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 --- include/linux/blk_types.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') 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 --- include/linux/nvme.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') 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 --- include/linux/nvme.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') 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 --- include/linux/aperture.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') 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 --- include/linux/aperture.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') 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 +- 1 file changed, 1 insertion(+), 1 deletion(-) (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); -- cgit v1.2.3 From 7b9c13dd4d0ebbe89dfd7e1ecd09696037622101 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Miros=C5=82aw?= 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 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 ++++++++++++++ 1 file changed, 14 insertions(+) (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 */ -- 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 +++++++++---- 1 file changed, 9 insertions(+), 4 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, -- 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 --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') 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; -- 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 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 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 ++++++++++ 1 file changed, 10 insertions(+) (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 */ }; -- 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 --- include/linux/fb.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') 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 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 ++++---- 1 file changed, 4 insertions(+), 4 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) -- 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 ++++ 1 file changed, 4 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) { } -- 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 ++ 1 file changed, 2 insertions(+) (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); -- 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 +- 1 file changed, 1 insertion(+), 1 deletion(-) (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 -- 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 --- include/linux/wmi.h | 41 ++++++++++++++++++++++++++++++++++++++--- 1 file changed, 38 insertions(+), 3 deletions(-) (limited to 'include/linux') 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 --- include/linux/acpi.h | 2 ++ include/linux/wmi.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include/linux') 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 --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') 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 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 --- include/linux/rcupdate.h | 25 ------------------------- 1 file changed, 25 deletions(-) (limited to 'include/linux') 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 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 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 --- include/linux/usb/hcd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') 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_