de074a6fd..166c3e6eae61 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -3058,26 +3058,38 @@ int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, return ret; } -int dl_cpu_busy(int cpu, struct task_struct *p) +enum dl_bw_request { + dl_bw_req_check_overflow = 0, + dl_bw_req_alloc, + dl_bw_req_free +}; + +static int dl_bw_manage(enum dl_bw_request req, int cpu, u64 dl_bw) { - unsigned long flags, cap; + unsigned long flags; struct dl_bw *dl_b; - bool overflow; + bool overflow = 0; rcu_read_lock_sched(); dl_b = dl_bw_of(cpu); raw_spin_lock_irqsave(&dl_b->lock, flags); - cap = dl_bw_capacity(cpu); - overflow = __dl_overflow(dl_b, cap, 0, p ? p->dl.dl_bw : 0); - if (!overflow && p) { - /* - * We reserve space for this task in the destination - * root_domain, as we can't fail after this point. - * We will free resources in the source root_domain - * later on (see set_cpus_allowed_dl()). - */ - __dl_add(dl_b, p->dl.dl_bw, dl_bw_cpus(cpu)); + if (req == dl_bw_req_free) { + __dl_sub(dl_b, dl_bw, dl_bw_cpus(cpu)); + } else { + unsigned long cap = dl_bw_capacity(cpu); + + overflow = __dl_overflow(dl_b, cap, 0, dl_bw); + + if (req == dl_bw_req_alloc && !overflow) { + /* + * We reserve space in the destination + * root_domain, as we can't fail after this point. + * We will free resources in the source root_domain + * later on (see set_cpus_allowed_dl()). + */ + __dl_add(dl_b, dl_bw, dl_bw_cpus(cpu)); + } } raw_spin_unlock_irqrestore(&dl_b->lock, flags); @@ -3085,6 +3097,21 @@ int dl_cpu_busy(int cpu, struct task_struct *p) return overflow ? -EBUSY : 0; } + +int dl_bw_check_overflow(int cpu) +{ + return dl_bw_manage(dl_bw_req_check_overflow, cpu, 0); +} + +int dl_bw_alloc(int cpu, u64 dl_bw) +{ + return dl_bw_manage(dl_bw_req_alloc, cpu, dl_bw); +} + +void dl_bw_free(int cpu, u64 dl_bw) +{ + dl_bw_manage(dl_bw_req_free, cpu, dl_bw); +} #endif #ifdef CONFIG_SCHED_DEBUG diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index ec7b3e0a2b20..0ad712811e35 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -330,7 +330,7 @@ extern void __getparam_dl(struct task_struct *p, struct sched_attr *attr); extern bool __checkparam_dl(const struct sched_attr *attr); extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr); extern int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial); -extern int dl_cpu_busy(int cpu, struct task_struct *p); +extern int dl_bw_check_overflow(int cpu); #ifdef CONFIG_CGROUP_SCHED -- cgit v1.2.3 From 2ef269ef1ac006acf974793d975539244d77b28f Mon Sep 17 00:00:00 2001 From: Dietmar Eggemann Date: Mon, 8 May 2023 09:58:54 +0200 Subject: cgroup/cpuset: Free DL BW in case can_attach() fails cpuset_can_attach() can fail. Postpone DL BW allocation until all tasks have been checked. DL BW is not allocated per-task but as a sum over all DL tasks migrating. If multiple controllers are attached to the cgroup next to the cpuset controller a non-cpuset can_attach() can fail. In this case free DL BW in cpuset_cancel_attach(). Finally, update cpuset DL task count (nr_deadline_tasks) only in cpuset_attach(). Suggested-by: Waiman Long Signed-off-by: Dietmar Eggemann Signed-off-by: Juri Lelli Reviewed-by: Waiman Long Signed-off-by: Tejun Heo --- include/linux/sched.h | 2 +- kernel/cgroup/cpuset.c | 53 +++++++++++++++++++++++++++++++++++++++++++++----- kernel/sched/core.c | 17 ++-------------- 3 files changed, 51 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 0bee06542450..2553918f0b61 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1852,7 +1852,7 @@ current_restore_flags(unsigned long orig_flags, unsigned long flags) } extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial); -extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_effective_cpus); +extern int task_can_attach(struct task_struct *p); extern int dl_bw_alloc(int cpu, u64 dl_bw); extern void dl_bw_free(int cpu, u64 dl_bw); #ifdef CONFIG_SMP diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index b7168970fff2..2c76fcd9f0bc 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -198,6 +198,8 @@ struct cpuset { * know when to rebuild associated root domain bandwidth information. */ int nr_deadline_tasks; + int nr_migrate_dl_tasks; + u64 sum_migrate_dl_bw; /* Invalid partition error code, not lock protected */ enum prs_errcode prs_err; @@ -2496,16 +2498,23 @@ static int cpuset_can_attach_check(struct cpuset *cs) return 0; } +static void reset_migrate_dl_data(struct cpuset *cs) +{ + cs->nr_migrate_dl_tasks = 0; + cs->sum_migrate_dl_bw = 0; +} + /* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */ static int cpuset_can_attach(struct cgroup_taskset *tset) { struct cgroup_subsys_state *css; - struct cpuset *cs; + struct cpuset *cs, *oldcs; struct task_struct *task; int ret; /* used later by cpuset_attach() */ cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css)); + oldcs = cpuset_attach_old_cs; cs = css_cs(css); mutex_lock(&cpuset_mutex); @@ -2516,7 +2525,7 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) goto out_unlock; cgroup_taskset_for_each(task, css, tset) { - ret = task_can_attach(task, cs->effective_cpus); + ret = task_can_attach(task); if (ret) goto out_unlock; ret = security_task_setscheduler(task); @@ -2524,11 +2533,31 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) goto out_unlock; if (dl_task(task)) { - cs->nr_deadline_tasks++; - cpuset_attach_old_cs->nr_deadline_tasks--; + cs->nr_migrate_dl_tasks++; + cs->sum_migrate_dl_bw += task->dl.dl_bw; } } + if (!cs->nr_migrate_dl_tasks) + goto out_success; + + if (!cpumask_intersects(oldcs->effective_cpus, cs->effective_cpus)) { + int cpu = cpumask_any_and(cpu_active_mask, cs->effective_cpus); + + if (unlikely(cpu >= nr_cpu_ids)) { + reset_migrate_dl_data(cs); + ret = -EINVAL; + goto out_unlock; + } + + ret = dl_bw_alloc(cpu, cs->sum_migrate_dl_bw); + if (ret) { + reset_migrate_dl_data(cs); + goto out_unlock; + } + } + +out_success: /* * Mark attach is in progress. This makes validate_change() fail * changes which zero cpus/mems_allowed. @@ -2551,6 +2580,14 @@ static void cpuset_cancel_attach(struct cgroup_taskset *tset) cs->attach_in_progress--; if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); + + if (cs->nr_migrate_dl_tasks) { + int cpu = cpumask_any(cs->effective_cpus); + + dl_bw_free(cpu, cs->sum_migrate_dl_bw); + reset_migrate_dl_data(cs); + } + mutex_unlock(&cpuset_mutex); } @@ -2651,6 +2688,12 @@ static void cpuset_attach(struct cgroup_taskset *tset) out: cs->old_mems_allowed = cpuset_attach_nodemask_to; + if (cs->nr_migrate_dl_tasks) { + cs->nr_deadline_tasks += cs->nr_migrate_dl_tasks; + oldcs->nr_deadline_tasks -= cs->nr_migrate_dl_tasks; + reset_migrate_dl_data(cs); + } + cs->attach_in_progress--; if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); @@ -3330,7 +3373,7 @@ static int cpuset_can_fork(struct task_struct *task, struct css_set *cset) if (ret) goto out_unlock; - ret = task_can_attach(task, cs->effective_cpus); + ret = task_can_attach(task); if (ret) goto out_unlock; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index df659892d7d5..ed0d7381b2ec 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -9294,8 +9294,7 @@ int cpuset_cpumask_can_shrink(const struct cpumask *cur, return ret; } -int task_can_attach(struct task_struct *p, - const struct cpumask *cs_effective_cpus) +int task_can_attach(struct task_struct *p) { int ret = 0; @@ -9308,21 +9307,9 @@ int task_can_attach(struct task_struct *p, * success of set_cpus_allowed_ptr() on all attached tasks * before cpus_mask may be changed. */ - if (p->flags & PF_NO_SETAFFINITY) { + if (p->flags & PF_NO_SETAFFINITY) ret = -EINVAL; - goto out; - } - - if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span, - cs_effective_cpus)) { - int cpu = cpumask_any_and(cpu_active_mask, cs_effective_cpus); - if (unlikely(cpu >= nr_cpu_ids)) - return -EINVAL; - ret = dl_bw_alloc(cpu, p->dl.dl_bw); - } - -out: return ret; } -- cgit v1.2.3 From b4cc979588ee94b179e28c6f3f5c2d6197ea6461 Mon Sep 17 00:00:00 2001 From: Armin Wolf Date: Tue, 25 Apr 2023 00:29:36 +0200 Subject: platform/x86: wmi: Add kernel doc comments Add kernel doc comments useful for documenting the functions/structs used to interact with the WMI driver core. Signed-off-by: Armin Wolf Tested-by: Randy Dunlap Acked-by: Randy Dunlap Link: https://lore.kernel.org/r/20230424222939.208137-2-W_Armin@gmx.de Signed-off-by: Hans de Goede --- drivers/platform/x86/wmi.c | 51 ++++++++++++++++++++++++++++++++++++++-------- include/linux/wmi.h | 41 ++++++++++++++++++++++++++++++++++--- 2 files changed, 80 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c index d81319a502ef..99af2cc03b0f 100644 --- a/drivers/platform/x86/wmi.c +++ b/drivers/platform/x86/wmi.c @@ -248,7 +248,9 @@ static acpi_status get_event_data(const struct wmi_block *wblock, struct acpi_bu * @wdev: A wmi bus device from a driver * @length: Required buffer size * - * Allocates memory needed for buffer, stores the buffer size in that memory + * Allocates memory needed for buffer, stores the buffer size in that memory. + * + * Return: 0 on success or a negative error code for failure. */ int set_required_buffer_size(struct wmi_device *wdev, u64 length) { @@ -269,7 +271,9 @@ EXPORT_SYMBOL_GPL(set_required_buffer_size); * @in: Buffer containing input for the method call * @out: Empty buffer to return the method results * - * Call an ACPI-WMI method + * Call an ACPI-WMI method, the caller must free @out. + * + * Return: acpi_status signaling success or error. */ acpi_status wmi_evaluate_method(const char *guid_string, u8 instance, u32 method_id, const struct acpi_buffer *in, struct acpi_buffer *out) @@ -294,7 +298,9 @@ EXPORT_SYMBOL_GPL(wmi_evaluate_method); * @in: Buffer containing input for the method call * @out: Empty buffer to return the method results * - * Call an ACPI-WMI method + * Call an ACPI-WMI method, the caller must free @out. + * + * Return: acpi_status signaling success or error. */ acpi_status wmidev_evaluate_method(struct wmi_device *wdev, u8 instance, u32 method_id, const struct acpi_buffer *in, struct acpi_buffer *out) @@ -411,7 +417,9 @@ static acpi_status __query_block(struct wmi_block *wblock, u8 instance, * @instance: Instance index * @out: Empty buffer to return the contents of the data block to * - * Return the contents of an ACPI-WMI data block to a buffer + * Query a ACPI-WMI block, the caller must free @out. + * + * Return: ACPI object containing the content of the WMI block. */ acpi_status wmi_query_block(const char *guid_string, u8 instance, struct acpi_buffer *out) @@ -427,6 +435,15 @@ acpi_status wmi_query_block(const char *guid_string, u8 instance, } EXPORT_SYMBOL_GPL(wmi_query_block); +/** + * wmidev_block_query - Return contents of a WMI block + * @wdev: A wmi bus device from a driver + * @instance: Instance index + * + * Query an ACPI-WMI block, the caller must free the result. + * + * Return: ACPI object containing the content of the WMI block. + */ union acpi_object *wmidev_block_query(struct wmi_device *wdev, u8 instance) { struct acpi_buffer out = { ACPI_ALLOCATE_BUFFER, NULL }; @@ -445,7 +462,9 @@ EXPORT_SYMBOL_GPL(wmidev_block_query); * @instance: Instance index * @in: Buffer containing new values for the data block * - * Write the contents of the input buffer to an ACPI-WMI data block + * Write the contents of the input buffer to an ACPI-WMI data block. + * + * Return: acpi_status signaling success or error. */ acpi_status wmi_set_block(const char *guid_string, u8 instance, const struct acpi_buffer *in) @@ -555,6 +574,8 @@ static void wmi_notify_debug(u32 value, void *context) * @data: Data to be returned to handler when event is fired * * Register a handler for events sent to the ACPI-WMI mapper device. + * + * Return: acpi_status signaling success or error. */ acpi_status wmi_install_notify_handler(const char *guid, wmi_notify_handler handler, @@ -597,6 +618,8 @@ EXPORT_SYMBOL_GPL(wmi_install_notify_handler); * @guid: 36 char string of the form fa50ff2b-f2e8-45de-83fa-65417f2f49ba * * Unregister handler for events sent to the ACPI-WMI mapper device. + * + * Return: acpi_status signaling success or error. */ acpi_status wmi_remove_notify_handler(const char *guid) { @@ -641,9 +664,11 @@ EXPORT_SYMBOL_GPL(wmi_remove_notify_handler); * wmi_get_event_data - Get WMI data associated with an event * * @event: Event to find - * @out: Buffer to hold event data. out->pointer should be freed with kfree() + * @out: Buffer to hold event data + * + * Get extra data associated with an WMI event, the caller needs to free @out. * - * Returns extra data associated with an event in WMI. + * Return: acpi_status signaling success or error. */ acpi_status wmi_get_event_data(u32 event, struct acpi_buffer *out) { @@ -664,7 +689,9 @@ EXPORT_SYMBOL_GPL(wmi_get_event_data); * wmi_has_guid - Check if a GUID is available * @guid_string: 36 char string of the form fa50ff2b-f2e8-45de-83fa-65417f2f49ba * - * Check if a given GUID is defined by _WDG + * Check if a given GUID is defined by _WDG. + * + * Return: True if GUID is available, false otherwise. */ bool wmi_has_guid(const char *guid_string) { @@ -678,7 +705,7 @@ EXPORT_SYMBOL_GPL(wmi_has_guid); * * Find the _UID of ACPI device associated with this WMI GUID. * - * Return: The ACPI _UID field value or NULL if the WMI GUID was not found + * Return: The ACPI _UID field value or NULL if the WMI GUID was not found. */ char *wmi_get_acpi_device_uid(const char *guid_string) { @@ -1454,6 +1481,12 @@ int __must_check __wmi_driver_register(struct wmi_driver *driver, } EXPORT_SYMBOL(__wmi_driver_register); +/** + * wmi_driver_unregister() - Unregister a WMI driver + * @driver: WMI driver to unregister + * + * Unregisters a WMI driver from the WMI bus. + */ void wmi_driver_unregister(struct wmi_driver *driver) { driver_unregister(&driver->driver); diff --git a/include/linux/wmi.h b/include/linux/wmi.h index b88d7b58e61e..c1a3bd4e4838 100644 --- a/include/linux/wmi.h +++ b/include/linux/wmi.h @@ -13,25 +13,44 @@ #include #include +/** + * struct wmi_device - WMI device structure + * @dev: Device associated with this WMI device + * @setable: True for devices implementing the Set Control Method + * + * This represents WMI devices discovered by the WMI driver core. + */ struct wmi_device { struct device dev; - /* True for data blocks implementing the Set Control Method */ + /* private: used by the WMI driver core */ bool setable; }; -/* evaluate the ACPI method associated with this device */ extern acpi_status wmidev_evaluate_method(struct wmi_device *wdev, u8 instance, u32 method_id, const struct acpi_buffer *in, struct acpi_buffer *out); -/* Caller must kfree the result. */ extern union acpi_object *wmidev_block_query(struct wmi_device *wdev, u8 instance); extern int set_required_buffer_size(struct wmi_device *wdev, u64 length); +/** + * struct wmi_driver - WMI driver structure + * @driver: Driver model structure + * @id_table: List of WMI GUIDs supported by this driver + * @no_notify_data: WMI events provide no event data + * @probe: Callback for device binding + * @remove: Callback for device unbinding + * @notify: Callback for receiving WMI events + * @filter_callback: Callback for filtering device IOCTLs + * + * This represents WMI drivers which handle WMI devices. + * @filter_callback is only necessary for drivers which + * want to set up a WMI IOCTL interface. + */ struct wmi_driver { struct device_driver driver; const struct wmi_device_id *id_table; @@ -47,8 +66,24 @@ struct wmi_driver { extern int __must_check __wmi_driver_register(struct wmi_driver *driver, struct module *owner); extern void wmi_driver_unregister(struct wmi_driver *driver); + +/** + * wmi_driver_register() - Helper macro to register a WMI driver + * @driver: wmi_driver struct + * + * Helper macro for registering a WMI driver. It automatically passes + * THIS_MODULE to the underlying function. + */ #define wmi_driver_register(driver) __wmi_driver_register((driver), THIS_MODULE) +/** + * module_wmi_driver() - Helper macro to register/unregister a WMI driver + * @__wmi_driver: wmi_driver struct + * + * Helper macro for WMI drivers which do not do anything special in module + * init/exit. This eliminates a lot of boilerplate. Each module may only + * use this macro once, and calling it replaces module_init() and module_exit(). + */ #define module_wmi_driver(__wmi_driver) \ module_driver(__wmi_driver, wmi_driver_register, \ wmi_driver_unregister) -- cgit v1.2.3 From 2a2b13ae50cf70e07b471301ff50299f31d81c1d Mon Sep 17 00:00:00 2001 From: Armin Wolf Date: Sun, 30 Apr 2023 22:31:52 +0200 Subject: platform/x86: wmi: Allow retrieving the number of WMI object instances Currently, the WMI driver core knows how many instances of a given WMI object exist, but WMI drivers cannot access this information. At the same time, some current and upcoming WMI drivers want to have access to this information. Add wmi_instance_count() and wmidev_instance_count() to allow WMI drivers to get the number of WMI object instances. Signed-off-by: Armin Wolf Link: https://lore.kernel.org/r/20230430203153.5587-2-W_Armin@gmx.de Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede --- drivers/platform/x86/wmi.c | 41 +++++++++++++++++++++++++++++++++++++++++ include/linux/acpi.h | 2 ++ include/linux/wmi.h | 2 ++ 3 files changed, 45 insertions(+) (limited to 'include/linux') diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c index c226dd4163a1..5b95d7aa5c2f 100644 --- a/drivers/platform/x86/wmi.c +++ b/drivers/platform/x86/wmi.c @@ -263,6 +263,47 @@ int set_required_buffer_size(struct wmi_device *wdev, u64 length) } EXPORT_SYMBOL_GPL(set_required_buffer_size); +/** + * wmi_instance_count - Get number of WMI object instances + * @guid_string: 36 char string of the form fa50ff2b-f2e8-45de-83fa-65417f2f49ba + * + * Get the number of WMI object instances. + * + * Returns: Number of WMI object instances or negative error code. + */ +int wmi_instance_count(const char *guid_string) +{ + struct wmi_block *wblock; + acpi_status status; + + status = find_guid(guid_string, &wblock); + if (ACPI_FAILURE(status)) { + if (status == AE_BAD_PARAMETER) + return -EINVAL; + + return -ENODEV; + } + + return wmidev_instance_count(&wblock->dev); +} +EXPORT_SYMBOL_GPL(wmi_instance_count); + +/** + * wmidev_instance_count - Get number of WMI object instances + * @wdev: A wmi bus device from a driver + * + * Get the number of WMI object instances. + * + * Returns: Number of WMI object instances. + */ +u8 wmidev_instance_count(struct wmi_device *wdev) +{ + struct wmi_block *wblock = container_of(wdev, struct wmi_block, dev); + + return wblock->gblock.instance_count; +} +EXPORT_SYMBOL_GPL(wmidev_instance_count); + /** * wmi_evaluate_method - Evaluate a WMI method (deprecated) * @guid_string: 36 char string of the form fa50ff2b-f2e8-45de-83fa-65417f2f49ba diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 7b71dd74baeb..5b9353f56928 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -414,6 +414,8 @@ extern bool acpi_is_pnp_device(struct acpi_device *); typedef void (*wmi_notify_handler) (u32 value, void *context); +int wmi_instance_count(const char *guid); + extern acpi_status wmi_evaluate_method(const char *guid, u8 instance, u32 method_id, const struct acpi_buffer *in, diff --git a/include/linux/wmi.h b/include/linux/wmi.h index c1a3bd4e4838..763bd382cf2d 100644 --- a/include/linux/wmi.h +++ b/include/linux/wmi.h @@ -35,6 +35,8 @@ extern acpi_status wmidev_evaluate_method(struct wmi_device *wdev, extern union acpi_object *wmidev_block_query(struct wmi_device *wdev, u8 instance); +u8 wmidev_instance_count(struct wmi_device *wdev); + extern int set_required_buffer_size(struct wmi_device *wdev, u64 length); /** -- cgit v1.2.3 From 0ac448e0d29d6ba978684b3fa2e3ac7294ec2475 Mon Sep 17 00:00:00 2001 From: Mike Pastore Date: Sun, 7 May 2023 02:35:19 -0500 Subject: PCI: Delay after FLR of Solidigm P44 Pro NVMe Prevent KVM hang when a Solidgm P44 Pro NVMe is passed through to a guest via IOMMU and the guest is subsequently rebooted. A similar issue was identified and patched by 51ba09452d11 ("PCI: Delay after FLR of Intel DC P3700 NVMe") and the same fix can be applied for this case. (Intel spun off their NAND and SSD business as Solidigm and sold it to SK Hynix in late 2021.) Link: https://lore.kernel.org/r/20230507073519.9737-1-mike@oobak.org Signed-off-by: Mike Pastore Signed-off-by: Bjorn Helgaas --- drivers/pci/quirks.c | 10 ++++++---- include/linux/pci_ids.h | 2 ++ 2 files changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index f4e2a88729fd..c1239706eeaf 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -3993,10 +3993,11 @@ static int nvme_disable_and_flr(struct pci_dev *dev, bool probe) } /* - * Intel DC P3700 NVMe controller will timeout waiting for ready status - * to change after NVMe enable if the driver starts interacting with the - * device too soon after FLR. A 250ms delay after FLR has heuristically - * proven to produce reliably working results for device assignment cases. + * Some NVMe controllers such as Intel DC P3700 and Solidigm P44 Pro will + * timeout waiting for ready status to change after NVMe enable if the driver + * starts interacting with the device too soon after FLR. A 250ms delay after + * FLR has heuristically proven to produce reliably working results for device + * assignment cases. */ static int delay_250ms_after_flr(struct pci_dev *dev, bool probe) { @@ -4083,6 +4084,7 @@ static const struct pci_dev_reset_methods pci_dev_reset_methods[] = { { PCI_VENDOR_ID_SAMSUNG, 0xa804, nvme_disable_and_flr }, { PCI_VENDOR_ID_INTEL, 0x0953, delay_250ms_after_flr }, { PCI_VENDOR_ID_INTEL, 0x0a54, delay_250ms_after_flr }, + { PCI_VENDOR_ID_SOLIDIGM, 0xf1ac, delay_250ms_after_flr }, { PCI_VENDOR_ID_CHELSIO, PCI_ANY_ID, reset_chelsio_generic_dev }, { PCI_VENDOR_ID_HUAWEI, PCI_DEVICE_ID_HINIC_VF, diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 45c3d62e616d..20c3403a62cd 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -158,6 +158,8 @@ #define PCI_VENDOR_ID_LOONGSON 0x0014 +#define PCI_VENDOR_ID_SOLIDIGM 0x025e + #define PCI_VENDOR_ID_TTTECH 0x0357 #define PCI_DEVICE_ID_TTTECH_MC322 0x000a -- cgit v1.2.3 From 1da82598cfc22f43fb0a3bd47774f7e886cc8b62 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 18 Mar 2023 13:51:10 -0700 Subject: srcu: Remove extraneous parentheses from srcu_read_lock() etc. This commit removes extraneous parentheses from srcu_read_lock(), srcu_read_lock_nmisafe(), srcu_read_unlock(), and srcu_read_unlock_nmisafe(). Looks like someone was once a macro. Cc: Christoph Hellwig Tested-by: Sachin Sant Tested-by: "Zhang, Qiang1" Signed-off-by: Paul E. McKenney --- include/linux/srcu.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 41c4b26fb1c1..eb92a50a4599 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -212,7 +212,7 @@ static inline int srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp) srcu_check_nmi_safety(ssp, false); retval = __srcu_read_lock(ssp); - srcu_lock_acquire(&(ssp)->dep_map); + srcu_lock_acquire(&ssp->dep_map); return retval; } @@ -229,7 +229,7 @@ static inline int srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires(ssp srcu_check_nmi_safety(ssp, true); retval = __srcu_read_lock_nmisafe(ssp); - rcu_lock_acquire(&(ssp)->dep_map); + rcu_lock_acquire(&ssp->dep_map); return retval; } @@ -284,7 +284,7 @@ static inline void srcu_read_unlock(struct srcu_struct *ssp, int idx) { WARN_ON_ONCE(idx & ~0x1); srcu_check_nmi_safety(ssp, false); - srcu_lock_release(&(ssp)->dep_map); + srcu_lock_release(&ssp->dep_map); __srcu_read_unlock(ssp, idx); } @@ -300,7 +300,7 @@ static inline void srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) { WARN_ON_ONCE(idx & ~0x1); srcu_check_nmi_safety(ssp, true); - rcu_lock_release(&(ssp)->dep_map); + rcu_lock_release(&ssp->dep_map); __srcu_read_unlock_nmisafe(ssp, idx); } -- cgit v1.2.3 From 7e3f926bf4538cb4988b3e3f8bc1cb4a603b2ef6 Mon Sep 17 00:00:00 2001 From: "Uladzislau Rezki (Sony)" Date: Wed, 1 Feb 2023 16:09:54 +0100 Subject: rcu/kvfree: Eliminate k[v]free_rcu() single argument macro The kvfree_rcu() and kfree_rcu() APIs are hazardous in that if you forget the second argument, it works, but might sleep. This sleeping can be a correctness bug from atomic contexts, and even in non-atomic contexts it might introduce unacceptable latencies. This commit therefore removes the single-argument kvfree_rcu() and kfree_rcu() macros. Code that would have previously used these single-argument kvfree_rcu() and kfree_rcu() macros should instead use kvfree_rcu_mightsleep() or kfree_rcu_mightsleep(). [ paulmck: Apply Joel Fernandes feedback. ] Signed-off-by: Uladzislau Rezki (Sony) Signed-off-by: Paul E. McKenney Signed-off-by: Joel Fernandes (Google) --- include/linux/rcupdate.h | 29 ++++++++--------------------- 1 file changed, 8 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index dcd2cf1e8326..744869ef930a 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -957,9 +957,8 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) /** * kfree_rcu() - kfree an object after a grace period. - * @ptr: pointer to kfree for both single- and double-argument invocations. - * @rhf: the name of the struct rcu_head within the type of @ptr, - * but only for double-argument invocations. + * @ptr: pointer to kfree for double-argument invocations. + * @rhf: the name of the struct rcu_head within the type of @ptr. * * Many rcu callbacks functions just call kfree() on the base structure. * These functions are trivial, but their size adds up, and furthermore @@ -984,26 +983,18 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) * The BUILD_BUG_ON check must not involve any function calls, hence the * checks are done in macros here. */ -#define kfree_rcu(ptr, rhf...) kvfree_rcu(ptr, ## rhf) +#define kfree_rcu(ptr, rhf) kvfree_rcu_arg_2(ptr, rhf) +#define kvfree_rcu(ptr, rhf) kvfree_rcu_arg_2(ptr, rhf) /** - * kvfree_rcu() - kvfree an object after a grace period. - * - * This macro consists of one or two arguments and it is - * based on whether an object is head-less or not. If it - * has a head then a semantic stays the same as it used - * to be before: - * - * kvfree_rcu(ptr, rhf); - * - * where @ptr is a pointer to kvfree(), @rhf is the name - * of the rcu_head structure within the type of @ptr. + * kfree_rcu_mightsleep() - kfree an object after a grace period. + * @ptr: pointer to kfree for single-argument invocations. * * When it comes to head-less variant, only one argument * is passed and that is just a pointer which has to be * freed after a grace period. Therefore the semantic is * - * kvfree_rcu(ptr); + * kfree_rcu_mightsleep(ptr); * * where @ptr is the pointer to be freed by kvfree(). * @@ -1012,13 +1003,9 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) * annotation. Otherwise, please switch and embed the * rcu_head structure within the type of @ptr. */ -#define kvfree_rcu(...) KVFREE_GET_MACRO(__VA_ARGS__, \ - kvfree_rcu_arg_2, kvfree_rcu_arg_1)(__VA_ARGS__) - +#define kfree_rcu_mightsleep(ptr) kvfree_rcu_arg_1(ptr) #define kvfree_rcu_mightsleep(ptr) kvfree_rcu_arg_1(ptr) -#define kfree_rcu_mightsleep(ptr) kvfree_rcu_mightsleep(ptr) -#define KVFREE_GET_MACRO(_1, _2, NAME, ...) NAME #define kvfree_rcu_arg_2(ptr, rhf) \ do { \ typeof (ptr) ___p = (ptr); \ -- cgit v1.2.3 From 212bc1ce618dd7c734920a68988fe4b473f09f40 Mon Sep 17 00:00:00 2001 From: Aidan MacDonald Date: Tue, 9 May 2023 12:00:55 +0100 Subject: regmap-irq: Fix typo in documentation for .get_irq_reg() It refers to a non-existent "num_type_settings" value, which is an old name I'd used during development of config registers and later dropped because it wasn't very clear. The correct bound for the range is num_config_regs, which can be verified by checking the implementation. Signed-off-by: Aidan MacDonald Date: Tue, 9 May 2023 12:00:56 +0100 Subject: regmap-irq: Remove virtual registers No remaining users, and it's been replaced by config registers. Signed-off-by: Aidan MacDonald chip->num_virt_regs) { - for (i = 0; i < d->chip->num_virt_regs; i++) { - for (j = 0; j < d->chip->num_regs; j++) { - reg = d->get_irq_reg(d, d->chip->virt_reg_base[i], - j); - ret = regmap_write(map, reg, d->virt_buf[i][j]); - if (ret != 0) - dev_err(d->map->dev, - "Failed to write virt 0x%x: %d\n", - reg, ret); - } - } - } - for (i = 0; i < d->chip->num_config_bases; i++) { for (j = 0; j < d->chip->num_config_regs; j++) { reg = d->get_irq_reg(d, d->chip->config_base[i], j); @@ -320,13 +305,6 @@ static int regmap_irq_set_type(struct irq_data *data, unsigned int type) return -EINVAL; } - if (d->chip->set_type_virt) { - ret = d->chip->set_type_virt(d->virt_buf, type, data->hwirq, - reg); - if (ret) - return ret; - } - if (d->chip->set_type_config) { ret = d->chip->set_type_config(d->config_buf, type, irq_data, reg, d->chip->irq_drv_data); @@ -758,9 +736,6 @@ int regmap_add_irq_chip_fwnode(struct fwnode_handle *fwnode, if (chip->num_type_reg) dev_warn(map->dev, "type registers are deprecated; use config registers instead"); - if (chip->num_virt_regs || chip->virt_reg_base || chip->set_type_virt) - dev_warn(map->dev, "virtual registers are deprecated; use config registers instead"); - if (irq_base) { irq_base = irq_alloc_descs(irq_base, 0, chip->num_irqs, 0); if (irq_base < 0) { @@ -824,24 +799,6 @@ int regmap_add_irq_chip_fwnode(struct fwnode_handle *fwnode, goto err_alloc; } - if (chip->num_virt_regs) { - /* - * Create virt_buf[chip->num_extra_config_regs][chip->num_regs] - */ - d->virt_buf = kcalloc(chip->num_virt_regs, sizeof(*d->virt_buf), - GFP_KERNEL); - if (!d->virt_buf) - goto err_alloc; - - for (i = 0; i < chip->num_virt_regs; i++) { - d->virt_buf[i] = kcalloc(chip->num_regs, - sizeof(**d->virt_buf), - GFP_KERNEL); - if (!d->virt_buf[i]) - goto err_alloc; - } - } - if (chip->num_config_bases && chip->num_config_regs) { /* * Create config_buf[num_config_bases][num_config_regs] @@ -1063,11 +1020,6 @@ err_alloc: kfree(d->mask_buf); kfree(d->status_buf); kfree(d->status_reg_buf); - if (d->virt_buf) { - for (i = 0; i < chip->num_virt_regs; i++) - kfree(d->virt_buf[i]); - kfree(d->virt_buf); - } if (d->config_buf) { for (i = 0; i < chip->num_config_bases; i++) kfree(d->config_buf[i]); diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 253f99fb282f..2ad0e3d77b95 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -1544,8 +1544,6 @@ struct regmap_irq_chip_data; * @wake_base: Base address for wake enables. If zero unsupported. * @type_base: Base address for irq type. If zero unsupported. Deprecated, * use @config_base instead. - * @virt_reg_base: Base addresses for extra config regs. Deprecated, use - * @config_base instead. * @config_base: Base address for IRQ type config regs. If null unsupported. * @irq_reg_stride: Stride to use for chips where registers are not contiguous. * @init_ack_masked: Ack all masked interrupts once during initalization. @@ -1586,9 +1584,6 @@ struct regmap_irq_chip_data; * * @num_type_reg: Number of type registers. Deprecated, use config registers * instead. - * @num_virt_regs: Number of non-standard irq configuration registers. - * If zero unsupported. Deprecated, use config registers - * instead. * @num_config_bases: Number of config base registers. * @num_config_regs: Number of config registers for each config base register. * @@ -1598,9 +1593,6 @@ struct regmap_irq_chip_data; * after handling the interrupts in regmap_irq_handler(). * @handle_mask_sync: Callback used to handle IRQ mask syncs. The index will be * in the range [0, num_regs) - * @set_type_virt: Driver specific callback to extend regmap_irq_set_type() - * and configure virt regs. Deprecated, use @set_type_config - * callback and config registers instead. * @set_type_config: Callback used for configuring irq types. * @get_irq_reg: Callback for mapping (base register, index) pairs to register * addresses. The base register will be one of @status_base, @@ -1630,7 +1622,6 @@ struct regmap_irq_chip { unsigned int ack_base; unsigned int wake_base; unsigned int type_base; - unsigned int *virt_reg_base; const unsigned int *config_base; unsigned int irq_reg_stride; unsigned int init_ack_masked:1; @@ -1652,7 +1643,6 @@ struct regmap_irq_chip { int num_irqs; int num_type_reg; - int num_virt_regs; int num_config_bases; int num_config_regs; @@ -1660,8 +1650,6 @@ struct regmap_irq_chip { int (*handle_post_irq)(void *irq_drv_data); int (*handle_mask_sync)(int index, unsigned int mask_buf_def, unsigned int mask_buf, void *irq_drv_data); - int (*set_type_virt)(unsigned int **buf, unsigned int type, - unsigned long hwirq, int reg); int (*set_type_config)(unsigned int **buf, unsigned int type, const struct regmap_irq *irq_data, int idx, void *irq_drv_data); -- cgit v1.2.3 From 7a3cc29136960c45eff362a7304dd4f6eaf34cdd Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 20 Mar 2023 18:37:51 +0100 Subject: rcu: Remove RCU_NONIDLE() Since there are now exactly _zero_ users of RCU_NONIDLE(), make it go away before someone else decides to (ab)use it. [ paulmck: Remove extraneous whitespace. ] Signed-off-by: Peter Zijlstra (Intel) Acked-by: Mark Rutland Acked-by: Frederic Weisbecker Signed-off-by: Paul E. McKenney --- .../RCU/Design/Requirements/Requirements.rst | 36 +--------------------- Documentation/RCU/whatisRCU.rst | 1 - include/linux/rcupdate.h | 25 --------------- 3 files changed, 1 insertion(+), 61 deletions(-) (limited to 'include/linux') diff --git a/Documentation/RCU/Design/Requirements/Requirements.rst b/Documentation/RCU/Design/Requirements/Requirements.rst index 49387d823619..f3b605285a87 100644 --- a/Documentation/RCU/Design/Requirements/Requirements.rst +++ b/Documentation/RCU/Design/Requirements/Requirements.rst @@ -2071,41 +2071,7 @@ call. Because RCU avoids interrupting idle CPUs, it is illegal to execute an RCU read-side critical section on an idle CPU. (Kernels built with -``CONFIG_PROVE_RCU=y`` will splat if you try it.) The RCU_NONIDLE() -macro and ``_rcuidle`` event tracing is provided to work around this -restriction. In addition, rcu_is_watching() may be used to test -whether or not it is currently legal to run RCU read-side critical -sections on this CPU. I learned of the need for diagnostics on the one -hand and RCU_NONIDLE() on the other while inspecting idle-loop code. -Steven Rostedt supplied ``_rcuidle`` event tracing, which is used quite -heavily in the idle loop. However, there are some restrictions on the -code placed within RCU_NONIDLE(): - -#. Blocking is prohibited. In practice, this is not a serious - restriction given that idle tasks are prohibited from blocking to - begin with. -#. Although nesting RCU_NONIDLE() is permitted, they cannot nest - indefinitely deeply. However, given that they can be nested on the - order of a million deep, even on 32-bit systems, this should not be a - serious restriction. This nesting limit would probably be reached - long after the compiler OOMed or the stack overflowed. -#. Any code path that enters RCU_NONIDLE() must sequence out of that - same RCU_NONIDLE(). For example, the following is grossly - illegal: - - :: - - 1 RCU_NONIDLE({ - 2 do_something(); - 3 goto bad_idea; /* BUG!!! */ - 4 do_something_else();}); - 5 bad_idea: - - - It is just as illegal to transfer control into the middle of - RCU_NONIDLE()'s argument. Yes, in theory, you could transfer in - as long as you also transferred out, but in practice you could also - expect to get sharply worded review comments. +``CONFIG_PROVE_RCU=y`` will splat if you try it.) It is similarly socially unacceptable to interrupt an ``nohz_full`` CPU running in userspace. RCU must therefore track ``nohz_full`` userspace diff --git a/Documentation/RCU/whatisRCU.rst b/Documentation/RCU/whatisRCU.rst index 8eddef28d3a1..e488c8e557a9 100644 --- a/Documentation/RCU/whatisRCU.rst +++ b/Documentation/RCU/whatisRCU.rst @@ -1117,7 +1117,6 @@ All: lockdep-checked RCU utility APIs:: RCU_LOCKDEP_WARN rcu_sleep_check - RCU_NONIDLE All: Unchecked RCU-protected pointer access:: diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index dcd2cf1e8326..aae31a3e28dd 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -156,31 +156,6 @@ static inline int rcu_nocb_cpu_deoffload(int cpu) { return 0; } static inline void rcu_nocb_flush_deferred_wakeup(void) { } #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ -/** - * RCU_NONIDLE - Indicate idle-loop code that needs RCU readers - * @a: Code that RCU needs to pay attention to. - * - * RCU read-side critical sections are forbidden in the inner idle loop, - * that is, between the ct_idle_enter() and the ct_idle_exit() -- RCU - * will happily ignore any such read-side critical sections. However, - * things like powertop need tracepoints in the inner idle loop. - * - * This macro provides the way out: RCU_NONIDLE(do_something_with_RCU()) - * will tell RCU that it needs to pay attention, invoke its argument - * (in this example, calling the do_something_with_RCU() function), - * and then tell RCU to go back to ignoring this CPU. It is permissible - * to nest RCU_NONIDLE() wrappers, but not indefinitely (but the limit is - * on the order of a million or so, even on 32-bit systems). It is - * not legal to block within RCU_NONIDLE(), nor is it permissible to - * transfer control either into or out of RCU_NONIDLE()'s statement. - */ -#define RCU_NONIDLE(a) \ - do { \ - ct_irq_enter_irqson(); \ - do { a; } while (0); \ - ct_irq_exit_irqson(); \ - } while (0) - /* * Note a quasi-voluntary context switch for RCU-tasks's benefit. * This is a macro rather than an inline function to avoid #include hell. -- cgit v1.2.3 From f05cbadce7e409b38acdf21f0a05d4420afa1b11 Mon Sep 17 00:00:00 2001 From: Aidan MacDonald Date: Thu, 11 May 2023 10:13:39 +0100 Subject: regmap-irq: Remove type registers No remaining users, these have been replaced by config registers. Signed-off-by: Aidan MacDonald chip->type_in_mask) { - for (i = 0; i < d->chip->num_type_reg; i++) { - if (!d->type_buf_def[i]) - continue; - reg = d->get_irq_reg(d, d->chip->type_base, i); - ret = regmap_update_bits(d->map, reg, - d->type_buf_def[i], d->type_buf[i]); - if (ret != 0) - dev_err(d->map->dev, "Failed to sync type in %x\n", - reg); - } - } - for (i = 0; i < d->chip->num_config_bases; i++) { for (j = 0; j < d->chip->num_config_regs; j++) { reg = d->get_irq_reg(d, d->chip->config_base[i], j); @@ -273,36 +259,11 @@ static int regmap_irq_set_type(struct irq_data *data, unsigned int type) reg = t->type_reg_offset / map->reg_stride; - if (t->type_reg_mask) - d->type_buf[reg] &= ~t->type_reg_mask; - else - d->type_buf[reg] &= ~(t->type_falling_val | - t->type_rising_val | - t->type_level_low_val | - t->type_level_high_val); - switch (type) { - case IRQ_TYPE_EDGE_FALLING: - d->type_buf[reg] |= t->type_falling_val; - break; - - case IRQ_TYPE_EDGE_RISING: - d->type_buf[reg] |= t->type_rising_val; - break; - - case IRQ_TYPE_EDGE_BOTH: - d->type_buf[reg] |= (t->type_falling_val | - t->type_rising_val); - break; - - case IRQ_TYPE_LEVEL_HIGH: - d->type_buf[reg] |= t->type_level_high_val; - break; - - case IRQ_TYPE_LEVEL_LOW: - d->type_buf[reg] |= t->type_level_low_val; - break; - default: - return -EINVAL; + if (d->chip->type_in_mask) { + ret = regmap_irq_set_type_config_simple(&d->type_buf, type, + irq_data, reg, d->chip->irq_drv_data); + if (ret) + return ret; } if (d->chip->set_type_config) { @@ -707,8 +668,6 @@ int regmap_add_irq_chip_fwnode(struct fwnode_handle *fwnode, struct regmap_irq_chip_data *d; int i; int ret = -ENOMEM; - int num_type_reg; - int num_regs; u32 reg; if (chip->num_regs <= 0) @@ -733,9 +692,6 @@ int regmap_add_irq_chip_fwnode(struct fwnode_handle *fwnode, return -EINVAL; } - if (chip->num_type_reg) - dev_warn(map->dev, "type registers are deprecated; use config registers instead"); - if (irq_base) { irq_base = irq_alloc_descs(irq_base, 0, chip->num_irqs, 0); if (irq_base < 0) { @@ -780,21 +736,13 @@ int regmap_add_irq_chip_fwnode(struct fwnode_handle *fwnode, goto err_alloc; } - /* - * Use num_config_regs if defined, otherwise fall back to num_type_reg - * to maintain backward compatibility. - */ - num_type_reg = chip->num_config_regs ? chip->num_config_regs - : chip->num_type_reg; - num_regs = chip->type_in_mask ? chip->num_regs : num_type_reg; - if (num_regs) { - d->type_buf_def = kcalloc(num_regs, + if (chip->type_in_mask) { + d->type_buf_def = kcalloc(chip->num_regs, sizeof(*d->type_buf_def), GFP_KERNEL); if (!d->type_buf_def) goto err_alloc; - d->type_buf = kcalloc(num_regs, sizeof(*d->type_buf), - GFP_KERNEL); + d->type_buf = kcalloc(chip->num_regs, sizeof(*d->type_buf), GFP_KERNEL); if (!d->type_buf) goto err_alloc; } @@ -970,20 +918,6 @@ int regmap_add_irq_chip_fwnode(struct fwnode_handle *fwnode, } } - if (chip->num_type_reg && !chip->type_in_mask) { - for (i = 0; i < chip->num_type_reg; ++i) { - reg = d->get_irq_reg(d, d->chip->type_base, i); - - ret = regmap_read(map, reg, &d->type_buf_def[i]); - - if (ret) { - dev_err(map->dev, "Failed to get type defaults at 0x%x: %d\n", - reg, ret); - goto err_alloc; - } - } - } - if (irq_base) d->domain = irq_domain_create_legacy(fwnode, chip->num_irqs, irq_base, 0, diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 2ad0e3d77b95..0b4b9eca480d 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -1542,8 +1542,6 @@ struct regmap_irq_chip_data; * @ack_base: Base ack address. If zero then the chip is clear on read. * Using zero value is possible with @use_ack bit. * @wake_base: Base address for wake enables. If zero unsupported. - * @type_base: Base address for irq type. If zero unsupported. Deprecated, - * use @config_base instead. * @config_base: Base address for IRQ type config regs. If null unsupported. * @irq_reg_stride: Stride to use for chips where registers are not contiguous. * @init_ack_masked: Ack all masked interrupts once during initalization. @@ -1581,9 +1579,6 @@ struct regmap_irq_chip_data; * @irqs: Descriptors for individual IRQs. Interrupt numbers are * assigned based on the index in the array of the interrupt. * @num_irqs: Number of descriptors. - * - * @num_type_reg: Number of type registers. Deprecated, use config registers - * instead. * @num_config_bases: Number of config base registers. * @num_config_regs: Number of config registers for each config base register. * @@ -1621,7 +1616,6 @@ struct regmap_irq_chip { unsigned int unmask_base; unsigned int ack_base; unsigned int wake_base; - unsigned int type_base; const unsigned int *config_base; unsigned int irq_reg_stride; unsigned int init_ack_masked:1; @@ -1642,7 +1636,6 @@ struct regmap_irq_chip { const struct regmap_irq *irqs; int num_irqs; - int num_type_reg; int num_config_bases; int num_config_regs; -- cgit v1.2.3 From 72cc0f523babca3886421721aa662c7d352a6d32 Mon Sep 17 00:00:00 2001 From: Aidan MacDonald Date: Thu, 11 May 2023 10:13:40 +0100 Subject: regmap-irq: Remove support for not_fixed_stride No remaining users, use a custom .get_irq_reg() callback instead. Signed-off-by: Aidan MacDonald offset[i]; unsigned int index = offset / map->reg_stride; - if (chip->not_fixed_stride) - ret = regmap_read(map, - chip->status_base + offset, - &data->status_buf[b]); - else - ret = regmap_read(map, - chip->status_base + offset, - &data->status_buf[index]); - + ret = regmap_read(map, chip->status_base + offset, + &data->status_buf[index]); if (ret) break; } @@ -391,17 +384,7 @@ static irqreturn_t regmap_irq_thread(int irq, void *d) * sake of simplicity. and add bulk reads only if needed */ for (i = 0; i < chip->num_main_regs; i++) { - /* - * For not_fixed_stride, don't use ->get_irq_reg(). - * It would produce an incorrect result. - */ - if (data->chip->not_fixed_stride) - reg = chip->main_status + - i * map->reg_stride * data->irq_reg_stride; - else - reg = data->get_irq_reg(data, - chip->main_status, i); - + reg = data->get_irq_reg(data, chip->main_status, i); ret = regmap_read(map, reg, &data->main_status_buf[i]); if (ret) { dev_err(map->dev, @@ -567,20 +550,8 @@ static const struct irq_domain_ops regmap_domain_ops = { unsigned int regmap_irq_get_irq_reg_linear(struct regmap_irq_chip_data *data, unsigned int base, int index) { - const struct regmap_irq_chip *chip = data->chip; struct regmap *map = data->map; - /* - * FIXME: This is for backward compatibility and should be removed - * when not_fixed_stride is dropped (it's only used by qcom-pm8008). - */ - if (chip->not_fixed_stride && chip->sub_reg_offsets) { - struct regmap_irq_sub_irq_map *subreg; - - subreg = &chip->sub_reg_offsets[0]; - return base + subreg->offset[0]; - } - return base + index * map->reg_stride * data->irq_reg_stride; } EXPORT_SYMBOL_GPL(regmap_irq_get_irq_reg_linear); @@ -684,14 +655,6 @@ int regmap_add_irq_chip_fwnode(struct fwnode_handle *fwnode, return -EINVAL; } - if (chip->not_fixed_stride) { - dev_warn(map->dev, "not_fixed_stride is deprecated; use ->get_irq_reg() instead"); - - for (i = 0; i < chip->num_regs; i++) - if (chip->sub_reg_offsets[i].num_regs != 1) - return -EINVAL; - } - if (irq_base) { irq_base = irq_alloc_descs(irq_base, 0, chip->num_irqs, 0); if (irq_base < 0) { diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 0b4b9eca480d..8fc0b3ebce44 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -1528,9 +1528,6 @@ struct regmap_irq_chip_data; * status_base. Should contain num_regs arrays. * Can be provided for chips with more complex mapping than * 1.st bit to 1.st sub-reg, 2.nd bit to 2.nd sub-reg, ... - * When used with not_fixed_stride, each one-element array - * member contains offset calculated as address from each - * peripheral to first peripheral. * @num_main_regs: Number of 'main status' irq registers for chips which have * main_status set. * @@ -1567,11 +1564,6 @@ struct regmap_irq_chip_data; * registers before unmasking interrupts to clear any bits * set when they were masked. * @runtime_pm: Hold a runtime PM lock on the device when accessing it. - * @not_fixed_stride: Used when chip peripherals are not laid out with fixed - * stride. Must be used with sub_reg_offsets containing the - * offsets to each peripheral. Deprecated; the same thing - * can be accomplished with a @get_irq_reg callback, without - * the need for a @sub_reg_offsets table. * @no_status: No status register: all interrupts assumed generated by device. * * @num_regs: Number of registers in each control bank. @@ -1628,7 +1620,6 @@ struct regmap_irq_chip { unsigned int type_in_mask:1; unsigned int clear_on_unmask:1; unsigned int runtime_pm:1; - unsigned int not_fixed_stride:1; unsigned int no_status:1; int num_regs; -- cgit v1.2.3 From 1f7d5520719dd1fed1a2947679f6cc26a55f1e6b Mon Sep 17 00:00:00 2001 From: Basavaraj Natikar Date: Fri, 28 Apr 2023 19:30:55 +0530 Subject: USB: Extend pci resume function to handle PM events Currently, the pci_resume method has only a flag indicating whether the system is resuming from hibernation. In order to handle all PM events like AUTO_RESUME (runtime resume from device in D3), RESUME (system resume from s2idle, S3 or S4 states) etc change the pci_resume method to handle all PM events. Signed-off-by: Basavaraj Natikar Acked-by: Alan Stern Acked-by: Mathias Nyman Link: https://lore.kernel.org/r/20230428140056.1318981-2-Basavaraj.Natikar@amd.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/hcd-pci.c | 24 +++++++++++++----------- drivers/usb/host/ehci-pci.c | 3 ++- drivers/usb/host/ohci-pci.c | 8 +++++++- drivers/usb/host/uhci-pci.c | 7 ++++--- drivers/usb/host/xhci-histb.c | 2 +- drivers/usb/host/xhci-pci.c | 4 ++-- drivers/usb/host/xhci-plat.c | 4 ++-- drivers/usb/host/xhci-tegra.c | 2 +- drivers/usb/host/xhci.c | 3 ++- drivers/usb/host/xhci.h | 2 +- include/linux/usb/hcd.h | 2 +- 11 files changed, 36 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/core/hcd-pci.c b/drivers/usb/core/hcd-pci.c index ab2f3737764e..990280688b25 100644 --- a/drivers/usb/core/hcd-pci.c +++ b/drivers/usb/core/hcd-pci.c @@ -415,12 +415,15 @@ static int check_root_hub_suspended(struct device *dev) return 0; } -static int suspend_common(struct device *dev, bool do_wakeup) +static int suspend_common(struct device *dev, pm_message_t msg) { struct pci_dev *pci_dev = to_pci_dev(dev); struct usb_hcd *hcd = pci_get_drvdata(pci_dev); + bool do_wakeup; int retval; + do_wakeup = PMSG_IS_AUTO(msg) ? true : device_may_wakeup(dev); + /* Root hub suspend should have stopped all downstream traffic, * and all bus master traffic. And done so for both the interface * and the stub usb_device (which we check here). But maybe it @@ -447,7 +450,7 @@ static int suspend_common(struct device *dev, bool do_wakeup) (retval == 0 && do_wakeup && hcd->shared_hcd && HCD_WAKEUP_PENDING(hcd->shared_hcd))) { if (hcd->driver->pci_resume) - hcd->driver->pci_resume(hcd, false); + hcd->driver->pci_resume(hcd, msg); retval = -EBUSY; } if (retval) @@ -470,7 +473,7 @@ static int suspend_common(struct device *dev, bool do_wakeup) return retval; } -static int resume_common(struct device *dev, int event) +static int resume_common(struct device *dev, pm_message_t msg) { struct pci_dev *pci_dev = to_pci_dev(dev); struct usb_hcd *hcd = pci_get_drvdata(pci_dev); @@ -498,12 +501,11 @@ static int resume_common(struct device *dev, int event) * No locking is needed because PCI controller drivers do not * get unbound during system resume. */ - if (pci_dev->class == CL_EHCI && event != PM_EVENT_AUTO_RESUME) + if (pci_dev->class == CL_EHCI && msg.event != PM_EVENT_AUTO_RESUME) for_each_companion(pci_dev, hcd, ehci_wait_for_companions); - retval = hcd->driver->pci_resume(hcd, - event == PM_EVENT_RESTORE); + retval = hcd->driver->pci_resume(hcd, msg); if (retval) { dev_err(dev, "PCI post-resume error %d!\n", retval); usb_hc_died(hcd); @@ -516,7 +518,7 @@ static int resume_common(struct device *dev, int event) static int hcd_pci_suspend(struct device *dev) { - return suspend_common(dev, device_may_wakeup(dev)); + return suspend_common(dev, PMSG_SUSPEND); } static int hcd_pci_suspend_noirq(struct device *dev) @@ -577,12 +579,12 @@ static int hcd_pci_resume_noirq(struct device *dev) static int hcd_pci_resume(struct device *dev) { - return resume_common(dev, PM_EVENT_RESUME); + return resume_common(dev, PMSG_RESUME); } static int hcd_pci_restore(struct device *dev) { - return resume_common(dev, PM_EVENT_RESTORE); + return resume_common(dev, PMSG_RESTORE); } #else @@ -600,7 +602,7 @@ static int hcd_pci_runtime_suspend(struct device *dev) { int retval; - retval = suspend_common(dev, true); + retval = suspend_common(dev, PMSG_AUTO_SUSPEND); if (retval == 0) powermac_set_asic(to_pci_dev(dev), 0); dev_dbg(dev, "hcd_pci_runtime_suspend: %d\n", retval); @@ -612,7 +614,7 @@ static int hcd_pci_runtime_resume(struct device *dev) int retval; powermac_set_asic(to_pci_dev(dev), 1); - retval = resume_common(dev, PM_EVENT_AUTO_RESUME); + retval = resume_common(dev, PMSG_AUTO_RESUME); dev_dbg(dev, "hcd_pci_runtime_resume: %d\n", retval); return retval; } diff --git a/drivers/usb/host/ehci-pci.c b/drivers/usb/host/ehci-pci.c index 4b148fe5e43b..889dc4426271 100644 --- a/drivers/usb/host/ehci-pci.c +++ b/drivers/usb/host/ehci-pci.c @@ -354,10 +354,11 @@ done: * Also they depend on separate root hub suspend/resume. */ -static int ehci_pci_resume(struct usb_hcd *hcd, bool hibernated) +static int ehci_pci_resume(struct usb_hcd *hcd, pm_message_t msg) { struct ehci_hcd *ehci = hcd_to_ehci(hcd); struct pci_dev *pdev = to_pci_dev(hcd->self.controller); + bool hibernated = (msg.event == PM_EVENT_RESTORE); if (ehci_resume(hcd, hibernated) != 0) (void) ehci_pci_reinit(ehci, pdev); diff --git a/drivers/usb/host/ohci-pci.c b/drivers/usb/host/ohci-pci.c index d7b4f40f9ff4..900ea0d368e0 100644 --- a/drivers/usb/host/ohci-pci.c +++ b/drivers/usb/host/ohci-pci.c @@ -301,6 +301,12 @@ static struct pci_driver ohci_pci_driver = { #endif }; +#ifdef CONFIG_PM +static int ohci_pci_resume(struct usb_hcd *hcd, pm_message_t msg) +{ + return ohci_resume(hcd, msg.event == PM_EVENT_RESTORE); +} +#endif static int __init ohci_pci_init(void) { if (usb_disabled()) @@ -311,7 +317,7 @@ static int __init ohci_pci_init(void) #ifdef CONFIG_PM /* Entries for the PCI suspend/resume callbacks are special */ ohci_pci_hc_driver.pci_suspend = ohci_suspend; - ohci_pci_hc_driver.pci_resume = ohci_resume; + ohci_pci_hc_driver.pci_resume = ohci_pci_resume; #endif return pci_register_driver(&ohci_pci_driver); diff --git a/drivers/usb/host/uhci-pci.c b/drivers/usb/host/uhci-pci.c index 3592f757fe05..5df4a1832b09 100644 --- a/drivers/usb/host/uhci-pci.c +++ b/drivers/usb/host/uhci-pci.c @@ -167,7 +167,7 @@ static void uhci_shutdown(struct pci_dev *pdev) #ifdef CONFIG_PM -static int uhci_pci_resume(struct usb_hcd *hcd, bool hibernated); +static int uhci_pci_resume(struct usb_hcd *hcd, pm_message_t state); static int uhci_pci_suspend(struct usb_hcd *hcd, bool do_wakeup) { @@ -202,14 +202,15 @@ done_okay: /* Check for race with a wakeup request */ if (do_wakeup && HCD_WAKEUP_PENDING(hcd)) { - uhci_pci_resume(hcd, false); + uhci_pci_resume(hcd, PMSG_SUSPEND); rc = -EBUSY; } return rc; } -static int uhci_pci_resume(struct usb_hcd *hcd, bool hibernated) +static int uhci_pci_resume(struct usb_hcd *hcd, pm_message_t msg) { + bool hibernated = (msg.event == PM_EVENT_RESTORE); struct uhci_hcd *uhci = hcd_to_uhci(hcd); dev_dbg(uhci_dev(uhci), "%s\n", __func__); diff --git a/drivers/usb/host/xhci-histb.c b/drivers/usb/host/xhci-histb.c index 08369857686e..91ce97821de5 100644 --- a/drivers/usb/host/xhci-histb.c +++ b/drivers/usb/host/xhci-histb.c @@ -367,7 +367,7 @@ static int __maybe_unused xhci_histb_resume(struct device *dev) if (!device_may_wakeup(dev)) xhci_histb_host_enable(histb); - return xhci_resume(xhci, 0); + return xhci_resume(xhci, PMSG_RESUME); } static const struct dev_pm_ops xhci_histb_pm_ops = { diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index ddb79f23fb3b..e834c77e188e 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -824,7 +824,7 @@ static int xhci_pci_suspend(struct usb_hcd *hcd, bool do_wakeup) return ret; } -static int xhci_pci_resume(struct usb_hcd *hcd, bool hibernated) +static int xhci_pci_resume(struct usb_hcd *hcd, pm_message_t msg) { struct xhci_hcd *xhci = hcd_to_xhci(hcd); struct pci_dev *pdev = to_pci_dev(hcd->self.controller); @@ -859,7 +859,7 @@ static int xhci_pci_resume(struct usb_hcd *hcd, bool hibernated) if (xhci->quirks & XHCI_PME_STUCK_QUIRK) xhci_pme_quirk(hcd); - retval = xhci_resume(xhci, hibernated); + retval = xhci_resume(xhci, msg); return retval; } diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index b0c8e8efc43b..f36633fa8362 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -478,7 +478,7 @@ static int __maybe_unused xhci_plat_resume(struct device *dev) if (ret) return ret; - ret = xhci_resume(xhci, 0); + ret = xhci_resume(xhci, PMSG_RESUME); if (ret) return ret; @@ -507,7 +507,7 @@ static int __maybe_unused xhci_plat_runtime_resume(struct device *dev) struct usb_hcd *hcd = dev_get_drvdata(dev); struct xhci_hcd *xhci = hcd_to_xhci(hcd); - return xhci_resume(xhci, 0); + return xhci_resume(xhci, PMSG_AUTO_RESUME); } const struct dev_pm_ops xhci_plat_pm_ops = { diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c index c75d93244143..8a9c7deb7686 100644 --- a/drivers/usb/host/xhci-tegra.c +++ b/drivers/usb/host/xhci-tegra.c @@ -2272,7 +2272,7 @@ static int tegra_xusb_exit_elpg(struct tegra_xusb *tegra, bool runtime) if (wakeup) tegra_xhci_disable_phy_sleepwalk(tegra); - err = xhci_resume(xhci, 0); + err = xhci_resume(xhci, runtime ? PMSG_AUTO_RESUME : PMSG_RESUME); if (err < 0) { dev_err(tegra->dev, "failed to resume XHCI: %d\n", err); goto disable_phy; diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 78790dc13c5f..65d54c8a2492 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -960,8 +960,9 @@ EXPORT_SYMBOL_GPL(xhci_suspend); * This is called when the machine transition from S3/S4 mode. * */ -int xhci_resume(struct xhci_hcd *xhci, bool hibernated) +int xhci_resume(struct xhci_hcd *xhci, pm_message_t msg) { + bool hibernated = (msg.event == PM_EVENT_RESTORE); u32 command, temp = 0; struct usb_hcd *hcd = xhci_to_hcd(xhci); int retval = 0; diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 08d721921b7b..047b290404b4 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -2140,7 +2140,7 @@ int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id); int xhci_ext_cap_init(struct xhci_hcd *xhci); int xhci_suspend(struct xhci_hcd *xhci, bool do_wakeup); -int xhci_resume(struct xhci_hcd *xhci, bool hibernated); +int xhci_resume(struct xhci_hcd *xhci, pm_message_t msg); irqreturn_t xhci_irq(struct usb_hcd *hcd); irqreturn_t xhci_msi_irq(int irq, void *hcd); diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 094c77eaf455..30ab8994f0c1 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -267,7 +267,7 @@ struct hc_driver { int (*pci_suspend)(struct usb_hcd *hcd, bool do_wakeup); /* called after entering D0 (etc), before resuming the hub */ - int (*pci_resume)(struct usb_hcd *hcd, bool hibernated); + int (*pci_resume)(struct usb_hcd *hcd, pm_message_t state); /* called just before hibernate final D3 state, allows host to poweroff parts */ int (*pci_poweroff_late)(struct usb_hcd *hcd, bool do_wakeup); -- cgit v1.2.3 From b245aa0cc583c3efa0335c50f309a32e5fec8ab7 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Thu, 11 May 2023 15:10:24 +0300 Subject: serial: 8250: Change dl_read/write to handle value as u32 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Divisor latch read/write functions currently handle the value is int. As the value is related to HW context, u32 makes much more sense than a signed type. While at it, name the parameters in the callback signature. Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230511121029.13128-2-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250.h | 4 ++-- drivers/tty/serial/8250/8250_em.c | 4 ++-- drivers/tty/serial/8250/8250_port.c | 10 +++++----- drivers/tty/serial/8250/8250_pxa.c | 2 +- drivers/tty/serial/8250/8250_uniphier.c | 4 ++-- include/linux/serial_8250.h | 4 ++-- 6 files changed, 14 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/serial/8250/8250.h b/drivers/tty/serial/8250/8250.h index 1e8fe44a7099..5418708f4631 100644 --- a/drivers/tty/serial/8250/8250.h +++ b/drivers/tty/serial/8250/8250.h @@ -167,12 +167,12 @@ static unsigned int __maybe_unused serial_icr_read(struct uart_8250_port *up, void serial8250_clear_and_reinit_fifos(struct uart_8250_port *p); -static inline int serial_dl_read(struct uart_8250_port *up) +static inline u32 serial_dl_read(struct uart_8250_port *up) { return up->dl_read(up); } -static inline void serial_dl_write(struct uart_8250_port *up, int value) +static inline void serial_dl_write(struct uart_8250_port *up, u32 value) { up->dl_write(up, value); } diff --git a/drivers/tty/serial/8250/8250_em.c b/drivers/tty/serial/8250/8250_em.c index 25a9ecf26be6..ef5019e944ea 100644 --- a/drivers/tty/serial/8250/8250_em.c +++ b/drivers/tty/serial/8250/8250_em.c @@ -139,12 +139,12 @@ static void serial8250_em_serial_out(struct uart_port *p, int offset, int value) } } -static int serial8250_em_serial_dl_read(struct uart_8250_port *up) +static u32 serial8250_em_serial_dl_read(struct uart_8250_port *up) { return serial_in(up, UART_DLL_EM) | serial_in(up, UART_DLM_EM) << 8; } -static void serial8250_em_serial_dl_write(struct uart_8250_port *up, int value) +static void serial8250_em_serial_dl_write(struct uart_8250_port *up, u32 value) { serial_out(up, UART_DLL_EM, value & 0xff); serial_out(up, UART_DLM_EM, value >> 8 & 0xff); diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index fe8d79c4ae95..344bd447639b 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -325,7 +325,7 @@ static const struct serial8250_config uart_config[] = { }; /* Uart divisor latch read */ -static int default_serial_dl_read(struct uart_8250_port *up) +static u32 default_serial_dl_read(struct uart_8250_port *up) { /* Assign these in pieces to truncate any bits above 7. */ unsigned char dll = serial_in(up, UART_DLL); @@ -335,7 +335,7 @@ static int default_serial_dl_read(struct uart_8250_port *up) } /* Uart divisor latch write */ -static void default_serial_dl_write(struct uart_8250_port *up, int value) +static void default_serial_dl_write(struct uart_8250_port *up, u32 value) { serial_out(up, UART_DLL, value & 0xff); serial_out(up, UART_DLM, value >> 8 & 0xff); @@ -389,12 +389,12 @@ void au_serial_out(struct uart_port *p, int offset, int value) } /* Au1x00 haven't got a standard divisor latch */ -static int au_serial_dl_read(struct uart_8250_port *up) +static u32 au_serial_dl_read(struct uart_8250_port *up) { return __raw_readl(up->port.membase + 0x28); } -static void au_serial_dl_write(struct uart_8250_port *up, int value) +static void au_serial_dl_write(struct uart_8250_port *up, u32 value) { __raw_writel(value, up->port.membase + 0x28); } @@ -847,7 +847,7 @@ static void disable_rsa(struct uart_8250_port *up) static int size_fifo(struct uart_8250_port *up) { unsigned char old_fcr, old_mcr, old_lcr; - unsigned short old_dl; + u32 old_dl; int count; old_lcr = serial_in(up, UART_LCR); diff --git a/drivers/tty/serial/8250/8250_pxa.c b/drivers/tty/serial/8250/8250_pxa.c index 795e55142d4c..28b341f602c6 100644 --- a/drivers/tty/serial/8250/8250_pxa.c +++ b/drivers/tty/serial/8250/8250_pxa.c @@ -60,7 +60,7 @@ static const struct of_device_id serial_pxa_dt_ids[] = { MODULE_DEVICE_TABLE(of, serial_pxa_dt_ids); /* Uart divisor latch write */ -static void serial_pxa_dl_write(struct uart_8250_port *up, int value) +static void serial_pxa_dl_write(struct uart_8250_port *up, u32 value) { unsigned int dll; diff --git a/drivers/tty/serial/8250/8250_uniphier.c b/drivers/tty/serial/8250/8250_uniphier.c index a2978abab0db..a405155264b1 100644 --- a/drivers/tty/serial/8250/8250_uniphier.c +++ b/drivers/tty/serial/8250/8250_uniphier.c @@ -145,12 +145,12 @@ static void uniphier_serial_out(struct uart_port *p, int offset, int value) * The divisor latch register exists at different address. * Override dl_read/write callbacks. */ -static int uniphier_serial_dl_read(struct uart_8250_port *up) +static u32 uniphier_serial_dl_read(struct uart_8250_port *up) { return readl(up->port.membase + UNIPHIER_UART_DLR); } -static void uniphier_serial_dl_write(struct uart_8250_port *up, int value) +static void uniphier_serial_dl_write(struct uart_8250_port *up, u32 value) { writel(value, up->port.membase + UNIPHIER_UART_DLR); } diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 6f78f302d272..7b5d558e4e0c 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -129,8 +129,8 @@ struct uart_8250_port { const struct uart_8250_ops *ops; /* 8250 specific callbacks */ - int (*dl_read)(struct uart_8250_port *); - void (*dl_write)(struct uart_8250_port *, int); + u32 (*dl_read)(struct uart_8250_port *up); + void (*dl_write)(struct uart_8250_port *up, u32 value); struct uart_8250_em485 *em485; void (*rs485_start_tx)(struct uart_8250_port *); -- cgit v1.2.3 From 98658ae8f3925d05c2d0c67749ff6cf47b9077a5 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Thu, 11 May 2023 15:10:25 +0300 Subject: serial: 8250: Document uart_8250_port's ->dl_read/write() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add documentation for the struct uart_8250_port divisor latch function pointers. Documentation is in kernel doc format but don't enable kernel doc yet as many other fields remain undocumented. Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230511121029.13128-3-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_8250.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 7b5d558e4e0c..d64e7bbe1f2f 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -90,8 +90,17 @@ struct uart_8250_em485 { * their own 8250 ports without registering their own * platform device. Using these will make your driver * dependent on the 8250 driver. + * + * @dl_read: ``u32 ()(struct uart_8250_port *port)`` + * + * UART divisor latch read. + * + * @dl_write: ``void ()(struct uart_8250_port *port, u32 value)`` + * + * Write @value into UART divisor latch. + * + * Locking: Caller holds port's lock. */ - struct uart_8250_port { struct uart_port port; struct timer_list timer; /* "no irq" timer */ -- cgit v1.2.3 From 30c61f53fdf23e8a396dca8378615b4900edff6f Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Thu, 11 May 2023 15:10:26 +0300 Subject: serial: 8250: Add dl_read/write, bugs and mapsize into plat_serial8250_port MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add mapsize, bugs, and divisor latch read/write functions (->dl_read/write()) into plat_serial8250_port to carry the setup necessary for RT288x/Au1xxx devices over to uart port. Document the added members with kerneldoc style but do not enable kerneldoc yet as there are many fields which remain undocumented. While at it, convert .bugs in struct uart_8250_port to u16 to match it with the type used in struct plat_serial8250_port. Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230511121029.13128-4-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_core.c | 4 ++++ include/linux/serial_8250.h | 21 ++++++++++++++++++++- 2 files changed, 24 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c index 560a3592ec05..4434c3256a92 100644 --- a/drivers/tty/serial/8250/8250_core.c +++ b/drivers/tty/serial/8250/8250_core.c @@ -850,12 +850,16 @@ static int serial8250_probe(struct platform_device *dev) uart.port.iotype = p->iotype; uart.port.flags = p->flags; uart.port.mapbase = p->mapbase; + uart.port.mapsize = p->mapsize; uart.port.hub6 = p->hub6; uart.port.has_sysrq = p->has_sysrq; uart.port.private_data = p->private_data; uart.port.type = p->type; + uart.bugs = p->bugs; uart.port.serial_in = p->serial_in; uart.port.serial_out = p->serial_out; + uart.dl_read = p->dl_read; + uart.dl_write = p->dl_write; uart.port.handle_irq = p->handle_irq; uart.port.handle_break = p->handle_break; uart.port.set_termios = p->set_termios; diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index d64e7bbe1f2f..42fc8f64f48e 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -11,13 +11,29 @@ #include #include +struct uart_8250_port; + /* * This is the platform device platform_data structure + * + * @mapsize: Port size for ioremap() + * @bugs: Port bugs + * + * @dl_read: ``u32 ()(struct uart_8250_port *up)`` + * + * UART divisor latch read. + * + * @dl_write: ``void ()(struct uart_8250_port *up, u32 value)`` + * + * Write @value into UART divisor latch. + * + * Locking: Caller holds port's lock. */ struct plat_serial8250_port { unsigned long iobase; /* io base address */ void __iomem *membase; /* ioremap cookie or NULL */ resource_size_t mapbase; /* resource base */ + resource_size_t mapsize; unsigned int uartclk; /* UART clock rate */ unsigned int irq; /* interrupt number */ unsigned long irqflags; /* request_irq flags */ @@ -28,8 +44,11 @@ struct plat_serial8250_port { unsigned char has_sysrq; /* supports magic SysRq */ unsigned int type; /* If UPF_FIXED_TYPE */ upf_t flags; /* UPF_* flags */ + u16 bugs; /* port bugs */ unsigned int (*serial_in)(struct uart_port *, int); void (*serial_out)(struct uart_port *, int, int); + u32 (*dl_read)(struct uart_8250_port *up); + void (*dl_write)(struct uart_8250_port *up, u32 value); void (*set_termios)(struct uart_port *, struct ktermios *new, const struct ktermios *old); @@ -106,7 +125,7 @@ struct uart_8250_port { struct timer_list timer; /* "no irq" timer */ struct list_head list; /* ports on this IRQ */ u32 capabilities; /* port capabilities */ - unsigned short bugs; /* port bugs */ + u16 bugs; /* port bugs */ bool fifo_bug; /* min RX trigger if enabled */ unsigned int tx_loadsz; /* transmit fifo load size */ unsigned char acr; -- cgit v1.2.3 From b334214ea08d941af376fec853621d856b12bc81 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Thu, 11 May 2023 15:10:27 +0300 Subject: serial: 8250: RT288x/Au1xxx code away from core MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A non-trivial amount of RT288x/Au1xxx code is encapsulated into ifdeffery in 8250_port / 8250_early and some if UPIO_AU blocks. Create a separate file from them. Also handle errors properly in the cases where RT288x/Au1xxx code is not configured. It seems that 0x1000 mapsize is likely overkill but I've kept it the same as previously (the value was shrunk to that value in commit b2b13cdfd05e ("SERIAL 8250: Fixes for Alchemy UARTs.")). Seemingly, the driver only needs to access register at 0x28 for the divisor latch. The Kconfig side is a bit tricky. As SERIAL_8250_RT288X is bool it can only be =y. It is possible to have SERIAL_8250=m + SERIAL_8250_RT288X=y which required altering when 8250/ is included or the rt288x would not be built. Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230511121029.13128-5-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- arch/mips/alchemy/common/platform.c | 10 ++- drivers/tty/serial/8250/8250_early.c | 21 ----- drivers/tty/serial/8250/8250_of.c | 4 +- drivers/tty/serial/8250/8250_port.c | 78 ------------------- drivers/tty/serial/8250/8250_rt288x.c | 142 ++++++++++++++++++++++++++++++++++ drivers/tty/serial/8250/Makefile | 1 + drivers/tty/serial/Makefile | 2 +- include/linux/serial_8250.h | 8 +- 8 files changed, 161 insertions(+), 105 deletions(-) create mode 100644 drivers/tty/serial/8250/8250_rt288x.c (limited to 'include/linux') diff --git a/arch/mips/alchemy/common/platform.c b/arch/mips/alchemy/common/platform.c index b8f3397c59c9..d4ab34b3b404 100644 --- a/arch/mips/alchemy/common/platform.c +++ b/arch/mips/alchemy/common/platform.c @@ -51,9 +51,9 @@ static void alchemy_8250_pm(struct uart_port *port, unsigned int state, #define PORT(_base, _irq) \ { \ .mapbase = _base, \ + .mapsize = 0x1000, \ .irq = _irq, \ .regshift = 2, \ - .iotype = UPIO_AU, \ .flags = UPF_SKIP_TEST | UPF_IOREMAP | \ UPF_FIXED_TYPE, \ .type = PORT_16550A, \ @@ -124,8 +124,14 @@ static void __init alchemy_setup_uarts(int ctype) au1xx0_uart_device.dev.platform_data = ports; /* Fill up uartclk. */ - for (s = 0; s < c; s++) + for (s = 0; s < c; s++) { ports[s].uartclk = uartclk; + if (au_platform_setup(&ports[s]) < 0) { + kfree(ports); + printk(KERN_INFO "Alchemy: missing support for UARTs\n"); + return; + } + } if (platform_device_register(&au1xx0_uart_device)) printk(KERN_INFO "Alchemy: failed to register UARTs\n"); } diff --git a/drivers/tty/serial/8250/8250_early.c b/drivers/tty/serial/8250/8250_early.c index 0ebde0ab8167..4299a8bd83d9 100644 --- a/drivers/tty/serial/8250/8250_early.c +++ b/drivers/tty/serial/8250/8250_early.c @@ -36,7 +36,6 @@ static unsigned int serial8250_early_in(struct uart_port *port, int offset) { - int reg_offset = offset; offset <<= port->regshift; switch (port->iotype) { @@ -50,8 +49,6 @@ static unsigned int serial8250_early_in(struct uart_port *port, int offset) return ioread32be(port->membase + offset); case UPIO_PORT: return inb(port->iobase + offset); - case UPIO_AU: - return port->serial_in(port, reg_offset); default: return 0; } @@ -59,7 +56,6 @@ static unsigned int serial8250_early_in(struct uart_port *port, int offset) static void serial8250_early_out(struct uart_port *port, int offset, int value) { - int reg_offset = offset; offset <<= port->regshift; switch (port->iotype) { @@ -78,9 +74,6 @@ static void serial8250_early_out(struct uart_port *port, int offset, int value) case UPIO_PORT: outb(value, port->iobase + offset); break; - case UPIO_AU: - port->serial_out(port, reg_offset, value); - break; } } @@ -199,17 +192,3 @@ OF_EARLYCON_DECLARE(omap8250, "ti,omap3-uart", early_omap8250_setup); OF_EARLYCON_DECLARE(omap8250, "ti,omap4-uart", early_omap8250_setup); #endif - -#ifdef CONFIG_SERIAL_8250_RT288X - -static int __init early_au_setup(struct earlycon_device *dev, const char *opt) -{ - dev->port.serial_in = au_serial_in; - dev->port.serial_out = au_serial_out; - dev->port.iotype = UPIO_AU; - dev->con->write = early_serial8250_write; - return 0; -} -OF_EARLYCON_DECLARE(palmchip, "ralink,rt2880-uart", early_au_setup); - -#endif diff --git a/drivers/tty/serial/8250/8250_of.c b/drivers/tty/serial/8250/8250_of.c index 1b461fba15a3..c9f6bd7a7038 100644 --- a/drivers/tty/serial/8250/8250_of.c +++ b/drivers/tty/serial/8250/8250_of.c @@ -171,7 +171,9 @@ static int of_platform_serial_setup(struct platform_device *ofdev, switch (type) { case PORT_RT2880: - port->iotype = UPIO_AU; + ret = rt288x_setup(port); + if (ret) + goto err_unprepare; break; } diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 344bd447639b..0cef9bfd0471 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -341,66 +341,6 @@ static void default_serial_dl_write(struct uart_8250_port *up, u32 value) serial_out(up, UART_DLM, value >> 8 & 0xff); } -#ifdef CONFIG_SERIAL_8250_RT288X - -#define UART_REG_UNMAPPED -1 - -/* Au1x00/RT288x UART hardware has a weird register layout */ -static const s8 au_io_in_map[8] = { - [UART_RX] = 0, - [UART_IER] = 2, - [UART_IIR] = 3, - [UART_LCR] = 5, - [UART_MCR] = 6, - [UART_LSR] = 7, - [UART_MSR] = 8, - [UART_SCR] = UART_REG_UNMAPPED, -}; - -static const s8 au_io_out_map[8] = { - [UART_TX] = 1, - [UART_IER] = 2, - [UART_FCR] = 4, - [UART_LCR] = 5, - [UART_MCR] = 6, - [UART_LSR] = UART_REG_UNMAPPED, - [UART_MSR] = UART_REG_UNMAPPED, - [UART_SCR] = UART_REG_UNMAPPED, -}; - -unsigned int au_serial_in(struct uart_port *p, int offset) -{ - if (offset >= ARRAY_SIZE(au_io_in_map)) - return UINT_MAX; - offset = au_io_in_map[offset]; - if (offset == UART_REG_UNMAPPED) - return UINT_MAX; - return __raw_readl(p->membase + (offset << p->regshift)); -} - -void au_serial_out(struct uart_port *p, int offset, int value) -{ - if (offset >= ARRAY_SIZE(au_io_out_map)) - return; - offset = au_io_out_map[offset]; - if (offset == UART_REG_UNMAPPED) - return; - __raw_writel(value, p->membase + (offset << p->regshift)); -} - -/* Au1x00 haven't got a standard divisor latch */ -static u32 au_serial_dl_read(struct uart_8250_port *up) -{ - return __raw_readl(up->port.membase + 0x28); -} - -static void au_serial_dl_write(struct uart_8250_port *up, u32 value) -{ - __raw_writel(value, up->port.membase + 0x28); -} - -#endif - static unsigned int hub6_serial_in(struct uart_port *p, int offset) { offset = offset << p->regshift; @@ -510,15 +450,6 @@ static void set_io_from_upio(struct uart_port *p) p->serial_out = mem32be_serial_out; break; -#ifdef CONFIG_SERIAL_8250_RT288X - case UPIO_AU: - p->serial_in = au_serial_in; - p->serial_out = au_serial_out; - up->dl_read = au_serial_dl_read; - up->dl_write = au_serial_dl_write; - break; -#endif - default: p->serial_in = io_serial_in; p->serial_out = io_serial_out; @@ -2968,11 +2899,6 @@ static unsigned int serial8250_port_size(struct uart_8250_port *pt) { if (pt->port.mapsize) return pt->port.mapsize; - if (pt->port.iotype == UPIO_AU) { - if (pt->port.type == PORT_RT2880) - return 0x100; - return 0x1000; - } if (is_omap1_8250(pt)) return 0x16 << pt->port.regshift; @@ -3222,10 +3148,6 @@ static void serial8250_config_port(struct uart_port *port, int flags) if (flags & UART_CONFIG_TYPE) autoconfig(up); - /* if access method is AU, it is a 16550 with a quirk */ - if (port->type == PORT_16550A && port->iotype == UPIO_AU) - up->bugs |= UART_BUG_NOMSR; - /* HW bugs may trigger IRQ while IIR == NO_INT */ if (port->type == PORT_TEGRA) up->bugs |= UART_BUG_NOMSR; diff --git a/drivers/tty/serial/8250/8250_rt288x.c b/drivers/tty/serial/8250/8250_rt288x.c new file mode 100644 index 000000000000..51b1cf5476dd --- /dev/null +++ b/drivers/tty/serial/8250/8250_rt288x.c @@ -0,0 +1,142 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * RT288x/Au1xxx driver + */ + +#include +#include +#include +#include +#include +#include + +#include "8250.h" + +#define UART_REG_UNMAPPED -1 + +/* Au1x00/RT288x UART hardware has a weird register layout */ +static const s8 au_io_in_map[8] = { + [UART_RX] = 0, + [UART_IER] = 2, + [UART_IIR] = 3, + [UART_LCR] = 5, + [UART_MCR] = 6, + [UART_LSR] = 7, + [UART_MSR] = 8, + [UART_SCR] = UART_REG_UNMAPPED, +}; + +static const s8 au_io_out_map[8] = { + [UART_TX] = 1, + [UART_IER] = 2, + [UART_FCR] = 4, + [UART_LCR] = 5, + [UART_MCR] = 6, + [UART_LSR] = UART_REG_UNMAPPED, + [UART_MSR] = UART_REG_UNMAPPED, + [UART_SCR] = UART_REG_UNMAPPED, +}; + +static unsigned int au_serial_in(struct uart_port *p, int offset) +{ + if (offset >= ARRAY_SIZE(au_io_in_map)) + return UINT_MAX; + offset = au_io_in_map[offset]; + if (offset == UART_REG_UNMAPPED) + return UINT_MAX; + return __raw_readl(p->membase + (offset << p->regshift)); +} + +static void au_serial_out(struct uart_port *p, int offset, int value) +{ + if (offset >= ARRAY_SIZE(au_io_out_map)) + return; + offset = au_io_out_map[offset]; + if (offset == UART_REG_UNMAPPED) + return; + __raw_writel(value, p->membase + (offset << p->regshift)); +} + +/* Au1x00 haven't got a standard divisor latch */ +static u32 au_serial_dl_read(struct uart_8250_port *up) +{ + return __raw_readl(up->port.membase + 0x28); +} + +static void au_serial_dl_write(struct uart_8250_port *up, u32 value) +{ + __raw_writel(value, up->port.membase + 0x28); +} + +int au_platform_setup(struct plat_serial8250_port *p) +{ + p->iotype = UPIO_AU; + + p->serial_in = au_serial_in; + p->serial_out = au_serial_out; + p->dl_read = au_serial_dl_read; + p->dl_write = au_serial_dl_write; + + p->mapsize = 0x1000; + + p->bugs |= UART_BUG_NOMSR; + + return 0; +} +EXPORT_SYMBOL_GPL(au_platform_setup); + +int rt288x_setup(struct uart_port *p) +{ + struct uart_8250_port *up = up_to_u8250p(p); + + p->iotype = UPIO_AU; + + p->serial_in = au_serial_in; + p->serial_out = au_serial_out; + up->dl_read = au_serial_dl_read; + up->dl_write = au_serial_dl_write; + + p->mapsize = 0x100; + + up->bugs |= UART_BUG_NOMSR; + + return 0; +} +EXPORT_SYMBOL_GPL(rt288x_setup); + +#ifdef CONFIG_SERIAL_8250_CONSOLE +static void au_putc(struct uart_port *port, unsigned char c) +{ + unsigned int status; + + au_serial_out(port, UART_TX, c); + + for (;;) { + status = au_serial_in(port, UART_LSR); + if (uart_lsr_tx_empty(status)) + break; + cpu_relax(); + } +} + +static void au_early_serial8250_write(struct console *console, + const char *s, unsigned int count) +{ + struct earlycon_device *device = console->data; + struct uart_port *port = &device->port; + + uart_console_write(port, s, count, au_putc); +} + +static int __init early_au_setup(struct earlycon_device *dev, const char *opt) +{ + rt288x_setup(&dev->port); + dev->con->write = au_early_serial8250_write; + + return 0; +} +OF_EARLYCON_DECLARE(palmchip, "ralink,rt2880-uart", early_au_setup); +#endif + +MODULE_DESCRIPTION("RT288x/Au1xxx UART driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/tty/serial/8250/Makefile b/drivers/tty/serial/8250/Makefile index 4fc2fc1f41b6..628b75be312e 100644 --- a/drivers/tty/serial/8250/Makefile +++ b/drivers/tty/serial/8250/Makefile @@ -35,6 +35,7 @@ obj-$(CONFIG_SERIAL_8250_DW) += 8250_dw.o obj-$(CONFIG_SERIAL_8250_EM) += 8250_em.o obj-$(CONFIG_SERIAL_8250_IOC3) += 8250_ioc3.o obj-$(CONFIG_SERIAL_8250_OMAP) += 8250_omap.o +obj-$(CONFIG_SERIAL_8250_RT288X) += 8250_rt288x.o obj-$(CONFIG_SERIAL_8250_LPC18XX) += 8250_lpc18xx.o obj-$(CONFIG_SERIAL_8250_MT6577) += 8250_mtk.o obj-$(CONFIG_SERIAL_8250_UNIPHIER) += 8250_uniphier.o diff --git a/drivers/tty/serial/Makefile b/drivers/tty/serial/Makefile index cd9afd9e3018..531ec3a19dae 100644 --- a/drivers/tty/serial/Makefile +++ b/drivers/tty/serial/Makefile @@ -21,7 +21,7 @@ obj-$(CONFIG_SERIAL_SUNSAB) += sunsab.o obj-$(CONFIG_SERIAL_21285) += 21285.o # Now bring in any enabled 8250/16450/16550 type drivers. -obj-$(CONFIG_SERIAL_8250) += 8250/ +obj-y += 8250/ obj-$(CONFIG_SERIAL_AMBA_PL010) += amba-pl010.o obj-$(CONFIG_SERIAL_AMBA_PL011) += amba-pl011.o diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 42fc8f64f48e..eb44420b39ec 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -7,6 +7,7 @@ #ifndef _LINUX_SERIAL_8250_H #define _LINUX_SERIAL_8250_H +#include #include #include #include @@ -211,8 +212,11 @@ void serial8250_set_isa_configurator(void (*v)(int port, struct uart_port *up, u32 *capabilities)); #ifdef CONFIG_SERIAL_8250_RT288X -unsigned int au_serial_in(struct uart_port *p, int offset); -void au_serial_out(struct uart_port *p, int offset, int value); +int rt288x_setup(struct uart_port *p); +int au_platform_setup(struct plat_serial8250_port *p); +#else +static inline int rt288x_setup(struct uart_port *p) { return -ENODEV; } +static inline int au_platform_setup(struct plat_serial8250_port *p) { return -ENODEV; } #endif #endif -- cgit v1.2.3 From d5b3d02d0b107345f2a6ecb5b06f98356f5c97ab Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Fri, 12 May 2023 19:38:10 +0200 Subject: serial: Make uart_remove_one_port() return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The return value is only ever used as a return value for remove callbacks of platform drivers. This return value is ignored by the driver core. (The only effect is an error message, but uart_remove_one_port() already emitted one in this case.) So the return value isn't used at all and uart_remove_one_port() can be changed to return void without any loss. Also this better matches the Linux device model as remove functions are not supposed to fail. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230512173810.131447-3-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/atmel_serial.c | 5 ++--- drivers/tty/serial/clps711x.c | 4 +++- drivers/tty/serial/cpm_uart/cpm_uart_core.c | 5 ++++- drivers/tty/serial/imx.c | 4 +++- drivers/tty/serial/lantiq.c | 4 +++- drivers/tty/serial/serial_core.c | 6 +----- drivers/tty/serial/st-asc.c | 4 +++- drivers/tty/serial/uartlite.c | 12 ++++-------- drivers/tty/serial/xilinx_uartps.c | 5 ++--- include/linux/serial_core.h | 2 +- 10 files changed, 26 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c index 9cd7479b03c0..6e9192f122aa 100644 --- a/drivers/tty/serial/atmel_serial.c +++ b/drivers/tty/serial/atmel_serial.c @@ -3006,14 +3006,13 @@ static int atmel_serial_remove(struct platform_device *pdev) { struct uart_port *port = platform_get_drvdata(pdev); struct atmel_uart_port *atmel_port = to_atmel_uart_port(port); - int ret = 0; tasklet_kill(&atmel_port->tasklet_rx); tasklet_kill(&atmel_port->tasklet_tx); device_init_wakeup(&pdev->dev, 0); - ret = uart_remove_one_port(&atmel_uart, port); + uart_remove_one_port(&atmel_uart, port); kfree(atmel_port->rx_ring.buf); @@ -3023,7 +3022,7 @@ static int atmel_serial_remove(struct platform_device *pdev) pdev->dev.of_node = NULL; - return ret; + return 0; } static SIMPLE_DEV_PM_OPS(atmel_serial_pm_ops, atmel_serial_suspend, diff --git a/drivers/tty/serial/clps711x.c b/drivers/tty/serial/clps711x.c index e190dce58f46..e49bc4019b50 100644 --- a/drivers/tty/serial/clps711x.c +++ b/drivers/tty/serial/clps711x.c @@ -514,7 +514,9 @@ static int uart_clps711x_remove(struct platform_device *pdev) { struct clps711x_port *s = platform_get_drvdata(pdev); - return uart_remove_one_port(&clps711x_uart, &s->port); + uart_remove_one_port(&clps711x_uart, &s->port); + + return 0; } static const struct of_device_id __maybe_unused clps711x_uart_dt_ids[] = { diff --git a/drivers/tty/serial/cpm_uart/cpm_uart_core.c b/drivers/tty/serial/cpm_uart/cpm_uart_core.c index 349e7da643f0..66afa9bea6bf 100644 --- a/drivers/tty/serial/cpm_uart/cpm_uart_core.c +++ b/drivers/tty/serial/cpm_uart/cpm_uart_core.c @@ -1431,7 +1431,10 @@ static int cpm_uart_probe(struct platform_device *ofdev) static int cpm_uart_remove(struct platform_device *ofdev) { struct uart_cpm_port *pinfo = platform_get_drvdata(ofdev); - return uart_remove_one_port(&cpm_reg, &pinfo->port); + + uart_remove_one_port(&cpm_reg, &pinfo->port); + + return 0; } static const struct of_device_id cpm_uart_match[] = { diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index c5e17569c3ad..b2bf3cb449f4 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -2467,7 +2467,9 @@ static int imx_uart_remove(struct platform_device *pdev) { struct imx_port *sport = platform_get_drvdata(pdev); - return uart_remove_one_port(&imx_uart_uart_driver, &sport->port); + uart_remove_one_port(&imx_uart_uart_driver, &sport->port); + + return 0; } static void imx_uart_restore_context(struct imx_port *sport) diff --git a/drivers/tty/serial/lantiq.c b/drivers/tty/serial/lantiq.c index a58e9277dfad..d413f97f7190 100644 --- a/drivers/tty/serial/lantiq.c +++ b/drivers/tty/serial/lantiq.c @@ -889,7 +889,9 @@ static int lqasc_remove(struct platform_device *pdev) { struct uart_port *port = platform_get_drvdata(pdev); - return uart_remove_one_port(&lqasc_reg, port); + uart_remove_one_port(&lqasc_reg, port); + + return 0; } static const struct ltq_soc_data soc_data_lantiq = { diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 54e82f476a2c..4b98d13555c0 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -3154,13 +3154,12 @@ EXPORT_SYMBOL(uart_add_one_port); * This unhooks (and hangs up) the specified port structure from the core * driver. No further calls will be made to the low-level code for this port. */ -int uart_remove_one_port(struct uart_driver *drv, struct uart_port *uport) +void uart_remove_one_port(struct uart_driver *drv, struct uart_port *uport) { struct uart_state *state = drv->state + uport->line; struct tty_port *port = &state->port; struct uart_port *uart_port; struct tty_struct *tty; - int ret = 0; mutex_lock(&port_mutex); @@ -3176,7 +3175,6 @@ int uart_remove_one_port(struct uart_driver *drv, struct uart_port *uport) if (!uart_port) { mutex_unlock(&port->mutex); - ret = -EINVAL; goto out; } uport->flags |= UPF_DEAD; @@ -3219,8 +3217,6 @@ int uart_remove_one_port(struct uart_driver *drv, struct uart_port *uport) mutex_unlock(&port->mutex); out: mutex_unlock(&port_mutex); - - return ret; } EXPORT_SYMBOL(uart_remove_one_port); diff --git a/drivers/tty/serial/st-asc.c b/drivers/tty/serial/st-asc.c index 5215e6910f68..dc2f2051435c 100644 --- a/drivers/tty/serial/st-asc.c +++ b/drivers/tty/serial/st-asc.c @@ -796,7 +796,9 @@ static int asc_serial_remove(struct platform_device *pdev) { struct uart_port *port = platform_get_drvdata(pdev); - return uart_remove_one_port(&asc_uart_driver, port); + uart_remove_one_port(&asc_uart_driver, port); + + return 0; } #ifdef CONFIG_PM_SLEEP diff --git a/drivers/tty/serial/uartlite.c b/drivers/tty/serial/uartlite.c index 94584e54ebbe..679574893ebe 100644 --- a/drivers/tty/serial/uartlite.c +++ b/drivers/tty/serial/uartlite.c @@ -685,18 +685,15 @@ static int ulite_assign(struct device *dev, int id, phys_addr_t base, int irq, * * @dev: pointer to device structure */ -static int ulite_release(struct device *dev) +static void ulite_release(struct device *dev) { struct uart_port *port = dev_get_drvdata(dev); - int rc = 0; if (port) { - rc = uart_remove_one_port(&ulite_uart_driver, port); + uart_remove_one_port(&ulite_uart_driver, port); dev_set_drvdata(dev, NULL); port->mapbase = 0; } - - return rc; } /** @@ -900,14 +897,13 @@ static int ulite_remove(struct platform_device *pdev) { struct uart_port *port = dev_get_drvdata(&pdev->dev); struct uartlite_data *pdata = port->private_data; - int rc; clk_disable_unprepare(pdata->clk); - rc = ulite_release(&pdev->dev); + ulite_release(&pdev->dev); pm_runtime_disable(&pdev->dev); pm_runtime_set_suspended(&pdev->dev); pm_runtime_dont_use_autosuspend(&pdev->dev); - return rc; + return 0; } /* work with hotplug and coldplug */ diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c index 8e521c69a959..20a751663ef9 100644 --- a/drivers/tty/serial/xilinx_uartps.c +++ b/drivers/tty/serial/xilinx_uartps.c @@ -1670,14 +1670,13 @@ static int cdns_uart_remove(struct platform_device *pdev) { struct uart_port *port = platform_get_drvdata(pdev); struct cdns_uart *cdns_uart_data = port->private_data; - int rc; /* Remove the cdns_uart port from the serial core */ #ifdef CONFIG_COMMON_CLK clk_notifier_unregister(cdns_uart_data->uartclk, &cdns_uart_data->clk_rate_change_nb); #endif - rc = uart_remove_one_port(cdns_uart_data->cdns_uart_driver, port); + uart_remove_one_port(cdns_uart_data->cdns_uart_driver, port); port->mapbase = 0; clk_disable_unprepare(cdns_uart_data->uartclk); clk_disable_unprepare(cdns_uart_data->pclk); @@ -1693,7 +1692,7 @@ static int cdns_uart_remove(struct platform_device *pdev) if (!--instances) uart_unregister_driver(cdns_uart_data->cdns_uart_driver); - return rc; + return 0; } static struct platform_driver cdns_uart_platform_driver = { diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 66ecec15a1bf..ddcdb5b8523e 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -853,7 +853,7 @@ void uart_console_write(struct uart_port *port, const char *s, int uart_register_driver(struct uart_driver *uart); void uart_unregister_driver(struct uart_driver *uart); int uart_add_one_port(struct uart_driver *reg, struct uart_port *port); -int uart_remove_one_port(struct uart_driver *reg, struct uart_port *port); +void uart_remove_one_port(struct uart_driver *reg, struct uart_port *port); bool uart_match_port(const struct uart_port *port1, const struct uart_port *port2); -- cgit v1.2.3 From a7e3448086d580abadccff399316c6eb5ecdedbf Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 11 May 2023 10:21:08 -0700 Subject: net: phy: Allow drivers to always call into ->suspend() A few PHY drivers are currently attempting to not suspend the PHY when Wake-on-LAN is enabled, however that code is not currently executing at all due to an early check in phy_suspend(). This prevents PHY drivers from making an appropriate decisions and put the hardware into a low power state if desired. In order to allow the PHY drivers to opt into getting their ->suspend routine to be called, add a PHY_ALWAYS_CALL_SUSPEND bit which can be set. A boolean that tracks whether the PHY or the attached MAC has Wake-on-LAN enabled is also provided for convenience. If phydev::wol_enabled then the PHY shall not prevent its own Wake-on-LAN detection logic from working and shall not prevent the Ethernet MAC from receiving packets for matching. Reviewed-by: Simon Horman Reviewed-by: Andrew Lunn Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/phy_device.c | 5 +++-- include/linux/phy.h | 4 ++++ 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 17d0d0555a79..8852b0c53114 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1860,9 +1860,10 @@ int phy_suspend(struct phy_device *phydev) if (phydev->suspended) return 0; - /* If the device has WOL enabled, we cannot suspend the PHY */ phy_ethtool_get_wol(phydev, &wol); - if (wol.wolopts || (netdev && netdev->wol_enabled)) + phydev->wol_enabled = wol.wolopts || (netdev && netdev->wol_enabled); + /* If the device has WOL enabled, we cannot suspend the PHY */ + if (phydev->wol_enabled && !(phydrv->flags & PHY_ALWAYS_CALL_SUSPEND)) return -EBUSY; if (!phydrv || !phydrv->suspend) diff --git a/include/linux/phy.h b/include/linux/phy.h index c5a0dc829714..e0df8b3c2bdb 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -86,6 +86,7 @@ extern const int phy_10gbit_features_array[1]; #define PHY_IS_INTERNAL 0x00000001 #define PHY_RST_AFTER_CLK_EN 0x00000002 #define PHY_POLL_CABLE_TEST 0x00000004 +#define PHY_ALWAYS_CALL_SUSPEND 0x00000008 #define MDIO_DEVICE_IS_PHY 0x80000000 /** @@ -548,6 +549,8 @@ struct macsec_ops; * @downshifted_rate: Set true if link speed has been downshifted. * @is_on_sfp_module: Set true if PHY is located on an SFP module. * @mac_managed_pm: Set true if MAC driver takes of suspending/resuming PHY + * @wol_enabled: Set to true if the PHY or the attached MAC have Wake-on-LAN + * enabled. * @state: State of the PHY for management purposes * @dev_flags: Device-specific flags used by the PHY driver. * @@ -644,6 +647,7 @@ struct phy_device { unsigned downshifted_rate:1; unsigned is_on_sfp_module:1; unsigned mac_managed_pm:1; + unsigned wol_enabled:1; unsigned autoneg:1; /* The most recently read link state */ -- cgit v1.2.3 From 8baddaa9d4bac939004b5058f3ade7e2bf0a6e43 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 11 May 2023 10:21:09 -0700 Subject: net: phy: broadcom: Add support for Wake-on-LAN Add support for WAKE_UCAST, WAKE_MCAST, WAKE_BCAST, WAKE_MAGIC and WAKE_MAGICSECURE. This is only supported with the BCM54210E and compatible Ethernet PHYs. Using the in-band interrupt or an out of band GPIO interrupts are supported. Broadcom PHYs will generate a Wake-on-LAN level low interrupt on LED4 as soon as one of the supported patterns is being matched. That includes generating such an interrupt even if the PHY is operated during normal modes. If WAKE_UCAST is selected, this could lead to the LED4 interrupt firing up for every packet being received which is absolutely undesirable from a performance point of view. Because the Wake-on-LAN configuration can be set long before the system is actually put to sleep, we cannot have an interrupt service routine to clear on read the interrupt status register and ensure that new packet matches will be detected. It is desirable to enable the Wake-on-LAN interrupt as late as possible during the system suspend process such that we limit the number of interrupts to be handled by the system, but also conversely feed into the Linux's system suspend way of dealing with interrupts in and around the points of no return. Reviewed-by: Simon Horman Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/bcm-phy-lib.c | 212 ++++++++++++++++++++++++++++++++++++++++++ drivers/net/phy/bcm-phy-lib.h | 5 + drivers/net/phy/broadcom.c | 126 ++++++++++++++++++++++++- include/linux/brcmphy.h | 55 +++++++++++ 4 files changed, 395 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/bcm-phy-lib.c b/drivers/net/phy/bcm-phy-lib.c index b2c0baa51f39..27c57f6ab211 100644 --- a/drivers/net/phy/bcm-phy-lib.c +++ b/drivers/net/phy/bcm-phy-lib.c @@ -6,12 +6,14 @@ #include "bcm-phy-lib.h" #include #include +#include #include #include #include #include #include #include +#include #define MII_BCM_CHANNEL_WIDTH 0x2000 #define BCM_CL45VEN_EEE_ADV 0x3c @@ -816,6 +818,216 @@ int bcm_phy_cable_test_get_status_rdb(struct phy_device *phydev, } EXPORT_SYMBOL_GPL(bcm_phy_cable_test_get_status_rdb); +#define BCM54XX_WOL_SUPPORTED_MASK (WAKE_UCAST | \ + WAKE_MCAST | \ + WAKE_BCAST | \ + WAKE_MAGIC | \ + WAKE_MAGICSECURE) + +int bcm_phy_set_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol) +{ + struct net_device *ndev = phydev->attached_dev; + u8 da[ETH_ALEN], mask[ETH_ALEN]; + unsigned int i; + u16 ctl; + int ret; + + /* Allow a MAC driver to play through its own Wake-on-LAN + * implementation + */ + if (wol->wolopts & ~BCM54XX_WOL_SUPPORTED_MASK) + return -EOPNOTSUPP; + + /* The PHY supports passwords of 4, 6 and 8 bytes in size, but Linux's + * ethtool only supports 6, for now. + */ + BUILD_BUG_ON(sizeof(wol->sopass) != ETH_ALEN); + + /* Clear previous interrupts */ + ret = bcm_phy_read_exp(phydev, BCM54XX_WOL_INT_STATUS); + if (ret < 0) + return ret; + + ret = bcm_phy_read_exp(phydev, BCM54XX_WOL_MAIN_CTL); + if (ret < 0) + return ret; + + ctl = ret; + + if (!wol->wolopts) { + if (phy_interrupt_is_valid(phydev)) + disable_irq_wake(phydev->irq); + + /* Leave all interrupts disabled */ + ret = bcm_phy_write_exp(phydev, BCM54XX_WOL_INT_MASK, + BCM54XX_WOL_ALL_INTRS); + if (ret < 0) + return ret; + + /* Disable the global Wake-on-LAN enable bit */ + ctl &= ~BCM54XX_WOL_EN; + + return bcm_phy_write_exp(phydev, BCM54XX_WOL_MAIN_CTL, ctl); + } + + /* Clear the previously configured mode and mask mode for Wake-on-LAN */ + ctl &= ~(BCM54XX_WOL_MODE_MASK << BCM54XX_WOL_MODE_SHIFT); + ctl &= ~(BCM54XX_WOL_MASK_MODE_MASK << BCM54XX_WOL_MASK_MODE_SHIFT); + ctl &= ~BCM54XX_WOL_DIR_PKT_EN; + ctl &= ~(BCM54XX_WOL_SECKEY_OPT_MASK << BCM54XX_WOL_SECKEY_OPT_SHIFT); + + /* When using WAKE_MAGIC, we program the magic pattern filter to match + * the device's MAC address and we accept any MAC DA in the Ethernet + * frame. + * + * When using WAKE_UCAST, WAKE_BCAST or WAKE_MCAST, we program the + * following: + * - WAKE_UCAST -> MAC DA is the device's MAC with a perfect match + * - WAKE_MCAST -> MAC DA is X1:XX:XX:XX:XX:XX where XX is don't care + * - WAKE_BCAST -> MAC DA is FF:FF:FF:FF:FF:FF with a perfect match + * + * Note that the Broadcast MAC DA is inherently going to match the + * multicast pattern being matched. + */ + memset(mask, 0, sizeof(mask)); + + if (wol->wolopts & WAKE_MCAST) { + memset(da, 0, sizeof(da)); + memset(mask, 0xff, sizeof(mask)); + da[0] = 0x01; + mask[0] = ~da[0]; + } else { + if (wol->wolopts & WAKE_UCAST) { + ether_addr_copy(da, ndev->dev_addr); + } else if (wol->wolopts & WAKE_BCAST) { + eth_broadcast_addr(da); + } else if (wol->wolopts & WAKE_MAGICSECURE) { + ether_addr_copy(da, wol->sopass); + } else if (wol->wolopts & WAKE_MAGIC) { + memset(da, 0, sizeof(da)); + memset(mask, 0xff, sizeof(mask)); + } + } + + for (i = 0; i < ETH_ALEN / 2; i++) { + if (wol->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE)) { + ret = bcm_phy_write_exp(phydev, + BCM54XX_WOL_MPD_DATA1(2 - i), + ndev->dev_addr[i * 2] << 8 | + ndev->dev_addr[i * 2 + 1]); + if (ret < 0) + return ret; + } + + ret = bcm_phy_write_exp(phydev, BCM54XX_WOL_MPD_DATA2(2 - i), + da[i * 2] << 8 | da[i * 2 + 1]); + if (ret < 0) + return ret; + + ret = bcm_phy_write_exp(phydev, BCM54XX_WOL_MASK(2 - i), + mask[i * 2] << 8 | mask[i * 2 + 1]); + if (ret) + return ret; + } + + if (wol->wolopts & WAKE_MAGICSECURE) { + ctl |= BCM54XX_WOL_SECKEY_OPT_6B << + BCM54XX_WOL_SECKEY_OPT_SHIFT; + ctl |= BCM54XX_WOL_MODE_SINGLE_MPDSEC << BCM54XX_WOL_MODE_SHIFT; + ctl |= BCM54XX_WOL_MASK_MODE_DA_FF << + BCM54XX_WOL_MASK_MODE_SHIFT; + } else { + if (wol->wolopts & WAKE_MAGIC) + ctl |= BCM54XX_WOL_MODE_SINGLE_MPD; + else + ctl |= BCM54XX_WOL_DIR_PKT_EN; + ctl |= BCM54XX_WOL_MASK_MODE_DA_ONLY << + BCM54XX_WOL_MASK_MODE_SHIFT; + } + + /* Globally enable Wake-on-LAN */ + ctl |= BCM54XX_WOL_EN | BCM54XX_WOL_CRC_CHK; + + ret = bcm_phy_write_exp(phydev, BCM54XX_WOL_MAIN_CTL, ctl); + if (ret < 0) + return ret; + + /* Enable WOL interrupt on LED4 */ + ret = bcm_phy_read_exp(phydev, BCM54XX_TOP_MISC_LED_CTL); + if (ret < 0) + return ret; + + ret |= BCM54XX_LED4_SEL_INTR; + ret = bcm_phy_write_exp(phydev, BCM54XX_TOP_MISC_LED_CTL, ret); + if (ret < 0) + return ret; + + /* Enable all Wake-on-LAN interrupt sources */ + ret = bcm_phy_write_exp(phydev, BCM54XX_WOL_INT_MASK, 0); + if (ret < 0) + return ret; + + if (phy_interrupt_is_valid(phydev)) + enable_irq_wake(phydev->irq); + + return 0; +} +EXPORT_SYMBOL_GPL(bcm_phy_set_wol); + +void bcm_phy_get_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol) +{ + struct net_device *ndev = phydev->attached_dev; + u8 da[ETH_ALEN]; + unsigned int i; + int ret; + u16 ctl; + + wol->supported = BCM54XX_WOL_SUPPORTED_MASK; + wol->wolopts = 0; + + ret = bcm_phy_read_exp(phydev, BCM54XX_WOL_MAIN_CTL); + if (ret < 0) + return; + + ctl = ret; + + if (!(ctl & BCM54XX_WOL_EN)) + return; + + for (i = 0; i < sizeof(da) / 2; i++) { + ret = bcm_phy_read_exp(phydev, + BCM54XX_WOL_MPD_DATA2(2 - i)); + if (ret < 0) + return; + + da[i * 2] = ret >> 8; + da[i * 2 + 1] = ret & 0xff; + } + + if (ctl & BCM54XX_WOL_DIR_PKT_EN) { + if (is_broadcast_ether_addr(da)) + wol->wolopts |= WAKE_BCAST; + else if (is_multicast_ether_addr(da)) + wol->wolopts |= WAKE_MCAST; + else if (ether_addr_equal(da, ndev->dev_addr)) + wol->wolopts |= WAKE_UCAST; + } else { + ctl = (ctl >> BCM54XX_WOL_MODE_SHIFT) & BCM54XX_WOL_MODE_MASK; + switch (ctl) { + case BCM54XX_WOL_MODE_SINGLE_MPD: + wol->wolopts |= WAKE_MAGIC; + break; + case BCM54XX_WOL_MODE_SINGLE_MPDSEC: + wol->wolopts |= WAKE_MAGICSECURE; + memcpy(wol->sopass, da, sizeof(da)); + break; + default: + break; + } + } +} +EXPORT_SYMBOL_GPL(bcm_phy_get_wol); + MODULE_DESCRIPTION("Broadcom PHY Library"); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Broadcom Corporation"); diff --git a/drivers/net/phy/bcm-phy-lib.h b/drivers/net/phy/bcm-phy-lib.h index 729db441797a..c6fed43ec913 100644 --- a/drivers/net/phy/bcm-phy-lib.h +++ b/drivers/net/phy/bcm-phy-lib.h @@ -9,6 +9,8 @@ #include #include +struct ethtool_wolinfo; + /* 28nm only register definitions */ #define MISC_ADDR(base, channel) base, channel @@ -111,4 +113,7 @@ static inline void bcm_ptp_stop(struct bcm_ptp_private *priv) } #endif +int bcm_phy_set_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol); +void bcm_phy_get_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol); + #endif /* _LINUX_BCM_PHY_LIB_H */ diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index ad71c88c87e7..418e6bc0e998 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -14,8 +14,12 @@ #include #include #include +#include #include #include +#include +#include +#include #define BRCM_PHY_MODEL(phydev) \ ((phydev)->drv->phy_id & (phydev)->drv->phy_id_mask) @@ -30,8 +34,17 @@ MODULE_LICENSE("GPL"); struct bcm54xx_phy_priv { u64 *stats; struct bcm_ptp_private *ptp; + int wake_irq; + bool wake_irq_enabled; }; +static bool bcm54xx_phy_can_wakeup(struct phy_device *phydev) +{ + struct bcm54xx_phy_priv *priv = phydev->priv; + + return phy_interrupt_is_valid(phydev) || priv->wake_irq >= 0; +} + static int bcm54xx_config_clock_delay(struct phy_device *phydev) { int rc, val; @@ -413,6 +426,16 @@ static int bcm54xx_config_init(struct phy_device *phydev) bcm54xx_ptp_config_init(phydev); + /* Acknowledge any left over interrupt and charge the device for + * wake-up. + */ + err = bcm_phy_read_exp(phydev, BCM54XX_WOL_INT_STATUS); + if (err < 0) + return err; + + if (err) + pm_wakeup_event(&phydev->mdio.dev, 0); + return 0; } @@ -437,12 +460,39 @@ out: return ret; } +static int bcm54xx_set_wakeup_irq(struct phy_device *phydev, bool state) +{ + struct bcm54xx_phy_priv *priv = phydev->priv; + int ret = 0; + + if (!bcm54xx_phy_can_wakeup(phydev)) + return ret; + + if (priv->wake_irq_enabled != state) { + if (state) + ret = enable_irq_wake(priv->wake_irq); + else + ret = disable_irq_wake(priv->wake_irq); + priv->wake_irq_enabled = state; + } + + return ret; +} + static int bcm54xx_suspend(struct phy_device *phydev) { - int ret; + int ret = 0; bcm54xx_ptp_stop(phydev); + /* Acknowledge any Wake-on-LAN interrupt prior to suspend */ + ret = bcm_phy_read_exp(phydev, BCM54XX_WOL_INT_STATUS); + if (ret < 0) + return ret; + + if (phydev->wol_enabled) + return bcm54xx_set_wakeup_irq(phydev, true); + /* We cannot use a read/modify/write here otherwise the PHY gets into * a bad state where its LEDs keep flashing, thus defeating the purpose * of low power mode. @@ -456,7 +506,13 @@ static int bcm54xx_suspend(struct phy_device *phydev) static int bcm54xx_resume(struct phy_device *phydev) { - int ret; + int ret = 0; + + if (phydev->wol_enabled) { + ret = bcm54xx_set_wakeup_irq(phydev, false); + if (ret) + return ret; + } ret = bcm54xx_iddq_set(phydev, false); if (ret < 0) @@ -801,14 +857,54 @@ static int brcm_fet_suspend(struct phy_device *phydev) return err; } +static void bcm54xx_phy_get_wol(struct phy_device *phydev, + struct ethtool_wolinfo *wol) +{ + /* We cannot wake-up if we do not have a dedicated PHY interrupt line + * or an out of band GPIO descriptor for wake-up. Zeroing + * wol->supported allows the caller (MAC driver) to play through and + * offer its own Wake-on-LAN scheme if available. + */ + if (!bcm54xx_phy_can_wakeup(phydev)) { + wol->supported = 0; + return; + } + + bcm_phy_get_wol(phydev, wol); +} + +static int bcm54xx_phy_set_wol(struct phy_device *phydev, + struct ethtool_wolinfo *wol) +{ + int ret; + + /* We cannot wake-up if we do not have a dedicated PHY interrupt line + * or an out of band GPIO descriptor for wake-up. Returning -EOPNOTSUPP + * allows the caller (MAC driver) to play through and offer its own + * Wake-on-LAN scheme if available. + */ + if (!bcm54xx_phy_can_wakeup(phydev)) + return -EOPNOTSUPP; + + ret = bcm_phy_set_wol(phydev, wol); + if (ret < 0) + return ret; + + return 0; +} + static int bcm54xx_phy_probe(struct phy_device *phydev) { struct bcm54xx_phy_priv *priv; + struct gpio_desc *wakeup_gpio; + int ret = 0; priv = devm_kzalloc(&phydev->mdio.dev, sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; + priv->wake_irq = -ENXIO; + phydev->priv = priv; priv->stats = devm_kcalloc(&phydev->mdio.dev, @@ -821,7 +917,28 @@ static int bcm54xx_phy_probe(struct phy_device *phydev) if (IS_ERR(priv->ptp)) return PTR_ERR(priv->ptp); - return 0; + /* We cannot utilize the _optional variant here since we want to know + * whether the GPIO descriptor exists or not to advertise Wake-on-LAN + * support or not. + */ + wakeup_gpio = devm_gpiod_get(&phydev->mdio.dev, "wakeup", GPIOD_IN); + if (PTR_ERR(wakeup_gpio) == -EPROBE_DEFER) + return PTR_ERR(wakeup_gpio); + + if (!IS_ERR(wakeup_gpio)) { + priv->wake_irq = gpiod_to_irq(wakeup_gpio); + ret = irq_set_irq_type(priv->wake_irq, IRQ_TYPE_LEVEL_LOW); + if (ret) + return ret; + } + + /* If we do not have a main interrupt or a side-band wake-up interrupt, + * then the device cannot be marked as wake-up capable. + */ + if (!bcm54xx_phy_can_wakeup(phydev)) + return 0; + + return device_init_wakeup(&phydev->mdio.dev, true); } static void bcm54xx_get_stats(struct phy_device *phydev, @@ -894,6 +1011,7 @@ static struct phy_driver broadcom_drivers[] = { .phy_id_mask = 0xfffffff0, .name = "Broadcom BCM54210E", /* PHY_GBIT_FEATURES */ + .flags = PHY_ALWAYS_CALL_SUSPEND, .get_sset_count = bcm_phy_get_sset_count, .get_strings = bcm_phy_get_strings, .get_stats = bcm54xx_get_stats, @@ -904,6 +1022,8 @@ static struct phy_driver broadcom_drivers[] = { .link_change_notify = bcm54xx_link_change_notify, .suspend = bcm54xx_suspend, .resume = bcm54xx_resume, + .get_wol = bcm54xx_phy_get_wol, + .set_wol = bcm54xx_phy_set_wol, }, { .phy_id = PHY_ID_BCM5461, .phy_id_mask = 0xfffffff0, diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 9e77165f3ef6..e9afbfb6d7a5 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -89,6 +89,7 @@ #define MII_BCM54XX_EXP_SEL 0x17 /* Expansion register select */ #define MII_BCM54XX_EXP_SEL_TOP 0x0d00 /* TOP_MISC expansion register select */ #define MII_BCM54XX_EXP_SEL_SSD 0x0e00 /* Secondary SerDes select */ +#define MII_BCM54XX_EXP_SEL_WOL 0x0e00 /* Wake-on-LAN expansion select register */ #define MII_BCM54XX_EXP_SEL_ER 0x0f00 /* Expansion register select */ #define MII_BCM54XX_EXP_SEL_ETC 0x0d00 /* Expansion register spare + 2k mem */ @@ -253,6 +254,9 @@ #define BCM54XX_TOP_MISC_IDDQ_SD (1 << 2) #define BCM54XX_TOP_MISC_IDDQ_SR (1 << 3) +#define BCM54XX_TOP_MISC_LED_CTL (MII_BCM54XX_EXP_SEL_TOP + 0x0C) +#define BCM54XX_LED4_SEL_INTR BIT(1) + /* * BCM5482: Secondary SerDes registers */ @@ -272,6 +276,57 @@ #define BCM54612E_EXP_SPARE0 (MII_BCM54XX_EXP_SEL_ETC + 0x34) #define BCM54612E_LED4_CLK125OUT_EN (1 << 1) + +/* Wake-on-LAN registers */ +#define BCM54XX_WOL_MAIN_CTL (MII_BCM54XX_EXP_SEL_WOL + 0x80) +#define BCM54XX_WOL_EN BIT(0) +#define BCM54XX_WOL_MODE_SINGLE_MPD 0 +#define BCM54XX_WOL_MODE_SINGLE_MPDSEC 1 +#define BCM54XX_WOL_MODE_DUAL 2 +#define BCM54XX_WOL_MODE_SHIFT 1 +#define BCM54XX_WOL_MODE_MASK 0x3 +#define BCM54XX_WOL_MP_MSB_FF_EN BIT(3) +#define BCM54XX_WOL_SECKEY_OPT_4B 0 +#define BCM54XX_WOL_SECKEY_OPT_6B 1 +#define BCM54XX_WOL_SECKEY_OPT_8B 2 +#define BCM54XX_WOL_SECKEY_OPT_SHIFT 4 +#define BCM54XX_WOL_SECKEY_OPT_MASK 0x3 +#define BCM54XX_WOL_L2_TYPE_CHK BIT(6) +#define BCM54XX_WOL_L4IPV4UDP_CHK BIT(7) +#define BCM54XX_WOL_L4IPV6UDP_CHK BIT(8) +#define BCM54XX_WOL_UDPPORT_CHK BIT(9) +#define BCM54XX_WOL_CRC_CHK BIT(10) +#define BCM54XX_WOL_SECKEY_MODE BIT(11) +#define BCM54XX_WOL_RST BIT(12) +#define BCM54XX_WOL_DIR_PKT_EN BIT(13) +#define BCM54XX_WOL_MASK_MODE_DA_FF 0 +#define BCM54XX_WOL_MASK_MODE_DA_MPD 1 +#define BCM54XX_WOL_MASK_MODE_DA_ONLY 2 +#define BCM54XX_WOL_MASK_MODE_MPD 3 +#define BCM54XX_WOL_MASK_MODE_SHIFT 14 +#define BCM54XX_WOL_MASK_MODE_MASK 0x3 + +#define BCM54XX_WOL_INNER_PROTO (MII_BCM54XX_EXP_SEL_WOL + 0x81) +#define BCM54XX_WOL_OUTER_PROTO (MII_BCM54XX_EXP_SEL_WOL + 0x82) +#define BCM54XX_WOL_OUTER_PROTO2 (MII_BCM54XX_EXP_SEL_WOL + 0x83) + +#define BCM54XX_WOL_MPD_DATA1(x) (MII_BCM54XX_EXP_SEL_WOL + 0x84 + (x)) +#define BCM54XX_WOL_MPD_DATA2(x) (MII_BCM54XX_EXP_SEL_WOL + 0x87 + (x)) +#define BCM54XX_WOL_SEC_KEY_8B (MII_BCM54XX_EXP_SEL_WOL + 0x8A) +#define BCM54XX_WOL_MASK(x) (MII_BCM54XX_EXP_SEL_WOL + 0x8B + (x)) +#define BCM54XX_SEC_KEY_STORE(x) (MII_BCM54XX_EXP_SEL_WOL + 0x8E) +#define BCM54XX_WOL_SHARED_CNT (MII_BCM54XX_EXP_SEL_WOL + 0x92) + +#define BCM54XX_WOL_INT_MASK (MII_BCM54XX_EXP_SEL_WOL + 0x93) +#define BCM54XX_WOL_PKT1 BIT(0) +#define BCM54XX_WOL_PKT2 BIT(1) +#define BCM54XX_WOL_DIR BIT(2) +#define BCM54XX_WOL_ALL_INTRS (BCM54XX_WOL_PKT1 | \ + BCM54XX_WOL_PKT2 | \ + BCM54XX_WOL_DIR) + +#define BCM54XX_WOL_INT_STATUS (MII_BCM54XX_EXP_SEL_WOL + 0x94) + /*****************************************************************************/ /* Fast Ethernet Transceiver definitions. */ /*****************************************************************************/ -- cgit v1.2.3 From 672cde9ef80ffde9e76d38f7aa2b287c4a18de9a Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Fri, 21 Apr 2023 08:46:11 +0300 Subject: iio: fix doc for iio_gts_find_sel_by_int_time The kerneldoc for iio_gts_find_sel_by_int_time() has an error. Documentation states that function is searching a selector for a HW-gain while it is searching a selector for an integration time. Fix the documentation by saying the function is looking for a selector for an integration time. Fixes: 38416c28e168 ("iio: light: Add gain-time-scale helpers") Signed-off-by: Matti Vaittinen Link: https://lore.kernel.org/r/ZEIjI4YUzqPZk/9X@fedora Signed-off-by: Jonathan Cameron --- include/linux/iio/iio-gts-helper.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio-gts-helper.h b/include/linux/iio/iio-gts-helper.h index dd64e544a3da..9cb6c80dea71 100644 --- a/include/linux/iio/iio-gts-helper.h +++ b/include/linux/iio/iio-gts-helper.h @@ -135,7 +135,7 @@ static inline int iio_gts_find_int_time_by_sel(struct iio_gts *gts, int sel) /** * iio_gts_find_sel_by_int_time - find selector matching integration time * @gts: Gain time scale descriptor - * @gain: HW-gain for which matching selector is searched for + * @time: Integration time for which matching selector is searched for * * Return: a selector matching given integration time or -EINVAL if * selector was not found. -- cgit v1.2.3 From 9445368bca2f62cadfcf98e06219f784ae94dce0 Mon Sep 17 00:00:00 2001 From: Marius Hoch Date: Sun, 16 Apr 2023 01:11:25 +0200 Subject: iio: accel: st_accel: Add LSM303D The lsm303d has the same register mapping as the lsm9ds0, thus we can just re-use that. Tested on a Lenovo Yoga Tablet 2 1051-F. Signed-off-by: Marius Hoch Reviewed-by: Linus Walleij Tested-by: Hans de Goede Link: https://lore.kernel.org/r/20230415231130.115094-2-mail@mariushoch.de Signed-off-by: Jonathan Cameron --- drivers/iio/accel/st_accel_core.c | 1 + include/linux/iio/common/st_sensors.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/drivers/iio/accel/st_accel_core.c b/drivers/iio/accel/st_accel_core.c index 5f7d81b44b1d..7c4f58c90f94 100644 --- a/drivers/iio/accel/st_accel_core.c +++ b/drivers/iio/accel/st_accel_core.c @@ -1007,6 +1007,7 @@ static const struct st_sensor_settings st_accel_sensors_settings[] = { .wai_addr = ST_SENSORS_DEFAULT_WAI_ADDRESS, .sensors_supported = { [0] = LSM9DS0_IMU_DEV_NAME, + [1] = LSM303D_IMU_DEV_NAME, }, .ch = (struct iio_chan_spec *)st_accel_16bit_channels, .odr = { diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index f5f3ee57bc70..607c3a89a647 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -22,6 +22,7 @@ #include #define LSM9DS0_IMU_DEV_NAME "lsm9ds0" +#define LSM303D_IMU_DEV_NAME "lsm303d" /* * Buffer size max case: 2bytes per channel, 3 channels in total + -- cgit v1.2.3 From 69ee1fb21340cb83df531175f298010697a87448 Mon Sep 17 00:00:00 2001 From: Marius Hoch Date: Sun, 16 Apr 2023 01:11:29 +0200 Subject: iio: Comment that the LSM303D also has the Magnetometer DRDY Per its datasheet, the LSM303D also features that pin. Signed-off-by: Marius Hoch Reviewed-by: Linus Walleij Tested-by: Hans de Goede Link: https://lore.kernel.org/r/20230415231130.115094-6-mail@mariushoch.de Signed-off-by: Jonathan Cameron --- include/linux/platform_data/st_sensors_pdata.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/st_sensors_pdata.h b/include/linux/platform_data/st_sensors_pdata.h index 897051e51b78..a657830232ae 100644 --- a/include/linux/platform_data/st_sensors_pdata.h +++ b/include/linux/platform_data/st_sensors_pdata.h @@ -15,7 +15,7 @@ * @drdy_int_pin: Redirect DRDY on pin 1 (1) or pin 2 (2). * Available only for accelerometer, magnetometer and pressure sensors. * Accelerometer DRDY on LSM330 available only on pin 1 (see datasheet). - * Magnetometer DRDY is supported only on LSM9DS0. + * Magnetometer DRDY is supported only on LSM9DS0 and LSM303D. * @open_drain: set the interrupt line to be open drain if possible. * @spi_3wire: enable spi-3wire mode. * @pullups: enable/disable i2c controller pullup resistors. -- cgit v1.2.3 From 123627ad03d9915f6a6ecb69bb86a80da69ee972 Mon Sep 17 00:00:00 2001 From: Marijn Suijten Date: Tue, 2 May 2023 01:17:33 +0200 Subject: iio: core: Point users of extend_name field to read_label callback As mentioned and discussed in [1] extend_name should not be used for full channel labels (and most drivers seem to only use it to express a short type of a channel) as this affects sysfs filenames, while the label name is supposed to be extracted from the *_label sysfs file instead. This appears to have been unclear to some drivers as extend_name is also used when read_label is unset, achieving an initial goal of providing sensible names in *_label sysfs files without noticing that sysfs filenames are (negatively and likely unintentionally) affected as well. Point readers of iio_chan_spec::extend_name to iio_info::read_label by mentioning deprecation and side-effects of this field. [1]: https://lore.kernel.org/linux-arm-msm/20221221223432.si2aasbleiicayfl@SoMainline.org/ Suggested-by: Jonathan Cameron Signed-off-by: Marijn Suijten Link: https://lore.kernel.org/r/20230502-iio-adc-propagate-fw-node-label-v3-1-6be5db6e6b5a@somainline.org Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 81413cd3a3e7..6fc06063505a 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -221,6 +221,9 @@ struct iio_event_spec { * @extend_name: Allows labeling of channel attributes with an * informative name. Note this has no effect codes etc, * unlike modifiers. + * This field is deprecated in favour of providing + * iio_info->read_label() to override the label, which + * unlike @extend_name does not affect sysfs filenames. * @datasheet_name: A name used in in-kernel mapping of channels. It should * correspond to the first name that the channel is referred * to by in the datasheet (e.g. IND), or the nearest -- cgit v1.2.3 From b51f4113ebb02011f0ca86abc3134b28d2071b6a Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Thu, 11 May 2023 09:12:12 +0800 Subject: net: introduce and use skb_frag_fill_page_desc() Most users use __skb_frag_set_page()/skb_frag_off_set()/ skb_frag_size_set() to fill the page desc for a skb frag. Introduce skb_frag_fill_page_desc() to do that. net/bpf/test_run.c does not call skb_frag_off_set() to set the offset, "copy_from_user(page_address(page), ...)" and 'shinfo' being part of the 'data' kzalloced in bpf_test_init() suggest that it is assuming offset to be initialized as zero, so call skb_frag_fill_page_desc() with offset being zero for this case. Also, skb_frag_set_page() is not used anymore, so remove it. Signed-off-by: Yunsheng Lin Reviewed-by: Leon Romanovsky Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/aquantia/atlantic/aq_ring.c | 6 ++--- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 5 ++-- drivers/net/ethernet/chelsio/cxgb3/sge.c | 5 ++-- drivers/net/ethernet/emulex/benet/be_main.c | 32 +++++++++++++----------- drivers/net/ethernet/freescale/enetc/enetc.c | 5 ++-- drivers/net/ethernet/fungible/funeth/funeth_rx.c | 5 ++-- drivers/net/ethernet/marvell/mvneta.c | 5 ++-- drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 4 +-- drivers/net/ethernet/sun/cassini.c | 8 ++---- drivers/net/virtio_net.c | 4 +-- drivers/net/vmxnet3/vmxnet3_drv.c | 4 +-- drivers/net/xen-netback/netback.c | 4 +-- include/linux/skbuff.h | 27 ++++++++------------ net/bpf/test_run.c | 3 +-- net/core/gro.c | 4 +-- net/core/pktgen.c | 13 ++++++---- net/core/skbuff.c | 7 +++--- net/tls/tls_device.c | 10 +++----- net/xfrm/xfrm_ipcomp.c | 5 +--- 19 files changed, 64 insertions(+), 92 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 7f933175cbda..4de22eed099a 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -532,10 +532,10 @@ static bool aq_add_rx_fragment(struct device *dev, buff_->rxdata.pg_off, buff_->len, DMA_FROM_DEVICE); - skb_frag_off_set(frag, buff_->rxdata.pg_off); - skb_frag_size_set(frag, buff_->len); sinfo->xdp_frags_size += buff_->len; - __skb_frag_set_page(frag, buff_->rxdata.page); + skb_frag_fill_page_desc(frag, buff_->rxdata.page, + buff_->rxdata.pg_off, + buff_->len); buff_->is_cleaned = 1; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index dcd9367f05af..efaff5018af8 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1085,9 +1085,8 @@ static u32 __bnxt_rx_agg_pages(struct bnxt *bp, RX_AGG_CMP_LEN) >> RX_AGG_CMP_LEN_SHIFT; cons_rx_buf = &rxr->rx_agg_ring[cons]; - skb_frag_off_set(frag, cons_rx_buf->offset); - skb_frag_size_set(frag, frag_len); - __skb_frag_set_page(frag, cons_rx_buf->page); + skb_frag_fill_page_desc(frag, cons_rx_buf->page, + cons_rx_buf->offset, frag_len); shinfo->nr_frags = i + 1; __clear_bit(cons, rxr->rx_agg_bmap); diff --git a/drivers/net/ethernet/chelsio/cxgb3/sge.c b/drivers/net/ethernet/chelsio/cxgb3/sge.c index efa7f401529e..2e9a74fe0970 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb3/sge.c @@ -2184,9 +2184,8 @@ static void lro_add_page(struct adapter *adap, struct sge_qset *qs, len -= offset; rx_frag += nr_frags; - __skb_frag_set_page(rx_frag, sd->pg_chunk.page); - skb_frag_off_set(rx_frag, sd->pg_chunk.offset + offset); - skb_frag_size_set(rx_frag, len); + skb_frag_fill_page_desc(rx_frag, sd->pg_chunk.page, + sd->pg_chunk.offset + offset, len); skb->len += len; skb->data_len += len; diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 7e408bcc88de..3164ed205cf7 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -2343,11 +2343,10 @@ static void skb_fill_rx_data(struct be_rx_obj *rxo, struct sk_buff *skb, hdr_len = ETH_HLEN; memcpy(skb->data, start, hdr_len); skb_shinfo(skb)->nr_frags = 1; - skb_frag_set_page(skb, 0, page_info->page); - skb_frag_off_set(&skb_shinfo(skb)->frags[0], - page_info->page_offset + hdr_len); - skb_frag_size_set(&skb_shinfo(skb)->frags[0], - curr_frag_len - hdr_len); + skb_frag_fill_page_desc(&skb_shinfo(skb)->frags[0], + page_info->page, + page_info->page_offset + hdr_len, + curr_frag_len - hdr_len); skb->data_len = curr_frag_len - hdr_len; skb->truesize += rx_frag_size; skb->tail += hdr_len; @@ -2369,16 +2368,17 @@ static void skb_fill_rx_data(struct be_rx_obj *rxo, struct sk_buff *skb, if (page_info->page_offset == 0) { /* Fresh page */ j++; - skb_frag_set_page(skb, j, page_info->page); - skb_frag_off_set(&skb_shinfo(skb)->frags[j], - page_info->page_offset); - skb_frag_size_set(&skb_shinfo(skb)->frags[j], 0); + skb_frag_fill_page_desc(&skb_shinfo(skb)->frags[j], + page_info->page, + page_info->page_offset, + curr_frag_len); skb_shinfo(skb)->nr_frags++; } else { put_page(page_info->page); + skb_frag_size_add(&skb_shinfo(skb)->frags[j], + curr_frag_len); } - skb_frag_size_add(&skb_shinfo(skb)->frags[j], curr_frag_len); skb->len += curr_frag_len; skb->data_len += curr_frag_len; skb->truesize += rx_frag_size; @@ -2451,14 +2451,16 @@ static void be_rx_compl_process_gro(struct be_rx_obj *rxo, if (i == 0 || page_info->page_offset == 0) { /* First frag or Fresh page */ j++; - skb_frag_set_page(skb, j, page_info->page); - skb_frag_off_set(&skb_shinfo(skb)->frags[j], - page_info->page_offset); - skb_frag_size_set(&skb_shinfo(skb)->frags[j], 0); + skb_frag_fill_page_desc(&skb_shinfo(skb)->frags[j], + page_info->page, + page_info->page_offset, + curr_frag_len); } else { put_page(page_info->page); + skb_frag_size_add(&skb_shinfo(skb)->frags[j], + curr_frag_len); } - skb_frag_size_add(&skb_shinfo(skb)->frags[j], curr_frag_len); + skb->truesize += rx_frag_size; remaining -= curr_frag_len; memset(page_info, 0, sizeof(*page_info)); diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 3c4fa26f0f9b..63854294ac33 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -1445,9 +1445,8 @@ static void enetc_add_rx_buff_to_xdp(struct enetc_bdr *rx_ring, int i, xdp_buff_set_frag_pfmemalloc(xdp_buff); frag = &shinfo->frags[shinfo->nr_frags]; - skb_frag_off_set(frag, rx_swbd->page_offset); - skb_frag_size_set(frag, size); - __skb_frag_set_page(frag, rx_swbd->page); + skb_frag_fill_page_desc(frag, rx_swbd->page, rx_swbd->page_offset, + size); shinfo->nr_frags++; } diff --git a/drivers/net/ethernet/fungible/funeth/funeth_rx.c b/drivers/net/ethernet/fungible/funeth/funeth_rx.c index 29a6c2ede43a..7e2584895de3 100644 --- a/drivers/net/ethernet/fungible/funeth/funeth_rx.c +++ b/drivers/net/ethernet/fungible/funeth/funeth_rx.c @@ -323,9 +323,8 @@ static int fun_gather_pkt(struct funeth_rxq *q, unsigned int tot_len, if (ref_ok) ref_ok |= buf->node; - __skb_frag_set_page(frags, buf->page); - skb_frag_off_set(frags, q->buf_offset); - skb_frag_size_set(frags++, frag_len); + skb_frag_fill_page_desc(frags++, buf->page, q->buf_offset, + frag_len); tot_len -= frag_len; if (!tot_len) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 6c6b66d3ea6e..e2abc00d0472 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -2376,9 +2376,8 @@ mvneta_swbm_add_rx_fragment(struct mvneta_port *pp, if (data_len > 0 && sinfo->nr_frags < MAX_SKB_FRAGS) { skb_frag_t *frag = &sinfo->frags[sinfo->nr_frags++]; - skb_frag_off_set(frag, pp->rx_offset_correction); - skb_frag_size_set(frag, data_len); - __skb_frag_set_page(frag, page); + skb_frag_fill_page_desc(frag, page, + pp->rx_offset_correction, data_len); if (!xdp_buff_has_frags(xdp)) { sinfo->xdp_frags_size = *size; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 69634829558e..704b022cd1f0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -491,9 +491,7 @@ mlx5e_add_skb_shared_info_frag(struct mlx5e_rq *rq, struct skb_shared_info *sinf } frag = &sinfo->frags[sinfo->nr_frags++]; - __skb_frag_set_page(frag, frag_page->page); - skb_frag_off_set(frag, frag_offset); - skb_frag_size_set(frag, len); + skb_frag_fill_page_desc(frag, frag_page->page, frag_offset, len); if (page_is_pfmemalloc(frag_page->page)) xdp_buff_set_frag_pfmemalloc(xdp); diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c index 4ef05bad4613..2d52f54ebb45 100644 --- a/drivers/net/ethernet/sun/cassini.c +++ b/drivers/net/ethernet/sun/cassini.c @@ -1998,10 +1998,8 @@ static int cas_rx_process_pkt(struct cas *cp, struct cas_rx_comp *rxc, skb->truesize += hlen - swivel; skb->len += hlen - swivel; - __skb_frag_set_page(frag, page->buffer); + skb_frag_fill_page_desc(frag, page->buffer, off, hlen - swivel); __skb_frag_ref(frag); - skb_frag_off_set(frag, off); - skb_frag_size_set(frag, hlen - swivel); /* any more data? */ if ((words[0] & RX_COMP1_SPLIT_PKT) && ((dlen -= hlen) > 0)) { @@ -2024,10 +2022,8 @@ static int cas_rx_process_pkt(struct cas *cp, struct cas_rx_comp *rxc, skb->len += hlen; frag++; - __skb_frag_set_page(frag, page->buffer); + skb_frag_fill_page_desc(frag, page->buffer, 0, hlen); __skb_frag_ref(frag); - skb_frag_off_set(frag, 0); - skb_frag_size_set(frag, hlen); RX_USED_ADD(page, hlen + cp->crc_size); } diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 97241006d64a..29eccc8ff41f 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1272,9 +1272,7 @@ static int virtnet_build_xdp_buff_mrg(struct net_device *dev, } frag = &shinfo->frags[shinfo->nr_frags++]; - __skb_frag_set_page(frag, page); - skb_frag_off_set(frag, offset); - skb_frag_size_set(frag, len); + skb_frag_fill_page_desc(frag, page, offset, len); if (page_is_pfmemalloc(page)) xdp_buff_set_frag_pfmemalloc(xdp); diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index f2b76ee866a4..7fa74b8b2100 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -686,9 +686,7 @@ vmxnet3_append_frag(struct sk_buff *skb, struct Vmxnet3_RxCompDesc *rcd, BUG_ON(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS); - __skb_frag_set_page(frag, rbi->page); - skb_frag_off_set(frag, 0); - skb_frag_size_set(frag, rcd->len); + skb_frag_fill_page_desc(frag, rbi->page, 0, rcd->len); skb->data_len += rcd->len; skb->truesize += PAGE_SIZE; skb_shinfo(skb)->nr_frags++; diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index c1501f41e2d8..3d79b35eb577 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -1128,9 +1128,7 @@ static int xenvif_handle_frag_list(struct xenvif_queue *queue, struct sk_buff *s BUG(); offset += len; - __skb_frag_set_page(&frags[i], page); - skb_frag_off_set(&frags[i], 0); - skb_frag_size_set(&frags[i], len); + skb_frag_fill_page_desc(&frags[i], page, 0, len); } /* Release all the original (foreign) frags. */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 738776ab8838..30be21c7d05f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2411,6 +2411,15 @@ static inline unsigned int skb_pagelen(const struct sk_buff *skb) return skb_headlen(skb) + __skb_pagelen(skb); } +static inline void skb_frag_fill_page_desc(skb_frag_t *frag, + struct page *page, + int off, int size) +{ + frag->bv_page = page; + frag->bv_offset = off; + skb_frag_size_set(frag, size); +} + static inline void __skb_fill_page_desc_noacc(struct skb_shared_info *shinfo, int i, struct page *page, int off, int size) @@ -2422,9 +2431,7 @@ static inline void __skb_fill_page_desc_noacc(struct skb_shared_info *shinfo, * that not all callers have unique ownership of the page but rely * on page_is_pfmemalloc doing the right thing(tm). */ - frag->bv_page = page; - frag->bv_offset = off; - skb_frag_size_set(frag, size); + skb_frag_fill_page_desc(frag, page, off, size); } /** @@ -3496,20 +3503,6 @@ static inline void __skb_frag_set_page(skb_frag_t *frag, struct page *page) frag->bv_page = page; } -/** - * skb_frag_set_page - sets the page contained in a paged fragment of an skb - * @skb: the buffer - * @f: the fragment offset - * @page: the page to set - * - * Sets the @f'th fragment of @skb to contain @page. - */ -static inline void skb_frag_set_page(struct sk_buff *skb, int f, - struct page *page) -{ - __skb_frag_set_page(&skb_shinfo(skb)->frags[f], page); -} - bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio); /** diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index e79e3a415ca9..98143b86a9dd 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -1415,11 +1415,10 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, } frag = &sinfo->frags[sinfo->nr_frags++]; - __skb_frag_set_page(frag, page); data_len = min_t(u32, kattr->test.data_size_in - size, PAGE_SIZE); - skb_frag_size_set(frag, data_len); + skb_frag_fill_page_desc(frag, page, 0, data_len); if (copy_from_user(page_address(page), data_in + size, data_len)) { diff --git a/net/core/gro.c b/net/core/gro.c index 2d84165cb4f1..6783a47a6136 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -239,9 +239,7 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) pinfo->nr_frags = nr_frags + 1 + skbinfo->nr_frags; - __skb_frag_set_page(frag, page); - skb_frag_off_set(frag, first_offset); - skb_frag_size_set(frag, first_size); + skb_frag_fill_page_desc(frag, page, first_offset, first_size); memcpy(frag + 1, skbinfo->frags, sizeof(*frag) * skbinfo->nr_frags); /* We dont need to clear skbinfo->nr_frags here */ diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 760238196db1..f56b8d697014 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2785,14 +2785,17 @@ static void pktgen_finalize_skb(struct pktgen_dev *pkt_dev, struct sk_buff *skb, break; } get_page(pkt_dev->page); - skb_frag_set_page(skb, i, pkt_dev->page); - skb_frag_off_set(&skb_shinfo(skb)->frags[i], 0); + /*last fragment, fill rest of data*/ if (i == (frags - 1)) - skb_frag_size_set(&skb_shinfo(skb)->frags[i], - (datalen < PAGE_SIZE ? datalen : PAGE_SIZE)); + skb_frag_fill_page_desc(&skb_shinfo(skb)->frags[i], + pkt_dev->page, 0, + (datalen < PAGE_SIZE ? + datalen : PAGE_SIZE)); else - skb_frag_size_set(&skb_shinfo(skb)->frags[i], frag_len); + skb_frag_fill_page_desc(&skb_shinfo(skb)->frags[i], + pkt_dev->page, 0, frag_len); + datalen -= skb_frag_size(&skb_shinfo(skb)->frags[i]); skb->len += skb_frag_size(&skb_shinfo(skb)->frags[i]); skb->data_len += skb_frag_size(&skb_shinfo(skb)->frags[i]); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 01b48e68aca0..6724a84ebb09 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4234,10 +4234,9 @@ static inline skb_frag_t skb_head_frag_to_page_desc(struct sk_buff *frag_skb) struct page *page; page = virt_to_head_page(frag_skb->head); - __skb_frag_set_page(&head_frag, page); - skb_frag_off_set(&head_frag, frag_skb->data - - (unsigned char *)page_address(page)); - skb_frag_size_set(&head_frag, skb_headlen(frag_skb)); + skb_frag_fill_page_desc(&head_frag, page, frag_skb->data - + (unsigned char *)page_address(page), + skb_headlen(frag_skb)); return head_frag; } diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index a7cc4f9faac2..daeff54bdbfa 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -268,9 +268,8 @@ static void tls_append_frag(struct tls_record_info *record, skb_frag_size_add(frag, size); } else { ++frag; - __skb_frag_set_page(frag, pfrag->page); - skb_frag_off_set(frag, pfrag->offset); - skb_frag_size_set(frag, size); + skb_frag_fill_page_desc(frag, pfrag->page, pfrag->offset, + size); ++record->num_frags; get_page(pfrag->page); } @@ -357,9 +356,8 @@ static int tls_create_new_record(struct tls_offload_context_tx *offload_ctx, return -ENOMEM; frag = &record->frags[0]; - __skb_frag_set_page(frag, pfrag->page); - skb_frag_off_set(frag, pfrag->offset); - skb_frag_size_set(frag, prepend_size); + skb_frag_fill_page_desc(frag, pfrag->page, pfrag->offset, + prepend_size); get_page(pfrag->page); pfrag->offset += prepend_size; diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c index 80143360bf09..9c0fa0e1786a 100644 --- a/net/xfrm/xfrm_ipcomp.c +++ b/net/xfrm/xfrm_ipcomp.c @@ -74,14 +74,11 @@ static int ipcomp_decompress(struct xfrm_state *x, struct sk_buff *skb) if (!page) return -ENOMEM; - __skb_frag_set_page(frag, page); - len = PAGE_SIZE; if (dlen < len) len = dlen; - skb_frag_off_set(frag, 0); - skb_frag_size_set(frag, len); + skb_frag_fill_page_desc(frag, page, 0, len); memcpy(skb_frag_address(frag), scratch, len); skb->truesize += len; -- cgit v1.2.3 From 278fda0d52f67244044384abd7dd5b3a5b3a5604 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Thu, 11 May 2023 09:12:13 +0800 Subject: net: remove __skb_frag_set_page() The remaining users calling __skb_frag_set_page() with page being NULL seems to be doing defensive programming, as shinfo->nr_frags is already decremented, so remove them. Signed-off-by: Yunsheng Lin Reviewed-by: Leon Romanovsky Reviewed-by: Michael Chan Reviewed-by: Jesse Brandeburg Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2.c | 1 - drivers/net/ethernet/broadcom/bnxt/bnxt.c | 5 +---- include/linux/skbuff.h | 12 ------------ 3 files changed, 1 insertion(+), 17 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c index 466e1d62bcf6..0d917a9699c5 100644 --- a/drivers/net/ethernet/broadcom/bnx2.c +++ b/drivers/net/ethernet/broadcom/bnx2.c @@ -2955,7 +2955,6 @@ bnx2_reuse_rx_skb_pages(struct bnx2 *bp, struct bnx2_rx_ring_info *rxr, shinfo = skb_shinfo(skb); shinfo->nr_frags--; page = skb_frag_page(&shinfo->frags[shinfo->nr_frags]); - __skb_frag_set_page(&shinfo->frags[shinfo->nr_frags], NULL); cons_rx_pg->page = page; dev_kfree_skb(skb); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index efaff5018af8..f42e51bd3e42 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1102,10 +1102,7 @@ static u32 __bnxt_rx_agg_pages(struct bnxt *bp, xdp_buff_set_frag_pfmemalloc(xdp); if (bnxt_alloc_rx_page(bp, rxr, prod, GFP_ATOMIC) != 0) { - unsigned int nr_frags; - - nr_frags = --shinfo->nr_frags; - __skb_frag_set_page(&shinfo->frags[nr_frags], NULL); + --shinfo->nr_frags; cons_rx_buf->page = page; /* Update prod since possibly some pages have been diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 30be21c7d05f..00e8c435fa1a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3491,18 +3491,6 @@ static inline void skb_frag_page_copy(skb_frag_t *fragto, fragto->bv_page = fragfrom->bv_page; } -/** - * __skb_frag_set_page - sets the page contained in a paged fragment - * @frag: the paged fragment - * @page: the page to set - * - * Sets the fragment @frag to contain @page. - */ -static inline void __skb_frag_set_page(skb_frag_t *frag, struct page *page) -{ - frag->bv_page = page; -} - bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio); /** -- cgit v1.2.3 From a0b7955310a445fc0d45a0ac576bad8720cd6057 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Fri, 12 May 2023 17:58:37 +0100 Subject: net: phylink: constify fwnode arguments Both phylink_create() and phylink_fwnode_phy_connect() do not modify the fwnode argument that they are passed, so lets constify these. Reviewed-by: Simon Horman Signed-off-by: Russell King (Oracle) Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 11 ++++++----- include/linux/phylink.h | 9 +++++---- 2 files changed, 11 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index a4111f1be375..cf53096047e6 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -708,7 +708,7 @@ static int phylink_validate(struct phylink *pl, unsigned long *supported, } static int phylink_parse_fixedlink(struct phylink *pl, - struct fwnode_handle *fwnode) + const struct fwnode_handle *fwnode) { struct fwnode_handle *fixed_node; bool pause, asym_pause, autoneg; @@ -819,7 +819,8 @@ static int phylink_parse_fixedlink(struct phylink *pl, return 0; } -static int phylink_parse_mode(struct phylink *pl, struct fwnode_handle *fwnode) +static int phylink_parse_mode(struct phylink *pl, + const struct fwnode_handle *fwnode) { struct fwnode_handle *dn; const char *managed; @@ -1441,7 +1442,7 @@ static void phylink_fixed_poll(struct timer_list *t) static const struct sfp_upstream_ops sfp_phylink_ops; static int phylink_register_sfp(struct phylink *pl, - struct fwnode_handle *fwnode) + const struct fwnode_handle *fwnode) { struct sfp_bus *bus; int ret; @@ -1480,7 +1481,7 @@ static int phylink_register_sfp(struct phylink *pl, * must use IS_ERR() to check for errors from this function. */ struct phylink *phylink_create(struct phylink_config *config, - struct fwnode_handle *fwnode, + const struct fwnode_handle *fwnode, phy_interface_t iface, const struct phylink_mac_ops *mac_ops) { @@ -1809,7 +1810,7 @@ EXPORT_SYMBOL_GPL(phylink_of_phy_connect); * Returns 0 on success or a negative errno. */ int phylink_fwnode_phy_connect(struct phylink *pl, - struct fwnode_handle *fwnode, + const struct fwnode_handle *fwnode, u32 flags) { struct fwnode_handle *phy_fwnode; diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 71755c66c162..bb782f05ad08 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -568,16 +568,17 @@ void phylink_generic_validate(struct phylink_config *config, unsigned long *supported, struct phylink_link_state *state); -struct phylink *phylink_create(struct phylink_config *, struct fwnode_handle *, - phy_interface_t iface, - const struct phylink_mac_ops *mac_ops); +struct phylink *phylink_create(struct phylink_config *, + const struct fwnode_handle *, + phy_interface_t, + const struct phylink_mac_ops *); void phylink_destroy(struct phylink *); bool phylink_expects_phy(struct phylink *pl); int phylink_connect_phy(struct phylink *, struct phy_device *); int phylink_of_phy_connect(struct phylink *, struct device_node *, u32 flags); int phylink_fwnode_phy_connect(struct phylink *pl, - struct fwnode_handle *fwnode, + const struct fwnode_handle *fwnode, u32 flags); void phylink_disconnect_phy(struct phylink *); -- cgit v1.2.3 From a7eb54d44045d424624d3ac7d02feb8ef96744ec Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Fri, 12 May 2023 22:46:46 +0200 Subject: ata: libata: Make ata_platform_remove_one return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The function returned zero unconditionally, so the function returning an int is something between useless and irritating. With the goal to make platform drivers' remove function return void, it's helpful to convert the function accordingly. This converts several drivers to the new .remove_new callback that was introduced to smoothen the platform driver conversion. Signed-off-by: Uwe Kleine-König Acked-by: Jernej Skrabec Acked-by: Serge Semin Reviewed-by: Sergey Shtylyov Signed-off-by: Damien Le Moal --- drivers/ata/ahci_brcm.c | 6 +++--- drivers/ata/ahci_ceva.c | 2 +- drivers/ata/ahci_da850.c | 2 +- drivers/ata/ahci_dm816.c | 2 +- drivers/ata/ahci_dwc.c | 2 +- drivers/ata/ahci_imx.c | 2 +- drivers/ata/ahci_mtk.c | 2 +- drivers/ata/ahci_mvebu.c | 2 +- drivers/ata/ahci_platform.c | 2 +- drivers/ata/ahci_qoriq.c | 2 +- drivers/ata/ahci_seattle.c | 2 +- drivers/ata/ahci_st.c | 2 +- drivers/ata/ahci_sunxi.c | 2 +- drivers/ata/ahci_tegra.c | 2 +- drivers/ata/ahci_xgene.c | 2 +- drivers/ata/libata-core.c | 4 +--- drivers/ata/pata_ixp4xx_cf.c | 2 +- drivers/ata/pata_of_platform.c | 2 +- drivers/ata/pata_platform.c | 2 +- drivers/ata/sata_highbank.c | 2 +- include/linux/libata.h | 2 +- 21 files changed, 23 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/ahci_brcm.c b/drivers/ata/ahci_brcm.c index 4e3dc2b6d67f..70c3a33eee6f 100644 --- a/drivers/ata/ahci_brcm.c +++ b/drivers/ata/ahci_brcm.c @@ -544,7 +544,7 @@ out_reset: return ret; } -static int brcm_ahci_remove(struct platform_device *pdev) +static void brcm_ahci_remove(struct platform_device *pdev) { struct ata_host *host = dev_get_drvdata(&pdev->dev); struct ahci_host_priv *hpriv = host->private_data; @@ -552,7 +552,7 @@ static int brcm_ahci_remove(struct platform_device *pdev) brcm_sata_phys_disable(priv); - return ata_platform_remove_one(pdev); + ata_platform_remove_one(pdev); } static void brcm_ahci_shutdown(struct platform_device *pdev) @@ -573,7 +573,7 @@ static SIMPLE_DEV_PM_OPS(ahci_brcm_pm_ops, brcm_ahci_suspend, brcm_ahci_resume); static struct platform_driver brcm_ahci_driver = { .probe = brcm_ahci_probe, - .remove = brcm_ahci_remove, + .remove_new = brcm_ahci_remove, .shutdown = brcm_ahci_shutdown, .driver = { .name = DRV_NAME, diff --git a/drivers/ata/ahci_ceva.c b/drivers/ata/ahci_ceva.c index bc027468decb..c2b6be083af4 100644 --- a/drivers/ata/ahci_ceva.c +++ b/drivers/ata/ahci_ceva.c @@ -369,7 +369,7 @@ MODULE_DEVICE_TABLE(of, ceva_ahci_of_match); static struct platform_driver ceva_ahci_driver = { .probe = ceva_ahci_probe, - .remove = ata_platform_remove_one, + .remove_new = ata_platform_remove_one, .driver = { .name = DRV_NAME, .of_match_table = ceva_ahci_of_match, diff --git a/drivers/ata/ahci_da850.c b/drivers/ata/ahci_da850.c index ca0924dc5bd2..55a6627d5450 100644 --- a/drivers/ata/ahci_da850.c +++ b/drivers/ata/ahci_da850.c @@ -238,7 +238,7 @@ MODULE_DEVICE_TABLE(of, ahci_da850_of_match); static struct platform_driver ahci_da850_driver = { .probe = ahci_da850_probe, - .remove = ata_platform_remove_one, + .remove_new = ata_platform_remove_one, .driver = { .name = DRV_NAME, .of_match_table = ahci_da850_of_match, diff --git a/drivers/ata/ahci_dm816.c b/drivers/ata/ahci_dm816.c index b08547b877a1..4cb70064fb99 100644 --- a/drivers/ata/ahci_dm816.c +++ b/drivers/ata/ahci_dm816.c @@ -182,7 +182,7 @@ MODULE_DEVICE_TABLE(of, ahci_dm816_of_match); static struct platform_driver ahci_dm816_driver = { .probe = ahci_dm816_probe, - .remove = ata_platform_remove_one, + .remove_new = ata_platform_remove_one, .driver = { .name = AHCI_DM816_DRV_NAME, .of_match_table = ahci_dm816_of_match, diff --git a/drivers/ata/ahci_dwc.c b/drivers/ata/ahci_dwc.c index 4bfbb09cdc02..9604a2f6ed48 100644 --- a/drivers/ata/ahci_dwc.c +++ b/drivers/ata/ahci_dwc.c @@ -478,7 +478,7 @@ MODULE_DEVICE_TABLE(of, ahci_dwc_of_match); static struct platform_driver ahci_dwc_driver = { .probe = ahci_dwc_probe, - .remove = ata_platform_remove_one, + .remove_new = ata_platform_remove_one, .shutdown = ahci_platform_shutdown, .driver = { .name = DRV_NAME, diff --git a/drivers/ata/ahci_imx.c b/drivers/ata/ahci_imx.c index 3a8c248e7c0e..9fa005965f3b 100644 --- a/drivers/ata/ahci_imx.c +++ b/drivers/ata/ahci_imx.c @@ -1223,7 +1223,7 @@ static SIMPLE_DEV_PM_OPS(ahci_imx_pm_ops, imx_ahci_suspend, imx_ahci_resume); static struct platform_driver imx_ahci_driver = { .probe = imx_ahci_probe, - .remove = ata_platform_remove_one, + .remove_new = ata_platform_remove_one, .driver = { .name = DRV_NAME, .of_match_table = imx_ahci_of_match, diff --git a/drivers/ata/ahci_mtk.c b/drivers/ata/ahci_mtk.c index 0bf83a297091..5083fb6c4927 100644 --- a/drivers/ata/ahci_mtk.c +++ b/drivers/ata/ahci_mtk.c @@ -173,7 +173,7 @@ MODULE_DEVICE_TABLE(of, ahci_of_match); static struct platform_driver mtk_ahci_driver = { .probe = mtk_ahci_probe, - .remove = ata_platform_remove_one, + .remove_new = ata_platform_remove_one, .driver = { .name = DRV_NAME, .of_match_table = ahci_of_match, diff --git a/drivers/ata/ahci_mvebu.c b/drivers/ata/ahci_mvebu.c index 596cf017f427..764501518582 100644 --- a/drivers/ata/ahci_mvebu.c +++ b/drivers/ata/ahci_mvebu.c @@ -245,7 +245,7 @@ MODULE_DEVICE_TABLE(of, ahci_mvebu_of_match); static struct platform_driver ahci_mvebu_driver = { .probe = ahci_mvebu_probe, - .remove = ata_platform_remove_one, + .remove_new = ata_platform_remove_one, .suspend = ahci_mvebu_suspend, .resume = ahci_mvebu_resume, .driver = { diff --git a/drivers/ata/ahci_platform.c b/drivers/ata/ahci_platform.c index 299ee686ac49..ab30c7138d73 100644 --- a/drivers/ata/ahci_platform.c +++ b/drivers/ata/ahci_platform.c @@ -96,7 +96,7 @@ MODULE_DEVICE_TABLE(acpi, ahci_acpi_match); static struct platform_driver ahci_driver = { .probe = ahci_probe, - .remove = ata_platform_remove_one, + .remove_new = ata_platform_remove_one, .shutdown = ahci_platform_shutdown, .driver = { .name = DRV_NAME, diff --git a/drivers/ata/ahci_qoriq.c b/drivers/ata/ahci_qoriq.c index 0ba764d283c8..3d01b118c9a1 100644 --- a/drivers/ata/ahci_qoriq.c +++ b/drivers/ata/ahci_qoriq.c @@ -359,7 +359,7 @@ static SIMPLE_DEV_PM_OPS(ahci_qoriq_pm_ops, ahci_platform_suspend, static struct platform_driver ahci_qoriq_driver = { .probe = ahci_qoriq_probe, - .remove = ata_platform_remove_one, + .remove_new = ata_platform_remove_one, .driver = { .name = DRV_NAME, .of_match_table = ahci_qoriq_of_match, diff --git a/drivers/ata/ahci_seattle.c b/drivers/ata/ahci_seattle.c index 9eda7bbd2151..2c32d58c6ae7 100644 --- a/drivers/ata/ahci_seattle.c +++ b/drivers/ata/ahci_seattle.c @@ -187,7 +187,7 @@ MODULE_DEVICE_TABLE(acpi, ahci_acpi_match); static struct platform_driver ahci_seattle_driver = { .probe = ahci_seattle_probe, - .remove = ata_platform_remove_one, + .remove_new = ata_platform_remove_one, .driver = { .name = DRV_NAME, .acpi_match_table = ahci_acpi_match, diff --git a/drivers/ata/ahci_st.c b/drivers/ata/ahci_st.c index f2c1edb36986..d4a626f87963 100644 --- a/drivers/ata/ahci_st.c +++ b/drivers/ata/ahci_st.c @@ -239,7 +239,7 @@ static struct platform_driver st_ahci_driver = { .of_match_table = st_ahci_match, }, .probe = st_ahci_probe, - .remove = ata_platform_remove_one, + .remove_new = ata_platform_remove_one, }; module_platform_driver(st_ahci_driver); diff --git a/drivers/ata/ahci_sunxi.c b/drivers/ata/ahci_sunxi.c index 076c12b4ba08..04531fa95e40 100644 --- a/drivers/ata/ahci_sunxi.c +++ b/drivers/ata/ahci_sunxi.c @@ -292,7 +292,7 @@ MODULE_DEVICE_TABLE(of, ahci_sunxi_of_match); static struct platform_driver ahci_sunxi_driver = { .probe = ahci_sunxi_probe, - .remove = ata_platform_remove_one, + .remove_new = ata_platform_remove_one, .driver = { .name = DRV_NAME, .of_match_table = ahci_sunxi_of_match, diff --git a/drivers/ata/ahci_tegra.c b/drivers/ata/ahci_tegra.c index 8e5e2b359f2d..21c20793e517 100644 --- a/drivers/ata/ahci_tegra.c +++ b/drivers/ata/ahci_tegra.c @@ -609,7 +609,7 @@ deinit_controller: static struct platform_driver tegra_ahci_driver = { .probe = tegra_ahci_probe, - .remove = ata_platform_remove_one, + .remove_new = ata_platform_remove_one, .driver = { .name = DRV_NAME, .of_match_table = tegra_ahci_of_match, diff --git a/drivers/ata/ahci_xgene.c b/drivers/ata/ahci_xgene.c index 83f5ff54ef5b..eb773f2e28fc 100644 --- a/drivers/ata/ahci_xgene.c +++ b/drivers/ata/ahci_xgene.c @@ -868,7 +868,7 @@ disable_resources: static struct platform_driver xgene_ahci_driver = { .probe = xgene_ahci_probe, - .remove = ata_platform_remove_one, + .remove_new = ata_platform_remove_one, .driver = { .name = DRV_NAME, .of_match_table = xgene_ahci_of_match, diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 8bf612bdd61a..e9fc69fbe06b 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -6141,13 +6141,11 @@ EXPORT_SYMBOL_GPL(ata_pci_device_resume); * LOCKING: * Inherited from platform layer (may sleep). */ -int ata_platform_remove_one(struct platform_device *pdev) +void ata_platform_remove_one(struct platform_device *pdev) { struct ata_host *host = platform_get_drvdata(pdev); ata_host_detach(host); - - return 0; } EXPORT_SYMBOL_GPL(ata_platform_remove_one); diff --git a/drivers/ata/pata_ixp4xx_cf.c b/drivers/ata/pata_ixp4xx_cf.c index 99a2ce723495..b1daa4d3fcd9 100644 --- a/drivers/ata/pata_ixp4xx_cf.c +++ b/drivers/ata/pata_ixp4xx_cf.c @@ -303,7 +303,7 @@ static struct platform_driver ixp4xx_pata_platform_driver = { .of_match_table = ixp4xx_pata_of_match, }, .probe = ixp4xx_pata_probe, - .remove = ata_platform_remove_one, + .remove_new = ata_platform_remove_one, }; module_platform_driver(ixp4xx_pata_platform_driver); diff --git a/drivers/ata/pata_of_platform.c b/drivers/ata/pata_of_platform.c index 178b28eff170..4956f0f5b93f 100644 --- a/drivers/ata/pata_of_platform.c +++ b/drivers/ata/pata_of_platform.c @@ -89,7 +89,7 @@ static struct platform_driver pata_of_platform_driver = { .of_match_table = pata_of_platform_match, }, .probe = pata_of_platform_probe, - .remove = ata_platform_remove_one, + .remove_new = ata_platform_remove_one, }; module_platform_driver(pata_of_platform_driver); diff --git a/drivers/ata/pata_platform.c b/drivers/ata/pata_platform.c index 87479bc893b2..232c3dad7ee8 100644 --- a/drivers/ata/pata_platform.c +++ b/drivers/ata/pata_platform.c @@ -223,7 +223,7 @@ static int pata_platform_probe(struct platform_device *pdev) static struct platform_driver pata_platform_driver = { .probe = pata_platform_probe, - .remove = ata_platform_remove_one, + .remove_new = ata_platform_remove_one, .driver = { .name = DRV_NAME, }, diff --git a/drivers/ata/sata_highbank.c b/drivers/ata/sata_highbank.c index 8237ece4a46f..d6b324d03e59 100644 --- a/drivers/ata/sata_highbank.c +++ b/drivers/ata/sata_highbank.c @@ -614,7 +614,7 @@ static SIMPLE_DEV_PM_OPS(ahci_highbank_pm_ops, ahci_highbank_suspend, ahci_highbank_resume); static struct platform_driver ahci_highbank_driver = { - .remove = ata_platform_remove_one, + .remove_new = ata_platform_remove_one, .driver = { .name = "highbank-ahci", .of_match_table = ahci_of_match, diff --git a/include/linux/libata.h b/include/linux/libata.h index 311cd93377c7..01f9fbb69f89 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1276,7 +1276,7 @@ extern int ata_pci_device_resume(struct pci_dev *pdev); struct platform_device; -extern int ata_platform_remove_one(struct platform_device *pdev); +extern void ata_platform_remove_one(struct platform_device *pdev); /* * ACPI - drivers/ata/libata-acpi.c -- cgit v1.2.3 From 38f1755a3e59a3f88e33030f8e4ee0421de2f05a Mon Sep 17 00:00:00 2001 From: Min-Hua Chen Date: Fri, 12 May 2023 00:46:25 +0800 Subject: fs: use correct __poll_t type Fix the following sparse warnings by using __poll_t instead of unsigned type. fs/eventpoll.c:541:9: sparse: warning: restricted __poll_t degrades to integer fs/eventfd.c:67:17: sparse: warning: restricted __poll_t degrades to integer Signed-off-by: Min-Hua Chen Message-Id: <20230511164628.336586-1-minhuadotchen@gmail.com> Signed-off-by: Christian Brauner --- fs/eventfd.c | 2 +- fs/eventpoll.c | 2 +- include/linux/eventfd.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/fs/eventfd.c b/fs/eventfd.c index 95850a13ce8d..6c06a527747f 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -43,7 +43,7 @@ struct eventfd_ctx { int id; }; -__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, unsigned mask) +__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, __poll_t mask) { unsigned long flags; diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 980483455cc0..e0eabaae7402 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -536,7 +536,7 @@ static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi, #else static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi, - unsigned pollflags) + __poll_t pollflags) { wake_up_poll(&ep->poll_wait, EPOLLIN | pollflags); } diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index 36a486505b08..98d31cdaca40 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -40,7 +40,7 @@ struct file *eventfd_fget(int fd); struct eventfd_ctx *eventfd_ctx_fdget(int fd); struct eventfd_ctx *eventfd_ctx_fileget(struct file *file); __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n); -__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, unsigned mask); +__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, __poll_t mask); int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait, __u64 *cnt); void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt); -- cgit v1.2.3 From 6f0621238b7e7680d5e26c00aa4cd473314d05b2 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 12 May 2023 23:07:27 +0200 Subject: cpu/hotplug: Add CPU state tracking and synchronization The CPU state tracking and synchronization mechanism in smpboot.c is completely independent of the hotplug code and all logic around it is implemented in architecture specific code. Except for the state reporting of the AP there is absolutely nothing architecture specific and the sychronization and decision functions can be moved into the generic hotplug core code. Provide an integrated variant and add the core synchronization and decision points. This comes in two flavours: 1) DEAD state synchronization Updated by the architecture code once the AP reaches the point where it is ready to be torn down by the control CPU, e.g. by removing power or clocks or tear down via the hypervisor. The control CPU waits for this state to be reached with a timeout. If the state is reached an architecture specific cleanup function is invoked. 2) Full state synchronization This extends #1 with AP alive synchronization. This is new functionality, which allows to replace architecture specific wait mechanims, e.g. cpumasks, completely. It also prevents that an AP which is in a limbo state can be brought up again. This can happen when an AP failed to report dead state during a previous off-line operation. The dead synchronization is what most architectures use. Only x86 makes a bringup decision based on that state at the moment. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Tested-by: Michael Kelley Tested-by: Oleksandr Natalenko Tested-by: Helge Deller # parisc Tested-by: Guilherme G. Piccoli # Steam Deck Link: https://lore.kernel.org/r/20230512205256.476305035@linutronix.de --- arch/Kconfig | 15 ++++ include/linux/cpuhotplug.h | 12 +++ kernel/cpu.c | 193 ++++++++++++++++++++++++++++++++++++++++++++- kernel/smpboot.c | 2 + 4 files changed, 221 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/arch/Kconfig b/arch/Kconfig index 205fd23e0cad..f55c5fcbea38 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -34,6 +34,21 @@ config ARCH_HAS_SUBPAGE_FAULTS config HOTPLUG_SMT bool +# Selected by HOTPLUG_CORE_SYNC_DEAD or HOTPLUG_CORE_SYNC_FULL +config HOTPLUG_CORE_SYNC + bool + +# Basic CPU dead synchronization selected by architecture +config HOTPLUG_CORE_SYNC_DEAD + bool + select HOTPLUG_CORE_SYNC + +# Full CPU synchronization with alive state selected by architecture +config HOTPLUG_CORE_SYNC_FULL + bool + select HOTPLUG_CORE_SYNC_DEAD if HOTPLUG_CPU + select HOTPLUG_CORE_SYNC + config GENERIC_ENTRY bool diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 0f1001dca0e0..5def71f81ec5 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -517,4 +517,16 @@ void cpuhp_online_idle(enum cpuhp_state state); static inline void cpuhp_online_idle(enum cpuhp_state state) { } #endif +void cpuhp_ap_sync_alive(void); +void arch_cpuhp_sync_state_poll(void); +void arch_cpuhp_cleanup_kick_cpu(unsigned int cpu); + +#ifdef CONFIG_HOTPLUG_CORE_SYNC_DEAD +void cpuhp_ap_report_dead(void); +void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu); +#else +static inline void cpuhp_ap_report_dead(void) { } +static inline void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu) { } +#endif + #endif diff --git a/kernel/cpu.c b/kernel/cpu.c index df8f137f0271..64b624291316 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -59,6 +60,7 @@ * @last: For multi-instance rollback, remember how far we got * @cb_state: The state for a single callback (install/uninstall) * @result: Result of the operation + * @ap_sync_state: State for AP synchronization * @done_up: Signal completion to the issuer of the task for cpu-up * @done_down: Signal completion to the issuer of the task for cpu-down */ @@ -76,6 +78,7 @@ struct cpuhp_cpu_state { struct hlist_node *last; enum cpuhp_state cb_state; int result; + atomic_t ap_sync_state; struct completion done_up; struct completion done_down; #endif @@ -276,6 +279,182 @@ static bool cpuhp_is_atomic_state(enum cpuhp_state state) return CPUHP_AP_IDLE_DEAD <= state && state < CPUHP_AP_ONLINE; } +/* Synchronization state management */ +enum cpuhp_sync_state { + SYNC_STATE_DEAD, + SYNC_STATE_KICKED, + SYNC_STATE_SHOULD_DIE, + SYNC_STATE_ALIVE, + SYNC_STATE_SHOULD_ONLINE, + SYNC_STATE_ONLINE, +}; + +#ifdef CONFIG_HOTPLUG_CORE_SYNC +/** + * cpuhp_ap_update_sync_state - Update synchronization state during bringup/teardown + * @state: The synchronization state to set + * + * No synchronization point. Just update of the synchronization state, but implies + * a full barrier so that the AP changes are visible before the control CPU proceeds. + */ +static inline void cpuhp_ap_update_sync_state(enum cpuhp_sync_state state) +{ + atomic_t *st = this_cpu_ptr(&cpuhp_state.ap_sync_state); + + (void)atomic_xchg(st, state); +} + +void __weak arch_cpuhp_sync_state_poll(void) { cpu_relax(); } + +static bool cpuhp_wait_for_sync_state(unsigned int cpu, enum cpuhp_sync_state state, + enum cpuhp_sync_state next_state) +{ + atomic_t *st = per_cpu_ptr(&cpuhp_state.ap_sync_state, cpu); + ktime_t now, end, start = ktime_get(); + int sync; + + end = start + 10ULL * NSEC_PER_SEC; + + sync = atomic_read(st); + while (1) { + if (sync == state) { + if (!atomic_try_cmpxchg(st, &sync, next_state)) + continue; + return true; + } + + now = ktime_get(); + if (now > end) { + /* Timeout. Leave the state unchanged */ + return false; + } else if (now - start < NSEC_PER_MSEC) { + /* Poll for one millisecond */ + arch_cpuhp_sync_state_poll(); + } else { + usleep_range_state(USEC_PER_MSEC, 2 * USEC_PER_MSEC, TASK_UNINTERRUPTIBLE); + } + sync = atomic_read(st); + } + return true; +} +#else /* CONFIG_HOTPLUG_CORE_SYNC */ +static inline void cpuhp_ap_update_sync_state(enum cpuhp_sync_state state) { } +#endif /* !CONFIG_HOTPLUG_CORE_SYNC */ + +#ifdef CONFIG_HOTPLUG_CORE_SYNC_DEAD +/** + * cpuhp_ap_report_dead - Update synchronization state to DEAD + * + * No synchronization point. Just update of the synchronization state. + */ +void cpuhp_ap_report_dead(void) +{ + cpuhp_ap_update_sync_state(SYNC_STATE_DEAD); +} + +void __weak arch_cpuhp_cleanup_dead_cpu(unsigned int cpu) { } + +/* + * Late CPU shutdown synchronization point. Cannot use cpuhp_state::done_down + * because the AP cannot issue complete() at this stage. + */ +static void cpuhp_bp_sync_dead(unsigned int cpu) +{ + atomic_t *st = per_cpu_ptr(&cpuhp_state.ap_sync_state, cpu); + int sync = atomic_read(st); + + do { + /* CPU can have reported dead already. Don't overwrite that! */ + if (sync == SYNC_STATE_DEAD) + break; + } while (!atomic_try_cmpxchg(st, &sync, SYNC_STATE_SHOULD_DIE)); + + if (cpuhp_wait_for_sync_state(cpu, SYNC_STATE_DEAD, SYNC_STATE_DEAD)) { + /* CPU reached dead state. Invoke the cleanup function */ + arch_cpuhp_cleanup_dead_cpu(cpu); + return; + } + + /* No further action possible. Emit message and give up. */ + pr_err("CPU%u failed to report dead state\n", cpu); +} +#else /* CONFIG_HOTPLUG_CORE_SYNC_DEAD */ +static inline void cpuhp_bp_sync_dead(unsigned int cpu) { } +#endif /* !CONFIG_HOTPLUG_CORE_SYNC_DEAD */ + +#ifdef CONFIG_HOTPLUG_CORE_SYNC_FULL +/** + * cpuhp_ap_sync_alive - Synchronize AP with the control CPU once it is alive + * + * Updates the AP synchronization state to SYNC_STATE_ALIVE and waits + * for the BP to release it. + */ +void cpuhp_ap_sync_alive(void) +{ + atomic_t *st = this_cpu_ptr(&cpuhp_state.ap_sync_state); + + cpuhp_ap_update_sync_state(SYNC_STATE_ALIVE); + + /* Wait for the control CPU to release it. */ + while (atomic_read(st) != SYNC_STATE_SHOULD_ONLINE) + cpu_relax(); +} + +static bool cpuhp_can_boot_ap(unsigned int cpu) +{ + atomic_t *st = per_cpu_ptr(&cpuhp_state.ap_sync_state, cpu); + int sync = atomic_read(st); + +again: + switch (sync) { + case SYNC_STATE_DEAD: + /* CPU is properly dead */ + break; + case SYNC_STATE_KICKED: + /* CPU did not come up in previous attempt */ + break; + case SYNC_STATE_ALIVE: + /* CPU is stuck cpuhp_ap_sync_alive(). */ + break; + default: + /* CPU failed to report online or dead and is in limbo state. */ + return false; + } + + /* Prepare for booting */ + if (!atomic_try_cmpxchg(st, &sync, SYNC_STATE_KICKED)) + goto again; + + return true; +} + +void __weak arch_cpuhp_cleanup_kick_cpu(unsigned int cpu) { } + +/* + * Early CPU bringup synchronization point. Cannot use cpuhp_state::done_up + * because the AP cannot issue complete() so early in the bringup. + */ +static int cpuhp_bp_sync_alive(unsigned int cpu) +{ + int ret = 0; + + if (!IS_ENABLED(CONFIG_HOTPLUG_CORE_SYNC_FULL)) + return 0; + + if (!cpuhp_wait_for_sync_state(cpu, SYNC_STATE_ALIVE, SYNC_STATE_SHOULD_ONLINE)) { + pr_err("CPU%u failed to report alive state\n", cpu); + ret = -EIO; + } + + /* Let the architecture cleanup the kick alive mechanics. */ + arch_cpuhp_cleanup_kick_cpu(cpu); + return ret; +} +#else /* CONFIG_HOTPLUG_CORE_SYNC_FULL */ +static inline int cpuhp_bp_sync_alive(unsigned int cpu) { return 0; } +static inline bool cpuhp_can_boot_ap(unsigned int cpu) { return true; } +#endif /* !CONFIG_HOTPLUG_CORE_SYNC_FULL */ + /* Serializes the updates to cpu_online_mask, cpu_present_mask */ static DEFINE_MUTEX(cpu_add_remove_lock); bool cpuhp_tasks_frozen; @@ -588,6 +767,9 @@ static int bringup_cpu(unsigned int cpu) struct task_struct *idle = idle_thread_get(cpu); int ret; + if (!cpuhp_can_boot_ap(cpu)) + return -EAGAIN; + /* * Reset stale stack state from the last time this CPU was online. */ @@ -610,6 +792,10 @@ static int bringup_cpu(unsigned int cpu) if (ret) goto out_unlock; + ret = cpuhp_bp_sync_alive(cpu); + if (ret) + goto out_unlock; + ret = bringup_wait_for_ap_online(cpu); if (ret) goto out_unlock; @@ -1113,6 +1299,8 @@ static int takedown_cpu(unsigned int cpu) /* This actually kills the CPU. */ __cpu_die(cpu); + cpuhp_bp_sync_dead(cpu); + tick_cleanup_dead_cpu(cpu); rcutree_migrate_callbacks(cpu); return 0; @@ -1359,8 +1547,10 @@ void cpuhp_online_idle(enum cpuhp_state state) if (state != CPUHP_AP_ONLINE_IDLE) return; + cpuhp_ap_update_sync_state(SYNC_STATE_ONLINE); + /* - * Unpart the stopper thread before we start the idle loop (and start + * Unpark the stopper thread before we start the idle loop (and start * scheduling); this ensures the stopper task is always available. */ stop_machine_unpark(smp_processor_id()); @@ -2737,6 +2927,7 @@ void __init boot_cpu_hotplug_init(void) { #ifdef CONFIG_SMP cpumask_set_cpu(smp_processor_id(), &cpus_booted_once_mask); + atomic_set(this_cpu_ptr(&cpuhp_state.ap_sync_state), SYNC_STATE_ONLINE); #endif this_cpu_write(cpuhp_state.state, CPUHP_ONLINE); this_cpu_write(cpuhp_state.target, CPUHP_ONLINE); diff --git a/kernel/smpboot.c b/kernel/smpboot.c index 2c7396da470c..3dcfd3f04ed0 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -326,6 +326,7 @@ void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread) } EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread); +#ifndef CONFIG_HOTPLUG_CORE_SYNC static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD); /* @@ -488,3 +489,4 @@ bool cpu_report_death(void) } #endif /* #ifdef CONFIG_HOTPLUG_CPU */ +#endif /* !CONFIG_HOTPLUG_CORE_SYNC */ -- cgit v1.2.3 From 5356297d12d9ee6f70d09485878904bc41bac422 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 12 May 2023 23:07:30 +0200 Subject: cpu/hotplug: Remove cpu_report_state() and related unused cruft No more users. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Tested-by: Michael Kelley Tested-by: Oleksandr Natalenko Tested-by: Helge Deller # parisc Tested-by: Guilherme G. Piccoli # Steam Deck Link: https://lore.kernel.org/r/20230512205256.582584351@linutronix.de --- include/linux/cpu.h | 2 -- kernel/smpboot.c | 90 ----------------------------------------------------- 2 files changed, 92 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 8582a7142623..68f69e8e4f19 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -184,8 +184,6 @@ void arch_cpu_idle_enter(void); void arch_cpu_idle_exit(void); void __noreturn arch_cpu_idle_dead(void); -int cpu_report_state(int cpu); -int cpu_check_up_prepare(int cpu); void cpu_set_state_online(int cpu); void play_idle_precise(u64 duration_ns, u64 latency_ns); diff --git a/kernel/smpboot.c b/kernel/smpboot.c index 3dcfd3f04ed0..1940f33a40a3 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -329,97 +329,7 @@ EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread); #ifndef CONFIG_HOTPLUG_CORE_SYNC static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD); -/* - * Called to poll specified CPU's state, for example, when waiting for - * a CPU to come online. - */ -int cpu_report_state(int cpu) -{ - return atomic_read(&per_cpu(cpu_hotplug_state, cpu)); -} - -/* - * If CPU has died properly, set its state to CPU_UP_PREPARE and - * return success. Otherwise, return -EBUSY if the CPU died after - * cpu_wait_death() timed out. And yet otherwise again, return -EAGAIN - * if cpu_wait_death() timed out and the CPU still hasn't gotten around - * to dying. In the latter two cases, the CPU might not be set up - * properly, but it is up to the arch-specific code to decide. - * Finally, -EIO indicates an unanticipated problem. - * - * Note that it is permissible to omit this call entirely, as is - * done in architectures that do no CPU-hotplug error checking. - */ -int cpu_check_up_prepare(int cpu) -{ - if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) { - atomic_set(&per_cpu(cpu_hotplug_state, cpu), CPU_UP_PREPARE); - return 0; - } - - switch (atomic_read(&per_cpu(cpu_hotplug_state, cpu))) { - - case CPU_POST_DEAD: - - /* The CPU died properly, so just start it up again. */ - atomic_set(&per_cpu(cpu_hotplug_state, cpu), CPU_UP_PREPARE); - return 0; - - case CPU_DEAD_FROZEN: - - /* - * Timeout during CPU death, so let caller know. - * The outgoing CPU completed its processing, but after - * cpu_wait_death() timed out and reported the error. The - * caller is free to proceed, in which case the state - * will be reset properly by cpu_set_state_online(). - * Proceeding despite this -EBUSY return makes sense - * for systems where the outgoing CPUs take themselves - * offline, with no post-death manipulation required from - * a surviving CPU. - */ - return -EBUSY; - - case CPU_BROKEN: - - /* - * The most likely reason we got here is that there was - * a timeout during CPU death, and the outgoing CPU never - * did complete its processing. This could happen on - * a virtualized system if the outgoing VCPU gets preempted - * for more than five seconds, and the user attempts to - * immediately online that same CPU. Trying again later - * might return -EBUSY above, hence -EAGAIN. - */ - return -EAGAIN; - - case CPU_UP_PREPARE: - /* - * Timeout while waiting for the CPU to show up. Allow to try - * again later. - */ - return 0; - - default: - - /* Should not happen. Famous last words. */ - return -EIO; - } -} - -/* - * Mark the specified CPU online. - * - * Note that it is permissible to omit this call entirely, as is - * done in architectures that do no CPU-hotplug error checking. - */ -void cpu_set_state_online(int cpu) -{ - (void)atomic_xchg(&per_cpu(cpu_hotplug_state, cpu), CPU_ONLINE); -} - #ifdef CONFIG_HOTPLUG_CPU - /* * Wait for the specified CPU to exit the idle loop and die. */ -- cgit v1.2.3 From bc088f9a0d5bdf12bb18980739336dfcc092e55b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 12 May 2023 23:07:41 +0200 Subject: cpu/hotplug: Remove unused state functions All users converted to the hotplug core mechanism. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Tested-by: Michael Kelley Tested-by: Oleksandr Natalenko Tested-by: Helge Deller # parisc Tested-by: Guilherme G. Piccoli # Steam Deck Link: https://lore.kernel.org/r/20230512205256.972894276@linutronix.de --- include/linux/cpu.h | 2 -- kernel/smpboot.c | 75 ----------------------------------------------------- 2 files changed, 77 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 68f69e8e4f19..d321dbd53405 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -193,8 +193,6 @@ static inline void play_idle(unsigned long duration_us) } #ifdef CONFIG_HOTPLUG_CPU -bool cpu_wait_death(unsigned int cpu, int seconds); -bool cpu_report_death(void); void cpuhp_report_idle_dead(void); #else static inline void cpuhp_report_idle_dead(void) { } diff --git a/kernel/smpboot.c b/kernel/smpboot.c index 1940f33a40a3..f47d8f375946 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -325,78 +325,3 @@ void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread) cpus_read_unlock(); } EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread); - -#ifndef CONFIG_HOTPLUG_CORE_SYNC -static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD); - -#ifdef CONFIG_HOTPLUG_CPU -/* - * Wait for the specified CPU to exit the idle loop and die. - */ -bool cpu_wait_death(unsigned int cpu, int seconds) -{ - int jf_left = seconds * HZ; - int oldstate; - bool ret = true; - int sleep_jf = 1; - - might_sleep(); - - /* The outgoing CPU will normally get done quite quickly. */ - if (atomic_read(&per_cpu(cpu_hotplug_state, cpu)) == CPU_DEAD) - goto update_state_early; - udelay(5); - - /* But if the outgoing CPU dawdles, wait increasingly long times. */ - while (atomic_read(&per_cpu(cpu_hotplug_state, cpu)) != CPU_DEAD) { - schedule_timeout_uninterruptible(sleep_jf); - jf_left -= sleep_jf; - if (jf_left <= 0) - break; - sleep_jf = DIV_ROUND_UP(sleep_jf * 11, 10); - } -update_state_early: - oldstate = atomic_read(&per_cpu(cpu_hotplug_state, cpu)); -update_state: - if (oldstate == CPU_DEAD) { - /* Outgoing CPU died normally, update state. */ - smp_mb(); /* atomic_read() before update. */ - atomic_set(&per_cpu(cpu_hotplug_state, cpu), CPU_POST_DEAD); - } else { - /* Outgoing CPU still hasn't died, set state accordingly. */ - if (!atomic_try_cmpxchg(&per_cpu(cpu_hotplug_state, cpu), - &oldstate, CPU_BROKEN)) - goto update_state; - ret = false; - } - return ret; -} - -/* - * Called by the outgoing CPU to report its successful death. Return - * false if this report follows the surviving CPU's timing out. - * - * A separate "CPU_DEAD_FROZEN" is used when the surviving CPU - * timed out. This approach allows architectures to omit calls to - * cpu_check_up_prepare() and cpu_set_state_online() without defeating - * the next cpu_wait_death()'s polling loop. - */ -bool cpu_report_death(void) -{ - int oldstate; - int newstate; - int cpu = smp_processor_id(); - - oldstate = atomic_read(&per_cpu(cpu_hotplug_state, cpu)); - do { - if (oldstate != CPU_BROKEN) - newstate = CPU_DEAD; - else - newstate = CPU_DEAD_FROZEN; - } while (!atomic_try_cmpxchg(&per_cpu(cpu_hotplug_state, cpu), - &oldstate, newstate)); - return newstate == CPU_DEAD; -} - -#endif /* #ifdef CONFIG_HOTPLUG_CPU */ -#endif /* !CONFIG_HOTPLUG_CORE_SYNC */ -- cgit v1.2.3 From a631be92b996c5db9b368e8b96305d22fb8c4180 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 12 May 2023 23:07:45 +0200 Subject: cpu/hotplug: Provide a split up CPUHP_BRINGUP mechanism The bring up logic of a to be onlined CPU consists of several parts, which are considered to be a single hotplug state: 1) Control CPU issues the wake-up 2) To be onlined CPU starts up, does the minimal initialization, reports to be alive and waits for release into the complete bring-up. 3) Control CPU waits for the alive report and releases the upcoming CPU for the complete bring-up. Allow to split this into two states: 1) Control CPU issues the wake-up After that the to be onlined CPU starts up, does the minimal initialization, reports to be alive and waits for release into the full bring-up. As this can run after the control CPU dropped the hotplug locks the code which is executed on the AP before it reports alive has to be carefully audited to not violate any of the hotplug constraints, especially not modifying any of the various cpumasks. This is really only meant to avoid waiting for the AP to react on the wake-up. Of course an architecture can move strict CPU related setup functionality, e.g. microcode loading, with care before the synchronization point to save further pointless waiting time. 2) Control CPU waits for the alive report and releases the upcoming CPU for the complete bring-up. This allows that the two states can be split up to run all to be onlined CPUs up to state #1 on the control CPU and then at a later point run state #2. This spares some of the latencies of the full serialized per CPU bringup by avoiding the per CPU wakeup/wait serialization. The assumption is that the first AP already waits when the last AP has been woken up. This obvioulsy depends on the hardware latencies and depending on the timings this might still not completely eliminate all wait scenarios. This split is just a preparatory step for enabling the parallel bringup later. The boot time bringup is still fully serialized. It has a separate config switch so that architectures which want to support parallel bringup can test the split of the CPUHP_BRINGUG step separately. To enable this the architecture must support the CPU hotplug core sync mechanism and has to be audited that there are no implicit hotplug state dependencies which require a fully serialized bringup. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Tested-by: Michael Kelley Tested-by: Oleksandr Natalenko Tested-by: Helge Deller # parisc Tested-by: Guilherme G. Piccoli # Steam Deck Link: https://lore.kernel.org/r/20230512205257.080801387@linutronix.de --- arch/Kconfig | 4 +++ include/linux/cpuhotplug.h | 4 +++ kernel/cpu.c | 70 ++++++++++++++++++++++++++++++++++++++++++++-- 3 files changed, 76 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/arch/Kconfig b/arch/Kconfig index f55c5fcbea38..d3015a61c148 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -49,6 +49,10 @@ config HOTPLUG_CORE_SYNC_FULL select HOTPLUG_CORE_SYNC_DEAD if HOTPLUG_CPU select HOTPLUG_CORE_SYNC +config HOTPLUG_SPLIT_STARTUP + bool + select HOTPLUG_CORE_SYNC_FULL + config GENERIC_ENTRY bool diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 5def71f81ec5..bc2d0a1d7608 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -133,6 +133,7 @@ enum cpuhp_state { CPUHP_MIPS_SOC_PREPARE, CPUHP_BP_PREPARE_DYN, CPUHP_BP_PREPARE_DYN_END = CPUHP_BP_PREPARE_DYN + 20, + CPUHP_BP_KICK_AP, CPUHP_BRINGUP_CPU, /* @@ -517,9 +518,12 @@ void cpuhp_online_idle(enum cpuhp_state state); static inline void cpuhp_online_idle(enum cpuhp_state state) { } #endif +struct task_struct; + void cpuhp_ap_sync_alive(void); void arch_cpuhp_sync_state_poll(void); void arch_cpuhp_cleanup_kick_cpu(unsigned int cpu); +int arch_cpuhp_kick_ap_alive(unsigned int cpu, struct task_struct *tidle); #ifdef CONFIG_HOTPLUG_CORE_SYNC_DEAD void cpuhp_ap_report_dead(void); diff --git a/kernel/cpu.c b/kernel/cpu.c index 0ab6a7d430c6..d2487aa4e7c8 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -761,6 +761,47 @@ static int bringup_wait_for_ap_online(unsigned int cpu) return 0; } +#ifdef CONFIG_HOTPLUG_SPLIT_STARTUP +static int cpuhp_kick_ap_alive(unsigned int cpu) +{ + if (!cpuhp_can_boot_ap(cpu)) + return -EAGAIN; + + return arch_cpuhp_kick_ap_alive(cpu, idle_thread_get(cpu)); +} + +static int cpuhp_bringup_ap(unsigned int cpu) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + int ret; + + /* + * Some architectures have to walk the irq descriptors to + * setup the vector space for the cpu which comes online. + * Prevent irq alloc/free across the bringup. + */ + irq_lock_sparse(); + + ret = cpuhp_bp_sync_alive(cpu); + if (ret) + goto out_unlock; + + ret = bringup_wait_for_ap_online(cpu); + if (ret) + goto out_unlock; + + irq_unlock_sparse(); + + if (st->target <= CPUHP_AP_ONLINE_IDLE) + return 0; + + return cpuhp_kick_ap(cpu, st, st->target); + +out_unlock: + irq_unlock_sparse(); + return ret; +} +#else static int bringup_cpu(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); @@ -781,7 +822,6 @@ static int bringup_cpu(unsigned int cpu) */ irq_lock_sparse(); - /* Arch-specific enabling code. */ ret = __cpu_up(cpu, idle); if (ret) goto out_unlock; @@ -805,6 +845,7 @@ out_unlock: irq_unlock_sparse(); return ret; } +#endif static int finish_cpu(unsigned int cpu) { @@ -1944,13 +1985,38 @@ static struct cpuhp_step cpuhp_hp_states[] = { .startup.single = timers_prepare_cpu, .teardown.single = timers_dead_cpu, }, - /* Kicks the plugged cpu into life */ + +#ifdef CONFIG_HOTPLUG_SPLIT_STARTUP + /* + * Kicks the AP alive. AP will wait in cpuhp_ap_sync_alive() until + * the next step will release it. + */ + [CPUHP_BP_KICK_AP] = { + .name = "cpu:kick_ap", + .startup.single = cpuhp_kick_ap_alive, + }, + + /* + * Waits for the AP to reach cpuhp_ap_sync_alive() and then + * releases it for the complete bringup. + */ + [CPUHP_BRINGUP_CPU] = { + .name = "cpu:bringup", + .startup.single = cpuhp_bringup_ap, + .teardown.single = finish_cpu, + .cant_stop = true, + }, +#else + /* + * All-in-one CPU bringup state which includes the kick alive. + */ [CPUHP_BRINGUP_CPU] = { .name = "cpu:bringup", .startup.single = bringup_cpu, .teardown.single = finish_cpu, .cant_stop = true, }, +#endif /* Final state before CPU kills itself */ [CPUHP_AP_IDLE_DEAD] = { .name = "idle:dead", -- cgit v1.2.3 From 18415f33e2ac4ab382cbca8b5ff82a9036b5bd49 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 12 May 2023 23:07:50 +0200 Subject: cpu/hotplug: Allow "parallel" bringup up to CPUHP_BP_KICK_AP_STATE There is often significant latency in the early stages of CPU bringup, and time is wasted by waking each CPU (e.g. with SIPI/INIT/INIT on x86) and then waiting for it to respond before moving on to the next. Allow a platform to enable parallel setup which brings all to be onlined CPUs up to the CPUHP_BP_KICK_AP state. While this state advancement on the control CPU (BP) is single-threaded the important part is the last state CPUHP_BP_KICK_AP which wakes the to be onlined CPUs up. This allows the CPUs to run up to the first sychronization point cpuhp_ap_sync_alive() where they wait for the control CPU to release them one by one for the full onlining procedure. This parallelism depends on the CPU hotplug core sync mechanism which ensures that the parallel brought up CPUs wait for release before touching any state which would make the CPU visible to anything outside the hotplug control mechanism. To handle the SMT constraints of X86 correctly the bringup happens in two iterations when CONFIG_HOTPLUG_SMT is enabled. The control CPU brings up the primary SMT threads of each core first, which can load the microcode without the need to rendevouz with the thread siblings. Once that's completed it brings up the secondary SMT threads. Co-developed-by: David Woodhouse Signed-off-by: David Woodhouse Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Tested-by: Michael Kelley Tested-by: Oleksandr Natalenko Tested-by: Helge Deller # parisc Tested-by: Guilherme G. Piccoli # Steam Deck Link: https://lore.kernel.org/r/20230512205257.240231377@linutronix.de --- Documentation/admin-guide/kernel-parameters.txt | 6 ++ arch/Kconfig | 4 + include/linux/cpuhotplug.h | 1 + kernel/cpu.c | 103 ++++++++++++++++++++++-- 4 files changed, 109 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index ccb91a255c6d..79fb1248f0ce 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -838,6 +838,12 @@ on every CPU online, such as boot, and resume from suspend. Default: 10000 + cpuhp.parallel= + [SMP] Enable/disable parallel bringup of secondary CPUs + Format: + Default is enabled if CONFIG_HOTPLUG_PARALLEL=y. Otherwise + the parameter has no effect. + crash_kexec_post_notifiers Run kdump after running panic-notifiers and dumping kmsg. This only for the users who doubt kdump always diff --git a/arch/Kconfig b/arch/Kconfig index d3015a61c148..64d771855ecd 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -53,6 +53,10 @@ config HOTPLUG_SPLIT_STARTUP bool select HOTPLUG_CORE_SYNC_FULL +config HOTPLUG_PARALLEL + bool + select HOTPLUG_SPLIT_STARTUP + config GENERIC_ENTRY bool diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index bc2d0a1d7608..a5e414cd82be 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -524,6 +524,7 @@ void cpuhp_ap_sync_alive(void); void arch_cpuhp_sync_state_poll(void); void arch_cpuhp_cleanup_kick_cpu(unsigned int cpu); int arch_cpuhp_kick_ap_alive(unsigned int cpu, struct task_struct *tidle); +bool arch_cpuhp_init_parallel_bringup(void); #ifdef CONFIG_HOTPLUG_CORE_SYNC_DEAD void cpuhp_ap_report_dead(void); diff --git a/kernel/cpu.c b/kernel/cpu.c index d2487aa4e7c8..005f863a3d2b 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -649,8 +649,23 @@ bool cpu_smt_possible(void) cpu_smt_control != CPU_SMT_NOT_SUPPORTED; } EXPORT_SYMBOL_GPL(cpu_smt_possible); + +static inline bool cpuhp_smt_aware(void) +{ + return topology_smt_supported(); +} + +static inline const struct cpumask *cpuhp_get_primary_thread_mask(void) +{ + return cpu_primary_thread_mask; +} #else static inline bool cpu_smt_allowed(unsigned int cpu) { return true; } +static inline bool cpuhp_smt_aware(void) { return false; } +static inline const struct cpumask *cpuhp_get_primary_thread_mask(void) +{ + return cpu_present_mask; +} #endif static inline enum cpuhp_state @@ -1747,18 +1762,96 @@ int bringup_hibernate_cpu(unsigned int sleep_cpu) return 0; } -void __init bringup_nonboot_cpus(unsigned int setup_max_cpus) +static void __init cpuhp_bringup_mask(const struct cpumask *mask, unsigned int ncpus, + enum cpuhp_state target) { unsigned int cpu; - for_each_present_cpu(cpu) { - if (num_online_cpus() >= setup_max_cpus) + for_each_cpu(cpu, mask) { + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + + if (!--ncpus) break; - if (!cpu_online(cpu)) - cpu_up(cpu, CPUHP_ONLINE); + + if (cpu_up(cpu, target) && can_rollback_cpu(st)) { + /* + * If this failed then cpu_up() might have only + * rolled back to CPUHP_BP_KICK_AP for the final + * online. Clean it up. NOOP if already rolled back. + */ + WARN_ON(cpuhp_invoke_callback_range(false, cpu, st, CPUHP_OFFLINE)); + } } } +#ifdef CONFIG_HOTPLUG_PARALLEL +static bool __cpuhp_parallel_bringup __ro_after_init = true; + +static int __init parallel_bringup_parse_param(char *arg) +{ + return kstrtobool(arg, &__cpuhp_parallel_bringup); +} +early_param("cpuhp.parallel", parallel_bringup_parse_param); + +/* + * On architectures which have enabled parallel bringup this invokes all BP + * prepare states for each of the to be onlined APs first. The last state + * sends the startup IPI to the APs. The APs proceed through the low level + * bringup code in parallel and then wait for the control CPU to release + * them one by one for the final onlining procedure. + * + * This avoids waiting for each AP to respond to the startup IPI in + * CPUHP_BRINGUP_CPU. + */ +static bool __init cpuhp_bringup_cpus_parallel(unsigned int ncpus) +{ + const struct cpumask *mask = cpu_present_mask; + + if (__cpuhp_parallel_bringup) + __cpuhp_parallel_bringup = arch_cpuhp_init_parallel_bringup(); + if (!__cpuhp_parallel_bringup) + return false; + + if (cpuhp_smt_aware()) { + const struct cpumask *pmask = cpuhp_get_primary_thread_mask(); + static struct cpumask tmp_mask __initdata; + + /* + * X86 requires to prevent that SMT siblings stopped while + * the primary thread does a microcode update for various + * reasons. Bring the primary threads up first. + */ + cpumask_and(&tmp_mask, mask, pmask); + cpuhp_bringup_mask(&tmp_mask, ncpus, CPUHP_BP_KICK_AP); + cpuhp_bringup_mask(&tmp_mask, ncpus, CPUHP_ONLINE); + /* Account for the online CPUs */ + ncpus -= num_online_cpus(); + if (!ncpus) + return true; + /* Create the mask for secondary CPUs */ + cpumask_andnot(&tmp_mask, mask, pmask); + mask = &tmp_mask; + } + + /* Bring the not-yet started CPUs up */ + cpuhp_bringup_mask(mask, ncpus, CPUHP_BP_KICK_AP); + cpuhp_bringup_mask(mask, ncpus, CPUHP_ONLINE); + return true; +} +#else +static inline bool cpuhp_bringup_cpus_parallel(unsigned int ncpus) { return false; } +#endif /* CONFIG_HOTPLUG_PARALLEL */ + +void __init bringup_nonboot_cpus(unsigned int setup_max_cpus) +{ + /* Try parallel bringup optimization if enabled */ + if (cpuhp_bringup_cpus_parallel(setup_max_cpus)) + return; + + /* Full per CPU serialized bringup */ + cpuhp_bringup_mask(cpu_present_mask, setup_max_cpus, CPUHP_ONLINE); +} + #ifdef CONFIG_PM_SLEEP_SMP static cpumask_var_t frozen_cpus; -- cgit v1.2.3 From 049449976f549605a6913d468b61356a9950a6a2 Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Thu, 4 May 2023 19:36:08 +0200 Subject: mfd: rk808: Replace 'struct i2c_client' with 'struct device' Put 'struct device' pointer into the MFD platform_data instead of the 'struct i2c_client' pointer. This simplifies the code and prepares the MFD for SPI support. Tested-by: Diederik de Haas # Rock64, Quartz64 Model A + B Tested-by: Vincent Legoll # Pine64 QuartzPro64 Signed-off-by: Sebastian Reichel Link: https://lore.kernel.org/r/20230504173618.142075-5-sebastian.reichel@collabora.com Signed-off-by: Lee Jones --- drivers/mfd/rk808.c | 6 +++--- include/linux/mfd/rk808.h | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/rk808.c b/drivers/mfd/rk808.c index f42e09e3a3f5..ce52307cbaea 100644 --- a/drivers/mfd/rk808.c +++ b/drivers/mfd/rk808.c @@ -577,7 +577,7 @@ static int rk808_power_off(struct sys_off_data *data) } ret = regmap_update_bits(rk808->regmap, reg, bit, bit); if (ret) - dev_err(&rk808->i2c->dev, "Failed to shutdown device!\n"); + dev_err(rk808->dev, "Failed to shutdown device!\n"); return NOTIFY_DONE; } @@ -600,7 +600,7 @@ static int rk808_restart(struct sys_off_data *data) } ret = regmap_update_bits(rk808->regmap, reg, bit, bit); if (ret) - dev_err(&rk808->i2c->dev, "Failed to restart device!\n"); + dev_err(rk808->dev, "Failed to restart device!\n"); return NOTIFY_DONE; } @@ -720,7 +720,7 @@ static int rk808_probe(struct i2c_client *client) return -EINVAL; } - rk808->i2c = client; + rk808->dev = &client->dev; i2c_set_clientdata(client, rk808); rk808->regmap = devm_regmap_init_i2c(client, rk808->regmap_cfg); diff --git a/include/linux/mfd/rk808.h b/include/linux/mfd/rk808.h index 9af1f3105f80..a89ddd9ba68e 100644 --- a/include/linux/mfd/rk808.h +++ b/include/linux/mfd/rk808.h @@ -787,7 +787,7 @@ enum { }; struct rk808 { - struct i2c_client *i2c; + struct device *dev; struct regmap_irq_chip_data *irq_data; struct regmap *regmap; long variant; -- cgit v1.2.3 From c20e8c5b1203af3726561ee5649b147194e0618e Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Thu, 4 May 2023 19:36:09 +0200 Subject: mfd: rk808: Split into core and i2c Split rk808 into a core and an i2c part in preparation for SPI support. Acked-by: Alexandre Belloni # for RTC Tested-by: Diederik de Haas # Rock64, Quartz64 Model A + B Tested-by: Vincent Legoll # Pine64 QuartzPro64 Signed-off-by: Sebastian Reichel Link: https://lore.kernel.org/r/20230504173618.142075-6-sebastian.reichel@collabora.com Signed-off-by: Lee Jones --- drivers/clk/Kconfig | 2 +- drivers/input/misc/Kconfig | 2 +- drivers/mfd/Kconfig | 7 +- drivers/mfd/Makefile | 3 +- drivers/mfd/rk808.c | 845 ------------------------------------------- drivers/mfd/rk8xx-core.c | 706 ++++++++++++++++++++++++++++++++++++ drivers/mfd/rk8xx-i2c.c | 200 ++++++++++ drivers/pinctrl/Kconfig | 2 +- drivers/power/supply/Kconfig | 2 +- drivers/regulator/Kconfig | 2 +- drivers/rtc/Kconfig | 2 +- include/linux/mfd/rk808.h | 6 + sound/soc/codecs/Kconfig | 2 +- 13 files changed, 927 insertions(+), 854 deletions(-) delete mode 100644 drivers/mfd/rk808.c create mode 100644 drivers/mfd/rk8xx-core.c create mode 100644 drivers/mfd/rk8xx-i2c.c (limited to 'include/linux') diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig index 016814e15536..c0c8e526a1e9 100644 --- a/drivers/clk/Kconfig +++ b/drivers/clk/Kconfig @@ -82,7 +82,7 @@ config COMMON_CLK_MAX9485 config COMMON_CLK_RK808 tristate "Clock driver for RK805/RK808/RK809/RK817/RK818" - depends on MFD_RK808 + depends on MFD_RK8XX help This driver supports RK805, RK809 and RK817, RK808 and RK818 crystal oscillator clock. These multi-function devices have two fixed-rate oscillators, clocked at 32KHz each. diff --git a/drivers/input/misc/Kconfig b/drivers/input/misc/Kconfig index 81a54a59e13c..8a320e6218e3 100644 --- a/drivers/input/misc/Kconfig +++ b/drivers/input/misc/Kconfig @@ -609,7 +609,7 @@ config INPUT_PWM_VIBRA config INPUT_RK805_PWRKEY tristate "Rockchip RK805 PMIC power key support" - depends on MFD_RK808 + depends on MFD_RK8XX help Select this option to enable power key driver for RK805. diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index e90463c4441c..de53e6c701fd 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -1183,12 +1183,17 @@ config MFD_RC5T583 Additional drivers must be enabled in order to use the different functionality of the device. -config MFD_RK808 +config MFD_RK8XX + bool + select MFD_CORE + +config MFD_RK8XX_I2C tristate "Rockchip RK805/RK808/RK809/RK817/RK818 Power Management Chip" depends on I2C && OF select MFD_CORE select REGMAP_I2C select REGMAP_IRQ + select MFD_RK8XX help If you say yes here you get support for the RK805, RK808, RK809, RK817 and RK818 Power Management chips. diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile index 1d2392f06f78..ba373193e999 100644 --- a/drivers/mfd/Makefile +++ b/drivers/mfd/Makefile @@ -214,7 +214,8 @@ obj-$(CONFIG_MFD_PALMAS) += palmas.o obj-$(CONFIG_MFD_VIPERBOARD) += viperboard.o obj-$(CONFIG_MFD_NTXEC) += ntxec.o obj-$(CONFIG_MFD_RC5T583) += rc5t583.o rc5t583-irq.o -obj-$(CONFIG_MFD_RK808) += rk808.o +obj-$(CONFIG_MFD_RK8XX) += rk8xx-core.o +obj-$(CONFIG_MFD_RK8XX_I2C) += rk8xx-i2c.o obj-$(CONFIG_MFD_RN5T618) += rn5t618.o obj-$(CONFIG_MFD_SEC_CORE) += sec-core.o sec-irq.o obj-$(CONFIG_MFD_SYSCON) += syscon.o diff --git a/drivers/mfd/rk808.c b/drivers/mfd/rk808.c deleted file mode 100644 index ce52307cbaea..000000000000 --- a/drivers/mfd/rk808.c +++ /dev/null @@ -1,845 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * MFD core driver for Rockchip RK808/RK818 - * - * Copyright (c) 2014, Fuzhou Rockchip Electronics Co., Ltd - * - * Author: Chris Zhong - * Author: Zhang Qing - * - * Copyright (C) 2016 PHYTEC Messtechnik GmbH - * - * Author: Wadim Egorov - */ - -#include -#include -#include -#include -#include -#include -#include -#include - -struct rk808_reg_data { - int addr; - int mask; - int value; -}; - -static bool rk808_is_volatile_reg(struct device *dev, unsigned int reg) -{ - /* - * Notes: - * - Technically the ROUND_30s bit makes RTC_CTRL_REG volatile, but - * we don't use that feature. It's better to cache. - * - It's unlikely we care that RK808_DEVCTRL_REG is volatile since - * bits are cleared in case when we shutoff anyway, but better safe. - */ - - switch (reg) { - case RK808_SECONDS_REG ... RK808_WEEKS_REG: - case RK808_RTC_STATUS_REG: - case RK808_VB_MON_REG: - case RK808_THERMAL_REG: - case RK808_DCDC_UV_STS_REG: - case RK808_LDO_UV_STS_REG: - case RK808_DCDC_PG_REG: - case RK808_LDO_PG_REG: - case RK808_DEVCTRL_REG: - case RK808_INT_STS_REG1: - case RK808_INT_STS_REG2: - return true; - } - - return false; -} - -static bool rk817_is_volatile_reg(struct device *dev, unsigned int reg) -{ - /* - * Notes: - * - Technically the ROUND_30s bit makes RTC_CTRL_REG volatile, but - * we don't use that feature. It's better to cache. - */ - - switch (reg) { - case RK817_SECONDS_REG ... RK817_WEEKS_REG: - case RK817_RTC_STATUS_REG: - case RK817_CODEC_DTOP_LPT_SRST: - case RK817_GAS_GAUGE_ADC_CONFIG0 ... RK817_GAS_GAUGE_CUR_ADC_K0: - case RK817_PMIC_CHRG_STS: - case RK817_PMIC_CHRG_OUT: - case RK817_PMIC_CHRG_IN: - case RK817_INT_STS_REG0: - case RK817_INT_STS_REG1: - case RK817_INT_STS_REG2: - case RK817_SYS_STS: - return true; - } - - return false; -} - -static const struct regmap_config rk818_regmap_config = { - .reg_bits = 8, - .val_bits = 8, - .max_register = RK818_USB_CTRL_REG, - .cache_type = REGCACHE_RBTREE, - .volatile_reg = rk808_is_volatile_reg, -}; - -static const struct regmap_config rk805_regmap_config = { - .reg_bits = 8, - .val_bits = 8, - .max_register = RK805_OFF_SOURCE_REG, - .cache_type = REGCACHE_RBTREE, - .volatile_reg = rk808_is_volatile_reg, -}; - -static const struct regmap_config rk808_regmap_config = { - .reg_bits = 8, - .val_bits = 8, - .max_register = RK808_IO_POL_REG, - .cache_type = REGCACHE_RBTREE, - .volatile_reg = rk808_is_volatile_reg, -}; - -static const struct regmap_config rk817_regmap_config = { - .reg_bits = 8, - .val_bits = 8, - .max_register = RK817_GPIO_INT_CFG, - .cache_type = REGCACHE_NONE, - .volatile_reg = rk817_is_volatile_reg, -}; - -static const struct resource rtc_resources[] = { - DEFINE_RES_IRQ(RK808_IRQ_RTC_ALARM), -}; - -static const struct resource rk817_rtc_resources[] = { - DEFINE_RES_IRQ(RK817_IRQ_RTC_ALARM), -}; - -static const struct resource rk805_key_resources[] = { - DEFINE_RES_IRQ(RK805_IRQ_PWRON_RISE), - DEFINE_RES_IRQ(RK805_IRQ_PWRON_FALL), -}; - -static const struct resource rk817_pwrkey_resources[] = { - DEFINE_RES_IRQ(RK817_IRQ_PWRON_RISE), - DEFINE_RES_IRQ(RK817_IRQ_PWRON_FALL), -}; - -static const struct resource rk817_charger_resources[] = { - DEFINE_RES_IRQ(RK817_IRQ_PLUG_IN), - DEFINE_RES_IRQ(RK817_IRQ_PLUG_OUT), -}; - -static const struct mfd_cell rk805s[] = { - { .name = "rk808-clkout", .id = PLATFORM_DEVID_NONE, }, - { .name = "rk808-regulator", .id = PLATFORM_DEVID_NONE, }, - { .name = "rk805-pinctrl", .id = PLATFORM_DEVID_NONE, }, - { - .name = "rk808-rtc", - .num_resources = ARRAY_SIZE(rtc_resources), - .resources = &rtc_resources[0], - .id = PLATFORM_DEVID_NONE, - }, - { .name = "rk805-pwrkey", - .num_resources = ARRAY_SIZE(rk805_key_resources), - .resources = &rk805_key_resources[0], - .id = PLATFORM_DEVID_NONE, - }, -}; - -static const struct mfd_cell rk808s[] = { - { .name = "rk808-clkout", .id = PLATFORM_DEVID_NONE, }, - { .name = "rk808-regulator", .id = PLATFORM_DEVID_NONE, }, - { - .name = "rk808-rtc", - .num_resources = ARRAY_SIZE(rtc_resources), - .resources = rtc_resources, - .id = PLATFORM_DEVID_NONE, - }, -}; - -static const struct mfd_cell rk817s[] = { - { .name = "rk808-clkout", .id = PLATFORM_DEVID_NONE, }, - { .name = "rk808-regulator", .id = PLATFORM_DEVID_NONE, }, - { - .name = "rk805-pwrkey", - .num_resources = ARRAY_SIZE(rk817_pwrkey_resources), - .resources = &rk817_pwrkey_resources[0], - .id = PLATFORM_DEVID_NONE, - }, - { - .name = "rk808-rtc", - .num_resources = ARRAY_SIZE(rk817_rtc_resources), - .resources = &rk817_rtc_resources[0], - .id = PLATFORM_DEVID_NONE, - }, - { .name = "rk817-codec", .id = PLATFORM_DEVID_NONE, }, - { - .name = "rk817-charger", - .num_resources = ARRAY_SIZE(rk817_charger_resources), - .resources = &rk817_charger_resources[0], - .id = PLATFORM_DEVID_NONE, - }, -}; - -static const struct mfd_cell rk818s[] = { - { .name = "rk808-clkout", .id = PLATFORM_DEVID_NONE, }, - { .name = "rk808-regulator", .id = PLATFORM_DEVID_NONE, }, - { - .name = "rk808-rtc", - .num_resources = ARRAY_SIZE(rtc_resources), - .resources = rtc_resources, - .id = PLATFORM_DEVID_NONE, - }, -}; - -static const struct rk808_reg_data rk805_pre_init_reg[] = { - {RK805_BUCK1_CONFIG_REG, RK805_BUCK1_2_ILMAX_MASK, - RK805_BUCK1_2_ILMAX_4000MA}, - {RK805_BUCK2_CONFIG_REG, RK805_BUCK1_2_ILMAX_MASK, - RK805_BUCK1_2_ILMAX_4000MA}, - {RK805_BUCK3_CONFIG_REG, RK805_BUCK3_4_ILMAX_MASK, - RK805_BUCK3_ILMAX_3000MA}, - {RK805_BUCK4_CONFIG_REG, RK805_BUCK3_4_ILMAX_MASK, - RK805_BUCK4_ILMAX_3500MA}, - {RK805_BUCK4_CONFIG_REG, BUCK_ILMIN_MASK, BUCK_ILMIN_400MA}, - {RK805_THERMAL_REG, TEMP_HOTDIE_MSK, TEMP115C}, -}; - -static const struct rk808_reg_data rk808_pre_init_reg[] = { - { RK808_BUCK3_CONFIG_REG, BUCK_ILMIN_MASK, BUCK_ILMIN_150MA }, - { RK808_BUCK4_CONFIG_REG, BUCK_ILMIN_MASK, BUCK_ILMIN_200MA }, - { RK808_BOOST_CONFIG_REG, BOOST_ILMIN_MASK, BOOST_ILMIN_100MA }, - { RK808_BUCK1_CONFIG_REG, BUCK1_RATE_MASK, BUCK_ILMIN_200MA }, - { RK808_BUCK2_CONFIG_REG, BUCK2_RATE_MASK, BUCK_ILMIN_200MA }, - { RK808_DCDC_UV_ACT_REG, BUCK_UV_ACT_MASK, BUCK_UV_ACT_DISABLE}, - { RK808_VB_MON_REG, MASK_ALL, VB_LO_ACT | - VB_LO_SEL_3500MV }, -}; - -static const struct rk808_reg_data rk817_pre_init_reg[] = { - {RK817_RTC_CTRL_REG, RTC_STOP, RTC_STOP}, - /* Codec specific registers */ - { RK817_CODEC_DTOP_VUCTL, MASK_ALL, 0x03 }, - { RK817_CODEC_DTOP_VUCTIME, MASK_ALL, 0x00 }, - { RK817_CODEC_DTOP_LPT_SRST, MASK_ALL, 0x00 }, - { RK817_CODEC_DTOP_DIGEN_CLKE, MASK_ALL, 0x00 }, - /* from vendor driver, CODEC_AREF_RTCFG0 not defined in data sheet */ - { RK817_CODEC_AREF_RTCFG0, MASK_ALL, 0x00 }, - { RK817_CODEC_AREF_RTCFG1, MASK_ALL, 0x06 }, - { RK817_CODEC_AADC_CFG0, MASK_ALL, 0xc8 }, - /* from vendor driver, CODEC_AADC_CFG1 not defined in data sheet */ - { RK817_CODEC_AADC_CFG1, MASK_ALL, 0x00 }, - { RK817_CODEC_DADC_VOLL, MASK_ALL, 0x00 }, - { RK817_CODEC_DADC_VOLR, MASK_ALL, 0x00 }, - { RK817_CODEC_DADC_SR_ACL0, MASK_ALL, 0x00 }, - { RK817_CODEC_DADC_ALC1, MASK_ALL, 0x00 }, - { RK817_CODEC_DADC_ALC2, MASK_ALL, 0x00 }, - { RK817_CODEC_DADC_NG, MASK_ALL, 0x00 }, - { RK817_CODEC_DADC_HPF, MASK_ALL, 0x00 }, - { RK817_CODEC_DADC_RVOLL, MASK_ALL, 0xff }, - { RK817_CODEC_DADC_RVOLR, MASK_ALL, 0xff }, - { RK817_CODEC_AMIC_CFG0, MASK_ALL, 0x70 }, - { RK817_CODEC_AMIC_CFG1, MASK_ALL, 0x00 }, - { RK817_CODEC_DMIC_PGA_GAIN, MASK_ALL, 0x66 }, - { RK817_CODEC_DMIC_LMT1, MASK_ALL, 0x00 }, - { RK817_CODEC_DMIC_LMT2, MASK_ALL, 0x00 }, - { RK817_CODEC_DMIC_NG1, MASK_ALL, 0x00 }, - { RK817_CODEC_DMIC_NG2, MASK_ALL, 0x00 }, - /* from vendor driver, CODEC_ADAC_CFG0 not defined in data sheet */ - { RK817_CODEC_ADAC_CFG0, MASK_ALL, 0x00 }, - { RK817_CODEC_ADAC_CFG1, MASK_ALL, 0x07 }, - { RK817_CODEC_DDAC_POPD_DACST, MASK_ALL, 0x82 }, - { RK817_CODEC_DDAC_VOLL, MASK_ALL, 0x00 }, - { RK817_CODEC_DDAC_VOLR, MASK_ALL, 0x00 }, - { RK817_CODEC_DDAC_SR_LMT0, MASK_ALL, 0x00 }, - { RK817_CODEC_DDAC_LMT1, MASK_ALL, 0x00 }, - { RK817_CODEC_DDAC_LMT2, MASK_ALL, 0x00 }, - { RK817_CODEC_DDAC_MUTE_MIXCTL, MASK_ALL, 0xa0 }, - { RK817_CODEC_DDAC_RVOLL, MASK_ALL, 0xff }, - { RK817_CODEC_DADC_RVOLR, MASK_ALL, 0xff }, - { RK817_CODEC_AMIC_CFG0, MASK_ALL, 0x70 }, - { RK817_CODEC_AMIC_CFG1, MASK_ALL, 0x00 }, - { RK817_CODEC_DMIC_PGA_GAIN, MASK_ALL, 0x66 }, - { RK817_CODEC_DMIC_LMT1, MASK_ALL, 0x00 }, - { RK817_CODEC_DMIC_LMT2, MASK_ALL, 0x00 }, - { RK817_CODEC_DMIC_NG1, MASK_ALL, 0x00 }, - { RK817_CODEC_DMIC_NG2, MASK_ALL, 0x00 }, - /* from vendor driver, CODEC_ADAC_CFG0 not defined in data sheet */ - { RK817_CODEC_ADAC_CFG0, MASK_ALL, 0x00 }, - { RK817_CODEC_ADAC_CFG1, MASK_ALL, 0x07 }, - { RK817_CODEC_DDAC_POPD_DACST, MASK_ALL, 0x82 }, - { RK817_CODEC_DDAC_VOLL, MASK_ALL, 0x00 }, - { RK817_CODEC_DDAC_VOLR, MASK_ALL, 0x00 }, - { RK817_CODEC_DDAC_SR_LMT0, MASK_ALL, 0x00 }, - { RK817_CODEC_DDAC_LMT1, MASK_ALL, 0x00 }, - { RK817_CODEC_DDAC_LMT2, MASK_ALL, 0x00 }, - { RK817_CODEC_DDAC_MUTE_MIXCTL, MASK_ALL, 0xa0 }, - { RK817_CODEC_DDAC_RVOLL, MASK_ALL, 0xff }, - { RK817_CODEC_DDAC_RVOLR, MASK_ALL, 0xff }, - { RK817_CODEC_AHP_ANTI0, MASK_ALL, 0x00 }, - { RK817_CODEC_AHP_ANTI1, MASK_ALL, 0x00 }, - { RK817_CODEC_AHP_CFG0, MASK_ALL, 0xe0 }, - { RK817_CODEC_AHP_CFG1, MASK_ALL, 0x1f }, - { RK817_CODEC_AHP_CP, MASK_ALL, 0x09 }, - { RK817_CODEC_ACLASSD_CFG1, MASK_ALL, 0x69 }, - { RK817_CODEC_ACLASSD_CFG2, MASK_ALL, 0x44 }, - { RK817_CODEC_APLL_CFG0, MASK_ALL, 0x04 }, - { RK817_CODEC_APLL_CFG1, MASK_ALL, 0x00 }, - { RK817_CODEC_APLL_CFG2, MASK_ALL, 0x30 }, - { RK817_CODEC_APLL_CFG3, MASK_ALL, 0x19 }, - { RK817_CODEC_APLL_CFG4, MASK_ALL, 0x65 }, - { RK817_CODEC_APLL_CFG5, MASK_ALL, 0x01 }, - { RK817_CODEC_DI2S_CKM, MASK_ALL, 0x01 }, - { RK817_CODEC_DI2S_RSD, MASK_ALL, 0x00 }, - { RK817_CODEC_DI2S_RXCR1, MASK_ALL, 0x00 }, - { RK817_CODEC_DI2S_RXCR2, MASK_ALL, 0x17 }, - { RK817_CODEC_DI2S_RXCMD_TSD, MASK_ALL, 0x00 }, - { RK817_CODEC_DI2S_TXCR1, MASK_ALL, 0x00 }, - { RK817_CODEC_DI2S_TXCR2, MASK_ALL, 0x17 }, - { RK817_CODEC_DI2S_TXCR3_TXCMD, MASK_ALL, 0x00 }, - {RK817_GPIO_INT_CFG, RK817_INT_POL_MSK, RK817_INT_POL_L}, - {RK817_SYS_CFG(1), RK817_HOTDIE_TEMP_MSK | RK817_TSD_TEMP_MSK, - RK817_HOTDIE_105 | RK817_TSD_140}, -}; - -static const struct rk808_reg_data rk818_pre_init_reg[] = { - /* improve efficiency */ - { RK818_BUCK2_CONFIG_REG, BUCK2_RATE_MASK, BUCK_ILMIN_250MA }, - { RK818_BUCK4_CONFIG_REG, BUCK_ILMIN_MASK, BUCK_ILMIN_250MA }, - { RK818_BOOST_CONFIG_REG, BOOST_ILMIN_MASK, BOOST_ILMIN_100MA }, - { RK818_USB_CTRL_REG, RK818_USB_ILIM_SEL_MASK, - RK818_USB_ILMIN_2000MA }, - /* close charger when usb lower then 3.4V */ - { RK818_USB_CTRL_REG, RK818_USB_CHG_SD_VSEL_MASK, - (0x7 << 4) }, - /* no action when vref */ - { RK818_H5V_EN_REG, BIT(1), RK818_REF_RDY_CTRL }, - /* enable HDMI 5V */ - { RK818_H5V_EN_REG, BIT(0), RK818_H5V_EN }, - { RK808_VB_MON_REG, MASK_ALL, VB_LO_ACT | - VB_LO_SEL_3500MV }, -}; - -static const struct regmap_irq rk805_irqs[] = { - [RK805_IRQ_PWRON_RISE] = { - .mask = RK805_IRQ_PWRON_RISE_MSK, - .reg_offset = 0, - }, - [RK805_IRQ_VB_LOW] = { - .mask = RK805_IRQ_VB_LOW_MSK, - .reg_offset = 0, - }, - [RK805_IRQ_PWRON] = { - .mask = RK805_IRQ_PWRON_MSK, - .reg_offset = 0, - }, - [RK805_IRQ_PWRON_LP] = { - .mask = RK805_IRQ_PWRON_LP_MSK, - .reg_offset = 0, - }, - [RK805_IRQ_HOTDIE] = { - .mask = RK805_IRQ_HOTDIE_MSK, - .reg_offset = 0, - }, - [RK805_IRQ_RTC_ALARM] = { - .mask = RK805_IRQ_RTC_ALARM_MSK, - .reg_offset = 0, - }, - [RK805_IRQ_RTC_PERIOD] = { - .mask = RK805_IRQ_RTC_PERIOD_MSK, - .reg_offset = 0, - }, - [RK805_IRQ_PWRON_FALL] = { - .mask = RK805_IRQ_PWRON_FALL_MSK, - .reg_offset = 0, - }, -}; - -static const struct regmap_irq rk808_irqs[] = { - /* INT_STS */ - [RK808_IRQ_VOUT_LO] = { - .mask = RK808_IRQ_VOUT_LO_MSK, - .reg_offset = 0, - }, - [RK808_IRQ_VB_LO] = { - .mask = RK808_IRQ_VB_LO_MSK, - .reg_offset = 0, - }, - [RK808_IRQ_PWRON] = { - .mask = RK808_IRQ_PWRON_MSK, - .reg_offset = 0, - }, - [RK808_IRQ_PWRON_LP] = { - .mask = RK808_IRQ_PWRON_LP_MSK, - .reg_offset = 0, - }, - [RK808_IRQ_HOTDIE] = { - .mask = RK808_IRQ_HOTDIE_MSK, - .reg_offset = 0, - }, - [RK808_IRQ_RTC_ALARM] = { - .mask = RK808_IRQ_RTC_ALARM_MSK, - .reg_offset = 0, - }, - [RK808_IRQ_RTC_PERIOD] = { - .mask = RK808_IRQ_RTC_PERIOD_MSK, - .reg_offset = 0, - }, - - /* INT_STS2 */ - [RK808_IRQ_PLUG_IN_INT] = { - .mask = RK808_IRQ_PLUG_IN_INT_MSK, - .reg_offset = 1, - }, - [RK808_IRQ_PLUG_OUT_INT] = { - .mask = RK808_IRQ_PLUG_OUT_INT_MSK, - .reg_offset = 1, - }, -}; - -static const struct regmap_irq rk818_irqs[] = { - /* INT_STS */ - [RK818_IRQ_VOUT_LO] = { - .mask = RK818_IRQ_VOUT_LO_MSK, - .reg_offset = 0, - }, - [RK818_IRQ_VB_LO] = { - .mask = RK818_IRQ_VB_LO_MSK, - .reg_offset = 0, - }, - [RK818_IRQ_PWRON] = { - .mask = RK818_IRQ_PWRON_MSK, - .reg_offset = 0, - }, - [RK818_IRQ_PWRON_LP] = { - .mask = RK818_IRQ_PWRON_LP_MSK, - .reg_offset = 0, - }, - [RK818_IRQ_HOTDIE] = { - .mask = RK818_IRQ_HOTDIE_MSK, - .reg_offset = 0, - }, - [RK818_IRQ_RTC_ALARM] = { - .mask = RK818_IRQ_RTC_ALARM_MSK, - .reg_offset = 0, - }, - [RK818_IRQ_RTC_PERIOD] = { - .mask = RK818_IRQ_RTC_PERIOD_MSK, - .reg_offset = 0, - }, - [RK818_IRQ_USB_OV] = { - .mask = RK818_IRQ_USB_OV_MSK, - .reg_offset = 0, - }, - - /* INT_STS2 */ - [RK818_IRQ_PLUG_IN] = { - .mask = RK818_IRQ_PLUG_IN_MSK, - .reg_offset = 1, - }, - [RK818_IRQ_PLUG_OUT] = { - .mask = RK818_IRQ_PLUG_OUT_MSK, - .reg_offset = 1, - }, - [RK818_IRQ_CHG_OK] = { - .mask = RK818_IRQ_CHG_OK_MSK, - .reg_offset = 1, - }, - [RK818_IRQ_CHG_TE] = { - .mask = RK818_IRQ_CHG_TE_MSK, - .reg_offset = 1, - }, - [RK818_IRQ_CHG_TS1] = { - .mask = RK818_IRQ_CHG_TS1_MSK, - .reg_offset = 1, - }, - [RK818_IRQ_TS2] = { - .mask = RK818_IRQ_TS2_MSK, - .reg_offset = 1, - }, - [RK818_IRQ_CHG_CVTLIM] = { - .mask = RK818_IRQ_CHG_CVTLIM_MSK, - .reg_offset = 1, - }, - [RK818_IRQ_DISCHG_ILIM] = { - .mask = RK818_IRQ_DISCHG_ILIM_MSK, - .reg_offset = 1, - }, -}; - -static const struct regmap_irq rk817_irqs[RK817_IRQ_END] = { - REGMAP_IRQ_REG_LINE(0, 8), - REGMAP_IRQ_REG_LINE(1, 8), - REGMAP_IRQ_REG_LINE(2, 8), - REGMAP_IRQ_REG_LINE(3, 8), - REGMAP_IRQ_REG_LINE(4, 8), - REGMAP_IRQ_REG_LINE(5, 8), - REGMAP_IRQ_REG_LINE(6, 8), - REGMAP_IRQ_REG_LINE(7, 8), - REGMAP_IRQ_REG_LINE(8, 8), - REGMAP_IRQ_REG_LINE(9, 8), - REGMAP_IRQ_REG_LINE(10, 8), - REGMAP_IRQ_REG_LINE(11, 8), - REGMAP_IRQ_REG_LINE(12, 8), - REGMAP_IRQ_REG_LINE(13, 8), - REGMAP_IRQ_REG_LINE(14, 8), - REGMAP_IRQ_REG_LINE(15, 8), - REGMAP_IRQ_REG_LINE(16, 8), - REGMAP_IRQ_REG_LINE(17, 8), - REGMAP_IRQ_REG_LINE(18, 8), - REGMAP_IRQ_REG_LINE(19, 8), - REGMAP_IRQ_REG_LINE(20, 8), - REGMAP_IRQ_REG_LINE(21, 8), - REGMAP_IRQ_REG_LINE(22, 8), - REGMAP_IRQ_REG_LINE(23, 8) -}; - -static struct regmap_irq_chip rk805_irq_chip = { - .name = "rk805", - .irqs = rk805_irqs, - .num_irqs = ARRAY_SIZE(rk805_irqs), - .num_regs = 1, - .status_base = RK805_INT_STS_REG, - .mask_base = RK805_INT_STS_MSK_REG, - .ack_base = RK805_INT_STS_REG, - .init_ack_masked = true, -}; - -static const struct regmap_irq_chip rk808_irq_chip = { - .name = "rk808", - .irqs = rk808_irqs, - .num_irqs = ARRAY_SIZE(rk808_irqs), - .num_regs = 2, - .irq_reg_stride = 2, - .status_base = RK808_INT_STS_REG1, - .mask_base = RK808_INT_STS_MSK_REG1, - .ack_base = RK808_INT_STS_REG1, - .init_ack_masked = true, -}; - -static struct regmap_irq_chip rk817_irq_chip = { - .name = "rk817", - .irqs = rk817_irqs, - .num_irqs = ARRAY_SIZE(rk817_irqs), - .num_regs = 3, - .irq_reg_stride = 2, - .status_base = RK817_INT_STS_REG0, - .mask_base = RK817_INT_STS_MSK_REG0, - .ack_base = RK817_INT_STS_REG0, - .init_ack_masked = true, -}; - -static const struct regmap_irq_chip rk818_irq_chip = { - .name = "rk818", - .irqs = rk818_irqs, - .num_irqs = ARRAY_SIZE(rk818_irqs), - .num_regs = 2, - .irq_reg_stride = 2, - .status_base = RK818_INT_STS_REG1, - .mask_base = RK818_INT_STS_MSK_REG1, - .ack_base = RK818_INT_STS_REG1, - .init_ack_masked = true, -}; - -static int rk808_power_off(struct sys_off_data *data) -{ - struct rk808 *rk808 = data->cb_data; - int ret; - unsigned int reg, bit; - - switch (rk808->variant) { - case RK805_ID: - reg = RK805_DEV_CTRL_REG; - bit = DEV_OFF; - break; - case RK808_ID: - reg = RK808_DEVCTRL_REG, - bit = DEV_OFF_RST; - break; - case RK809_ID: - case RK817_ID: - reg = RK817_SYS_CFG(3); - bit = DEV_OFF; - break; - case RK818_ID: - reg = RK818_DEVCTRL_REG; - bit = DEV_OFF; - break; - default: - return NOTIFY_DONE; - } - ret = regmap_update_bits(rk808->regmap, reg, bit, bit); - if (ret) - dev_err(rk808->dev, "Failed to shutdown device!\n"); - - return NOTIFY_DONE; -} - -static int rk808_restart(struct sys_off_data *data) -{ - struct rk808 *rk808 = data->cb_data; - unsigned int reg, bit; - int ret; - - switch (rk808->variant) { - case RK809_ID: - case RK817_ID: - reg = RK817_SYS_CFG(3); - bit = DEV_RST; - break; - - default: - return NOTIFY_DONE; - } - ret = regmap_update_bits(rk808->regmap, reg, bit, bit); - if (ret) - dev_err(rk808->dev, "Failed to restart device!\n"); - - return NOTIFY_DONE; -} - -static void rk8xx_shutdown(struct i2c_client *client) -{ - struct rk808 *rk808 = i2c_get_clientdata(client); - int ret; - - switch (rk808->variant) { - case RK805_ID: - ret = regmap_update_bits(rk808->regmap, - RK805_GPIO_IO_POL_REG, - SLP_SD_MSK, - SHUTDOWN_FUN); - break; - case RK809_ID: - case RK817_ID: - ret = regmap_update_bits(rk808->regmap, - RK817_SYS_CFG(3), - RK817_SLPPIN_FUNC_MSK, - SLPPIN_DN_FUN); - break; - default: - return; - } - if (ret) - dev_warn(&client->dev, - "Cannot switch to power down function\n"); -} - -static const struct of_device_id rk808_of_match[] = { - { .compatible = "rockchip,rk805" }, - { .compatible = "rockchip,rk808" }, - { .compatible = "rockchip,rk809" }, - { .compatible = "rockchip,rk817" }, - { .compatible = "rockchip,rk818" }, - { }, -}; -MODULE_DEVICE_TABLE(of, rk808_of_match); - -static int rk808_probe(struct i2c_client *client) -{ - struct device_node *np = client->dev.of_node; - struct rk808 *rk808; - const struct rk808_reg_data *pre_init_reg; - const struct mfd_cell *cells; - int nr_pre_init_regs; - int nr_cells; - int msb, lsb; - unsigned char pmic_id_msb, pmic_id_lsb; - int ret; - int i; - - rk808 = devm_kzalloc(&client->dev, sizeof(*rk808), GFP_KERNEL); - if (!rk808) - return -ENOMEM; - - if (of_device_is_compatible(np, "rockchip,rk817") || - of_device_is_compatible(np, "rockchip,rk809")) { - pmic_id_msb = RK817_ID_MSB; - pmic_id_lsb = RK817_ID_LSB; - } else { - pmic_id_msb = RK808_ID_MSB; - pmic_id_lsb = RK808_ID_LSB; - } - - /* Read chip variant */ - msb = i2c_smbus_read_byte_data(client, pmic_id_msb); - if (msb < 0) - return dev_err_probe(&client->dev, msb, "failed to read the chip id MSB\n"); - - lsb = i2c_smbus_read_byte_data(client, pmic_id_lsb); - if (lsb < 0) - return dev_err_probe(&client->dev, lsb, "failed to read the chip id LSB\n"); - - rk808->variant = ((msb << 8) | lsb) & RK8XX_ID_MSK; - dev_info(&client->dev, "chip id: 0x%x\n", (unsigned int)rk808->variant); - - switch (rk808->variant) { - case RK805_ID: - rk808->regmap_cfg = &rk805_regmap_config; - rk808->regmap_irq_chip = &rk805_irq_chip; - pre_init_reg = rk805_pre_init_reg; - nr_pre_init_regs = ARRAY_SIZE(rk805_pre_init_reg); - cells = rk805s; - nr_cells = ARRAY_SIZE(rk805s); - break; - case RK808_ID: - rk808->regmap_cfg = &rk808_regmap_config; - rk808->regmap_irq_chip = &rk808_irq_chip; - pre_init_reg = rk808_pre_init_reg; - nr_pre_init_regs = ARRAY_SIZE(rk808_pre_init_reg); - cells = rk808s; - nr_cells = ARRAY_SIZE(rk808s); - break; - case RK818_ID: - rk808->regmap_cfg = &rk818_regmap_config; - rk808->regmap_irq_chip = &rk818_irq_chip; - pre_init_reg = rk818_pre_init_reg; - nr_pre_init_regs = ARRAY_SIZE(rk818_pre_init_reg); - cells = rk818s; - nr_cells = ARRAY_SIZE(rk818s); - break; - case RK809_ID: - case RK817_ID: - rk808->regmap_cfg = &rk817_regmap_config; - rk808->regmap_irq_chip = &rk817_irq_chip; - pre_init_reg = rk817_pre_init_reg; - nr_pre_init_regs = ARRAY_SIZE(rk817_pre_init_reg); - cells = rk817s; - nr_cells = ARRAY_SIZE(rk817s); - break; - default: - dev_err(&client->dev, "Unsupported RK8XX ID %lu\n", - rk808->variant); - return -EINVAL; - } - - rk808->dev = &client->dev; - i2c_set_clientdata(client, rk808); - - rk808->regmap = devm_regmap_init_i2c(client, rk808->regmap_cfg); - if (IS_ERR(rk808->regmap)) - return dev_err_probe(&client->dev, PTR_ERR(rk808->regmap), - "regmap initialization failed\n"); - - if (!client->irq) - return dev_err_probe(&client->dev, -EINVAL, "No interrupt support, no core IRQ\n"); - - ret = devm_regmap_add_irq_chip(&client->dev, rk808->regmap, client->irq, - IRQF_ONESHOT, -1, - rk808->regmap_irq_chip, &rk808->irq_data); - if (ret) - return dev_err_probe(&client->dev, ret, "Failed to add irq_chip\n"); - - for (i = 0; i < nr_pre_init_regs; i++) { - ret = regmap_update_bits(rk808->regmap, - pre_init_reg[i].addr, - pre_init_reg[i].mask, - pre_init_reg[i].value); - if (ret) - return dev_err_probe(&client->dev, ret, "0x%x write err\n", - pre_init_reg[i].addr); - } - - ret = devm_mfd_add_devices(&client->dev, PLATFORM_DEVID_NONE, - cells, nr_cells, NULL, 0, - regmap_irq_get_domain(rk808->irq_data)); - if (ret) - return dev_err_probe(&client->dev, ret, "failed to add MFD devices\n"); - - if (of_property_read_bool(np, "rockchip,system-power-controller")) { - ret = devm_register_sys_off_handler(&client->dev, - SYS_OFF_MODE_POWER_OFF_PREPARE, SYS_OFF_PRIO_HIGH, - &rk808_power_off, rk808); - if (ret) - return dev_err_probe(&client->dev, ret, - "failed to register poweroff handler\n"); - - switch (rk808->variant) { - case RK809_ID: - case RK817_ID: - ret = devm_register_sys_off_handler(&client->dev, - SYS_OFF_MODE_RESTART, SYS_OFF_PRIO_HIGH, - &rk808_restart, rk808); - if (ret) - dev_warn(&client->dev, "failed to register rst handler, %d\n", ret); - break; - default: - dev_dbg(&client->dev, "pmic controlled board reset not supported\n"); - break; - } - } - - return 0; -} - -static int __maybe_unused rk8xx_suspend(struct device *dev) -{ - struct rk808 *rk808 = i2c_get_clientdata(to_i2c_client(dev)); - int ret = 0; - - switch (rk808->variant) { - case RK805_ID: - ret = regmap_update_bits(rk808->regmap, - RK805_GPIO_IO_POL_REG, - SLP_SD_MSK, - SLEEP_FUN); - break; - case RK809_ID: - case RK817_ID: - ret = regmap_update_bits(rk808->regmap, - RK817_SYS_CFG(3), - RK817_SLPPIN_FUNC_MSK, - SLPPIN_SLP_FUN); - break; - default: - break; - } - - return ret; -} - -static int __maybe_unused rk8xx_resume(struct device *dev) -{ - struct rk808 *rk808 = i2c_get_clientdata(to_i2c_client(dev)); - int ret = 0; - - switch (rk808->variant) { - case RK809_ID: - case RK817_ID: - ret = regmap_update_bits(rk808->regmap, - RK817_SYS_CFG(3), - RK817_SLPPIN_FUNC_MSK, - SLPPIN_NULL_FUN); - break; - default: - break; - } - - return ret; -} -static SIMPLE_DEV_PM_OPS(rk8xx_pm_ops, rk8xx_suspend, rk8xx_resume); - -static struct i2c_driver rk808_i2c_driver = { - .driver = { - .name = "rk808", - .of_match_table = rk808_of_match, - .pm = &rk8xx_pm_ops, - }, - .probe_new = rk808_probe, - .shutdown = rk8xx_shutdown, -}; - -module_i2c_driver(rk808_i2c_driver); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Chris Zhong "); -MODULE_AUTHOR("Zhang Qing "); -MODULE_AUTHOR("Wadim Egorov "); -MODULE_DESCRIPTION("RK808/RK818 PMIC driver"); diff --git a/drivers/mfd/rk8xx-core.c b/drivers/mfd/rk8xx-core.c new file mode 100644 index 000000000000..5c0a5acef34c --- /dev/null +++ b/drivers/mfd/rk8xx-core.c @@ -0,0 +1,706 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * MFD core driver for Rockchip RK8XX + * + * Copyright (c) 2014, Fuzhou Rockchip Electronics Co., Ltd + * Copyright (C) 2016 PHYTEC Messtechnik GmbH + * + * Author: Chris Zhong + * Author: Zhang Qing + * Author: Wadim Egorov + */ + +#include +#include +#include +#include +#include +#include +#include + +struct rk808_reg_data { + int addr; + int mask; + int value; +}; + +static const struct resource rtc_resources[] = { + DEFINE_RES_IRQ(RK808_IRQ_RTC_ALARM), +}; + +static const struct resource rk817_rtc_resources[] = { + DEFINE_RES_IRQ(RK817_IRQ_RTC_ALARM), +}; + +static const struct resource rk805_key_resources[] = { + DEFINE_RES_IRQ(RK805_IRQ_PWRON_RISE), + DEFINE_RES_IRQ(RK805_IRQ_PWRON_FALL), +}; + +static const struct resource rk817_pwrkey_resources[] = { + DEFINE_RES_IRQ(RK817_IRQ_PWRON_RISE), + DEFINE_RES_IRQ(RK817_IRQ_PWRON_FALL), +}; + +static const struct resource rk817_charger_resources[] = { + DEFINE_RES_IRQ(RK817_IRQ_PLUG_IN), + DEFINE_RES_IRQ(RK817_IRQ_PLUG_OUT), +}; + +static const struct mfd_cell rk805s[] = { + { .name = "rk808-clkout", .id = PLATFORM_DEVID_NONE, }, + { .name = "rk808-regulator", .id = PLATFORM_DEVID_NONE, }, + { .name = "rk805-pinctrl", .id = PLATFORM_DEVID_NONE, }, + { + .name = "rk808-rtc", + .num_resources = ARRAY_SIZE(rtc_resources), + .resources = &rtc_resources[0], + .id = PLATFORM_DEVID_NONE, + }, + { .name = "rk805-pwrkey", + .num_resources = ARRAY_SIZE(rk805_key_resources), + .resources = &rk805_key_resources[0], + .id = PLATFORM_DEVID_NONE, + }, +}; + +static const struct mfd_cell rk808s[] = { + { .name = "rk808-clkout", .id = PLATFORM_DEVID_NONE, }, + { .name = "rk808-regulator", .id = PLATFORM_DEVID_NONE, }, + { + .name = "rk808-rtc", + .num_resources = ARRAY_SIZE(rtc_resources), + .resources = rtc_resources, + .id = PLATFORM_DEVID_NONE, + }, +}; + +static const struct mfd_cell rk817s[] = { + { .name = "rk808-clkout", .id = PLATFORM_DEVID_NONE, }, + { .name = "rk808-regulator", .id = PLATFORM_DEVID_NONE, }, + { + .name = "rk805-pwrkey", + .num_resources = ARRAY_SIZE(rk817_pwrkey_resources), + .resources = &rk817_pwrkey_resources[0], + .id = PLATFORM_DEVID_NONE, + }, + { + .name = "rk808-rtc", + .num_resources = ARRAY_SIZE(rk817_rtc_resources), + .resources = &rk817_rtc_resources[0], + .id = PLATFORM_DEVID_NONE, + }, + { .name = "rk817-codec", .id = PLATFORM_DEVID_NONE, }, + { + .name = "rk817-charger", + .num_resources = ARRAY_SIZE(rk817_charger_resources), + .resources = &rk817_charger_resources[0], + .id = PLATFORM_DEVID_NONE, + }, +}; + +static const struct mfd_cell rk818s[] = { + { .name = "rk808-clkout", .id = PLATFORM_DEVID_NONE, }, + { .name = "rk808-regulator", .id = PLATFORM_DEVID_NONE, }, + { + .name = "rk808-rtc", + .num_resources = ARRAY_SIZE(rtc_resources), + .resources = rtc_resources, + .id = PLATFORM_DEVID_NONE, + }, +}; + +static const struct rk808_reg_data rk805_pre_init_reg[] = { + {RK805_BUCK1_CONFIG_REG, RK805_BUCK1_2_ILMAX_MASK, + RK805_BUCK1_2_ILMAX_4000MA}, + {RK805_BUCK2_CONFIG_REG, RK805_BUCK1_2_ILMAX_MASK, + RK805_BUCK1_2_ILMAX_4000MA}, + {RK805_BUCK3_CONFIG_REG, RK805_BUCK3_4_ILMAX_MASK, + RK805_BUCK3_ILMAX_3000MA}, + {RK805_BUCK4_CONFIG_REG, RK805_BUCK3_4_ILMAX_MASK, + RK805_BUCK4_ILMAX_3500MA}, + {RK805_BUCK4_CONFIG_REG, BUCK_ILMIN_MASK, BUCK_ILMIN_400MA}, + {RK805_THERMAL_REG, TEMP_HOTDIE_MSK, TEMP115C}, +}; + +static const struct rk808_reg_data rk808_pre_init_reg[] = { + { RK808_BUCK3_CONFIG_REG, BUCK_ILMIN_MASK, BUCK_ILMIN_150MA }, + { RK808_BUCK4_CONFIG_REG, BUCK_ILMIN_MASK, BUCK_ILMIN_200MA }, + { RK808_BOOST_CONFIG_REG, BOOST_ILMIN_MASK, BOOST_ILMIN_100MA }, + { RK808_BUCK1_CONFIG_REG, BUCK1_RATE_MASK, BUCK_ILMIN_200MA }, + { RK808_BUCK2_CONFIG_REG, BUCK2_RATE_MASK, BUCK_ILMIN_200MA }, + { RK808_DCDC_UV_ACT_REG, BUCK_UV_ACT_MASK, BUCK_UV_ACT_DISABLE}, + { RK808_VB_MON_REG, MASK_ALL, VB_LO_ACT | + VB_LO_SEL_3500MV }, +}; + +static const struct rk808_reg_data rk817_pre_init_reg[] = { + {RK817_RTC_CTRL_REG, RTC_STOP, RTC_STOP}, + /* Codec specific registers */ + { RK817_CODEC_DTOP_VUCTL, MASK_ALL, 0x03 }, + { RK817_CODEC_DTOP_VUCTIME, MASK_ALL, 0x00 }, + { RK817_CODEC_DTOP_LPT_SRST, MASK_ALL, 0x00 }, + { RK817_CODEC_DTOP_DIGEN_CLKE, MASK_ALL, 0x00 }, + /* from vendor driver, CODEC_AREF_RTCFG0 not defined in data sheet */ + { RK817_CODEC_AREF_RTCFG0, MASK_ALL, 0x00 }, + { RK817_CODEC_AREF_RTCFG1, MASK_ALL, 0x06 }, + { RK817_CODEC_AADC_CFG0, MASK_ALL, 0xc8 }, + /* from vendor driver, CODEC_AADC_CFG1 not defined in data sheet */ + { RK817_CODEC_AADC_CFG1, MASK_ALL, 0x00 }, + { RK817_CODEC_DADC_VOLL, MASK_ALL, 0x00 }, + { RK817_CODEC_DADC_VOLR, MASK_ALL, 0x00 }, + { RK817_CODEC_DADC_SR_ACL0, MASK_ALL, 0x00 }, + { RK817_CODEC_DADC_ALC1, MASK_ALL, 0x00 }, + { RK817_CODEC_DADC_ALC2, MASK_ALL, 0x00 }, + { RK817_CODEC_DADC_NG, MASK_ALL, 0x00 }, + { RK817_CODEC_DADC_HPF, MASK_ALL, 0x00 }, + { RK817_CODEC_DADC_RVOLL, MASK_ALL, 0xff }, + { RK817_CODEC_DADC_RVOLR, MASK_ALL, 0xff }, + { RK817_CODEC_AMIC_CFG0, MASK_ALL, 0x70 }, + { RK817_CODEC_AMIC_CFG1, MASK_ALL, 0x00 }, + { RK817_CODEC_DMIC_PGA_GAIN, MASK_ALL, 0x66 }, + { RK817_CODEC_DMIC_LMT1, MASK_ALL, 0x00 }, + { RK817_CODEC_DMIC_LMT2, MASK_ALL, 0x00 }, + { RK817_CODEC_DMIC_NG1, MASK_ALL, 0x00 }, + { RK817_CODEC_DMIC_NG2, MASK_ALL, 0x00 }, + /* from vendor driver, CODEC_ADAC_CFG0 not defined in data sheet */ + { RK817_CODEC_ADAC_CFG0, MASK_ALL, 0x00 }, + { RK817_CODEC_ADAC_CFG1, MASK_ALL, 0x07 }, + { RK817_CODEC_DDAC_POPD_DACST, MASK_ALL, 0x82 }, + { RK817_CODEC_DDAC_VOLL, MASK_ALL, 0x00 }, + { RK817_CODEC_DDAC_VOLR, MASK_ALL, 0x00 }, + { RK817_CODEC_DDAC_SR_LMT0, MASK_ALL, 0x00 }, + { RK817_CODEC_DDAC_LMT1, MASK_ALL, 0x00 }, + { RK817_CODEC_DDAC_LMT2, MASK_ALL, 0x00 }, + { RK817_CODEC_DDAC_MUTE_MIXCTL, MASK_ALL, 0xa0 }, + { RK817_CODEC_DDAC_RVOLL, MASK_ALL, 0xff }, + { RK817_CODEC_DADC_RVOLR, MASK_ALL, 0xff }, + { RK817_CODEC_AMIC_CFG0, MASK_ALL, 0x70 }, + { RK817_CODEC_AMIC_CFG1, MASK_ALL, 0x00 }, + { RK817_CODEC_DMIC_PGA_GAIN, MASK_ALL, 0x66 }, + { RK817_CODEC_DMIC_LMT1, MASK_ALL, 0x00 }, + { RK817_CODEC_DMIC_LMT2, MASK_ALL, 0x00 }, + { RK817_CODEC_DMIC_NG1, MASK_ALL, 0x00 }, + { RK817_CODEC_DMIC_NG2, MASK_ALL, 0x00 }, + /* from vendor driver, CODEC_ADAC_CFG0 not defined in data sheet */ + { RK817_CODEC_ADAC_CFG0, MASK_ALL, 0x00 }, + { RK817_CODEC_ADAC_CFG1, MASK_ALL, 0x07 }, + { RK817_CODEC_DDAC_POPD_DACST, MASK_ALL, 0x82 }, + { RK817_CODEC_DDAC_VOLL, MASK_ALL, 0x00 }, + { RK817_CODEC_DDAC_VOLR, MASK_ALL, 0x00 }, + { RK817_CODEC_DDAC_SR_LMT0, MASK_ALL, 0x00 }, + { RK817_CODEC_DDAC_LMT1, MASK_ALL, 0x00 }, + { RK817_CODEC_DDAC_LMT2, MASK_ALL, 0x00 }, + { RK817_CODEC_DDAC_MUTE_MIXCTL, MASK_ALL, 0xa0 }, + { RK817_CODEC_DDAC_RVOLL, MASK_ALL, 0xff }, + { RK817_CODEC_DDAC_RVOLR, MASK_ALL, 0xff }, + { RK817_CODEC_AHP_ANTI0, MASK_ALL, 0x00 }, + { RK817_CODEC_AHP_ANTI1, MASK_ALL, 0x00 }, + { RK817_CODEC_AHP_CFG0, MASK_ALL, 0xe0 }, + { RK817_CODEC_AHP_CFG1, MASK_ALL, 0x1f }, + { RK817_CODEC_AHP_CP, MASK_ALL, 0x09 }, + { RK817_CODEC_ACLASSD_CFG1, MASK_ALL, 0x69 }, + { RK817_CODEC_ACLASSD_CFG2, MASK_ALL, 0x44 }, + { RK817_CODEC_APLL_CFG0, MASK_ALL, 0x04 }, + { RK817_CODEC_APLL_CFG1, MASK_ALL, 0x00 }, + { RK817_CODEC_APLL_CFG2, MASK_ALL, 0x30 }, + { RK817_CODEC_APLL_CFG3, MASK_ALL, 0x19 }, + { RK817_CODEC_APLL_CFG4, MASK_ALL, 0x65 }, + { RK817_CODEC_APLL_CFG5, MASK_ALL, 0x01 }, + { RK817_CODEC_DI2S_CKM, MASK_ALL, 0x01 }, + { RK817_CODEC_DI2S_RSD, MASK_ALL, 0x00 }, + { RK817_CODEC_DI2S_RXCR1, MASK_ALL, 0x00 }, + { RK817_CODEC_DI2S_RXCR2, MASK_ALL, 0x17 }, + { RK817_CODEC_DI2S_RXCMD_TSD, MASK_ALL, 0x00 }, + { RK817_CODEC_DI2S_TXCR1, MASK_ALL, 0x00 }, + { RK817_CODEC_DI2S_TXCR2, MASK_ALL, 0x17 }, + { RK817_CODEC_DI2S_TXCR3_TXCMD, MASK_ALL, 0x00 }, + {RK817_GPIO_INT_CFG, RK817_INT_POL_MSK, RK817_INT_POL_L}, + {RK817_SYS_CFG(1), RK817_HOTDIE_TEMP_MSK | RK817_TSD_TEMP_MSK, + RK817_HOTDIE_105 | RK817_TSD_140}, +}; + +static const struct rk808_reg_data rk818_pre_init_reg[] = { + /* improve efficiency */ + { RK818_BUCK2_CONFIG_REG, BUCK2_RATE_MASK, BUCK_ILMIN_250MA }, + { RK818_BUCK4_CONFIG_REG, BUCK_ILMIN_MASK, BUCK_ILMIN_250MA }, + { RK818_BOOST_CONFIG_REG, BOOST_ILMIN_MASK, BOOST_ILMIN_100MA }, + { RK818_USB_CTRL_REG, RK818_USB_ILIM_SEL_MASK, + RK818_USB_ILMIN_2000MA }, + /* close charger when usb lower then 3.4V */ + { RK818_USB_CTRL_REG, RK818_USB_CHG_SD_VSEL_MASK, + (0x7 << 4) }, + /* no action when vref */ + { RK818_H5V_EN_REG, BIT(1), RK818_REF_RDY_CTRL }, + /* enable HDMI 5V */ + { RK818_H5V_EN_REG, BIT(0), RK818_H5V_EN }, + { RK808_VB_MON_REG, MASK_ALL, VB_LO_ACT | + VB_LO_SEL_3500MV }, +}; + +static const struct regmap_irq rk805_irqs[] = { + [RK805_IRQ_PWRON_RISE] = { + .mask = RK805_IRQ_PWRON_RISE_MSK, + .reg_offset = 0, + }, + [RK805_IRQ_VB_LOW] = { + .mask = RK805_IRQ_VB_LOW_MSK, + .reg_offset = 0, + }, + [RK805_IRQ_PWRON] = { + .mask = RK805_IRQ_PWRON_MSK, + .reg_offset = 0, + }, + [RK805_IRQ_PWRON_LP] = { + .mask = RK805_IRQ_PWRON_LP_MSK, + .reg_offset = 0, + }, + [RK805_IRQ_HOTDIE] = { + .mask = RK805_IRQ_HOTDIE_MSK, + .reg_offset = 0, + }, + [RK805_IRQ_RTC_ALARM] = { + .mask = RK805_IRQ_RTC_ALARM_MSK, + .reg_offset = 0, + }, + [RK805_IRQ_RTC_PERIOD] = { + .mask = RK805_IRQ_RTC_PERIOD_MSK, + .reg_offset = 0, + }, + [RK805_IRQ_PWRON_FALL] = { + .mask = RK805_IRQ_PWRON_FALL_MSK, + .reg_offset = 0, + }, +}; + +static const struct regmap_irq rk808_irqs[] = { + /* INT_STS */ + [RK808_IRQ_VOUT_LO] = { + .mask = RK808_IRQ_VOUT_LO_MSK, + .reg_offset = 0, + }, + [RK808_IRQ_VB_LO] = { + .mask = RK808_IRQ_VB_LO_MSK, + .reg_offset = 0, + }, + [RK808_IRQ_PWRON] = { + .mask = RK808_IRQ_PWRON_MSK, + .reg_offset = 0, + }, + [RK808_IRQ_PWRON_LP] = { + .mask = RK808_IRQ_PWRON_LP_MSK, + .reg_offset = 0, + }, + [RK808_IRQ_HOTDIE] = { + .mask = RK808_IRQ_HOTDIE_MSK, + .reg_offset = 0, + }, + [RK808_IRQ_RTC_ALARM] = { + .mask = RK808_IRQ_RTC_ALARM_MSK, + .reg_offset = 0, + }, + [RK808_IRQ_RTC_PERIOD] = { + .mask = RK808_IRQ_RTC_PERIOD_MSK, + .reg_offset = 0, + }, + + /* INT_STS2 */ + [RK808_IRQ_PLUG_IN_INT] = { + .mask = RK808_IRQ_PLUG_IN_INT_MSK, + .reg_offset = 1, + }, + [RK808_IRQ_PLUG_OUT_INT] = { + .mask = RK808_IRQ_PLUG_OUT_INT_MSK, + .reg_offset = 1, + }, +}; + +static const struct regmap_irq rk818_irqs[] = { + /* INT_STS */ + [RK818_IRQ_VOUT_LO] = { + .mask = RK818_IRQ_VOUT_LO_MSK, + .reg_offset = 0, + }, + [RK818_IRQ_VB_LO] = { + .mask = RK818_IRQ_VB_LO_MSK, + .reg_offset = 0, + }, + [RK818_IRQ_PWRON] = { + .mask = RK818_IRQ_PWRON_MSK, + .reg_offset = 0, + }, + [RK818_IRQ_PWRON_LP] = { + .mask = RK818_IRQ_PWRON_LP_MSK, + .reg_offset = 0, + }, + [RK818_IRQ_HOTDIE] = { + .mask = RK818_IRQ_HOTDIE_MSK, + .reg_offset = 0, + }, + [RK818_IRQ_RTC_ALARM] = { + .mask = RK818_IRQ_RTC_ALARM_MSK, + .reg_offset = 0, + }, + [RK818_IRQ_RTC_PERIOD] = { + .mask = RK818_IRQ_RTC_PERIOD_MSK, + .reg_offset = 0, + }, + [RK818_IRQ_USB_OV] = { + .mask = RK818_IRQ_USB_OV_MSK, + .reg_offset = 0, + }, + + /* INT_STS2 */ + [RK818_IRQ_PLUG_IN] = { + .mask = RK818_IRQ_PLUG_IN_MSK, + .reg_offset = 1, + }, + [RK818_IRQ_PLUG_OUT] = { + .mask = RK818_IRQ_PLUG_OUT_MSK, + .reg_offset = 1, + }, + [RK818_IRQ_CHG_OK] = { + .mask = RK818_IRQ_CHG_OK_MSK, + .reg_offset = 1, + }, + [RK818_IRQ_CHG_TE] = { + .mask = RK818_IRQ_CHG_TE_MSK, + .reg_offset = 1, + }, + [RK818_IRQ_CHG_TS1] = { + .mask = RK818_IRQ_CHG_TS1_MSK, + .reg_offset = 1, + }, + [RK818_IRQ_TS2] = { + .mask = RK818_IRQ_TS2_MSK, + .reg_offset = 1, + }, + [RK818_IRQ_CHG_CVTLIM] = { + .mask = RK818_IRQ_CHG_CVTLIM_MSK, + .reg_offset = 1, + }, + [RK818_IRQ_DISCHG_ILIM] = { + .mask = RK818_IRQ_DISCHG_ILIM_MSK, + .reg_offset = 1, + }, +}; + +static const struct regmap_irq rk817_irqs[RK817_IRQ_END] = { + REGMAP_IRQ_REG_LINE(0, 8), + REGMAP_IRQ_REG_LINE(1, 8), + REGMAP_IRQ_REG_LINE(2, 8), + REGMAP_IRQ_REG_LINE(3, 8), + REGMAP_IRQ_REG_LINE(4, 8), + REGMAP_IRQ_REG_LINE(5, 8), + REGMAP_IRQ_REG_LINE(6, 8), + REGMAP_IRQ_REG_LINE(7, 8), + REGMAP_IRQ_REG_LINE(8, 8), + REGMAP_IRQ_REG_LINE(9, 8), + REGMAP_IRQ_REG_LINE(10, 8), + REGMAP_IRQ_REG_LINE(11, 8), + REGMAP_IRQ_REG_LINE(12, 8), + REGMAP_IRQ_REG_LINE(13, 8), + REGMAP_IRQ_REG_LINE(14, 8), + REGMAP_IRQ_REG_LINE(15, 8), + REGMAP_IRQ_REG_LINE(16, 8), + REGMAP_IRQ_REG_LINE(17, 8), + REGMAP_IRQ_REG_LINE(18, 8), + REGMAP_IRQ_REG_LINE(19, 8), + REGMAP_IRQ_REG_LINE(20, 8), + REGMAP_IRQ_REG_LINE(21, 8), + REGMAP_IRQ_REG_LINE(22, 8), + REGMAP_IRQ_REG_LINE(23, 8) +}; + +static struct regmap_irq_chip rk805_irq_chip = { + .name = "rk805", + .irqs = rk805_irqs, + .num_irqs = ARRAY_SIZE(rk805_irqs), + .num_regs = 1, + .status_base = RK805_INT_STS_REG, + .mask_base = RK805_INT_STS_MSK_REG, + .ack_base = RK805_INT_STS_REG, + .init_ack_masked = true, +}; + +static const struct regmap_irq_chip rk808_irq_chip = { + .name = "rk808", + .irqs = rk808_irqs, + .num_irqs = ARRAY_SIZE(rk808_irqs), + .num_regs = 2, + .irq_reg_stride = 2, + .status_base = RK808_INT_STS_REG1, + .mask_base = RK808_INT_STS_MSK_REG1, + .ack_base = RK808_INT_STS_REG1, + .init_ack_masked = true, +}; + +static struct regmap_irq_chip rk817_irq_chip = { + .name = "rk817", + .irqs = rk817_irqs, + .num_irqs = ARRAY_SIZE(rk817_irqs), + .num_regs = 3, + .irq_reg_stride = 2, + .status_base = RK817_INT_STS_REG0, + .mask_base = RK817_INT_STS_MSK_REG0, + .ack_base = RK817_INT_STS_REG0, + .init_ack_masked = true, +}; + +static const struct regmap_irq_chip rk818_irq_chip = { + .name = "rk818", + .irqs = rk818_irqs, + .num_irqs = ARRAY_SIZE(rk818_irqs), + .num_regs = 2, + .irq_reg_stride = 2, + .status_base = RK818_INT_STS_REG1, + .mask_base = RK818_INT_STS_MSK_REG1, + .ack_base = RK818_INT_STS_REG1, + .init_ack_masked = true, +}; + +static int rk808_power_off(struct sys_off_data *data) +{ + struct rk808 *rk808 = data->cb_data; + int ret; + unsigned int reg, bit; + + switch (rk808->variant) { + case RK805_ID: + reg = RK805_DEV_CTRL_REG; + bit = DEV_OFF; + break; + case RK808_ID: + reg = RK808_DEVCTRL_REG, + bit = DEV_OFF_RST; + break; + case RK809_ID: + case RK817_ID: + reg = RK817_SYS_CFG(3); + bit = DEV_OFF; + break; + case RK818_ID: + reg = RK818_DEVCTRL_REG; + bit = DEV_OFF; + break; + default: + return NOTIFY_DONE; + } + ret = regmap_update_bits(rk808->regmap, reg, bit, bit); + if (ret) + dev_err(rk808->dev, "Failed to shutdown device!\n"); + + return NOTIFY_DONE; +} + +static int rk808_restart(struct sys_off_data *data) +{ + struct rk808 *rk808 = data->cb_data; + unsigned int reg, bit; + int ret; + + switch (rk808->variant) { + case RK809_ID: + case RK817_ID: + reg = RK817_SYS_CFG(3); + bit = DEV_RST; + break; + + default: + return NOTIFY_DONE; + } + ret = regmap_update_bits(rk808->regmap, reg, bit, bit); + if (ret) + dev_err(rk808->dev, "Failed to restart device!\n"); + + return NOTIFY_DONE; +} + +void rk8xx_shutdown(struct device *dev) +{ + struct rk808 *rk808 = dev_get_drvdata(dev); + int ret; + + switch (rk808->variant) { + case RK805_ID: + ret = regmap_update_bits(rk808->regmap, + RK805_GPIO_IO_POL_REG, + SLP_SD_MSK, + SHUTDOWN_FUN); + break; + case RK809_ID: + case RK817_ID: + ret = regmap_update_bits(rk808->regmap, + RK817_SYS_CFG(3), + RK817_SLPPIN_FUNC_MSK, + SLPPIN_DN_FUN); + break; + default: + return; + } + if (ret) + dev_warn(dev, + "Cannot switch to power down function\n"); +} +EXPORT_SYMBOL_GPL(rk8xx_shutdown); + +int rk8xx_probe(struct device *dev, int variant, unsigned int irq, struct regmap *regmap) +{ + struct rk808 *rk808; + const struct rk808_reg_data *pre_init_reg; + const struct mfd_cell *cells; + int nr_pre_init_regs; + int nr_cells; + int ret; + int i; + + rk808 = devm_kzalloc(dev, sizeof(*rk808), GFP_KERNEL); + if (!rk808) + return -ENOMEM; + rk808->dev = dev; + rk808->variant = variant; + rk808->regmap = regmap; + dev_set_drvdata(dev, rk808); + + switch (rk808->variant) { + case RK805_ID: + rk808->regmap_irq_chip = &rk805_irq_chip; + pre_init_reg = rk805_pre_init_reg; + nr_pre_init_regs = ARRAY_SIZE(rk805_pre_init_reg); + cells = rk805s; + nr_cells = ARRAY_SIZE(rk805s); + break; + case RK808_ID: + rk808->regmap_irq_chip = &rk808_irq_chip; + pre_init_reg = rk808_pre_init_reg; + nr_pre_init_regs = ARRAY_SIZE(rk808_pre_init_reg); + cells = rk808s; + nr_cells = ARRAY_SIZE(rk808s); + break; + case RK818_ID: + rk808->regmap_irq_chip = &rk818_irq_chip; + pre_init_reg = rk818_pre_init_reg; + nr_pre_init_regs = ARRAY_SIZE(rk818_pre_init_reg); + cells = rk818s; + nr_cells = ARRAY_SIZE(rk818s); + break; + case RK809_ID: + case RK817_ID: + rk808->regmap_irq_chip = &rk817_irq_chip; + pre_init_reg = rk817_pre_init_reg; + nr_pre_init_regs = ARRAY_SIZE(rk817_pre_init_reg); + cells = rk817s; + nr_cells = ARRAY_SIZE(rk817s); + break; + default: + dev_err(dev, "Unsupported RK8XX ID %lu\n", rk808->variant); + return -EINVAL; + } + + dev_info(dev, "chip id: 0x%x\n", (unsigned int)rk808->variant); + + if (!irq) + return dev_err_probe(dev, -EINVAL, "No interrupt support, no core IRQ\n"); + + ret = devm_regmap_add_irq_chip(dev, rk808->regmap, irq, + IRQF_ONESHOT, -1, + rk808->regmap_irq_chip, &rk808->irq_data); + if (ret) + return dev_err_probe(dev, ret, "Failed to add irq_chip\n"); + + for (i = 0; i < nr_pre_init_regs; i++) { + ret = regmap_update_bits(rk808->regmap, + pre_init_reg[i].addr, + pre_init_reg[i].mask, + pre_init_reg[i].value); + if (ret) + return dev_err_probe(dev, ret, "0x%x write err\n", + pre_init_reg[i].addr); + } + + ret = devm_mfd_add_devices(dev, PLATFORM_DEVID_NONE, + cells, nr_cells, NULL, 0, + regmap_irq_get_domain(rk808->irq_data)); + if (ret) + return dev_err_probe(dev, ret, "failed to add MFD devices\n"); + + if (device_property_read_bool(dev, "rockchip,system-power-controller")) { + ret = devm_register_sys_off_handler(dev, + SYS_OFF_MODE_POWER_OFF_PREPARE, SYS_OFF_PRIO_HIGH, + &rk808_power_off, rk808); + if (ret) + return dev_err_probe(dev, ret, + "failed to register poweroff handler\n"); + + switch (rk808->variant) { + case RK809_ID: + case RK817_ID: + ret = devm_register_sys_off_handler(dev, + SYS_OFF_MODE_RESTART, SYS_OFF_PRIO_HIGH, + &rk808_restart, rk808); + if (ret) + dev_warn(dev, "failed to register rst handler, %d\n", ret); + break; + default: + dev_dbg(dev, "pmic controlled board reset not supported\n"); + break; + } + } + + return 0; +} +EXPORT_SYMBOL_GPL(rk8xx_probe); + +int rk8xx_suspend(struct device *dev) +{ + struct rk808 *rk808 = dev_get_drvdata(dev); + int ret = 0; + + switch (rk808->variant) { + case RK805_ID: + ret = regmap_update_bits(rk808->regmap, + RK805_GPIO_IO_POL_REG, + SLP_SD_MSK, + SLEEP_FUN); + break; + case RK809_ID: + case RK817_ID: + ret = regmap_update_bits(rk808->regmap, + RK817_SYS_CFG(3), + RK817_SLPPIN_FUNC_MSK, + SLPPIN_SLP_FUN); + break; + default: + break; + } + + return ret; +} +EXPORT_SYMBOL_GPL(rk8xx_suspend); + +int rk8xx_resume(struct device *dev) +{ + struct rk808 *rk808 = dev_get_drvdata(dev); + int ret = 0; + + switch (rk808->variant) { + case RK809_ID: + case RK817_ID: + ret = regmap_update_bits(rk808->regmap, + RK817_SYS_CFG(3), + RK817_SLPPIN_FUNC_MSK, + SLPPIN_NULL_FUN); + break; + default: + break; + } + + return ret; +} +EXPORT_SYMBOL_GPL(rk8xx_resume); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Chris Zhong "); +MODULE_AUTHOR("Zhang Qing "); +MODULE_AUTHOR("Wadim Egorov "); +MODULE_DESCRIPTION("RK8xx PMIC core"); diff --git a/drivers/mfd/rk8xx-i2c.c b/drivers/mfd/rk8xx-i2c.c new file mode 100644 index 000000000000..6d121b589fec --- /dev/null +++ b/drivers/mfd/rk8xx-i2c.c @@ -0,0 +1,200 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Rockchip RK808/RK818 Core (I2C) driver + * + * Copyright (c) 2014, Fuzhou Rockchip Electronics Co., Ltd + * Copyright (C) 2016 PHYTEC Messtechnik GmbH + * + * Author: Chris Zhong + * Author: Zhang Qing + * Author: Wadim Egorov + */ + +#include +#include +#include +#include +#include + +static bool rk808_is_volatile_reg(struct device *dev, unsigned int reg) +{ + /* + * Notes: + * - Technically the ROUND_30s bit makes RTC_CTRL_REG volatile, but + * we don't use that feature. It's better to cache. + * - It's unlikely we care that RK808_DEVCTRL_REG is volatile since + * bits are cleared in case when we shutoff anyway, but better safe. + */ + + switch (reg) { + case RK808_SECONDS_REG ... RK808_WEEKS_REG: + case RK808_RTC_STATUS_REG: + case RK808_VB_MON_REG: + case RK808_THERMAL_REG: + case RK808_DCDC_UV_STS_REG: + case RK808_LDO_UV_STS_REG: + case RK808_DCDC_PG_REG: + case RK808_LDO_PG_REG: + case RK808_DEVCTRL_REG: + case RK808_INT_STS_REG1: + case RK808_INT_STS_REG2: + return true; + } + + return false; +} + +static bool rk817_is_volatile_reg(struct device *dev, unsigned int reg) +{ + /* + * Notes: + * - Technically the ROUND_30s bit makes RTC_CTRL_REG volatile, but + * we don't use that feature. It's better to cache. + */ + + switch (reg) { + case RK817_SECONDS_REG ... RK817_WEEKS_REG: + case RK817_RTC_STATUS_REG: + case RK817_CODEC_DTOP_LPT_SRST: + case RK817_GAS_GAUGE_ADC_CONFIG0 ... RK817_GAS_GAUGE_CUR_ADC_K0: + case RK817_PMIC_CHRG_STS: + case RK817_PMIC_CHRG_OUT: + case RK817_PMIC_CHRG_IN: + case RK817_INT_STS_REG0: + case RK817_INT_STS_REG1: + case RK817_INT_STS_REG2: + case RK817_SYS_STS: + return true; + } + + return false; +} + + +static const struct regmap_config rk818_regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .max_register = RK818_USB_CTRL_REG, + .cache_type = REGCACHE_RBTREE, + .volatile_reg = rk808_is_volatile_reg, +}; + +static const struct regmap_config rk805_regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .max_register = RK805_OFF_SOURCE_REG, + .cache_type = REGCACHE_RBTREE, + .volatile_reg = rk808_is_volatile_reg, +}; + +static const struct regmap_config rk808_regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .max_register = RK808_IO_POL_REG, + .cache_type = REGCACHE_RBTREE, + .volatile_reg = rk808_is_volatile_reg, +}; + +static const struct regmap_config rk817_regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .max_register = RK817_GPIO_INT_CFG, + .cache_type = REGCACHE_NONE, + .volatile_reg = rk817_is_volatile_reg, +}; + +static int rk8xx_i2c_get_variant(struct i2c_client *client) +{ + u8 pmic_id_msb, pmic_id_lsb; + int msb, lsb; + + if (of_device_is_compatible(client->dev.of_node, "rockchip,rk817") || + of_device_is_compatible(client->dev.of_node, "rockchip,rk809")) { + pmic_id_msb = RK817_ID_MSB; + pmic_id_lsb = RK817_ID_LSB; + } else { + pmic_id_msb = RK808_ID_MSB; + pmic_id_lsb = RK808_ID_LSB; + } + + /* Read chip variant */ + msb = i2c_smbus_read_byte_data(client, pmic_id_msb); + if (msb < 0) + return dev_err_probe(&client->dev, msb, "failed to read the chip id MSB\n"); + + lsb = i2c_smbus_read_byte_data(client, pmic_id_lsb); + if (lsb < 0) + return dev_err_probe(&client->dev, lsb, "failed to read the chip id LSB\n"); + + return ((msb << 8) | lsb) & RK8XX_ID_MSK; +} + +static int rk8xx_i2c_probe(struct i2c_client *client) +{ + const struct regmap_config *regmap_cfg; + struct regmap *regmap; + int variant; + + variant = rk8xx_i2c_get_variant(client); + if (variant < 0) + return variant; + + switch (variant) { + case RK805_ID: + regmap_cfg = &rk805_regmap_config; + break; + case RK808_ID: + regmap_cfg = &rk808_regmap_config; + break; + case RK818_ID: + regmap_cfg = &rk818_regmap_config; + break; + case RK809_ID: + case RK817_ID: + regmap_cfg = &rk817_regmap_config; + break; + default: + return dev_err_probe(&client->dev, -EINVAL, "Unsupported RK8XX ID %x\n", variant); + } + + regmap = devm_regmap_init_i2c(client, regmap_cfg); + if (IS_ERR(regmap)) + return dev_err_probe(&client->dev, PTR_ERR(regmap), + "regmap initialization failed\n"); + + return rk8xx_probe(&client->dev, variant, client->irq, regmap); +} + +static void rk8xx_i2c_shutdown(struct i2c_client *client) +{ + rk8xx_shutdown(&client->dev); +} + +static SIMPLE_DEV_PM_OPS(rk8xx_i2c_pm_ops, rk8xx_suspend, rk8xx_resume); + +static const struct of_device_id rk8xx_i2c_of_match[] = { + { .compatible = "rockchip,rk805" }, + { .compatible = "rockchip,rk808" }, + { .compatible = "rockchip,rk809" }, + { .compatible = "rockchip,rk817" }, + { .compatible = "rockchip,rk818" }, + { }, +}; +MODULE_DEVICE_TABLE(of, rk8xx_i2c_of_match); + +static struct i2c_driver rk8xx_i2c_driver = { + .driver = { + .name = "rk8xx-i2c", + .of_match_table = rk8xx_i2c_of_match, + .pm = &rk8xx_i2c_pm_ops, + }, + .probe_new = rk8xx_i2c_probe, + .shutdown = rk8xx_i2c_shutdown, +}; +module_i2c_driver(rk8xx_i2c_driver); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Chris Zhong "); +MODULE_AUTHOR("Zhang Qing "); +MODULE_AUTHOR("Wadim Egorov "); +MODULE_DESCRIPTION("RK8xx I2C PMIC driver"); diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig index 5787c579dcf6..77ff9a641aeb 100644 --- a/drivers/pinctrl/Kconfig +++ b/drivers/pinctrl/Kconfig @@ -407,7 +407,7 @@ config PINCTRL_PISTACHIO config PINCTRL_RK805 tristate "Pinctrl and GPIO driver for RK805 PMIC" - depends on MFD_RK808 + depends on MFD_RK8XX select GPIOLIB select PINMUX select GENERIC_PINCONF diff --git a/drivers/power/supply/Kconfig b/drivers/power/supply/Kconfig index c78be9f322e6..4a5e8e1d1237 100644 --- a/drivers/power/supply/Kconfig +++ b/drivers/power/supply/Kconfig @@ -706,7 +706,7 @@ config CHARGER_BQ256XX config CHARGER_RK817 tristate "Rockchip RK817 PMIC Battery Charger" - depends on MFD_RK808 + depends on MFD_RK8XX help Say Y to include support for Rockchip RK817 Battery Charger. diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig index e5f3613c15fa..f2881fe3e0a7 100644 --- a/drivers/regulator/Kconfig +++ b/drivers/regulator/Kconfig @@ -1056,7 +1056,7 @@ config REGULATOR_RC5T583 config REGULATOR_RK808 tristate "Rockchip RK805/RK808/RK809/RK817/RK818 Power regulators" - depends on MFD_RK808 + depends on MFD_RK8XX help Select this option to enable the power regulator of ROCKCHIP PMIC RK805,RK809&RK817,RK808 and RK818. diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig index 753872408615..ffca9a8bb878 100644 --- a/drivers/rtc/Kconfig +++ b/drivers/rtc/Kconfig @@ -395,7 +395,7 @@ config RTC_DRV_NCT3018Y config RTC_DRV_RK808 tristate "Rockchip RK805/RK808/RK809/RK817/RK818 RTC" - depends on MFD_RK808 + depends on MFD_RK8XX help If you say yes here you will get support for the RTC of RK805, RK809 and RK817, RK808 and RK818 PMIC. diff --git a/include/linux/mfd/rk808.h b/include/linux/mfd/rk808.h index a89ddd9ba68e..4183427a80fe 100644 --- a/include/linux/mfd/rk808.h +++ b/include/linux/mfd/rk808.h @@ -794,4 +794,10 @@ struct rk808 { const struct regmap_config *regmap_cfg; const struct regmap_irq_chip *regmap_irq_chip; }; + +void rk8xx_shutdown(struct device *dev); +int rk8xx_probe(struct device *dev, int variant, unsigned int irq, struct regmap *regmap); +int rk8xx_suspend(struct device *dev); +int rk8xx_resume(struct device *dev); + #endif /* __LINUX_REGULATOR_RK808_H */ diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig index 8020097d4e4c..0c4c5cbaa809 100644 --- a/sound/soc/codecs/Kconfig +++ b/sound/soc/codecs/Kconfig @@ -1313,7 +1313,7 @@ config SND_SOC_RK3328 config SND_SOC_RK817 tristate "Rockchip RK817 audio CODEC" - depends on MFD_RK808 || COMPILE_TEST + depends on MFD_RK8XX || COMPILE_TEST config SND_SOC_RL6231 tristate -- cgit v1.2.3 From 210f418f8ace9f056c337f7945e0ae3e242b3389 Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Thu, 4 May 2023 19:36:12 +0200 Subject: mfd: rk8xx: Add rk806 support Add support for SPI connected rk806, which is used by the RK3588 evaluation boards. The PMIC is advertised to support I2C and SPI, but the evaluation boards all use SPI. Thus only SPI support is added here. Tested-by: Diederik de Haas # Rock64, Quartz64 Model A + B Tested-by: Vincent Legoll # Pine64 QuartzPro64 Signed-off-by: Sebastian Reichel Link: https://lore.kernel.org/r/20230504173618.142075-9-sebastian.reichel@collabora.com Signed-off-by: Lee Jones --- drivers/mfd/Kconfig | 14 ++ drivers/mfd/Makefile | 1 + drivers/mfd/rk8xx-core.c | 69 +++++++- drivers/mfd/rk8xx-spi.c | 124 ++++++++++++++ include/linux/mfd/rk808.h | 409 ++++++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 614 insertions(+), 3 deletions(-) create mode 100644 drivers/mfd/rk8xx-spi.c (limited to 'include/linux') diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index de53e6c701fd..d4879cb4e1f6 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -1201,6 +1201,20 @@ config MFD_RK8XX_I2C through I2C interface. The device supports multiple sub-devices including interrupts, RTC, LDO & DCDC regulators, and onkey. +config MFD_RK8XX_SPI + tristate "Rockchip RK806 Power Management Chip" + depends on SPI && OF + select MFD_CORE + select REGMAP_SPI + select REGMAP_IRQ + select MFD_RK8XX + help + If you say yes here you get support for the RK806 Power Management + chip. + This driver provides common support for accessing the device + through an SPI interface. The device supports multiple sub-devices + including interrupts, LDO & DCDC regulators, and power on-key. + config MFD_RN5T618 tristate "Ricoh RN5T567/618 PMIC" depends on I2C diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile index ba373193e999..4e666ef5b7fc 100644 --- a/drivers/mfd/Makefile +++ b/drivers/mfd/Makefile @@ -216,6 +216,7 @@ obj-$(CONFIG_MFD_NTXEC) += ntxec.o obj-$(CONFIG_MFD_RC5T583) += rc5t583.o rc5t583-irq.o obj-$(CONFIG_MFD_RK8XX) += rk8xx-core.o obj-$(CONFIG_MFD_RK8XX_I2C) += rk8xx-i2c.o +obj-$(CONFIG_MFD_RK8XX_SPI) += rk8xx-spi.o obj-$(CONFIG_MFD_RN5T618) += rn5t618.o obj-$(CONFIG_MFD_SEC_CORE) += sec-core.o sec-irq.o obj-$(CONFIG_MFD_SYSCON) += syscon.o diff --git a/drivers/mfd/rk8xx-core.c b/drivers/mfd/rk8xx-core.c index ddf2052c5190..e8fc9e2ab1d0 100644 --- a/drivers/mfd/rk8xx-core.c +++ b/drivers/mfd/rk8xx-core.c @@ -37,6 +37,11 @@ static const struct resource rk805_key_resources[] = { DEFINE_RES_IRQ(RK805_IRQ_PWRON_FALL), }; +static struct resource rk806_pwrkey_resources[] = { + DEFINE_RES_IRQ(RK806_IRQ_PWRON_FALL), + DEFINE_RES_IRQ(RK806_IRQ_PWRON_RISE), +}; + static const struct resource rk817_pwrkey_resources[] = { DEFINE_RES_IRQ(RK817_IRQ_PWRON_RISE), DEFINE_RES_IRQ(RK817_IRQ_PWRON_FALL), @@ -64,6 +69,17 @@ static const struct mfd_cell rk805s[] = { }, }; +static const struct mfd_cell rk806s[] = { + { .name = "rk805-pinctrl", .id = PLATFORM_DEVID_AUTO, }, + { .name = "rk808-regulator", .id = PLATFORM_DEVID_AUTO, }, + { + .name = "rk805-pwrkey", + .resources = rk806_pwrkey_resources, + .num_resources = ARRAY_SIZE(rk806_pwrkey_resources), + .id = PLATFORM_DEVID_AUTO, + }, +}; + static const struct mfd_cell rk808s[] = { { .name = "rk808-clkout", .id = PLATFORM_DEVID_NONE, }, { .name = "rk808-regulator", .id = PLATFORM_DEVID_NONE, }, @@ -123,6 +139,12 @@ static const struct rk808_reg_data rk805_pre_init_reg[] = { {RK805_THERMAL_REG, TEMP_HOTDIE_MSK, TEMP115C}, }; +static const struct rk808_reg_data rk806_pre_init_reg[] = { + { RK806_GPIO_INT_CONFIG, RK806_INT_POL_MSK, RK806_INT_POL_L }, + { RK806_SYS_CFG3, RK806_SLAVE_RESTART_FUN_MSK, RK806_SLAVE_RESTART_FUN_EN }, + { RK806_SYS_OPTION, RK806_SYS_ENB2_2M_MSK, RK806_SYS_ENB2_2M_EN }, +}; + static const struct rk808_reg_data rk808_pre_init_reg[] = { { RK808_BUCK3_CONFIG_REG, BUCK_ILMIN_MASK, BUCK_ILMIN_150MA }, { RK808_BUCK4_CONFIG_REG, BUCK_ILMIN_MASK, BUCK_ILMIN_200MA }, @@ -273,6 +295,27 @@ static const struct regmap_irq rk805_irqs[] = { }, }; +static const struct regmap_irq rk806_irqs[] = { + /* INT_STS0 IRQs */ + REGMAP_IRQ_REG(RK806_IRQ_PWRON_FALL, 0, RK806_INT_STS_PWRON_FALL), + REGMAP_IRQ_REG(RK806_IRQ_PWRON_RISE, 0, RK806_INT_STS_PWRON_RISE), + REGMAP_IRQ_REG(RK806_IRQ_PWRON, 0, RK806_INT_STS_PWRON), + REGMAP_IRQ_REG(RK806_IRQ_PWRON_LP, 0, RK806_INT_STS_PWRON_LP), + REGMAP_IRQ_REG(RK806_IRQ_HOTDIE, 0, RK806_INT_STS_HOTDIE), + REGMAP_IRQ_REG(RK806_IRQ_VDC_RISE, 0, RK806_INT_STS_VDC_RISE), + REGMAP_IRQ_REG(RK806_IRQ_VDC_FALL, 0, RK806_INT_STS_VDC_FALL), + REGMAP_IRQ_REG(RK806_IRQ_VB_LO, 0, RK806_INT_STS_VB_LO), + /* INT_STS1 IRQs */ + REGMAP_IRQ_REG(RK806_IRQ_REV0, 1, RK806_INT_STS_REV0), + REGMAP_IRQ_REG(RK806_IRQ_REV1, 1, RK806_INT_STS_REV1), + REGMAP_IRQ_REG(RK806_IRQ_REV2, 1, RK806_INT_STS_REV2), + REGMAP_IRQ_REG(RK806_IRQ_CRC_ERROR, 1, RK806_INT_STS_CRC_ERROR), + REGMAP_IRQ_REG(RK806_IRQ_SLP3_GPIO, 1, RK806_INT_STS_SLP3_GPIO), + REGMAP_IRQ_REG(RK806_IRQ_SLP2_GPIO, 1, RK806_INT_STS_SLP2_GPIO), + REGMAP_IRQ_REG(RK806_IRQ_SLP1_GPIO, 1, RK806_INT_STS_SLP1_GPIO), + REGMAP_IRQ_REG(RK806_IRQ_WDT, 1, RK806_INT_STS_WDT), +}; + static const struct regmap_irq rk808_irqs[] = { /* INT_STS */ [RK808_IRQ_VOUT_LO] = { @@ -423,6 +466,18 @@ static struct regmap_irq_chip rk805_irq_chip = { .init_ack_masked = true, }; +static struct regmap_irq_chip rk806_irq_chip = { + .name = "rk806", + .irqs = rk806_irqs, + .num_irqs = ARRAY_SIZE(rk806_irqs), + .num_regs = 2, + .irq_reg_stride = 2, + .mask_base = RK806_INT_MSK0, + .status_base = RK806_INT_STS0, + .ack_base = RK806_INT_STS0, + .init_ack_masked = true, +}; + static const struct regmap_irq_chip rk808_irq_chip = { .name = "rk808", .irqs = rk808_irqs, @@ -549,6 +604,7 @@ int rk8xx_probe(struct device *dev, int variant, unsigned int irq, struct regmap struct rk808 *rk808; const struct rk808_reg_data *pre_init_reg; const struct mfd_cell *cells; + int dual_support = 0; int nr_pre_init_regs; int nr_cells; int ret; @@ -570,6 +626,14 @@ int rk8xx_probe(struct device *dev, int variant, unsigned int irq, struct regmap cells = rk805s; nr_cells = ARRAY_SIZE(rk805s); break; + case RK806_ID: + rk808->regmap_irq_chip = &rk806_irq_chip; + pre_init_reg = rk806_pre_init_reg; + nr_pre_init_regs = ARRAY_SIZE(rk806_pre_init_reg); + cells = rk806s; + nr_cells = ARRAY_SIZE(rk806s); + dual_support = IRQF_SHARED; + break; case RK808_ID: rk808->regmap_irq_chip = &rk808_irq_chip; pre_init_reg = rk808_pre_init_reg; @@ -601,7 +665,7 @@ int rk8xx_probe(struct device *dev, int variant, unsigned int irq, struct regmap return dev_err_probe(dev, -EINVAL, "No interrupt support, no core IRQ\n"); ret = devm_regmap_add_irq_chip(dev, rk808->regmap, irq, - IRQF_ONESHOT, -1, + IRQF_ONESHOT | dual_support, -1, rk808->regmap_irq_chip, &rk808->irq_data); if (ret) return dev_err_probe(dev, ret, "Failed to add irq_chip\n"); @@ -616,8 +680,7 @@ int rk8xx_probe(struct device *dev, int variant, unsigned int irq, struct regmap pre_init_reg[i].addr); } - ret = devm_mfd_add_devices(dev, PLATFORM_DEVID_NONE, - cells, nr_cells, NULL, 0, + ret = devm_mfd_add_devices(dev, 0, cells, nr_cells, NULL, 0, regmap_irq_get_domain(rk808->irq_data)); if (ret) return dev_err_probe(dev, ret, "failed to add MFD devices\n"); diff --git a/drivers/mfd/rk8xx-spi.c b/drivers/mfd/rk8xx-spi.c new file mode 100644 index 000000000000..fd137f38c2c4 --- /dev/null +++ b/drivers/mfd/rk8xx-spi.c @@ -0,0 +1,124 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Rockchip RK806 Core (SPI) driver + * + * Copyright (c) 2021 Rockchip Electronics Co., Ltd. + * Copyright (c) 2023 Collabora Ltd. + * + * Author: Xu Shengfei + * Author: Sebastian Reichel + */ + +#include +#include +#include +#include +#include +#include + +#define RK806_ADDR_SIZE 2 +#define RK806_CMD_WITH_SIZE(CMD, VALUE_BYTES) \ + (RK806_CMD_##CMD | RK806_CMD_CRC_DIS | (VALUE_BYTES - 1)) + +static const struct regmap_range rk806_volatile_ranges[] = { + regmap_reg_range(RK806_POWER_EN0, RK806_POWER_EN5), + regmap_reg_range(RK806_DVS_START_CTRL, RK806_INT_MSK1), +}; + +static const struct regmap_access_table rk806_volatile_table = { + .yes_ranges = rk806_volatile_ranges, + .n_yes_ranges = ARRAY_SIZE(rk806_volatile_ranges), +}; + +static const struct regmap_config rk806_regmap_config_spi = { + .reg_bits = 16, + .val_bits = 8, + .max_register = RK806_BUCK_RSERVE_REG5, + .cache_type = REGCACHE_RBTREE, + .volatile_table = &rk806_volatile_table, +}; + +static int rk806_spi_bus_write(void *context, const void *vdata, size_t count) +{ + struct device *dev = context; + struct spi_device *spi = to_spi_device(dev); + struct spi_transfer xfer[2] = { 0 }; + /* data and thus count includes the register address */ + size_t val_size = count - RK806_ADDR_SIZE; + char cmd; + + if (val_size < 1 || val_size > (RK806_CMD_LEN_MSK + 1)) + return -EINVAL; + + cmd = RK806_CMD_WITH_SIZE(WRITE, val_size); + + xfer[0].tx_buf = &cmd; + xfer[0].len = sizeof(cmd); + xfer[1].tx_buf = vdata; + xfer[1].len = count; + + return spi_sync_transfer(spi, xfer, ARRAY_SIZE(xfer)); +} + +static int rk806_spi_bus_read(void *context, const void *vreg, size_t reg_size, + void *val, size_t val_size) +{ + struct device *dev = context; + struct spi_device *spi = to_spi_device(dev); + char txbuf[3] = { 0 }; + + if (reg_size != RK806_ADDR_SIZE || + val_size < 1 || val_size > (RK806_CMD_LEN_MSK + 1)) + return -EINVAL; + + /* TX buffer contains command byte followed by two address bytes */ + txbuf[0] = RK806_CMD_WITH_SIZE(READ, val_size); + memcpy(txbuf+1, vreg, reg_size); + + return spi_write_then_read(spi, txbuf, sizeof(txbuf), val, val_size); +} + +static const struct regmap_bus rk806_regmap_bus_spi = { + .write = rk806_spi_bus_write, + .read = rk806_spi_bus_read, + .reg_format_endian_default = REGMAP_ENDIAN_LITTLE, +}; + +static int rk8xx_spi_probe(struct spi_device *spi) +{ + struct regmap *regmap; + + regmap = devm_regmap_init(&spi->dev, &rk806_regmap_bus_spi, + &spi->dev, &rk806_regmap_config_spi); + if (IS_ERR(regmap)) + return dev_err_probe(&spi->dev, PTR_ERR(regmap), + "Failed to init regmap\n"); + + return rk8xx_probe(&spi->dev, RK806_ID, spi->irq, regmap); +} + +static const struct of_device_id rk8xx_spi_of_match[] = { + { .compatible = "rockchip,rk806", }, + { } +}; +MODULE_DEVICE_TABLE(of, rk8xx_spi_of_match); + +static const struct spi_device_id rk8xx_spi_id_table[] = { + { "rk806", 0 }, + { } +}; +MODULE_DEVICE_TABLE(spi, rk8xx_spi_id_table); + +static struct spi_driver rk8xx_spi_driver = { + .driver = { + .name = "rk8xx-spi", + .of_match_table = rk8xx_spi_of_match, + }, + .probe = rk8xx_spi_probe, + .id_table = rk8xx_spi_id_table, +}; +module_spi_driver(rk8xx_spi_driver); + +MODULE_AUTHOR("Xu Shengfei "); +MODULE_DESCRIPTION("RK8xx SPI PMIC driver"); +MODULE_LICENSE("GPL"); diff --git a/include/linux/mfd/rk808.h b/include/linux/mfd/rk808.h index 4183427a80fe..78e167a92483 100644 --- a/include/linux/mfd/rk808.h +++ b/include/linux/mfd/rk808.h @@ -289,6 +289,414 @@ enum rk805_reg { #define RK805_INT_ALARM_EN (1 << 3) #define RK805_INT_TIMER_EN (1 << 2) +/* RK806 */ +#define RK806_POWER_EN0 0x0 +#define RK806_POWER_EN1 0x1 +#define RK806_POWER_EN2 0x2 +#define RK806_POWER_EN3 0x3 +#define RK806_POWER_EN4 0x4 +#define RK806_POWER_EN5 0x5 +#define RK806_POWER_SLP_EN0 0x6 +#define RK806_POWER_SLP_EN1 0x7 +#define RK806_POWER_SLP_EN2 0x8 +#define RK806_POWER_DISCHRG_EN0 0x9 +#define RK806_POWER_DISCHRG_EN1 0xA +#define RK806_POWER_DISCHRG_EN2 0xB +#define RK806_BUCK_FB_CONFIG 0xC +#define RK806_SLP_LP_CONFIG 0xD +#define RK806_POWER_FPWM_EN0 0xE +#define RK806_POWER_FPWM_EN1 0xF +#define RK806_BUCK1_CONFIG 0x10 +#define RK806_BUCK2_CONFIG 0x11 +#define RK806_BUCK3_CONFIG 0x12 +#define RK806_BUCK4_CONFIG 0x13 +#define RK806_BUCK5_CONFIG 0x14 +#define RK806_BUCK6_CONFIG 0x15 +#define RK806_BUCK7_CONFIG 0x16 +#define RK806_BUCK8_CONFIG 0x17 +#define RK806_BUCK9_CONFIG 0x18 +#define RK806_BUCK10_CONFIG 0x19 +#define RK806_BUCK1_ON_VSEL 0x1A +#define RK806_BUCK2_ON_VSEL 0x1B +#define RK806_BUCK3_ON_VSEL 0x1C +#define RK806_BUCK4_ON_VSEL 0x1D +#define RK806_BUCK5_ON_VSEL 0x1E +#define RK806_BUCK6_ON_VSEL 0x1F +#define RK806_BUCK7_ON_VSEL 0x20 +#define RK806_BUCK8_ON_VSEL 0x21 +#define RK806_BUCK9_ON_VSEL 0x22 +#define RK806_BUCK10_ON_VSEL 0x23 +#define RK806_BUCK1_SLP_VSEL 0x24 +#define RK806_BUCK2_SLP_VSEL 0x25 +#define RK806_BUCK3_SLP_VSEL 0x26 +#define RK806_BUCK4_SLP_VSEL 0x27 +#define RK806_BUCK5_SLP_VSEL 0x28 +#define RK806_BUCK6_SLP_VSEL 0x29 +#define RK806_BUCK7_SLP_VSEL 0x2A +#define RK806_BUCK8_SLP_VSEL 0x2B +#define RK806_BUCK9_SLP_VSEL 0x2D +#define RK806_BUCK10_SLP_VSEL 0x2E +#define RK806_BUCK_DEBUG1 0x30 +#define RK806_BUCK_DEBUG2 0x31 +#define RK806_BUCK_DEBUG3 0x32 +#define RK806_BUCK_DEBUG4 0x33 +#define RK806_BUCK_DEBUG5 0x34 +#define RK806_BUCK_DEBUG6 0x35 +#define RK806_BUCK_DEBUG7 0x36 +#define RK806_BUCK_DEBUG8 0x37 +#define RK806_BUCK_DEBUG9 0x38 +#define RK806_BUCK_DEBUG10 0x39 +#define RK806_BUCK_DEBUG11 0x3A +#define RK806_BUCK_DEBUG12 0x3B +#define RK806_BUCK_DEBUG13 0x3C +#define RK806_BUCK_DEBUG14 0x3D +#define RK806_BUCK_DEBUG15 0x3E +#define RK806_BUCK_DEBUG16 0x3F +#define RK806_BUCK_DEBUG17 0x40 +#define RK806_BUCK_DEBUG18 0x41 +#define RK806_NLDO_IMAX 0x42 +#define RK806_NLDO1_ON_VSEL 0x43 +#define RK806_NLDO2_ON_VSEL 0x44 +#define RK806_NLDO3_ON_VSEL 0x45 +#define RK806_NLDO4_ON_VSEL 0x46 +#define RK806_NLDO5_ON_VSEL 0x47 +#define RK806_NLDO1_SLP_VSEL 0x48 +#define RK806_NLDO2_SLP_VSEL 0x49 +#define RK806_NLDO3_SLP_VSEL 0x4A +#define RK806_NLDO4_SLP_VSEL 0x4B +#define RK806_NLDO5_SLP_VSEL 0x4C +#define RK806_PLDO_IMAX 0x4D +#define RK806_PLDO1_ON_VSEL 0x4E +#define RK806_PLDO2_ON_VSEL 0x4F +#define RK806_PLDO3_ON_VSEL 0x50 +#define RK806_PLDO4_ON_VSEL 0x51 +#define RK806_PLDO5_ON_VSEL 0x52 +#define RK806_PLDO6_ON_VSEL 0x53 +#define RK806_PLDO1_SLP_VSEL 0x54 +#define RK806_PLDO2_SLP_VSEL 0x55 +#define RK806_PLDO3_SLP_VSEL 0x56 +#define RK806_PLDO4_SLP_VSEL 0x57 +#define RK806_PLDO5_SLP_VSEL 0x58 +#define RK806_PLDO6_SLP_VSEL 0x59 +#define RK806_CHIP_NAME 0x5A +#define RK806_CHIP_VER 0x5B +#define RK806_OTP_VER 0x5C +#define RK806_SYS_STS 0x5D +#define RK806_SYS_CFG0 0x5E +#define RK806_SYS_CFG1 0x5F +#define RK806_SYS_OPTION 0x61 +#define RK806_SLEEP_CONFIG0 0x62 +#define RK806_SLEEP_CONFIG1 0x63 +#define RK806_SLEEP_CTR_SEL0 0x64 +#define RK806_SLEEP_CTR_SEL1 0x65 +#define RK806_SLEEP_CTR_SEL2 0x66 +#define RK806_SLEEP_CTR_SEL3 0x67 +#define RK806_SLEEP_CTR_SEL4 0x68 +#define RK806_SLEEP_CTR_SEL5 0x69 +#define RK806_DVS_CTRL_SEL0 0x6A +#define RK806_DVS_CTRL_SEL1 0x6B +#define RK806_DVS_CTRL_SEL2 0x6C +#define RK806_DVS_CTRL_SEL3 0x6D +#define RK806_DVS_CTRL_SEL4 0x6E +#define RK806_DVS_CTRL_SEL5 0x6F +#define RK806_DVS_START_CTRL 0x70 +#define RK806_SLEEP_GPIO 0x71 +#define RK806_SYS_CFG3 0x72 +#define RK806_ON_SOURCE 0x74 +#define RK806_OFF_SOURCE 0x75 +#define RK806_PWRON_KEY 0x76 +#define RK806_INT_STS0 0x77 +#define RK806_INT_MSK0 0x78 +#define RK806_INT_STS1 0x79 +#define RK806_INT_MSK1 0x7A +#define RK806_GPIO_INT_CONFIG 0x7B +#define RK806_DATA_REG0 0x7C +#define RK806_DATA_REG1 0x7D +#define RK806_DATA_REG2 0x7E +#define RK806_DATA_REG3 0x7F +#define RK806_DATA_REG4 0x80 +#define RK806_DATA_REG5 0x81 +#define RK806_DATA_REG6 0x82 +#define RK806_DATA_REG7 0x83 +#define RK806_DATA_REG8 0x84 +#define RK806_DATA_REG9 0x85 +#define RK806_DATA_REG10 0x86 +#define RK806_DATA_REG11 0x87 +#define RK806_DATA_REG12 0x88 +#define RK806_DATA_REG13 0x89 +#define RK806_DATA_REG14 0x8A +#define RK806_DATA_REG15 0x8B +#define RK806_TM_REG 0x8C +#define RK806_OTP_EN_REG 0x8D +#define RK806_FUNC_OTP_EN_REG 0x8E +#define RK806_TEST_REG1 0x8F +#define RK806_TEST_REG2 0x90 +#define RK806_TEST_REG3 0x91 +#define RK806_TEST_REG4 0x92 +#define RK806_TEST_REG5 0x93 +#define RK806_BUCK_VSEL_OTP_REG0 0x94 +#define RK806_BUCK_VSEL_OTP_REG1 0x95 +#define RK806_BUCK_VSEL_OTP_REG2 0x96 +#define RK806_BUCK_VSEL_OTP_REG3 0x97 +#define RK806_BUCK_VSEL_OTP_REG4 0x98 +#define RK806_BUCK_VSEL_OTP_REG5 0x99 +#define RK806_BUCK_VSEL_OTP_REG6 0x9A +#define RK806_BUCK_VSEL_OTP_REG7 0x9B +#define RK806_BUCK_VSEL_OTP_REG8 0x9C +#define RK806_BUCK_VSEL_OTP_REG9 0x9D +#define RK806_NLDO1_VSEL_OTP_REG0 0x9E +#define RK806_NLDO1_VSEL_OTP_REG1 0x9F +#define RK806_NLDO1_VSEL_OTP_REG2 0xA0 +#define RK806_NLDO1_VSEL_OTP_REG3 0xA1 +#define RK806_NLDO1_VSEL_OTP_REG4 0xA2 +#define RK806_PLDO_VSEL_OTP_REG0 0xA3 +#define RK806_PLDO_VSEL_OTP_REG1 0xA4 +#define RK806_PLDO_VSEL_OTP_REG2 0xA5 +#define RK806_PLDO_VSEL_OTP_REG3 0xA6 +#define RK806_PLDO_VSEL_OTP_REG4 0xA7 +#define RK806_PLDO_VSEL_OTP_REG5 0xA8 +#define RK806_BUCK_EN_OTP_REG1 0xA9 +#define RK806_NLDO_EN_OTP_REG1 0xAA +#define RK806_PLDO_EN_OTP_REG1 0xAB +#define RK806_BUCK_FB_RES_OTP_REG1 0xAC +#define RK806_OTP_RESEV_REG0 0xAD +#define RK806_OTP_RESEV_REG1 0xAE +#define RK806_OTP_RESEV_REG2 0xAF +#define RK806_OTP_RESEV_REG3 0xB0 +#define RK806_OTP_RESEV_REG4 0xB1 +#define RK806_BUCK_SEQ_REG0 0xB2 +#define RK806_BUCK_SEQ_REG1 0xB3 +#define RK806_BUCK_SEQ_REG2 0xB4 +#define RK806_BUCK_SEQ_REG3 0xB5 +#define RK806_BUCK_SEQ_REG4 0xB6 +#define RK806_BUCK_SEQ_REG5 0xB7 +#define RK806_BUCK_SEQ_REG6 0xB8 +#define RK806_BUCK_SEQ_REG7 0xB9 +#define RK806_BUCK_SEQ_REG8 0xBA +#define RK806_BUCK_SEQ_REG9 0xBB +#define RK806_BUCK_SEQ_REG10 0xBC +#define RK806_BUCK_SEQ_REG11 0xBD +#define RK806_BUCK_SEQ_REG12 0xBE +#define RK806_BUCK_SEQ_REG13 0xBF +#define RK806_BUCK_SEQ_REG14 0xC0 +#define RK806_BUCK_SEQ_REG15 0xC1 +#define RK806_BUCK_SEQ_REG16 0xC2 +#define RK806_BUCK_SEQ_REG17 0xC3 +#define RK806_HK_TRIM_REG1 0xC4 +#define RK806_HK_TRIM_REG2 0xC5 +#define RK806_BUCK_REF_TRIM_REG1 0xC6 +#define RK806_BUCK_REF_TRIM_REG2 0xC7 +#define RK806_BUCK_REF_TRIM_REG3 0xC8 +#define RK806_BUCK_REF_TRIM_REG4 0xC9 +#define RK806_BUCK_REF_TRIM_REG5 0xCA +#define RK806_BUCK_OSC_TRIM_REG1 0xCB +#define RK806_BUCK_OSC_TRIM_REG2 0xCC +#define RK806_BUCK_OSC_TRIM_REG3 0xCD +#define RK806_BUCK_OSC_TRIM_REG4 0xCE +#define RK806_BUCK_OSC_TRIM_REG5 0xCF +#define RK806_BUCK_TRIM_ZCDIOS_REG1 0xD0 +#define RK806_BUCK_TRIM_ZCDIOS_REG2 0xD1 +#define RK806_NLDO_TRIM_REG1 0xD2 +#define RK806_NLDO_TRIM_REG2 0xD3 +#define RK806_NLDO_TRIM_REG3 0xD4 +#define RK806_PLDO_TRIM_REG1 0xD5 +#define RK806_PLDO_TRIM_REG2 0xD6 +#define RK806_PLDO_TRIM_REG3 0xD7 +#define RK806_TRIM_ICOMP_REG1 0xD8 +#define RK806_TRIM_ICOMP_REG2 0xD9 +#define RK806_EFUSE_CONTROL_REGH 0xDA +#define RK806_FUSE_PROG_REG 0xDB +#define RK806_MAIN_FSM_STS_REG 0xDD +#define RK806_FSM_REG 0xDE +#define RK806_TOP_RESEV_OFFR 0xEC +#define RK806_TOP_RESEV_POR 0xED +#define RK806_BUCK_VRSN_REG1 0xEE +#define RK806_BUCK_VRSN_REG2 0xEF +#define RK806_NLDO_RLOAD_SEL_REG1 0xF0 +#define RK806_PLDO_RLOAD_SEL_REG1 0xF1 +#define RK806_PLDO_RLOAD_SEL_REG2 0xF2 +#define RK806_BUCK_CMIN_MX_REG1 0xF3 +#define RK806_BUCK_CMIN_MX_REG2 0xF4 +#define RK806_BUCK_FREQ_SET_REG1 0xF5 +#define RK806_BUCK_FREQ_SET_REG2 0xF6 +#define RK806_BUCK_RS_MEABS_REG1 0xF7 +#define RK806_BUCK_RS_MEABS_REG2 0xF8 +#define RK806_BUCK_RS_ZDLEB_REG1 0xF9 +#define RK806_BUCK_RS_ZDLEB_REG2 0xFA +#define RK806_BUCK_RSERVE_REG1 0xFB +#define RK806_BUCK_RSERVE_REG2 0xFC +#define RK806_BUCK_RSERVE_REG3 0xFD +#define RK806_BUCK_RSERVE_REG4 0xFE +#define RK806_BUCK_RSERVE_REG5 0xFF + +/* INT_STS Register field definitions */ +#define RK806_INT_STS_PWRON_FALL BIT(0) +#define RK806_INT_STS_PWRON_RISE BIT(1) +#define RK806_INT_STS_PWRON BIT(2) +#define RK806_INT_STS_PWRON_LP BIT(3) +#define RK806_INT_STS_HOTDIE BIT(4) +#define RK806_INT_STS_VDC_RISE BIT(5) +#define RK806_INT_STS_VDC_FALL BIT(6) +#define RK806_INT_STS_VB_LO BIT(7) +#define RK806_INT_STS_REV0 BIT(0) +#define RK806_INT_STS_REV1 BIT(1) +#define RK806_INT_STS_REV2 BIT(2) +#define RK806_INT_STS_CRC_ERROR BIT(3) +#define RK806_INT_STS_SLP3_GPIO BIT(4) +#define RK806_INT_STS_SLP2_GPIO BIT(5) +#define RK806_INT_STS_SLP1_GPIO BIT(6) +#define RK806_INT_STS_WDT BIT(7) + +/* SPI command */ +#define RK806_CMD_READ 0 +#define RK806_CMD_WRITE BIT(7) +#define RK806_CMD_CRC_EN BIT(6) +#define RK806_CMD_CRC_DIS 0 +#define RK806_CMD_LEN_MSK 0x0f +#define RK806_REG_H 0x00 + +#define VERSION_AB 0x01 + +enum rk806_reg_id { + RK806_ID_DCDC1 = 0, + RK806_ID_DCDC2, + RK806_ID_DCDC3, + RK806_ID_DCDC4, + RK806_ID_DCDC5, + RK806_ID_DCDC6, + RK806_ID_DCDC7, + RK806_ID_DCDC8, + RK806_ID_DCDC9, + RK806_ID_DCDC10, + + RK806_ID_NLDO1, + RK806_ID_NLDO2, + RK806_ID_NLDO3, + RK806_ID_NLDO4, + RK806_ID_NLDO5, + + RK806_ID_PLDO1, + RK806_ID_PLDO2, + RK806_ID_PLDO3, + RK806_ID_PLDO4, + RK806_ID_PLDO5, + RK806_ID_PLDO6, + RK806_ID_END, +}; + +/* Define the RK806 IRQ numbers */ +enum rk806_irqs { + /* INT_STS0 registers */ + RK806_IRQ_PWRON_FALL, + RK806_IRQ_PWRON_RISE, + RK806_IRQ_PWRON, + RK806_IRQ_PWRON_LP, + RK806_IRQ_HOTDIE, + RK806_IRQ_VDC_RISE, + RK806_IRQ_VDC_FALL, + RK806_IRQ_VB_LO, + + /* INT_STS0 registers */ + RK806_IRQ_REV0, + RK806_IRQ_REV1, + RK806_IRQ_REV2, + RK806_IRQ_CRC_ERROR, + RK806_IRQ_SLP3_GPIO, + RK806_IRQ_SLP2_GPIO, + RK806_IRQ_SLP1_GPIO, + RK806_IRQ_WDT, +}; + +/* VCC1 Low Voltage Threshold */ +enum rk806_lv_sel { + VB_LO_SEL_2800, + VB_LO_SEL_2900, + VB_LO_SEL_3000, + VB_LO_SEL_3100, + VB_LO_SEL_3200, + VB_LO_SEL_3300, + VB_LO_SEL_3400, + VB_LO_SEL_3500, +}; + +/* System Shutdown Voltage Select */ +enum rk806_uv_sel { + VB_UV_SEL_2700, + VB_UV_SEL_2800, + VB_UV_SEL_2900, + VB_UV_SEL_3000, + VB_UV_SEL_3100, + VB_UV_SEL_3200, + VB_UV_SEL_3300, + VB_UV_SEL_3400, +}; + +/* Pin Function */ +enum rk806_pwrctrl_fun { + PWRCTRL_NULL_FUN, + PWRCTRL_SLP_FUN, + PWRCTRL_POWOFF_FUN, + PWRCTRL_RST_FUN, + PWRCTRL_DVS_FUN, + PWRCTRL_GPIO_FUN, +}; + +/* Pin Polarity */ +enum rk806_pin_level { + POL_LOW, + POL_HIGH, +}; + +enum rk806_vsel_ctr_sel { + CTR_BY_NO_EFFECT, + CTR_BY_PWRCTRL1, + CTR_BY_PWRCTRL2, + CTR_BY_PWRCTRL3, +}; + +enum rk806_dvs_ctr_sel { + CTR_SEL_NO_EFFECT, + CTR_SEL_DVS_START1, + CTR_SEL_DVS_START2, + CTR_SEL_DVS_START3, +}; + +enum rk806_pin_dr_sel { + RK806_PIN_INPUT, + RK806_PIN_OUTPUT, +}; + +#define RK806_INT_POL_MSK BIT(1) +#define RK806_INT_POL_H BIT(1) +#define RK806_INT_POL_L 0 + +#define RK806_SLAVE_RESTART_FUN_MSK BIT(1) +#define RK806_SLAVE_RESTART_FUN_EN BIT(1) +#define RK806_SLAVE_RESTART_FUN_OFF 0 + +#define RK806_SYS_ENB2_2M_MSK BIT(1) +#define RK806_SYS_ENB2_2M_EN BIT(1) +#define RK806_SYS_ENB2_2M_OFF 0 + +enum rk806_int_fun { + RK806_INT_ONLY, + RK806_INT_ADN_WKUP, +}; + +enum rk806_dvs_mode { + RK806_DVS_NOT_SUPPORT, + RK806_DVS_START1, + RK806_DVS_START2, + RK806_DVS_START3, + RK806_DVS_PWRCTRL1, + RK806_DVS_PWRCTRL2, + RK806_DVS_PWRCTRL3, + RK806_DVS_START_PWRCTR1, + RK806_DVS_START_PWRCTR2, + RK806_DVS_START_PWRCTR3, + RK806_DVS_END, +}; + /* RK808 IRQ Definitions */ #define RK808_IRQ_VOUT_LO 0 #define RK808_IRQ_VB_LO 1 @@ -780,6 +1188,7 @@ enum { enum { RK805_ID = 0x8050, + RK806_ID = 0x8060, RK808_ID = 0x0000, RK809_ID = 0x8090, RK817_ID = 0x8170, -- cgit v1.2.3 From 47e79cbeea4b3891ad476047f4c68543eb51c8e0 Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Mon, 15 May 2023 13:08:48 +0000 Subject: bpf: Remove bpf trampoline selector After commit e21aa341785c ("bpf: Fix fexit trampoline."), the selector is only used to indicate how many times the bpf trampoline image are updated and been displayed in the trampoline ksym name. After the trampoline is freed, the selector will start from 0 again. So the selector is a useless value to the user. We can remove it. If the user want to check whether the bpf trampoline image has been updated or not, the user can compare the address. Each time the trampoline image is updated, the address will change consequently. Jiri also pointed out another issue that perf is still using the old name "bpf_trampoline_%lu", so this change can fix the issue in perf. Fixes: e21aa341785c ("bpf: Fix fexit trampoline.") Signed-off-by: Yafang Shao Signed-off-by: Daniel Borkmann Acked-by: Song Liu Cc: Jiri Olsa Link: https://lore.kernel.org/bpf/ZFvOOlrmHiY9AgXE@krava Link: https://lore.kernel.org/bpf/20230515130849.57502-3-laoar.shao@gmail.com --- include/linux/bpf.h | 1 - kernel/bpf/trampoline.c | 11 ++++------- 2 files changed, 4 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 456f33b9d205..36e4b2d8cca2 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1125,7 +1125,6 @@ struct bpf_trampoline { int progs_cnt[BPF_TRAMP_MAX]; /* Executable image of trampoline */ struct bpf_tramp_image *cur_image; - u64 selector; struct module *mod; }; diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index ac021bc43a66..84850e66ce3d 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -344,7 +344,7 @@ static void bpf_tramp_image_put(struct bpf_tramp_image *im) call_rcu_tasks_trace(&im->rcu, __bpf_tramp_image_put_rcu_tasks); } -static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key, u32 idx) +static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key) { struct bpf_tramp_image *im; struct bpf_ksym *ksym; @@ -371,7 +371,7 @@ static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key, u32 idx) ksym = &im->ksym; INIT_LIST_HEAD_RCU(&ksym->lnode); - snprintf(ksym->name, KSYM_NAME_LEN, "bpf_trampoline_%llu_%u", key, idx); + snprintf(ksym->name, KSYM_NAME_LEN, "bpf_trampoline_%llu", key); bpf_image_ksym_add(image, ksym); return im; @@ -401,11 +401,10 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut err = unregister_fentry(tr, tr->cur_image->image); bpf_tramp_image_put(tr->cur_image); tr->cur_image = NULL; - tr->selector = 0; goto out; } - im = bpf_tramp_image_alloc(tr->key, tr->selector); + im = bpf_tramp_image_alloc(tr->key); if (IS_ERR(im)) { err = PTR_ERR(im); goto out; @@ -442,8 +441,7 @@ again: set_memory_rox((long)im->image, 1); - WARN_ON(tr->cur_image && tr->selector == 0); - WARN_ON(!tr->cur_image && tr->selector); + WARN_ON(tr->cur_image && total == 0); if (tr->cur_image) /* progs already running at this address */ err = modify_fentry(tr, tr->cur_image->image, im->image, lock_direct_mutex); @@ -473,7 +471,6 @@ again: if (tr->cur_image) bpf_tramp_image_put(tr->cur_image); tr->cur_image = im; - tr->selector++; out: /* If any error happens, restore previous flags */ if (err) -- cgit v1.2.3 From 6882011e8854c6cb227770fccb57ed70a88a716f Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Sun, 23 Apr 2023 13:06:39 +0200 Subject: can: length: make header self contained Include the headers that "can/length.h" depends on. Fixes: bdd2e413192d ("can: dev: move length related code into seperate file") Link: https://lore.kernel.org/all/20230509122854.350426-1-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- include/linux/can/length.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/can/length.h b/include/linux/can/length.h index 6995092b774e..69336549d24f 100644 --- a/include/linux/can/length.h +++ b/include/linux/can/length.h @@ -6,6 +6,9 @@ #ifndef _CAN_LENGTH_H #define _CAN_LENGTH_H +#include +#include + /* * Size of a Classical CAN Standard Frame * -- cgit v1.2.3 From 8b33485128ad932f807f4535e0b440733d8b5808 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Mon, 15 May 2023 13:01:07 +0800 Subject: net: skbuff: update comment about pfmemalloc propagating __skb_fill_page_desc_noacc() is not doing any pfmemalloc propagating, and yet it has a comment about that, commit 84ce071e38a6 ("net: introduce __skb_fill_page_desc_noacc") may have accidentally moved it to __skb_fill_page_desc_noacc(), so move it back to __skb_fill_page_desc() which is supposed to be doing pfmemalloc propagating. Signed-off-by: Yunsheng Lin CC: Pavel Begunkov Reviewed-by: Pavel Begunkov Link: https://lore.kernel.org/r/20230515050107.46397-1-linyunsheng@huawei.com Signed-off-by: Paolo Abeni --- include/linux/skbuff.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 00e8c435fa1a..4b8d55247198 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2426,11 +2426,6 @@ static inline void __skb_fill_page_desc_noacc(struct skb_shared_info *shinfo, { skb_frag_t *frag = &shinfo->frags[i]; - /* - * Propagate page pfmemalloc to the skb if we can. The problem is - * that not all callers have unique ownership of the page but rely - * on page_is_pfmemalloc doing the right thing(tm). - */ skb_frag_fill_page_desc(frag, page, off, size); } @@ -2463,6 +2458,11 @@ static inline void __skb_fill_page_desc(struct sk_buff *skb, int i, struct page *page, int off, int size) { __skb_fill_page_desc_noacc(skb_shinfo(skb), i, page, off, size); + + /* Propagate page pfmemalloc to the skb if we can. The problem is + * that not all callers have unique ownership of the page but rely + * on page_is_pfmemalloc doing the right thing(tm). + */ page = compound_head(page); if (page_is_pfmemalloc(page)) skb->pfmemalloc = true; -- cgit v1.2.3 From 31b2ebc0929e964f4edfbfa7129d43f7e3c17165 Mon Sep 17 00:00:00 2001 From: "Ritesh Harjani (IBM)" Date: Fri, 21 Apr 2023 15:16:12 +0530 Subject: fs/buffer.c: Add generic_buffers_fsync*() implementation Some of the higher layers like iomap takes inode_lock() when calling generic_write_sync(). Also writeback already happens from other paths without inode lock, so it's difficult to say that we really need sync_mapping_buffers() to take any inode locking here. Having said that, let's add generic_buffers_fsync/_noflush() implementation in buffer.c with no inode_lock/unlock() for now so that filesystems like ext2 and ext4's nojournal mode can use it. Ext4 when got converted to iomap for direct-io already copied it's own variant of __generic_file_fsync() without lock. This patch adds generic_buffers_fsync() & generic_buffers_fsync_noflush() implementations for use in filesystems like ext2 & ext4 respectively. Later we can review other filesystems as well to see if we can make generic_buffers_fsync/_noflush() which does not take any inode_lock() as the default path. Tested-by: Disha Goel Reviewed-by: Christoph Hellwig Signed-off-by: Ritesh Harjani (IBM) Signed-off-by: Jan Kara Message-Id: --- fs/buffer.c | 70 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/buffer_head.h | 4 +++ 2 files changed, 74 insertions(+) (limited to 'include/linux') diff --git a/fs/buffer.c b/fs/buffer.c index a7fc561758b1..00cad2658a07 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -592,6 +592,76 @@ int sync_mapping_buffers(struct address_space *mapping) } EXPORT_SYMBOL(sync_mapping_buffers); +/** + * generic_buffers_fsync_noflush - generic buffer fsync implementation + * for simple filesystems with no inode lock + * + * @file: file to synchronize + * @start: start offset in bytes + * @end: end offset in bytes (inclusive) + * @datasync: only synchronize essential metadata if true + * + * This is a generic implementation of the fsync method for simple + * filesystems which track all non-inode metadata in the buffers list + * hanging off the address_space structure. + */ +int generic_buffers_fsync_noflush(struct file *file, loff_t start, loff_t end, + bool datasync) +{ + struct inode *inode = file->f_mapping->host; + int err; + int ret; + + err = file_write_and_wait_range(file, start, end); + if (err) + return err; + + ret = sync_mapping_buffers(inode->i_mapping); + if (!(inode->i_state & I_DIRTY_ALL)) + goto out; + if (datasync && !(inode->i_state & I_DIRTY_DATASYNC)) + goto out; + + err = sync_inode_metadata(inode, 1); + if (ret == 0) + ret = err; + +out: + /* check and advance again to catch errors after syncing out buffers */ + err = file_check_and_advance_wb_err(file); + if (ret == 0) + ret = err; + return ret; +} +EXPORT_SYMBOL(generic_buffers_fsync_noflush); + +/** + * generic_buffers_fsync - generic buffer fsync implementation + * for simple filesystems with no inode lock + * + * @file: file to synchronize + * @start: start offset in bytes + * @end: end offset in bytes (inclusive) + * @datasync: only synchronize essential metadata if true + * + * This is a generic implementation of the fsync method for simple + * filesystems which track all non-inode metadata in the buffers list + * hanging off the address_space structure. This also makes sure that + * a device cache flush operation is called at the end. + */ +int generic_buffers_fsync(struct file *file, loff_t start, loff_t end, + bool datasync) +{ + struct inode *inode = file->f_mapping->host; + int ret; + + ret = generic_buffers_fsync_noflush(file, start, end, datasync); + if (!ret) + ret = blkdev_issue_flush(inode->i_sb->s_bdev); + return ret; +} +EXPORT_SYMBOL(generic_buffers_fsync); + /* * Called when we've recently written block `bblock', and it is known that * `bblock' was for a buffer_boundary() buffer. This means that the block at diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 1520793c72da..1bd73cefd311 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -217,6 +217,10 @@ int inode_has_buffers(struct inode *); void invalidate_inode_buffers(struct inode *); int remove_inode_buffers(struct inode *inode); int sync_mapping_buffers(struct address_space *mapping); +int generic_buffers_fsync_noflush(struct file *file, loff_t start, loff_t end, + bool datasync); +int generic_buffers_fsync(struct file *file, loff_t start, loff_t end, + bool datasync); void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len); static inline void clean_bdev_bh_alias(struct buffer_head *bh) -- cgit v1.2.3 From 9a38cb27668e275ed912e67388cf11f454a24cc6 Mon Sep 17 00:00:00 2001 From: Sumit Gupta Date: Thu, 11 May 2023 23:02:04 +0530 Subject: memory: tegra: Add interconnect support for DRAM scaling in Tegra234 Add Interconnect framework support to dynamically set the DRAM bandwidth from different clients. Both the MC and EMC drivers are added as ICC providers. The path for any request is: MC-Client[1-n] -> MC -> EMC -> EMEM/DRAM MC client's request for bandwidth will go to the MC driver which passes the client request info like BPMP Client ID, Client type and the Bandwidth to the BPMP-FW. The final DRAM freq to achieve the requested bandwidth is set by the BPMP-FW based on the passed parameters. Signed-off-by: Sumit Gupta Acked-by: Krzysztof Kozlowski Signed-off-by: Thierry Reding --- drivers/memory/tegra/mc.c | 5 ++ drivers/memory/tegra/tegra186-emc.c | 133 ++++++++++++++++++++++++++++++++++ drivers/memory/tegra/tegra234.c | 138 +++++++++++++++++++++++++++++++++++- include/linux/tegra-icc.h | 65 +++++++++++++++++ include/soc/tegra/mc.h | 7 ++ 5 files changed, 347 insertions(+), 1 deletion(-) create mode 100644 include/linux/tegra-icc.h (limited to 'include/linux') diff --git a/drivers/memory/tegra/mc.c b/drivers/memory/tegra/mc.c index 9082b6c3763d..983455b1f98d 100644 --- a/drivers/memory/tegra/mc.c +++ b/drivers/memory/tegra/mc.c @@ -15,6 +15,7 @@ #include #include #include +#include #include @@ -792,6 +793,8 @@ static int tegra_mc_interconnect_setup(struct tegra_mc *mc) mc->provider.data = &mc->provider; mc->provider.set = mc->soc->icc_ops->set; mc->provider.aggregate = mc->soc->icc_ops->aggregate; + mc->provider.get_bw = mc->soc->icc_ops->get_bw; + mc->provider.xlate = mc->soc->icc_ops->xlate; mc->provider.xlate_extended = mc->soc->icc_ops->xlate_extended; icc_provider_init(&mc->provider); @@ -824,6 +827,8 @@ static int tegra_mc_interconnect_setup(struct tegra_mc *mc) err = icc_link_create(node, TEGRA_ICC_MC); if (err) goto remove_nodes; + + node->data = (struct tegra_mc_client *)&(mc->soc->clients[i]); } err = icc_provider_register(&mc->provider); diff --git a/drivers/memory/tegra/tegra186-emc.c b/drivers/memory/tegra/tegra186-emc.c index e935ad4e95b6..6ad8a4023dd7 100644 --- a/drivers/memory/tegra/tegra186-emc.c +++ b/drivers/memory/tegra/tegra186-emc.c @@ -7,9 +7,11 @@ #include #include #include +#include #include #include +#include "mc.h" struct tegra186_emc_dvfs { unsigned long latency; @@ -29,8 +31,15 @@ struct tegra186_emc { unsigned long min_rate; unsigned long max_rate; } debugfs; + + struct icc_provider provider; }; +static inline struct tegra186_emc *to_tegra186_emc(struct icc_provider *provider) +{ + return container_of(provider, struct tegra186_emc, provider); +} + /* * debugfs interface * @@ -146,8 +155,102 @@ DEFINE_DEBUGFS_ATTRIBUTE(tegra186_emc_debug_max_rate_fops, tegra186_emc_debug_max_rate_get, tegra186_emc_debug_max_rate_set, "%llu\n"); +/* + * tegra_emc_icc_set_bw() - Set BW api for EMC provider + * @src: ICC node for External Memory Controller (EMC) + * @dst: ICC node for External Memory (DRAM) + * + * Do nothing here as info to BPMP-FW is now passed in the BW set function + * of the MC driver. BPMP-FW sets the final Freq based on the passed values. + */ +static int tegra_emc_icc_set_bw(struct icc_node *src, struct icc_node *dst) +{ + return 0; +} + +static struct icc_node * +tegra_emc_of_icc_xlate(struct of_phandle_args *spec, void *data) +{ + struct icc_provider *provider = data; + struct icc_node *node; + + /* External Memory is the only possible ICC route */ + list_for_each_entry(node, &provider->nodes, node_list) { + if (node->id != TEGRA_ICC_EMEM) + continue; + + return node; + } + + return ERR_PTR(-EPROBE_DEFER); +} + +static int tegra_emc_icc_get_init_bw(struct icc_node *node, u32 *avg, u32 *peak) +{ + *avg = 0; + *peak = 0; + + return 0; +} + +static int tegra_emc_interconnect_init(struct tegra186_emc *emc) +{ + struct tegra_mc *mc = dev_get_drvdata(emc->dev->parent); + const struct tegra_mc_soc *soc = mc->soc; + struct icc_node *node; + int err; + + emc->provider.dev = emc->dev; + emc->provider.set = tegra_emc_icc_set_bw; + emc->provider.data = &emc->provider; + emc->provider.aggregate = soc->icc_ops->aggregate; + emc->provider.xlate = tegra_emc_of_icc_xlate; + emc->provider.get_bw = tegra_emc_icc_get_init_bw; + + icc_provider_init(&emc->provider); + + /* create External Memory Controller node */ + node = icc_node_create(TEGRA_ICC_EMC); + if (IS_ERR(node)) { + err = PTR_ERR(node); + goto err_msg; + } + + node->name = "External Memory Controller"; + icc_node_add(node, &emc->provider); + + /* link External Memory Controller to External Memory (DRAM) */ + err = icc_link_create(node, TEGRA_ICC_EMEM); + if (err) + goto remove_nodes; + + /* create External Memory node */ + node = icc_node_create(TEGRA_ICC_EMEM); + if (IS_ERR(node)) { + err = PTR_ERR(node); + goto remove_nodes; + } + + node->name = "External Memory (DRAM)"; + icc_node_add(node, &emc->provider); + + err = icc_provider_register(&emc->provider); + if (err) + goto remove_nodes; + + return 0; + +remove_nodes: + icc_nodes_remove(&emc->provider); +err_msg: + dev_err(emc->dev, "failed to initialize ICC: %d\n", err); + + return err; +} + static int tegra186_emc_probe(struct platform_device *pdev) { + struct tegra_mc *mc = dev_get_drvdata(pdev->dev.parent); struct mrq_emc_dvfs_latency_response response; struct tegra_bpmp_message msg; struct tegra186_emc *emc; @@ -236,6 +339,32 @@ static int tegra186_emc_probe(struct platform_device *pdev) debugfs_create_file("max_rate", S_IRUGO | S_IWUSR, emc->debugfs.root, emc, &tegra186_emc_debug_max_rate_fops); + if (mc && mc->soc->icc_ops) { + if (tegra_bpmp_mrq_is_supported(emc->bpmp, MRQ_BWMGR_INT)) { + mc->bwmgr_mrq_supported = true; + + /* + * MC driver probe can't get BPMP reference as it gets probed + * earlier than BPMP. So, save the BPMP ref got from the EMC + * DT node in the mc->bpmp and use it in MC's icc_set hook. + */ + mc->bpmp = emc->bpmp; + barrier(); + } + + /* + * Initialize the ICC even if BPMP-FW doesn't support 'MRQ_BWMGR_INT'. + * Use the flag 'mc->bwmgr_mrq_supported' within MC driver and return + * EINVAL instead of passing the request to BPMP-FW later when the BW + * request is made by client with 'icc_set_bw()' call. + */ + err = tegra_emc_interconnect_init(emc); + if (err) { + mc->bpmp = NULL; + goto put_bpmp; + } + } + return 0; put_bpmp: @@ -245,9 +374,12 @@ put_bpmp: static int tegra186_emc_remove(struct platform_device *pdev) { + struct tegra_mc *mc = dev_get_drvdata(pdev->dev.parent); struct tegra186_emc *emc = platform_get_drvdata(pdev); debugfs_remove_recursive(emc->debugfs.root); + + mc->bpmp = NULL; tegra_bpmp_put(emc->bpmp); return 0; @@ -272,6 +404,7 @@ static struct platform_driver tegra186_emc_driver = { .name = "tegra186-emc", .of_match_table = tegra186_emc_of_match, .suppress_bind_attrs = true, + .sync_state = icc_sync_state, }, .probe = tegra186_emc_probe, .remove = tegra186_emc_remove, diff --git a/drivers/memory/tegra/tegra234.c b/drivers/memory/tegra/tegra234.c index 02dcc5748bba..56d911926d54 100644 --- a/drivers/memory/tegra/tegra234.c +++ b/drivers/memory/tegra/tegra234.c @@ -1,18 +1,23 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) 2021-2022, NVIDIA CORPORATION. All rights reserved. + * Copyright (C) 2022-2023, NVIDIA CORPORATION. All rights reserved. */ #include #include +#include +#include +#include #include "mc.h" static const struct tegra_mc_client tegra234_mc_clients[] = { { .id = TEGRA234_MEMORY_CLIENT_MGBEARD, .name = "mgbeard", + .bpmp_id = TEGRA_ICC_BPMP_EQOS, + .type = TEGRA_ICC_NISO, .sid = TEGRA234_SID_MGBE, .regs = { .sid = { @@ -23,6 +28,8 @@ static const struct tegra_mc_client tegra234_mc_clients[] = { }, { .id = TEGRA234_MEMORY_CLIENT_MGBEBRD, .name = "mgbebrd", + .bpmp_id = TEGRA_ICC_BPMP_EQOS, + .type = TEGRA_ICC_NISO, .sid = TEGRA234_SID_MGBE_VF1, .regs = { .sid = { @@ -33,6 +40,8 @@ static const struct tegra_mc_client tegra234_mc_clients[] = { }, { .id = TEGRA234_MEMORY_CLIENT_MGBECRD, .name = "mgbecrd", + .bpmp_id = TEGRA_ICC_BPMP_EQOS, + .type = TEGRA_ICC_NISO, .sid = TEGRA234_SID_MGBE_VF2, .regs = { .sid = { @@ -43,6 +52,8 @@ static const struct tegra_mc_client tegra234_mc_clients[] = { }, { .id = TEGRA234_MEMORY_CLIENT_MGBEDRD, .name = "mgbedrd", + .bpmp_id = TEGRA_ICC_BPMP_EQOS, + .type = TEGRA_ICC_NISO, .sid = TEGRA234_SID_MGBE_VF3, .regs = { .sid = { @@ -52,6 +63,8 @@ static const struct tegra_mc_client tegra234_mc_clients[] = { }, }, { .id = TEGRA234_MEMORY_CLIENT_MGBEAWR, + .bpmp_id = TEGRA_ICC_BPMP_EQOS, + .type = TEGRA_ICC_NISO, .name = "mgbeawr", .sid = TEGRA234_SID_MGBE, .regs = { @@ -63,6 +76,8 @@ static const struct tegra_mc_client tegra234_mc_clients[] = { }, { .id = TEGRA234_MEMORY_CLIENT_MGBEBWR, .name = "mgbebwr", + .bpmp_id = TEGRA_ICC_BPMP_EQOS, + .type = TEGRA_ICC_NISO, .sid = TEGRA234_SID_MGBE_VF1, .regs = { .sid = { @@ -73,6 +88,8 @@ static const struct tegra_mc_client tegra234_mc_clients[] = { }, { .id = TEGRA234_MEMORY_CLIENT_MGBECWR, .name = "mgbecwr", + .bpmp_id = TEGRA_ICC_BPMP_EQOS, + .type = TEGRA_ICC_NISO, .sid = TEGRA234_SID_MGBE_VF2, .regs = { .sid = { @@ -83,6 +100,8 @@ static const struct tegra_mc_client tegra234_mc_clients[] = { }, { .id = TEGRA234_MEMORY_CLIENT_SDMMCRAB, .name = "sdmmcrab", + .bpmp_id = TEGRA_ICC_BPMP_SDMMC_4, + .type = TEGRA_ICC_NISO, .sid = TEGRA234_SID_SDMMC4, .regs = { .sid = { @@ -93,6 +112,8 @@ static const struct tegra_mc_client tegra234_mc_clients[] = { }, { .id = TEGRA234_MEMORY_CLIENT_MGBEDWR, .name = "mgbedwr", + .bpmp_id = TEGRA_ICC_BPMP_EQOS, + .type = TEGRA_ICC_NISO, .sid = TEGRA234_SID_MGBE_VF3, .regs = { .sid = { @@ -103,6 +124,8 @@ static const struct tegra_mc_client tegra234_mc_clients[] = { }, { .id = TEGRA234_MEMORY_CLIENT_SDMMCWAB, .name = "sdmmcwab", + .bpmp_id = TEGRA_ICC_BPMP_SDMMC_4, + .type = TEGRA_ICC_NISO, .sid = TEGRA234_SID_SDMMC4, .regs = { .sid = { @@ -153,6 +176,8 @@ static const struct tegra_mc_client tegra234_mc_clients[] = { }, { .id = TEGRA234_MEMORY_CLIENT_APEDMAR, .name = "apedmar", + .bpmp_id = TEGRA_ICC_BPMP_APEDMA, + .type = TEGRA_ICC_ISO_AUDIO, .sid = TEGRA234_SID_APE, .regs = { .sid = { @@ -163,6 +188,8 @@ static const struct tegra_mc_client tegra234_mc_clients[] = { }, { .id = TEGRA234_MEMORY_CLIENT_APEDMAW, .name = "apedmaw", + .bpmp_id = TEGRA_ICC_BPMP_APEDMA, + .type = TEGRA_ICC_ISO_AUDIO, .sid = TEGRA234_SID_APE, .regs = { .sid = { @@ -333,6 +360,114 @@ static const struct tegra_mc_client tegra234_mc_clients[] = { }, }; +/* + * tegra234_mc_icc_set() - Pass MC client info to the BPMP-FW + * @src: ICC node for Memory Controller's (MC) Client + * @dst: ICC node for Memory Controller (MC) + * + * Passing the current request info from the MC to the BPMP-FW where + * LA and PTSA registers are accessed and the final EMC freq is set + * based on client_id, type, latency and bandwidth. + * icc_set_bw() makes set_bw calls for both MC and EMC providers in + * sequence. Both the calls are protected by 'mutex_lock(&icc_lock)'. + * So, the data passed won't be updated by concurrent set calls from + * other clients. + */ +static int tegra234_mc_icc_set(struct icc_node *src, struct icc_node *dst) +{ + struct tegra_mc *mc = icc_provider_to_tegra_mc(dst->provider); + struct mrq_bwmgr_int_request bwmgr_req = { 0 }; + struct mrq_bwmgr_int_response bwmgr_resp = { 0 }; + const struct tegra_mc_client *pclient = src->data; + struct tegra_bpmp_message msg; + int ret; + + /* + * Same Src and Dst node will happen during boot from icc_node_add(). + * This can be used to pre-initialize and set bandwidth for all clients + * before their drivers are loaded. We are skipping this case as for us, + * the pre-initialization already happened in Bootloader(MB2) and BPMP-FW. + */ + if (src->id == dst->id) + return 0; + + if (!mc->bwmgr_mrq_supported) + return -EINVAL; + + if (!mc->bpmp) { + dev_err(mc->dev, "BPMP reference NULL\n"); + return -ENOENT; + } + + if (pclient->type == TEGRA_ICC_NISO) + bwmgr_req.bwmgr_calc_set_req.niso_bw = src->avg_bw; + else + bwmgr_req.bwmgr_calc_set_req.iso_bw = src->avg_bw; + + bwmgr_req.bwmgr_calc_set_req.client_id = pclient->bpmp_id; + + bwmgr_req.cmd = CMD_BWMGR_INT_CALC_AND_SET; + bwmgr_req.bwmgr_calc_set_req.mc_floor = src->peak_bw; + bwmgr_req.bwmgr_calc_set_req.floor_unit = BWMGR_INT_UNIT_KBPS; + + memset(&msg, 0, sizeof(msg)); + msg.mrq = MRQ_BWMGR_INT; + msg.tx.data = &bwmgr_req; + msg.tx.size = sizeof(bwmgr_req); + msg.rx.data = &bwmgr_resp; + msg.rx.size = sizeof(bwmgr_resp); + + ret = tegra_bpmp_transfer(mc->bpmp, &msg); + if (ret < 0) { + dev_err(mc->dev, "BPMP transfer failed: %d\n", ret); + goto error; + } + if (msg.rx.ret < 0) { + pr_err("failed to set bandwidth for %u: %d\n", + bwmgr_req.bwmgr_calc_set_req.client_id, msg.rx.ret); + ret = -EINVAL; + } + +error: + return ret; +} + +static struct icc_node* +tegra234_mc_of_icc_xlate(struct of_phandle_args *spec, void *data) +{ + struct tegra_mc *mc = icc_provider_to_tegra_mc(data); + unsigned int cl_id = spec->args[0]; + struct icc_node *node; + + list_for_each_entry(node, &mc->provider.nodes, node_list) { + if (node->id != cl_id) + continue; + + return node; + } + + /* + * If a client driver calls devm_of_icc_get() before the MC driver + * is probed, then return EPROBE_DEFER to the client driver. + */ + return ERR_PTR(-EPROBE_DEFER); +} + +static int tegra234_mc_icc_get_init_bw(struct icc_node *node, u32 *avg, u32 *peak) +{ + *avg = 0; + *peak = 0; + + return 0; +} + +static const struct tegra_mc_icc_ops tegra234_mc_icc_ops = { + .xlate = tegra234_mc_of_icc_xlate, + .aggregate = icc_std_aggregate, + .get_bw = tegra234_mc_icc_get_init_bw, + .set = tegra234_mc_icc_set, +}; + const struct tegra_mc_soc tegra234_mc_soc = { .num_clients = ARRAY_SIZE(tegra234_mc_clients), .clients = tegra234_mc_clients, @@ -345,6 +480,7 @@ const struct tegra_mc_soc tegra234_mc_soc = { MC_INT_SECURITY_VIOLATION | MC_INT_DECERR_EMEM, .has_addr_hi_reg = true, .ops = &tegra186_mc_ops, + .icc_ops = &tegra234_mc_icc_ops, .ch_intmask = 0x0000ff00, .global_intstatus_channel_shift = 8, /* diff --git a/include/linux/tegra-icc.h b/include/linux/tegra-icc.h new file mode 100644 index 000000000000..4b4d4bee290c --- /dev/null +++ b/include/linux/tegra-icc.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2022-2023 NVIDIA CORPORATION. All rights reserved. + */ + +#ifndef LINUX_TEGRA_ICC_H +#define LINUX_TEGRA_ICC_H + +enum tegra_icc_client_type { + TEGRA_ICC_NONE, + TEGRA_ICC_NISO, + TEGRA_ICC_ISO_DISPLAY, + TEGRA_ICC_ISO_VI, + TEGRA_ICC_ISO_AUDIO, + TEGRA_ICC_ISO_VIFAL, +}; + +/* ICC ID's for MC client's used in BPMP */ +#define TEGRA_ICC_BPMP_DEBUG 1 +#define TEGRA_ICC_BPMP_CPU_CLUSTER0 2 +#define TEGRA_ICC_BPMP_CPU_CLUSTER1 3 +#define TEGRA_ICC_BPMP_CPU_CLUSTER2 4 +#define TEGRA_ICC_BPMP_GPU 5 +#define TEGRA_ICC_BPMP_CACTMON 6 +#define TEGRA_ICC_BPMP_DISPLAY 7 +#define TEGRA_ICC_BPMP_VI 8 +#define TEGRA_ICC_BPMP_EQOS 9 +#define TEGRA_ICC_BPMP_PCIE_0 10 +#define TEGRA_ICC_BPMP_PCIE_1 11 +#define TEGRA_ICC_BPMP_PCIE_2 12 +#define TEGRA_ICC_BPMP_PCIE_3 13 +#define TEGRA_ICC_BPMP_PCIE_4 14 +#define TEGRA_ICC_BPMP_PCIE_5 15 +#define TEGRA_ICC_BPMP_PCIE_6 16 +#define TEGRA_ICC_BPMP_PCIE_7 17 +#define TEGRA_ICC_BPMP_PCIE_8 18 +#define TEGRA_ICC_BPMP_PCIE_9 19 +#define TEGRA_ICC_BPMP_PCIE_10 20 +#define TEGRA_ICC_BPMP_DLA_0 21 +#define TEGRA_ICC_BPMP_DLA_1 22 +#define TEGRA_ICC_BPMP_SDMMC_1 23 +#define TEGRA_ICC_BPMP_SDMMC_2 24 +#define TEGRA_ICC_BPMP_SDMMC_3 25 +#define TEGRA_ICC_BPMP_SDMMC_4 26 +#define TEGRA_ICC_BPMP_NVDEC 27 +#define TEGRA_ICC_BPMP_NVENC 28 +#define TEGRA_ICC_BPMP_NVJPG_0 29 +#define TEGRA_ICC_BPMP_NVJPG_1 30 +#define TEGRA_ICC_BPMP_OFAA 31 +#define TEGRA_ICC_BPMP_XUSB_HOST 32 +#define TEGRA_ICC_BPMP_XUSB_DEV 33 +#define TEGRA_ICC_BPMP_TSEC 34 +#define TEGRA_ICC_BPMP_VIC 35 +#define TEGRA_ICC_BPMP_APE 36 +#define TEGRA_ICC_BPMP_APEDMA 37 +#define TEGRA_ICC_BPMP_SE 38 +#define TEGRA_ICC_BPMP_ISP 39 +#define TEGRA_ICC_BPMP_HDA 40 +#define TEGRA_ICC_BPMP_VIFAL 41 +#define TEGRA_ICC_BPMP_VI2FAL 42 +#define TEGRA_ICC_BPMP_VI2 43 +#define TEGRA_ICC_BPMP_RCE 44 +#define TEGRA_ICC_BPMP_PVA 45 + +#endif /* LINUX_TEGRA_ICC_H */ diff --git a/include/soc/tegra/mc.h b/include/soc/tegra/mc.h index 51a2263e1bc5..900d88b26fae 100644 --- a/include/soc/tegra/mc.h +++ b/include/soc/tegra/mc.h @@ -13,6 +13,7 @@ #include #include #include +#include struct clk; struct device; @@ -26,6 +27,8 @@ struct tegra_mc_timing { struct tegra_mc_client { unsigned int id; + unsigned int bpmp_id; + enum tegra_icc_client_type type; const char *name; /* * For Tegra210 and earlier, this is the SWGROUP ID used for IOVA translations in the @@ -166,8 +169,10 @@ struct tegra_mc_icc_ops { int (*set)(struct icc_node *src, struct icc_node *dst); int (*aggregate)(struct icc_node *node, u32 tag, u32 avg_bw, u32 peak_bw, u32 *agg_avg, u32 *agg_peak); + struct icc_node* (*xlate)(struct of_phandle_args *spec, void *data); struct icc_node_data *(*xlate_extended)(struct of_phandle_args *spec, void *data); + int (*get_bw)(struct icc_node *node, u32 *avg, u32 *peak); }; struct tegra_mc_ops { @@ -214,6 +219,7 @@ struct tegra_mc_soc { }; struct tegra_mc { + struct tegra_bpmp *bpmp; struct device *dev; struct tegra_smmu *smmu; struct gart_device *gart; @@ -229,6 +235,7 @@ struct tegra_mc { struct tegra_mc_timing *timings; unsigned int num_timings; + bool bwmgr_mrq_supported; struct reset_controller_dev reset; struct icc_provider provider; -- cgit v1.2.3 From 514ca14ed5444b911de59ed3381dfd195d99fe4b Mon Sep 17 00:00:00 2001 From: "ndesaulniers@google.com" Date: Mon, 17 Apr 2023 15:00:05 -0700 Subject: start_kernel: Add __no_stack_protector function attribute Back during the discussion of commit a9a3ed1eff36 ("x86: Fix early boot crash on gcc-10, third try") we discussed the need for a function attribute to control the omission of stack protectors on a per-function basis; at the time Clang had support for no_stack_protector but GCC did not. This was fixed in gcc-11. Now that the function attribute is available, let's start using it. Callers of boot_init_stack_canary need to use this function attribute unless they're compiled with -fno-stack-protector, otherwise the canary stored in the stack slot of the caller will differ upon the call to boot_init_stack_canary. This will lead to a call to __stack_chk_fail() then panic. Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94722 Link: https://lore.kernel.org/all/20200316130414.GC12561@hirez.programming.kicks-ass.net/ Tested-by: Nathan Chancellor Acked-by: Michael Ellerman (powerpc) Acked-by: Miguel Ojeda Acked-by: Peter Zijlstra (Intel) Signed-off-by: Nick Desaulniers Link: https://lore.kernel.org/r/20230412-no_stackp-v2-1-116f9fe4bbe7@google.com Signed-off-by: Josh Poimboeuf Signed-off-by: ndesaulniers@google.com --- arch/powerpc/kernel/smp.c | 1 + include/linux/compiler_attributes.h | 12 ++++++++++++ init/main.c | 3 ++- 3 files changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 265801a3e94c..6903a7222273 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1605,6 +1605,7 @@ static void add_cpu_to_masks(int cpu) } /* Activate a secondary processor. */ +__no_stack_protector void start_secondary(void *unused) { unsigned int cpu = raw_smp_processor_id(); diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index e659cb6fded3..84864767a56a 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -255,6 +255,18 @@ */ #define __noreturn __attribute__((__noreturn__)) +/* + * Optional: only supported since GCC >= 11.1, clang >= 7.0. + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-no_005fstack_005fprotector-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#no-stack-protector-safebuffers + */ +#if __has_attribute(__no_stack_protector__) +# define __no_stack_protector __attribute__((__no_stack_protector__)) +#else +# define __no_stack_protector +#endif + /* * Optional: not supported by gcc. * diff --git a/init/main.c b/init/main.c index af50044deed5..c445c1fb19b9 100644 --- a/init/main.c +++ b/init/main.c @@ -877,7 +877,8 @@ static void __init print_unknown_bootoptions(void) memblock_free(unknown_options, len); } -asmlinkage __visible void __init __no_sanitize_address __noreturn start_kernel(void) +asmlinkage __visible __init __no_sanitize_address __noreturn __no_stack_protector +void start_kernel(void) { char *command_line; char *after_dashes; -- 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/linux') 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 42ae6f1695beed57958e7a2554e6d52dddc56e43 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 16 May 2023 14:55:34 +0200 Subject: dmaengine: ste_dma40: Remove platform data The Ux500 is device tree-only since ages. Delete the platform data header and push it into or next to the driver instead. Drop the non-DT probe path since this will not happen. Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20230417-ux500-dma40-cleanup-v3-4-60bfa6785968@linaro.org Signed-off-by: Vinod Koul --- drivers/dma/ste_dma40.c | 56 +++++--- drivers/dma/ste_dma40.h | 110 +++++++++++++++ drivers/dma/ste_dma40_ll.c | 3 +- include/linux/platform_data/dma-ste-dma40.h | 209 ---------------------------- 4 files changed, 150 insertions(+), 228 deletions(-) create mode 100644 drivers/dma/ste_dma40.h delete mode 100644 include/linux/platform_data/dma-ste-dma40.h (limited to 'include/linux') diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c index 813de4efced5..48c9606cfd46 100644 --- a/drivers/dma/ste_dma40.c +++ b/drivers/dma/ste_dma40.c @@ -23,11 +23,39 @@ #include #include #include -#include #include "dmaengine.h" +#include "ste_dma40.h" #include "ste_dma40_ll.h" +/** + * struct stedma40_platform_data - Configuration struct for the dma device. + * + * @dev_tx: mapping between destination event line and io address + * @dev_rx: mapping between source event line and io address + * @disabled_channels: A vector, ending with -1, that marks physical channels + * that are for different reasons not available for the driver. + * @soft_lli_chans: A vector, that marks physical channels will use LLI by SW + * which avoids HW bug that exists in some versions of the controller. + * SoftLLI introduces relink overhead that could impact performace for + * certain use cases. + * @num_of_soft_lli_chans: The number of channels that needs to be configured + * to use SoftLLI. + * @use_esram_lcla: flag for mapping the lcla into esram region + * @num_of_memcpy_chans: The number of channels reserved for memcpy. + * @num_of_phy_chans: The number of physical channels implemented in HW. + * 0 means reading the number of channels from DMA HW but this is only valid + * for 'multiple of 4' channels, like 8. + */ +struct stedma40_platform_data { + int disabled_channels[STEDMA40_MAX_PHYS]; + int *soft_lli_chans; + int num_of_soft_lli_chans; + bool use_esram_lcla; + int num_of_memcpy_chans; + int num_of_phy_chans; +}; + #define D40_NAME "dma40" #define D40_PHY_CHAN -1 @@ -2269,7 +2297,7 @@ d40_prep_sg(struct dma_chan *dchan, struct scatterlist *sg_src, return NULL; } -bool stedma40_filter(struct dma_chan *chan, void *data) +static bool stedma40_filter(struct dma_chan *chan, void *data) { struct stedma40_chan_cfg *info = data; struct d40_chan *d40c = @@ -2288,7 +2316,6 @@ bool stedma40_filter(struct dma_chan *chan, void *data) return err == 0; } -EXPORT_SYMBOL(stedma40_filter); static void __d40_set_prio_rt(struct d40_chan *d40c, int dev_type, bool src) { @@ -3517,16 +3544,9 @@ static int __init d40_probe(struct platform_device *pdev) int num_reserved_chans; u32 val; - if (!plat_data) { - if (np) { - if (d40_of_probe(pdev, np)) { - ret = -ENOMEM; - goto report_failure; - } - } else { - d40_err(dev, "No pdata or Device Tree provided\n"); - goto report_failure; - } + if (d40_of_probe(pdev, np)) { + ret = -ENOMEM; + goto report_failure; } base = d40_hw_detect_init(pdev); @@ -3650,11 +3670,11 @@ static int __init d40_probe(struct platform_device *pdev) d40_hw_init(base); - if (np) { - ret = of_dma_controller_register(np, d40_xlate, NULL); - if (ret) - dev_err(dev, - "could not register of_dma_controller\n"); + ret = of_dma_controller_register(np, d40_xlate, NULL); + if (ret) { + dev_err(dev, + "could not register of_dma_controller\n"); + goto destroy_cache; } dev_info(base->dev, "initialized\n"); diff --git a/drivers/dma/ste_dma40.h b/drivers/dma/ste_dma40.h new file mode 100644 index 000000000000..c697bfe16a01 --- /dev/null +++ b/drivers/dma/ste_dma40.h @@ -0,0 +1,110 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef STE_DMA40_H +#define STE_DMA40_H + +/* + * Maxium size for a single dma descriptor + * Size is limited to 16 bits. + * Size is in the units of addr-widths (1,2,4,8 bytes) + * Larger transfers will be split up to multiple linked desc + */ +#define STEDMA40_MAX_SEG_SIZE 0xFFFF + +/* dev types for memcpy */ +#define STEDMA40_DEV_DST_MEMORY (-1) +#define STEDMA40_DEV_SRC_MEMORY (-1) + +enum stedma40_mode { + STEDMA40_MODE_LOGICAL = 0, + STEDMA40_MODE_PHYSICAL, + STEDMA40_MODE_OPERATION, +}; + +enum stedma40_mode_opt { + STEDMA40_PCHAN_BASIC_MODE = 0, + STEDMA40_LCHAN_SRC_LOG_DST_LOG = 0, + STEDMA40_PCHAN_MODULO_MODE, + STEDMA40_PCHAN_DOUBLE_DST_MODE, + STEDMA40_LCHAN_SRC_PHY_DST_LOG, + STEDMA40_LCHAN_SRC_LOG_DST_PHY, +}; + +#define STEDMA40_ESIZE_8_BIT 0x0 +#define STEDMA40_ESIZE_16_BIT 0x1 +#define STEDMA40_ESIZE_32_BIT 0x2 +#define STEDMA40_ESIZE_64_BIT 0x3 + +/* The value 4 indicates that PEN-reg shall be set to 0 */ +#define STEDMA40_PSIZE_PHY_1 0x4 +#define STEDMA40_PSIZE_PHY_2 0x0 +#define STEDMA40_PSIZE_PHY_4 0x1 +#define STEDMA40_PSIZE_PHY_8 0x2 +#define STEDMA40_PSIZE_PHY_16 0x3 + +/* + * The number of elements differ in logical and + * physical mode + */ +#define STEDMA40_PSIZE_LOG_1 STEDMA40_PSIZE_PHY_2 +#define STEDMA40_PSIZE_LOG_4 STEDMA40_PSIZE_PHY_4 +#define STEDMA40_PSIZE_LOG_8 STEDMA40_PSIZE_PHY_8 +#define STEDMA40_PSIZE_LOG_16 STEDMA40_PSIZE_PHY_16 + +/* Maximum number of possible physical channels */ +#define STEDMA40_MAX_PHYS 32 + +enum stedma40_flow_ctrl { + STEDMA40_NO_FLOW_CTRL, + STEDMA40_FLOW_CTRL, +}; + +/** + * struct stedma40_half_channel_info - dst/src channel configuration + * + * @big_endian: true if the src/dst should be read as big endian + * @data_width: Data width of the src/dst hardware + * @p_size: Burst size + * @flow_ctrl: Flow control on/off. + */ +struct stedma40_half_channel_info { + bool big_endian; + enum dma_slave_buswidth data_width; + int psize; + enum stedma40_flow_ctrl flow_ctrl; +}; + +/** + * struct stedma40_chan_cfg - Structure to be filled by client drivers. + * + * @dir: MEM 2 MEM, PERIPH 2 MEM , MEM 2 PERIPH, PERIPH 2 PERIPH + * @high_priority: true if high-priority + * @realtime: true if realtime mode is to be enabled. Only available on DMA40 + * version 3+, i.e DB8500v2+ + * @mode: channel mode: physical, logical, or operation + * @mode_opt: options for the chosen channel mode + * @dev_type: src/dst device type (driver uses dir to figure out which) + * @src_info: Parameters for dst half channel + * @dst_info: Parameters for dst half channel + * @use_fixed_channel: if true, use physical channel specified by phy_channel + * @phy_channel: physical channel to use, only if use_fixed_channel is true + * + * This structure has to be filled by the client drivers. + * It is recommended to do all dma configurations for clients in the machine. + * + */ +struct stedma40_chan_cfg { + enum dma_transfer_direction dir; + bool high_priority; + bool realtime; + enum stedma40_mode mode; + enum stedma40_mode_opt mode_opt; + int dev_type; + struct stedma40_half_channel_info src_info; + struct stedma40_half_channel_info dst_info; + + bool use_fixed_channel; + int phy_channel; +}; + +#endif /* STE_DMA40_H */ diff --git a/drivers/dma/ste_dma40_ll.c b/drivers/dma/ste_dma40_ll.c index b5287c661eb7..4c489b126cb2 100644 --- a/drivers/dma/ste_dma40_ll.c +++ b/drivers/dma/ste_dma40_ll.c @@ -6,8 +6,9 @@ */ #include -#include +#include +#include "ste_dma40.h" #include "ste_dma40_ll.h" static u8 d40_width_to_bits(enum dma_slave_buswidth width) diff --git a/include/linux/platform_data/dma-ste-dma40.h b/include/linux/platform_data/dma-ste-dma40.h deleted file mode 100644 index 10641633facc..000000000000 --- a/include/linux/platform_data/dma-ste-dma40.h +++ /dev/null @@ -1,209 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) ST-Ericsson SA 2007-2010 - * Author: Per Forlin for ST-Ericsson - * Author: Jonas Aaberg for ST-Ericsson - */ - - -#ifndef STE_DMA40_H -#define STE_DMA40_H - -#include -#include -#include -#include - -/* - * Maxium size for a single dma descriptor - * Size is limited to 16 bits. - * Size is in the units of addr-widths (1,2,4,8 bytes) - * Larger transfers will be split up to multiple linked desc - */ -#define STEDMA40_MAX_SEG_SIZE 0xFFFF - -/* dev types for memcpy */ -#define STEDMA40_DEV_DST_MEMORY (-1) -#define STEDMA40_DEV_SRC_MEMORY (-1) - -enum stedma40_mode { - STEDMA40_MODE_LOGICAL = 0, - STEDMA40_MODE_PHYSICAL, - STEDMA40_MODE_OPERATION, -}; - -enum stedma40_mode_opt { - STEDMA40_PCHAN_BASIC_MODE = 0, - STEDMA40_LCHAN_SRC_LOG_DST_LOG = 0, - STEDMA40_PCHAN_MODULO_MODE, - STEDMA40_PCHAN_DOUBLE_DST_MODE, - STEDMA40_LCHAN_SRC_PHY_DST_LOG, - STEDMA40_LCHAN_SRC_LOG_DST_PHY, -}; - -#define STEDMA40_ESIZE_8_BIT 0x0 -#define STEDMA40_ESIZE_16_BIT 0x1 -#define STEDMA40_ESIZE_32_BIT 0x2 -#define STEDMA40_ESIZE_64_BIT 0x3 - -/* The value 4 indicates that PEN-reg shall be set to 0 */ -#define STEDMA40_PSIZE_PHY_1 0x4 -#define STEDMA40_PSIZE_PHY_2 0x0 -#define STEDMA40_PSIZE_PHY_4 0x1 -#define STEDMA40_PSIZE_PHY_8 0x2 -#define STEDMA40_PSIZE_PHY_16 0x3 - -/* - * The number of elements differ in logical and - * physical mode - */ -#define STEDMA40_PSIZE_LOG_1 STEDMA40_PSIZE_PHY_2 -#define STEDMA40_PSIZE_LOG_4 STEDMA40_PSIZE_PHY_4 -#define STEDMA40_PSIZE_LOG_8 STEDMA40_PSIZE_PHY_8 -#define STEDMA40_PSIZE_LOG_16 STEDMA40_PSIZE_PHY_16 - -/* Maximum number of possible physical channels */ -#define STEDMA40_MAX_PHYS 32 - -enum stedma40_flow_ctrl { - STEDMA40_NO_FLOW_CTRL, - STEDMA40_FLOW_CTRL, -}; - -/** - * struct stedma40_half_channel_info - dst/src channel configuration - * - * @big_endian: true if the src/dst should be read as big endian - * @data_width: Data width of the src/dst hardware - * @p_size: Burst size - * @flow_ctrl: Flow control on/off. - */ -struct stedma40_half_channel_info { - bool big_endian; - enum dma_slave_buswidth data_width; - int psize; - enum stedma40_flow_ctrl flow_ctrl; -}; - -/** - * struct stedma40_chan_cfg - Structure to be filled by client drivers. - * - * @dir: MEM 2 MEM, PERIPH 2 MEM , MEM 2 PERIPH, PERIPH 2 PERIPH - * @high_priority: true if high-priority - * @realtime: true if realtime mode is to be enabled. Only available on DMA40 - * version 3+, i.e DB8500v2+ - * @mode: channel mode: physical, logical, or operation - * @mode_opt: options for the chosen channel mode - * @dev_type: src/dst device type (driver uses dir to figure out which) - * @src_info: Parameters for dst half channel - * @dst_info: Parameters for dst half channel - * @use_fixed_channel: if true, use physical channel specified by phy_channel - * @phy_channel: physical channel to use, only if use_fixed_channel is true - * - * This structure has to be filled by the client drivers. - * It is recommended to do all dma configurations for clients in the machine. - * - */ -struct stedma40_chan_cfg { - enum dma_transfer_direction dir; - bool high_priority; - bool realtime; - enum stedma40_mode mode; - enum stedma40_mode_opt mode_opt; - int dev_type; - struct stedma40_half_channel_info src_info; - struct stedma40_half_channel_info dst_info; - - bool use_fixed_channel; - int phy_channel; -}; - -/** - * struct stedma40_platform_data - Configuration struct for the dma device. - * - * @dev_tx: mapping between destination event line and io address - * @dev_rx: mapping between source event line and io address - * @disabled_channels: A vector, ending with -1, that marks physical channels - * that are for different reasons not available for the driver. - * @soft_lli_chans: A vector, that marks physical channels will use LLI by SW - * which avoids HW bug that exists in some versions of the controller. - * SoftLLI introduces relink overhead that could impact performace for - * certain use cases. - * @num_of_soft_lli_chans: The number of channels that needs to be configured - * to use SoftLLI. - * @use_esram_lcla: flag for mapping the lcla into esram region - * @num_of_memcpy_chans: The number of channels reserved for memcpy. - * @num_of_phy_chans: The number of physical channels implemented in HW. - * 0 means reading the number of channels from DMA HW but this is only valid - * for 'multiple of 4' channels, like 8. - */ -struct stedma40_platform_data { - int disabled_channels[STEDMA40_MAX_PHYS]; - int *soft_lli_chans; - int num_of_soft_lli_chans; - bool use_esram_lcla; - int num_of_memcpy_chans; - int num_of_phy_chans; -}; - -#ifdef CONFIG_STE_DMA40 - -/** - * stedma40_filter() - Provides stedma40_chan_cfg to the - * ste_dma40 dma driver via the dmaengine framework. - * does some checking of what's provided. - * - * Never directly called by client. It used by dmaengine. - * @chan: dmaengine handle. - * @data: Must be of type: struct stedma40_chan_cfg and is - * the configuration of the framework. - * - * - */ - -bool stedma40_filter(struct dma_chan *chan, void *data); - -/** - * stedma40_slave_mem() - Transfers a raw data buffer to or from a slave - * (=device) - * - * @chan: dmaengine handle - * @addr: source or destination physicall address. - * @size: bytes to transfer - * @direction: direction of transfer - * @flags: is actually enum dma_ctrl_flags. See dmaengine.h - */ - -static inline struct -dma_async_tx_descriptor *stedma40_slave_mem(struct dma_chan *chan, - dma_addr_t addr, - unsigned int size, - enum dma_transfer_direction direction, - unsigned long flags) -{ - struct scatterlist sg; - sg_init_table(&sg, 1); - sg.dma_address = addr; - sg.length = size; - - return dmaengine_prep_slave_sg(chan, &sg, 1, direction, flags); -} - -#else -static inline bool stedma40_filter(struct dma_chan *chan, void *data) -{ - return false; -} - -static inline struct -dma_async_tx_descriptor *stedma40_slave_mem(struct dma_chan *chan, - dma_addr_t addr, - unsigned int size, - enum dma_transfer_direction direction, - unsigned long flags) -{ - return NULL; -} -#endif - -#endif -- cgit v1.2.3 From 26f457142d7ee2da20a5b701862230e4961423d9 Mon Sep 17 00:00:00 2001 From: Ricardo Koller Date: Wed, 26 Apr 2023 17:23:22 +0000 Subject: KVM: arm64: Export kvm_are_all_memslots_empty() Export kvm_are_all_memslots_empty(). This will be used by a future commit when checking before setting a capability. Signed-off-by: Ricardo Koller Reviewed-by: Shaoqin Huang Reviewed-by: Gavin Shan Link: https://lore.kernel.org/r/20230426172330.1439644-5-ricarkol@google.com Signed-off-by: Oliver Upton --- include/linux/kvm_host.h | 2 ++ virt/kvm/kvm_main.c | 3 ++- 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 0e571e973bc2..7651069ada46 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -991,6 +991,8 @@ static inline bool kvm_memslots_empty(struct kvm_memslots *slots) return RB_EMPTY_ROOT(&slots->gfn_tree); } +bool kvm_are_all_memslots_empty(struct kvm *kvm); + #define kvm_for_each_memslot(memslot, bkt, slots) \ hash_for_each(slots->id_hash, bkt, memslot, id_node[slots->node_idx]) \ if (WARN_ON_ONCE(!memslot->npages)) { \ diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index cb5c13eee193..13aed654111a 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -4598,7 +4598,7 @@ int __attribute__((weak)) kvm_vm_ioctl_enable_cap(struct kvm *kvm, return -EINVAL; } -static bool kvm_are_all_memslots_empty(struct kvm *kvm) +bool kvm_are_all_memslots_empty(struct kvm *kvm) { int i; @@ -4611,6 +4611,7 @@ static bool kvm_are_all_memslots_empty(struct kvm *kvm) return true; } +EXPORT_SYMBOL_GPL(kvm_are_all_memslots_empty); static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm, struct kvm_enable_cap *cap) -- cgit v1.2.3 From ead62aa370a81c4fb42a44c4edeafe13e0a3a703 Mon Sep 17 00:00:00 2001 From: Arne Welzel Date: Sat, 13 May 2023 11:18:40 +0200 Subject: fortify: strscpy: Fix flipped q and p docstring typo Fix typo in the strscpy() docstring where q and p were flipped. Signed-off-by: Arne Welzel Signed-off-by: Kees Cook --- include/linux/fortify-string.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index c9de1f59ee80..e29df83bff8a 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -299,8 +299,8 @@ extern ssize_t __real_strscpy(char *, const char *, size_t) __RENAME(strscpy); * @q: Where to copy the string from * @size: Size of destination buffer * - * Copy the source string @p, or as much of it as fits, into the destination - * @q buffer. The behavior is undefined if the string buffers overlap. The + * Copy the source string @q, or as much of it as fits, into the destination + * @p buffer. The behavior is undefined if the string buffers overlap. The * destination @p buffer is always NUL terminated, unless it's zero-sized. * * Preferred to strlcpy() since the API doesn't require reading memory -- cgit v1.2.3 From 21a2c74b0a2a784228c9e3af63cff96d0dea7b8a Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 7 Apr 2023 12:27:10 -0700 Subject: fortify: Use const variables for __member_size tracking The sizes reported by __member_size should never change in a given function. Mark them as such. Suggested-by: Miguel Ojeda Cc: linux-hardening@vger.kernel.org Signed-off-by: Kees Cook Reviewed-by: Nick Desaulniers Link: https://lore.kernel.org/r/20230407192717.636137-4-keescook@chromium.org --- include/linux/fortify-string.h | 42 +++++++++++++++++++++--------------------- 1 file changed, 21 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index e29df83bff8a..2e7a47b62ba2 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -20,7 +20,7 @@ void __write_overflow_field(size_t avail, size_t wanted) __compiletime_warning(" ({ \ char *__p = (char *)(p); \ size_t __ret = SIZE_MAX; \ - size_t __p_size = __member_size(p); \ + const size_t __p_size = __member_size(p); \ if (__p_size != SIZE_MAX && \ __builtin_constant_p(*__p)) { \ size_t __p_len = __p_size - 1; \ @@ -142,7 +142,7 @@ extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __FORTIFY_INLINE __diagnose_as(__builtin_strncpy, 1, 2, 3) char *strncpy(char * const POS p, const char *q, __kernel_size_t size) { - size_t p_size = __member_size(p); + const size_t p_size = __member_size(p); if (__compiletime_lessthan(p_size, size)) __write_overflow(); @@ -169,7 +169,7 @@ char *strncpy(char * const POS p, const char *q, __kernel_size_t size) __FORTIFY_INLINE __diagnose_as(__builtin_strcat, 1, 2) char *strcat(char * const POS p, const char *q) { - size_t p_size = __member_size(p); + const size_t p_size = __member_size(p); if (p_size == SIZE_MAX) return __underlying_strcat(p, q); @@ -191,8 +191,8 @@ extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(st */ __FORTIFY_INLINE __kernel_size_t strnlen(const char * const POS p, __kernel_size_t maxlen) { - size_t p_size = __member_size(p); - size_t p_len = __compiletime_strlen(p); + const size_t p_size = __member_size(p); + const size_t p_len = __compiletime_strlen(p); size_t ret; /* We can take compile-time actions when maxlen is const. */ @@ -233,8 +233,8 @@ __FORTIFY_INLINE __kernel_size_t strnlen(const char * const POS p, __kernel_size __FORTIFY_INLINE __diagnose_as(__builtin_strlen, 1) __kernel_size_t __fortify_strlen(const char * const POS p) { + const size_t p_size = __member_size(p); __kernel_size_t ret; - size_t p_size = __member_size(p); /* Give up if we don't know how large p is. */ if (p_size == SIZE_MAX) @@ -267,8 +267,8 @@ extern size_t __real_strlcpy(char *, const char *, size_t) __RENAME(strlcpy); */ __FORTIFY_INLINE size_t strlcpy(char * const POS p, const char * const POS q, size_t size) { - size_t p_size = __member_size(p); - size_t q_size = __member_size(q); + const size_t p_size = __member_size(p); + const size_t q_size = __member_size(q); size_t q_len; /* Full count of source string length. */ size_t len; /* Count of characters going into destination. */ @@ -318,10 +318,10 @@ extern ssize_t __real_strscpy(char *, const char *, size_t) __RENAME(strscpy); */ __FORTIFY_INLINE ssize_t strscpy(char * const POS p, const char * const POS q, size_t size) { - size_t len; /* Use string size rather than possible enclosing struct size. */ - size_t p_size = __member_size(p); - size_t q_size = __member_size(q); + const size_t p_size = __member_size(p); + const size_t q_size = __member_size(q); + size_t len; /* If we cannot get size of p and q default to call strscpy. */ if (p_size == SIZE_MAX && q_size == SIZE_MAX) @@ -394,9 +394,9 @@ __FORTIFY_INLINE ssize_t strscpy(char * const POS p, const char * const POS q, s __FORTIFY_INLINE __diagnose_as(__builtin_strncat, 1, 2, 3) char *strncat(char * const POS p, const char * const POS q, __kernel_size_t count) { + const size_t p_size = __member_size(p); + const size_t q_size = __member_size(q); size_t p_len, copy_len; - size_t p_size = __member_size(p); - size_t q_size = __member_size(q); if (p_size == SIZE_MAX && q_size == SIZE_MAX) return __underlying_strncat(p, q, count); @@ -639,7 +639,7 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan); __FORTIFY_INLINE void *memscan(void * const POS0 p, int c, __kernel_size_t size) { - size_t p_size = __struct_size(p); + const size_t p_size = __struct_size(p); if (__compiletime_lessthan(p_size, size)) __read_overflow(); @@ -651,8 +651,8 @@ __FORTIFY_INLINE void *memscan(void * const POS0 p, int c, __kernel_size_t size) __FORTIFY_INLINE __diagnose_as(__builtin_memcmp, 1, 2, 3) int memcmp(const void * const POS0 p, const void * const POS0 q, __kernel_size_t size) { - size_t p_size = __struct_size(p); - size_t q_size = __struct_size(q); + const size_t p_size = __struct_size(p); + const size_t q_size = __struct_size(q); if (__builtin_constant_p(size)) { if (__compiletime_lessthan(p_size, size)) @@ -668,7 +668,7 @@ int memcmp(const void * const POS0 p, const void * const POS0 q, __kernel_size_t __FORTIFY_INLINE __diagnose_as(__builtin_memchr, 1, 2, 3) void *memchr(const void * const POS0 p, int c, __kernel_size_t size) { - size_t p_size = __struct_size(p); + const size_t p_size = __struct_size(p); if (__compiletime_lessthan(p_size, size)) __read_overflow(); @@ -680,7 +680,7 @@ void *memchr(const void * const POS0 p, int c, __kernel_size_t size) void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv); __FORTIFY_INLINE void *memchr_inv(const void * const POS0 p, int c, size_t size) { - size_t p_size = __struct_size(p); + const size_t p_size = __struct_size(p); if (__compiletime_lessthan(p_size, size)) __read_overflow(); @@ -693,7 +693,7 @@ extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kme __realloc_size(2); __FORTIFY_INLINE void *kmemdup(const void * const POS0 p, size_t size, gfp_t gfp) { - size_t p_size = __struct_size(p); + const size_t p_size = __struct_size(p); if (__compiletime_lessthan(p_size, size)) __read_overflow(); @@ -720,8 +720,8 @@ __FORTIFY_INLINE void *kmemdup(const void * const POS0 p, size_t size, gfp_t gfp __FORTIFY_INLINE __diagnose_as(__builtin_strcpy, 1, 2) char *strcpy(char * const POS p, const char * const POS q) { - size_t p_size = __member_size(p); - size_t q_size = __member_size(q); + const size_t p_size = __member_size(p); + const size_t q_size = __member_size(q); size_t size; /* If neither buffer size is known, immediately give up. */ -- cgit v1.2.3 From 605395cd7ceded5842c8ba6763ea24feee690c87 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Sun, 2 Apr 2023 23:00:05 -0700 Subject: fortify: Add protection for strlcat() The definition of strcat() was defined in terms of unfortified strlcat(), but that meant there was no bounds checking done on the internal strlen() calls, and the (bounded) copy would be performed before reporting a failure. Additionally, pathological cases (i.e. unterminated destination buffer) did not make calls to fortify_panic(), which will make future unit testing more difficult. Instead, explicitly define a fortified strlcat() wrapper for strcat() to use. Signed-off-by: Kees Cook --- include/linux/fortify-string.h | 64 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 64 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index 2e7a47b62ba2..756c89bb88e0 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -371,6 +371,70 @@ __FORTIFY_INLINE ssize_t strscpy(char * const POS p, const char * const POS q, s return __real_strscpy(p, q, len); } +/* Defined after fortified strlen() to reuse it. */ +extern size_t __real_strlcat(char *p, const char *q, size_t avail) __RENAME(strlcat); +/** + * strlcat - Append a string to an existing string + * + * @p: pointer to %NUL-terminated string to append to + * @q: pointer to %NUL-terminated string to append from + * @avail: Maximum bytes available in @p + * + * Appends %NUL-terminated string @q after the %NUL-terminated + * string at @p, but will not write beyond @avail bytes total, + * potentially truncating the copy from @q. @p will stay + * %NUL-terminated only if a %NUL already existed within + * the @avail bytes of @p. If so, the resulting number of + * bytes copied from @q will be at most "@avail - strlen(@p) - 1". + * + * Do not use this function. While FORTIFY_SOURCE tries to avoid + * read and write overflows, this is only possible when the sizes + * of @p and @q are known to the compiler. Prefer building the + * string with formatting, via scnprintf(), seq_buf, or similar. + * + * Returns total bytes that _would_ have been contained by @p + * regardless of truncation, similar to snprintf(). If return + * value is >= @avail, the string has been truncated. + * + */ +__FORTIFY_INLINE +size_t strlcat(char * const POS p, const char * const POS q, size_t avail) +{ + const size_t p_size = __member_size(p); + const size_t q_size = __member_size(q); + size_t p_len, copy_len; + size_t actual, wanted; + + /* Give up immediately if both buffer sizes are unknown. */ + if (p_size == SIZE_MAX && q_size == SIZE_MAX) + return __real_strlcat(p, q, avail); + + p_len = strnlen(p, avail); + copy_len = strlen(q); + wanted = actual = p_len + copy_len; + + /* Cannot append any more: report truncation. */ + if (avail <= p_len) + return wanted; + + /* Give up if string is already overflowed. */ + if (p_size <= p_len) + fortify_panic(__func__); + + if (actual >= avail) { + copy_len = avail - p_len - 1; + actual = p_len + copy_len; + } + + /* Give up if copy will overflow. */ + if (p_size <= actual) + fortify_panic(__func__); + __underlying_memcpy(p + p_len, q, copy_len); + p[actual] = '\0'; + + return wanted; +} + /** * strncat - Append a string to an existing string * -- cgit v1.2.3 From 55c84a5cf2c72a821719823ef2ebef01b119025b Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 4 Apr 2023 14:24:27 -0700 Subject: fortify: strcat: Move definition to use fortified strlcat() Move the definition of fortified strcat() to after strlcat() to use it for bounds checking. Signed-off-by: Kees Cook --- include/linux/fortify-string.h | 53 +++++++++++++++++++++--------------------- 1 file changed, 26 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index 756c89bb88e0..da51a83b2829 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -151,33 +151,6 @@ char *strncpy(char * const POS p, const char *q, __kernel_size_t size) return __underlying_strncpy(p, q, size); } -/** - * strcat - Append a string to an existing string - * - * @p: pointer to NUL-terminated string to append to - * @q: pointer to NUL-terminated source string to append from - * - * Do not use this function. While FORTIFY_SOURCE tries to avoid - * read and write overflows, this is only possible when the - * destination buffer size is known to the compiler. Prefer - * building the string with formatting, via scnprintf() or similar. - * At the very least, use strncat(). - * - * Returns @p. - * - */ -__FORTIFY_INLINE __diagnose_as(__builtin_strcat, 1, 2) -char *strcat(char * const POS p, const char *q) -{ - const size_t p_size = __member_size(p); - - if (p_size == SIZE_MAX) - return __underlying_strcat(p, q); - if (strlcat(p, q, p_size) >= p_size) - fortify_panic(__func__); - return p; -} - extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(strnlen); /** * strnlen - Return bounded count of characters in a NUL-terminated string @@ -435,6 +408,32 @@ size_t strlcat(char * const POS p, const char * const POS q, size_t avail) return wanted; } +/* Defined after fortified strlcat() to reuse it. */ +/** + * strcat - Append a string to an existing string + * + * @p: pointer to NUL-terminated string to append to + * @q: pointer to NUL-terminated source string to append from + * + * Do not use this function. While FORTIFY_SOURCE tries to avoid + * read and write overflows, this is only possible when the + * destination buffer size is known to the compiler. Prefer + * building the string with formatting, via scnprintf() or similar. + * At the very least, use strncat(). + * + * Returns @p. + * + */ +__FORTIFY_INLINE __diagnose_as(__builtin_strcat, 1, 2) +char *strcat(char * const POS p, const char *q) +{ + const size_t p_size = __member_size(p); + + if (strlcat(p, q, p_size) >= p_size) + fortify_panic(__func__); + return p; +} + /** * strncat - Append a string to an existing string * -- cgit v1.2.3 From 247c8d2f9837a3e29e3b6b7a4aa9c36c37659dd4 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 21:56:12 +0200 Subject: fs: pipe: reveal missing function protoypes A couple of functions from fs/pipe.c are used both internally and for the watch queue code, but the declaration is only visible when the latter is enabled: fs/pipe.c:1254:5: error: no previous prototype for 'pipe_resize_ring' fs/pipe.c:758:15: error: no previous prototype for 'account_pipe_buffers' fs/pipe.c:764:6: error: no previous prototype for 'too_many_pipe_buffers_soft' fs/pipe.c:771:6: error: no previous prototype for 'too_many_pipe_buffers_hard' fs/pipe.c:777:6: error: no previous prototype for 'pipe_is_unprivileged_user' Make the visible unconditionally to avoid these warnings. Fixes: c73be61cede5 ("pipe: Add general notification queue support") Signed-off-by: Arnd Bergmann Message-Id: <20230516195629.551602-1-arnd@kernel.org> Signed-off-by: Christian Brauner --- include/linux/pipe_fs_i.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index d2c3f16cf6b1..02e0086b10f6 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -261,18 +261,14 @@ void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *); extern const struct pipe_buf_operations nosteal_pipe_buf_ops; -#ifdef CONFIG_WATCH_QUEUE unsigned long account_pipe_buffers(struct user_struct *user, unsigned long old, unsigned long new); bool too_many_pipe_buffers_soft(unsigned long user_bufs); bool too_many_pipe_buffers_hard(unsigned long user_bufs); bool pipe_is_unprivileged_user(void); -#endif /* for F_SETPIPE_SZ and F_GETPIPE_SZ */ -#ifdef CONFIG_WATCH_QUEUE int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots); -#endif long pipe_fcntl(struct file *, unsigned int, unsigned long arg); struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice); -- cgit v1.2.3 From ef104443bffa004f631729dfc924f0b84abbd602 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 21:57:29 +0200 Subject: procfs: consolidate arch_report_meminfo declaration The arch_report_meminfo() function is provided by four architectures, with a __weak fallback in procfs itself. On architectures that don't have a custom version, the __weak version causes a warning because of the missing prototype. Remove the architecture specific prototypes and instead add one in linux/proc_fs.h. Signed-off-by: Arnd Bergmann Acked-by: Dave Hansen # for arch/x86 Acked-by: Helge Deller # parisc Reviewed-by: Alexander Gordeev Message-Id: <20230516195834.551901-1-arnd@kernel.org> Signed-off-by: Christian Brauner --- arch/parisc/include/asm/pgtable.h | 3 --- arch/powerpc/include/asm/pgtable.h | 3 --- arch/s390/include/asm/pgtable.h | 3 --- arch/s390/mm/pageattr.c | 1 + arch/x86/include/asm/pgtable.h | 1 + arch/x86/include/asm/pgtable_types.h | 3 --- arch/x86/mm/pat/set_memory.c | 1 + include/linux/proc_fs.h | 2 ++ 8 files changed, 5 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index e715df5385d6..5656395c95ee 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -472,9 +472,6 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, #define pte_same(A,B) (pte_val(A) == pte_val(B)) -struct seq_file; -extern void arch_report_meminfo(struct seq_file *m); - #endif /* !__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index 9972626ddaf6..6a88bfdaa69b 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -165,9 +165,6 @@ static inline bool is_ioremap_addr(const void *x) return addr >= IOREMAP_BASE && addr < IOREMAP_END; } - -struct seq_file; -void arch_report_meminfo(struct seq_file *m); #endif /* CONFIG_PPC64 */ #endif /* __ASSEMBLY__ */ diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 6822a11c2c8a..c55f3c3365af 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -42,9 +42,6 @@ static inline void update_page_count(int level, long count) atomic_long_add(count, &direct_pages_count[level]); } -struct seq_file; -void arch_report_meminfo(struct seq_file *m); - /* * The S390 doesn't have any external MMU info: the kernel page * tables contain all the necessary information. diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c index 5ba3bd8a7b12..ca5a418c58a8 100644 --- a/arch/s390/mm/pageattr.c +++ b/arch/s390/mm/pageattr.c @@ -4,6 +4,7 @@ * Author(s): Jan Glauber */ #include +#include #include #include #include diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 15ae4d6ba476..5700bb337987 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -27,6 +27,7 @@ extern pgd_t early_top_pgt[PTRS_PER_PGD]; bool __init __early_make_pgtable(unsigned long address, pmdval_t pmd); +struct seq_file; void ptdump_walk_pgd_level(struct seq_file *m, struct mm_struct *mm); void ptdump_walk_pgd_level_debugfs(struct seq_file *m, struct mm_struct *mm, bool user); diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 447d4bee25c4..ba3e2554799a 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -513,9 +513,6 @@ extern void native_pagetable_init(void); #define native_pagetable_init paging_init #endif -struct seq_file; -extern void arch_report_meminfo(struct seq_file *m); - enum pg_level { PG_LEVEL_NONE, PG_LEVEL_4K, diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 7159cf787613..d1515756e369 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 0260f5ea98fe..253f2676d93a 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -158,6 +158,8 @@ int proc_pid_arch_status(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task); #endif /* CONFIG_PROC_PID_ARCH_STATUS */ +void arch_report_meminfo(struct seq_file *m); + #else /* CONFIG_PROC_FS */ static inline void proc_root_init(void) -- cgit v1.2.3 From f15afbd34d8fadbd375f1212e97837e32bc170cc Mon Sep 17 00:00:00 2001 From: Hao Ge Date: Mon, 24 Apr 2023 13:18:35 +0800 Subject: fs: fix undefined behavior in bit shift for SB_NOUSER Shifting signed 32-bit value by 31 bits is undefined, so changing significant bit to unsigned. It was spotted by UBSAN. So let's just fix this by using the BIT() helper for all SB_* flags. Fixes: e462ec50cb5f ("VFS: Differentiate mount flags (MS_*) from internal superblock flags") Signed-off-by: Hao Ge Message-Id: <20230424051835.374204-1-gehao@kylinos.cn> [brauner@kernel.org: use BIT() for all SB_* flags] Signed-off-by: Christian Brauner --- include/linux/fs.h | 42 +++++++++++++++++++++--------------------- 1 file changed, 21 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 21a981680856..133f0640fb24 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1076,29 +1076,29 @@ extern int send_sigurg(struct fown_struct *fown); * sb->s_flags. Note that these mirror the equivalent MS_* flags where * represented in both. */ -#define SB_RDONLY 1 /* Mount read-only */ -#define SB_NOSUID 2 /* Ignore suid and sgid bits */ -#define SB_NODEV 4 /* Disallow access to device special files */ -#define SB_NOEXEC 8 /* Disallow program execution */ -#define SB_SYNCHRONOUS 16 /* Writes are synced at once */ -#define SB_MANDLOCK 64 /* Allow mandatory locks on an FS */ -#define SB_DIRSYNC 128 /* Directory modifications are synchronous */ -#define SB_NOATIME 1024 /* Do not update access times. */ -#define SB_NODIRATIME 2048 /* Do not update directory access times */ -#define SB_SILENT 32768 -#define SB_POSIXACL (1<<16) /* VFS does not apply the umask */ -#define SB_INLINECRYPT (1<<17) /* Use blk-crypto for encrypted files */ -#define SB_KERNMOUNT (1<<22) /* this is a kern_mount call */ -#define SB_I_VERSION (1<<23) /* Update inode I_version field */ -#define SB_LAZYTIME (1<<25) /* Update the on-disk [acm]times lazily */ +#define SB_RDONLY BIT(0) /* Mount read-only */ +#define SB_NOSUID BIT(1) /* Ignore suid and sgid bits */ +#define SB_NODEV BIT(2) /* Disallow access to device special files */ +#define SB_NOEXEC BIT(3) /* Disallow program execution */ +#define SB_SYNCHRONOUS BIT(4) /* Writes are synced at once */ +#define SB_MANDLOCK BIT(6) /* Allow mandatory locks on an FS */ +#define SB_DIRSYNC BIT(7) /* Directory modifications are synchronous */ +#define SB_NOATIME BIT(10) /* Do not update access times. */ +#define SB_NODIRATIME BIT(11) /* Do not update directory access times */ +#define SB_SILENT BIT(15) +#define SB_POSIXACL BIT(16) /* VFS does not apply the umask */ +#define SB_INLINECRYPT BIT(17) /* Use blk-crypto for encrypted files */ +#define SB_KERNMOUNT BIT(22) /* this is a kern_mount call */ +#define SB_I_VERSION BIT(23) /* Update inode I_version field */ +#define SB_LAZYTIME BIT(25) /* Update the on-disk [acm]times lazily */ /* These sb flags are internal to the kernel */ -#define SB_SUBMOUNT (1<<26) -#define SB_FORCE (1<<27) -#define SB_NOSEC (1<<28) -#define SB_BORN (1<<29) -#define SB_ACTIVE (1<<30) -#define SB_NOUSER (1<<31) +#define SB_SUBMOUNT BIT(26) +#define SB_FORCE BIT(27) +#define SB_NOSEC BIT(28) +#define SB_BORN BIT(29) +#define SB_ACTIVE BIT(30) +#define SB_NOUSER BIT(31) /* These flags relate to encoding and casefolding */ #define SB_ENC_STRICT_MODE_FL (1 << 0) -- cgit v1.2.3 From 67d1b0a1030fb20d54b720df6e976c06b893fb00 Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Fri, 14 Apr 2023 10:25:39 +0530 Subject: soc: ti: pruss: Add pruss_get()/put() API Add two new get and put API, pruss_get() and pruss_put() to the PRUSS platform driver to allow client drivers to request a handle to a PRUSS device. This handle will be used by client drivers to request various operations of the PRUSS platform driver through additional API that will be added in the following patches. The pruss_get() function returns the pruss handle corresponding to a PRUSS device referenced by a PRU remoteproc instance. The pruss_put() is the complimentary function to pruss_get(). Co-developed-by: Suman Anna Signed-off-by: Suman Anna Signed-off-by: Tero Kristo Co-developed-by: Grzegorz Jaszczyk Signed-off-by: Grzegorz Jaszczyk Signed-off-by: Puranjay Mohan Reviewed-by: Roger Quadros Reviewed-by: Tony Lindgren Reviewed-by: Simon Horman Acked-by: Mathieu Poirier Signed-off-by: MD Danish Anwar Link: https://lore.kernel.org/r/20230414045542.3249939-2-danishanwar@ti.com Signed-off-by: Nishanth Menon --- drivers/soc/ti/pruss.c | 62 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/pruss_driver.h | 18 +++++++++++++ 2 files changed, 80 insertions(+) (limited to 'include/linux') diff --git a/drivers/soc/ti/pruss.c b/drivers/soc/ti/pruss.c index e68441bd7b30..f836660dac64 100644 --- a/drivers/soc/ti/pruss.c +++ b/drivers/soc/ti/pruss.c @@ -6,6 +6,7 @@ * Author(s): * Suman Anna * Andrew F. Davis + * Tero Kristo */ #include @@ -18,6 +19,7 @@ #include #include #include +#include #include /** @@ -30,6 +32,66 @@ struct pruss_private_data { bool has_core_mux_clock; }; +/** + * pruss_get() - get the pruss for a given PRU remoteproc + * @rproc: remoteproc handle of a PRU instance + * + * Finds the parent pruss device for a PRU given the @rproc handle of the + * PRU remote processor. This function increments the pruss device's refcount, + * so always use pruss_put() to decrement it back once pruss isn't needed + * anymore. + * + * This API doesn't check if @rproc is valid or not. It is expected the caller + * will have done a pru_rproc_get() on @rproc, before calling this API to make + * sure that @rproc is valid. + * + * Return: pruss handle on success, and an ERR_PTR on failure using one + * of the following error values + * -EINVAL if invalid parameter + * -ENODEV if PRU device or PRUSS device is not found + */ +struct pruss *pruss_get(struct rproc *rproc) +{ + struct pruss *pruss; + struct device *dev; + struct platform_device *ppdev; + + if (IS_ERR_OR_NULL(rproc)) + return ERR_PTR(-EINVAL); + + dev = &rproc->dev; + + /* make sure it is PRU rproc */ + if (!dev->parent || !is_pru_rproc(dev->parent)) + return ERR_PTR(-ENODEV); + + ppdev = to_platform_device(dev->parent->parent); + pruss = platform_get_drvdata(ppdev); + if (!pruss) + return ERR_PTR(-ENODEV); + + get_device(pruss->dev); + + return pruss; +} +EXPORT_SYMBOL_GPL(pruss_get); + +/** + * pruss_put() - decrement pruss device's usecount + * @pruss: pruss handle + * + * Complimentary function for pruss_get(). Needs to be called + * after the PRUSS is used, and only if the pruss_get() succeeds. + */ +void pruss_put(struct pruss *pruss) +{ + if (IS_ERR_OR_NULL(pruss)) + return; + + put_device(pruss->dev); +} +EXPORT_SYMBOL_GPL(pruss_put); + static void pruss_of_free_clk_provider(void *data) { struct device_node *clk_mux_np = data; diff --git a/include/linux/pruss_driver.h b/include/linux/pruss_driver.h index ecfded30ed05..cb40c2b31045 100644 --- a/include/linux/pruss_driver.h +++ b/include/linux/pruss_driver.h @@ -9,7 +9,9 @@ #ifndef _PRUSS_DRIVER_H_ #define _PRUSS_DRIVER_H_ +#include #include +#include /* * enum pruss_mem - PRUSS memory range identifiers @@ -51,4 +53,20 @@ struct pruss { struct clk *iep_clk_mux; }; +#if IS_ENABLED(CONFIG_TI_PRUSS) + +struct pruss *pruss_get(struct rproc *rproc); +void pruss_put(struct pruss *pruss); + +#else + +static inline struct pruss *pruss_get(struct rproc *rproc) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline void pruss_put(struct pruss *pruss) { } + +#endif /* CONFIG_TI_PRUSS */ + #endif /* _PRUSS_DRIVER_H_ */ -- cgit v1.2.3 From b789ca1e3380ab63b60c3356c026a7e8eb26ba01 Mon Sep 17 00:00:00 2001 From: "Andrew F. Davis" Date: Fri, 14 Apr 2023 10:25:40 +0530 Subject: soc: ti: pruss: Add pruss_{request,release}_mem_region() API Add two new API - pruss_request_mem_region() & pruss_release_mem_region(), to the PRUSS platform driver to allow client drivers to acquire and release the common memory resources present within a PRU-ICSS subsystem. This allows the client drivers to directly manipulate the respective memories, as per their design contract with the associated firmware. Co-developed-by: Suman Anna Signed-off-by: Suman Anna Signed-off-by: Andrew F. Davis Co-developed-by: Grzegorz Jaszczyk Signed-off-by: Grzegorz Jaszczyk Reviewed-by: Roger Quadros Acked-by: Mathieu Poirier Reviewed-by: Tony Lindgren Reviewed-by: Simon Horman Signed-off-by: MD Danish Anwar Link: https://lore.kernel.org/r/20230414045542.3249939-3-danishanwar@ti.com Signed-off-by: Nishanth Menon --- drivers/soc/ti/pruss.c | 77 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/pruss_driver.h | 22 +++++++++++++ 2 files changed, 99 insertions(+) (limited to 'include/linux') diff --git a/drivers/soc/ti/pruss.c b/drivers/soc/ti/pruss.c index f836660dac64..df5eb4d959f8 100644 --- a/drivers/soc/ti/pruss.c +++ b/drivers/soc/ti/pruss.c @@ -92,6 +92,82 @@ void pruss_put(struct pruss *pruss) } EXPORT_SYMBOL_GPL(pruss_put); +/** + * pruss_request_mem_region() - request a memory resource + * @pruss: the pruss instance + * @mem_id: the memory resource id + * @region: pointer to memory region structure to be filled in + * + * This function allows a client driver to request a memory resource, + * and if successful, will let the client driver own the particular + * memory region until released using the pruss_release_mem_region() + * API. + * + * Return: 0 if requested memory region is available (in such case pointer to + * memory region is returned via @region), an error otherwise + */ +int pruss_request_mem_region(struct pruss *pruss, enum pruss_mem mem_id, + struct pruss_mem_region *region) +{ + if (!pruss || !region || mem_id >= PRUSS_MEM_MAX) + return -EINVAL; + + mutex_lock(&pruss->lock); + + if (pruss->mem_in_use[mem_id]) { + mutex_unlock(&pruss->lock); + return -EBUSY; + } + + *region = pruss->mem_regions[mem_id]; + pruss->mem_in_use[mem_id] = region; + + mutex_unlock(&pruss->lock); + + return 0; +} +EXPORT_SYMBOL_GPL(pruss_request_mem_region); + +/** + * pruss_release_mem_region() - release a memory resource + * @pruss: the pruss instance + * @region: the memory region to release + * + * This function is the complimentary function to + * pruss_request_mem_region(), and allows the client drivers to + * release back a memory resource. + * + * Return: 0 on success, an error code otherwise + */ +int pruss_release_mem_region(struct pruss *pruss, + struct pruss_mem_region *region) +{ + int id; + + if (!pruss || !region) + return -EINVAL; + + mutex_lock(&pruss->lock); + + /* find out the memory region being released */ + for (id = 0; id < PRUSS_MEM_MAX; id++) { + if (pruss->mem_in_use[id] == region) + break; + } + + if (id == PRUSS_MEM_MAX) { + mutex_unlock(&pruss->lock); + return -EINVAL; + } + + pruss->mem_in_use[id] = NULL; + + mutex_unlock(&pruss->lock); + + return 0; +} +EXPORT_SYMBOL_GPL(pruss_release_mem_region); + static void pruss_of_free_clk_provider(void *data) { struct device_node *clk_mux_np = data; @@ -298,6 +374,7 @@ static int pruss_probe(struct platform_device *pdev) return -ENOMEM; pruss->dev = dev; + mutex_init(&pruss->lock); child = of_get_child_by_name(np, "memories"); if (!child) { diff --git a/include/linux/pruss_driver.h b/include/linux/pruss_driver.h index cb40c2b31045..c8f2e53b911b 100644 --- a/include/linux/pruss_driver.h +++ b/include/linux/pruss_driver.h @@ -9,6 +9,7 @@ #ifndef _PRUSS_DRIVER_H_ #define _PRUSS_DRIVER_H_ +#include #include #include #include @@ -41,6 +42,8 @@ struct pruss_mem_region { * @cfg_base: base iomap for CFG region * @cfg_regmap: regmap for config region * @mem_regions: data for each of the PRUSS memory regions + * @mem_in_use: to indicate if memory resource is in use + * @lock: mutex to serialize access to resources * @core_clk_mux: clk handle for PRUSS CORE_CLK_MUX * @iep_clk_mux: clk handle for PRUSS IEP_CLK_MUX */ @@ -49,6 +52,8 @@ struct pruss { void __iomem *cfg_base; struct regmap *cfg_regmap; struct pruss_mem_region mem_regions[PRUSS_MEM_MAX]; + struct pruss_mem_region *mem_in_use[PRUSS_MEM_MAX]; + struct mutex lock; /* PRU resource lock */ struct clk *core_clk_mux; struct clk *iep_clk_mux; }; @@ -57,6 +62,10 @@ struct pruss { struct pruss *pruss_get(struct rproc *rproc); void pruss_put(struct pruss *pruss); +int pruss_request_mem_region(struct pruss *pruss, enum pruss_mem mem_id, + struct pruss_mem_region *region); +int pruss_release_mem_region(struct pruss *pruss, + struct pruss_mem_region *region); #else @@ -67,6 +76,19 @@ static inline struct pruss *pruss_get(struct rproc *rproc) static inline void pruss_put(struct pruss *pruss) { } +static inline int pruss_request_mem_region(struct pruss *pruss, + enum pruss_mem mem_id, + struct pruss_mem_region *region) +{ + return -EOPNOTSUPP; +} + +static inline int pruss_release_mem_region(struct pruss *pruss, + struct pruss_mem_region *region) +{ + return -EOPNOTSUPP; +} + #endif /* CONFIG_TI_PRUSS */ #endif /* _PRUSS_DRIVER_H_ */ -- cgit v1.2.3 From 51b5760e56ef19106a3c4487a66d186d46ccc6f4 Mon Sep 17 00:00:00 2001 From: Suman Anna Date: Fri, 14 Apr 2023 10:25:41 +0530 Subject: soc: ti: pruss: Add pruss_cfg_read()/update(), pruss_cfg_get_gpmux()/set_gpmux() APIs Add two new generic API pruss_cfg_read() and pruss_cfg_update() to the PRUSS platform driver to read and program respectively a register within the PRUSS CFG sub-module represented by a syscon driver. These APIs are internal to PRUSS driver. Add two new helper functions pruss_cfg_get_gpmux() & pruss_cfg_set_gpmux() to get and set the GP MUX mode for programming the PRUSS internal wrapper mux functionality as needed by usecases. Various useful registers and macros for certain register bit-fields and their values have also been added. Signed-off-by: Suman Anna Co-developed-by: Grzegorz Jaszczyk Signed-off-by: Grzegorz Jaszczyk Signed-off-by: Puranjay Mohan Reviewed-by: Roger Quadros Reviewed-by: Tony Lindgren Reviewed-by: Simon Horman Acked-by: Mathieu Poirier Signed-off-by: MD Danish Anwar Link: https://lore.kernel.org/r/20230414045542.3249939-4-danishanwar@ti.com Signed-off-by: Nishanth Menon --- drivers/soc/ti/pruss.c | 45 ++++++++++++++++++++++ drivers/soc/ti/pruss.h | 88 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/pruss_driver.h | 32 ++++++++++++++++ 3 files changed, 165 insertions(+) create mode 100644 drivers/soc/ti/pruss.h (limited to 'include/linux') diff --git a/drivers/soc/ti/pruss.c b/drivers/soc/ti/pruss.c index df5eb4d959f8..2c44913c083b 100644 --- a/drivers/soc/ti/pruss.c +++ b/drivers/soc/ti/pruss.c @@ -21,6 +21,7 @@ #include #include #include +#include "pruss.h" /** * struct pruss_private_data - PRUSS driver private data @@ -168,6 +169,50 @@ int pruss_release_mem_region(struct pruss *pruss, } EXPORT_SYMBOL_GPL(pruss_release_mem_region); +/** + * pruss_cfg_get_gpmux() - get the current GPMUX value for a PRU device + * @pruss: pruss instance + * @pru_id: PRU identifier (0-1) + * @mux: pointer to store the current mux value into + * + * Return: 0 on success, or an error code otherwise + */ +int pruss_cfg_get_gpmux(struct pruss *pruss, enum pruss_pru_id pru_id, u8 *mux) +{ + int ret; + u32 val; + + if (pru_id >= PRUSS_NUM_PRUS || !mux) + return -EINVAL; + + ret = pruss_cfg_read(pruss, PRUSS_CFG_GPCFG(pru_id), &val); + if (!ret) + *mux = (u8)((val & PRUSS_GPCFG_PRU_MUX_SEL_MASK) >> + PRUSS_GPCFG_PRU_MUX_SEL_SHIFT); + return ret; +} +EXPORT_SYMBOL_GPL(pruss_cfg_get_gpmux); + +/** + * pruss_cfg_set_gpmux() - set the GPMUX value for a PRU device + * @pruss: pruss instance + * @pru_id: PRU identifier (0-1) + * @mux: new mux value for PRU + * + * Return: 0 on success, or an error code otherwise + */ +int pruss_cfg_set_gpmux(struct pruss *pruss, enum pruss_pru_id pru_id, u8 mux) +{ + if (mux >= PRUSS_GP_MUX_SEL_MAX || + pru_id >= PRUSS_NUM_PRUS) + return -EINVAL; + + return pruss_cfg_update(pruss, PRUSS_CFG_GPCFG(pru_id), + PRUSS_GPCFG_PRU_MUX_SEL_MASK, + (u32)mux << PRUSS_GPCFG_PRU_MUX_SEL_SHIFT); +} +EXPORT_SYMBOL_GPL(pruss_cfg_set_gpmux); + static void pruss_of_free_clk_provider(void *data) { struct device_node *clk_mux_np = data; diff --git a/drivers/soc/ti/pruss.h b/drivers/soc/ti/pruss.h new file mode 100644 index 000000000000..6c55987e0e55 --- /dev/null +++ b/drivers/soc/ti/pruss.h @@ -0,0 +1,88 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * PRU-ICSS Subsystem user interfaces + * + * Copyright (C) 2015-2023 Texas Instruments Incorporated - http://www.ti.com + * MD Danish Anwar + */ + +#ifndef _SOC_TI_PRUSS_H_ +#define _SOC_TI_PRUSS_H_ + +#include +#include + +/* + * PRU_ICSS_CFG registers + * SYSCFG, ISRP, ISP, IESP, IECP, SCRP applicable on AMxxxx devices only + */ +#define PRUSS_CFG_REVID 0x00 +#define PRUSS_CFG_SYSCFG 0x04 +#define PRUSS_CFG_GPCFG(x) (0x08 + (x) * 4) +#define PRUSS_CFG_CGR 0x10 +#define PRUSS_CFG_ISRP 0x14 +#define PRUSS_CFG_ISP 0x18 +#define PRUSS_CFG_IESP 0x1C +#define PRUSS_CFG_IECP 0x20 +#define PRUSS_CFG_SCRP 0x24 +#define PRUSS_CFG_PMAO 0x28 +#define PRUSS_CFG_MII_RT 0x2C +#define PRUSS_CFG_IEPCLK 0x30 +#define PRUSS_CFG_SPP 0x34 +#define PRUSS_CFG_PIN_MX 0x40 + +/* PRUSS_GPCFG register bits */ +#define PRUSS_GPCFG_PRU_GPI_MODE_MASK GENMASK(1, 0) +#define PRUSS_GPCFG_PRU_GPI_MODE_SHIFT 0 + +#define PRUSS_GPCFG_PRU_MUX_SEL_SHIFT 26 +#define PRUSS_GPCFG_PRU_MUX_SEL_MASK GENMASK(29, 26) + +/* PRUSS_MII_RT register bits */ +#define PRUSS_MII_RT_EVENT_EN BIT(0) + +/* PRUSS_SPP register bits */ +#define PRUSS_SPP_XFER_SHIFT_EN BIT(1) +#define PRUSS_SPP_PRU1_PAD_HP_EN BIT(0) +#define PRUSS_SPP_RTU_XFR_SHIFT_EN BIT(3) + +/** + * pruss_cfg_read() - read a PRUSS CFG sub-module register + * @pruss: the pruss instance handle + * @reg: register offset within the CFG sub-module + * @val: pointer to return the value in + * + * Reads a given register within the PRUSS CFG sub-module and + * returns it through the passed-in @val pointer + * + * Return: 0 on success, or an error code otherwise + */ +static int pruss_cfg_read(struct pruss *pruss, unsigned int reg, unsigned int *val) +{ + if (IS_ERR_OR_NULL(pruss)) + return -EINVAL; + + return regmap_read(pruss->cfg_regmap, reg, val); +} + +/** + * pruss_cfg_update() - configure a PRUSS CFG sub-module register + * @pruss: the pruss instance handle + * @reg: register offset within the CFG sub-module + * @mask: bit mask to use for programming the @val + * @val: value to write + * + * Programs a given register within the PRUSS CFG sub-module + * + * Return: 0 on success, or an error code otherwise + */ +static int pruss_cfg_update(struct pruss *pruss, unsigned int reg, + unsigned int mask, unsigned int val) +{ + if (IS_ERR_OR_NULL(pruss)) + return -EINVAL; + + return regmap_update_bits(pruss->cfg_regmap, reg, mask, val); +} + +#endif /* _SOC_TI_PRUSS_H_ */ diff --git a/include/linux/pruss_driver.h b/include/linux/pruss_driver.h index c8f2e53b911b..5bb8897724a9 100644 --- a/include/linux/pruss_driver.h +++ b/include/linux/pruss_driver.h @@ -14,6 +14,24 @@ #include #include +/* + * enum pruss_gp_mux_sel - PRUSS GPI/O Mux modes for the + * PRUSS_GPCFG0/1 registers + * + * NOTE: The below defines are the most common values, but there + * are some exceptions like on 66AK2G, where the RESERVED and MII2 + * values are interchanged. Also, this bit-field does not exist on + * AM335x SoCs + */ +enum pruss_gp_mux_sel { + PRUSS_GP_MUX_SEL_GP, + PRUSS_GP_MUX_SEL_ENDAT, + PRUSS_GP_MUX_SEL_RESERVED, + PRUSS_GP_MUX_SEL_SD, + PRUSS_GP_MUX_SEL_MII2, + PRUSS_GP_MUX_SEL_MAX, +}; + /* * enum pruss_mem - PRUSS memory range identifiers */ @@ -66,6 +84,8 @@ int pruss_request_mem_region(struct pruss *pruss, enum pruss_mem mem_id, struct pruss_mem_region *region); int pruss_release_mem_region(struct pruss *pruss, struct pruss_mem_region *region); +int pruss_cfg_get_gpmux(struct pruss *pruss, enum pruss_pru_id pru_id, u8 *mux); +int pruss_cfg_set_gpmux(struct pruss *pruss, enum pruss_pru_id pru_id, u8 mux); #else @@ -89,6 +109,18 @@ static inline int pruss_release_mem_region(struct pruss *pruss, return -EOPNOTSUPP; } +static inline int pruss_cfg_get_gpmux(struct pruss *pruss, + enum pruss_pru_id pru_id, u8 *mux) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline int pruss_cfg_set_gpmux(struct pruss *pruss, + enum pruss_pru_id pru_id, u8 mux) +{ + return ERR_PTR(-EOPNOTSUPP); +} + #endif /* CONFIG_TI_PRUSS */ #endif /* _PRUSS_DRIVER_H_ */ -- cgit v1.2.3 From 0211cc1e4fbbc81853227147bf0982c47362c567 Mon Sep 17 00:00:00 2001 From: Suman Anna Date: Fri, 14 Apr 2023 10:25:42 +0530 Subject: soc: ti: pruss: Add helper functions to set GPI mode, MII_RT_event and XFR The PRUSS CFG module is represented as a syscon node and is currently managed by the PRUSS platform driver. Add easy accessor functions to set GPI mode, MII_RT event enable/disable and XFR (XIN XOUT) enable/disable to enable the PRUSS Ethernet usecase. These functions reuse the generic pruss_cfg_update() API function. Signed-off-by: Suman Anna Co-developed-by: Grzegorz Jaszczyk Signed-off-by: Grzegorz Jaszczyk Signed-off-by: Puranjay Mohan Reviewed-by: Roger Quadros Reviewed-by: Tony Lindgren Reviewed-by: Simon Horman Reviewed-by: Mathieu Poirier Signed-off-by: MD Danish Anwar Link: https://lore.kernel.org/r/20230414045542.3249939-5-danishanwar@ti.com Signed-off-by: Nishanth Menon --- drivers/remoteproc/pru_rproc.c | 15 --------- drivers/soc/ti/pruss.c | 71 ++++++++++++++++++++++++++++++++++++++++++ include/linux/pruss_driver.h | 51 ++++++++++++++++++++++++++++++ 3 files changed, 122 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/remoteproc/pru_rproc.c b/drivers/remoteproc/pru_rproc.c index 095f66130f48..54f5ce302e7a 100644 --- a/drivers/remoteproc/pru_rproc.c +++ b/drivers/remoteproc/pru_rproc.c @@ -81,21 +81,6 @@ enum pru_iomem { PRU_IOMEM_MAX, }; -/** - * enum pru_type - PRU core type identifier - * - * @PRU_TYPE_PRU: Programmable Real-time Unit - * @PRU_TYPE_RTU: Auxiliary Programmable Real-Time Unit - * @PRU_TYPE_TX_PRU: Transmit Programmable Real-Time Unit - * @PRU_TYPE_MAX: just keep this one at the end - */ -enum pru_type { - PRU_TYPE_PRU = 0, - PRU_TYPE_RTU, - PRU_TYPE_TX_PRU, - PRU_TYPE_MAX, -}; - /** * struct pru_private_data - device data for a PRU core * @type: type of the PRU core (PRU, RTU, Tx_PRU) diff --git a/drivers/soc/ti/pruss.c b/drivers/soc/ti/pruss.c index 2c44913c083b..7fdefee1ed87 100644 --- a/drivers/soc/ti/pruss.c +++ b/drivers/soc/ti/pruss.c @@ -213,6 +213,77 @@ int pruss_cfg_set_gpmux(struct pruss *pruss, enum pruss_pru_id pru_id, u8 mux) } EXPORT_SYMBOL_GPL(pruss_cfg_set_gpmux); +/** + * pruss_cfg_gpimode() - set the GPI mode of the PRU + * @pruss: the pruss instance handle + * @pru_id: id of the PRU core within the PRUSS + * @mode: GPI mode to set + * + * Sets the GPI mode for a given PRU by programming the + * corresponding PRUSS_CFG_GPCFGx register + * + * Return: 0 on success, or an error code otherwise + */ +int pruss_cfg_gpimode(struct pruss *pruss, enum pruss_pru_id pru_id, + enum pruss_gpi_mode mode) +{ + if (pru_id >= PRUSS_NUM_PRUS || mode >= PRUSS_GPI_MODE_MAX) + return -EINVAL; + + return pruss_cfg_update(pruss, PRUSS_CFG_GPCFG(pru_id), + PRUSS_GPCFG_PRU_GPI_MODE_MASK, + mode << PRUSS_GPCFG_PRU_GPI_MODE_SHIFT); +} +EXPORT_SYMBOL_GPL(pruss_cfg_gpimode); + +/** + * pruss_cfg_miirt_enable() - Enable/disable MII RT Events + * @pruss: the pruss instance + * @enable: enable/disable + * + * Enable/disable the MII RT Events for the PRUSS. + * + * Return: 0 on success, or an error code otherwise + */ +int pruss_cfg_miirt_enable(struct pruss *pruss, bool enable) +{ + u32 set = enable ? PRUSS_MII_RT_EVENT_EN : 0; + + return pruss_cfg_update(pruss, PRUSS_CFG_MII_RT, + PRUSS_MII_RT_EVENT_EN, set); +} +EXPORT_SYMBOL_GPL(pruss_cfg_miirt_enable); + +/** + * pruss_cfg_xfr_enable() - Enable/disable XIN XOUT shift functionality + * @pruss: the pruss instance + * @pru_type: PRU core type identifier + * @enable: enable/disable + * + * Return: 0 on success, or an error code otherwise + */ +int pruss_cfg_xfr_enable(struct pruss *pruss, enum pru_type pru_type, + bool enable) +{ + u32 mask, set; + + switch (pru_type) { + case PRU_TYPE_PRU: + mask = PRUSS_SPP_XFER_SHIFT_EN; + break; + case PRU_TYPE_RTU: + mask = PRUSS_SPP_RTU_XFR_SHIFT_EN; + break; + default: + return -EINVAL; + } + + set = enable ? mask : 0; + + return pruss_cfg_update(pruss, PRUSS_CFG_SPP, mask, set); +} +EXPORT_SYMBOL_GPL(pruss_cfg_xfr_enable); + static void pruss_of_free_clk_provider(void *data) { struct device_node *clk_mux_np = data; diff --git a/include/linux/pruss_driver.h b/include/linux/pruss_driver.h index 5bb8897724a9..c9a31c567e85 100644 --- a/include/linux/pruss_driver.h +++ b/include/linux/pruss_driver.h @@ -32,6 +32,33 @@ enum pruss_gp_mux_sel { PRUSS_GP_MUX_SEL_MAX, }; +/* + * enum pruss_gpi_mode - PRUSS GPI configuration modes, used + * to program the PRUSS_GPCFG0/1 registers + */ +enum pruss_gpi_mode { + PRUSS_GPI_MODE_DIRECT, + PRUSS_GPI_MODE_PARALLEL, + PRUSS_GPI_MODE_28BIT_SHIFT, + PRUSS_GPI_MODE_MII, + PRUSS_GPI_MODE_MAX, +}; + +/** + * enum pru_type - PRU core type identifier + * + * @PRU_TYPE_PRU: Programmable Real-time Unit + * @PRU_TYPE_RTU: Auxiliary Programmable Real-Time Unit + * @PRU_TYPE_TX_PRU: Transmit Programmable Real-Time Unit + * @PRU_TYPE_MAX: just keep this one at the end + */ +enum pru_type { + PRU_TYPE_PRU, + PRU_TYPE_RTU, + PRU_TYPE_TX_PRU, + PRU_TYPE_MAX, +}; + /* * enum pruss_mem - PRUSS memory range identifiers */ @@ -86,6 +113,11 @@ int pruss_release_mem_region(struct pruss *pruss, struct pruss_mem_region *region); int pruss_cfg_get_gpmux(struct pruss *pruss, enum pruss_pru_id pru_id, u8 *mux); int pruss_cfg_set_gpmux(struct pruss *pruss, enum pruss_pru_id pru_id, u8 mux); +int pruss_cfg_gpimode(struct pruss *pruss, enum pruss_pru_id pru_id, + enum pruss_gpi_mode mode); +int pruss_cfg_miirt_enable(struct pruss *pruss, bool enable); +int pruss_cfg_xfr_enable(struct pruss *pruss, enum pru_type pru_type, + bool enable); #else @@ -121,6 +153,25 @@ static inline int pruss_cfg_set_gpmux(struct pruss *pruss, return ERR_PTR(-EOPNOTSUPP); } +static inline int pruss_cfg_gpimode(struct pruss *pruss, + enum pruss_pru_id pru_id, + enum pruss_gpi_mode mode) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline int pruss_cfg_miirt_enable(struct pruss *pruss, bool enable) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline int pruss_cfg_xfr_enable(struct pruss *pruss, + enum pru_type pru_type, + bool enable); +{ + return ERR_PTR(-EOPNOTSUPP); +} + #endif /* CONFIG_TI_PRUSS */ #endif /* _PRUSS_DRIVER_H_ */ -- cgit v1.2.3 From e455ca40dbcf2cd50d1e59bf4b2752b300bcdad4 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 17 May 2023 15:10:52 +0200 Subject: audit: avoid missing-prototype warnings Building with 'make W=1' reveals two function definitions without a previous prototype in the audit code: lib/compat_audit.c:32:5: error: no previous prototype for 'audit_classify_compat_syscall' [-Werror=missing-prototypes] kernel/audit.c:1813:14: error: no previous prototype for 'audit_serial' [-Werror=missing-prototypes] The first one needs a declaration from linux/audit.h but cannot include that header without causing conflicting (compat) syscall number definitions, so move the it into linux/audit_arch.h. The second one is declared conditionally based on CONFIG_AUDITSYSCALL but needed as a local function even when that option is disabled, so move the declaration out of the #ifdef block. Signed-off-by: Arnd Bergmann Signed-off-by: Paul Moore --- include/linux/audit.h | 2 -- include/linux/audit_arch.h | 2 ++ kernel/audit.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 31086a72e32a..6a3a9e122bb5 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -130,8 +130,6 @@ extern unsigned compat_dir_class[]; extern unsigned compat_chattr_class[]; extern unsigned compat_signal_class[]; -extern int audit_classify_compat_syscall(int abi, unsigned syscall); - /* audit_names->type values */ #define AUDIT_TYPE_UNKNOWN 0 /* we don't know yet */ #define AUDIT_TYPE_NORMAL 1 /* a "normal" audit record */ diff --git a/include/linux/audit_arch.h b/include/linux/audit_arch.h index 8fdb1afe251a..0e34d673ef17 100644 --- a/include/linux/audit_arch.h +++ b/include/linux/audit_arch.h @@ -21,4 +21,6 @@ enum auditsc_class_t { AUDITSC_NVALS /* count */ }; +extern int audit_classify_compat_syscall(int abi, unsigned syscall); + #endif diff --git a/kernel/audit.h b/kernel/audit.h index c57b008b9914..94738bce40b2 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -259,8 +259,8 @@ extern struct tty_struct *audit_get_tty(void); extern void audit_put_tty(struct tty_struct *tty); /* audit watch/mark/tree functions */ -#ifdef CONFIG_AUDITSYSCALL extern unsigned int audit_serial(void); +#ifdef CONFIG_AUDITSYSCALL extern int auditsc_get_stamp(struct audit_context *ctx, struct timespec64 *t, unsigned int *serial); -- cgit v1.2.3 From d86ff3333cb1d5f42d8898fb5fdb304e143c0237 Mon Sep 17 00:00:00 2001 From: Anisse Astier Date: Wed, 17 May 2023 17:38:12 +0200 Subject: efivarfs: expose used and total size When writing EFI variables, one might get errors with no other message on why it fails. Being able to see how much is used by EFI variables helps analyzing such issues. Since this is not a conventional filesystem, block size is intentionally set to 1 instead of PAGE_SIZE. x86 quirks of reserved size are taken into account; so that available and free size can be different, further helping debugging space issues. With this patch, one can see the remaining space in EFI variable storage via efivarfs, like this: $ df -h /sys/firmware/efi/efivars/ Filesystem Size Used Avail Use% Mounted on efivarfs 176K 106K 66K 62% /sys/firmware/efi/efivars Signed-off-by: Anisse Astier [ardb: - rename efi_reserved_space() to efivar_reserved_space() - whitespace/coding style tweaks] Signed-off-by: Ard Biesheuvel --- arch/x86/platform/efi/quirks.c | 8 ++++++++ drivers/firmware/efi/efi.c | 1 + drivers/firmware/efi/vars.c | 12 ++++++++++++ fs/efivarfs/super.c | 39 ++++++++++++++++++++++++++++++++++++++- include/linux/efi.h | 11 +++++++++++ 5 files changed, 70 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index b0b848d6933a..f0cc00032751 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -114,6 +114,14 @@ void efi_delete_dummy_variable(void) EFI_VARIABLE_RUNTIME_ACCESS, 0, NULL); } +u64 efivar_reserved_space(void) +{ + if (efi_no_storage_paranoia) + return 0; + return EFI_MIN_RESERVE; +} +EXPORT_SYMBOL_GPL(efivar_reserved_space); + /* * In the nonblocking case we do not attempt to perform garbage * collection if we do not have enough free space. Rather, we do the diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index abeff7dc0b58..d0dfa007bffc 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -211,6 +211,7 @@ static int generic_ops_register(void) generic_ops.get_variable = efi.get_variable; generic_ops.get_next_variable = efi.get_next_variable; generic_ops.query_variable_store = efi_query_variable_store; + generic_ops.query_variable_info = efi.query_variable_info; if (efi_rt_services_supported(EFI_RT_SUPPORTED_SET_VARIABLE)) { generic_ops.set_variable = efi.set_variable; diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c index bfc5fa6aa47b..e9dc7116daf1 100644 --- a/drivers/firmware/efi/vars.c +++ b/drivers/firmware/efi/vars.c @@ -245,3 +245,15 @@ efi_status_t efivar_set_variable(efi_char16_t *name, efi_guid_t *vendor, return status; } EXPORT_SYMBOL_NS_GPL(efivar_set_variable, EFIVAR); + +efi_status_t efivar_query_variable_info(u32 attr, + u64 *storage_space, + u64 *remaining_space, + u64 *max_variable_size) +{ + if (!__efivars->ops->query_variable_info) + return EFI_UNSUPPORTED; + return __efivars->ops->query_variable_info(attr, storage_space, + remaining_space, max_variable_size); +} +EXPORT_SYMBOL_NS_GPL(efivar_query_variable_info, EFIVAR); diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 482d612b716b..e028fafa04f3 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -13,6 +13,7 @@ #include #include #include +#include #include "internal.h" @@ -23,8 +24,44 @@ static void efivarfs_evict_inode(struct inode *inode) clear_inode(inode); } +static int efivarfs_statfs(struct dentry *dentry, struct kstatfs *buf) +{ + const u32 attr = EFI_VARIABLE_NON_VOLATILE | + EFI_VARIABLE_BOOTSERVICE_ACCESS | + EFI_VARIABLE_RUNTIME_ACCESS; + u64 storage_space, remaining_space, max_variable_size; + efi_status_t status; + + status = efivar_query_variable_info(attr, &storage_space, &remaining_space, + &max_variable_size); + if (status != EFI_SUCCESS) + return efi_status_to_err(status); + + /* + * This is not a normal filesystem, so no point in pretending it has a block + * size; we declare f_bsize to 1, so that we can then report the exact value + * sent by EFI QueryVariableInfo in f_blocks and f_bfree + */ + buf->f_bsize = 1; + buf->f_namelen = NAME_MAX; + buf->f_blocks = storage_space; + buf->f_bfree = remaining_space; + buf->f_type = dentry->d_sb->s_magic; + + /* + * In f_bavail we declare the free space that the kernel will allow writing + * when the storage_paranoia x86 quirk is active. To use more, users + * should boot the kernel with efi_no_storage_paranoia. + */ + if (remaining_space > efivar_reserved_space()) + buf->f_bavail = remaining_space - efivar_reserved_space(); + else + buf->f_bavail = 0; + + return 0; +} static const struct super_operations efivarfs_ops = { - .statfs = simple_statfs, + .statfs = efivarfs_statfs, .drop_inode = generic_delete_inode, .evict_inode = efivarfs_evict_inode, }; diff --git a/include/linux/efi.h b/include/linux/efi.h index 7aa62c92185f..bed3c92cbc31 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1042,6 +1042,7 @@ struct efivar_operations { efi_set_variable_t *set_variable; efi_set_variable_t *set_variable_nonblocking; efi_query_variable_store_t *query_variable_store; + efi_query_variable_info_t *query_variable_info; }; struct efivars { @@ -1049,6 +1050,12 @@ struct efivars { const struct efivar_operations *ops; }; +#ifdef CONFIG_X86 +u64 __attribute_const__ efivar_reserved_space(void); +#else +static inline u64 efivar_reserved_space(void) { return 0; } +#endif + /* * The maximum size of VariableName + Data = 1024 * Therefore, it's reasonable to save that much @@ -1087,6 +1094,10 @@ efi_status_t efivar_set_variable_locked(efi_char16_t *name, efi_guid_t *vendor, efi_status_t efivar_set_variable(efi_char16_t *name, efi_guid_t *vendor, u32 attr, unsigned long data_size, void *data); +efi_status_t efivar_query_variable_info(u32 attr, u64 *storage_space, + u64 *remaining_space, + u64 *max_variable_size); + #if IS_ENABLED(CONFIG_EFI_CAPSULE_LOADER) extern bool efi_capsule_pending(int *reset_type); -- cgit v1.2.3 From 8ff1541da3908b504cb53e5384d5deae2b9c6e1a Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Fri, 12 May 2023 12:24:42 +0200 Subject: fbdev: Include instead of Replace include statements for with . Fixes the coding style: if a header is available in asm/ and linux/, it is preferable to include the header from linux/. This only affects a few source files, most of which already include . Suggested-by: Sam Ravnborg Signed-off-by: Thomas Zimmermann Reviewed-by: Arnd Bergmann Reviewed-by: Sui Jingfeng Reviewed-by: Sam Ravnborg Link: https://patchwork.freedesktop.org/patch/msgid/20230512102444.5438-6-tzimmermann@suse.de --- arch/parisc/video/fbdev.c | 3 +-- arch/sparc/video/fbdev.c | 1 - arch/x86/video/fbdev.c | 2 -- drivers/staging/sm750fb/sm750.c | 2 +- drivers/video/fbdev/core/fbcon.c | 1 - drivers/video/fbdev/core/fbmem.c | 2 -- include/linux/fb.h | 2 ++ 7 files changed, 4 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/arch/parisc/video/fbdev.c b/arch/parisc/video/fbdev.c index 4a0ae08fc75b..137561d98246 100644 --- a/arch/parisc/video/fbdev.c +++ b/arch/parisc/video/fbdev.c @@ -5,10 +5,9 @@ * Copyright (C) 2001-2002 Thomas Bogendoerfer */ +#include #include -#include - #include