From e71da1fd0e84bc5c87a78b405e40713840eecc80 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 6 Feb 2021 16:13:48 +0100 Subject: HID: intel-ish-hid: Make remove callback return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver core ignores the return value of struct bus_type::remove() because there is only little that can be done. To simplify the quest to make this function return void, let struct ishtp_cl_driver::remove() return void, too. All users already unconditionally return 0, this commit makes it obvious that returning an error value is a bad idea. Signed-off-by: Uwe Kleine-König Acked-by: Srinivas Pandruvada Signed-off-by: Jiri Kosina --- include/linux/intel-ish-client-if.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/intel-ish-client-if.h b/include/linux/intel-ish-client-if.h index 0d6b4bc191c5..94669e21dc8b 100644 --- a/include/linux/intel-ish-client-if.h +++ b/include/linux/intel-ish-client-if.h @@ -36,7 +36,7 @@ struct ishtp_cl_driver { const char *name; const guid_t *guid; int (*probe)(struct ishtp_cl_device *dev); - int (*remove)(struct ishtp_cl_device *dev); + void (*remove)(struct ishtp_cl_device *dev); int (*reset)(struct ishtp_cl_device *dev); const struct dev_pm_ops *pm; }; -- cgit v1.2.3 From c57179c73562e31d39139ac245b8a2d337e1823b Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Fri, 26 Mar 2021 14:34:58 +0000 Subject: HID: ishtp-hid-client: Fix 'suggest-attribute=format' compiler warning MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes the following W=1 kernel build warning(s): drivers/hid/intel-ish-hid/ishtp/bus.c: In function ‘ishtp_trace_callback’: drivers/hid/intel-ish-hid/ishtp/bus.c:876:29: warning: return type might be a candidate for a format attribute [-Wsuggest-attribute=format] 876 | return cl_device->ishtp_dev->print_log; | ~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~ Cc: Srinivas Pandruvada Cc: Jiri Kosina Cc: Benjamin Tissoires Cc: Daniel Drubin Cc: linux-input@vger.kernel.org Suggested-by: Arnd Bergmann Signed-off-by: Lee Jones Acked-by: Srinivas Pandruvada Signed-off-by: Benjamin Tissoires --- include/linux/intel-ish-client-if.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/intel-ish-client-if.h b/include/linux/intel-ish-client-if.h index 94669e21dc8b..25e2b4e80502 100644 --- a/include/linux/intel-ish-client-if.h +++ b/include/linux/intel-ish-client-if.h @@ -8,11 +8,17 @@ #ifndef _INTEL_ISH_CLIENT_IF_H_ #define _INTEL_ISH_CLIENT_IF_H_ +#include +#include + struct ishtp_cl_device; struct ishtp_device; struct ishtp_cl; struct ishtp_fw_client; +typedef __printf(2, 3) void (*ishtp_print_log)(struct ishtp_device *dev, + const char *format, ...); + /* Client state */ enum cl_state { ISHTP_CL_INITIALIZING = 0, @@ -76,7 +82,7 @@ int ishtp_register_event_cb(struct ishtp_cl_device *device, /* Get the device * from ishtp device instance */ struct device *ishtp_device(struct ishtp_cl_device *cl_device); /* Trace interface for clients */ -void *ishtp_trace_callback(struct ishtp_cl_device *cl_device); +ishtp_print_log ishtp_trace_callback(struct ishtp_cl_device *cl_device); /* Get device pointer of PCI device for DMA acces */ struct device *ishtp_get_pci_device(struct ishtp_cl_device *cl_device); -- cgit v1.2.3 From ffb37ca3bd16ce6ea2df2f87fde9a31e94ebb54b Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 1 Apr 2021 19:00:57 -0400 Subject: switch file_open_root() to struct path ... and provide file_open_root_mnt(), using the root of given mount. Signed-off-by: Al Viro --- include/linux/fs.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index ec8f3ddf4a6a..1acea2bb9d60 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2632,8 +2632,14 @@ extern long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode); extern struct file *file_open_name(struct filename *, int, umode_t); extern struct file *filp_open(const char *, int, umode_t); -extern struct file *file_open_root(struct dentry *, struct vfsmount *, +extern struct file *file_open_root(const struct path *, const char *, int, umode_t); +static inline struct file *file_open_root_mnt(struct vfsmount *mnt, + const char *name, int flags, umode_t mode) +{ + return file_open_root(&(struct path){.mnt = mnt, .dentry = mnt->mnt_root}, + name, flags, mode); +} extern struct file * dentry_open(const struct path *, int, const struct cred *); extern struct file * open_with_fake_path(const struct path *, int, struct inode*, const struct cred *); -- cgit v1.2.3 From bcba1e7d0d520adba895d9e0800a056f734b0a6a Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 1 Apr 2021 22:03:41 -0400 Subject: take LOOKUP_{ROOT,ROOT_GRABBED,JUMPED} out of LOOKUP_... space Separate field in nameidata (nd->state) holding the flags that should be internal-only - that way we both get some spare bits in LOOKUP_... and get simpler rules for nd->root lifetime rules, since we can set the replacement of LOOKUP_ROOT (ND_ROOT_PRESET) at the same time we set nd->root. Signed-off-by: Al Viro --- include/linux/namei.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index b9605b2b46e7..be9a2b349ca7 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -36,9 +36,6 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT}; /* internal use only */ #define LOOKUP_PARENT 0x0010 -#define LOOKUP_JUMPED 0x1000 -#define LOOKUP_ROOT 0x2000 -#define LOOKUP_ROOT_GRABBED 0x0008 /* Scoping flags for lookup. */ #define LOOKUP_NO_SYMLINKS 0x010000 /* No symlink crossing. */ -- cgit v1.2.3 From f9c82a4ea89c384d49ce03768ba88d049ed3f1f0 Mon Sep 17 00:00:00 2001 From: Alexey Gladkov Date: Thu, 22 Apr 2021 14:27:08 +0200 Subject: Increase size of ucounts to atomic_long_t RLIMIT_MSGQUEUE and RLIMIT_MEMLOCK use unsigned long to store their counters. As a preparation for moving rlimits based on ucounts, we need to increase the size of the variable to long. Signed-off-by: Alexey Gladkov Link: https://lkml.kernel.org/r/257aa5fb1a7d81cf0f4c34f39ada2320c4284771.1619094428.git.legion@kernel.org Signed-off-by: Eric W. Biederman --- include/linux/user_namespace.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index f6c5f784be5a..c242c10906c5 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -88,7 +88,7 @@ struct user_namespace { struct ctl_table_header *sysctls; #endif struct ucounts *ucounts; - int ucount_max[UCOUNT_COUNTS]; + long ucount_max[UCOUNT_COUNTS]; } __randomize_layout; struct ucounts { @@ -96,7 +96,7 @@ struct ucounts { struct user_namespace *ns; kuid_t uid; int count; - atomic_t ucount[UCOUNT_COUNTS]; + atomic_long_t ucount[UCOUNT_COUNTS]; }; extern struct user_namespace init_user_ns; -- cgit v1.2.3 From 905ae01c4ae2ae3df05bb141801b1db4b7d83c61 Mon Sep 17 00:00:00 2001 From: Alexey Gladkov Date: Thu, 22 Apr 2021 14:27:09 +0200 Subject: Add a reference to ucounts for each cred For RLIMIT_NPROC and some other rlimits the user_struct that holds the global limit is kept alive for the lifetime of a process by keeping it in struct cred. Adding a pointer to ucounts in the struct cred will allow to track RLIMIT_NPROC not only for user in the system, but for user in the user_namespace. Updating ucounts may require memory allocation which may fail. So, we cannot change cred.ucounts in the commit_creds() because this function cannot fail and it should always return 0. For this reason, we modify cred.ucounts before calling the commit_creds(). Changelog v6: * Fix null-ptr-deref in is_ucounts_overlimit() detected by trinity. This error was caused by the fact that cred_alloc_blank() left the ucounts pointer empty. Reported-by: kernel test robot Signed-off-by: Alexey Gladkov Link: https://lkml.kernel.org/r/b37aaef28d8b9b0d757e07ba6dd27281bbe39259.1619094428.git.legion@kernel.org Signed-off-by: Eric W. Biederman --- include/linux/cred.h | 2 ++ include/linux/user_namespace.h | 4 ++++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cred.h b/include/linux/cred.h index 4c6350503697..66436e655032 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -144,6 +144,7 @@ struct cred { #endif struct user_struct *user; /* real user ID subscription */ struct user_namespace *user_ns; /* user_ns the caps and keyrings are relative to. */ + struct ucounts *ucounts; struct group_info *group_info; /* supplementary groups for euid/fsgid */ /* RCU deletion */ union { @@ -170,6 +171,7 @@ extern int set_security_override_from_ctx(struct cred *, const char *); extern int set_create_files_as(struct cred *, struct inode *); extern int cred_fscmp(const struct cred *, const struct cred *); extern void __init cred_init(void); +extern int set_cred_ucounts(struct cred *); /* * check for validity of credentials diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index c242c10906c5..7919b80d57ed 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -100,11 +100,15 @@ struct ucounts { }; extern struct user_namespace init_user_ns; +extern struct ucounts init_ucounts; bool setup_userns_sysctls(struct user_namespace *ns); void retire_userns_sysctls(struct user_namespace *ns); struct ucounts *inc_ucount(struct user_namespace *ns, kuid_t uid, enum ucount_type type); void dec_ucount(struct ucounts *ucounts, enum ucount_type type); +struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid); +struct ucounts *get_ucounts(struct ucounts *ucounts); +void put_ucounts(struct ucounts *ucounts); #ifdef CONFIG_USER_NS -- cgit v1.2.3 From b6c336528926ef73b0f70260f2636de2c3b94c14 Mon Sep 17 00:00:00 2001 From: Alexey Gladkov Date: Thu, 22 Apr 2021 14:27:10 +0200 Subject: Use atomic_t for ucounts reference counting The current implementation of the ucounts reference counter requires the use of spin_lock. We're going to use get_ucounts() in more performance critical areas like a handling of RLIMIT_SIGPENDING. Now we need to use spin_lock only if we want to change the hashtable. v10: * Always try to put ucounts in case we cannot increase ucounts->count. This will allow to cover the case when all consumers will return ucounts at once. v9: * Use a negative value to check that the ucounts->count is close to overflow. Signed-off-by: Alexey Gladkov Link: https://lkml.kernel.org/r/94d1dbecab060a6b116b0a2d1accd8ca1bbb4f5f.1619094428.git.legion@kernel.org Signed-off-by: Eric W. Biederman --- include/linux/user_namespace.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 7919b80d57ed..80b5bf12feae 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -95,7 +95,7 @@ struct ucounts { struct hlist_node node; struct user_namespace *ns; kuid_t uid; - int count; + atomic_t count; atomic_long_t ucount[UCOUNT_COUNTS]; }; @@ -107,7 +107,7 @@ void retire_userns_sysctls(struct user_namespace *ns); struct ucounts *inc_ucount(struct user_namespace *ns, kuid_t uid, enum ucount_type type); void dec_ucount(struct ucounts *ucounts, enum ucount_type type); struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid); -struct ucounts *get_ucounts(struct ucounts *ucounts); +struct ucounts * __must_check get_ucounts(struct ucounts *ucounts); void put_ucounts(struct ucounts *ucounts); #ifdef CONFIG_USER_NS -- cgit v1.2.3 From 21d1c5e386bc751f1953b371d72cd5b7d9c9e270 Mon Sep 17 00:00:00 2001 From: Alexey Gladkov Date: Thu, 22 Apr 2021 14:27:11 +0200 Subject: Reimplement RLIMIT_NPROC on top of ucounts The rlimit counter is tied to uid in the user_namespace. This allows rlimit values to be specified in userns even if they are already globally exceeded by the user. However, the value of the previous user_namespaces cannot be exceeded. To illustrate the impact of rlimits, let's say there is a program that does not fork. Some service-A wants to run this program as user X in multiple containers. Since the program never fork the service wants to set RLIMIT_NPROC=1. service-A \- program (uid=1000, container1, rlimit_nproc=1) \- program (uid=1000, container2, rlimit_nproc=1) The service-A sets RLIMIT_NPROC=1 and runs the program in container1. When the service-A tries to run a program with RLIMIT_NPROC=1 in container2 it fails since user X already has one running process. We cannot use existing inc_ucounts / dec_ucounts because they do not allow us to exceed the maximum for the counter. Some rlimits can be overlimited by root or if the user has the appropriate capability. Changelog v11: * Change inc_rlimit_ucounts() which now returns top value of ucounts. * Drop inc_rlimit_ucounts_and_test() because the return code of inc_rlimit_ucounts() can be checked. Signed-off-by: Alexey Gladkov Link: https://lkml.kernel.org/r/c5286a8aa16d2d698c222f7532f3d735c82bc6bc.1619094428.git.legion@kernel.org Signed-off-by: Eric W. Biederman --- include/linux/cred.h | 2 ++ include/linux/sched/user.h | 1 - include/linux/user_namespace.h | 12 ++++++++++++ 3 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cred.h b/include/linux/cred.h index 66436e655032..5ca1e8a1d035 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -372,6 +372,7 @@ static inline void put_cred(const struct cred *_cred) #define task_uid(task) (task_cred_xxx((task), uid)) #define task_euid(task) (task_cred_xxx((task), euid)) +#define task_ucounts(task) (task_cred_xxx((task), ucounts)) #define current_cred_xxx(xxx) \ ({ \ @@ -388,6 +389,7 @@ static inline void put_cred(const struct cred *_cred) #define current_fsgid() (current_cred_xxx(fsgid)) #define current_cap() (current_cred_xxx(cap_effective)) #define current_user() (current_cred_xxx(user)) +#define current_ucounts() (current_cred_xxx(ucounts)) extern struct user_namespace init_user_ns; #ifdef CONFIG_USER_NS diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h index a8ec3b6093fc..d33d867ad6c1 100644 --- a/include/linux/sched/user.h +++ b/include/linux/sched/user.h @@ -12,7 +12,6 @@ */ struct user_struct { refcount_t __count; /* reference count */ - atomic_t processes; /* How many processes does this user have? */ atomic_t sigpending; /* How many pending signals does this user have? */ #ifdef CONFIG_FANOTIFY atomic_t fanotify_listeners; diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 80b5bf12feae..4a97acc35990 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -50,9 +50,12 @@ enum ucount_type { UCOUNT_INOTIFY_INSTANCES, UCOUNT_INOTIFY_WATCHES, #endif + UCOUNT_RLIMIT_NPROC, UCOUNT_COUNTS, }; +#define MAX_PER_NAMESPACE_UCOUNTS UCOUNT_RLIMIT_NPROC + struct user_namespace { struct uid_gid_map uid_map; struct uid_gid_map gid_map; @@ -110,6 +113,15 @@ struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid); struct ucounts * __must_check get_ucounts(struct ucounts *ucounts); void put_ucounts(struct ucounts *ucounts); +static inline long get_ucounts_value(struct ucounts *ucounts, enum ucount_type type) +{ + return atomic_long_read(&ucounts->ucount[type]); +} + +long inc_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v); +bool dec_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v); +bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long max); + #ifdef CONFIG_USER_NS static inline struct user_namespace *get_user_ns(struct user_namespace *ns) -- cgit v1.2.3 From 6e52a9f0532f912af37bab4caf18b57d1b9845f4 Mon Sep 17 00:00:00 2001 From: Alexey Gladkov Date: Thu, 22 Apr 2021 14:27:12 +0200 Subject: Reimplement RLIMIT_MSGQUEUE on top of ucounts The rlimit counter is tied to uid in the user_namespace. This allows rlimit values to be specified in userns even if they are already globally exceeded by the user. However, the value of the previous user_namespaces cannot be exceeded. Signed-off-by: Alexey Gladkov Link: https://lkml.kernel.org/r/2531f42f7884bbfee56a978040b3e0d25cdf6cde.1619094428.git.legion@kernel.org Signed-off-by: Eric W. Biederman --- include/linux/sched/user.h | 4 ---- include/linux/user_namespace.h | 1 + 2 files changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h index d33d867ad6c1..8a34446681aa 100644 --- a/include/linux/sched/user.h +++ b/include/linux/sched/user.h @@ -18,10 +18,6 @@ struct user_struct { #endif #ifdef CONFIG_EPOLL atomic_long_t epoll_watches; /* The number of file descriptors currently watched */ -#endif -#ifdef CONFIG_POSIX_MQUEUE - /* protected by mq_lock */ - unsigned long mq_bytes; /* How many bytes can be allocated to mqueue? */ #endif unsigned long locked_shm; /* How many pages of mlocked shm ? */ unsigned long unix_inflight; /* How many files in flight in unix sockets */ diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 4a97acc35990..5eeb86b00e68 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -51,6 +51,7 @@ enum ucount_type { UCOUNT_INOTIFY_WATCHES, #endif UCOUNT_RLIMIT_NPROC, + UCOUNT_RLIMIT_MSGQUEUE, UCOUNT_COUNTS, }; -- cgit v1.2.3 From d64696905554e919321e31afc210606653b8f6a4 Mon Sep 17 00:00:00 2001 From: Alexey Gladkov Date: Thu, 22 Apr 2021 14:27:13 +0200 Subject: Reimplement RLIMIT_SIGPENDING on top of ucounts The rlimit counter is tied to uid in the user_namespace. This allows rlimit values to be specified in userns even if they are already globally exceeded by the user. However, the value of the previous user_namespaces cannot be exceeded. Changelog v11: * Revert most of changes to fix performance issues. v10: * Fix memory leak on get_ucounts failure. Signed-off-by: Alexey Gladkov Link: https://lkml.kernel.org/r/df9d7764dddd50f28616b7840de74ec0f81711a8.1619094428.git.legion@kernel.org Signed-off-by: Eric W. Biederman --- include/linux/sched/user.h | 1 - include/linux/signal_types.h | 4 +++- include/linux/user_namespace.h | 1 + 3 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h index 8a34446681aa..8ba9cec4fb99 100644 --- a/include/linux/sched/user.h +++ b/include/linux/sched/user.h @@ -12,7 +12,6 @@ */ struct user_struct { refcount_t __count; /* reference count */ - atomic_t sigpending; /* How many pending signals does this user have? */ #ifdef CONFIG_FANOTIFY atomic_t fanotify_listeners; #endif diff --git a/include/linux/signal_types.h b/include/linux/signal_types.h index 68e06c75c5b2..34cb28b8f16c 100644 --- a/include/linux/signal_types.h +++ b/include/linux/signal_types.h @@ -13,6 +13,8 @@ typedef struct kernel_siginfo { __SIGINFO; } kernel_siginfo_t; +struct ucounts; + /* * Real Time signals may be queued. */ @@ -21,7 +23,7 @@ struct sigqueue { struct list_head list; int flags; kernel_siginfo_t info; - struct user_struct *user; + struct ucounts *ucounts; }; /* flags values. */ diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 5eeb86b00e68..58f417986472 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -52,6 +52,7 @@ enum ucount_type { #endif UCOUNT_RLIMIT_NPROC, UCOUNT_RLIMIT_MSGQUEUE, + UCOUNT_RLIMIT_SIGPENDING, UCOUNT_COUNTS, }; -- cgit v1.2.3 From d7c9e99aee48e6bc0b427f3e3c658a6aba15001e Mon Sep 17 00:00:00 2001 From: Alexey Gladkov Date: Thu, 22 Apr 2021 14:27:14 +0200 Subject: Reimplement RLIMIT_MEMLOCK on top of ucounts The rlimit counter is tied to uid in the user_namespace. This allows rlimit values to be specified in userns even if they are already globally exceeded by the user. However, the value of the previous user_namespaces cannot be exceeded. Changelog v11: * Fix issue found by lkp robot. v8: * Fix issues found by lkp-tests project. v7: * Keep only ucounts for RLIMIT_MEMLOCK checks instead of struct cred. v6: * Fix bug in hugetlb_file_setup() detected by trinity. Reported-by: kernel test robot Reported-by: kernel test robot Signed-off-by: Alexey Gladkov Link: https://lkml.kernel.org/r/970d50c70c71bfd4496e0e8d2a0a32feebebb350.1619094428.git.legion@kernel.org Signed-off-by: Eric W. Biederman --- include/linux/hugetlb.h | 4 ++-- include/linux/mm.h | 4 ++-- include/linux/sched/user.h | 1 - include/linux/shmem_fs.h | 2 +- include/linux/user_namespace.h | 1 + 5 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index cccd1aab69dd..96d63dbdec65 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -434,7 +434,7 @@ static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode) extern const struct file_operations hugetlbfs_file_operations; extern const struct vm_operations_struct hugetlb_vm_ops; struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct, - struct user_struct **user, int creat_flags, + struct ucounts **ucounts, int creat_flags, int page_size_log); static inline bool is_file_hugepages(struct file *file) @@ -454,7 +454,7 @@ static inline struct hstate *hstate_inode(struct inode *i) #define is_file_hugepages(file) false static inline struct file * hugetlb_file_setup(const char *name, size_t size, vm_flags_t acctflag, - struct user_struct **user, int creat_flags, + struct ucounts **ucounts, int creat_flags, int page_size_log) { return ERR_PTR(-ENOSYS); diff --git a/include/linux/mm.h b/include/linux/mm.h index 8ba434287387..3b4e24738ce4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1670,8 +1670,8 @@ extern bool can_do_mlock(void); #else static inline bool can_do_mlock(void) { return false; } #endif -extern int user_shm_lock(size_t, struct user_struct *); -extern void user_shm_unlock(size_t, struct user_struct *); +extern int user_shm_lock(size_t, struct ucounts *); +extern void user_shm_unlock(size_t, struct ucounts *); /* * Parameter block passed down to zap_pte_range in exceptional cases. diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h index 8ba9cec4fb99..82bd2532da6b 100644 --- a/include/linux/sched/user.h +++ b/include/linux/sched/user.h @@ -18,7 +18,6 @@ struct user_struct { #ifdef CONFIG_EPOLL atomic_long_t epoll_watches; /* The number of file descriptors currently watched */ #endif - unsigned long locked_shm; /* How many pages of mlocked shm ? */ unsigned long unix_inflight; /* How many files in flight in unix sockets */ atomic_long_t pipe_bufs; /* how many pages are allocated in pipe buffers */ diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index d82b6f396588..aa77dcd1646f 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -65,7 +65,7 @@ extern struct file *shmem_file_setup_with_mnt(struct vfsmount *mnt, extern int shmem_zero_setup(struct vm_area_struct *); extern unsigned long shmem_get_unmapped_area(struct file *, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); -extern int shmem_lock(struct file *file, int lock, struct user_struct *user); +extern int shmem_lock(struct file *file, int lock, struct ucounts *ucounts); #ifdef CONFIG_SHMEM extern const struct address_space_operations shmem_aops; static inline bool shmem_mapping(struct address_space *mapping) diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 58f417986472..2a3177b9b8bf 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -53,6 +53,7 @@ enum ucount_type { UCOUNT_RLIMIT_NPROC, UCOUNT_RLIMIT_MSGQUEUE, UCOUNT_RLIMIT_SIGPENDING, + UCOUNT_RLIMIT_MEMLOCK, UCOUNT_COUNTS, }; -- cgit v1.2.3 From c1ada3dc7219b02b3467aa906c2f5f8b098578d1 Mon Sep 17 00:00:00 2001 From: Alexey Gladkov Date: Thu, 22 Apr 2021 14:27:16 +0200 Subject: ucounts: Set ucount_max to the largest positive value the type can hold The ns->ucount_max[] is signed long which is less than the rlimit size. We have to protect ucount_max[] from overflow and only use the largest value that we can hold. On 32bit using "long" instead of "unsigned long" to hold the counts has the downside that RLIMIT_MSGQUEUE and RLIMIT_MEMLOCK are limited to 2GiB instead of 4GiB. I don't think anyone cares but it should be mentioned in case someone does. The RLIMIT_NPROC and RLIMIT_SIGPENDING used atomic_t so their maximum hasn't changed. Signed-off-by: Alexey Gladkov Link: https://lkml.kernel.org/r/1825a5dfa18bc5a570e79feb05e2bd07fd57e7e3.1619094428.git.legion@kernel.org Signed-off-by: Eric W. Biederman --- include/linux/user_namespace.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 2a3177b9b8bf..61794ae32fa8 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -125,6 +125,12 @@ long inc_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v); bool dec_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v); bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long max); +static inline void set_rlimit_ucount_max(struct user_namespace *ns, + enum ucount_type type, unsigned long max) +{ + ns->ucount_max[type] = max <= LONG_MAX ? max : LONG_MAX; +} + #ifdef CONFIG_USER_NS static inline struct user_namespace *get_user_ns(struct user_namespace *ns) -- cgit v1.2.3 From 1333a6779501f4cc662ff5c8b36b0a22f3a7ddc6 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Sat, 24 Apr 2021 13:06:04 +0200 Subject: nvmem: core: allow specifying of_node Until now, the of_node of the parent device is used. Some devices provide more than just the nvmem provider. To avoid name space clashes, add a way to allow specifying the nvmem cells in subnodes. Consider the following example: flash@0 { compatible = "jedec,spi-nor"; partitions { compatible = "fixed-partitions"; #address-cells = <1>; #size-cells = <1>; partition@0 { reg = <0x000000 0x010000>; }; }; otp { compatible = "user-otp"; #address-cells = <1>; #size-cells = <1>; serial-number@0 { reg = <0x0 0x8>; }; }; }; There the nvmem provider might be the MTD partition or the OTP region of the flash. Add a new config->of_node parameter, which if set, will be used instead of the parent's of_node. Signed-off-by: Michael Walle Acked-by: Srinivas Kandagatla Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210424110608.15748-2-michael@walle.cc --- include/linux/nvmem-provider.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index e162b757b6d5..471cb7b9e896 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -57,6 +57,7 @@ struct nvmem_keepout { * @type: Type of the nvmem storage * @read_only: Device is read-only. * @root_only: Device is accessibly to root only. + * @of_node: If given, this will be used instead of the parent's of_node. * @no_of_node: Device should not use the parent's of_node even if it's !NULL. * @reg_read: Callback to read data. * @reg_write: Callback to write data. @@ -86,6 +87,7 @@ struct nvmem_config { enum nvmem_type type; bool read_only; bool root_only; + struct device_node *of_node; bool no_of_node; nvmem_reg_read_t reg_read; nvmem_reg_write_t reg_write; -- cgit v1.2.3 From 4b361cfa862479fbb1d14ddf01de4dbc7146dcc5 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Sat, 24 Apr 2021 13:06:08 +0200 Subject: mtd: core: add OTP nvmem provider support Flash OTP regions can already be read via user space. Some boards have their serial number or MAC addresses stored in the OTP regions. Add support for them being a (read-only) nvmem provider. The API to read the OTP data is already in place. It distinguishes between factory and user OTP, thus there are up to two different providers. Signed-off-by: Michael Walle Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210424110608.15748-6-michael@walle.cc --- include/linux/mtd/mtd.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index a89955f3cbc8..88227044fc86 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -380,6 +380,8 @@ struct mtd_info { int usecount; struct mtd_debug_info dbg; struct nvmem_device *nvmem; + struct nvmem_device *otp_user_nvmem; + struct nvmem_device *otp_factory_nvmem; /* * Parent device from the MTD partition point of view. -- cgit v1.2.3 From 0e4768713e71dd224633fd7e00ad358bc48f433a Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 23 Apr 2021 21:24:31 +0300 Subject: spi: pxa2xx: Replace header inclusions by forward declarations When the data structure is only referred by pointer, compiler may not need to see the contents of the data type. Thus, we may replace header inclusions by respective forward declarations. Due to above add missed headers as well. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20210423182441.50272-5-andriy.shevchenko@linux.intel.com Signed-off-by: Mark Brown --- include/linux/spi/pxa2xx_spi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/pxa2xx_spi.h b/include/linux/spi/pxa2xx_spi.h index 31f00c7f4f59..1e0e2f136319 100644 --- a/include/linux/spi/pxa2xx_spi.h +++ b/include/linux/spi/pxa2xx_spi.h @@ -5,6 +5,8 @@ #ifndef __linux_pxa2xx_spi_h #define __linux_pxa2xx_spi_h +#include + #include #define PXA2XX_CS_ASSERT (0x01) -- cgit v1.2.3 From 5edc24901f4d469f8fc943004f73655933e89dbf Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 23 Apr 2021 21:24:32 +0300 Subject: spi: pxa2xx: Unify ifdeffery used in the headers The two headers have quite different ifdeffery to prevent multiple inclusion. Unify them with the pattern that in particular reflects their location. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20210423182441.50272-6-andriy.shevchenko@linux.intel.com Signed-off-by: Mark Brown --- include/linux/pxa2xx_ssp.h | 6 +++--- include/linux/spi/pxa2xx_spi.h | 7 ++++--- 2 files changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index 7f73b26ed22e..14b049840faf 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -11,8 +11,8 @@ * PXA3xx SSP1, SSP2, SSP3, SSP4 */ -#ifndef __LINUX_SSP_H -#define __LINUX_SSP_H +#ifndef __LINUX_PXA2XX_SSP_H +#define __LINUX_PXA2XX_SSP_H #include #include @@ -270,4 +270,4 @@ static inline struct ssp_device *pxa_ssp_request_of(const struct device_node *n, static inline void pxa_ssp_free(struct ssp_device *ssp) {} #endif -#endif +#endif /* __LINUX_PXA2XX_SSP_H */ diff --git a/include/linux/spi/pxa2xx_spi.h b/include/linux/spi/pxa2xx_spi.h index 1e0e2f136319..12ef04d0896d 100644 --- a/include/linux/spi/pxa2xx_spi.h +++ b/include/linux/spi/pxa2xx_spi.h @@ -2,8 +2,8 @@ /* * Copyright (C) 2005 Stephen Street / StreetFire Sound Labs */ -#ifndef __linux_pxa2xx_spi_h -#define __linux_pxa2xx_spi_h +#ifndef __LINUX_SPI_PXA2XX_SPI_H +#define __LINUX_SPI_PXA2XX_SPI_H #include @@ -51,4 +51,5 @@ struct pxa2xx_spi_chip { extern void pxa2xx_set_spi_info(unsigned id, struct pxa2xx_spi_controller *info); #endif -#endif + +#endif /* __LINUX_SPI_PXA2XX_SPI_H */ -- cgit v1.2.3 From 1beb37b0e3f98708bfb37778049764b4500756da Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 23 Apr 2021 21:24:33 +0300 Subject: spi: pxa2xx: Group Intel Quark specific definitions DDS_RATE is Intel Quark specific definition. Move it to the rest Intel Quark related. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20210423182441.50272-7-andriy.shevchenko@linux.intel.com Signed-off-by: Mark Brown --- include/linux/pxa2xx_ssp.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index 14b049840faf..1b6c1a0922bd 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -38,7 +38,6 @@ struct device_node; #define SSDR (0x10) /* SSP Data Write/Data Read Register */ #define SSTO (0x28) /* SSP Time Out Register */ -#define DDS_RATE (0x28) /* SSP DDS Clock Rate Register (Intel Quark) */ #define SSPSP (0x2C) /* SSP Programmable Serial Protocol */ #define SSTSA (0x30) /* SSP Tx Timeslot Active */ #define SSRSA (0x34) /* SSP Rx Timeslot Active */ @@ -105,6 +104,9 @@ struct device_node; #define CE4100_SSCR1_RFT GENMASK(11, 10) /* Receive FIFO Threshold (mask) */ #define CE4100_SSCR1_RxTresh(x) (((x) - 1) << 10) /* level [1..4] */ +/* Intel Quark X1000 */ +#define DDS_RATE 0x28 /* SSP DDS Clock Rate Register */ + /* QUARK_X1000 SSCR0 bit definition */ #define QUARK_X1000_SSCR0_DSS GENMASK(4, 0) /* Data Size Select (mask) */ #define QUARK_X1000_SSCR0_DataSize(x) ((x) - 1) /* Data Size Select [4..32] */ -- cgit v1.2.3 From 661ee6280931548f7b3b887ad26a157474ae5ac4 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Sat, 8 May 2021 14:15:38 +0200 Subject: cgroup: introduce cgroup.kill Introduce the cgroup.kill file. It does what it says on the tin and allows a caller to kill a cgroup by writing "1" into cgroup.kill. The file is available in non-root cgroups. Killing cgroups is a process directed operation, i.e. the whole thread-group is affected. Consequently trying to write to cgroup.kill in threaded cgroups will be rejected and EOPNOTSUPP returned. This behavior aligns with cgroup.procs where reads in threaded-cgroups are rejected with EOPNOTSUPP. The cgroup.kill file is write-only since killing a cgroup is an event not which makes it different from e.g. freezer where a cgroup transitions between the two states. As with all new cgroup features cgroup.kill is recursive by default. Killing a cgroup is protected against concurrent migrations through the cgroup mutex. To protect against forkbombs and to mitigate the effect of racing forks a new CGRP_KILL css set lock protected flag is introduced that is set prior to killing a cgroup and unset after the cgroup has been killed. We can then check in cgroup_post_fork() where we hold the css set lock already whether the cgroup is currently being killed. If so we send the child a SIGKILL signal immediately taking it down as soon as it returns to userspace. To make the killing of the child semantically clean it is killed after all cgroup attachment operations have been finalized. There are various use-cases of this interface: - Containers usually have a conservative layout where each container usually has a delegated cgroup. For such layouts there is a 1:1 mapping between container and cgroup. If the container in addition uses a separate pid namespace then killing a container usually becomes a simple kill -9 from an ancestor pid namespace. However, there are quite a few scenarios where that isn't true. For example, there are containers that share the cgroup with other processes on purpose that are supposed to be bound to the lifetime of the container but are not in the same pidns of the container. Containers that are in a delegated cgroup but share the pid namespace with the host or other containers. - Service managers such as systemd use cgroups to group and organize processes belonging to a service. They usually rely on a recursive algorithm now to kill a service. With cgroup.kill this becomes a simple write to cgroup.kill. - Userspace OOM implementations can make good use of this feature to efficiently take down whole cgroups quickly. - The kill program can gain a new kill --cgroup /sys/fs/cgroup/delegated flag to take down cgroups. A few observations about the semantics: - If parent and child are in the same cgroup and CLONE_INTO_CGROUP is not specified we are not taking cgroup mutex meaning the cgroup can be killed while a process in that cgroup is forking. If the kill request happens right before cgroup_can_fork() and before the parent grabs its siglock the parent is guaranteed to see the pending SIGKILL. In addition we perform another check in cgroup_post_fork() whether the cgroup is being killed and is so take down the child (see above). This is robust enough and protects gainst forkbombs. If userspace really really wants to have stricter protection the simple solution would be to grab the write side of the cgroup threadgroup rwsem which will force all ongoing forks to complete before killing starts. We concluded that this is not necessary as the semantics for concurrent forking should simply align with freezer where a similar check as cgroup_post_fork() is performed. For all other cases CLONE_INTO_CGROUP is required. In this case we will grab the cgroup mutex so the cgroup can't be killed while we fork. Once we're done with the fork and have dropped cgroup mutex we are visible and will be found by any subsequent kill request. - We obviously don't kill kthreads. This means a cgroup that has a kthread will not become empty after killing and consequently no unpopulated event will be generated. The assumption is that kthreads should be in the root cgroup only anyway so this is not an issue. - We skip killing tasks that already have pending fatal signals. - Freezer doesn't care about tasks in different pid namespaces, i.e. if you have two tasks in different pid namespaces the cgroup would still be frozen. The cgroup.kill mechanism consequently behaves the same way, i.e. we kill all processes and ignore in which pid namespace they exist. - If the caller is located in a cgroup that is killed the caller will obviously be killed as well. Link: https://lore.kernel.org/r/20210503143922.3093755-1-brauner@kernel.org Cc: Shakeel Butt Cc: Roman Gushchin Cc: Tejun Heo Cc: cgroups@vger.kernel.org Reviewed-by: Shakeel Butt Reviewed-by: Serge Hallyn Acked-by: Roman Gushchin Signed-off-by: Christian Brauner Signed-off-by: Tejun Heo --- include/linux/cgroup-defs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 559ee05f86b2..43fef771009a 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -71,6 +71,9 @@ enum { /* Cgroup is frozen. */ CGRP_FROZEN, + + /* Control group has to be killed. */ + CGRP_KILL, }; /* cgroup_root->flags */ -- cgit v1.2.3 From bf067edf5d2f5b2948ee7197974a719aae3e526c Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sat, 8 May 2021 00:07:47 +0200 Subject: openrisc: always use unaligned-struct header openrisc is the only architecture using the linux/unaligned/*memmove infrastructure. There is a comment saying that this version is more efficient, but this was added in 2011 before the openrisc gcc port was merged upstream. I checked a couple of files to see what the actual difference is with the mainline gcc (9.4 and 11.1), and found that the generic header seems to produce better code now, regardless of the gcc version. Specifically, the be_memmove leads to allocating a stack slot and copying the data one byte at a time, then reading the whole word from the stack: 00000000 : 0: 9c 21 ff f4 l.addi r1,r1,-12 4: d4 01 10 04 l.sw 4(r1),r2 8: 8e 63 00 00 l.lbz r19,0(r3) c: 9c 41 00 0c l.addi r2,r1,12 10: 8e 23 00 01 l.lbz r17,1(r3) 14: db e2 9f f4 l.sb -12(r2),r19 18: db e2 8f f5 l.sb -11(r2),r17 1c: 8e 63 00 02 l.lbz r19,2(r3) 20: 8e 23 00 03 l.lbz r17,3(r3) 24: d4 01 48 08 l.sw 8(r1),r9 28: db e2 9f f6 l.sb -10(r2),r19 2c: db e2 8f f7 l.sb -9(r2),r17 30: 85 62 ff f4 l.lwz r11,-12(r2) 34: 85 21 00 08 l.lwz r9,8(r1) 38: 84 41 00 04 l.lwz r2,4(r1) 3c: 44 00 48 00 l.jr r9 40: 9c 21 00 0c l.addi r1,r1,12 while the be_struct version reads each byte into a register and does a shift to the right position: 00000000 : 0: 9c 21 ff f8 l.addi r1,r1,-8 4: 8e 63 00 00 l.lbz r19,0(r3) 8: aa 20 00 18 l.ori r17,r0,0x18 c: e2 73 88 08 l.sll r19,r19,r17 10: 8d 63 00 01 l.lbz r11,1(r3) 14: aa 20 00 10 l.ori r17,r0,0x10 18: e1 6b 88 08 l.sll r11,r11,r17 1c: e1 6b 98 04 l.or r11,r11,r19 20: 8e 23 00 02 l.lbz r17,2(r3) 24: aa 60 00 08 l.ori r19,r0,0x8 28: e2 31 98 08 l.sll r17,r17,r19 2c: d4 01 10 00 l.sw 0(r1),r2 30: d4 01 48 04 l.sw 4(r1),r9 34: 9c 41 00 08 l.addi r2,r1,8 38: e2 31 58 04 l.or r17,r17,r11 3c: 8d 63 00 03 l.lbz r11,3(r3) 40: e1 6b 88 04 l.or r11,r11,r17 44: 84 41 00 00 l.lwz r2,0(r1) 48: 85 21 00 04 l.lwz r9,4(r1) 4c: 44 00 48 00 l.jr r9 50: 9c 21 00 08 l.addi r1,r1,8 According to Stafford Horne, the new version should in fact perform better. In the trivial example, the struct version is a few instructions longer, but building a whole kernel shows an overall reduction in code size, presumably because it now has to manage fewer stack slots: text data bss dec hex filename 4792010 181480 82324 5055814 4d2546 vmlinux-unaligned-memmove 4790642 181480 82324 5054446 4d1fee vmlinux-unaligned-struct Remove the memmove version completely and let openrisc use the same code as everyone else, as a simplification. Signed-off-by: Arnd Bergmann Acked-by: Stafford Horne --- include/linux/unaligned/be_memmove.h | 37 ----------------------------- include/linux/unaligned/le_memmove.h | 37 ----------------------------- include/linux/unaligned/memmove.h | 46 ------------------------------------ 3 files changed, 120 deletions(-) delete mode 100644 include/linux/unaligned/be_memmove.h delete mode 100644 include/linux/unaligned/le_memmove.h delete mode 100644 include/linux/unaligned/memmove.h (limited to 'include/linux') diff --git a/include/linux/unaligned/be_memmove.h b/include/linux/unaligned/be_memmove.h deleted file mode 100644 index 7164214a4ba1..000000000000 --- a/include/linux/unaligned/be_memmove.h +++ /dev/null @@ -1,37 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_UNALIGNED_BE_MEMMOVE_H -#define _LINUX_UNALIGNED_BE_MEMMOVE_H - -#include - -static inline u16 get_unaligned_be16(const void *p) -{ - return __get_unaligned_memmove16((const u8 *)p); -} - -static inline u32 get_unaligned_be32(const void *p) -{ - return __get_unaligned_memmove32((const u8 *)p); -} - -static inline u64 get_unaligned_be64(const void *p) -{ - return __get_unaligned_memmove64((const u8 *)p); -} - -static inline void put_unaligned_be16(u16 val, void *p) -{ - __put_unaligned_memmove16(val, p); -} - -static inline void put_unaligned_be32(u32 val, void *p) -{ - __put_unaligned_memmove32(val, p); -} - -static inline void put_unaligned_be64(u64 val, void *p) -{ - __put_unaligned_memmove64(val, p); -} - -#endif /* _LINUX_UNALIGNED_LE_MEMMOVE_H */ diff --git a/include/linux/unaligned/le_memmove.h b/include/linux/unaligned/le_memmove.h deleted file mode 100644 index 9202e864d026..000000000000 --- a/include/linux/unaligned/le_memmove.h +++ /dev/null @@ -1,37 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_UNALIGNED_LE_MEMMOVE_H -#define _LINUX_UNALIGNED_LE_MEMMOVE_H - -#include - -static inline u16 get_unaligned_le16(const void *p) -{ - return __get_unaligned_memmove16((const u8 *)p); -} - -static inline u32 get_unaligned_le32(const void *p) -{ - return __get_unaligned_memmove32((const u8 *)p); -} - -static inline u64 get_unaligned_le64(const void *p) -{ - return __get_unaligned_memmove64((const u8 *)p); -} - -static inline void put_unaligned_le16(u16 val, void *p) -{ - __put_unaligned_memmove16(val, p); -} - -static inline void put_unaligned_le32(u32 val, void *p) -{ - __put_unaligned_memmove32(val, p); -} - -static inline void put_unaligned_le64(u64 val, void *p) -{ - __put_unaligned_memmove64(val, p); -} - -#endif /* _LINUX_UNALIGNED_LE_MEMMOVE_H */ diff --git a/include/linux/unaligned/memmove.h b/include/linux/unaligned/memmove.h deleted file mode 100644 index ac71b53bc6dc..000000000000 --- a/include/linux/unaligned/memmove.h +++ /dev/null @@ -1,46 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_UNALIGNED_MEMMOVE_H -#define _LINUX_UNALIGNED_MEMMOVE_H - -#include -#include - -/* Use memmove here, so gcc does not insert a __builtin_memcpy. */ - -static inline u16 __get_unaligned_memmove16(const void *p) -{ - u16 tmp; - memmove(&tmp, p, 2); - return tmp; -} - -static inline u32 __get_unaligned_memmove32(const void *p) -{ - u32 tmp; - memmove(&tmp, p, 4); - return tmp; -} - -static inline u64 __get_unaligned_memmove64(const void *p) -{ - u64 tmp; - memmove(&tmp, p, 8); - return tmp; -} - -static inline void __put_unaligned_memmove16(u16 val, void *p) -{ - memmove(p, &val, 2); -} - -static inline void __put_unaligned_memmove32(u32 val, void *p) -{ - memmove(p, &val, 4); -} - -static inline void __put_unaligned_memmove64(u64 val, void *p) -{ - memmove(p, &val, 8); -} - -#endif /* _LINUX_UNALIGNED_MEMMOVE_H */ -- cgit v1.2.3 From 0652035a57945e14e611dafae2ec5b46a05bc1d1 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sat, 8 May 2021 00:07:51 +0200 Subject: asm-generic: unaligned: remove byteshift helpers In theory, compilers should be able to work this out themselves so we can use a simpler version based on the swab() helpers. I have verified that this works on all supported compiler versions (gcc-4.9 and up, clang-10 and up). Looking at the object code produced by gcc-11, I found that the impact is mostly a change in inlining decisions that lead to slightly larger code. In other cases, this version produces explicit byte swaps in place of separate byte access, or comparing against pre-swapped constants. While the source code is clearly simpler, I have not seen an indication of the new version actually producing better code on Arm, so maybe we want to skip this after all. From what I can tell, gcc recognizes the byteswap pattern in the byteshift.h header and can turn it into explicit instructions, but it does not turn a __builtin_bswap32() back into individual bytes when that would result in better output, e.g. when storing a byte-reversed constant. Suggested-by: Linus Torvalds Signed-off-by: Arnd Bergmann --- include/linux/unaligned/be_byteshift.h | 71 ---------------------------------- include/linux/unaligned/be_struct.h | 30 ++++++++++++++ include/linux/unaligned/le_byteshift.h | 71 ---------------------------------- include/linux/unaligned/le_struct.h | 30 ++++++++++++++ 4 files changed, 60 insertions(+), 142 deletions(-) delete mode 100644 include/linux/unaligned/be_byteshift.h delete mode 100644 include/linux/unaligned/le_byteshift.h (limited to 'include/linux') diff --git a/include/linux/unaligned/be_byteshift.h b/include/linux/unaligned/be_byteshift.h deleted file mode 100644 index c43ff5918c8a..000000000000 --- a/include/linux/unaligned/be_byteshift.h +++ /dev/null @@ -1,71 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_UNALIGNED_BE_BYTESHIFT_H -#define _LINUX_UNALIGNED_BE_BYTESHIFT_H - -#include - -static inline u16 __get_unaligned_be16(const u8 *p) -{ - return p[0] << 8 | p[1]; -} - -static inline u32 __get_unaligned_be32(const u8 *p) -{ - return p[0] << 24 | p[1] << 16 | p[2] << 8 | p[3]; -} - -static inline u64 __get_unaligned_be64(const u8 *p) -{ - return (u64)__get_unaligned_be32(p) << 32 | - __get_unaligned_be32(p + 4); -} - -static inline void __put_unaligned_be16(u16 val, u8 *p) -{ - *p++ = val >> 8; - *p++ = val; -} - -static inline void __put_unaligned_be32(u32 val, u8 *p) -{ - __put_unaligned_be16(val >> 16, p); - __put_unaligned_be16(val, p + 2); -} - -static inline void __put_unaligned_be64(u64 val, u8 *p) -{ - __put_unaligned_be32(val >> 32, p); - __put_unaligned_be32(val, p + 4); -} - -static inline u16 get_unaligned_be16(const void *p) -{ - return __get_unaligned_be16(p); -} - -static inline u32 get_unaligned_be32(const void *p) -{ - return __get_unaligned_be32(p); -} - -static inline u64 get_unaligned_be64(const void *p) -{ - return __get_unaligned_be64(p); -} - -static inline void put_unaligned_be16(u16 val, void *p) -{ - __put_unaligned_be16(val, p); -} - -static inline void put_unaligned_be32(u32 val, void *p) -{ - __put_unaligned_be32(val, p); -} - -static inline void put_unaligned_be64(u64 val, void *p) -{ - __put_unaligned_be64(val, p); -} - -#endif /* _LINUX_UNALIGNED_BE_BYTESHIFT_H */ diff --git a/include/linux/unaligned/be_struct.h b/include/linux/unaligned/be_struct.h index 15ea503a13fc..76d9fe297c33 100644 --- a/include/linux/unaligned/be_struct.h +++ b/include/linux/unaligned/be_struct.h @@ -34,4 +34,34 @@ static inline void put_unaligned_be64(u64 val, void *p) __put_unaligned_cpu64(val, p); } +static inline u16 get_unaligned_le16(const void *p) +{ + return swab16(__get_unaligned_cpu16((const u8 *)p)); +} + +static inline u32 get_unaligned_le32(const void *p) +{ + return swab32(__get_unaligned_cpu32((const u8 *)p)); +} + +static inline u64 get_unaligned_le64(const void *p) +{ + return swab64(__get_unaligned_cpu64((const u8 *)p)); +} + +static inline void put_unaligned_le16(u16 val, void *p) +{ + __put_unaligned_cpu16(swab16(val), p); +} + +static inline void put_unaligned_le32(u32 val, void *p) +{ + __put_unaligned_cpu32(swab32(val), p); +} + +static inline void put_unaligned_le64(u64 val, void *p) +{ + __put_unaligned_cpu64(swab64(val), p); +} + #endif /* _LINUX_UNALIGNED_BE_STRUCT_H */ diff --git a/include/linux/unaligned/le_byteshift.h b/include/linux/unaligned/le_byteshift.h deleted file mode 100644 index 2248dcb0df76..000000000000 --- a/include/linux/unaligned/le_byteshift.h +++ /dev/null @@ -1,71 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_UNALIGNED_LE_BYTESHIFT_H -#define _LINUX_UNALIGNED_LE_BYTESHIFT_H - -#include - -static inline u16 __get_unaligned_le16(const u8 *p) -{ - return p[0] | p[1] << 8; -} - -static inline u32 __get_unaligned_le32(const u8 *p) -{ - return p[0] | p[1] << 8 | p[2] << 16 | p[3] << 24; -} - -static inline u64 __get_unaligned_le64(const u8 *p) -{ - return (u64)__get_unaligned_le32(p + 4) << 32 | - __get_unaligned_le32(p); -} - -static inline void __put_unaligned_le16(u16 val, u8 *p) -{ - *p++ = val; - *p++ = val >> 8; -} - -static inline void __put_unaligned_le32(u32 val, u8 *p) -{ - __put_unaligned_le16(val >> 16, p + 2); - __put_unaligned_le16(val, p); -} - -static inline void __put_unaligned_le64(u64 val, u8 *p) -{ - __put_unaligned_le32(val >> 32, p + 4); - __put_unaligned_le32(val, p); -} - -static inline u16 get_unaligned_le16(const void *p) -{ - return __get_unaligned_le16(p); -} - -static inline u32 get_unaligned_le32(const void *p) -{ - return __get_unaligned_le32(p); -} - -static inline u64 get_unaligned_le64(const void *p) -{ - return __get_unaligned_le64(p); -} - -static inline void put_unaligned_le16(u16 val, void *p) -{ - __put_unaligned_le16(val, p); -} - -static inline void put_unaligned_le32(u32 val, void *p) -{ - __put_unaligned_le32(val, p); -} - -static inline void put_unaligned_le64(u64 val, void *p) -{ - __put_unaligned_le64(val, p); -} - -#endif /* _LINUX_UNALIGNED_LE_BYTESHIFT_H */ diff --git a/include/linux/unaligned/le_struct.h b/include/linux/unaligned/le_struct.h index 9977987883a6..22f90a4afaa5 100644 --- a/include/linux/unaligned/le_struct.h +++ b/include/linux/unaligned/le_struct.h @@ -34,4 +34,34 @@ static inline void put_unaligned_le64(u64 val, void *p) __put_unaligned_cpu64(val, p); } +static inline u16 get_unaligned_be16(const void *p) +{ + return swab16(__get_unaligned_cpu16((const u8 *)p)); +} + +static inline u32 get_unaligned_be32(const void *p) +{ + return swab32(__get_unaligned_cpu32((const u8 *)p)); +} + +static inline u64 get_unaligned_be64(const void *p) +{ + return swab64(__get_unaligned_cpu64((const u8 *)p)); +} + +static inline void put_unaligned_be16(u16 val, void *p) +{ + __put_unaligned_cpu16(swab16(val), p); +} + +static inline void put_unaligned_be32(u32 val, void *p) +{ + __put_unaligned_cpu32(swab32(val), p); +} + +static inline void put_unaligned_be64(u64 val, void *p) +{ + __put_unaligned_cpu64(swab64(val), p); +} + #endif /* _LINUX_UNALIGNED_LE_STRUCT_H */ -- cgit v1.2.3 From 778aaefb8e864fc61f850539ea479554dd4caea1 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sat, 8 May 2021 00:07:52 +0200 Subject: asm-generic: unaligned always use struct helpers As found by Vineet Gupta and Linus Torvalds, gcc has somewhat unexpected behavior when faced with overlapping unaligned pointers. The kernel's unaligned/access-ok.h header technically invokes undefined behavior that happens to usually work on the architectures using it, but if the compiler optimizes code based on the assumption that undefined behavior doesn't happen, it can create output that actually causes data corruption. A related problem was previously found on 32-bit ARMv7, where most instructions can be used on unaligned data, but 64-bit ldrd/strd causes an exception. The workaround was to always use the unaligned/le_struct.h helper instead of unaligned/access-ok.h, in commit 1cce91dfc8f7 ("ARM: 8715/1: add a private asm/unaligned.h"). The same solution should work on all other architectures as well, so remove the access-ok.h variant and use the other one unconditionally on all architectures, picking either the big-endian or little-endian version. With this, the arm specific header can be removed as well, and the only file including linux/unaligned/access_ok.h gets moved to including the normal file. Fortunately, this made almost no difference to the object code produced by gcc-11. On x86, s390, powerpc, and arc, the resulting binary appears to be identical to the previous version, while on arm64 and m68k there are minimal differences that looks like an optimization pass went into a different direction, usually using fewer stack spills on the new version. Signed-off-by: Arnd Bergmann Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=100363 --- include/linux/unaligned/access_ok.h | 68 ------------------------------------- 1 file changed, 68 deletions(-) delete mode 100644 include/linux/unaligned/access_ok.h (limited to 'include/linux') diff --git a/include/linux/unaligned/access_ok.h b/include/linux/unaligned/access_ok.h deleted file mode 100644 index 167aa849c0ce..000000000000 --- a/include/linux/unaligned/access_ok.h +++ /dev/null @@ -1,68 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_UNALIGNED_ACCESS_OK_H -#define _LINUX_UNALIGNED_ACCESS_OK_H - -#include -#include - -static __always_inline u16 get_unaligned_le16(const void *p) -{ - return le16_to_cpup((__le16 *)p); -} - -static __always_inline u32 get_unaligned_le32(const void *p) -{ - return le32_to_cpup((__le32 *)p); -} - -static __always_inline u64 get_unaligned_le64(const void *p) -{ - return le64_to_cpup((__le64 *)p); -} - -static __always_inline u16 get_unaligned_be16(const void *p) -{ - return be16_to_cpup((__be16 *)p); -} - -static __always_inline u32 get_unaligned_be32(const void *p) -{ - return be32_to_cpup((__be32 *)p); -} - -static __always_inline u64 get_unaligned_be64(const void *p) -{ - return be64_to_cpup((__be64 *)p); -} - -static __always_inline void put_unaligned_le16(u16 val, void *p) -{ - *((__le16 *)p) = cpu_to_le16(val); -} - -static __always_inline void put_unaligned_le32(u32 val, void *p) -{ - *((__le32 *)p) = cpu_to_le32(val); -} - -static __always_inline void put_unaligned_le64(u64 val, void *p) -{ - *((__le64 *)p) = cpu_to_le64(val); -} - -static __always_inline void put_unaligned_be16(u16 val, void *p) -{ - *((__be16 *)p) = cpu_to_be16(val); -} - -static __always_inline void put_unaligned_be32(u32 val, void *p) -{ - *((__be32 *)p) = cpu_to_be32(val); -} - -static __always_inline void put_unaligned_be64(u64 val, void *p) -{ - *((__be64 *)p) = cpu_to_be64(val); -} - -#endif /* _LINUX_UNALIGNED_ACCESS_OK_H */ -- cgit v1.2.3 From 9d9d415f0048e4f7a6109595e2d1657850569c6c Mon Sep 17 00:00:00 2001 From: "Radu Pirea (NXP OSS)" Date: Mon, 10 May 2021 18:34:32 +0300 Subject: ptp: ptp_clock: make scaled_ppm_to_ppb static inline Make scaled_ppm_to_ppb static inline to be able to build drivers that use this function even with PTP_1588_CLOCK disabled. Signed-off-by: Radu Pirea (NXP OSS) Signed-off-by: David S. Miller --- include/linux/ptp_clock_kernel.h | 34 ++++++++++++++++++++++++++-------- 1 file changed, 26 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 0d47fd33b228..a311bddd9e85 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -186,6 +186,32 @@ struct ptp_clock_event { }; }; +/** + * scaled_ppm_to_ppb() - convert scaled ppm to ppb + * + * @ppm: Parts per million, but with a 16 bit binary fractional field + */ +static inline s32 scaled_ppm_to_ppb(long ppm) +{ + /* + * The 'freq' field in the 'struct timex' is in parts per + * million, but with a 16 bit binary fractional field. + * + * We want to calculate + * + * ppb = scaled_ppm * 1000 / 2^16 + * + * which simplifies to + * + * ppb = scaled_ppm * 125 / 2^13 + */ + s64 ppb = 1 + ppm; + + ppb *= 125; + ppb >>= 13; + return (s32)ppb; +} + #if IS_REACHABLE(CONFIG_PTP_1588_CLOCK) /** @@ -229,14 +255,6 @@ extern void ptp_clock_event(struct ptp_clock *ptp, extern int ptp_clock_index(struct ptp_clock *ptp); -/** - * scaled_ppm_to_ppb() - convert scaled ppm to ppb - * - * @ppm: Parts per million, but with a 16 bit binary fractional field - */ - -extern s32 scaled_ppm_to_ppb(long ppm); - /** * ptp_find_pin() - obtain the pin index of a given auxiliary function * -- cgit v1.2.3 From 258ca95e2cd9a0fcc4508a1bf1742b1a3e9a7bbb Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 23 Feb 2021 01:10:04 +0100 Subject: timer: Revert "timer: Add timer_curr_running()" This reverts commit dcd42591ebb8a25895b551a5297ea9c24414ba54. The only user was RCU/nocb. Signed-off-by: Frederic Weisbecker Cc: Josh Triplett Cc: Lai Jiangshan Cc: Joel Fernandes Cc: Neeraj Upadhyay Cc: Boqun Feng Cc: Thomas Gleixner Signed-off-by: Paul E. McKenney --- include/linux/timer.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timer.h b/include/linux/timer.h index 4118a97e62fb..fda13c9d1256 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -192,8 +192,6 @@ extern int try_to_del_timer_sync(struct timer_list *timer); #define del_singleshot_timer_sync(t) del_timer_sync(t) -extern bool timer_curr_running(struct timer_list *timer); - extern void init_timers(void); struct hrtimer; extern enum hrtimer_restart it_real_fn(struct hrtimer *); -- cgit v1.2.3 From 7bf0a6141ab9c1d113bd85d6d13d43903a4278ba Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 9 Apr 2021 00:38:58 +0200 Subject: srcu: Unconditionally embed struct lockdep_map Since struct lockdep_map has zero size when CONFIG_DEBUG_LOCK_ALLOC=n, this commit removes the #ifdef from the srcu_struct structure's ->dep_map. This change will simplify further manipulations of this field. Signed-off-by: Frederic Weisbecker Cc: Uladzislau Rezki Cc: Boqun Feng Cc: Lai Jiangshan Cc: Neeraj Upadhyay Cc: Josh Triplett Cc: Joel Fernandes Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 9cfcc8a756ae..cb1f4351e8ba 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -82,9 +82,7 @@ struct srcu_struct { /* callback for the barrier */ /* operation. */ struct delayed_work work; -#ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; -#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ }; /* Values for state variable (bottom bits of ->srcu_gp_seq). */ -- cgit v1.2.3 From 8e9c01c717df7e05c5bd1ca86aaa3a74b31f37f1 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 9 Apr 2021 00:38:59 +0200 Subject: srcu: Initialize SRCU after timers Once srcu_init() is called, the SRCU core will make use of delayed workqueues, which rely on timers. However init_timers() is called several steps after rcu_init(). This means that a call_srcu() after rcu_init() but before init_timers() would find itself within a dangerously uninitialized timer core. This commit therefore creates a separate call to srcu_init() after init_timer() completes, which ensures that we stay in early SRCU mode until timers are safe(r). Signed-off-by: Frederic Weisbecker Cc: Uladzislau Rezki Cc: Boqun Feng Cc: Lai Jiangshan Cc: Neeraj Upadhyay Cc: Josh Triplett Cc: Joel Fernandes Signed-off-by: Paul E. McKenney --- include/linux/srcu.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/srcu.h b/include/linux/srcu.h index a0895bbf71ce..e6011a9975af 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -64,6 +64,12 @@ unsigned long get_state_synchronize_srcu(struct srcu_struct *ssp); unsigned long start_poll_synchronize_srcu(struct srcu_struct *ssp); bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie); +#ifdef CONFIG_SRCU +void srcu_init(void); +#else /* #ifdef CONFIG_SRCU */ +static inline void srcu_init(void) { } +#endif /* #else #ifdef CONFIG_SRCU */ + #ifdef CONFIG_DEBUG_LOCK_ALLOC /** -- cgit v1.2.3 From c9e73e3d2b1eb1ea7ff068e05007eec3bd8ef1c9 Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Thu, 29 Apr 2021 14:46:56 +0100 Subject: bpf: verifier: Allocate idmap scratch in verifier env func_states_equal makes a very short lived allocation for idmap, probably because it's too large to fit on the stack. However the function is called quite often, leading to a lot of alloc / free churn. Replace the temporary allocation with dedicated scratch space in struct bpf_verifier_env. Signed-off-by: Lorenz Bauer Signed-off-by: Alexei Starovoitov Acked-by: Edward Cree Link: https://lore.kernel.org/bpf/20210429134656.122225-4-lmb@cloudflare.com --- include/linux/bpf_verifier.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 06841517ab1e..d4632aa3ca50 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -215,6 +215,13 @@ struct bpf_idx_pair { u32 idx; }; +struct bpf_id_pair { + u32 old; + u32 cur; +}; + +/* Maximum number of register states that can exist at once */ +#define BPF_ID_MAP_SIZE (MAX_BPF_REG + MAX_BPF_STACK / BPF_REG_SIZE) #define MAX_CALL_FRAMES 8 struct bpf_verifier_state { /* call stack tracking */ @@ -418,6 +425,7 @@ struct bpf_verifier_env { const struct bpf_line_info *prev_linfo; struct bpf_verifier_log log; struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 1]; + struct bpf_id_pair idmap_scratch[BPF_ID_MAP_SIZE]; struct { int *insn_state; int *insn_stack; -- cgit v1.2.3 From ce7c169dee28866539abb0e603b9a23055d30fdc Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 30 Mar 2021 13:23:49 -0700 Subject: rcu: Remove the unused rcu_irq_exit_preempt() function Commit 9ee01e0f69a9 ("x86/entry: Clean up idtentry_enter/exit() leftovers") left the rcu_irq_exit_preempt() in place in order to avoid conflicts with the -rcu tree. Now that this change has long since hit mainline, this commit removes the no-longer-used rcu_irq_exit_preempt() function. Signed-off-by: Paul E. McKenney --- include/linux/rcutiny.h | 1 - include/linux/rcutree.h | 1 - 2 files changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 35e0be326ffc..953e70fafe38 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -86,7 +86,6 @@ static inline void rcu_irq_enter(void) { } static inline void rcu_irq_exit_irqson(void) { } static inline void rcu_irq_enter_irqson(void) { } static inline void rcu_irq_exit(void) { } -static inline void rcu_irq_exit_preempt(void) { } static inline void rcu_irq_exit_check_preempt(void) { } #define rcu_is_idle_cpu(cpu) \ (is_idle_task(current) && !in_nmi() && !in_irq() && !in_serving_softirq()) diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index b89b54130f49..53209d669400 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -49,7 +49,6 @@ void rcu_idle_enter(void); void rcu_idle_exit(void); void rcu_irq_enter(void); void rcu_irq_exit(void); -void rcu_irq_exit_preempt(void); void rcu_irq_enter_irqson(void); void rcu_irq_exit_irqson(void); bool rcu_is_idle_cpu(int cpu); -- cgit v1.2.3 From 3066820034b5dd4e89bd74a7739c51c2d6f5e554 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 5 Apr 2021 09:51:05 -0700 Subject: rcu: Reject RCU_LOCKDEP_WARN() false positives If another lockdep report runs concurrently with an RCU lockdep report from RCU_LOCKDEP_WARN(), the following sequence of events can occur: 1. debug_lockdep_rcu_enabled() sees that lockdep is enabled when called from (say) synchronize_rcu(). 2. Lockdep is disabled by a concurrent lockdep report. 3. debug_lockdep_rcu_enabled() evaluates its lockdep-expression argument, for example, lock_is_held(&rcu_bh_lock_map). 4. Because lockdep is now disabled, lock_is_held() plays it safe and returns the constant 1. 5. But in this case, the constant 1 is not safe, because invoking synchronize_rcu() under rcu_read_lock_bh() is disallowed. 6. debug_lockdep_rcu_enabled() wrongly invokes lockdep_rcu_suspicious(), resulting in a false-positive splat. This commit therefore changes RCU_LOCKDEP_WARN() to check debug_lockdep_rcu_enabled() after checking the lockdep expression, so that any "safe" returns from lock_is_held() are rejected by debug_lockdep_rcu_enabled(). This requires memory ordering, which is supplied by READ_ONCE(debug_locks). The resulting volatile accesses prevent the compiler from reordering and the fact that only one variable is being accessed prevents the underlying hardware from reordering. The combination works for IA64, which can reorder reads to the same location, but this is defeated by the volatile accesses, which compile to load instructions that provide ordering. Reported-by: syzbot+dde0cc33951735441301@syzkaller.appspotmail.com Reported-by: Matthew Wilcox Reported-by: syzbot+88e4f02896967fe1ab0d@syzkaller.appspotmail.com Reported-by: Thomas Gleixner Suggested-by: Boqun Feng Reviewed-by: Boqun Feng Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 9455476c5ba2..1199ffd305d1 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -315,7 +315,7 @@ static inline int rcu_read_lock_any_held(void) #define RCU_LOCKDEP_WARN(c, s) \ do { \ static bool __section(".data.unlikely") __warned; \ - if (debug_lockdep_rcu_enabled() && !__warned && (c)) { \ + if ((c) && debug_lockdep_rcu_enabled() && !__warned) { \ __warned = true; \ lockdep_rcu_suspicious(__FILE__, __LINE__, s); \ } \ -- cgit v1.2.3 From f4f809f66b7545b89bff4b132cdb37adc2d2c157 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Mon, 10 May 2021 14:39:46 -0700 Subject: cgroup: inline cgroup_task_freeze() After the introduction of the cgroup.kill there is only one call site of cgroup_task_freeze() left: cgroup_exit(). cgroup_task_freeze() is currently taking rcu_read_lock() to read task's cgroup flags, but because it's always called with css_set_lock locked, the rcu protection is excessive. Simplify the code by inlining cgroup_task_freeze(). v2: fix build Signed-off-by: Roman Gushchin Reviewed-by: Shakeel Butt Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 18 ------------------ 1 file changed, 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 4f2f79de083e..a72764287cb5 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -906,20 +906,6 @@ void cgroup_freeze(struct cgroup *cgrp, bool freeze); void cgroup_freezer_migrate_task(struct task_struct *task, struct cgroup *src, struct cgroup *dst); -static inline bool cgroup_task_freeze(struct task_struct *task) -{ - bool ret; - - if (task->flags & PF_KTHREAD) - return false; - - rcu_read_lock(); - ret = test_bit(CGRP_FREEZE, &task_dfl_cgroup(task)->flags); - rcu_read_unlock(); - - return ret; -} - static inline bool cgroup_task_frozen(struct task_struct *task) { return task->frozen; @@ -929,10 +915,6 @@ static inline bool cgroup_task_frozen(struct task_struct *task) static inline void cgroup_enter_frozen(void) { } static inline void cgroup_leave_frozen(bool always_leave) { } -static inline bool cgroup_task_freeze(struct task_struct *task) -{ - return false; -} static inline bool cgroup_task_frozen(struct task_struct *task) { return false; -- cgit v1.2.3 From 8a922805fb0950187ff037801e337aec010a6ccb Mon Sep 17 00:00:00 2001 From: Zhongjun Tan Date: Fri, 9 Apr 2021 13:48:41 +0800 Subject: selinux: delete selinux_xfrm_policy_lookup() useless argument seliunx_xfrm_policy_lookup() is hooks of security_xfrm_policy_lookup(). The dir argument is uselss in security_xfrm_policy_lookup(). So remove the dir argument from selinux_xfrm_policy_lookup() and security_xfrm_policy_lookup(). Signed-off-by: Zhongjun Tan [PM: reformat the subject line] Signed-off-by: Paul Moore --- include/linux/lsm_hook_defs.h | 3 +-- include/linux/security.h | 4 ++-- 2 files changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 04c01794de83..2adeea44c0d5 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -358,8 +358,7 @@ LSM_HOOK(int, 0, xfrm_state_alloc_acquire, struct xfrm_state *x, struct xfrm_sec_ctx *polsec, u32 secid) LSM_HOOK(void, LSM_RET_VOID, xfrm_state_free_security, struct xfrm_state *x) LSM_HOOK(int, 0, xfrm_state_delete_security, struct xfrm_state *x) -LSM_HOOK(int, 0, xfrm_policy_lookup, struct xfrm_sec_ctx *ctx, u32 fl_secid, - u8 dir) +LSM_HOOK(int, 0, xfrm_policy_lookup, struct xfrm_sec_ctx *ctx, u32 fl_secid) LSM_HOOK(int, 1, xfrm_state_pol_flow_match, struct xfrm_state *x, struct xfrm_policy *xp, const struct flowi_common *flic) LSM_HOOK(int, 0, xfrm_decode_session, struct sk_buff *skb, u32 *secid, diff --git a/include/linux/security.h b/include/linux/security.h index 06f7c50ce77f..24eda04221e9 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1681,7 +1681,7 @@ int security_xfrm_state_alloc_acquire(struct xfrm_state *x, struct xfrm_sec_ctx *polsec, u32 secid); int security_xfrm_state_delete(struct xfrm_state *x); void security_xfrm_state_free(struct xfrm_state *x); -int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir); +int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid); int security_xfrm_state_pol_flow_match(struct xfrm_state *x, struct xfrm_policy *xp, const struct flowi_common *flic); @@ -1732,7 +1732,7 @@ static inline int security_xfrm_state_delete(struct xfrm_state *x) return 0; } -static inline int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir) +static inline int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid) { return 0; } -- cgit v1.2.3 From 0c8ccd8b267fc735e4621774ce62728f27d42863 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 10 May 2021 15:41:29 +0300 Subject: spi: pxa2xx: Use pxa_ssp_enable()/pxa_ssp_disable() in the driver There are few places that repeat the logic of pxa_ssp_enable() and pxa_ssp_disable(). Use them instead of open coded variants. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20210510124134.24638-10-andriy.shevchenko@linux.intel.com Signed-off-by: Mark Brown --- include/linux/pxa2xx_ssp.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index 1b6c1a0922bd..fdfbe17e15f4 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -254,6 +254,22 @@ static inline u32 pxa_ssp_read_reg(struct ssp_device *dev, u32 reg) return __raw_readl(dev->mmio_base + reg); } +static inline void pxa_ssp_enable(struct ssp_device *ssp) +{ + u32 sscr0; + + sscr0 = pxa_ssp_read_reg(ssp, SSCR0) | SSCR0_SSE; + pxa_ssp_write_reg(ssp, SSCR0, sscr0); +} + +static inline void pxa_ssp_disable(struct ssp_device *ssp) +{ + u32 sscr0; + + sscr0 = pxa_ssp_read_reg(ssp, SSCR0) & ~SSCR0_SSE; + pxa_ssp_write_reg(ssp, SSCR0, sscr0); +} + #if IS_ENABLED(CONFIG_PXA_SSP) struct ssp_device *pxa_ssp_request(int port, const char *label); void pxa_ssp_free(struct ssp_device *); -- cgit v1.2.3 From 3fdb59cf10b020b32b9f1dfc78611320623dcb3e Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 10 May 2021 15:41:34 +0300 Subject: spi: pxa2xx: Introduce special type for Merrifield SPIs Intel Merrifield SPI is actually more closer to PXA3xx. It has extended FIFO (32 bytes) and additional registers to get or set FIFO thresholds. Introduce new type for Intel Merrifield SPI host controllers and handle bigger FIFO size. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20210510124134.24638-15-andriy.shevchenko@linux.intel.com Signed-off-by: Mark Brown --- include/linux/pxa2xx_ssp.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index fdfbe17e15f4..2b21bc1f3c73 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -183,6 +183,21 @@ struct device_node; #define SSACD_ACPS(x) ((x) << 4) /* Audio clock PLL select */ #define SSACD_SCDX8 BIT(7) /* SYSCLK division ratio select */ +/* Intel Merrifield SSP */ +#define SFIFOL 0x68 /* FIFO level */ +#define SFIFOTT 0x6c /* FIFO trigger threshold */ + +#define RX_THRESH_MRFLD_DFLT 16 +#define TX_THRESH_MRFLD_DFLT 16 + +#define SFIFOL_TFL_MASK GENMASK(15, 0) /* Transmit FIFO Level mask */ +#define SFIFOL_RFL_MASK GENMASK(31, 16) /* Receive FIFO Level mask */ + +#define SFIFOTT_TFT GENMASK(15, 0) /* Transmit FIFO Threshold (mask) */ +#define SFIFOTT_TxThresh(x) (((x) - 1) << 0) /* TX FIFO trigger threshold / level */ +#define SFIFOTT_RFT GENMASK(31, 16) /* Receive FIFO Threshold (mask) */ +#define SFIFOTT_RxThresh(x) (((x) - 1) << 16) /* RX FIFO trigger threshold / level */ + /* LPSS SSP */ #define SSITF 0x44 /* TX FIFO trigger level */ #define SSITF_TxHiThresh(x) (((x) - 1) << 0) @@ -205,6 +220,7 @@ enum pxa_ssp_type { MMP2_SSP, PXA910_SSP, CE4100_SSP, + MRFLD_SSP, QUARK_X1000_SSP, LPSS_LPT_SSP, /* Keep LPSS types sorted with lpss_platforms[] */ LPSS_BYT_SSP, -- cgit v1.2.3 From 345e9f5ca798600e44c0843646621f2804eb99f4 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 11 May 2021 11:00:45 +0800 Subject: soundwire: bus: only use CLOCK_STOP_MODE0 and fix confusions Existing devices and implementations only support the required CLOCK_STOP_MODE0. All the code related to CLOCK_STOP_MODE1 has not been tested and is highly questionable, with a clear confusion between CLOCK_STOP_MODE1 and the simple clock stop state machine. This patch removes all usages of CLOCK_STOP_MODE1 - which has no impact on any solution - and fixes the use of the simple clock stop state machine. The resulting code should be a lot more symmetrical and easier to maintain. Note that CLOCK_STOP_MODE1 is not supported in the SoundWire Device Class specification so it's rather unlikely that we need to re-add this mode later. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Guennadi Liakhovetski Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20210511030048.25622-2-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index ced07f8fde87..5d93d9949653 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -624,7 +624,6 @@ struct sdw_slave_ops { int (*port_prep)(struct sdw_slave *slave, struct sdw_prepare_ch *prepare_ch, enum sdw_port_prep_ops pre_ops); - int (*get_clk_stop_mode)(struct sdw_slave *slave); int (*clk_stop)(struct sdw_slave *slave, enum sdw_clk_stop_mode mode, enum sdw_clk_stop_type type); @@ -675,7 +674,6 @@ struct sdw_slave { struct list_head node; struct completion port_ready[SDW_MAX_PORTS]; unsigned int m_port_map[SDW_MAX_PORTS]; - enum sdw_clk_stop_mode curr_clk_stop_mode; u16 dev_num; u16 dev_num_sticky; bool probed; -- cgit v1.2.3 From 448df2d8fcab6cc50e0de4679ce3afe2ece282f2 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 11 May 2021 11:00:46 +0800 Subject: soundwire: add missing kernel-doc description For some reason we never added a description for the clk_stop callback. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Guennadi Liakhovetski Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20210511030048.25622-3-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 5d93d9949653..8ca736e92d5a 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -612,6 +612,7 @@ struct sdw_bus_params { * @update_status: Update Slave status * @bus_config: Update the bus config for Slave * @port_prep: Prepare the port with parameters + * @clk_stop: handle imp-def sequences before and after prepare and de-prepare */ struct sdw_slave_ops { int (*read_prop)(struct sdw_slave *sdw); -- cgit v1.2.3 From bf30396cdf8132a199af5f8f0e60367876f455df Mon Sep 17 00:00:00 2001 From: Loic Poulain Date: Tue, 11 May 2021 16:42:22 +0200 Subject: net: wwan: Add unknown port type Some devices may have ports with unknown type/protocol which need to be tagged (though not supported by WWAN core). This will be the case for cdc-wdm based drivers. Signed-off-by: Loic Poulain Signed-off-by: David S. Miller --- include/linux/wwan.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/wwan.h b/include/linux/wwan.h index aa05a253dcf9..7216c114d758 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -15,6 +15,7 @@ * @WWAN_PORT_QMI: Qcom modem/MSM interface for modem control * @WWAN_PORT_QCDM: Qcom Modem diagnostic interface * @WWAN_PORT_FIREHOSE: XML based command protocol + * @WWAN_PORT_UNKNOWN: Unknown port type * @WWAN_PORT_MAX: Number of supported port types */ enum wwan_port_type { @@ -23,7 +24,8 @@ enum wwan_port_type { WWAN_PORT_QMI, WWAN_PORT_QCDM, WWAN_PORT_FIREHOSE, - WWAN_PORT_MAX, + WWAN_PORT_UNKNOWN, + WWAN_PORT_MAX = WWAN_PORT_UNKNOWN, }; struct wwan_port; -- cgit v1.2.3 From cac6fb015f719104e60b1c68c15ca5b734f57b9c Mon Sep 17 00:00:00 2001 From: Loic Poulain Date: Tue, 11 May 2021 16:42:23 +0200 Subject: usb: class: cdc-wdm: WWAN framework integration The WWAN framework provides a unified way to handle WWAN/modems and its control port(s). It has initially been introduced to support MHI/PCI modems, offering the same control protocols as the USB variants such as MBIM, QMI, AT... The WWAN framework exposes these control protocols as character devices, similarly to cdc-wdm, but in a bus agnostic fashion. This change adds registration of the USB modem cdc-wdm control endpoints to the WWAN framework as standard control ports (wwanXpY...). Exposing cdc-wdm through WWAN framework normally maintains backward compatibility, e.g: $ qmicli --device-open-qmi -d /dev/wwan0p1QMI --dms-get-ids instead of $ qmicli --device-open-qmi -d /dev/cdc-wdm0 --dms-get-ids However, some tools may rely on cdc-wdm driver/device name for device detection. It is then safer to keep the 'legacy' cdc-wdm character device to prevent any breakage. This is handled in this change by API mutual exclusion, only one access method can be used at a time, either cdc-wdm chardev or WWAN API. Note that unknown channel types (other than MBIM, AT or MBIM) are not registered to the WWAN framework. Signed-off-by: Loic Poulain Signed-off-by: David S. Miller --- include/linux/usb/cdc-wdm.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/cdc-wdm.h b/include/linux/usb/cdc-wdm.h index 9b895f93d8de..9f5a51f79ba5 100644 --- a/include/linux/usb/cdc-wdm.h +++ b/include/linux/usb/cdc-wdm.h @@ -12,11 +12,12 @@ #ifndef __LINUX_USB_CDC_WDM_H #define __LINUX_USB_CDC_WDM_H +#include #include extern struct usb_driver *usb_cdc_wdm_register(struct usb_interface *intf, struct usb_endpoint_descriptor *ep, - int bufsize, + int bufsize, enum wwan_port_type type, int (*manage_power)(struct usb_interface *, int)); #endif /* __LINUX_USB_CDC_WDM_H */ -- cgit v1.2.3 From c5895d3f06cbb80ccb311f1dcb37074651030cb6 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 4 May 2021 22:43:42 +0200 Subject: sched: Simplify sched_info_on() The situation around sched_info is somewhat complicated, it is used by sched_stats and delayacct and, indirectly, kvm. If SCHEDSTATS=Y (but disabled by default) sched_info_on() is unconditionally true -- this is the case for all distro kernel configs I checked. If for some reason SCHEDSTATS=N, but TASK_DELAY_ACCT=Y, then sched_info_on() can return false when delayacct is disabled, presumably because there would be no other users left; except kvm is. Instead of complicating matters further by accurately accounting sched_stat and kvm state, simply unconditionally enable when SCHED_INFO=Y, matching the common distro case. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Thomas Gleixner Reviewed-by: Ingo Molnar Acked-by: Johannes Weiner Link: https://lkml.kernel.org/r/20210505111525.121458839@infradead.org --- include/linux/sched/stat.h | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/stat.h b/include/linux/sched/stat.h index 568286411b43..939c3ec9e1b9 100644 --- a/include/linux/sched/stat.h +++ b/include/linux/sched/stat.h @@ -3,6 +3,7 @@ #define _LINUX_SCHED_STAT_H #include +#include /* * Various counters maintained by the scheduler and fork(), @@ -23,14 +24,7 @@ extern unsigned long nr_iowait_cpu(int cpu); static inline int sched_info_on(void) { -#ifdef CONFIG_SCHEDSTATS - return 1; -#elif defined(CONFIG_TASK_DELAY_ACCT) - extern int delayacct_on; - return delayacct_on; -#else - return 0; -#endif + return IS_ENABLED(CONFIG_SCHED_INFO); } #ifdef CONFIG_SCHEDSTATS -- cgit v1.2.3 From eee4d9fee2544389e5ce5697ed92db67c86d7a9f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 4 May 2021 22:43:36 +0200 Subject: delayacct: Add static_branch in scheduler hooks Cheaper when delayacct is disabled. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Thomas Gleixner Reviewed-by: Ingo Molnar Acked-by: Balbir Singh Acked-by: Johannes Weiner Link: https://lkml.kernel.org/r/20210505111525.248028369@infradead.org --- include/linux/delayacct.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 21651f946751..57fefa54b53a 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -58,8 +58,10 @@ struct task_delay_info { #include #include +#include #ifdef CONFIG_TASK_DELAY_ACCT +DECLARE_STATIC_KEY_TRUE(delayacct_key); extern int delayacct_on; /* Delay accounting turned on/off */ extern struct kmem_cache *delayacct_cache; extern void delayacct_init(void); @@ -114,6 +116,9 @@ static inline void delayacct_tsk_free(struct task_struct *tsk) static inline void delayacct_blkio_start(void) { + if (!static_branch_likely(&delayacct_key)) + return; + delayacct_set_flag(current, DELAYACCT_PF_BLKIO); if (current->delays) __delayacct_blkio_start(); @@ -121,6 +126,9 @@ static inline void delayacct_blkio_start(void) static inline void delayacct_blkio_end(struct task_struct *p) { + if (!static_branch_likely(&delayacct_key)) + return; + if (p->delays) __delayacct_blkio_end(p); delayacct_clear_flag(p, DELAYACCT_PF_BLKIO); -- cgit v1.2.3 From e4042ad492357fa995921376462b04a025dd53b6 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 4 May 2021 22:43:32 +0200 Subject: delayacct: Default disabled Assuming this stuff isn't actually used much; disable it by default and avoid allocating and tracking the task_delay_info structure. taskstats is changed to still report the regular sched and sched_info and only skip the missing task_delay_info fields instead of not reporting anything. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Thomas Gleixner Reviewed-by: Ingo Molnar Link: https://lkml.kernel.org/r/20210505111525.308018373@infradead.org --- include/linux/delayacct.h | 16 ++++------------ 1 file changed, 4 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 57fefa54b53a..225c8e01a111 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -61,7 +61,7 @@ struct task_delay_info { #include #ifdef CONFIG_TASK_DELAY_ACCT -DECLARE_STATIC_KEY_TRUE(delayacct_key); +DECLARE_STATIC_KEY_FALSE(delayacct_key); extern int delayacct_on; /* Delay accounting turned on/off */ extern struct kmem_cache *delayacct_cache; extern void delayacct_init(void); @@ -69,7 +69,7 @@ extern void __delayacct_tsk_init(struct task_struct *); extern void __delayacct_tsk_exit(struct task_struct *); extern void __delayacct_blkio_start(void); extern void __delayacct_blkio_end(struct task_struct *); -extern int __delayacct_add_tsk(struct taskstats *, struct task_struct *); +extern int delayacct_add_tsk(struct taskstats *, struct task_struct *); extern __u64 __delayacct_blkio_ticks(struct task_struct *); extern void __delayacct_freepages_start(void); extern void __delayacct_freepages_end(void); @@ -116,7 +116,7 @@ static inline void delayacct_tsk_free(struct task_struct *tsk) static inline void delayacct_blkio_start(void) { - if (!static_branch_likely(&delayacct_key)) + if (!static_branch_unlikely(&delayacct_key)) return; delayacct_set_flag(current, DELAYACCT_PF_BLKIO); @@ -126,7 +126,7 @@ static inline void delayacct_blkio_start(void) static inline void delayacct_blkio_end(struct task_struct *p) { - if (!static_branch_likely(&delayacct_key)) + if (!static_branch_unlikely(&delayacct_key)) return; if (p->delays) @@ -134,14 +134,6 @@ static inline void delayacct_blkio_end(struct task_struct *p) delayacct_clear_flag(p, DELAYACCT_PF_BLKIO); } -static inline int delayacct_add_tsk(struct taskstats *d, - struct task_struct *tsk) -{ - if (!delayacct_on || !tsk->delays) - return 0; - return __delayacct_add_tsk(d, tsk); -} - static inline __u64 delayacct_blkio_ticks(struct task_struct *tsk) { if (tsk->delays) -- cgit v1.2.3 From 0cd7c741f01de13dc1eecf22557593b3514639bb Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 10 May 2021 14:01:00 +0200 Subject: delayacct: Add sysctl to enable at runtime Just like sched_schedstats, allow runtime enabling (and disabling) of delayacct. This is useful if one forgot to add the delayacct boot time option. Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/YJkhebGJAywaZowX@hirez.programming.kicks-ass.net --- include/linux/delayacct.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 225c8e01a111..af7e6eb50283 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -65,6 +65,10 @@ DECLARE_STATIC_KEY_FALSE(delayacct_key); extern int delayacct_on; /* Delay accounting turned on/off */ extern struct kmem_cache *delayacct_cache; extern void delayacct_init(void); + +extern int sysctl_delayacct(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos); + extern void __delayacct_tsk_init(struct task_struct *); extern void __delayacct_tsk_exit(struct task_struct *); extern void __delayacct_blkio_start(void); -- cgit v1.2.3 From 8a311c740b53324ec584e0e3bb7077d56b123c28 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 17 Nov 2020 18:19:36 -0500 Subject: sched: Basic tracking of matching tasks Introduce task_struct::core_cookie as an opaque identifier for core scheduling. When enabled; core scheduling will only allow matching task to be on the core; where idle matches everything. When task_struct::core_cookie is set (and core scheduling is enabled) these tasks are indexed in a second RB-tree, first on cookie value then on scheduling function, such that matching task selection always finds the most elegible match. NOTE: *shudder* at the overhead... NOTE: *sigh*, a 3rd copy of the scheduling function; the alternative is per class tracking of cookies and that just duplicates a lot of stuff for no raisin (the 2nd copy lives in the rt-mutex PI code). [Joel: folded fixes] Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Joel Fernandes (Google) Signed-off-by: Peter Zijlstra (Intel) Tested-by: Don Hiatt Tested-by: Hongyu Ning Tested-by: Vincent Guittot Link: https://lkml.kernel.org/r/20210422123308.496975854@infradead.org --- include/linux/sched.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index d2c881384517..45eedccf86aa 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -700,10 +700,16 @@ struct task_struct { const struct sched_class *sched_class; struct sched_entity se; struct sched_rt_entity rt; + struct sched_dl_entity dl; + +#ifdef CONFIG_SCHED_CORE + struct rb_node core_node; + unsigned long core_cookie; +#endif + #ifdef CONFIG_CGROUP_SCHED struct task_group *sched_task_group; #endif - struct sched_dl_entity dl; #ifdef CONFIG_UCLAMP_TASK /* -- cgit v1.2.3 From d2dfa17bc7de67e99685c4d6557837bf801a102c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 17 Nov 2020 18:19:43 -0500 Subject: sched: Trivial forced-newidle balancer When a sibling is forced-idle to match the core-cookie; search for matching tasks to fill the core. rcu_read_unlock() can incur an infrequent deadlock in sched_core_balance(). Fix this by using the RCU-sched flavor instead. Signed-off-by: Peter Zijlstra (Intel) Tested-by: Don Hiatt Tested-by: Hongyu Ning Tested-by: Vincent Guittot Link: https://lkml.kernel.org/r/20210422123308.800048269@infradead.org --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 45eedccf86aa..9b822e383212 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -705,6 +705,7 @@ struct task_struct { #ifdef CONFIG_SCHED_CORE struct rb_node core_node; unsigned long core_cookie; + unsigned int core_occupation; #endif #ifdef CONFIG_CGROUP_SCHED -- cgit v1.2.3 From 6e33cad0af49336952e5541464bd02f5b5fd433e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 26 Mar 2021 18:55:06 +0100 Subject: sched: Trivial core scheduling cookie management In order to not have to use pid_struct, create a new, smaller, structure to manage task cookies for core scheduling. Signed-off-by: Peter Zijlstra (Intel) Tested-by: Don Hiatt Tested-by: Hongyu Ning Tested-by: Vincent Guittot Link: https://lkml.kernel.org/r/20210422123308.919768100@infradead.org --- include/linux/sched.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 9b822e383212..eab3f7c4251b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2179,4 +2179,10 @@ int sched_trace_rq_nr_running(struct rq *rq); const struct cpumask *sched_trace_rd_span(struct root_domain *rd); +#ifdef CONFIG_SCHED_CORE +extern void sched_core_free(struct task_struct *tsk); +#else +static inline void sched_core_free(struct task_struct *tsk) { } +#endif + #endif -- cgit v1.2.3 From 85dd3f61203c5cfa72b308ff327b5fbf3fc1ce5e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 29 Mar 2021 15:18:35 +0200 Subject: sched: Inherit task cookie on fork() Note that sched_core_fork() is called from under tasklist_lock, and not from sched_fork() earlier. This avoids a few races later. Signed-off-by: Peter Zijlstra (Intel) Tested-by: Don Hiatt Tested-by: Hongyu Ning Tested-by: Vincent Guittot Link: https://lkml.kernel.org/r/20210422123308.980003687@infradead.org --- 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 eab3f7c4251b..fba47e52e482 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2181,8 +2181,10 @@ const struct cpumask *sched_trace_rd_span(struct root_domain *rd); #ifdef CONFIG_SCHED_CORE extern void sched_core_free(struct task_struct *tsk); +extern void sched_core_fork(struct task_struct *p); #else static inline void sched_core_free(struct task_struct *tsk) { } +static inline void sched_core_fork(struct task_struct *p) { } #endif #endif -- cgit v1.2.3 From 7ac592aa35a684ff1858fb9ec282886b9e3575ac Mon Sep 17 00:00:00 2001 From: Chris Hyser Date: Wed, 24 Mar 2021 17:40:15 -0400 Subject: sched: prctl() core-scheduling interface This patch provides support for setting and copying core scheduling 'task cookies' between threads (PID), processes (TGID), and process groups (PGID). The value of core scheduling isn't that tasks don't share a core, 'nosmt' can do that. The value lies in exploiting all the sharing opportunities that exist to recover possible lost performance and that requires a degree of flexibility in the API. From a security perspective (and there are others), the thread, process and process group distinction is an existent hierarchal categorization of tasks that reflects many of the security concerns about 'data sharing'. For example, protecting against cache-snooping by a thread that can just read the memory directly isn't all that useful. With this in mind, subcommands to CREATE/SHARE (TO/FROM) provide a mechanism to create and share cookies. CREATE/SHARE_TO specify a target pid with enum pidtype used to specify the scope of the targeted tasks. For example, PIDTYPE_TGID will share the cookie with the process and all of it's threads as typically desired in a security scenario. API: prctl(PR_SCHED_CORE, PR_SCHED_CORE_GET, tgtpid, pidtype, &cookie) prctl(PR_SCHED_CORE, PR_SCHED_CORE_CREATE, tgtpid, pidtype, NULL) prctl(PR_SCHED_CORE, PR_SCHED_CORE_SHARE_TO, tgtpid, pidtype, NULL) prctl(PR_SCHED_CORE, PR_SCHED_CORE_SHARE_FROM, srcpid, pidtype, NULL) where 'tgtpid/srcpid == 0' implies the current process and pidtype is kernel enum pid_type {PIDTYPE_PID, PIDTYPE_TGID, PIDTYPE_PGID, ...}. For return values, EINVAL, ENOMEM are what they say. ESRCH means the tgtpid/srcpid was not found. EPERM indicates lack of PTRACE permission access to tgtpid/srcpid. ENODEV indicates your machines lacks SMT. [peterz: complete rewrite] Signed-off-by: Chris Hyser Signed-off-by: Peter Zijlstra (Intel) Tested-by: Don Hiatt Tested-by: Hongyu Ning Tested-by: Vincent Guittot Link: https://lkml.kernel.org/r/20210422123309.039845339@infradead.org --- 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 fba47e52e482..c7e7d50e2fdc 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2182,6 +2182,8 @@ const struct cpumask *sched_trace_rd_span(struct root_domain *rd); #ifdef CONFIG_SCHED_CORE extern void sched_core_free(struct task_struct *tsk); extern void sched_core_fork(struct task_struct *p); +extern int sched_core_share_pid(unsigned int cmd, pid_t pid, enum pid_type type, + unsigned long uaddr); #else static inline void sched_core_free(struct task_struct *tsk) { } static inline void sched_core_fork(struct task_struct *p) { } -- cgit v1.2.3 From fa5e5dc39669b4427830c546ede8709323b8276c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 6 May 2021 21:33:58 +0200 Subject: jump_label, x86: Introduce jump_entry_size() This allows architectures to have variable sized jumps. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210506194157.786777050@infradead.org --- include/linux/jump_label.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 05f5554d860f..8c45f58292ac 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -176,6 +176,15 @@ static inline void jump_entry_set_init(struct jump_entry *entry) entry->key |= 2; } +static inline int jump_entry_size(struct jump_entry *entry) +{ +#ifdef JUMP_LABEL_NOP_SIZE + return JUMP_LABEL_NOP_SIZE; +#else + return arch_jump_entry_size(entry); +#endif +} + #endif #endif -- cgit v1.2.3 From 5af0ea293d78c8b8f0b87ae2b13f7ac584057bc3 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 6 May 2021 21:34:00 +0200 Subject: jump_label: Free jump_entry::key bit1 for build use Have jump_label_init() set jump_entry::key bit1 to either 0 ot 1 unconditionally. This makes it available for build-time games. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210506194157.906893264@infradead.org --- include/linux/jump_label.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 8c45f58292ac..48b9b2a82767 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -171,9 +171,12 @@ static inline bool jump_entry_is_init(const struct jump_entry *entry) return (unsigned long)entry->key & 2UL; } -static inline void jump_entry_set_init(struct jump_entry *entry) +static inline void jump_entry_set_init(struct jump_entry *entry, bool set) { - entry->key |= 2; + if (set) + entry->key |= 2; + else + entry->key &= ~2; } static inline int jump_entry_size(struct jump_entry *entry) -- cgit v1.2.3 From cc00c1988801dc71f63bb7bad019e85046865095 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 12 May 2021 19:51:31 +0200 Subject: sched: Fix leftover comment typos A few more snuck in. Also capitalize 'CPU' while at it. Signed-off-by: Ingo Molnar --- include/linux/sched_clock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched_clock.h b/include/linux/sched_clock.h index 528718e4ed52..835ee87ed792 100644 --- a/include/linux/sched_clock.h +++ b/include/linux/sched_clock.h @@ -14,7 +14,7 @@ * @sched_clock_mask: Bitmask for two's complement subtraction of non 64bit * clocks. * @read_sched_clock: Current clock source (or dummy source when suspended). - * @mult: Multipler for scaled math conversion. + * @mult: Multiplier for scaled math conversion. * @shift: Shift value for scaled math conversion. * * Care must be taken when updating this structure; it is read by -- cgit v1.2.3 From 93d0955e6cf562d02aae37f5f8d98d9d9d16e0d4 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 12 May 2021 20:04:28 +0200 Subject: locking: Fix comment typos A few snuck through. Signed-off-by: Ingo Molnar --- include/linux/lockdep_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h index 2ec9ff5a7fff..3e726ace5c62 100644 --- a/include/linux/lockdep_types.h +++ b/include/linux/lockdep_types.h @@ -52,7 +52,7 @@ enum lockdep_lock_type { * NR_LOCKDEP_CACHING_CLASSES ... Number of classes * cached in the instance of lockdep_map * - * Currently main class (subclass == 0) and signle depth subclass + * Currently main class (subclass == 0) and single depth subclass * are cached in lockdep_map. This optimization is mainly targeting * on rq->lock. double_rq_lock() acquires this highly competitive with * single depth. -- cgit v1.2.3 From 01aee8fd7fb23049e2b52abadbe1f7b5e94a52d2 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 22 Apr 2021 23:02:25 +0300 Subject: sched: Make nr_running() return 32-bit value Creating 2**32 tasks is impossible due to futex pid limits and wasteful anyway. Nobody has done it. Bring nr_running() into 32-bit world to save on REX prefixes. Signed-off-by: Alexey Dobriyan Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210422200228.1423391-1-adobriyan@gmail.com --- include/linux/sched/stat.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched/stat.h b/include/linux/sched/stat.h index 939c3ec9e1b9..73606b3de394 100644 --- a/include/linux/sched/stat.h +++ b/include/linux/sched/stat.h @@ -17,7 +17,7 @@ extern unsigned long total_forks; extern int nr_threads; DECLARE_PER_CPU(unsigned long, process_counts); extern int nr_processes(void); -extern unsigned long nr_running(void); +extern unsigned int nr_running(void); extern bool single_task_running(void); extern unsigned long nr_iowait(void); extern unsigned long nr_iowait_cpu(int cpu); -- cgit v1.2.3 From 9745516841a55c77163a5d549bce1374d776df54 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 22 Apr 2021 23:02:26 +0300 Subject: sched: Make nr_iowait() return 32-bit value Creating 2**32 tasks to wait in D-state is impossible and wasteful. Return "unsigned int" and save on REX prefixes. Signed-off-by: Alexey Dobriyan Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210422200228.1423391-2-adobriyan@gmail.com --- include/linux/sched/stat.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched/stat.h b/include/linux/sched/stat.h index 73606b3de394..81d9b539e3b7 100644 --- a/include/linux/sched/stat.h +++ b/include/linux/sched/stat.h @@ -19,7 +19,7 @@ DECLARE_PER_CPU(unsigned long, process_counts); extern int nr_processes(void); extern unsigned int nr_running(void); extern bool single_task_running(void); -extern unsigned long nr_iowait(void); +extern unsigned int nr_iowait(void); extern unsigned long nr_iowait_cpu(int cpu); static inline int sched_info_on(void) -- cgit v1.2.3 From 8fc2858e572ce761bffcade81a42ac72005e76f9 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 22 Apr 2021 23:02:27 +0300 Subject: sched: Make nr_iowait_cpu() return 32-bit value Runqueue ->nr_iowait counters are 32-bit anyway. Propagate 32-bitness into other code, but don't try too hard. Signed-off-by: Alexey Dobriyan Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210422200228.1423391-3-adobriyan@gmail.com --- include/linux/sched/stat.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched/stat.h b/include/linux/sched/stat.h index 81d9b539e3b7..0108a38bb64d 100644 --- a/include/linux/sched/stat.h +++ b/include/linux/sched/stat.h @@ -20,7 +20,7 @@ extern int nr_processes(void); extern unsigned int nr_running(void); extern bool single_task_running(void); extern unsigned int nr_iowait(void); -extern unsigned long nr_iowait_cpu(int cpu); +extern unsigned int nr_iowait_cpu(int cpu); static inline int sched_info_on(void) { -- cgit v1.2.3 From f105dfec0a951cd0d5bfbfe9dc067ea69f71ad5c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 13 May 2021 01:29:15 +0200 Subject: tick/nohz: Evaluate the CPU expression after the static key When tick_nohz_full_cpu() is called with smp_processor_id(), the latter is unconditionally evaluated whether the static key is on or off. It is not necessary in the off-case though, so make sure the cpu expression is executed at the last moment. Illustrate with the following test function: int tick_nohz_test(void) { return tick_nohz_full_cpu(smp_processor_id()); } The resulting code before was: mov %gs:0x7eea92d1(%rip),%eax # smp_processor_id() fetch nopl 0x0(%rax,%rax,1) xor %eax,%eax retq cmpb $0x0,0x29d393a(%rip) # je tick_nohz_test+0x29 # jump to below eax clear mov %eax,%eax bt %rax,0x29d3936(%rip) # setb %al movzbl %al,%eax retq xor %eax,%eax retq Now it becomes: nopl 0x0(%rax,%rax,1) xor %eax,%eax retq cmpb $0x0,0x29d3871(%rip) # je tick_nohz_test+0x29 # jump to below eax clear mov %gs:0x7eea91f0(%rip),%eax # smp_processor_id() fetch, after static key mov %eax,%eax bt %rax,0x29d3866(%rip) # setb %al movzbl %al,%eax retq xor %eax,%eax retq Signed-off-by: Peter Zijlstra Signed-off-by: Frederic Weisbecker Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210512232924.150322-2-frederic@kernel.org --- include/linux/tick.h | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tick.h b/include/linux/tick.h index 7340613c7eff..2258984a0e8a 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -185,13 +185,17 @@ static inline bool tick_nohz_full_enabled(void) return tick_nohz_full_running; } -static inline bool tick_nohz_full_cpu(int cpu) -{ - if (!tick_nohz_full_enabled()) - return false; - - return cpumask_test_cpu(cpu, tick_nohz_full_mask); -} +/* + * Check if a CPU is part of the nohz_full subset. Arrange for evaluating + * the cpu expression (typically smp_processor_id()) _after_ the static + * key. + */ +#define tick_nohz_full_cpu(_cpu) ({ \ + bool __ret = false; \ + if (tick_nohz_full_enabled()) \ + __ret = cpumask_test_cpu((_cpu), tick_nohz_full_mask); \ + __ret; \ +}) static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) { -- cgit v1.2.3 From 1e4ca26d367ae71743e25068e5cd8750ef3f5f7d Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Thu, 13 May 2021 01:29:21 +0200 Subject: tick/nohz: Change signal tick dependency to wake up CPUs of member tasks Rather than waking up all nohz_full CPUs on the system, only wake up the target CPUs of member threads of the signal. Reduces interruptions to nohz_full CPUs. Signed-off-by: Marcelo Tosatti Signed-off-by: Frederic Weisbecker Signed-off-by: Ingo Molnar Acked-by: Peter Zijlstra Link: https://lore.kernel.org/r/20210512232924.150322-8-frederic@kernel.org --- include/linux/tick.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tick.h b/include/linux/tick.h index 2258984a0e8a..0bb80a7f05b9 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -211,7 +211,7 @@ extern void tick_nohz_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit); extern void tick_nohz_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit); -extern void tick_nohz_dep_set_signal(struct signal_struct *signal, +extern void tick_nohz_dep_set_signal(struct task_struct *tsk, enum tick_dep_bits bit); extern void tick_nohz_dep_clear_signal(struct signal_struct *signal, enum tick_dep_bits bit); @@ -256,11 +256,11 @@ static inline void tick_dep_clear_task(struct task_struct *tsk, if (tick_nohz_full_enabled()) tick_nohz_dep_clear_task(tsk, bit); } -static inline void tick_dep_set_signal(struct signal_struct *signal, +static inline void tick_dep_set_signal(struct task_struct *tsk, enum tick_dep_bits bit) { if (tick_nohz_full_enabled()) - tick_nohz_dep_set_signal(signal, bit); + tick_nohz_dep_set_signal(tsk, bit); } static inline void tick_dep_clear_signal(struct signal_struct *signal, enum tick_dep_bits bit) @@ -288,7 +288,7 @@ static inline void tick_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit) { } static inline void tick_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit) { } -static inline void tick_dep_set_signal(struct signal_struct *signal, +static inline void tick_dep_set_signal(struct task_struct *tsk, enum tick_dep_bits bit) { } static inline void tick_dep_clear_signal(struct signal_struct *signal, enum tick_dep_bits bit) { } -- cgit v1.2.3 From a1dfb6311c7739e21e160bc4c5575a1b21b48c87 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Thu, 13 May 2021 01:29:22 +0200 Subject: tick/nohz: Kick only _queued_ task whose tick dependency is updated When the tick dependency of a task is updated, we want it to aknowledge the new state and restart the tick if needed. If the task is not running, we don't need to kick it because it will observe the new dependency upon scheduling in. But if the task is running, we may need to send an IPI to it so that it gets notified. Unfortunately we don't have the means to check if a task is running in a race free way. Checking p->on_cpu in a synchronized way against p->tick_dep_mask would imply adding a full barrier between prepare_task_switch() and tick_nohz_task_switch(), which we want to avoid in this fast-path. Therefore we blindly fire an IPI to the task's CPU. Meanwhile we can check if the task is queued on the CPU rq because p->on_rq is always set to TASK_ON_RQ_QUEUED _before_ schedule() and its full barrier that precedes tick_nohz_task_switch(). And if the task is queued on a nohz_full CPU, it also has fair chances to be running as the isolation constraints prescribe running single tasks on full dynticks CPUs. So use this as a trick to check if we can spare an IPI toward a non-running task. NOTE: For the ordering to be correct, it is assumed that we never deactivate a task while it is running, the only exception being the task deactivating itself while scheduling out. Suggested-by: Peter Zijlstra Signed-off-by: Marcelo Tosatti Signed-off-by: Frederic Weisbecker Signed-off-by: Ingo Molnar Acked-by: Peter Zijlstra Link: https://lore.kernel.org/r/20210512232924.150322-9-frederic@kernel.org --- 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 d2c881384517..3341ae2e8231 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2011,6 +2011,8 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu) #endif /* CONFIG_SMP */ +extern bool sched_task_on_rq(struct task_struct *p); + /* * In order to reduce various lock holder preemption latencies provide an * interface to see if a vCPU is currently running or not. -- cgit v1.2.3 From cbbc07e1e892c373f30f4ba08fedecd49afca247 Mon Sep 17 00:00:00 2001 From: Peter Chen Date: Sat, 8 May 2021 13:33:57 +0800 Subject: usb: host: move EH SINGLE_STEP_SET_FEATURE implementation to core It is needed at USB Certification test for Embedded Host 2.0, and the detail is at CH6.4.1.1 of On-The-Go and Embedded Host Supplement to the USB Revision 2.0 Specification. Since other USB 2.0 capable host like XHCI also need it, so move it to HCD core. Acked-by: Alan Stern Signed-off-by: Peter Chen Signed-off-by: Li Jun Link: https://lore.kernel.org/r/1620452039-11694-1-git-send-email-jun.li@nxp.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/hcd.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 96281cd50ff6..22c5d1c0acf3 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -409,7 +409,10 @@ struct hc_driver { int (*find_raw_port_number)(struct usb_hcd *, int); /* Call for power on/off the port if necessary */ int (*port_power)(struct usb_hcd *hcd, int portnum, bool enable); - + /* Call for SINGLE_STEP_SET_FEATURE Test for USB2 EH certification */ +#define EHSET_TEST_SINGLE_STEP_SET_FEATURE 0x06 + int (*submit_single_step_set_feature)(struct usb_hcd *, + struct urb *, int); }; static inline int hcd_giveback_urb_in_bh(struct usb_hcd *hcd) @@ -474,6 +477,14 @@ int usb_hcd_setup_local_mem(struct usb_hcd *hcd, phys_addr_t phys_addr, struct platform_device; extern void usb_hcd_platform_shutdown(struct platform_device *dev); +#ifdef CONFIG_USB_HCD_TEST_MODE +extern int ehset_single_step_set_feature(struct usb_hcd *hcd, int port); +#else +static inline int ehset_single_step_set_feature(struct usb_hcd *hcd, int port) +{ + return 0; +} +#endif /* CONFIG_USB_HCD_TEST_MODE */ #ifdef CONFIG_USB_PCI struct pci_dev; -- cgit v1.2.3 From 0733d83905326baef3c25d8bd9a96fdc9eb71b86 Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Sun, 25 Apr 2021 10:00:24 +0800 Subject: firmware: replace HOTPLUG with UEVENT in FW_ACTION defines With commit 312c004d36ce ("[PATCH] driver core: replace "hotplug" by "uevent"") already in the tree over a decade, update the name of FW_ACTION defines to follow semantics, and reflect what the defines are really meant for, i.e. whether or not generate user space event. Acked-by: Lee Jones Signed-off-by: Shawn Guo Link: https://lore.kernel.org/r/20210425020024.28057-1-shawn.guo@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firmware.h b/include/linux/firmware.h index 84e346ae766e..25109192cebe 100644 --- a/include/linux/firmware.h +++ b/include/linux/firmware.h @@ -6,8 +6,8 @@ #include #include -#define FW_ACTION_NOHOTPLUG 0 -#define FW_ACTION_HOTPLUG 1 +#define FW_ACTION_NOUEVENT 0 +#define FW_ACTION_UEVENT 1 struct firmware { size_t size; -- cgit v1.2.3 From ed5aecd3da2eabd8a6c9f5593df2c4f00985fca2 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 5 May 2021 11:18:54 +0200 Subject: tty: remove broken r3964 line discipline Noone stepped up in the past two years since it was marked as BROKEN by commit c7084edc3f6d (tty: mark Siemens R3964 line discipline as BROKEN). Remove the line discipline for good. Three remarks: * we remove also the uapi header (as noone is able to use that interface anyway) * we do *not* remove the N_R3964 constant definition from tty.h, so it remains reserved. * in_interrupt() check is now removed from vt's con_put_char. Noone else calls tty_operations::put_char from interrupt context. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210505091928.22010-2-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/n_r3964.h | 175 ------------------------------------------------ 1 file changed, 175 deletions(-) delete mode 100644 include/linux/n_r3964.h (limited to 'include/linux') diff --git a/include/linux/n_r3964.h b/include/linux/n_r3964.h deleted file mode 100644 index 90a803aa42e8..000000000000 --- a/include/linux/n_r3964.h +++ /dev/null @@ -1,175 +0,0 @@ -/* r3964 linediscipline for linux - * - * ----------------------------------------------------------- - * Copyright by - * Philips Automation Projects - * Kassel (Germany) - * ----------------------------------------------------------- - * This software may be used and distributed according to the terms of - * the GNU General Public License, incorporated herein by reference. - * - * Author: - * L. Haag - * - * $Log: r3964.h,v $ - * Revision 1.4 2005/12/21 19:54:24 Kurt Huwig - * Fixed HZ usage on 2.6 kernels - * Removed unnecessary include - * - * Revision 1.3 2001/03/18 13:02:24 dwmw2 - * Fix timer usage, use spinlocks properly. - * - * Revision 1.2 2001/03/18 12:53:15 dwmw2 - * Merge changes in 2.4.2 - * - * Revision 1.1.1.1 1998/10/13 16:43:14 dwmw2 - * This'll screw the version control - * - * Revision 1.6 1998/09/30 00:40:38 dwmw2 - * Updated to use kernel's N_R3964 if available - * - * Revision 1.4 1998/04/02 20:29:44 lhaag - * select, blocking, ... - * - * Revision 1.3 1998/02/12 18:58:43 root - * fixed some memory leaks - * calculation of checksum characters - * - * Revision 1.2 1998/02/07 13:03:17 root - * ioctl read_telegram - * - * Revision 1.1 1998/02/06 19:19:43 root - * Initial revision - * - * - */ -#ifndef __LINUX_N_R3964_H__ -#define __LINUX_N_R3964_H__ - - -#include -#include - -/* - * Common ascii handshake characters: - */ - -#define STX 0x02 -#define ETX 0x03 -#define DLE 0x10 -#define NAK 0x15 - -/* - * Timeouts (from milliseconds to jiffies) - */ - -#define R3964_TO_QVZ ((550)*HZ/1000) -#define R3964_TO_ZVZ ((220)*HZ/1000) -#define R3964_TO_NO_BUF ((400)*HZ/1000) -#define R3964_NO_TX_ROOM ((100)*HZ/1000) -#define R3964_TO_RX_PANIC ((4000)*HZ/1000) -#define R3964_MAX_RETRIES 5 - - -enum { R3964_IDLE, - R3964_TX_REQUEST, R3964_TRANSMITTING, - R3964_WAIT_ZVZ_BEFORE_TX_RETRY, R3964_WAIT_FOR_TX_ACK, - R3964_WAIT_FOR_RX_BUF, - R3964_RECEIVING, R3964_WAIT_FOR_BCC, R3964_WAIT_FOR_RX_REPEAT - }; - -/* - * All open file-handles are 'clients' and are stored in a linked list: - */ - -struct r3964_message; - -struct r3964_client_info { - spinlock_t lock; - struct pid *pid; - unsigned int sig_flags; - - struct r3964_client_info *next; - - struct r3964_message *first_msg; - struct r3964_message *last_msg; - struct r3964_block_header *next_block_to_read; - int msg_count; -}; - - - -struct r3964_block_header; - -/* internal version of client_message: */ -struct r3964_message { - int msg_id; - int arg; - int error_code; - struct r3964_block_header *block; - struct r3964_message *next; -}; - -/* - * Header of received block in rx_buf/tx_buf: - */ - -struct r3964_block_header -{ - unsigned int length; /* length in chars without header */ - unsigned char *data; /* usually data is located - immediately behind this struct */ - unsigned int locks; /* only used in rx_buffer */ - - struct r3964_block_header *next; - struct r3964_client_info *owner; /* =NULL in rx_buffer */ -}; - -/* - * If rx_buf hasn't enough space to store R3964_MTU chars, - * we will reject all incoming STX-requests by sending NAK. - */ - -#define RX_BUF_SIZE 4000 -#define TX_BUF_SIZE 4000 -#define R3964_MAX_BLOCKS_IN_RX_QUEUE 100 - -#define R3964_PARITY 0x0001 -#define R3964_FRAME 0x0002 -#define R3964_OVERRUN 0x0004 -#define R3964_UNKNOWN 0x0008 -#define R3964_BREAK 0x0010 -#define R3964_CHECKSUM 0x0020 -#define R3964_ERROR 0x003f -#define R3964_BCC 0x4000 -#define R3964_DEBUG 0x8000 - - -struct r3964_info { - spinlock_t lock; - struct tty_struct *tty; - unsigned char priority; - unsigned char *rx_buf; /* ring buffer */ - unsigned char *tx_buf; - - struct r3964_block_header *rx_first; - struct r3964_block_header *rx_last; - struct r3964_block_header *tx_first; - struct r3964_block_header *tx_last; - unsigned int tx_position; - unsigned int rx_position; - unsigned char last_rx; - unsigned char bcc; - unsigned int blocks_in_rx_queue; - - struct mutex read_lock; /* serialize r3964_read */ - - struct r3964_client_info *firstClient; - unsigned int state; - unsigned int flags; - - struct timer_list tmr; - int nRetry; -}; - -#endif -- cgit v1.2.3 From 0f3dcf3b5d76669123bf99fec812b8b0acd60375 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 5 May 2021 11:19:04 +0200 Subject: tty: make fp of tty_ldisc_ops::receive_buf{,2} const Char pointer (cp) passed to tty_ldisc_ops::receive_buf{,2} is const. There is no reason for flag pointer (fp) not to be too. So switch it in the definition and all uses. Signed-off-by: Jiri Slaby Cc: William Hubbs Cc: Chris Brannon Cc: Kirk Reiser Cc: Samuel Thibault Cc: Marcel Holtmann Cc: Johan Hedberg Cc: Luiz Augusto von Dentz Cc: Dmitry Torokhov Cc: Arnd Bergmann Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Wolfgang Grandegger Cc: Marc Kleine-Budde Cc: Andreas Koensgen Cc: Paul Mackerras Cc: Liam Girdwood Cc: Mark Brown Cc: Jaroslav Kysela Cc: Takashi Iwai Cc: Peter Ujfalusi Link: https://lore.kernel.org/r/20210505091928.22010-12-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 2 +- include/linux/tty_ldisc.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index e5d6b1f28823..5aad2220266c 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -628,7 +628,7 @@ extern int tty_register_ldisc(int disc, struct tty_ldisc_ops *new_ldisc); extern int tty_unregister_ldisc(int disc); extern int tty_set_ldisc(struct tty_struct *tty, int disc); extern int tty_ldisc_receive_buf(struct tty_ldisc *ld, const unsigned char *p, - char *f, int count); + const char *f, int count); /* n_tty.c */ extern void n_tty_inherit_ops(struct tty_ldisc_ops *ops); diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index 31284b55bd4f..c20ca6a75b4c 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -201,11 +201,11 @@ struct tty_ldisc_ops { * The following routines are called from below. */ void (*receive_buf)(struct tty_struct *, const unsigned char *cp, - char *fp, int count); + const char *fp, int count); void (*write_wakeup)(struct tty_struct *); void (*dcd_change)(struct tty_struct *, unsigned int); int (*receive_buf2)(struct tty_struct *, const unsigned char *cp, - char *fp, int count); + const char *fp, int count); struct module *owner; -- cgit v1.2.3 From 6e94dbc7a4e49a028b81302d755bba1a518f973b Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 5 May 2021 11:19:05 +0200 Subject: tty: cumulate and document tty_struct::flow* members Group the flow flags under a single struct called flow. The new struct contains 'stopped' and 'tco_stopped' bools which used to be bits in a bitfield. The struct also contains the lock protecting them to potentially share the same cache line. Note that commit c545b66c6922b (tty: Serialize tcflow() with other tty flow control changes) added a padding to the original bitfield. It was for the bitfield to occupy a whole 64b word to avoid interferring stores on Alpha (cannot we evaporate this arch with weird implications to C code yet?). But it doesn't work as expected as the padding (tty_struct::unused) is aligned to a 8B boundary too and occupies some bytes from the next word. So make it reliable by: 1) setting __aligned of the struct -- that aligns the start, and 2) making 'unsigned long unused[0]' as the last member of the struct -- pads the end. This is also the perfect time to start the documentation of tty_struct where all this lives. So we start by documenting what these bools actually serve for. And why we do all the alignment dances. Only the few up-to-date information from the Theodore's comment made it into this new Kerneldoc comment. Signed-off-by: Jiri Slaby Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Jonathan Corbet Cc: Arnd Bergmann Cc: Ulf Hansson Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Christian Borntraeger Cc: Shawn Guo Cc: Sascha Hauer Cc: Vineet Gupta Cc: "Maciej W. Rozycki" Link: https://lore.kernel.org/r/20210505091928.22010-13-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 2 +- include/linux/tty.h | 38 ++++++++++++++++++++++---------------- include/linux/tty_driver.h | 4 ++-- 3 files changed, 25 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index d7ed00f1594e..7445c8fd88c0 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -428,7 +428,7 @@ int uart_resume_port(struct uart_driver *reg, struct uart_port *port); static inline int uart_tx_stopped(struct uart_port *port) { struct tty_struct *tty = port->state->port.tty; - if ((tty && tty->stopped) || port->hw_stopped) + if ((tty && tty->flow.stopped) || port->hw_stopped) return 1; return 0; } diff --git a/include/linux/tty.h b/include/linux/tty.h index 5aad2220266c..df3a69b2e1ea 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -243,20 +243,22 @@ struct tty_port { #define TTY_PORT_KOPENED 5 /* device exclusively opened by kernel */ -/* - * Where all of the state associated with a tty is kept while the tty - * is open. Since the termios state should be kept even if the tty - * has been closed --- for things like the baud rate, etc --- it is - * not stored here, but rather a pointer to the real state is stored - * here. Possible the winsize structure should have the same - * treatment, but (1) the default 80x24 is usually right and (2) it's - * most often used by a windowing system, which will set the correct - * size each time the window is created or resized anyway. - * - TYT, 9/14/92 - */ - struct tty_operations; +/** + * struct tty_struct - state associated with a tty while open + * + * @flow.lock: lock for flow members + * @flow.stopped: tty stopped/started by tty_stop/tty_start + * @flow.tco_stopped: tty stopped/started by TCOOFF/TCOON ioctls (it has + * precedense over @flow.stopped) + * @flow.unused: alignment for Alpha, so that no members other than @flow.* are + * modified by the same 64b word store. The @flow's __aligned is + * there for the very same reason. + * + * All of the state associated with a tty while the tty is open. Persistent + * storage for tty devices is referenced here as @port in struct tty_port. + */ struct tty_struct { int magic; struct kref kref; @@ -275,7 +277,6 @@ struct tty_struct { struct rw_semaphore termios_rwsem; struct mutex winsize_mutex; spinlock_t ctrl_lock; - spinlock_t flow_lock; /* Termios values are protected by the termios rwsem */ struct ktermios termios, termios_locked; char name[64]; @@ -288,9 +289,14 @@ struct tty_struct { unsigned long flags; int count; struct winsize winsize; /* winsize_mutex */ - unsigned long stopped:1, /* flow_lock */ - flow_stopped:1, - unused:BITS_PER_LONG - 2; + + struct { + spinlock_t lock; + bool stopped; + bool tco_stopped; + unsigned long unused[0]; + } __aligned(sizeof(unsigned long)) flow; + int hw_stopped; unsigned long ctrl_status:8, /* ctrl_lock */ packet:1, diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index 2f719b471d52..653fa5af3a22 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -153,7 +153,7 @@ * This routine notifies the tty driver that it should stop * outputting characters to the tty device. * - * Called with ->flow_lock held. Serialized with start() method. + * Called with ->flow.lock held. Serialized with start() method. * * Optional: * @@ -164,7 +164,7 @@ * This routine notifies the tty driver that it resume sending * characters to the tty device. * - * Called with ->flow_lock held. Serialized with stop() method. + * Called with ->flow.lock held. Serialized with stop() method. * * Optional: * -- cgit v1.2.3 From 64d608db38ffc0c7a25455387096e0aad9410397 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 5 May 2021 11:19:06 +0200 Subject: tty: cumulate and document tty_struct::ctrl* members Group the ctrl members under a single struct called ctrl. The new struct contains 'pgrp', 'session', 'pktstatus', and 'packet'. 'pktstatus' and 'packet' used to be bits in a bitfield. The struct also contains the lock protecting them to share the same cache line. Note that commit c545b66c6922b (tty: Serialize tcflow() with other tty flow control changes) added a padding to the original bitfield. It was for the bitfield to occupy a whole 64b word to avoid interferring stores on Alpha (cannot we evaporate this arch with weird implications to C code yet?). But it doesn't work as expected as the padding (tty_struct::ctrl_unused) is aligned to a 8B boundary too and occupies some bytes from the next word. So make it reliable by: 1) setting __aligned of the struct -- that aligns the start, and 2) making 'unsigned long unused[0]' as the last member of the struct -- pads the end. Add a kerneldoc comment for this grouped members. Signed-off-by: Jiri Slaby Cc: "David S. Miller" Cc: Jakub Kicinski Cc: netdev@vger.kernel.org Link: https://lore.kernel.org/r/20210505091928.22010-14-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index df3a69b2e1ea..283ac5f29052 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -255,6 +255,13 @@ struct tty_operations; * @flow.unused: alignment for Alpha, so that no members other than @flow.* are * modified by the same 64b word store. The @flow's __aligned is * there for the very same reason. + * @ctrl.lock: lock for ctrl members + * @ctrl.pgrp: process group of this tty (setpgrp(2)) + * @ctrl.session: session of this tty (setsid(2)). Writes are protected by both + * @ctrl.lock and legacy mutex, readers must use at least one of + * them. + * @ctrl.pktstatus: packet mode status (bitwise OR of TIOCPKT_* constants) + * @ctrl.packet: packet mode enabled * * All of the state associated with a tty while the tty is open. Persistent * storage for tty devices is referenced here as @port in struct tty_port. @@ -276,16 +283,9 @@ struct tty_struct { struct mutex throttle_mutex; struct rw_semaphore termios_rwsem; struct mutex winsize_mutex; - spinlock_t ctrl_lock; /* Termios values are protected by the termios rwsem */ struct ktermios termios, termios_locked; char name[64]; - struct pid *pgrp; /* Protected by ctrl lock */ - /* - * Writes protected by both ctrl lock and legacy mutex, readers must use - * at least one of them. - */ - struct pid *session; unsigned long flags; int count; struct winsize winsize; /* winsize_mutex */ @@ -297,10 +297,16 @@ struct tty_struct { unsigned long unused[0]; } __aligned(sizeof(unsigned long)) flow; + struct { + spinlock_t lock; + struct pid *pgrp; + struct pid *session; + unsigned char pktstatus; + bool packet; + unsigned long unused[0]; + } __aligned(sizeof(unsigned long)) ctrl; + int hw_stopped; - unsigned long ctrl_status:8, /* ctrl_lock */ - packet:1, - unused_ctrl:BITS_PER_LONG - 9; unsigned int receive_room; /* Bytes free for queue */ int flow_change; -- cgit v1.2.3 From fbadf70a8053b3dce78a45997ae55651693a2a81 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 5 May 2021 11:19:07 +0200 Subject: tty: set tty_ldisc_ops::num statically There is no reason to pass the ldisc number to tty_register_ldisc separately. Just set it in the already defined tty_ldisc_ops in all the ldiscs. This simplifies tty_register_ldisc a bit too (no need to set the num member there). Signed-off-by: Jiri Slaby Cc: William Hubbs Cc: Chris Brannon Cc: Kirk Reiser Cc: Samuel Thibault Cc: Marcel Holtmann Cc: Johan Hedberg Cc: Luiz Augusto von Dentz Cc: Dmitry Torokhov Cc: Arnd Bergmann Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Wolfgang Grandegger Cc: Marc Kleine-Budde Cc: Andreas Koensgen Cc: Paul Mackerras Cc: Rodolfo Giometti Cc: Peter Ujfalusi Cc: Liam Girdwood Cc: Mark Brown Cc: Jaroslav Kysela Cc: Takashi Iwai Link: https://lore.kernel.org/r/20210505091928.22010-15-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 283ac5f29052..95c632299fb4 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -636,7 +636,7 @@ static inline int tty_port_users(struct tty_port *port) return port->count + port->blocked_open; } -extern int tty_register_ldisc(int disc, struct tty_ldisc_ops *new_ldisc); +extern int tty_register_ldisc(struct tty_ldisc_ops *new_ldisc); extern int tty_unregister_ldisc(int disc); extern int tty_set_ldisc(struct tty_struct *tty, int disc); extern int tty_ldisc_receive_buf(struct tty_ldisc *ld, const unsigned char *p, -- cgit v1.2.3 From f81ee8b8b8421dc06d13f197bb53191559cc51da Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 5 May 2021 11:19:09 +0200 Subject: tty: make tty_ldisc_ops a param in tty_unregister_ldisc Make tty_unregister_ldisc symmetric to tty_register_ldisc by accepting struct tty_ldisc_ops as a parameter instead of ldisc number. This avoids checking of the ldisc number bounds in tty_unregister_ldisc. Signed-off-by: Jiri Slaby Cc: William Hubbs Cc: Chris Brannon Cc: Kirk Reiser Cc: Samuel Thibault Cc: Marcel Holtmann Cc: Johan Hedberg Cc: Luiz Augusto von Dentz Cc: Dmitry Torokhov Cc: Arnd Bergmann Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Wolfgang Grandegger Cc: Marc Kleine-Budde Cc: Andreas Koensgen Cc: Paul Mackerras Cc: Rodolfo Giometti Cc: Peter Ujfalusi Cc: Liam Girdwood Cc: Mark Brown Cc: Jaroslav Kysela Cc: Takashi Iwai Link: https://lore.kernel.org/r/20210505091928.22010-17-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 95c632299fb4..6a72d0ff6391 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -637,7 +637,7 @@ static inline int tty_port_users(struct tty_port *port) } extern int tty_register_ldisc(struct tty_ldisc_ops *new_ldisc); -extern int tty_unregister_ldisc(int disc); +extern int tty_unregister_ldisc(struct tty_ldisc_ops *ldisc); extern int tty_set_ldisc(struct tty_struct *tty, int disc); extern int tty_ldisc_receive_buf(struct tty_ldisc *ld, const unsigned char *p, const char *f, int count); -- cgit v1.2.3 From 19475209331168cdb8070a011650535f1c54a730 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 5 May 2021 11:19:10 +0200 Subject: tty: drop tty_ldisc_ops::refcount The refcount is checked only in tty_unregister_ldisc and EBUSY returned if it is nonzero. But none of the tty_unregister_ldisc callers act anyhow if this (or any other) error is returned. So remove tty_ldisc_ops::refcount completely and make tty_unregister_ldisc return 'void' in the next patches. That means we assume tty_unregister_ldisc is not called while the ldisc might be in use. That relies on try_module_get in get_ldops and module_put in put_ldops. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210505091928.22010-18-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/tty_ldisc.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index c20ca6a75b4c..fbe9de278629 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -208,8 +208,6 @@ struct tty_ldisc_ops { const char *fp, int count); struct module *owner; - - int refcount; }; struct tty_ldisc { -- cgit v1.2.3 From f6f19595a7efdaa0c196d7fa2b343b5588f94470 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 5 May 2021 11:19:12 +0200 Subject: tty: return void from tty_unregister_ldisc Now that noone checks the return value of tty_unregister_ldisc, make the function return 'void'. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210505091928.22010-20-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 6a72d0ff6391..e18a4f1ac39d 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -637,7 +637,7 @@ static inline int tty_port_users(struct tty_port *port) } extern int tty_register_ldisc(struct tty_ldisc_ops *new_ldisc); -extern int tty_unregister_ldisc(struct tty_ldisc_ops *ldisc); +extern void tty_unregister_ldisc(struct tty_ldisc_ops *ldisc); extern int tty_set_ldisc(struct tty_struct *tty, int disc); extern int tty_ldisc_receive_buf(struct tty_ldisc *ld, const unsigned char *p, const char *f, int count); -- cgit v1.2.3 From 03b3b1a2405ccd71570cd5ec1fe4abd7bb4891cb Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 5 May 2021 11:19:15 +0200 Subject: tty: make tty_operations::write_room return uint Line disciplines expect a positive value or zero returned from tty->ops->write_room (invoked by tty_write_room). So make this assumption explicit by using unsigned int as a return value. Both of tty->ops->write_room and tty_write_room. Signed-off-by: Jiri Slaby Acked-by: Laurentiu Tudor Acked-by: Alex Elder Acked-by: Max Filippov # xtensa Acked-by: David Sterba Acked-By: Anton Ivanov Acked-by: Geert Uytterhoeven Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: Matt Turner Cc: "James E.J. Bottomley" Cc: Helge Deller Cc: Jeff Dike Cc: Richard Weinberger Cc: Chris Zankel Cc: Arnd Bergmann Cc: Samuel Iglesias Gonsalvez Cc: Jens Taprogge Cc: Karsten Keil Cc: Scott Branden Cc: Ulf Hansson Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Christian Borntraeger Cc: David Lin Cc: Johan Hovold Cc: Jiri Kosina Cc: Shawn Guo Cc: Sascha Hauer Cc: Oliver Neukum Cc: Felipe Balbi Cc: Mathias Nyman Cc: Marcel Holtmann Cc: Johan Hedberg Cc: Luiz Augusto von Dentz Link: https://lore.kernel.org/r/20210505091928.22010-23-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 2 +- include/linux/tty_driver.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index e18a4f1ac39d..d18fc34d3054 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -459,7 +459,7 @@ extern void tty_write_message(struct tty_struct *tty, char *msg); extern int tty_send_xchar(struct tty_struct *tty, char ch); extern int tty_put_char(struct tty_struct *tty, unsigned char c); extern int tty_chars_in_buffer(struct tty_struct *tty); -extern int tty_write_room(struct tty_struct *tty); +extern unsigned int tty_write_room(struct tty_struct *tty); extern void tty_driver_flush_buffer(struct tty_struct *tty); extern void tty_throttle(struct tty_struct *tty); extern void tty_unthrottle(struct tty_struct *tty); diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index 653fa5af3a22..ea5b15c72764 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -89,7 +89,7 @@ * * Note: Do not call this function directly, call tty_driver_flush_chars * - * int (*write_room)(struct tty_struct *tty); + * unsigned int (*write_room)(struct tty_struct *tty); * * This routine returns the numbers of characters the tty driver * will accept for queuing to be written. This number is subject @@ -256,7 +256,7 @@ struct tty_operations { const unsigned char *buf, int count); int (*put_char)(struct tty_struct *tty, unsigned char ch); void (*flush_chars)(struct tty_struct *tty); - int (*write_room)(struct tty_struct *tty); + unsigned int (*write_room)(struct tty_struct *tty); int (*chars_in_buffer)(struct tty_struct *tty); int (*ioctl)(struct tty_struct *tty, unsigned int cmd, unsigned long arg); -- cgit v1.2.3 From 76c8eaafe4f061f3790112842a2fbb297e4bea88 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 21 Apr 2021 14:30:54 -0700 Subject: rcu: Create an unrcu_pointer() to remove __rcu from a pointer MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The xchg() and cmpxchg() functions are sometimes used to carry out RCU updates. Unfortunately, this can result in sparse warnings for both the old-value and new-value arguments, as well as for the return value. The arguments can be dealt with using RCU_INITIALIZER(): old_p = xchg(&p, RCU_INITIALIZER(new_p)); But a sparse warning still remains due to assigning the __rcu pointer returned from xchg to the (most likely) non-__rcu pointer old_p. This commit therefore provides an unrcu_pointer() macro that strips the __rcu. This macro can be used as follows: old_p = unrcu_pointer(xchg(&p, RCU_INITIALIZER(new_p))); Reported-by: Toke Høiland-Jørgensen Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 1199ffd305d1..b071d02a028a 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -363,6 +363,20 @@ static inline void rcu_preempt_sleep_check(void) { } #define rcu_check_sparse(p, space) #endif /* #else #ifdef __CHECKER__ */ +/** + * unrcu_pointer - mark a pointer as not being RCU protected + * @p: pointer needing to lose its __rcu property + * + * Converts @p from an __rcu pointer to a __kernel pointer. + * This allows an __rcu pointer to be used with xchg() and friends. + */ +#define unrcu_pointer(p) \ +({ \ + typeof(*p) *_________p1 = (typeof(*p) *__force)(p); \ + rcu_check_sparse(p, __rcu); \ + ((typeof(*p) __force __kernel *)(_________p1)); \ +}) + #define __rcu_access_pointer(p, space) \ ({ \ typeof(*p) *_________p1 = (typeof(*p) *__force)READ_ONCE(p); \ -- cgit v1.2.3 From 1893afd63409111c6edcee9d6e1196fc06cf4fd7 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 29 Apr 2021 11:18:01 -0700 Subject: rcu: Improve comments describing RCU read-side critical sections There are a number of places that call out the fact that preempt-disable regions of code now act as RCU read-side critical sections, where preempt-disable regions of code include irq-disable regions of code, bh-disable regions of code, hardirq handlers, and NMI handlers. However, someone relying solely on (for example) the call_rcu() header comment might well have no idea that preempt-disable regions of code have RCU semantics. This commit therefore updates the header comments for call_rcu(), synchronize_rcu(), rcu_dereference_bh_check(), and rcu_dereference_sched_check() to call out these new(ish) forms of RCU readers. Reported-by: Michel Lespinasse [ paulmck: Apply Matthew Wilcox and Michel Lespinasse feedback. ] Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 35 ++++++++++++++++++++++++++++------- 1 file changed, 28 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index b071d02a028a..f0eecb9e49c8 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -532,7 +532,12 @@ do { \ * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * - * This is the RCU-bh counterpart to rcu_dereference_check(). + * This is the RCU-bh counterpart to rcu_dereference_check(). However, + * please note that starting in v5.0 kernels, vanilla RCU grace periods + * wait for local_bh_disable() regions of code in addition to regions of + * code demarked by rcu_read_lock() and rcu_read_unlock(). This means + * that synchronize_rcu(), call_rcu, and friends all take not only + * rcu_read_lock() but also rcu_read_lock_bh() into account. */ #define rcu_dereference_bh_check(p, c) \ __rcu_dereference_check((p), (c) || rcu_read_lock_bh_held(), __rcu) @@ -543,6 +548,11 @@ do { \ * @c: The conditions under which the dereference will take place * * This is the RCU-sched counterpart to rcu_dereference_check(). + * However, please note that starting in v5.0 kernels, vanilla RCU grace + * periods wait for preempt_disable() regions of code in addition to + * regions of code demarked by rcu_read_lock() and rcu_read_unlock(). + * This means that synchronize_rcu(), call_rcu, and friends all take not + * only rcu_read_lock() but also rcu_read_lock_sched() into account. */ #define rcu_dereference_sched_check(p, c) \ __rcu_dereference_check((p), (c) || rcu_read_lock_sched_held(), \ @@ -634,6 +644,12 @@ do { \ * sections, invocation of the corresponding RCU callback is deferred * until after the all the other CPUs exit their critical sections. * + * In v5.0 and later kernels, synchronize_rcu() and call_rcu() also + * wait for regions of code with preemption disabled, including regions of + * code with interrupts or softirqs disabled. In pre-v5.0 kernels, which + * define synchronize_sched(), only code enclosed within rcu_read_lock() + * and rcu_read_unlock() are guaranteed to be waited for. + * * Note, however, that RCU callbacks are permitted to run concurrently * with new RCU read-side critical sections. One way that this can happen * is via the following sequence of events: (1) CPU 0 enters an RCU @@ -728,9 +744,11 @@ static inline void rcu_read_unlock(void) /** * rcu_read_lock_bh() - mark the beginning of an RCU-bh critical section * - * This is equivalent of rcu_read_lock(), but also disables softirqs. - * Note that anything else that disables softirqs can also serve as - * an RCU read-side critical section. + * This is equivalent to rcu_read_lock(), but also disables softirqs. + * Note that anything else that disables softirqs can also serve as an RCU + * read-side critical section. However, please note that this equivalence + * applies only to v5.0 and later. Before v5.0, rcu_read_lock() and + * rcu_read_lock_bh() were unrelated. * * Note that rcu_read_lock_bh() and the matching rcu_read_unlock_bh() * must occur in the same context, for example, it is illegal to invoke @@ -763,9 +781,12 @@ static inline void rcu_read_unlock_bh(void) /** * rcu_read_lock_sched() - mark the beginning of a RCU-sched critical section * - * This is equivalent of rcu_read_lock(), but disables preemption. - * Read-side critical sections can also be introduced by anything else - * that disables preemption, including local_irq_disable() and friends. + * This is equivalent to rcu_read_lock(), but also disables preemption. + * Read-side critical sections can also be introduced by anything else that + * disables preemption, including local_irq_disable() and friends. However, + * please note that the equivalence to rcu_read_lock() applies only to + * v5.0 and later. Before v5.0, rcu_read_lock() and rcu_read_lock_sched() + * were unrelated. * * Note that rcu_read_lock_sched() and the matching rcu_read_unlock_sched() * must occur in the same context, for example, it is illegal to invoke -- cgit v1.2.3 From 0223846010750e28e4330f1beefb5564ba406ef7 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 29 Apr 2021 11:30:49 -0700 Subject: rcu: Remove obsolete rcu_read_unlock() deadlock commentary The deferred quiescent states resulting from the consolidation of RCU-bh and RCU-sched into RCU means that rcu_read_unlock() will no longer attempt to acquire scheduler locks if interrupts were disabled across that call to rcu_read_unlock(). The cautions in the rcu_read_unlock() header comment are therefore obsolete. This commit therefore removes them. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 33 ++++++--------------------------- 1 file changed, 6 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index f0eecb9e49c8..d9680b798b21 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -702,33 +702,12 @@ static __always_inline void rcu_read_lock(void) /** * rcu_read_unlock() - marks the end of an RCU read-side critical section. * - * In most situations, rcu_read_unlock() is immune from deadlock. - * However, in kernels built with CONFIG_RCU_BOOST, rcu_read_unlock() - * is responsible for deboosting, which it does via rt_mutex_unlock(). - * Unfortunately, this function acquires the scheduler's runqueue and - * priority-inheritance spinlocks. This means that deadlock could result - * if the caller of rcu_read_unlock() already holds one of these locks or - * any lock that is ever acquired while holding them. - * - * That said, RCU readers are never priority boosted unless they were - * preempted. Therefore, one way to avoid deadlock is to make sure - * that preemption never happens within any RCU read-side critical - * section whose outermost rcu_read_unlock() is called with one of - * rt_mutex_unlock()'s locks held. Such preemption can be avoided in - * a number of ways, for example, by invoking preempt_disable() before - * critical section's outermost rcu_read_lock(). - * - * Given that the set of locks acquired by rt_mutex_unlock() might change - * at any time, a somewhat more future-proofed approach is to make sure - * that that preemption never happens within any RCU read-side critical - * section whose outermost rcu_read_unlock() is called with irqs disabled. - * This approach relies on the fact that rt_mutex_unlock() currently only - * acquires irq-disabled locks. - * - * The second of these two approaches is best in most situations, - * however, the first approach can also be useful, at least to those - * developers willing to keep abreast of the set of locks acquired by - * rt_mutex_unlock(). + * In almost all situations, rcu_read_unlock() is immune from deadlock. + * In recent kernels that have consolidated synchronize_sched() and + * synchronize_rcu_bh() into synchronize_rcu(), this deadlock immunity + * also extends to the scheduler's runqueue and priority-inheritance + * spinlocks, courtesy of the quiescent-state deferral that is carried + * out when rcu_read_unlock() is invoked with interrupts disabled. * * See rcu_read_lock() for more information. */ -- cgit v1.2.3 From 9a33fbf9d23034d7e89849c587b0aed0e4cf794d Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 5 May 2021 11:19:17 +0200 Subject: tty: make tty_buffer_space_avail return uint tty_buffer_space_avail returns values >= 0, so make it clear by the return type. Signed-off-by: Jiri Slaby Cc: Joel Stanley Link: https://lore.kernel.org/r/20210505091928.22010-25-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/tty_flip.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty_flip.h b/include/linux/tty_flip.h index 767f62086bd9..d6729281ec50 100644 --- a/include/linux/tty_flip.h +++ b/include/linux/tty_flip.h @@ -3,7 +3,7 @@ #define _LINUX_TTY_FLIP_H extern int tty_buffer_set_limit(struct tty_port *port, int limit); -extern int tty_buffer_space_avail(struct tty_port *port); +extern unsigned int tty_buffer_space_avail(struct tty_port *port); extern int tty_buffer_request_room(struct tty_port *port, size_t size); extern int tty_insert_flip_string_flags(struct tty_port *port, const unsigned char *chars, const char *flags, size_t size); -- cgit v1.2.3 From fff4ef17a9400fcd276b5c3a00ce5793f6c465e6 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 5 May 2021 11:19:19 +0200 Subject: tty: make tty_operations::chars_in_buffer return uint tty_operations::chars_in_buffer is another hook which is expected to return values >= 0. So make it explicit by the return type too -- use unsigned int. Signed-off-by: Jiri Slaby Acked-By: Anton Ivanov Acked-by: David Sterba Cc: Jeff Dike Cc: Richard Weinberger Cc: Arnd Bergmann Cc: Samuel Iglesias Gonsalvez Cc: Jens Taprogge Cc: Karsten Keil Cc: Ulf Hansson Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Christian Borntraeger Cc: David Lin Cc: Johan Hovold Cc: Alex Elder Cc: Jiri Kosina Cc: Shawn Guo Cc: Sascha Hauer Cc: Oliver Neukum Cc: Felipe Balbi Cc: Mathias Nyman Cc: Marcel Holtmann Cc: Johan Hedberg Cc: Luiz Augusto von Dentz Link: https://lore.kernel.org/r/20210505091928.22010-27-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 2 +- include/linux/tty_driver.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index d18fc34d3054..5cf6b2e7331b 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -458,7 +458,7 @@ extern void tty_unregister_device(struct tty_driver *driver, unsigned index); extern void tty_write_message(struct tty_struct *tty, char *msg); extern int tty_send_xchar(struct tty_struct *tty, char ch); extern int tty_put_char(struct tty_struct *tty, unsigned char c); -extern int tty_chars_in_buffer(struct tty_struct *tty); +extern unsigned int tty_chars_in_buffer(struct tty_struct *tty); extern unsigned int tty_write_room(struct tty_struct *tty); extern void tty_driver_flush_buffer(struct tty_struct *tty); extern void tty_throttle(struct tty_struct *tty); diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index ea5b15c72764..a4694bb125cc 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -257,7 +257,7 @@ struct tty_operations { int (*put_char)(struct tty_struct *tty, unsigned char ch); void (*flush_chars)(struct tty_struct *tty); unsigned int (*write_room)(struct tty_struct *tty); - int (*chars_in_buffer)(struct tty_struct *tty); + unsigned int (*chars_in_buffer)(struct tty_struct *tty); int (*ioctl)(struct tty_struct *tty, unsigned int cmd, unsigned long arg); long (*compat_ioctl)(struct tty_struct *tty, -- cgit v1.2.3 From 76af233d9b0c0b749e97b8f90fd0ff0e417ce3e3 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Mon, 10 May 2021 08:59:22 +0200 Subject: tty: remove unused tty_throttle The last user was removed in commit e91e52e42814 (n_tty: Fix stuck throttled driver) in 2013. So remove exported tty_throttle completely. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210510065923.5112-1-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 1 - include/linux/tty_driver.h | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 5cf6b2e7331b..4c0c7ca1d9a4 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -461,7 +461,6 @@ extern int tty_put_char(struct tty_struct *tty, unsigned char c); extern unsigned int tty_chars_in_buffer(struct tty_struct *tty); extern unsigned int tty_write_room(struct tty_struct *tty); extern void tty_driver_flush_buffer(struct tty_struct *tty); -extern void tty_throttle(struct tty_struct *tty); extern void tty_unthrottle(struct tty_struct *tty); extern int tty_throttle_safe(struct tty_struct *tty); extern int tty_unthrottle_safe(struct tty_struct *tty); diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index a4694bb125cc..448f8ee6db6e 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -136,7 +136,7 @@ * the line discipline are close to full, and it should somehow * signal that no more characters should be sent to the tty. * - * Optional: Always invoke via tty_throttle(), called under the + * Optional: Always invoke via tty_throttle_safe(), called under the * termios lock. * * void (*unthrottle)(struct tty_struct * tty); -- cgit v1.2.3 From 3b85f9ba3480c1bcbebb2bb490822bec0e7a1201 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Linus=20L=C3=BCssing?= Date: Thu, 13 May 2021 15:20:53 +0200 Subject: net: bridge: mcast: export multicast router presence adjacent to a port MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To properly support routable multicast addresses in batman-adv in a group-aware way, a batman-adv node needs to know if it serves multicast routers. This adds a function to the bridge to export this so that batman-adv can then make full use of the Multicast Router Discovery capability of the bridge. Signed-off-by: Linus Lüssing Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 2cc35038a8ca..12e9a32dbca0 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -67,6 +67,7 @@ int br_multicast_list_adjacent(struct net_device *dev, struct list_head *br_ip_list); bool br_multicast_has_querier_anywhere(struct net_device *dev, int proto); bool br_multicast_has_querier_adjacent(struct net_device *dev, int proto); +bool br_multicast_has_router_adjacent(struct net_device *dev, int proto); bool br_multicast_enabled(const struct net_device *dev); bool br_multicast_router(const struct net_device *dev); int br_mdb_replay(struct net_device *br_dev, struct net_device *dev, @@ -87,6 +88,13 @@ static inline bool br_multicast_has_querier_adjacent(struct net_device *dev, { return false; } + +static inline bool br_multicast_has_router_adjacent(struct net_device *dev, + int proto) +{ + return true; +} + static inline bool br_multicast_enabled(const struct net_device *dev) { return false; -- cgit v1.2.3 From 14374fbb3f06ddaba186d608a58c07f3d48d08df Mon Sep 17 00:00:00 2001 From: Emmanuel Gil Peyrot Date: Tue, 11 May 2021 23:07:25 +0200 Subject: misc: eeprom_93xx46: Add new 93c56 and 93c66 compatible strings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit These two devices have respectively 2048 and 4096 bits of storage, compared to 1024 for the 93c46. Reviewed-by: Jonathan Neuschäfer Signed-off-by: Emmanuel Gil Peyrot Link: https://lore.kernel.org/r/20210511210727.24895-3-linkmauve@linkmauve.fr Signed-off-by: Greg Kroah-Hartman --- include/linux/eeprom_93xx46.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/eeprom_93xx46.h b/include/linux/eeprom_93xx46.h index 99580c22f91a..34c2175e6a1e 100644 --- a/include/linux/eeprom_93xx46.h +++ b/include/linux/eeprom_93xx46.h @@ -10,6 +10,9 @@ struct eeprom_93xx46_platform_data { #define EE_ADDR8 0x01 /* 8 bit addr. cfg */ #define EE_ADDR16 0x02 /* 16 bit addr. cfg */ #define EE_READONLY 0x08 /* forbid writing */ +#define EE_SIZE1K 0x10 /* 1 kb of data, that is a 93xx46 */ +#define EE_SIZE2K 0x20 /* 2 kb of data, that is a 93xx56 */ +#define EE_SIZE4K 0x40 /* 4 kb of data, that is a 93xx66 */ unsigned int quirks; /* Single word read transfers only; no sequential read. */ -- cgit v1.2.3 From ea030ca688193462b8d612c1628c37129aa30072 Mon Sep 17 00:00:00 2001 From: Lucas Tanure Date: Wed, 12 May 2021 14:52:22 +0100 Subject: regmap-i2c: Set regmap max raw r/w from quirks Set regmap raw read/write from i2c quirks max read/write so regmap_raw_read/write can split the access into chunks Signed-off-by: Lucas Tanure Link: https://lore.kernel.org/r/20210512135222.223203-1-tanureal@opensource.cirrus.com Signed-off-by: Mark Brown --- include/linux/regmap.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index f87a11a5cc4a..8c16e6fa0f66 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -502,6 +502,7 @@ typedef void (*regmap_hw_free_context)(void *context); * DEFAULT, BIG is assumed. * @max_raw_read: Max raw read size that can be used on the bus. * @max_raw_write: Max raw write size that can be used on the bus. + * @free_on_exit: kfree this on exit of regmap */ struct regmap_bus { bool fast_io; @@ -519,6 +520,7 @@ struct regmap_bus { enum regmap_endian val_format_endian_default; size_t max_raw_read; size_t max_raw_write; + bool free_on_exit; }; /* -- cgit v1.2.3 From adae1e931acd8b430d31141a283ea06d4b705417 Mon Sep 17 00:00:00 2001 From: Andres Beltran Date: Thu, 8 Apr 2021 18:14:39 +0200 Subject: Drivers: hv: vmbus: Copy packets sent by Hyper-V out of the ring buffer Pointers to ring-buffer packets sent by Hyper-V are used within the guest VM. Hyper-V can send packets with erroneous values or modify packet fields after they are processed by the guest. To defend against these scenarios, return a copy of the incoming VMBus packet after validating its length and offset fields in hv_pkt_iter_first(). In this way, the packet can no longer be modified by the host. Signed-off-by: Andres Beltran Co-developed-by: Andrea Parri (Microsoft) Signed-off-by: Andrea Parri (Microsoft) Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20210408161439.341988-1-parri.andrea@gmail.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 48 ++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 40 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index d1e59dbef1dd..3932446f215f 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -181,6 +181,10 @@ struct hv_ring_buffer_info { * being freed while the ring buffer is being accessed. */ struct mutex ring_buffer_mutex; + + /* Buffer that holds a copy of an incoming host packet */ + void *pkt_buffer; + u32 pkt_buffer_size; }; @@ -799,6 +803,8 @@ struct vmbus_device { bool allowed_in_isolated; }; +#define VMBUS_DEFAULT_MAX_PKT_SIZE 4096 + struct vmbus_channel { struct list_head listentry; @@ -1021,6 +1027,9 @@ struct vmbus_channel { /* request/transaction ids for VMBus */ struct vmbus_requestor requestor; u32 rqstor_size; + + /* The max size of a packet on this channel */ + u32 max_pkt_size; }; u64 vmbus_next_request_id(struct vmbus_requestor *rqstor, u64 rqst_addr); @@ -1662,32 +1671,55 @@ static inline u32 hv_pkt_datalen(const struct vmpacket_descriptor *desc) } +struct vmpacket_descriptor * +hv_pkt_iter_first_raw(struct vmbus_channel *channel); + struct vmpacket_descriptor * hv_pkt_iter_first(struct vmbus_channel *channel); struct vmpacket_descriptor * __hv_pkt_iter_next(struct vmbus_channel *channel, - const struct vmpacket_descriptor *pkt); + const struct vmpacket_descriptor *pkt, + bool copy); void hv_pkt_iter_close(struct vmbus_channel *channel); -/* - * Get next packet descriptor from iterator - * If at end of list, return NULL and update host. - */ static inline struct vmpacket_descriptor * -hv_pkt_iter_next(struct vmbus_channel *channel, - const struct vmpacket_descriptor *pkt) +hv_pkt_iter_next_pkt(struct vmbus_channel *channel, + const struct vmpacket_descriptor *pkt, + bool copy) { struct vmpacket_descriptor *nxt; - nxt = __hv_pkt_iter_next(channel, pkt); + nxt = __hv_pkt_iter_next(channel, pkt, copy); if (!nxt) hv_pkt_iter_close(channel); return nxt; } +/* + * Get next packet descriptor without copying it out of the ring buffer + * If at end of list, return NULL and update host. + */ +static inline struct vmpacket_descriptor * +hv_pkt_iter_next_raw(struct vmbus_channel *channel, + const struct vmpacket_descriptor *pkt) +{ + return hv_pkt_iter_next_pkt(channel, pkt, false); +} + +/* + * Get next packet descriptor from iterator + * If at end of list, return NULL and update host. + */ +static inline struct vmpacket_descriptor * +hv_pkt_iter_next(struct vmbus_channel *channel, + const struct vmpacket_descriptor *pkt) +{ + return hv_pkt_iter_next_pkt(channel, pkt, true); +} + #define foreach_vmbus_pkt(pkt, channel) \ for (pkt = hv_pkt_iter_first(channel); pkt; \ pkt = hv_pkt_iter_next(channel, pkt)) -- cgit v1.2.3 From bf5fd8cae3c8f0d1e6f71a076e0ce2bd17645d0b Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Mon, 10 May 2021 23:08:41 +0200 Subject: scsi: storvsc: Use blk_mq_unique_tag() to generate requestIDs Use blk_mq_unique_tag() to generate requestIDs for StorVSC, avoiding all issues with allocating enough entries in the VMbus requestor. Suggested-by: Michael Kelley Signed-off-by: Andrea Parri (Microsoft) Reviewed-by: Michael Kelley Acked-by: Martin K. Petersen Link: https://lore.kernel.org/r/20210510210841.370472-1-parri.andrea@gmail.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 3932446f215f..2e859d2f9609 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -794,7 +794,11 @@ struct vmbus_requestor { #define VMBUS_NO_RQSTOR U64_MAX #define VMBUS_RQST_ERROR (U64_MAX - 1) +/* NetVSC-specific */ #define VMBUS_RQST_ID_NO_RESPONSE (U64_MAX - 2) +/* StorVSC-specific */ +#define VMBUS_RQST_INIT (U64_MAX - 2) +#define VMBUS_RQST_RESET (U64_MAX - 3) struct vmbus_device { u16 dev_type; @@ -1024,6 +1028,11 @@ struct vmbus_channel { u32 fuzz_testing_interrupt_delay; u32 fuzz_testing_message_delay; + /* callback to generate a request ID from a request address */ + u64 (*next_request_id_callback)(struct vmbus_channel *channel, u64 rqst_addr); + /* callback to retrieve a request address from a request ID */ + u64 (*request_addr_callback)(struct vmbus_channel *channel, u64 rqst_id); + /* request/transaction ids for VMBus */ struct vmbus_requestor requestor; u32 rqstor_size; @@ -1032,8 +1041,8 @@ struct vmbus_channel { u32 max_pkt_size; }; -u64 vmbus_next_request_id(struct vmbus_requestor *rqstor, u64 rqst_addr); -u64 vmbus_request_addr(struct vmbus_requestor *rqstor, u64 trans_id); +u64 vmbus_next_request_id(struct vmbus_channel *channel, u64 rqst_addr); +u64 vmbus_request_addr(struct vmbus_channel *channel, u64 trans_id); static inline bool is_hvsock_channel(const struct vmbus_channel *c) { -- cgit v1.2.3 From 869cbeef18e5c4370157e733b947d44f37441ea9 Mon Sep 17 00:00:00 2001 From: Ondrej Mosnacek Date: Wed, 12 May 2021 16:32:10 +0200 Subject: lsm_audit,selinux: pass IB device name by reference While trying to address a Coverity warning that the dev_name string might end up unterminated when strcpy'ing it in selinux_ib_endport_manage_subnet(), I realized that it is possible (and simpler) to just pass the dev_name pointer directly, rather than copying the string to a buffer. The ibendport variable goes out of scope at the end of the function anyway, so the lifetime of the dev_name pointer will never be shorter than that of ibendport, thus we can safely just pass the dev_name pointer and be done with it. Signed-off-by: Ondrej Mosnacek Acked-by: Richard Guy Briggs Signed-off-by: Paul Moore --- include/linux/lsm_audit.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_audit.h b/include/linux/lsm_audit.h index cd23355d2271..17d02eda9538 100644 --- a/include/linux/lsm_audit.h +++ b/include/linux/lsm_audit.h @@ -48,13 +48,13 @@ struct lsm_ioctlop_audit { }; struct lsm_ibpkey_audit { - u64 subnet_prefix; - u16 pkey; + u64 subnet_prefix; + u16 pkey; }; struct lsm_ibendport_audit { - char dev_name[IB_DEVICE_NAME_MAX]; - u8 port; + const char *dev_name; + u8 port; }; /* Auxiliary data to use in generating the audit record. */ -- cgit v1.2.3 From 803f4e1eab7a8938ba3a3c30dd4eb5e9eeef5e63 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sat, 8 May 2021 00:07:57 +0200 Subject: asm-generic: simplify asm/unaligned.h The get_unaligned()/put_unaligned() implementations are much more complex than necessary, now that all architectures use the same code. Move everything into one file and use a much more compact way to express the same logic. I've compared the binary output using gcc-11 across defconfig builds for all architectures and found this patch to make no difference, except for a single function on powerpc that needs two additional register moves because of random differences in register allocation. There are a handful of callers of the low-level __get_unaligned_cpu32, so leave that in place for the time being even though the common code no longer uses it. This adds a warning for any caller of get_unaligned()/put_unaligned() that passes in a single-byte pointer, but I've sent patches for all instances that show up in x86 and randconfig builds. It would be nice to change the arguments of the endian-specific accessors to take the matching __be16/__be32/__be64/__le16/__le32/__le64 arguments instead of a void pointer, but that requires more changes to the rest of the kernel. This new version does allow aggregate types into get_unaligned(), which was not the original goal but might come in handy. Signed-off-by: Arnd Bergmann --- include/linux/unaligned/be_struct.h | 67 --------------------- include/linux/unaligned/generic.h | 115 ------------------------------------ include/linux/unaligned/le_struct.h | 67 --------------------- 3 files changed, 249 deletions(-) delete mode 100644 include/linux/unaligned/be_struct.h delete mode 100644 include/linux/unaligned/generic.h delete mode 100644 include/linux/unaligned/le_struct.h (limited to 'include/linux') diff --git a/include/linux/unaligned/be_struct.h b/include/linux/unaligned/be_struct.h deleted file mode 100644 index 76d9fe297c33..000000000000 --- a/include/linux/unaligned/be_struct.h +++ /dev/null @@ -1,67 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_UNALIGNED_BE_STRUCT_H -#define _LINUX_UNALIGNED_BE_STRUCT_H - -#include - -static inline u16 get_unaligned_be16(const void *p) -{ - return __get_unaligned_cpu16((const u8 *)p); -} - -static inline u32 get_unaligned_be32(const void *p) -{ - return __get_unaligned_cpu32((const u8 *)p); -} - -static inline u64 get_unaligned_be64(const void *p) -{ - return __get_unaligned_cpu64((const u8 *)p); -} - -static inline void put_unaligned_be16(u16 val, void *p) -{ - __put_unaligned_cpu16(val, p); -} - -static inline void put_unaligned_be32(u32 val, void *p) -{ - __put_unaligned_cpu32(val, p); -} - -static inline void put_unaligned_be64(u64 val, void *p) -{ - __put_unaligned_cpu64(val, p); -} - -static inline u16 get_unaligned_le16(const void *p) -{ - return swab16(__get_unaligned_cpu16((const u8 *)p)); -} - -static inline u32 get_unaligned_le32(const void *p) -{ - return swab32(__get_unaligned_cpu32((const u8 *)p)); -} - -static inline u64 get_unaligned_le64(const void *p) -{ - return swab64(__get_unaligned_cpu64((const u8 *)p)); -} - -static inline void put_unaligned_le16(u16 val, void *p) -{ - __put_unaligned_cpu16(swab16(val), p); -} - -static inline void put_unaligned_le32(u32 val, void *p) -{ - __put_unaligned_cpu32(swab32(val), p); -} - -static inline void put_unaligned_le64(u64 val, void *p) -{ - __put_unaligned_cpu64(swab64(val), p); -} - -#endif /* _LINUX_UNALIGNED_BE_STRUCT_H */ diff --git a/include/linux/unaligned/generic.h b/include/linux/unaligned/generic.h deleted file mode 100644 index 303289492859..000000000000 --- a/include/linux/unaligned/generic.h +++ /dev/null @@ -1,115 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_UNALIGNED_GENERIC_H -#define _LINUX_UNALIGNED_GENERIC_H - -#include - -/* - * Cause a link-time error if we try an unaligned access other than - * 1,2,4 or 8 bytes long - */ -extern void __bad_unaligned_access_size(void); - -#define __get_unaligned_le(ptr) ((__force typeof(*(ptr)))({ \ - __builtin_choose_expr(sizeof(*(ptr)) == 1, *(ptr), \ - __builtin_choose_expr(sizeof(*(ptr)) == 2, get_unaligned_le16((ptr)), \ - __builtin_choose_expr(sizeof(*(ptr)) == 4, get_unaligned_le32((ptr)), \ - __builtin_choose_expr(sizeof(*(ptr)) == 8, get_unaligned_le64((ptr)), \ - __bad_unaligned_access_size())))); \ - })) - -#define __get_unaligned_be(ptr) ((__force typeof(*(ptr)))({ \ - __builtin_choose_expr(sizeof(*(ptr)) == 1, *(ptr), \ - __builtin_choose_expr(sizeof(*(ptr)) == 2, get_unaligned_be16((ptr)), \ - __builtin_choose_expr(sizeof(*(ptr)) == 4, get_unaligned_be32((ptr)), \ - __builtin_choose_expr(sizeof(*(ptr)) == 8, get_unaligned_be64((ptr)), \ - __bad_unaligned_access_size())))); \ - })) - -#define __put_unaligned_le(val, ptr) ({ \ - void *__gu_p = (ptr); \ - switch (sizeof(*(ptr))) { \ - case 1: \ - *(u8 *)__gu_p = (__force u8)(val); \ - break; \ - case 2: \ - put_unaligned_le16((__force u16)(val), __gu_p); \ - break; \ - case 4: \ - put_unaligned_le32((__force u32)(val), __gu_p); \ - break; \ - case 8: \ - put_unaligned_le64((__force u64)(val), __gu_p); \ - break; \ - default: \ - __bad_unaligned_access_size(); \ - break; \ - } \ - (void)0; }) - -#define __put_unaligned_be(val, ptr) ({ \ - void *__gu_p = (ptr); \ - switch (sizeof(*(ptr))) { \ - case 1: \ - *(u8 *)__gu_p = (__force u8)(val); \ - break; \ - case 2: \ - put_unaligned_be16((__force u16)(val), __gu_p); \ - break; \ - case 4: \ - put_unaligned_be32((__force u32)(val), __gu_p); \ - break; \ - case 8: \ - put_unaligned_be64((__force u64)(val), __gu_p); \ - break; \ - default: \ - __bad_unaligned_access_size(); \ - break; \ - } \ - (void)0; }) - -static inline u32 __get_unaligned_be24(const u8 *p) -{ - return p[0] << 16 | p[1] << 8 | p[2]; -} - -static inline u32 get_unaligned_be24(const void *p) -{ - return __get_unaligned_be24(p); -} - -static inline u32 __get_unaligned_le24(const u8 *p) -{ - return p[0] | p[1] << 8 | p[2] << 16; -} - -static inline u32 get_unaligned_le24(const void *p) -{ - return __get_unaligned_le24(p); -} - -static inline void __put_unaligned_be24(const u32 val, u8 *p) -{ - *p++ = val >> 16; - *p++ = val >> 8; - *p++ = val; -} - -static inline void put_unaligned_be24(const u32 val, void *p) -{ - __put_unaligned_be24(val, p); -} - -static inline void __put_unaligned_le24(const u32 val, u8 *p) -{ - *p++ = val; - *p++ = val >> 8; - *p++ = val >> 16; -} - -static inline void put_unaligned_le24(const u32 val, void *p) -{ - __put_unaligned_le24(val, p); -} - -#endif /* _LINUX_UNALIGNED_GENERIC_H */ diff --git a/include/linux/unaligned/le_struct.h b/include/linux/unaligned/le_struct.h deleted file mode 100644 index 22f90a4afaa5..000000000000 --- a/include/linux/unaligned/le_struct.h +++ /dev/null @@ -1,67 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_UNALIGNED_LE_STRUCT_H -#define _LINUX_UNALIGNED_LE_STRUCT_H - -#include - -static inline u16 get_unaligned_le16(const void *p) -{ - return __get_unaligned_cpu16((const u8 *)p); -} - -static inline u32 get_unaligned_le32(const void *p) -{ - return __get_unaligned_cpu32((const u8 *)p); -} - -static inline u64 get_unaligned_le64(const void *p) -{ - return __get_unaligned_cpu64((const u8 *)p); -} - -static inline void put_unaligned_le16(u16 val, void *p) -{ - __put_unaligned_cpu16(val, p); -} - -static inline void put_unaligned_le32(u32 val, void *p) -{ - __put_unaligned_cpu32(val, p); -} - -static inline void put_unaligned_le64(u64 val, void *p) -{ - __put_unaligned_cpu64(val, p); -} - -static inline u16 get_unaligned_be16(const void *p) -{ - return swab16(__get_unaligned_cpu16((const u8 *)p)); -} - -static inline u32 get_unaligned_be32(const void *p) -{ - return swab32(__get_unaligned_cpu32((const u8 *)p)); -} - -static inline u64 get_unaligned_be64(const void *p) -{ - return swab64(__get_unaligned_cpu64((const u8 *)p)); -} - -static inline void put_unaligned_be16(u16 val, void *p) -{ - __put_unaligned_cpu16(swab16(val), p); -} - -static inline void put_unaligned_be32(u32 val, void *p) -{ - __put_unaligned_cpu32(swab32(val), p); -} - -static inline void put_unaligned_be64(u64 val, void *p) -{ - __put_unaligned_cpu64(swab64(val), p); -} - -#endif /* _LINUX_UNALIGNED_LE_STRUCT_H */ -- cgit v1.2.3 From dbf20809d6e0072ad189c937761d58bf98a47b43 Mon Sep 17 00:00:00 2001 From: Nuno Sa Date: Tue, 27 Apr 2021 10:54:52 +0200 Subject: iio: adis: add burst_max_speed_hz variable Typically, in burst mode, the device cannot operate at it's full spi speed. Hence, the spi transfers for burst mode have to take this into account. With this change we avoid a potential race with the spi core as drivers were 'hacking' the device 'max_speed_hz' directly in the trigger handler. Reviewed-by: Alexandru Ardelean Signed-off-by: Nuno Sa Link: https://lore.kernel.org/r/20210427085454.30616-5-nuno.sa@analog.com Signed-off-by: Jonathan Cameron --- include/linux/iio/imu/adis.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index f9b728d490b1..cf49997d5903 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -55,6 +55,7 @@ struct adis_timeout { * this should be the minimum size supported by the device. * @burst_max_len: Holds the maximum burst size when the device supports * more than one burst mode with different sizes + * @burst_max_speed_hz: Maximum spi speed that can be used in burst mode */ struct adis_data { unsigned int read_delay; @@ -83,6 +84,7 @@ struct adis_data { unsigned int burst_reg_cmd; unsigned int burst_len; unsigned int burst_max_len; + unsigned int burst_max_speed_hz; }; /** -- cgit v1.2.3 From 15ea2878bfb255099092634d28f31177f237ccd7 Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Mon, 26 Apr 2021 18:49:03 +0100 Subject: iio: core: move @id from struct iio_dev to struct iio_dev_opaque Continuing from Alexandru Ardelean's introduction of the split between driver modifiable fields and those that should only be set by the core. This could have been done in two steps to make the actual move after introducing iio_device_id() but there seemed limited point to that given how mechanical the majority of the patch is. Includes fixup from Alex for missing mxs-lradc-adc conversion. Signed-off-by: Jonathan Cameron Reviewed-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20210426174911.397061-2-jic23@kernel.org --- include/linux/iio/iio-opaque.h | 2 ++ include/linux/iio/iio.h | 4 ++-- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio-opaque.h b/include/linux/iio/iio-opaque.h index 32addd5e790e..e66b029d99de 100644 --- a/include/linux/iio/iio-opaque.h +++ b/include/linux/iio/iio-opaque.h @@ -6,6 +6,7 @@ /** * struct iio_dev_opaque - industrial I/O device opaque information * @indio_dev: public industrial I/O device information + * @id: used to identify device internally * @event_interface: event chrdevs associated with interrupt lines * @attached_buffers: array of buffers statically attached by the driver * @attached_buffers_cnt: number of buffers in the array of statically attached buffers @@ -26,6 +27,7 @@ */ struct iio_dev_opaque { struct iio_dev indio_dev; + int id; struct iio_event_interface *event_interface; struct iio_buffer **attached_buffers; unsigned int attached_buffers_cnt; diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index f2d65e2e88b6..569861d5887a 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -488,7 +488,6 @@ struct iio_buffer_setup_ops { /** * struct iio_dev - industrial I/O device - * @id: [INTERN] used to identify device internally * @driver_module: [INTERN] used to make it harder to undercut users * @modes: [DRIVER] operating modes supported by device * @currentmode: [DRIVER] current operating mode @@ -523,7 +522,6 @@ struct iio_buffer_setup_ops { * **MUST** be accessed **ONLY** via iio_priv() helper */ struct iio_dev { - int id; struct module *driver_module; int modes; @@ -559,6 +557,8 @@ struct iio_dev { void *priv; }; +int iio_device_id(struct iio_dev *indio_dev); + const struct iio_chan_spec *iio_find_channel_from_si(struct iio_dev *indio_dev, int si); /** -- cgit v1.2.3 From e5333ed09e0f8ece3cbb37912c17cf9880ee3fb0 Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Mon, 26 Apr 2021 18:49:04 +0100 Subject: iio: avoid shadowing of variable name in to_iio_dev_opaque() indio_dev was both the macro input parameter and the field name in this macro. That causes trouble if the instance of struct iio_dev passed in is not called indio_dev. Whilst a fix of sorts, no need to backport as it seems we never hit this previously due to some very consistent naming in IIO. Signed-off-by: Jonathan Cameron Reviewed-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20210426174911.397061-3-jic23@kernel.org --- include/linux/iio/iio-opaque.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio-opaque.h b/include/linux/iio/iio-opaque.h index e66b029d99de..f876e3aede2c 100644 --- a/include/linux/iio/iio-opaque.h +++ b/include/linux/iio/iio-opaque.h @@ -48,7 +48,7 @@ struct iio_dev_opaque { #endif }; -#define to_iio_dev_opaque(indio_dev) \ - container_of(indio_dev, struct iio_dev_opaque, indio_dev) +#define to_iio_dev_opaque(_indio_dev) \ + container_of((_indio_dev), struct iio_dev_opaque, indio_dev) #endif -- cgit v1.2.3 From 6eaf9f6a2738789dedb1e962096f61aaddd81464 Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Mon, 26 Apr 2021 18:49:05 +0100 Subject: iio: core: move @driver_module from struct iio_dev to struct iio_dev_opaque Continuing move to hide internal elements from drivers, move this structure element over. It's only accessed from iio core files so this one was straight forward and no accessor functions are needed. Signed-off-by: Jonathan Cameron Reviewed-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20210426174911.397061-4-jic23@kernel.org --- include/linux/iio/iio-opaque.h | 2 ++ include/linux/iio/iio.h | 3 --- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio-opaque.h b/include/linux/iio/iio-opaque.h index f876e3aede2c..96dd265103d0 100644 --- a/include/linux/iio/iio-opaque.h +++ b/include/linux/iio/iio-opaque.h @@ -7,6 +7,7 @@ * struct iio_dev_opaque - industrial I/O device opaque information * @indio_dev: public industrial I/O device information * @id: used to identify device internally + * @driver_module: used to make it harder to undercut users * @event_interface: event chrdevs associated with interrupt lines * @attached_buffers: array of buffers statically attached by the driver * @attached_buffers_cnt: number of buffers in the array of statically attached buffers @@ -28,6 +29,7 @@ struct iio_dev_opaque { struct iio_dev indio_dev; int id; + struct module *driver_module; struct iio_event_interface *event_interface; struct iio_buffer **attached_buffers; unsigned int attached_buffers_cnt; diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 569861d5887a..9e8e1358a032 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -488,7 +488,6 @@ struct iio_buffer_setup_ops { /** * struct iio_dev - industrial I/O device - * @driver_module: [INTERN] used to make it harder to undercut users * @modes: [DRIVER] operating modes supported by device * @currentmode: [DRIVER] current operating mode * @dev: [DRIVER] device structure, should be assigned a parent @@ -522,8 +521,6 @@ struct iio_buffer_setup_ops { * **MUST** be accessed **ONLY** via iio_priv() helper */ struct iio_dev { - struct module *driver_module; - int modes; int currentmode; struct device dev; -- cgit v1.2.3 From 3028e0c2af95dd476ccd71f4fc025990385168c2 Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Mon, 26 Apr 2021 18:49:06 +0100 Subject: iio: core: move @trig_readonly from struct iio_dev to struct iio_dev_opaque This is only set via the iio_trig_set_immutable() call and later used by the IIO core so there is no benefit in drivers being able to access it. Signed-off-by: Jonathan Cameron Reviewed-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20210426174911.397061-5-jic23@kernel.org --- include/linux/iio/iio-opaque.h | 2 ++ include/linux/iio/iio.h | 2 -- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio-opaque.h b/include/linux/iio/iio-opaque.h index 96dd265103d0..10aa97239117 100644 --- a/include/linux/iio/iio-opaque.h +++ b/include/linux/iio/iio-opaque.h @@ -8,6 +8,7 @@ * @indio_dev: public industrial I/O device information * @id: used to identify device internally * @driver_module: used to make it harder to undercut users + * @trig_readonly: mark the current trigger immutable * @event_interface: event chrdevs associated with interrupt lines * @attached_buffers: array of buffers statically attached by the driver * @attached_buffers_cnt: number of buffers in the array of statically attached buffers @@ -30,6 +31,7 @@ struct iio_dev_opaque { struct iio_dev indio_dev; int id; struct module *driver_module; + bool trig_readonly; struct iio_event_interface *event_interface; struct iio_buffer **attached_buffers; unsigned int attached_buffers_cnt; diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 9e8e1358a032..672f141f74c5 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -503,7 +503,6 @@ struct iio_buffer_setup_ops { * @scan_timestamp: [INTERN] set if any buffers have requested timestamp * @scan_index_timestamp:[INTERN] cache of the index to the timestamp * @trig: [INTERN] current device trigger (buffer modes) - * @trig_readonly: [INTERN] mark the current trigger immutable * @pollfunc: [DRIVER] function run on trigger being received * @pollfunc_event: [DRIVER] function run on events trigger being received * @channels: [DRIVER] channel specification structure table @@ -535,7 +534,6 @@ struct iio_dev { bool scan_timestamp; unsigned scan_index_timestamp; struct iio_trigger *trig; - bool trig_readonly; struct iio_poll_func *pollfunc; struct iio_poll_func *pollfunc_event; -- cgit v1.2.3 From 62f4f36cdfcdbb961bbbeab15e6595dd391d2205 Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Mon, 26 Apr 2021 18:49:07 +0100 Subject: iio: core: move @scan_index_timestamp to struct iio_dev_opaque No reason for this cached value to be exposed to drivers so move it to the opaque structure. Signed-off-by: Jonathan Cameron Reviewed-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20210426174911.397061-6-jic23@kernel.org --- include/linux/iio/iio-opaque.h | 4 ++++ include/linux/iio/iio.h | 2 -- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio-opaque.h b/include/linux/iio/iio-opaque.h index 10aa97239117..02038fb2d291 100644 --- a/include/linux/iio/iio-opaque.h +++ b/include/linux/iio/iio-opaque.h @@ -22,6 +22,7 @@ * @groupcounter: index of next attribute group * @legacy_scan_el_group: attribute group for legacy scan elements attribute group * @legacy_buffer_group: attribute group for legacy buffer attributes group + * @scan_index_timestamp: cache of the index to the timestamp * @debugfs_dentry: device specific debugfs dentry * @cached_reg_addr: cached register address for debugfs reads * @read_buf: read buffer to be used for the initial reg read @@ -44,6 +45,9 @@ struct iio_dev_opaque { int groupcounter; struct attribute_group legacy_scan_el_group; struct attribute_group legacy_buffer_group; + + unsigned int scan_index_timestamp; + #if defined(CONFIG_DEBUG_FS) struct dentry *debugfs_dentry; unsigned cached_reg_addr; diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 672f141f74c5..cbc9e9ece0a6 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -501,7 +501,6 @@ struct iio_buffer_setup_ops { * channels * @active_scan_mask: [INTERN] union of all scan masks requested by buffers * @scan_timestamp: [INTERN] set if any buffers have requested timestamp - * @scan_index_timestamp:[INTERN] cache of the index to the timestamp * @trig: [INTERN] current device trigger (buffer modes) * @pollfunc: [DRIVER] function run on trigger being received * @pollfunc_event: [DRIVER] function run on events trigger being received @@ -532,7 +531,6 @@ struct iio_dev { unsigned masklength; const unsigned long *active_scan_mask; bool scan_timestamp; - unsigned scan_index_timestamp; struct iio_trigger *trig; struct iio_poll_func *pollfunc; struct iio_poll_func *pollfunc_event; -- cgit v1.2.3 From b804e2b76ac6d5559b99588e0190ac97b5597497 Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Mon, 26 Apr 2021 18:49:08 +0100 Subject: iio: core: move @info_exist_lock to struct iio_dev_opaque This lock is only of interest to the IIO core, so make it only visible there. Signed-off-by: Jonathan Cameron Reviewed-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20210426174911.397061-7-jic23@kernel.org --- include/linux/iio/iio-opaque.h | 2 ++ include/linux/iio/iio.h | 2 -- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio-opaque.h b/include/linux/iio/iio-opaque.h index 02038fb2d291..538b4b5ef1a9 100644 --- a/include/linux/iio/iio-opaque.h +++ b/include/linux/iio/iio-opaque.h @@ -8,6 +8,7 @@ * @indio_dev: public industrial I/O device information * @id: used to identify device internally * @driver_module: used to make it harder to undercut users + * @info_exist_lock: lock to prevent use during removal * @trig_readonly: mark the current trigger immutable * @event_interface: event chrdevs associated with interrupt lines * @attached_buffers: array of buffers statically attached by the driver @@ -32,6 +33,7 @@ struct iio_dev_opaque { struct iio_dev indio_dev; int id; struct module *driver_module; + struct mutex info_exist_lock; bool trig_readonly; struct iio_event_interface *event_interface; struct iio_buffer **attached_buffers; diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index cbc9e9ece0a6..a12bbd8b1e74 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -510,7 +510,6 @@ struct iio_buffer_setup_ops { * @label: [DRIVER] unique name to identify which device this is * @info: [DRIVER] callbacks and constant info from driver * @clock_id: [INTERN] timestamping clock posix identifier - * @info_exist_lock: [INTERN] lock to prevent use during removal * @setup_ops: [DRIVER] callbacks to call before and after buffer * enable/disable * @chrdev: [INTERN] associated character device @@ -542,7 +541,6 @@ struct iio_dev { const char *label; const struct iio_info *info; clockid_t clock_id; - struct mutex info_exist_lock; const struct iio_buffer_setup_ops *setup_ops; struct cdev chrdev; -- cgit v1.2.3 From 396f7234856956eb29f009da6e5d846f29f87ebd Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Mon, 26 Apr 2021 18:49:09 +0100 Subject: iio: core: move @chrdev from struct iio_dev to struct iio_dev_opaque No reason for this to be exposed to the drivers, so lets move it to the opaque structure. Signed-off-by: Jonathan Cameron Reviewed-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20210426174911.397061-8-jic23@kernel.org --- include/linux/iio/iio-opaque.h | 2 ++ include/linux/iio/iio.h | 2 -- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio-opaque.h b/include/linux/iio/iio-opaque.h index 538b4b5ef1a9..2f8ef5d15a66 100644 --- a/include/linux/iio/iio-opaque.h +++ b/include/linux/iio/iio-opaque.h @@ -24,6 +24,7 @@ * @legacy_scan_el_group: attribute group for legacy scan elements attribute group * @legacy_buffer_group: attribute group for legacy buffer attributes group * @scan_index_timestamp: cache of the index to the timestamp + * @chrdev: associated character device * @debugfs_dentry: device specific debugfs dentry * @cached_reg_addr: cached register address for debugfs reads * @read_buf: read buffer to be used for the initial reg read @@ -49,6 +50,7 @@ struct iio_dev_opaque { struct attribute_group legacy_buffer_group; unsigned int scan_index_timestamp; + struct cdev chrdev; #if defined(CONFIG_DEBUG_FS) struct dentry *debugfs_dentry; diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index a12bbd8b1e74..586e2dc4fbf3 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -512,7 +512,6 @@ struct iio_buffer_setup_ops { * @clock_id: [INTERN] timestamping clock posix identifier * @setup_ops: [DRIVER] callbacks to call before and after buffer * enable/disable - * @chrdev: [INTERN] associated character device * @flags: [INTERN] file ops related flags including busy flag. * @priv: [DRIVER] reference to driver's private information * **MUST** be accessed **ONLY** via iio_priv() helper @@ -542,7 +541,6 @@ struct iio_dev { const struct iio_info *info; clockid_t clock_id; const struct iio_buffer_setup_ops *setup_ops; - struct cdev chrdev; unsigned long flags; void *priv; -- cgit v1.2.3 From 8b1c82cb849f8f7c758891099f2128b8fbc05744 Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Mon, 26 Apr 2021 18:49:10 +0100 Subject: iio: core: move @flags from struct iio_dev to struct iio_dev_opaque No reason any driver should ever need access to this field, so hide it. Signed-off-by: Jonathan Cameron Reviewed-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20210426174911.397061-9-jic23@kernel.org --- include/linux/iio/iio-opaque.h | 2 ++ include/linux/iio/iio.h | 2 -- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio-opaque.h b/include/linux/iio/iio-opaque.h index 2f8ef5d15a66..d7c3036861ac 100644 --- a/include/linux/iio/iio-opaque.h +++ b/include/linux/iio/iio-opaque.h @@ -25,6 +25,7 @@ * @legacy_buffer_group: attribute group for legacy buffer attributes group * @scan_index_timestamp: cache of the index to the timestamp * @chrdev: associated character device + * @flags: file ops related flags including busy flag. * @debugfs_dentry: device specific debugfs dentry * @cached_reg_addr: cached register address for debugfs reads * @read_buf: read buffer to be used for the initial reg read @@ -51,6 +52,7 @@ struct iio_dev_opaque { unsigned int scan_index_timestamp; struct cdev chrdev; + unsigned long flags; #if defined(CONFIG_DEBUG_FS) struct dentry *debugfs_dentry; diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 586e2dc4fbf3..ed0537015eee 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -512,7 +512,6 @@ struct iio_buffer_setup_ops { * @clock_id: [INTERN] timestamping clock posix identifier * @setup_ops: [DRIVER] callbacks to call before and after buffer * enable/disable - * @flags: [INTERN] file ops related flags including busy flag. * @priv: [DRIVER] reference to driver's private information * **MUST** be accessed **ONLY** via iio_priv() helper */ @@ -542,7 +541,6 @@ struct iio_dev { clockid_t clock_id; const struct iio_buffer_setup_ops *setup_ops; - unsigned long flags; void *priv; }; -- cgit v1.2.3 From 62a486c46d61bc684967fc3f83eed15dde49cf9b Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Mon, 26 Apr 2021 18:49:11 +0100 Subject: iio: core: move @clock_id from struct iio_dev to struct iio_dev_opaque There is already an acessor function used to access it, making this move straight forward. Signed-off-by: Jonathan Cameron Reviewed-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20210426174911.397061-10-jic23@kernel.org --- include/linux/iio/iio-opaque.h | 2 ++ include/linux/iio/iio.h | 12 +----------- 2 files changed, 3 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio-opaque.h b/include/linux/iio/iio-opaque.h index d7c3036861ac..c9504e9da571 100644 --- a/include/linux/iio/iio-opaque.h +++ b/include/linux/iio/iio-opaque.h @@ -24,6 +24,7 @@ * @legacy_scan_el_group: attribute group for legacy scan elements attribute group * @legacy_buffer_group: attribute group for legacy buffer attributes group * @scan_index_timestamp: cache of the index to the timestamp + * @clock_id: timestamping clock posix identifier * @chrdev: associated character device * @flags: file ops related flags including busy flag. * @debugfs_dentry: device specific debugfs dentry @@ -51,6 +52,7 @@ struct iio_dev_opaque { struct attribute_group legacy_buffer_group; unsigned int scan_index_timestamp; + clockid_t clock_id; struct cdev chrdev; unsigned long flags; diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index ed0537015eee..5606a3f4c4cb 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -509,7 +509,6 @@ struct iio_buffer_setup_ops { * @name: [DRIVER] name of the device. * @label: [DRIVER] unique name to identify which device this is * @info: [DRIVER] callbacks and constant info from driver - * @clock_id: [INTERN] timestamping clock posix identifier * @setup_ops: [DRIVER] callbacks to call before and after buffer * enable/disable * @priv: [DRIVER] reference to driver's private information @@ -538,7 +537,6 @@ struct iio_dev { const char *name; const char *label; const struct iio_info *info; - clockid_t clock_id; const struct iio_buffer_setup_ops *setup_ops; void *priv; @@ -589,15 +587,7 @@ static inline void iio_device_put(struct iio_dev *indio_dev) put_device(&indio_dev->dev); } -/** - * iio_device_get_clock() - Retrieve current timestamping clock for the device - * @indio_dev: IIO device structure containing the device - */ -static inline clockid_t iio_device_get_clock(const struct iio_dev *indio_dev) -{ - return indio_dev->clock_id; -} - +clockid_t iio_device_get_clock(const struct iio_dev *indio_dev); int iio_device_set_clock(struct iio_dev *indio_dev, clockid_t clock_id); /** -- cgit v1.2.3 From 38934daf7b5c1b35a01748cb7d4272282cc3a890 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 14 Apr 2021 22:54:50 +0300 Subject: iio: magnetometer: st_magn: Provide default platform data Provide default platform data for magnetometer in case it supports DRDY. One case is LSM9DS0 IMU, on which it is the case. Since accelerometer is using INT1, default magnetometer to INT2. While at it, update description of the drdy_int_pin field. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20210414195454.84183-3-andriy.shevchenko@linux.intel.com Signed-off-by: Jonathan Cameron --- include/linux/platform_data/st_sensors_pdata.h | 3 ++- 1 file changed, 2 insertions(+), 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 e40b28ca892e..897051e51b78 100644 --- a/include/linux/platform_data/st_sensors_pdata.h +++ b/include/linux/platform_data/st_sensors_pdata.h @@ -13,8 +13,9 @@ /** * struct st_sensors_platform_data - Platform data for the ST sensors * @drdy_int_pin: Redirect DRDY on pin 1 (1) or pin 2 (2). - * Available only for accelerometer and pressure sensors. + * 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. * @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 d61881ef7f08aef02d9bfc8c66f4c89c59cdf112 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 14 Apr 2021 22:54:52 +0300 Subject: iio: st_sensors: Make accel, gyro, magn and pressure probe shared Some IMUs may utilize existing library code for STMicro accelerometer, gyroscope, magnetometer and pressure. Let's share them via st_sensors.h. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20210414195454.84183-5-andriy.shevchenko@linux.intel.com Signed-off-by: Jonathan Cameron --- include/linux/iio/common/st_sensors.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index 33e939977444..aa017b90fb06 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -317,4 +317,24 @@ ssize_t st_sensors_sysfs_scale_avail(struct device *dev, void st_sensors_dev_name_probe(struct device *dev, char *name, int len); +/* Accelerometer */ +const struct st_sensor_settings *st_accel_get_settings(const char *name); +int st_accel_common_probe(struct iio_dev *indio_dev); +void st_accel_common_remove(struct iio_dev *indio_dev); + +/* Gyroscope */ +const struct st_sensor_settings *st_gyro_get_settings(const char *name); +int st_gyro_common_probe(struct iio_dev *indio_dev); +void st_gyro_common_remove(struct iio_dev *indio_dev); + +/* Magnetometer */ +const struct st_sensor_settings *st_magn_get_settings(const char *name); +int st_magn_common_probe(struct iio_dev *indio_dev); +void st_magn_common_remove(struct iio_dev *indio_dev); + +/* Pressure */ +const struct st_sensor_settings *st_press_get_settings(const char *name); +int st_press_common_probe(struct iio_dev *indio_dev); +void st_press_common_remove(struct iio_dev *indio_dev); + #endif /* ST_SENSORS_H */ -- cgit v1.2.3 From 6731ca3999ffa4c878a661b980759300dfb0237e Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 14 Apr 2021 22:54:53 +0300 Subject: iio: st_sensors: Add lsm9ds0 IMU support We can utilize separate drivers for accelerometer and magnetometer, so here is the glue driver to enable LSM9DS0 IMU support. The idea was suggested by Crestez Dan Leonard in [1]. The proposed change was sent as RFC due to race condition concerns, which are indeed possible. In order to amend the initial change, I went further by providing a specific multi-instantiate probe driver that reuses existing accelerometer and magnetometer. [1]: https://lore.kernel.org/patchwork/patch/670353/ Suggested-by: Crestez Dan Leonard Cc: mr.lahorde@laposte.net Cc: Matija Podravec Cc: Sergey Borishchenko Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20210414195454.84183-6-andriy.shevchenko@linux.intel.com Signed-off-by: Jonathan Cameron --- include/linux/iio/common/st_sensors.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index aa017b90fb06..0b9aeb479f48 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -20,6 +20,8 @@ #include +#define LSM9DS0_IMU_DEV_NAME "lsm9ds0" + /* * Buffer size max case: 2bytes per channel, 3 channels in total + * 8bytes timestamp channel (s64) -- cgit v1.2.3 From 8dea228b174ac9637b567e5ef54f4c40db4b3c41 Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Sat, 1 May 2021 18:13:47 +0100 Subject: iio: cros_ec_sensors: Fix alignment of buffer in iio_push_to_buffers_with_timestamp() The samples buffer is passed to iio_push_to_buffers_with_timestamp() which requires a buffer aligned to 8 bytes as it is assumed that the timestamp will be naturally aligned if present. Fixes tag is inaccurate but prior to that likely manual backporting needed (for anything before 4.18) Earlier than that the include file to fix is drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.h: commit 974e6f02e27 ("iio: cros_ec_sensors_core: Add common functions for the ChromeOS EC Sensor Hub.") present since kernel stable 4.10. (Thanks to Gwendal for tracking this down) Fixes: 5a0b8cb46624c ("iio: cros_ec: Move cros_ec_sensors_core.h in /include") Signed-off-by: Jonathan Cameron Reviewed-by: Gwendal Grignou Date: Fri, 9 Apr 2021 18:34:56 +0300 Subject: ata: Replace inclusion of kernel.h by bits.h in the header ata.h uses BIT() macro, hence bits.h must be included. Otherwise there is no need to have kernel.h included, I do not see any direct users of it in ata.h. Hence replace inclusion of kernel.h. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20210409153456.87798-1-andriy.shevchenko@linux.intel.com Signed-off-by: Jens Axboe --- include/linux/ata.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index 6e67aded28f8..1b44f40c7700 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -13,7 +13,7 @@ #ifndef __LINUX_ATA_H__ #define __LINUX_ATA_H__ -#include +#include #include #include #include -- cgit v1.2.3 From c2b1063e8feb2115537addce10f36c0c82d11d9b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 2 Apr 2021 08:23:25 +0200 Subject: genirq: Add a IRQF_NO_DEBUG flag MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The whole call to note_interrupt() can be avoided or return early when interrupts would be marked accordingly. For IPI handlers which always return HANDLED the whole procedure is pretty pointless to begin with. Add a IRQF_NO_DEBUG flag and mark the interrupt accordingly if supplied when the interrupt is requested. When noirqdebug is set on the kernel commandline, then the interrupt is marked unconditionally so that there is only one condition in the hotpath to evaluate. [ clg: Add changelog ] Signed-off-by: Thomas Gleixner Signed-off-by: Cédric Le Goater Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/7a8ad02f-63a8-c1aa-fdd1-39d973593d02@kaod.org --- include/linux/interrupt.h | 3 +++ include/linux/irq.h | 2 ++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 4777850a6dc7..a52109c3f3a4 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -64,6 +64,8 @@ * IRQF_NO_AUTOEN - Don't enable IRQ or NMI automatically when users request it. * Users will enable it explicitly by enable_irq() or enable_nmi() * later. + * IRQF_NO_DEBUG - Exclude from runnaway detection for IPI and similar handlers, + * depends on IRQF_PERCPU. */ #define IRQF_SHARED 0x00000080 #define IRQF_PROBE_SHARED 0x00000100 @@ -78,6 +80,7 @@ #define IRQF_EARLY_RESUME 0x00020000 #define IRQF_COND_SUSPEND 0x00040000 #define IRQF_NO_AUTOEN 0x00080000 +#define IRQF_NO_DEBUG 0x00100000 #define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD) diff --git a/include/linux/irq.h b/include/linux/irq.h index 31b347c9f8dd..8e9a9ae471a6 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -72,6 +72,7 @@ enum irqchip_irq_state; * mechanism and from core side polling. * IRQ_DISABLE_UNLAZY - Disable lazy irq disable * IRQ_HIDDEN - Don't show up in /proc/interrupts + * IRQ_NO_DEBUG - Exclude from note_interrupt() debugging */ enum { IRQ_TYPE_NONE = 0x00000000, @@ -99,6 +100,7 @@ enum { IRQ_IS_POLLED = (1 << 18), IRQ_DISABLE_UNLAZY = (1 << 19), IRQ_HIDDEN = (1 << 20), + IRQ_NO_DEBUG = (1 << 21), }; #define IRQF_MODIFY_MASK \ -- cgit v1.2.3 From 7617af3d1a5e0938eb1fd2742f19bcea772c7f8d Mon Sep 17 00:00:00 2001 From: Michael Sit Wei Hong Date: Mon, 17 May 2021 17:43:31 +0800 Subject: net: pcs: Introducing support for DWC xpcs Energy Efficient Ethernet Add DWC xpcs EEE support callbacks.The callback function is used to set EEE registers on xpcs. xpcs transparent mode is enabled to allow PHY to detect MAC EEE status. Signed-off-by: Michael Sit Wei Hong Signed-off-by: David S. Miller --- include/linux/pcs/pcs-xpcs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index 2cb5188a7ef1..5938ced805f4 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -32,6 +32,8 @@ struct mdio_xpcs_ops { int (*link_up)(struct mdio_xpcs_args *xpcs, int speed, phy_interface_t interface); int (*probe)(struct mdio_xpcs_args *xpcs, phy_interface_t interface); + int (*config_eee)(struct mdio_xpcs_args *xpcs, int mult_fact_100ns, + int enable); }; #if IS_ENABLED(CONFIG_PCS_XPCS) -- cgit v1.2.3 From e80fe71b3ffe1ec31c4a9be60170f897bbdf1b92 Mon Sep 17 00:00:00 2001 From: Michael Sit Wei Hong Date: Mon, 17 May 2021 17:43:32 +0800 Subject: net: stmmac: Add callbacks for DWC xpcs Energy Efficient Ethernet Link xpcs callback functions for MAC to configure the xpcs EEE feature. The clk_eee frequency is used to calculate the MULT_FACT_100NS. This is to adjust the clock tic closer to 100ns. Signed-off-by: Michael Sit Wei Hong Signed-off-by: David S. Miller --- include/linux/stmmac.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 0db36360ef21..e14a12df381b 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -223,6 +223,7 @@ struct plat_stmmacenet_data { struct clk *clk_ptp_ref; unsigned int clk_ptp_rate; unsigned int clk_ref_rate; + unsigned int mult_fact_100ns; s32 ptp_max_adj; struct reset_control *stmmac_rst; struct stmmac_axi *axi; -- cgit v1.2.3 From 00b89fe0197f0c55a045775c11553c0cdb7082fe Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Mon, 10 May 2021 16:10:23 +0100 Subject: sched: Make the idle task quack like a per-CPU kthread For all intents and purposes, the idle task is a per-CPU kthread. It isn't created via the same route as other pcpu kthreads however, and as a result it is missing a few bells and whistles: it fails kthread_is_per_cpu() and it doesn't have PF_NO_SETAFFINITY set. Fix the former by giving the idle task a kthread struct along with the KTHREAD_IS_PER_CPU flag. This requires some extra iffery as init_idle() call be called more than once on the same idle task. Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210510151024.2448573-2-valentin.schneider@arm.com --- include/linux/kthread.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 2484ed97e72f..d9133d6db308 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -33,6 +33,8 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), unsigned int cpu, const char *namefmt); +void set_kthread_struct(struct task_struct *p); + void kthread_set_per_cpu(struct task_struct *k, int cpu); bool kthread_is_per_cpu(struct task_struct *k); -- cgit v1.2.3 From 8083d6b812cac5e38db9c707b41cd478beed4a0c Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 17 May 2021 17:03:49 +0300 Subject: spi: pxa2xx: Fix style of and typos in the comments and messages Fix style of the comments and messages along with typos in them. While at it, update Intel Copyright year. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20210517140351.901-8-andriy.shevchenko@linux.intel.com Signed-off-by: Mark Brown --- include/linux/pxa2xx_ssp.h | 9 +++++---- include/linux/spi/pxa2xx_spi.h | 12 +++++++++--- 2 files changed, 14 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index 2b21bc1f3c73..a3fec2de512f 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (C) 2003 Russell King, All Rights Reserved. + * Copyright (C) 2003 Russell King, All Rights Reserved. * * This driver supports the following PXA CPU/SSP ports:- * @@ -59,7 +59,7 @@ struct device_node; /* PXA27x, PXA3xx */ #define SSCR0_EDSS BIT(20) /* Extended data size select */ #define SSCR0_NCS BIT(21) /* Network clock select */ -#define SSCR0_RIM BIT(22) /* Receive FIFO overrrun interrupt mask */ +#define SSCR0_RIM BIT(22) /* Receive FIFO overrun interrupt mask */ #define SSCR0_TUM BIT(23) /* Transmit FIFO underrun interrupt mask */ #define SSCR0_FRDC GENMASK(26, 24) /* Frame rate divider control (mask) */ #define SSCR0_SlotsPerFrm(x) (((x) - 1) << 24) /* Time slots per frame [1..8] */ @@ -126,7 +126,7 @@ struct device_node; #define QUARK_X1000_SSCR1_EFWR BIT(16) /* Enable FIFO Write/Read */ #define QUARK_X1000_SSCR1_STRF BIT(17) /* Select FIFO or EFWR */ -/* extra bits in PXA255, PXA26x and PXA27x SSP ports */ +/* Extra bits in PXA255, PXA26x and PXA27x SSP ports */ #define SSCR0_TISSP (1 << 4) /* TI Sync Serial Protocol */ #define SSCR0_PSP (3 << 4) /* PSP - Programmable Serial Protocol */ @@ -222,7 +222,8 @@ enum pxa_ssp_type { CE4100_SSP, MRFLD_SSP, QUARK_X1000_SSP, - LPSS_LPT_SSP, /* Keep LPSS types sorted with lpss_platforms[] */ + /* Keep LPSS types sorted with lpss_platforms[] */ + LPSS_LPT_SSP, LPSS_BYT_SSP, LPSS_BSW_SSP, LPSS_SPT_SSP, diff --git a/include/linux/spi/pxa2xx_spi.h b/include/linux/spi/pxa2xx_spi.h index 12ef04d0896d..eaab121ee575 100644 --- a/include/linux/spi/pxa2xx_spi.h +++ b/include/linux/spi/pxa2xx_spi.h @@ -14,7 +14,10 @@ struct dma_chan; -/* device.platform_data for SSP controller devices */ +/* + * The platform data for SSP controller devices + * (resides in device.platform_data). + */ struct pxa2xx_spi_controller { u16 num_chipselect; u8 enable_dma; @@ -30,8 +33,11 @@ struct pxa2xx_spi_controller { struct ssp_device ssp; }; -/* spi_board_info.controller_data for SPI slave devices, - * copied to spi_device.platform_data ... mostly for dma tuning +/* + * The controller specific data for SPI slave devices + * (resides in spi_board_info.controller_data), + * copied to spi_device.platform_data ... mostly for + * DMA tuning. */ struct pxa2xx_spi_chip { u8 tx_threshold; -- cgit v1.2.3 From c49661aa6f7097047b7e86ad37b1cf308a7a8d4f Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Sun, 16 May 2021 19:23:48 -0700 Subject: skmsg: Remove unused parameters of sk_msg_wait_data() 'err' and 'flags' are not used, we can just get rid of them. Signed-off-by: Cong Wang Signed-off-by: Daniel Borkmann Acked-by: Song Liu Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20210517022348.50555-1-xiyou.wangcong@gmail.com --- include/linux/skmsg.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index aba0f0f429be..fcaa9a7996c8 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -126,8 +126,7 @@ int sk_msg_zerocopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes); int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes); -int sk_msg_wait_data(struct sock *sk, struct sk_psock *psock, int flags, - long timeo, int *err); +int sk_msg_wait_data(struct sock *sk, struct sk_psock *psock, long timeo); int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags); -- cgit v1.2.3 From 86544c3de6a2185409c5a3d02f674ea223a14217 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 18 May 2021 20:49:24 +0300 Subject: net: mdio: provide shim implementation of devm_of_mdiobus_register Similar to the way in which of_mdiobus_register() has a fallback to the non-DT based mdiobus_register() when CONFIG_OF is not set, we can create a shim for the device-managed devm_of_mdiobus_register() which calls devm_mdiobus_register() and discards the struct device_node *. In particular, this solves a build issue with the qca8k DSA driver which uses devm_of_mdiobus_register and can be compiled without CONFIG_OF. Reported-by: Randy Dunlap Signed-off-by: Vladimir Oltean Acked-by: Randy Dunlap # build-tested Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/of_mdio.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index 2b05e7f7c238..da633d34ab86 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -72,6 +72,13 @@ static inline int of_mdiobus_register(struct mii_bus *mdio, struct device_node * return mdiobus_register(mdio); } +static inline int devm_of_mdiobus_register(struct device *dev, + struct mii_bus *mdio, + struct device_node *np) +{ + return devm_mdiobus_register(dev, mdio); +} + static inline struct mdio_device *of_mdio_find_device(struct device_node *np) { return NULL; -- cgit v1.2.3 From 79a7f8bdb159d9914b58740f3d31d602a6e4aca8 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 13 May 2021 17:36:03 -0700 Subject: bpf: Introduce bpf_sys_bpf() helper and program type. Add placeholders for bpf_sys_bpf() helper and new program type. Make sure to check that expected_attach_type is zero for future extensibility. Allow tracing helper functions to be used in this program type, since they will only execute from user context via bpf_prog_test_run. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210514003623.28033-2-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 10 ++++++++++ include/linux/bpf_types.h | 2 ++ 2 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 02b02cb29ce2..04a2bf41ae72 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1826,6 +1826,9 @@ static inline bool bpf_map_is_dev_bound(struct bpf_map *map) struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr); void bpf_map_offload_map_free(struct bpf_map *map); +int bpf_prog_test_run_syscall(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr); #else static inline int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) @@ -1851,6 +1854,13 @@ static inline struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr) static inline void bpf_map_offload_map_free(struct bpf_map *map) { } + +static inline int bpf_prog_test_run_syscall(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr) +{ + return -ENOTSUPP; +} #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index f883f01a5061..a9db1eae6796 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -77,6 +77,8 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_LSM, lsm, void *, void *) #endif /* CONFIG_BPF_LSM */ #endif +BPF_PROG_TYPE(BPF_PROG_TYPE_SYSCALL, bpf_syscall, + void *, void *) BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops) -- cgit v1.2.3 From cdf7fb0a9f3d36b279590ac41e61c6b655db0d4a Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 13 May 2021 17:36:04 -0700 Subject: bpf: Introduce bpfptr_t user/kernel pointer. Similar to sockptr_t introduce bpfptr_t with few additions: make_bpfptr() creates new user/kernel pointer in the same address space as existing user/kernel pointer. bpfptr_add() advances the user/kernel pointer. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210514003623.28033-3-alexei.starovoitov@gmail.com --- include/linux/bpfptr.h | 75 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 75 insertions(+) create mode 100644 include/linux/bpfptr.h (limited to 'include/linux') diff --git a/include/linux/bpfptr.h b/include/linux/bpfptr.h new file mode 100644 index 000000000000..5cdeab497cb3 --- /dev/null +++ b/include/linux/bpfptr.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* A pointer that can point to either kernel or userspace memory. */ +#ifndef _LINUX_BPFPTR_H +#define _LINUX_BPFPTR_H + +#include + +typedef sockptr_t bpfptr_t; + +static inline bool bpfptr_is_kernel(bpfptr_t bpfptr) +{ + return bpfptr.is_kernel; +} + +static inline bpfptr_t KERNEL_BPFPTR(void *p) +{ + return (bpfptr_t) { .kernel = p, .is_kernel = true }; +} + +static inline bpfptr_t USER_BPFPTR(void __user *p) +{ + return (bpfptr_t) { .user = p }; +} + +static inline bpfptr_t make_bpfptr(u64 addr, bool is_kernel) +{ + if (is_kernel) + return KERNEL_BPFPTR((void*) (uintptr_t) addr); + else + return USER_BPFPTR(u64_to_user_ptr(addr)); +} + +static inline bool bpfptr_is_null(bpfptr_t bpfptr) +{ + if (bpfptr_is_kernel(bpfptr)) + return !bpfptr.kernel; + return !bpfptr.user; +} + +static inline void bpfptr_add(bpfptr_t *bpfptr, size_t val) +{ + if (bpfptr_is_kernel(*bpfptr)) + bpfptr->kernel += val; + else + bpfptr->user += val; +} + +static inline int copy_from_bpfptr_offset(void *dst, bpfptr_t src, + size_t offset, size_t size) +{ + return copy_from_sockptr_offset(dst, (sockptr_t) src, offset, size); +} + +static inline int copy_from_bpfptr(void *dst, bpfptr_t src, size_t size) +{ + return copy_from_bpfptr_offset(dst, src, 0, size); +} + +static inline int copy_to_bpfptr_offset(bpfptr_t dst, size_t offset, + const void *src, size_t size) +{ + return copy_to_sockptr_offset((sockptr_t) dst, offset, src, size); +} + +static inline void *memdup_bpfptr(bpfptr_t src, size_t len) +{ + return memdup_sockptr((sockptr_t) src, len); +} + +static inline long strncpy_from_bpfptr(char *dst, bpfptr_t src, size_t count) +{ + return strncpy_from_sockptr(dst, (sockptr_t) src, count); +} + +#endif /* _LINUX_BPFPTR_H */ -- cgit v1.2.3 From af2ac3e13e45752af03c8a933f9b6e18841b128b Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 13 May 2021 17:36:05 -0700 Subject: bpf: Prepare bpf syscall to be used from kernel and user space. With the help from bpfptr_t prepare relevant bpf syscall commands to be used from kernel and user space. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210514003623.28033-4-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 04a2bf41ae72..7fd53380c981 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -22,6 +22,7 @@ #include #include #include +#include struct bpf_verifier_env; struct bpf_verifier_log; @@ -1428,7 +1429,7 @@ struct bpf_iter__bpf_map_elem { int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info); void bpf_iter_unreg_target(const struct bpf_iter_reg *reg_info); bool bpf_iter_prog_supported(struct bpf_prog *prog); -int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); +int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr, struct bpf_prog *prog); int bpf_iter_new_fd(struct bpf_link *link); bool bpf_link_is_iter(struct bpf_link *link); struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop); @@ -1459,7 +1460,7 @@ int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file, int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value); int bpf_get_file_flag(int flags); -int bpf_check_uarg_tail_zero(void __user *uaddr, size_t expected_size, +int bpf_check_uarg_tail_zero(bpfptr_t uaddr, size_t expected_size, size_t actual_size); /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and @@ -1479,8 +1480,7 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) } /* verify correctness of eBPF program */ -int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, - union bpf_attr __user *uattr); +int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, bpfptr_t uattr); #ifndef CONFIG_BPF_JIT_ALWAYS_ON void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth); -- cgit v1.2.3 From c571bd752e91602f092823b2f1ee685a74d2726c Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 13 May 2021 17:36:08 -0700 Subject: bpf: Make btf_load command to be bpfptr_t compatible. Similar to prog_load make btf_load command to be availble to bpf_prog_type_syscall program. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210514003623.28033-7-alexei.starovoitov@gmail.com --- include/linux/btf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h index 3bac66e0183a..94a0c976c90f 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -21,7 +21,7 @@ extern const struct file_operations btf_fops; void btf_get(struct btf *btf); void btf_put(struct btf *btf); -int btf_new_fd(const union bpf_attr *attr); +int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr); struct btf *btf_get_by_fd(int fd); int btf_get_info_by_fd(const struct btf *btf, const union bpf_attr *attr, -- cgit v1.2.3 From 387544bfa291a22383d60b40f887360e2b931ec6 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 13 May 2021 17:36:10 -0700 Subject: bpf: Introduce fd_idx Typical program loading sequence involves creating bpf maps and applying map FDs into bpf instructions in various places in the bpf program. This job is done by libbpf that is using compiler generated ELF relocations to patch certain instruction after maps are created and BTFs are loaded. The goal of fd_idx is to allow bpf instructions to stay immutable after compilation. At load time the libbpf would still create maps as usual, but it wouldn't need to patch instructions. It would store map_fds into __u32 fd_array[] and would pass that pointer to sys_bpf(BPF_PROG_LOAD). Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210514003623.28033-9-alexei.starovoitov@gmail.com --- include/linux/bpf_verifier.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index d4632aa3ca50..e774ecc1cd1f 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -450,6 +450,7 @@ struct bpf_verifier_env { u32 peak_states; /* longest register parentage chain walked for liveness marking */ u32 longest_mark_read_walk; + bpfptr_t fd_array; }; __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log, -- cgit v1.2.3 From 3d78417b60fba249cc555468cb72d96f5cde2964 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 13 May 2021 17:36:11 -0700 Subject: bpf: Add bpf_btf_find_by_name_kind() helper. Add new helper: long bpf_btf_find_by_name_kind(char *name, int name_sz, u32 kind, int flags) Description Find BTF type with given name and kind in vmlinux BTF or in module's BTFs. Return Returns btf_id and btf_obj_fd in lower and upper 32 bits. It will be used by loader program to find btf_id to attach the program to and to find btf_ids of ksyms. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210514003623.28033-10-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 7fd53380c981..9dc44ba97584 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1974,6 +1974,7 @@ extern const struct bpf_func_proto bpf_get_socket_ptr_cookie_proto; extern const struct bpf_func_proto bpf_task_storage_get_proto; extern const struct bpf_func_proto bpf_task_storage_delete_proto; extern const struct bpf_func_proto bpf_for_each_map_elem_proto; +extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); -- cgit v1.2.3 From 94cc7aeaf6c0cff0b8aeb7cb3579cee46b923560 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 5 May 2021 11:19:16 +0200 Subject: USB: serial: make usb_serial_driver::write_room return uint Line disciplines expect a positive value or zero returned from tty->ops->write_room (invoked by tty_write_room). Both of them are being updated to return an unsigned int. Switch also usb_serial_driver::write_room and all its users. Signed-off-by: Jiri Slaby [ johan: amend commit message, drop unrelated comment change ] Signed-off-by: Johan Hovold --- include/linux/usb/serial.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index 8c63fa9bfc74..6472d1f7b028 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -276,7 +276,7 @@ struct usb_serial_driver { int (*write)(struct tty_struct *tty, struct usb_serial_port *port, const unsigned char *buf, int count); /* Called only by the tty layer */ - int (*write_room)(struct tty_struct *tty); + unsigned int (*write_room)(struct tty_struct *tty); int (*ioctl)(struct tty_struct *tty, unsigned int cmd, unsigned long arg); void (*get_serial)(struct tty_struct *tty, struct serial_struct *ss); @@ -347,7 +347,7 @@ int usb_serial_generic_write(struct tty_struct *tty, struct usb_serial_port *por const unsigned char *buf, int count); void usb_serial_generic_close(struct usb_serial_port *port); int usb_serial_generic_resume(struct usb_serial *serial); -int usb_serial_generic_write_room(struct tty_struct *tty); +unsigned int usb_serial_generic_write_room(struct tty_struct *tty); int usb_serial_generic_chars_in_buffer(struct tty_struct *tty); void usb_serial_generic_wait_until_sent(struct tty_struct *tty, long timeout); void usb_serial_generic_read_bulk_callback(struct urb *urb); -- cgit v1.2.3 From 155591d3ceeec2cd6a50b40278e2014c45f6b5f6 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 5 May 2021 11:19:20 +0200 Subject: USB: serial: make usb_serial_driver::chars_in_buffer return uint tty_operations::chars_in_buffer is being switched to return uint. Do the same for usb_serial_driver's chars_in_buffer. Signed-off-by: Jiri Slaby [ johan: amend commit message ] Signed-off-by: Johan Hovold --- include/linux/usb/serial.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index 6472d1f7b028..95c729446e27 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -284,7 +284,7 @@ struct usb_serial_driver { void (*set_termios)(struct tty_struct *tty, struct usb_serial_port *port, struct ktermios *old); void (*break_ctl)(struct tty_struct *tty, int break_state); - int (*chars_in_buffer)(struct tty_struct *tty); + unsigned int (*chars_in_buffer)(struct tty_struct *tty); void (*wait_until_sent)(struct tty_struct *tty, long timeout); bool (*tx_empty)(struct usb_serial_port *port); void (*throttle)(struct tty_struct *tty); @@ -348,7 +348,7 @@ int usb_serial_generic_write(struct tty_struct *tty, struct usb_serial_port *por void usb_serial_generic_close(struct usb_serial_port *port); int usb_serial_generic_resume(struct usb_serial *serial); unsigned int usb_serial_generic_write_room(struct tty_struct *tty); -int usb_serial_generic_chars_in_buffer(struct tty_struct *tty); +unsigned int usb_serial_generic_chars_in_buffer(struct tty_struct *tty); void usb_serial_generic_wait_until_sent(struct tty_struct *tty, long timeout); void usb_serial_generic_read_bulk_callback(struct urb *urb); void usb_serial_generic_write_bulk_callback(struct urb *urb); -- cgit v1.2.3 From 4d80d6ca5d77fde9880da8466e5b64f250e5bf82 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 18 May 2021 11:17:26 +0200 Subject: genirq: Export affinity setter for modules Perf modules abuse irq_set_affinity_hint() to set the affinity of system PMU interrupts just because irq_set_affinity() was not exported. The fact that irq_set_affinity_hint() actually sets the affinity is a non-documented side effect and the name is clearly saying it's a hint. To clean this up, export the real affinity setter. Signed-off-by: Thomas Gleixner Acked-by: Mark Rutland Link: https://lore.kernel.org/r/20210518093117.968251441@linutronix.de --- include/linux/interrupt.h | 35 ++--------------------------------- 1 file changed, 2 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 4777850a6dc7..35a374241515 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -319,39 +319,8 @@ struct irq_affinity_desc { extern cpumask_var_t irq_default_affinity; -/* Internal implementation. Use the helpers below */ -extern int __irq_set_affinity(unsigned int irq, const struct cpumask *cpumask, - bool force); - -/** - * irq_set_affinity - Set the irq affinity of a given irq - * @irq: Interrupt to set affinity - * @cpumask: cpumask - * - * Fails if cpumask does not contain an online CPU - */ -static inline int -irq_set_affinity(unsigned int irq, const struct cpumask *cpumask) -{ - return __irq_set_affinity(irq, cpumask, false); -} - -/** - * irq_force_affinity - Force the irq affinity of a given irq - * @irq: Interrupt to set affinity - * @cpumask: cpumask - * - * Same as irq_set_affinity, but without checking the mask against - * online cpus. - * - * Solely for low level cpu hotplug code, where we need to make per - * cpu interrupts affine before the cpu becomes online. - */ -static inline int -irq_force_affinity(unsigned int irq, const struct cpumask *cpumask) -{ - return __irq_set_affinity(irq, cpumask, true); -} +extern int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask); +extern int irq_force_affinity(unsigned int irq, const struct cpumask *cpumask); extern int irq_can_set_affinity(unsigned int irq); extern int irq_select_affinity(unsigned int irq); -- cgit v1.2.3 From 2beb4a53fc3f1081cedc1c1a198c7f56cc4fc60c Mon Sep 17 00:00:00 2001 From: "Chang S. Bae" Date: Tue, 18 May 2021 13:03:19 -0700 Subject: x86/signal: Detect and prevent an alternate signal stack overflow The kernel pushes context on to the userspace stack to prepare for the user's signal handler. When the user has supplied an alternate signal stack, via sigaltstack(2), it is easy for the kernel to verify that the stack size is sufficient for the current hardware context. Check if writing the hardware context to the alternate stack will exceed it's size. If yes, then instead of corrupting user-data and proceeding with the original signal handler, an immediate SIGSEGV signal is delivered. Refactor the stack pointer check code from on_sig_stack() and use the new helper. While the kernel allows new source code to discover and use a sufficient alternate signal stack size, this check is still necessary to protect binaries with insufficient alternate signal stack size from data corruption. Fixes: c2bc11f10a39 ("x86, AVX-512: Enable AVX-512 States Context Switch") Reported-by: Florian Weimer Suggested-by: Jann Horn Suggested-by: Andy Lutomirski Signed-off-by: Chang S. Bae Signed-off-by: Borislav Petkov Reviewed-by: Len Brown Acked-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20210518200320.17239-6-chang.seok.bae@intel.com Link: https://bugzilla.kernel.org/show_bug.cgi?id=153531 --- include/linux/sched/signal.h | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 3f6a0fcaa10c..ae60f838ebb9 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -537,6 +537,17 @@ static inline int kill_cad_pid(int sig, int priv) #define SEND_SIG_NOINFO ((struct kernel_siginfo *) 0) #define SEND_SIG_PRIV ((struct kernel_siginfo *) 1) +static inline int __on_sig_stack(unsigned long sp) +{ +#ifdef CONFIG_STACK_GROWSUP + return sp >= current->sas_ss_sp && + sp - current->sas_ss_sp < current->sas_ss_size; +#else + return sp > current->sas_ss_sp && + sp - current->sas_ss_sp <= current->sas_ss_size; +#endif +} + /* * True if we are on the alternate signal stack. */ @@ -554,13 +565,7 @@ static inline int on_sig_stack(unsigned long sp) if (current->sas_ss_flags & SS_AUTODISARM) return 0; -#ifdef CONFIG_STACK_GROWSUP - return sp >= current->sas_ss_sp && - sp - current->sas_ss_sp < current->sas_ss_size; -#else - return sp > current->sas_ss_sp && - sp - current->sas_ss_sp <= current->sas_ss_size; -#endif + return __on_sig_stack(sp); } static inline int sas_ss_flags(unsigned long sp) -- cgit v1.2.3 From c06a40e9513d246bdeacd290f2357bb99251dc9a Mon Sep 17 00:00:00 2001 From: Luca Ceresoli Date: Fri, 19 Feb 2021 23:39:08 +0100 Subject: mfd: lp87565: Fix typo in define names "GOIO" should be "GPIO" here. Signed-off-by: Luca Ceresoli Signed-off-by: Lee Jones --- include/linux/mfd/lp87565.h | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/lp87565.h b/include/linux/mfd/lp87565.h index 5640e6088fe6..a8799ae50dcf 100644 --- a/include/linux/mfd/lp87565.h +++ b/include/linux/mfd/lp87565.h @@ -222,20 +222,20 @@ enum lp87565_device_type { #define LP87565_GPIO2_SEL BIT(1) #define LP87565_GPIO1_SEL BIT(0) -#define LP87565_GOIO3_OD BIT(6) -#define LP87565_GOIO2_OD BIT(5) -#define LP87565_GOIO1_OD BIT(4) -#define LP87565_GOIO3_DIR BIT(2) -#define LP87565_GOIO2_DIR BIT(1) -#define LP87565_GOIO1_DIR BIT(0) - -#define LP87565_GOIO3_IN BIT(2) -#define LP87565_GOIO2_IN BIT(1) -#define LP87565_GOIO1_IN BIT(0) - -#define LP87565_GOIO3_OUT BIT(2) -#define LP87565_GOIO2_OUT BIT(1) -#define LP87565_GOIO1_OUT BIT(0) +#define LP87565_GPIO3_OD BIT(6) +#define LP87565_GPIO2_OD BIT(5) +#define LP87565_GPIO1_OD BIT(4) +#define LP87565_GPIO3_DIR BIT(2) +#define LP87565_GPIO2_DIR BIT(1) +#define LP87565_GPIO1_DIR BIT(0) + +#define LP87565_GPIO3_IN BIT(2) +#define LP87565_GPIO2_IN BIT(1) +#define LP87565_GPIO1_IN BIT(0) + +#define LP87565_GPIO3_OUT BIT(2) +#define LP87565_GPIO2_OUT BIT(1) +#define LP87565_GPIO1_OUT BIT(0) enum LP87565_regulator_id { /* BUCK's */ -- cgit v1.2.3 From 5258f7eed42f4565d065726fd82d3430dd618a68 Mon Sep 17 00:00:00 2001 From: Luca Ceresoli Date: Fri, 19 Feb 2021 23:39:10 +0100 Subject: mfd: lp87565: Move LP87565_regulator_id to .c file This enum is used only internally to the regulator driver for buck indexes. Signed-off-by: Luca Ceresoli Signed-off-by: Lee Jones --- include/linux/mfd/lp87565.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/lp87565.h b/include/linux/mfd/lp87565.h index a8799ae50dcf..94cb581af34b 100644 --- a/include/linux/mfd/lp87565.h +++ b/include/linux/mfd/lp87565.h @@ -237,17 +237,6 @@ enum lp87565_device_type { #define LP87565_GPIO2_OUT BIT(1) #define LP87565_GPIO1_OUT BIT(0) -enum LP87565_regulator_id { - /* BUCK's */ - LP87565_BUCK_0, - LP87565_BUCK_1, - LP87565_BUCK_2, - LP87565_BUCK_3, - LP87565_BUCK_10, - LP87565_BUCK_23, - LP87565_BUCK_3210, -}; - /** * struct LP87565 - state holder for the LP87565 driver * @dev: struct device pointer for MFD device -- cgit v1.2.3 From 1f89d2fe16072a74b34bdb895160910091427891 Mon Sep 17 00:00:00 2001 From: Sander Vanheule Date: Mon, 17 May 2021 21:28:03 +0200 Subject: regmap: Add MDIO bus support Basic support for MDIO bus access. Support only includes clause-22 register access, with 5-bit addresses, and 16-bit wide registers. Signed-off-by: Sander Vanheule Link: https://lore.kernel.org/r/63b99a2fec2c4ea3c461d59d451af8d675ecf312.1621279162.git.sander@svanheule.net Signed-off-by: Mark Brown --- include/linux/regmap.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index f87a11a5cc4a..e97dd05f7cdb 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -27,6 +27,7 @@ struct device_node; struct i2c_client; struct i3c_device; struct irq_domain; +struct mdio_device; struct slim_device; struct spi_device; struct spmi_device; @@ -538,6 +539,10 @@ struct regmap *__regmap_init_i2c(struct i2c_client *i2c, const struct regmap_config *config, struct lock_class_key *lock_key, const char *lock_name); +struct regmap *__regmap_init_mdio(struct mdio_device *mdio_dev, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); struct regmap *__regmap_init_sccb(struct i2c_client *i2c, const struct regmap_config *config, struct lock_class_key *lock_key, @@ -594,6 +599,10 @@ struct regmap *__devm_regmap_init_i2c(struct i2c_client *i2c, const struct regmap_config *config, struct lock_class_key *lock_key, const char *lock_name); +struct regmap *__devm_regmap_init_mdio(struct mdio_device *mdio_dev, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); struct regmap *__devm_regmap_init_sccb(struct i2c_client *i2c, const struct regmap_config *config, struct lock_class_key *lock_key, @@ -697,6 +706,19 @@ int regmap_attach_dev(struct device *dev, struct regmap *map, __regmap_lockdep_wrapper(__regmap_init_i2c, #config, \ i2c, config) +/** + * regmap_init_mdio() - Initialise register map + * + * @mdio_dev: Device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer to + * a struct regmap. + */ +#define regmap_init_mdio(mdio_dev, config) \ + __regmap_lockdep_wrapper(__regmap_init_mdio, #config, \ + mdio_dev, config) + /** * regmap_init_sccb() - Initialise register map * @@ -888,6 +910,20 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg); __regmap_lockdep_wrapper(__devm_regmap_init_i2c, #config, \ i2c, config) +/** + * devm_regmap_init_mdio() - Initialise managed register map + * + * @mdio_dev: Device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer + * to a struct regmap. The regmap will be automatically freed by the + * device management code. + */ +#define devm_regmap_init_mdio(mdio_dev, config) \ + __regmap_lockdep_wrapper(__devm_regmap_init_mdio, #config, \ + mdio_dev, config) + /** * devm_regmap_init_sccb() - Initialise managed register map * -- cgit v1.2.3 From f1069a8756b9e9f6c055e709740d2d66650f0fb0 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Wed, 19 May 2021 15:03:08 +0200 Subject: compiler.h: Avoid using inline asm operand modifiers The expansion of annotate_reachable/annotate_unreachable on s390 will result in a compiler error if the __COUNTER__ value is high enough. For example with "i" (154) the "%c0" operand of annotate_reachable will be expanded to -102: -102: .pushsection .discard.reachable .long -102b - . .popsection This is a quirk of the gcc backend for s390, it interprets the %c0 as a signed byte value. Avoid using operand modifiers in this case by simply converting __COUNTER__ to string, with the same result, but in an arch assembler independent way. Signed-off-by: Vasily Gorbik Signed-off-by: Josh Poimboeuf Link: https://lore.kernel.org/r/patch-1.thread-1a26be.git-930d1b44844a.your-ad-here.call-01621428935-ext-2104@work.hours Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Miroslav Benes Cc: Borislav Petkov Cc: linux-kernel@vger.kernel.org --- include/linux/compiler.h | 22 ++++++++++++++-------- 1 file changed, 14 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index df5b405e6305..77047904cf70 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -115,18 +115,24 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, * The __COUNTER__ based labels are a hack to make each instance of the macros * unique, to convince GCC not to merge duplicate inline asm statements. */ -#define annotate_reachable() ({ \ - asm volatile("%c0:\n\t" \ +#define __stringify_label(n) #n + +#define __annotate_reachable(c) ({ \ + asm volatile(__stringify_label(c) ":\n\t" \ ".pushsection .discard.reachable\n\t" \ - ".long %c0b - .\n\t" \ - ".popsection\n\t" : : "i" (__COUNTER__)); \ + ".long " __stringify_label(c) "b - .\n\t" \ + ".popsection\n\t"); \ }) -#define annotate_unreachable() ({ \ - asm volatile("%c0:\n\t" \ +#define annotate_reachable() __annotate_reachable(__COUNTER__) + +#define __annotate_unreachable(c) ({ \ + asm volatile(__stringify_label(c) ":\n\t" \ ".pushsection .discard.unreachable\n\t" \ - ".long %c0b - .\n\t" \ - ".popsection\n\t" : : "i" (__COUNTER__)); \ + ".long " __stringify_label(c) "b - .\n\t" \ + ".popsection\n\t"); \ }) +#define annotate_unreachable() __annotate_unreachable(__COUNTER__) + #define ASM_UNREACHABLE \ "999:\n\t" \ ".pushsection .discard.unreachable\n\t" \ -- cgit v1.2.3 From c199f64ff93c48a45add92eee4456ffcabfc838e Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Wed, 19 May 2021 15:03:13 +0200 Subject: instrumentation.h: Avoid using inline asm operand modifiers The expansion of instrumentation_begin/instrumentation_end on s390 will result in a compiler error if the __COUNTER__ value is high enough. For example with "i" (154) the "%c0" operand of annotate_reachable will be expanded to -102: -102: .pushsection .discard.instr_begin .long -102b - . .popsection This is a quirk of the gcc backend for s390, it interprets the %c0 as a signed byte value. Avoid using operand modifiers in this case by simply converting __COUNTER__ to string, with the same result, but in an arch assembler independent way. Signed-off-by: Vasily Gorbik Signed-off-by: Josh Poimboeuf Link: https://lore.kernel.org/r/patch-2.thread-1a26be.git-1a26be80cb18.your-ad-here.call-01621428935-ext-2104@work.hours Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Miroslav Benes Cc: Borislav Petkov Cc: linux-kernel@vger.kernel.org --- include/linux/instrumentation.h | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/instrumentation.h b/include/linux/instrumentation.h index 93e2ad67fc10..fa2cd8c63dcc 100644 --- a/include/linux/instrumentation.h +++ b/include/linux/instrumentation.h @@ -4,13 +4,16 @@ #if defined(CONFIG_DEBUG_ENTRY) && defined(CONFIG_STACK_VALIDATION) +#include + /* Begin/end of an instrumentation safe region */ -#define instrumentation_begin() ({ \ - asm volatile("%c0: nop\n\t" \ +#define __instrumentation_begin(c) ({ \ + asm volatile(__stringify(c) ": nop\n\t" \ ".pushsection .discard.instr_begin\n\t" \ - ".long %c0b - .\n\t" \ - ".popsection\n\t" : : "i" (__COUNTER__)); \ + ".long " __stringify(c) "b - .\n\t" \ + ".popsection\n\t"); \ }) +#define instrumentation_begin() __instrumentation_begin(__COUNTER__) /* * Because instrumentation_{begin,end}() can nest, objtool validation considers @@ -43,12 +46,13 @@ * To avoid this, have _end() be a NOP instruction, this ensures it will be * part of the condition block and does not escape. */ -#define instrumentation_end() ({ \ - asm volatile("%c0: nop\n\t" \ +#define __instrumentation_end(c) ({ \ + asm volatile(__stringify(c) ": nop\n\t" \ ".pushsection .discard.instr_end\n\t" \ - ".long %c0b - .\n\t" \ - ".popsection\n\t" : : "i" (__COUNTER__)); \ + ".long " __stringify(c) "b - .\n\t" \ + ".popsection\n\t"); \ }) +#define instrumentation_end() __instrumentation_end(__COUNTER__) #else # define instrumentation_begin() do { } while(0) # define instrumentation_end() do { } while(0) -- cgit v1.2.3 From 57b55eeb755201832c2fc2df58818f64fc023fdb Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 10 May 2021 22:47:17 +0300 Subject: pinctrl: Keep enum pin_config_param ordered by name (part 2) It seems the ordering is by name. Keep it that way. Here updating the entire list (there were two more options not in order). Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20210510194717.12255-1-andriy.shevchenko@linux.intel.com Signed-off-by: Linus Walleij --- include/linux/pinctrl/pinconf-generic.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h index e18ab3d5908f..98ed5959ca9a 100644 --- a/include/linux/pinctrl/pinconf-generic.h +++ b/include/linux/pinctrl/pinconf-generic.h @@ -81,28 +81,28 @@ struct pinctrl_map; * passed in the argument on a custom form, else just use argument 1 * to indicate low power mode, argument 0 turns low power mode off. * @PIN_CONFIG_MODE_PWM: this will configure the pin for PWM + * @PIN_CONFIG_OUTPUT: this will configure the pin as an output and drive a + * value on the line. Use argument 1 to indicate high level, argument 0 to + * indicate low level. (Please see Documentation/driver-api/pinctl.rst, + * section "GPIO mode pitfalls" for a discussion around this parameter.) * @PIN_CONFIG_OUTPUT_ENABLE: this will enable the pin's output mode * without driving a value there. For most platforms this reduces to * enable the output buffers and then let the pin controller current * configuration (eg. the currently selected mux function) drive values on * the line. Use argument 1 to enable output mode, argument 0 to disable * it. - * @PIN_CONFIG_OUTPUT: this will configure the pin as an output and drive a - * value on the line. Use argument 1 to indicate high level, argument 0 to - * indicate low level. (Please see Documentation/driver-api/pinctl.rst, - * section "GPIO mode pitfalls" for a discussion around this parameter.) * @PIN_CONFIG_PERSIST_STATE: retain pin state across sleep or controller reset * @PIN_CONFIG_POWER_SOURCE: if the pin can select between different power * supplies, the argument to this parameter (on a custom format) tells * the driver which alternative power source to use. - * @PIN_CONFIG_SLEEP_HARDWARE_STATE: indicate this is sleep related state. - * @PIN_CONFIG_SLEW_RATE: if the pin can select slew rate, the argument to - * this parameter (on a custom format) tells the driver which alternative - * slew rate to use. * @PIN_CONFIG_SKEW_DELAY: if the pin has programmable skew rate (on inputs) * or latch delay (on outputs) this parameter (in a custom format) * specifies the clock skew or latch delay. It typically controls how * many double inverters are put in front of the line. + * @PIN_CONFIG_SLEEP_HARDWARE_STATE: indicate this is sleep related state. + * @PIN_CONFIG_SLEW_RATE: if the pin can select slew rate, the argument to + * this parameter (on a custom format) tells the driver which alternative + * slew rate to use. * @PIN_CONFIG_END: this is the last enumerator for pin configurations, if * you need to pass in custom configurations to the pin controller, use * PIN_CONFIG_END+1 as the base offset. @@ -127,13 +127,13 @@ enum pin_config_param { PIN_CONFIG_INPUT_SCHMITT_ENABLE, PIN_CONFIG_MODE_LOW_POWER, PIN_CONFIG_MODE_PWM, - PIN_CONFIG_OUTPUT_ENABLE, PIN_CONFIG_OUTPUT, + PIN_CONFIG_OUTPUT_ENABLE, PIN_CONFIG_PERSIST_STATE, PIN_CONFIG_POWER_SOURCE, + PIN_CONFIG_SKEW_DELAY, PIN_CONFIG_SLEEP_HARDWARE_STATE, PIN_CONFIG_SLEW_RATE, - PIN_CONFIG_SKEW_DELAY, PIN_CONFIG_END = 0x7F, PIN_CONFIG_MAX = 0xFF, }; -- cgit v1.2.3 From ded13b9cfd595adb478a1e371d2282048bba1df5 Mon Sep 17 00:00:00 2001 From: Andrey Grodzovsky Date: Wed, 12 May 2021 10:26:39 -0400 Subject: PCI: Add support for dev_groups to struct pci_driver This helps converting PCI drivers sysfs attributes to static. Analogous to' commit b71b283e3d6d ("USB: add support for dev_groups to struct usb_driver")' Signed-off-by: Andrey Grodzovsky Suggested-by: Greg Kroah-Hartman Acked-by: Bjorn Helgaas Link: https://patchwork.freedesktop.org/patch/msgid/20210512142648.666476-8-andrey.grodzovsky@amd.com --- include/linux/pci.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index c20211e59a57..4c048ed5bc55 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -862,6 +862,8 @@ struct module; * MSI-X vectors available for distribution to the VFs. * @err_handler: See Documentation/PCI/pci-error-recovery.rst * @groups: Sysfs attribute groups. + * @dev_groups: Attributes attached to the device that will be + * created once it is bound to the driver. * @driver: Driver model structure. * @dynids: List of dynamically added device IDs. */ @@ -879,6 +881,7 @@ struct pci_driver { u32 (*sriov_get_vf_total_msix)(struct pci_dev *pf); const struct pci_error_handlers *err_handler; const struct attribute_group **groups; + const struct attribute_group **dev_groups; struct device_driver driver; struct pci_dynids dynids; }; -- cgit v1.2.3 From b8be5db573b822920b0f6230498d900752bede17 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 19 May 2021 09:21:50 +0200 Subject: tty/serial: clean up uart_match_port * make parameters const (as they are only read) * return bool (as comparison results are returned) * add \n before final return Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210519072153.3859-1-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 7445c8fd88c0..52d7fb92a69d 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -408,7 +408,8 @@ 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); -int uart_match_port(struct uart_port *port1, struct uart_port *port2); +bool uart_match_port(const struct uart_port *port1, + const struct uart_port *port2); /* * Power Management -- cgit v1.2.3 From cd256b068f80e8b4a1eccd73527b67b3eb50f7ad Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 19 May 2021 09:21:51 +0200 Subject: tty/serial: make port of serial8250_register_8250_port const After the previous patch, we can make port passed to serial8250_find_match_or_unused const. And then we can make const also port of serial8250_register_8250_port. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210519072153.3859-2-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_8250.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 9e655055112d..5db211f43b29 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -146,7 +146,7 @@ static inline struct uart_8250_port *up_to_u8250p(struct uart_port *up) return container_of(up, struct uart_8250_port, port); } -int serial8250_register_8250_port(struct uart_8250_port *); +int serial8250_register_8250_port(const struct uart_8250_port *); void serial8250_unregister_port(int line); void serial8250_suspend_port(int line); void serial8250_resume_port(int line); -- cgit v1.2.3 From ee62c89cd45999ba4e09938bd01ec6d1a83ca6d6 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 19 May 2021 10:51:38 +0200 Subject: docs: update sysfs-platform_profile.rst reference The file name: Documentation/ABI/testing/sysfs-platform_profile.rst should be, instead: Documentation/userspace-api/sysfs-platform_profile.rst. Update its cross-reference accordingly. Fixes: a2ff95e018f1 ("ACPI: platform: Add platform profile support") Fixes: 8e0cbf356377 ("Documentation: Add documentation for new platform_profile sysfs attribute") Signed-off-by: Mauro Carvalho Chehab Reviewed-by: Hans de Goede Reviewed-by: Mark Pearson Link: https://lore.kernel.org/r/295089effd8353578b9725c61c0453d920978d72.1621413933.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/platform_profile.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_profile.h b/include/linux/platform_profile.h index a6329003aee7..e5cbb6841f3a 100644 --- a/include/linux/platform_profile.h +++ b/include/linux/platform_profile.h @@ -2,7 +2,7 @@ /* * Platform profile sysfs interface * - * See Documentation/ABI/testing/sysfs-platform_profile.rst for more + * See Documentation/userspace-api/sysfs-platform_profile.rst for more * information. */ -- cgit v1.2.3 From 4b0c9948a4c2f446a11bd592bd7d23f06ad75d8e Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 19 May 2021 10:51:42 +0200 Subject: docs: update pin-control.rst references Changeset 5513b411ea5b ("Documentation: rename pinctl to pin-control") renamed: Documentation/driver-api/pinctl.rst to: Documentation/driver-api/pin-control.rst. Update the cross-references accordingly. Fixes: 5513b411ea5b ("Documentation: rename pinctl to pin-control") Signed-off-by: Mauro Carvalho Chehab Acked-by: Charles Keepax Acked-by: Lee Jones Link: https://lore.kernel.org/r/46ac2e918c7c4a4b701d54870f167b78466ec578.1621413933.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/device.h | 2 +- include/linux/mfd/madera/pdata.h | 2 +- include/linux/pinctrl/pinconf-generic.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 38a2071cf776..d1183cfdc8fb 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -399,7 +399,7 @@ struct dev_links_info { * along with subsystem-level and driver-level callbacks. * @em_pd: device's energy model performance domain * @pins: For device pin management. - * See Documentation/driver-api/pinctl.rst for details. + * See Documentation/driver-api/pin-control.rst for details. * @msi_list: Hosts MSI descriptors * @msi_domain: The generic MSI domain this device is using. * @numa_node: NUMA node this device is close to. diff --git a/include/linux/mfd/madera/pdata.h b/include/linux/mfd/madera/pdata.h index 601cbbc10370..32e3470708ed 100644 --- a/include/linux/mfd/madera/pdata.h +++ b/include/linux/mfd/madera/pdata.h @@ -31,7 +31,7 @@ struct pinctrl_map; * @irq_flags: Mode for primary IRQ (defaults to active low) * @gpio_base: Base GPIO number * @gpio_configs: Array of GPIO configurations (See - * Documentation/driver-api/pinctl.rst) + * Documentation/driver-api/pin-control.rst) * @n_gpio_configs: Number of entries in gpio_configs * @gpsw: General purpose switch mode setting. Depends on the external * hardware connected to the switch. (See the SW1_MODE field diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h index e18ab3d5908f..5a96602a3316 100644 --- a/include/linux/pinctrl/pinconf-generic.h +++ b/include/linux/pinctrl/pinconf-generic.h @@ -89,7 +89,7 @@ struct pinctrl_map; * it. * @PIN_CONFIG_OUTPUT: this will configure the pin as an output and drive a * value on the line. Use argument 1 to indicate high level, argument 0 to - * indicate low level. (Please see Documentation/driver-api/pinctl.rst, + * indicate low level. (Please see Documentation/driver-api/pin-control.rst, * section "GPIO mode pitfalls" for a discussion around this parameter.) * @PIN_CONFIG_PERSIST_STATE: retain pin state across sleep or controller reset * @PIN_CONFIG_POWER_SOURCE: if the pin can select between different power -- cgit v1.2.3 From 2ade8fc65076095460e3ea1ca65a8f619d7d9a3a Mon Sep 17 00:00:00 2001 From: David Bartley Date: Thu, 20 May 2021 10:41:30 -0700 Subject: x86/amd_nb: Add AMD family 19h model 50h PCI ids This is required to support Zen3 APUs in k10temp. Signed-off-by: David Bartley Signed-off-by: Borislav Petkov Acked-by: Wei Huang Link: https://lkml.kernel.org/r/20210520174130.94954-1-andareed@gmail.com --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 4c3fa5293d76..5356ccf1c275 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -555,6 +555,7 @@ #define PCI_DEVICE_ID_AMD_17H_M60H_DF_F3 0x144b #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F3 0x1443 #define PCI_DEVICE_ID_AMD_19H_DF_F3 0x1653 +#define PCI_DEVICE_ID_AMD_19H_M50H_DF_F3 0x166d #define PCI_DEVICE_ID_AMD_CNB17H_F3 0x1703 #define PCI_DEVICE_ID_AMD_LANCE 0x2000 #define PCI_DEVICE_ID_AMD_LANCE_HOME 0x2001 -- cgit v1.2.3 From e1327a127703f94b8838d756cf6eaac506b329a7 Mon Sep 17 00:00:00 2001 From: Quentin Perret Date: Thu, 8 Apr 2021 18:01:05 +0000 Subject: export: Make CRCs robust to symbol trimming The CRC calculation done by genksyms is triggered when the parser hits EXPORT_SYMBOL*() macros. At this point, genksyms recursively expands the types, and uses that as the input for the CRC calculation. In the case of forward-declared structs, the type expands to 'UNKNOWN'. Next, the result of the expansion of each type is cached, and is re-used when/if the same type is seen again for another exported symbol in the file. Unfortunately, this can cause CRC 'stability' issues when a struct definition becomes visible in the middle of a C file. For example, let's assume code with the following pattern: struct foo; int bar(struct foo *arg) { /* Do work ... */ } EXPORT_SYMBOL_GPL(bar); /* This contains struct foo's definition */ #include "foo.h" int baz(struct foo *arg) { /* Do more work ... */ } EXPORT_SYMBOL_GPL(baz); Here, baz's CRC will be computed using the expansion of struct foo that was cached after bar's CRC calculation ('UNKOWN' here). But if EXPORT_SYMBOL_GPL(bar) is removed from the file (because of e.g. symbol trimming using CONFIG_TRIM_UNUSED_KSYMS), struct foo will be expanded late, during baz's CRC calculation, which now has visibility over the full struct definition, hence resulting in a different CRC for baz. This can cause annoying issues for distro kernel (such as the Android Generic Kernel Image) which use CONFIG_UNUSED_KSYMS_WHITELIST. Indeed, as per the above, adding a symbol to the whitelist can change the CRC of symbols that are already kept exported. As such, modules built against a kernel with a trimmed ABI may not load against the same kernel built with an extended whitelist, even though they are still strictly binary compatible. While rebuilding the modules would obviously solve the issue, I believe this classifies as an odd genksyms corner case, and it gets in the way of kernel updates in the GKI context. To work around the issue, make sure to keep issuing the __GENKSYMS_EXPORT_SYMBOL macros for all trimmed symbols, hence making the genksyms parsing insensitive to symbol trimming. Acked-by: Greg Kroah-Hartman Signed-off-by: Quentin Perret Link: https://lore.kernel.org/r/20210408180105.2496212-1-qperret@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/export.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/export.h b/include/linux/export.h index 6271a5d9c988..27d848712b90 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -140,7 +140,12 @@ struct kernel_symbol { #define ___cond_export_sym(sym, sec, ns, enabled) \ __cond_export_sym_##enabled(sym, sec, ns) #define __cond_export_sym_1(sym, sec, ns) ___EXPORT_SYMBOL(sym, sec, ns) + +#ifdef __GENKSYMS__ +#define __cond_export_sym_0(sym, sec, ns) __GENKSYMS_EXPORT_SYMBOL(sym) +#else #define __cond_export_sym_0(sym, sec, ns) /* nothing */ +#endif #else -- cgit v1.2.3 From e3ccfe1ad7d895487977ef64eda3441d16c9851a Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Fri, 14 May 2021 17:27:45 +0200 Subject: evm: Introduce evm_revalidate_status() When EVM_ALLOW_METADATA_WRITES is set, EVM allows any operation on metadata. Its main purpose is to allow users to freely set metadata when it is protected by a portable signature, until an HMAC key is loaded. However, callers of evm_verifyxattr() are not notified about metadata changes and continue to rely on the last status returned by the function. For example IMA, since it caches the appraisal result, will not call again evm_verifyxattr() until the appraisal flags are cleared, and will grant access to the file even if there was a metadata operation that made the portable signature invalid. This patch introduces evm_revalidate_status(), which callers of evm_verifyxattr() can use in their xattr hooks to determine whether re-validation is necessary and to do the proper actions. IMA calls it in its xattr hooks to reset the appraisal flags, so that the EVM status is re-evaluated after a metadata operation. Lastly, this patch also adds a call to evm_reset_status() in evm_inode_post_setattr() to invalidate the cached EVM status after a setattr operation. Signed-off-by: Roberto Sassu Signed-off-by: Mimi Zohar --- include/linux/evm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/evm.h b/include/linux/evm.h index 8302bc29bb35..39bb17a8236b 100644 --- a/include/linux/evm.h +++ b/include/linux/evm.h @@ -35,6 +35,7 @@ extern void evm_inode_post_removexattr(struct dentry *dentry, extern int evm_inode_init_security(struct inode *inode, const struct xattr *xattr_array, struct xattr *evm); +extern bool evm_revalidate_status(const char *xattr_name); #ifdef CONFIG_FS_POSIX_ACL extern int posix_xattr_acl(const char *xattrname); #else @@ -104,5 +105,10 @@ static inline int evm_inode_init_security(struct inode *inode, return 0; } +static inline bool evm_revalidate_status(const char *xattr_name) +{ + return false; +} + #endif /* CONFIG_EVM */ #endif /* LINUX_EVM_H */ -- cgit v1.2.3 From cdef685be5b4ae55c3959289e72d520402839c29 Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Fri, 14 May 2021 17:27:47 +0200 Subject: evm: Allow xattr/attr operations for portable signatures If files with portable signatures are copied from one location to another or are extracted from an archive, verification can temporarily fail until all xattrs/attrs are set in the destination. Only portable signatures may be moved or copied from one file to another, as they don't depend on system-specific information such as the inode generation. Instead portable signatures must include security.ima. Unlike other security.evm types, EVM portable signatures are also immutable. Thus, it wouldn't be a problem to allow xattr/attr operations when verification fails, as portable signatures will never be replaced with the HMAC on possibly corrupted xattrs/attrs. This patch first introduces a new integrity status called INTEGRITY_FAIL_IMMUTABLE, that allows callers of evm_verify_current_integrity() to detect that a portable signature didn't pass verification and then adds an exception in evm_protect_xattr() and evm_inode_setattr() for this status and returns 0 instead of -EPERM. Signed-off-by: Roberto Sassu Signed-off-by: Mimi Zohar --- include/linux/integrity.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/integrity.h b/include/linux/integrity.h index 2271939c5c31..2ea0f2f65ab6 100644 --- a/include/linux/integrity.h +++ b/include/linux/integrity.h @@ -13,6 +13,7 @@ enum integrity_status { INTEGRITY_PASS = 0, INTEGRITY_PASS_IMMUTABLE, INTEGRITY_FAIL, + INTEGRITY_FAIL_IMMUTABLE, INTEGRITY_NOLABEL, INTEGRITY_NOXATTRS, INTEGRITY_UNKNOWN, -- cgit v1.2.3 From 7e135dc725417ecc0629afb4b3b24457d2a4869d Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Fri, 14 May 2021 17:27:48 +0200 Subject: evm: Pass user namespace to set/remove xattr hooks In preparation for 'evm: Allow setxattr() and setattr() for unmodified metadata', this patch passes mnt_userns to the inode set/remove xattr hooks so that the GID of the inode on an idmapped mount is correctly determined by posix_acl_update_mode(). Signed-off-by: Roberto Sassu Reviewed-by: Christian Brauner Cc: Andreas Gruenbacher Signed-off-by: Mimi Zohar --- include/linux/evm.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/evm.h b/include/linux/evm.h index 39bb17a8236b..31ef1dbbb3ac 100644 --- a/include/linux/evm.h +++ b/include/linux/evm.h @@ -23,13 +23,15 @@ extern enum integrity_status evm_verifyxattr(struct dentry *dentry, struct integrity_iint_cache *iint); extern int evm_inode_setattr(struct dentry *dentry, struct iattr *attr); extern void evm_inode_post_setattr(struct dentry *dentry, int ia_valid); -extern int evm_inode_setxattr(struct dentry *dentry, const char *name, +extern int evm_inode_setxattr(struct user_namespace *mnt_userns, + struct dentry *dentry, const char *name, const void *value, size_t size); extern void evm_inode_post_setxattr(struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len); -extern int evm_inode_removexattr(struct dentry *dentry, const char *xattr_name); +extern int evm_inode_removexattr(struct user_namespace *mnt_userns, + struct dentry *dentry, const char *xattr_name); extern void evm_inode_post_removexattr(struct dentry *dentry, const char *xattr_name); extern int evm_inode_init_security(struct inode *inode, @@ -72,7 +74,8 @@ static inline void evm_inode_post_setattr(struct dentry *dentry, int ia_valid) return; } -static inline int evm_inode_setxattr(struct dentry *dentry, const char *name, +static inline int evm_inode_setxattr(struct user_namespace *mnt_userns, + struct dentry *dentry, const char *name, const void *value, size_t size) { return 0; @@ -86,7 +89,8 @@ static inline void evm_inode_post_setxattr(struct dentry *dentry, return; } -static inline int evm_inode_removexattr(struct dentry *dentry, +static inline int evm_inode_removexattr(struct user_namespace *mnt_userns, + struct dentry *dentry, const char *xattr_name) { return 0; -- cgit v1.2.3 From 24bb0076d7bc0ea4caf0af55bd0273a1c343748a Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Mon, 17 May 2021 17:40:20 +0800 Subject: usb: fix spelling mistakes in header files Fix some spelling mistakes in comments: trasfer ==> transfer consumtion ==> consumption endoint ==> endpoint sharable ==> shareable contraints ==> constraints Auxilary ==> Auxiliary correspondig ==> corresponding interupt ==> interrupt inifinite ==> infinite assignement ==> assignment Signed-off-by: Zhen Lei Link: https://lore.kernel.org/r/20210517094020.7310-1-thunder.leizhen@huawei.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 2 +- include/linux/usb/composite.h | 2 +- include/linux/usb/gadget.h | 2 +- include/linux/usb/hcd.h | 4 ++-- include/linux/usb/otg-fsm.h | 6 +++--- include/linux/usb/otg.h | 2 +- include/linux/usb/quirks.h | 2 +- include/linux/usb/serial.h | 2 +- include/linux/usb/typec_dp.h | 2 +- 9 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index eaae24217e8a..4db6b824af5c 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1485,7 +1485,7 @@ typedef void (*usb_complete_t)(struct urb *); * * Note that transfer_buffer must still be set if the controller * does not support DMA (as indicated by hcd_uses_dma()) and when talking - * to root hub. If you have to trasfer between highmem zone and the device + * to root hub. If you have to transfer between highmem zone and the device * on such controller, create a bounce buffer or bail out with an error. * If transfer_buffer cannot be set (is in highmem) and the controller is DMA * capable, assign NULL to it, so that usbmon knows not to use the value. diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index c71150f2c639..9d2762279286 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -271,7 +271,7 @@ int config_ep_by_speed(struct usb_gadget *g, struct usb_function *f, * @bConfigurationValue: Copied into configuration descriptor. * @iConfiguration: Copied into configuration descriptor. * @bmAttributes: Copied into configuration descriptor. - * @MaxPower: Power consumtion in mA. Used to compute bMaxPower in the + * @MaxPower: Power consumption in mA. Used to compute bMaxPower in the * configuration descriptor after considering the bus speed. * @cdev: assigned by @usb_add_config() before calling @bind(); this is * the device associated with this configuration. diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index ee04ef214ce8..8811eb96e5cc 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -197,7 +197,7 @@ struct usb_ep_caps { * @name:identifier for the endpoint, such as "ep-a" or "ep9in-bulk" * @ops: Function pointers used to access hardware-specific operations. * @ep_list:the gadget's ep_list holds all of its endpoints - * @caps:The structure describing types and directions supported by endoint. + * @caps:The structure describing types and directions supported by endpoint. * @enabled: The current endpoint enabled/disabled state. * @claimed: True if this endpoint is claimed by a function. * @maxpacket:The maximum packet size used on this endpoint. The initial diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 22c5d1c0acf3..548a028f2dab 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -59,7 +59,7 @@ * USB Host Controller Driver (usb_hcd) framework * * Since "struct usb_bus" is so thin, you can't share much code in it. - * This framework is a layer over that, and should be more sharable. + * This framework is a layer over that, and should be more shareable. */ /*-------------------------------------------------------------------------*/ @@ -299,7 +299,7 @@ struct hc_driver { * (optional) these hooks allow an HCD to override the default DMA * mapping and unmapping routines. In general, they shouldn't be * necessary unless the host controller has special DMA requirements, - * such as alignment contraints. If these are not specified, the + * such as alignment constraints. If these are not specified, the * general usb_hcd_(un)?map_urb_for_dma functions will be used instead * (and it may be a good idea to call these functions in your HCD * implementation) diff --git a/include/linux/usb/otg-fsm.h b/include/linux/usb/otg-fsm.h index e78eb577d0fa..3aee78dda16d 100644 --- a/include/linux/usb/otg-fsm.h +++ b/include/linux/usb/otg-fsm.h @@ -98,7 +98,7 @@ enum otg_fsm_timer { * @b_bus_req: TRUE during the time that the Application running on the * B-device wants to use the bus * - * Auxilary inputs (OTG v1.3 only. Obsolete now.) + * Auxiliary inputs (OTG v1.3 only. Obsolete now.) * @a_sess_vld: TRUE if the A-device detects that VBUS is above VA_SESS_VLD * @b_bus_suspend: TRUE when the A-device detects that the B-device has put * the bus into suspend @@ -153,7 +153,7 @@ struct otg_fsm { int a_bus_req; int b_bus_req; - /* Auxilary inputs */ + /* Auxiliary inputs */ int a_sess_vld; int b_bus_resume; int b_bus_suspend; @@ -177,7 +177,7 @@ struct otg_fsm { int a_bus_req_inf; int a_clr_err_inf; int b_bus_req_inf; - /* Auxilary informative variables */ + /* Auxiliary informative variables */ int a_suspend_req_inf; /* Timeout indicator for timers */ diff --git a/include/linux/usb/otg.h b/include/linux/usb/otg.h index 69f1b6328532..7ceeecbb9e02 100644 --- a/include/linux/usb/otg.h +++ b/include/linux/usb/otg.h @@ -125,7 +125,7 @@ enum usb_dr_mode { * @dev: Pointer to the given device * * The function gets phy interface string from property 'dr_mode', - * and returns the correspondig enum usb_dr_mode + * and returns the corresponding enum usb_dr_mode */ extern enum usb_dr_mode usb_get_dr_mode(struct device *dev); diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index 5e4c497f54d6..eeb7c2157c72 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -32,7 +32,7 @@ #define USB_QUIRK_DELAY_INIT BIT(6) /* - * For high speed and super speed interupt endpoints, the USB 2.0 and + * For high speed and super speed interrupt endpoints, the USB 2.0 and * USB 3.0 spec require the interval in microframes * (1 microframe = 125 microseconds) to be calculated as * interval = 2 ^ (bInterval-1). diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index 8c63fa9bfc74..b81eb604e092 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -395,7 +395,7 @@ static inline void usb_serial_debug_data(struct device *dev, } /* - * Macro for reporting errors in write path to avoid inifinite loop + * Macro for reporting errors in write path to avoid infinite loop * when port is used as a console. */ #define dev_err_console(usport, fmt, ...) \ diff --git a/include/linux/usb/typec_dp.h b/include/linux/usb/typec_dp.h index fc4c7edb2e8a..cfb916cccd31 100644 --- a/include/linux/usb/typec_dp.h +++ b/include/linux/usb/typec_dp.h @@ -97,7 +97,7 @@ enum { #define DP_CONF_PIN_ASSIGNEMENT_SHIFT 8 #define DP_CONF_PIN_ASSIGNEMENT_MASK GENMASK(15, 8) -/* Helper for setting/getting the pin assignement value to the configuration */ +/* Helper for setting/getting the pin assignment value to the configuration */ #define DP_CONF_SET_PIN_ASSIGN(_a_) ((_a_) << 8) #define DP_CONF_GET_PIN_ASSIGN(_conf_) (((_conf_) & GENMASK(15, 8)) >> 8) -- cgit v1.2.3 From f9a88370e6751c68a8f0d1c3f23100ca20596249 Mon Sep 17 00:00:00 2001 From: Rui Miguel Silva Date: Thu, 13 May 2021 09:47:12 +0100 Subject: usb: isp1760: remove platform data struct and code Since the removal of the Blackfin port with: commit 4ba66a976072 ("arch: remove blackfin port") No one is using or referencing this header and platform data struct. Remove them. Signed-off-by: Rui Miguel Silva Link: https://lore.kernel.org/r/20210513084717.2487366-5-rui.silva@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/isp1760.h | 19 ------------------- 1 file changed, 19 deletions(-) delete mode 100644 include/linux/usb/isp1760.h (limited to 'include/linux') diff --git a/include/linux/usb/isp1760.h b/include/linux/usb/isp1760.h deleted file mode 100644 index b75ded28db81..000000000000 --- a/include/linux/usb/isp1760.h +++ /dev/null @@ -1,19 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * board initialization should put one of these into dev->platform_data - * and place the isp1760 onto platform_bus named "isp1760-hcd". - */ - -#ifndef __LINUX_USB_ISP1760_H -#define __LINUX_USB_ISP1760_H - -struct isp1760_platform_data { - unsigned is_isp1761:1; /* Chip is ISP1761 */ - unsigned bus_width_16:1; /* 16/32-bit data bus width */ - unsigned port1_otg:1; /* Port 1 supports OTG */ - unsigned analog_oc:1; /* Analog overcurrent */ - unsigned dack_polarity_high:1; /* DACK active high */ - unsigned dreq_polarity_high:1; /* DREQ active high */ -}; - -#endif /* __LINUX_USB_ISP1760_H */ -- cgit v1.2.3 From 59d4d06c8ab0375dcc4bab329e6ecd44dd46373e Mon Sep 17 00:00:00 2001 From: Badhri Jagan Sridharan Date: Mon, 17 May 2021 12:21:11 -0700 Subject: usb: typec: tcpm: Move TCPC to APPLY_RC state during PR_SWAP When vbus auto discharge is enabled, TCPCI based TCPC transitions into Attached.SNK/Attached.SRC state. During PR_SWAP, TCPCI based TCPC would disconnect when partner changes power roles. TCPC has to be moved APPLY RC state during PR_SWAP. This is done by ROLE_CONTROL.CC1 != ROLE_CONTROL.CC2 and POWER_CONTROL.AutodischargeDisconnect is 0. Once the swap sequence is done, AutoDischargeDisconnect is re-enabled. Fixes: f321a02caebd ("usb: typec: tcpm: Implement enabling Auto Discharge disconnect support") Reviewed-by: Guenter Roeck Acked-by: Heikki Krogerus Signed-off-by: Badhri Jagan Sridharan Link: https://lore.kernel.org/r/20210517192112.40934-3-badhri@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/tcpm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/tcpm.h b/include/linux/usb/tcpm.h index 42fcfbe10590..bffc8d3e14ad 100644 --- a/include/linux/usb/tcpm.h +++ b/include/linux/usb/tcpm.h @@ -66,6 +66,8 @@ enum tcpm_transmit_type { * For example, some tcpcs may include BC1.2 charger detection * and use that in this case. * @set_cc: Called to set value of CC pins + * @apply_rc: Optional; Needed to move TCPCI based chipset to APPLY_RC state + * as stated by the TCPCI specification. * @get_cc: Called to read current CC pin values * @set_polarity: * Called to set polarity @@ -120,6 +122,8 @@ struct tcpc_dev { int (*get_vbus)(struct tcpc_dev *dev); int (*get_current_limit)(struct tcpc_dev *dev); int (*set_cc)(struct tcpc_dev *dev, enum typec_cc_status cc); + int (*apply_rc)(struct tcpc_dev *dev, enum typec_cc_status cc, + enum typec_cc_polarity polarity); int (*get_cc)(struct tcpc_dev *dev, enum typec_cc_status *cc1, enum typec_cc_status *cc2); int (*set_polarity)(struct tcpc_dev *dev, -- cgit v1.2.3 From 393b06383fb77a006a29eb1574474d468e8c868b Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 21 May 2021 20:45:19 +0200 Subject: debugfs: remove return value of debugfs_create_bool() No one checks the return value of debugfs_create_bool(), as it's not needed, so make the return value void, so that no one tries to do so in the future. Link: https://lore.kernel.org/r/20210521184519.1356639-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/debugfs.h | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index 1fdb4343af9c..53150803eb7c 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -126,8 +126,8 @@ void debugfs_create_size_t(const char *name, umode_t mode, struct dentry *parent, size_t *value); void debugfs_create_atomic_t(const char *name, umode_t mode, struct dentry *parent, atomic_t *value); -struct dentry *debugfs_create_bool(const char *name, umode_t mode, - struct dentry *parent, bool *value); +void debugfs_create_bool(const char *name, umode_t mode, struct dentry *parent, + bool *value); void debugfs_create_str(const char *name, umode_t mode, struct dentry *parent, char **value); @@ -295,12 +295,8 @@ static inline void debugfs_create_atomic_t(const char *name, umode_t mode, atomic_t *value) { } -static inline struct dentry *debugfs_create_bool(const char *name, umode_t mode, - struct dentry *parent, - bool *value) -{ - return ERR_PTR(-ENODEV); -} +static inline void debugfs_create_bool(const char *name, umode_t mode, + struct dentry *parent, bool *value) { } static inline void debugfs_create_str(const char *name, umode_t mode, struct dentry *parent, -- cgit v1.2.3 From fb05b14c5b99a7a462d6e733155e4b2e80e28646 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 21 May 2021 20:43:40 +0200 Subject: debugfs: remove return value of debugfs_create_ulong() No one checks the return value of debugfs_create_ulong(), as it's not needed, so make the return value void, so that no one tries to do so in the future. Link: https://lore.kernel.org/r/20210521184340.1348539-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/debugfs.h | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index 53150803eb7c..c869f1e73d75 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -112,8 +112,8 @@ void debugfs_create_u32(const char *name, umode_t mode, struct dentry *parent, u32 *value); void debugfs_create_u64(const char *name, umode_t mode, struct dentry *parent, u64 *value); -struct dentry *debugfs_create_ulong(const char *name, umode_t mode, - struct dentry *parent, unsigned long *value); +void debugfs_create_ulong(const char *name, umode_t mode, struct dentry *parent, + unsigned long *value); void debugfs_create_x8(const char *name, umode_t mode, struct dentry *parent, u8 *value); void debugfs_create_x16(const char *name, umode_t mode, struct dentry *parent, @@ -266,13 +266,9 @@ static inline void debugfs_create_u32(const char *name, umode_t mode, static inline void debugfs_create_u64(const char *name, umode_t mode, struct dentry *parent, u64 *value) { } -static inline struct dentry *debugfs_create_ulong(const char *name, - umode_t mode, - struct dentry *parent, - unsigned long *value) -{ - return ERR_PTR(-ENODEV); -} +static inline void debugfs_create_ulong(const char *name, umode_t mode, + struct dentry *parent, + unsigned long *value) { } static inline void debugfs_create_x8(const char *name, umode_t mode, struct dentry *parent, u8 *value) { } -- cgit v1.2.3 From 46ad057245912fc8a49e18f6f8b57f80ab8d4dc1 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Wed, 19 May 2021 18:33:14 +0200 Subject: sysfs: Add helper BIN_ATTRIBUTE_GROUPS New helper BIN_ATTRIBUTE_GROUPS() does the same as ATTRIBUTE_GROUPS(), just for binary attributes. Signed-off-by: Heiner Kallweit Link: https://lore.kernel.org/r/e20db248-ed30-cf5d-a37c-b538dceaa5b2@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index d76a1ddf83a3..a12556a4b93a 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -162,6 +162,12 @@ static const struct attribute_group _name##_group = { \ }; \ __ATTRIBUTE_GROUPS(_name) +#define BIN_ATTRIBUTE_GROUPS(_name) \ +static const struct attribute_group _name##_group = { \ + .bin_attrs = _name##_attrs, \ +}; \ +__ATTRIBUTE_GROUPS(_name) + struct file; struct vm_area_struct; struct address_space; -- cgit v1.2.3 From 7ee3e97e00a3893e354c3993c3f7d9dc127e9c5e Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Thu, 13 May 2021 09:07:51 +0000 Subject: kprobes: Allow architectures to override optinsn page allocation Some architectures like powerpc require a non standard allocation of optinsn page, because module pages are too far from the kernel for direct branches. Define weak alloc_optinsn_page() and free_optinsn_page(), that fall back on alloc_insn_page() and free_insn_page() when not overridden by the architecture. Suggested-by: Masami Hiramatsu Signed-off-by: Christophe Leroy Reviewed-by: Naveen N. Rao Acked-by: Masami Hiramatsu Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/40a43d6df1fdf41ade36e9a46e60a4df774ca9f6.1620896780.git.christophe.leroy@csgroup.eu --- include/linux/kprobes.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 1883a4a9f16a..02d4020615a7 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -409,6 +409,9 @@ void dump_kprobe(struct kprobe *kp); void *alloc_insn_page(void); void free_insn_page(void *page); +void *alloc_optinsn_page(void); +void free_optinsn_page(void *page); + int kprobe_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym); -- cgit v1.2.3 From 42a7dfa26fc6df1624d7c2955200e5053dd0b818 Mon Sep 17 00:00:00 2001 From: David Bauer Date: Sat, 22 May 2021 09:44:52 +0200 Subject: spi: ath79: drop platform data The ath79 platform has been converted to pure OF. The platform data is not needed anymore because of this. Signed-off-by: David Bauer Link: https://lore.kernel.org/r/20210522074453.39299-1-mail@david-bauer.net Signed-off-by: Mark Brown --- include/linux/platform_data/spi-ath79.h | 16 ---------------- 1 file changed, 16 deletions(-) delete mode 100644 include/linux/platform_data/spi-ath79.h (limited to 'include/linux') diff --git a/include/linux/platform_data/spi-ath79.h b/include/linux/platform_data/spi-ath79.h deleted file mode 100644 index 81a388ff58cc..000000000000 --- a/include/linux/platform_data/spi-ath79.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Platform data definition for Atheros AR71XX/AR724X/AR913X SPI controller - * - * Copyright (C) 2008-2010 Gabor Juhos - */ - -#ifndef _ATH79_SPI_PLATFORM_H -#define _ATH79_SPI_PLATFORM_H - -struct ath79_spi_platform_data { - unsigned bus_num; - unsigned num_chipselect; -}; - -#endif /* _ATH79_SPI_PLATFORM_H */ -- cgit v1.2.3 From 3af3d772f7216cf23081bb4176e86f1219d32ebc Mon Sep 17 00:00:00 2001 From: "zhangyi (F)" Date: Sat, 13 Mar 2021 11:01:45 +0800 Subject: block_dump: remove block_dump feature We have already delete block_dump feature in mark_inode_dirty() because it can be replaced by tracepoints, now we also remove the part in submit_bio() for the same reason. The part of block dump feature in submit_bio() dump the write process, write region and sectors on the target disk into kernel message. it can be replaced by block_bio_queue tracepoint in submit_bio_checks(), so we do not need block_dump anymore, remove the whole block_dump feature. Signed-off-by: zhangyi (F) Reviewed-by: Jan Kara Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20210313030146.2882027-3-yi.zhang@huawei.com Signed-off-by: Jens Axboe --- include/linux/writeback.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 8e5c5bb16e2d..9ef50176f3a1 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -360,7 +360,6 @@ extern unsigned int dirty_writeback_interval; extern unsigned int dirty_expire_interval; extern unsigned int dirtytime_expire_interval; extern int vm_highmem_is_dirtyable; -extern int block_dump; extern int laptop_mode; int dirty_background_ratio_handler(struct ctl_table *table, int write, -- cgit v1.2.3 From d97e594c51660bea510a387731637b894651e4b5 Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 13 May 2021 20:00:58 +0800 Subject: blk-mq: Use request queue-wide tags for tagset-wide sbitmap The tags used for an IO scheduler are currently per hctx. As such, when q->nr_hw_queues grows, so does the request queue total IO scheduler tag depth. This may cause problems for SCSI MQ HBAs whose total driver depth is fixed. Ming and Yanhui report higher CPU usage and lower throughput in scenarios where the fixed total driver tag depth is appreciably lower than the total scheduler tag depth: https://lore.kernel.org/linux-block/440dfcfc-1a2c-bd98-1161-cec4d78c6dfc@huawei.com/T/#mc0d6d4f95275a2743d1c8c3e4dc9ff6c9aa3a76b In that scenario, since the scheduler tag is got first, much contention is introduced since a driver tag may not be available after we have got the sched tag. Improve this scenario by introducing request queue-wide tags for when a tagset-wide sbitmap is used. The static sched requests are still allocated per hctx, as requests are initialised per hctx, as in blk_mq_init_request(..., hctx_idx, ...) -> set->ops->init_request(.., hctx_idx, ...). For simplicity of resizing the request queue sbitmap when updating the request queue depth, just init at the max possible size, so we don't need to deal with the possibly with swapping out a new sbitmap for old if we need to grow. Signed-off-by: John Garry Reviewed-by: Ming Lei Link: https://lore.kernel.org/r/1620907258-30910-3-git-send-email-john.garry@huawei.com Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f69c75bd6d27..2c28577b50f4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -25,6 +25,7 @@ #include #include #include +#include struct module; struct scsi_ioctl_command; @@ -493,6 +494,9 @@ struct request_queue { atomic_t nr_active_requests_shared_sbitmap; + struct sbitmap_queue sched_bitmap_tags; + struct sbitmap_queue sched_breserved_tags; + struct list_head icq_list; #ifdef CONFIG_BLK_CGROUP DECLARE_BITMAP (blkcg_pols, BLKCG_MAX_POLS); -- cgit v1.2.3 From 3e87f192b405960c0fe83e0925bd0dadf4f8cf43 Mon Sep 17 00:00:00 2001 From: Denis Salopek Date: Tue, 11 May 2021 23:00:04 +0200 Subject: bpf: Add lookup_and_delete_elem support to hashtab Extend the existing bpf_map_lookup_and_delete_elem() functionality to hashtab map types, in addition to stacks and queues. Create a new hashtab bpf_map_ops function that does lookup and deletion of the element under the same bucket lock and add the created map_ops to bpf.h. Signed-off-by: Denis Salopek Signed-off-by: Andrii Nakryiko Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/4d18480a3e990ffbf14751ddef0325eed3be2966.1620763117.git.denis.salopek@sartura.hr --- include/linux/bpf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 9dc44ba97584..1e9a0ff3217b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -70,6 +70,8 @@ struct bpf_map_ops { void *(*map_lookup_elem_sys_only)(struct bpf_map *map, void *key); int (*map_lookup_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); + int (*map_lookup_and_delete_elem)(struct bpf_map *map, void *key, + void *value, u64 flags); int (*map_lookup_and_delete_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); -- cgit v1.2.3 From 8fb33b6055300a23f26868680c22a5726834785e Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Tue, 25 May 2021 10:56:59 +0800 Subject: bpf: Fix spelling mistakes Fix some spelling mistakes in comments: aother ==> another Netiher ==> Neither desribe ==> describe intializing ==> initializing funciton ==> function wont ==> won't and move the word 'the' at the end to the next line accross ==> across pathes ==> paths triggerred ==> triggered excute ==> execute ether ==> either conervative ==> conservative convetion ==> convention markes ==> marks interpeter ==> interpreter Signed-off-by: Zhen Lei Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210525025659.8898-2-thunder.leizhen@huawei.com --- include/linux/bpf_local_storage.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index b902c580c48d..24496bc28e7b 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -58,7 +58,7 @@ struct bpf_local_storage_data { * from the object's bpf_local_storage. * * Put it in the same cacheline as the data to minimize - * the number of cachelines access during the cache hit case. + * the number of cachelines accessed during the cache hit case. */ struct bpf_local_storage_map __rcu *smap; u8 data[] __aligned(8); @@ -71,7 +71,7 @@ struct bpf_local_storage_elem { struct bpf_local_storage __rcu *local_storage; struct rcu_head rcu; /* 8 bytes hole */ - /* The data is stored in aother cacheline to minimize + /* The data is stored in another cacheline to minimize * the number of cachelines access during a cache hit. */ struct bpf_local_storage_data sdata ____cacheline_aligned; -- cgit v1.2.3 From f4e44b393389c77958f7c58bf4415032b4cda15b Mon Sep 17 00:00:00 2001 From: Dai Ngo Date: Fri, 21 May 2021 15:09:37 -0400 Subject: NFSD: delay unmount source's export after inter-server copy completed. Currently the source's export is mounted and unmounted on every inter-server copy operation. This patch is an enhancement to delay the unmount of the source export for a certain period of time to eliminate the mount and unmount overhead on subsequent copy operations. After a copy operation completes, a work entry is added to the delayed unmount list with an expiration time. This list is serviced by the laundromat thread to unmount the export of the expired entries. Each time the export is being used again, its expiration time is extended and the entry is re-inserted to the tail of the list. The unmount task and the mount operation of the copy request are synced to make sure the export is not unmounted while it's being used. Signed-off-by: Dai Ngo Signed-off-by: J. Bruce Fields --- include/linux/nfs_ssc.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_ssc.h b/include/linux/nfs_ssc.h index f5ba0fbff72f..222ae8883e85 100644 --- a/include/linux/nfs_ssc.h +++ b/include/linux/nfs_ssc.h @@ -8,6 +8,7 @@ */ #include +#include extern struct nfs_ssc_client_ops_tbl nfs_ssc_client_tbl; @@ -52,6 +53,19 @@ static inline void nfs42_ssc_close(struct file *filep) if (nfs_ssc_client_tbl.ssc_nfs4_ops) (*nfs_ssc_client_tbl.ssc_nfs4_ops->sco_close)(filep); } + +struct nfsd4_ssc_umount_item { + struct list_head nsui_list; + bool nsui_busy; + /* + * nsui_refcnt inited to 2, 1 on list and 1 for consumer. Entry + * is removed when refcnt drops to 1 and nsui_expire expires. + */ + refcount_t nsui_refcnt; + unsigned long nsui_expire; + struct vfsmount *nsui_vfsmount; + char nsui_ipaddr[RPC_MAX_ADDRBUFLEN]; +}; #endif /* -- cgit v1.2.3 From e624d4ed4aa8cc3c69d1359b0aaea539203ed266 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Wed, 19 May 2021 17:07:45 +0800 Subject: xdp: Extend xdp_redirect_map with broadcast support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to extend xdp_redirect_map for broadcast support. With BPF_F_BROADCAST the packet will be broadcasted to all the interfaces in the map. with BPF_F_EXCLUDE_INGRESS the ingress interface will be excluded when do broadcasting. When getting the devices in dev hash map via dev_map_hash_get_next_key(), there is a possibility that we fall back to the first key when a device was removed. This will duplicate packets on some interfaces. So just walk the whole buckets to avoid this issue. For dev array map, we also walk the whole map to find valid interfaces. Function bpf_clear_redirect_map() was removed in commit ee75aef23afe ("bpf, xdp: Restructure redirect actions"). Add it back as we need to use ri->map again. With test topology: +-------------------+ +-------------------+ | Host A (i40e 10G) | ---------- | eno1(i40e 10G) | +-------------------+ | | | Host B | +-------------------+ | | | Host C (i40e 10G) | ---------- | eno2(i40e 10G) | +-------------------+ | | | +------+ | | veth0 -- | Peer | | | veth1 -- | | | | veth2 -- | NS | | | +------+ | +-------------------+ On Host A: # pktgen/pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -s 64 On Host B(Intel(R) Xeon(R) CPU E5-2690 v3 @ 2.60GHz, 128G Memory): Use xdp_redirect_map and xdp_redirect_map_multi in samples/bpf for testing. All the veth peers in the NS have a XDP_DROP program loaded. The forward_map max_entries in xdp_redirect_map_multi is modify to 4. Testing the performance impact on the regular xdp_redirect path with and without patch (to check impact of additional check for broadcast mode): 5.12 rc4 | redirect_map i40e->i40e | 2.0M | 9.7M 5.12 rc4 | redirect_map i40e->veth | 1.7M | 11.8M 5.12 rc4 + patch | redirect_map i40e->i40e | 2.0M | 9.6M 5.12 rc4 + patch | redirect_map i40e->veth | 1.7M | 11.7M Testing the performance when cloning packets with the redirect_map_multi test, using a redirect map size of 4, filled with 1-3 devices: 5.12 rc4 + patch | redirect_map multi i40e->veth (x1) | 1.7M | 11.4M 5.12 rc4 + patch | redirect_map multi i40e->veth (x2) | 1.1M | 4.3M 5.12 rc4 + patch | redirect_map multi i40e->veth (x3) | 0.8M | 2.6M Signed-off-by: Hangbin Liu Signed-off-by: Daniel Borkmann Acked-by: Toke Høiland-Jørgensen Acked-by: Martin KaFai Lau Acked-by: John Fastabend Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/bpf/20210519090747.1655268-3-liuhangbin@gmail.com --- include/linux/bpf.h | 20 ++++++++++++++++++++ include/linux/filter.h | 19 +++++++++++++++---- 2 files changed, 35 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1e9a0ff3217b..86dec5001ae2 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1501,8 +1501,13 @@ int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, struct net_device *dev_rx); int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, struct net_device *dev_rx); +int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx, + struct bpf_map *map, bool exclude_ingress); int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog); +int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, + struct bpf_prog *xdp_prog, struct bpf_map *map, + bool exclude_ingress); bool dev_map_can_have_prog(struct bpf_map *map); void __cpu_map_flush(void); @@ -1670,6 +1675,13 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, return 0; } +static inline +int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx, + struct bpf_map *map, bool exclude_ingress) +{ + return 0; +} + struct sk_buff; static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, @@ -1679,6 +1691,14 @@ static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, return 0; } +static inline +int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, + struct bpf_prog *xdp_prog, struct bpf_map *map, + bool exclude_ingress) +{ + return 0; +} + static inline void __cpu_map_flush(void) { } diff --git a/include/linux/filter.h b/include/linux/filter.h index 9a09547bc7ba..c5ad7df029ed 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -646,6 +646,7 @@ struct bpf_redirect_info { u32 flags; u32 tgt_index; void *tgt_value; + struct bpf_map *map; u32 map_id; enum bpf_map_type map_type; u32 kern_flags; @@ -1464,17 +1465,19 @@ static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol, } #endif /* IS_ENABLED(CONFIG_IPV6) */ -static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifindex, u64 flags, +static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifindex, + u64 flags, const u64 flag_mask, void *lookup_elem(struct bpf_map *map, u32 key)) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + const u64 action_mask = XDP_ABORTED | XDP_DROP | XDP_PASS | XDP_TX; /* Lower bits of the flags are used as return code on lookup failure */ - if (unlikely(flags > XDP_TX)) + if (unlikely(flags & ~(action_mask | flag_mask))) return XDP_ABORTED; ri->tgt_value = lookup_elem(map, ifindex); - if (unlikely(!ri->tgt_value)) { + if (unlikely(!ri->tgt_value) && !(flags & BPF_F_BROADCAST)) { /* If the lookup fails we want to clear out the state in the * redirect_info struct completely, so that if an eBPF program * performs multiple lookups, the last one always takes @@ -1482,13 +1485,21 @@ static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifind */ ri->map_id = INT_MAX; /* Valid map id idr range: [1,INT_MAX[ */ ri->map_type = BPF_MAP_TYPE_UNSPEC; - return flags; + return flags & action_mask; } ri->tgt_index = ifindex; ri->map_id = map->id; ri->map_type = map->map_type; + if (flags & BPF_F_BROADCAST) { + WRITE_ONCE(ri->map, map); + ri->flags = flags; + } else { + WRITE_ONCE(ri->map, NULL); + ri->flags = 0; + } + return XDP_REDIRECT; } -- cgit v1.2.3 From 961965c45c706175b24227868b1c12d72775e446 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 5 May 2021 23:37:29 +0200 Subject: mtd: rawnand: Add a helper to clarify the interface configuration Name it nand_interface_is_sdr() which will make even more sense when nand_interface_is_nvddr() will be introduced. Use it when relevant. Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210505213750.257417-2-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 29df2f43dcb5..39b31f8e03b7 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -496,6 +496,15 @@ struct nand_interface_config { } timings; }; +/** + * nand_interface_is_sdr - get the interface type + * @conf: The data interface + */ +static bool nand_interface_is_sdr(const struct nand_interface_config *conf) +{ + return conf->type == NAND_SDR_IFACE; +} + /** * nand_get_sdr_timings - get SDR timing from data interface * @conf: The data interface @@ -503,7 +512,7 @@ struct nand_interface_config { static inline const struct nand_sdr_timings * nand_get_sdr_timings(const struct nand_interface_config *conf) { - if (conf->type != NAND_SDR_IFACE) + if (!nand_interface_is_sdr(conf)) return ERR_PTR(-EINVAL); return &conf->timings.sdr; -- cgit v1.2.3 From 64de50e38e6fced70d1cb9ad3112de0691d0ed2d Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 5 May 2021 23:37:32 +0200 Subject: mtd: rawnand: onfi: Use the BIT() macro when possible Update the onfi.h header to use the BIT() macro. Signed-off-by: Miquel Raynal Acked-by: Alexander Dahl Link: https://lore.kernel.org/linux-mtd/20210505213750.257417-5-miquel.raynal@bootlin.com --- include/linux/mtd/onfi.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/onfi.h b/include/linux/mtd/onfi.h index 339ac798568e..cf14474bc454 100644 --- a/include/linux/mtd/onfi.h +++ b/include/linux/mtd/onfi.h @@ -24,17 +24,17 @@ #define ONFI_VERSION_4_0 BIT(9) /* ONFI features */ -#define ONFI_FEATURE_16_BIT_BUS (1 << 0) -#define ONFI_FEATURE_EXT_PARAM_PAGE (1 << 7) +#define ONFI_FEATURE_16_BIT_BUS BIT(0) +#define ONFI_FEATURE_EXT_PARAM_PAGE BIT(7) /* ONFI timing mode, used in both asynchronous and synchronous mode */ -#define ONFI_TIMING_MODE_0 (1 << 0) -#define ONFI_TIMING_MODE_1 (1 << 1) -#define ONFI_TIMING_MODE_2 (1 << 2) -#define ONFI_TIMING_MODE_3 (1 << 3) -#define ONFI_TIMING_MODE_4 (1 << 4) -#define ONFI_TIMING_MODE_5 (1 << 5) -#define ONFI_TIMING_MODE_UNKNOWN (1 << 6) +#define ONFI_TIMING_MODE_0 BIT(0) +#define ONFI_TIMING_MODE_1 BIT(1) +#define ONFI_TIMING_MODE_2 BIT(2) +#define ONFI_TIMING_MODE_3 BIT(3) +#define ONFI_TIMING_MODE_4 BIT(4) +#define ONFI_TIMING_MODE_5 BIT(5) +#define ONFI_TIMING_MODE_UNKNOWN BIT(6) /* ONFI feature number/address */ #define ONFI_FEATURE_NUMBER 256 @@ -49,7 +49,7 @@ #define ONFI_SUBFEATURE_PARAM_LEN 4 /* ONFI optional commands SET/GET FEATURES supported? */ -#define ONFI_OPT_CMD_SET_GET_FEATURES (1 << 2) +#define ONFI_OPT_CMD_SET_GET_FEATURES BIT(2) struct nand_onfi_params { /* rev info and features block */ -- cgit v1.2.3 From b16e0d5d7d693fe93e75569ac1ec80b513902a92 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 5 May 2021 23:37:33 +0200 Subject: mtd: rawnand: Update dead URL The current link to the ONFI specification is broken, the onfi.org website now points to materials on Micron's website. Update the URL accordingly. Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210505213750.257417-6-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 39b31f8e03b7..24aee0af5421 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -385,8 +385,8 @@ struct nand_ecc_ctrl { * This struct defines the timing requirements of a SDR NAND chip. * These information can be found in every NAND datasheets and the timings * meaning are described in the ONFI specifications: - * www.onfi.org/~/media/ONFI/specs/onfi_3_1_spec.pdf (chapter 4.15 Timing - * Parameters) + * https://media-www.micron.com/-/media/client/onfi/specs/onfi_3_1_spec.pdf + * (chapter 4.15 Timing Parameters) * * All these timings are expressed in picoseconds. * -- cgit v1.2.3 From dbb7b2e07564443c2d357398e83e27c2fa5a89ed Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 5 May 2021 23:37:34 +0200 Subject: mtd: rawnand: Use more recent ONFI specification wording In particular, first ONFI specifications referred to SDR modes as asynchronous modes, which is not the term we usually have in mind. The spec has then been updated, so do the same here in the NAND subsystem to avoid any possible confusion. Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210505213750.257417-7-miquel.raynal@bootlin.com --- include/linux/mtd/onfi.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/onfi.h b/include/linux/mtd/onfi.h index cf14474bc454..2ade5632dc5b 100644 --- a/include/linux/mtd/onfi.h +++ b/include/linux/mtd/onfi.h @@ -93,7 +93,7 @@ struct nand_onfi_params { /* electrical parameter block */ u8 io_pin_capacitance_max; - __le16 async_timing_mode; + __le16 sdr_timing_modes; __le16 program_cache_timing_mode; __le16 t_prog; __le16 t_bers; @@ -160,7 +160,7 @@ struct onfi_ext_param_page { * @tBERS: Block erase time * @tR: Page read time * @tCCS: Change column setup time - * @async_timing_mode: Supported asynchronous timing mode + * @sdr_timing_modes: Supported asynchronous/SDR timing modes * @vendor_revision: Vendor specific revision number * @vendor: Vendor specific data */ @@ -170,7 +170,7 @@ struct onfi_params { u16 tBERS; u16 tR; u16 tCCS; - u16 async_timing_mode; + u16 sdr_timing_modes; u16 vendor_revision; u8 vendor[88]; }; -- cgit v1.2.3 From 7ce872d9f55f46ef54b60ed39c0144b24578d7c3 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 5 May 2021 23:37:35 +0200 Subject: mtd: rawnand: Clarify the NV-DDR entries in the ONFI structure Both src_sync_timing_mode and src_ssync_features entries of the ONFI parameter page have been updated and now are named nvddr_timing_modes, nvddr2_timing_modes and nvddr_nvddr2_features, which is much more understandable for someone which do not know the history of the ONFI specification. Update the relevant structure with regard to these changes. Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210505213750.257417-8-miquel.raynal@bootlin.com --- include/linux/mtd/onfi.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/onfi.h b/include/linux/mtd/onfi.h index 2ade5632dc5b..319e1736851d 100644 --- a/include/linux/mtd/onfi.h +++ b/include/linux/mtd/onfi.h @@ -99,8 +99,9 @@ struct nand_onfi_params { __le16 t_bers; __le16 t_r; __le16 t_ccs; - __le16 src_sync_timing_mode; - u8 src_ssync_features; + u8 nvddr_timing_modes; + u8 nvddr2_timing_modes; + u8 nvddr_nvddr2_features; __le16 clk_pin_capacitance_typ; __le16 io_pin_capacitance_typ; __le16 input_pin_capacitance_typ; -- cgit v1.2.3 From 1666b815ad1a5b6373e950da5002ac46521a9b28 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 5 May 2021 23:37:36 +0200 Subject: mtd: rawnand: Add NV-DDR timings Create the relevant ONFI NV-DDR timings structure and fill it with default values from the ONFI specification. Add the relevant structure entries and helpers. Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210505213750.257417-9-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 112 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 112 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 24aee0af5421..a53a1543d1d4 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -471,12 +471,100 @@ struct nand_sdr_timings { u32 tWW_min; }; +/** + * struct nand_nvddr_timings - NV-DDR NAND chip timings + * + * This struct defines the timing requirements of a NV-DDR NAND data interface. + * These information can be found in every NAND datasheets and the timings + * meaning are described in the ONFI specifications: + * https://media-www.micron.com/-/media/client/onfi/specs/onfi_4_1_gold.pdf + * (chapter 4.18.2 NV-DDR) + * + * All these timings are expressed in picoseconds. + * + * @tBERS_max: Block erase time + * @tCCS_min: Change column setup time + * @tPROG_max: Page program time + * @tR_max: Page read time + * @tAC_min: Access window of DQ[7:0] from CLK + * @tAC_max: Access window of DQ[7:0] from CLK + * @tADL_min: ALE to data loading time + * @tCAD_min: Command, Address, Data delay + * @tCAH_min: Command/Address DQ hold time + * @tCALH_min: W/R_n, CLE and ALE hold time + * @tCALS_min: W/R_n, CLE and ALE setup time + * @tCAS_min: Command/address DQ setup time + * @tCEH_min: CE# high hold time + * @tCH_min: CE# hold time + * @tCK_min: Average clock cycle time + * @tCS_min: CE# setup time + * @tDH_min: Data hold time + * @tDQSCK_min: Start of the access window of DQS from CLK + * @tDQSCK_max: End of the access window of DQS from CLK + * @tDQSD_min: Min W/R_n low to DQS/DQ driven by device + * @tDQSD_max: Max W/R_n low to DQS/DQ driven by device + * @tDQSHZ_max: W/R_n high to DQS/DQ tri-state by device + * @tDQSQ_max: DQS-DQ skew, DQS to last DQ valid, per access + * @tDS_min: Data setup time + * @tDSC_min: DQS cycle time + * @tFEAT_max: Busy time for Set Features and Get Features + * @tITC_max: Interface and Timing Mode Change time + * @tQHS_max: Data hold skew factor + * @tRHW_min: Data output cycle to command, address, or data input cycle + * @tRR_min: Ready to RE# low (data only) + * @tRST_max: Device reset time, measured from the falling edge of R/B# to the + * rising edge of R/B#. + * @tWB_max: WE# high to SR[6] low + * @tWHR_min: WE# high to RE# low + * @tWRCK_min: W/R_n low to data output cycle + * @tWW_min: WP# transition to WE# low + */ +struct nand_nvddr_timings { + u64 tBERS_max; + u32 tCCS_min; + u64 tPROG_max; + u64 tR_max; + u32 tAC_min; + u32 tAC_max; + u32 tADL_min; + u32 tCAD_min; + u32 tCAH_min; + u32 tCALH_min; + u32 tCALS_min; + u32 tCAS_min; + u32 tCEH_min; + u32 tCH_min; + u32 tCK_min; + u32 tCS_min; + u32 tDH_min; + u32 tDQSCK_min; + u32 tDQSCK_max; + u32 tDQSD_min; + u32 tDQSD_max; + u32 tDQSHZ_max; + u32 tDQSQ_max; + u32 tDS_min; + u32 tDSC_min; + u32 tFEAT_max; + u32 tITC_max; + u32 tQHS_max; + u32 tRHW_min; + u32 tRR_min; + u32 tRST_max; + u32 tWB_max; + u32 tWHR_min; + u32 tWRCK_min; + u32 tWW_min; +}; + /** * enum nand_interface_type - NAND interface type * @NAND_SDR_IFACE: Single Data Rate interface + * @NAND_NVDDR_IFACE: Double Data Rate interface */ enum nand_interface_type { NAND_SDR_IFACE, + NAND_NVDDR_IFACE, }; /** @@ -485,6 +573,7 @@ enum nand_interface_type { * @timings: The timing information * @timings.mode: Timing mode as defined in the specification * @timings.sdr: Use it when @type is %NAND_SDR_IFACE. + * @timings.nvddr: Use it when @type is %NAND_NVDDR_IFACE. */ struct nand_interface_config { enum nand_interface_type type; @@ -492,6 +581,7 @@ struct nand_interface_config { unsigned int mode; union { struct nand_sdr_timings sdr; + struct nand_nvddr_timings nvddr; }; } timings; }; @@ -505,6 +595,15 @@ static bool nand_interface_is_sdr(const struct nand_interface_config *conf) return conf->type == NAND_SDR_IFACE; } +/** + * nand_interface_is_nvddr - get the interface type + * @conf: The data interface + */ +static bool nand_interface_is_nvddr(const struct nand_interface_config *conf) +{ + return conf->type == NAND_NVDDR_IFACE; +} + /** * nand_get_sdr_timings - get SDR timing from data interface * @conf: The data interface @@ -518,6 +617,19 @@ nand_get_sdr_timings(const struct nand_interface_config *conf) return &conf->timings.sdr; } +/** + * nand_get_nvddr_timings - get NV-DDR timing from data interface + * @conf: The data interface + */ +static inline const struct nand_nvddr_timings * +nand_get_nvddr_timings(const struct nand_interface_config *conf) +{ + if (!nand_interface_is_nvddr(conf)) + return ERR_PTR(-EINVAL); + + return &conf->timings.nvddr; +} + /** * struct nand_op_cmd_instr - Definition of a command instruction * @opcode: the command to issue in one cycle -- cgit v1.2.3 From 9310668fb60a7ee76c4fdfd6388747a6f2beaf75 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 5 May 2021 23:37:37 +0200 Subject: mtd: rawnand: Retrieve NV-DDR timing modes from the ONFI parameter page When parsing the ONFI parameter page, save the available NV-DDR timing modes in the core's dynamic ONFI structure. Once available to the rest of the core out of the ONFI driver, these values will then be used to derive the best timing mode. Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210505213750.257417-10-miquel.raynal@bootlin.com --- include/linux/mtd/onfi.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/onfi.h b/include/linux/mtd/onfi.h index 319e1736851d..14e66a49557e 100644 --- a/include/linux/mtd/onfi.h +++ b/include/linux/mtd/onfi.h @@ -25,6 +25,7 @@ /* ONFI features */ #define ONFI_FEATURE_16_BIT_BUS BIT(0) +#define ONFI_FEATURE_NV_DDR BIT(5) #define ONFI_FEATURE_EXT_PARAM_PAGE BIT(7) /* ONFI timing mode, used in both asynchronous and synchronous mode */ @@ -162,6 +163,7 @@ struct onfi_ext_param_page { * @tR: Page read time * @tCCS: Change column setup time * @sdr_timing_modes: Supported asynchronous/SDR timing modes + * @nvddr_timing_modes: Supported source synchronous/NV-DDR timing modes * @vendor_revision: Vendor specific revision number * @vendor: Vendor specific data */ @@ -172,6 +174,7 @@ struct onfi_params { u16 tR; u16 tCCS; u16 sdr_timing_modes; + u16 nvddr_timing_modes; u16 vendor_revision; u8 vendor[88]; }; -- cgit v1.2.3 From 45606518f961b9e7adddc017e7813fa9f92b43fb Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 5 May 2021 23:37:39 +0200 Subject: mtd: rawnand: Add onfi_fill_nvddr_interface_config() helper Same logic as for the SDR path, let's create a onfi_fill_nvddr_interface_config() helper to fill an interface configuration structure with NV-DDR timings, given a specific ONFI mode. There is one additional thing to do compared to SDR mode: tCAD timing can be fast or slow and this depends on an ONFI parameter page bit. By default the slow value is declared in the timings structure definition, but this helper can shrink it down if necessary. Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210505213750.257417-12-miquel.raynal@bootlin.com --- include/linux/mtd/onfi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/onfi.h b/include/linux/mtd/onfi.h index 14e66a49557e..a9677bf1e47e 100644 --- a/include/linux/mtd/onfi.h +++ b/include/linux/mtd/onfi.h @@ -162,6 +162,7 @@ struct onfi_ext_param_page { * @tBERS: Block erase time * @tR: Page read time * @tCCS: Change column setup time + * @fast_tCAD: Command/Address/Data slow or fast delay (NV-DDR only) * @sdr_timing_modes: Supported asynchronous/SDR timing modes * @nvddr_timing_modes: Supported source synchronous/NV-DDR timing modes * @vendor_revision: Vendor specific revision number @@ -173,6 +174,7 @@ struct onfi_params { u16 tBERS; u16 tR; u16 tCCS; + bool fast_tCAD; u16 sdr_timing_modes; u16 nvddr_timing_modes; u16 vendor_revision; -- cgit v1.2.3 From d7a773e8812bcf7a5412e4baebc6eb1c11242551 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 5 May 2021 23:37:41 +0200 Subject: mtd: rawnand: Access SDR and NV-DDR timings through a common macro Most timings related to the bus timings are different between SDR and NV-DDR. However, we identified 9 individual timings which are more related to the NAND chip internals. These are common between the two interface types. Fortunately, only these common timings are being shared through the NAND core and its ->exec_op() interface, which allows the writing of a simple macro checking the interface type and depending on it, returning either the relevant SDR timing or the NV-DDR timing. This is the purpose of the NAND_COMMON_TIMING_PS() macro. As all this is evaluated at build time, one will immediately be notified in case a non common timing is being accessed through this macro. Two handy macros are also inserted at the same time, which use PSEC_TO_NSEC or PSEC_TO_MSEC so that it is very easy to return timings in milli-, nano- or pico-seconds, as usually requested by the internal API. Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210505213750.257417-14-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index a53a1543d1d4..89b9c52c7387 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -557,6 +557,34 @@ struct nand_nvddr_timings { u32 tWW_min; }; +/* + * While timings related to the data interface itself are mostly different + * between SDR and NV-DDR, timings related to the internal chip behavior are + * common. IOW, the following entries which describe the internal delays have + * the same definition and are shared in both SDR and NV-DDR timing structures: + * - tADL_min + * - tBERS_max + * - tCCS_min + * - tFEAT_max + * - tPROG_max + * - tR_max + * - tRR_min + * - tRST_max + * - tWB_max + * + * The below macros return the value of a given timing, no matter the interface. + */ +#define NAND_COMMON_TIMING_PS(conf, timing_name) \ + nand_interface_is_sdr(conf) ? \ + nand_get_sdr_timings(conf)->timing_name : \ + nand_get_nvddr_timings(conf)->timing_name + +#define NAND_COMMON_TIMING_MS(conf, timing_name) \ + PSEC_TO_MSEC(NAND_COMMON_TIMING_PS((conf), timing_name)) + +#define NAND_COMMON_TIMING_NS(conf, timing_name) \ + PSEC_TO_NSEC(NAND_COMMON_TIMING_PS((conf), timing_name)) + /** * enum nand_interface_type - NAND interface type * @NAND_SDR_IFACE: Single Data Rate interface -- cgit v1.2.3 From f3fe156ede6db96a060cc98ff1bce1ee6417a68b Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 5 May 2021 23:37:44 +0200 Subject: mtd: rawnand: Support enabling NV-DDR through SET_FEATURES Until now the parameter of the ADDR_TIMING_MODE feature was just the ONFI timing mode (from 0 to 5) because we were only supporting the SDR data interface. In the same byte, bits 4 and 5 indicate which data interface is being configured so use them to set the right mode and also read them back to ensure the right timing has been setup on the chip's side. Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210505213750.257417-17-miquel.raynal@bootlin.com --- include/linux/mtd/onfi.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/onfi.h b/include/linux/mtd/onfi.h index a9677bf1e47e..a7376f9beddf 100644 --- a/include/linux/mtd/onfi.h +++ b/include/linux/mtd/onfi.h @@ -11,6 +11,7 @@ #define __LINUX_MTD_ONFI_H #include +#include /* ONFI version bits */ #define ONFI_VERSION_1_0 BIT(1) @@ -29,6 +30,9 @@ #define ONFI_FEATURE_EXT_PARAM_PAGE BIT(7) /* ONFI timing mode, used in both asynchronous and synchronous mode */ +#define ONFI_DATA_INTERFACE_SDR 0 +#define ONFI_DATA_INTERFACE_NVDDR BIT(4) +#define ONFI_DATA_INTERFACE_NVDDR2 BIT(5) #define ONFI_TIMING_MODE_0 BIT(0) #define ONFI_TIMING_MODE_1 BIT(1) #define ONFI_TIMING_MODE_2 BIT(2) @@ -36,6 +40,7 @@ #define ONFI_TIMING_MODE_4 BIT(4) #define ONFI_TIMING_MODE_5 BIT(5) #define ONFI_TIMING_MODE_UNKNOWN BIT(6) +#define ONFI_TIMING_MODE_PARAM(x) FIELD_GET(GENMASK(3, 0), (x)) /* ONFI feature number/address */ #define ONFI_FEATURE_NUMBER 256 -- cgit v1.2.3 From 9be85de97786a75f62080de1c0c13656f65cba84 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Tue, 25 May 2021 15:02:00 +0100 Subject: locking/atomic: make ARCH_ATOMIC a Kconfig symbol Subsequent patches will move architectures over to the ARCH_ATOMIC API, after preparing the asm-generic atomic implementations to function with or without ARCH_ATOMIC. As some architectures use the asm-generic implementations exclusively (and don't have a local atomic.h), and to avoid the risk that ARCH_ATOMIC isn't defined in some cases we expect, let's make the ARCH_ATOMIC macro a Kconfig symbol instead, so that we can guarantee it is consistently available where needed. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Cc: Boqun Feng Cc: Peter Zijlstra Cc: Will Deacon Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20210525140232.53872-2-mark.rutland@arm.com --- include/linux/atomic.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 571a11008ab5..4f8d83f9e480 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -77,7 +77,7 @@ __ret; \ }) -#ifdef ARCH_ATOMIC +#ifdef CONFIG_ARCH_ATOMIC #include #include #else -- cgit v1.2.3 From 3c1885187bc1faa0a1c52f7bd34550740a208169 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Tue, 25 May 2021 15:02:31 +0100 Subject: locking/atomic: delete !ARCH_ATOMIC remnants Now that all architectures implement ARCH_ATOMIC, we can make it mandatory, removing the Kconfig symbol and logic for !ARCH_ATOMIC. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Acked-by: Geert Uytterhoeven Cc: Boqun Feng Cc: Peter Zijlstra Cc: Will Deacon Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20210525140232.53872-33-mark.rutland@arm.com --- include/linux/atomic-fallback.h | 2595 --------------------------------------- include/linux/atomic.h | 4 - 2 files changed, 2599 deletions(-) delete mode 100644 include/linux/atomic-fallback.h (limited to 'include/linux') diff --git a/include/linux/atomic-fallback.h b/include/linux/atomic-fallback.h deleted file mode 100644 index 2a3f55d98be9..000000000000 --- a/include/linux/atomic-fallback.h +++ /dev/null @@ -1,2595 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -// Generated by scripts/atomic/gen-atomic-fallback.sh -// DO NOT MODIFY THIS FILE DIRECTLY - -#ifndef _LINUX_ATOMIC_FALLBACK_H -#define _LINUX_ATOMIC_FALLBACK_H - -#include - -#ifndef xchg_relaxed -#define xchg_acquire xchg -#define xchg_release xchg -#define xchg_relaxed xchg -#else /* xchg_relaxed */ - -#ifndef xchg_acquire -#define xchg_acquire(...) \ - __atomic_op_acquire(xchg, __VA_ARGS__) -#endif - -#ifndef xchg_release -#define xchg_release(...) \ - __atomic_op_release(xchg, __VA_ARGS__) -#endif - -#ifndef xchg -#define xchg(...) \ - __atomic_op_fence(xchg, __VA_ARGS__) -#endif - -#endif /* xchg_relaxed */ - -#ifndef cmpxchg_relaxed -#define cmpxchg_acquire cmpxchg -#define cmpxchg_release cmpxchg -#define cmpxchg_relaxed cmpxchg -#else /* cmpxchg_relaxed */ - -#ifndef cmpxchg_acquire -#define cmpxchg_acquire(...) \ - __atomic_op_acquire(cmpxchg, __VA_ARGS__) -#endif - -#ifndef cmpxchg_release -#define cmpxchg_release(...) \ - __atomic_op_release(cmpxchg, __VA_ARGS__) -#endif - -#ifndef cmpxchg -#define cmpxchg(...) \ - __atomic_op_fence(cmpxchg, __VA_ARGS__) -#endif - -#endif /* cmpxchg_relaxed */ - -#ifndef cmpxchg64_relaxed -#define cmpxchg64_acquire cmpxchg64 -#define cmpxchg64_release cmpxchg64 -#define cmpxchg64_relaxed cmpxchg64 -#else /* cmpxchg64_relaxed */ - -#ifndef cmpxchg64_acquire -#define cmpxchg64_acquire(...) \ - __atomic_op_acquire(cmpxchg64, __VA_ARGS__) -#endif - -#ifndef cmpxchg64_release -#define cmpxchg64_release(...) \ - __atomic_op_release(cmpxchg64, __VA_ARGS__) -#endif - -#ifndef cmpxchg64 -#define cmpxchg64(...) \ - __atomic_op_fence(cmpxchg64, __VA_ARGS__) -#endif - -#endif /* cmpxchg64_relaxed */ - -#ifndef try_cmpxchg_relaxed -#ifdef try_cmpxchg -#define try_cmpxchg_acquire try_cmpxchg -#define try_cmpxchg_release try_cmpxchg -#define try_cmpxchg_relaxed try_cmpxchg -#endif /* try_cmpxchg */ - -#ifndef try_cmpxchg -#define try_cmpxchg(_ptr, _oldp, _new) \ -({ \ - typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ - ___r = cmpxchg((_ptr), ___o, (_new)); \ - if (unlikely(___r != ___o)) \ - *___op = ___r; \ - likely(___r == ___o); \ -}) -#endif /* try_cmpxchg */ - -#ifndef try_cmpxchg_acquire -#define try_cmpxchg_acquire(_ptr, _oldp, _new) \ -({ \ - typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ - ___r = cmpxchg_acquire((_ptr), ___o, (_new)); \ - if (unlikely(___r != ___o)) \ - *___op = ___r; \ - likely(___r == ___o); \ -}) -#endif /* try_cmpxchg_acquire */ - -#ifndef try_cmpxchg_release -#define try_cmpxchg_release(_ptr, _oldp, _new) \ -({ \ - typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ - ___r = cmpxchg_release((_ptr), ___o, (_new)); \ - if (unlikely(___r != ___o)) \ - *___op = ___r; \ - likely(___r == ___o); \ -}) -#endif /* try_cmpxchg_release */ - -#ifndef try_cmpxchg_relaxed -#define try_cmpxchg_relaxed(_ptr, _oldp, _new) \ -({ \ - typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ - ___r = cmpxchg_relaxed((_ptr), ___o, (_new)); \ - if (unlikely(___r != ___o)) \ - *___op = ___r; \ - likely(___r == ___o); \ -}) -#endif /* try_cmpxchg_relaxed */ - -#else /* try_cmpxchg_relaxed */ - -#ifndef try_cmpxchg_acquire -#define try_cmpxchg_acquire(...) \ - __atomic_op_acquire(try_cmpxchg, __VA_ARGS__) -#endif - -#ifndef try_cmpxchg_release -#define try_cmpxchg_release(...) \ - __atomic_op_release(try_cmpxchg, __VA_ARGS__) -#endif - -#ifndef try_cmpxchg -#define try_cmpxchg(...) \ - __atomic_op_fence(try_cmpxchg, __VA_ARGS__) -#endif - -#endif /* try_cmpxchg_relaxed */ - -#define arch_atomic_read atomic_read -#define arch_atomic_read_acquire atomic_read_acquire - -#ifndef atomic_read_acquire -static __always_inline int -atomic_read_acquire(const atomic_t *v) -{ - return smp_load_acquire(&(v)->counter); -} -#define atomic_read_acquire atomic_read_acquire -#endif - -#define arch_atomic_set atomic_set -#define arch_atomic_set_release atomic_set_release - -#ifndef atomic_set_release -static __always_inline void -atomic_set_release(atomic_t *v, int i) -{ - smp_store_release(&(v)->counter, i); -} -#define atomic_set_release atomic_set_release -#endif - -#define arch_atomic_add atomic_add - -#define arch_atomic_add_return atomic_add_return -#define arch_atomic_add_return_acquire atomic_add_return_acquire -#define arch_atomic_add_return_release atomic_add_return_release -#define arch_atomic_add_return_relaxed atomic_add_return_relaxed - -#ifndef atomic_add_return_relaxed -#define atomic_add_return_acquire atomic_add_return -#define atomic_add_return_release atomic_add_return -#define atomic_add_return_relaxed atomic_add_return -#else /* atomic_add_return_relaxed */ - -#ifndef atomic_add_return_acquire -static __always_inline int -atomic_add_return_acquire(int i, atomic_t *v) -{ - int ret = atomic_add_return_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define atomic_add_return_acquire atomic_add_return_acquire -#endif - -#ifndef atomic_add_return_release -static __always_inline int -atomic_add_return_release(int i, atomic_t *v) -{ - __atomic_release_fence(); - return atomic_add_return_relaxed(i, v); -} -#define atomic_add_return_release atomic_add_return_release -#endif - -#ifndef atomic_add_return -static __always_inline int -atomic_add_return(int i, atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = atomic_add_return_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define atomic_add_return atomic_add_return -#endif - -#endif /* atomic_add_return_relaxed */ - -#define arch_atomic_fetch_add atomic_fetch_add -#define arch_atomic_fetch_add_acquire atomic_fetch_add_acquire -#define arch_atomic_fetch_add_release atomic_fetch_add_release -#define arch_atomic_fetch_add_relaxed atomic_fetch_add_relaxed - -#ifndef atomic_fetch_add_relaxed -#define atomic_fetch_add_acquire atomic_fetch_add -#define atomic_fetch_add_release atomic_fetch_add -#define atomic_fetch_add_relaxed atomic_fetch_add -#else /* atomic_fetch_add_relaxed */ - -#ifndef atomic_fetch_add_acquire -static __always_inline int -atomic_fetch_add_acquire(int i, atomic_t *v) -{ - int ret = atomic_fetch_add_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define atomic_fetch_add_acquire atomic_fetch_add_acquire -#endif - -#ifndef atomic_fetch_add_release -static __always_inline int -atomic_fetch_add_release(int i, atomic_t *v) -{ - __atomic_release_fence(); - return atomic_fetch_add_relaxed(i, v); -} -#define atomic_fetch_add_release atomic_fetch_add_release -#endif - -#ifndef atomic_fetch_add -static __always_inline int -atomic_fetch_add(int i, atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = atomic_fetch_add_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define atomic_fetch_add atomic_fetch_add -#endif - -#endif /* atomic_fetch_add_relaxed */ - -#define arch_atomic_sub atomic_sub - -#define arch_atomic_sub_return atomic_sub_return -#define arch_atomic_sub_return_acquire atomic_sub_return_acquire -#define arch_atomic_sub_return_release atomic_sub_return_release -#define arch_atomic_sub_return_relaxed atomic_sub_return_relaxed - -#ifndef atomic_sub_return_relaxed -#define atomic_sub_return_acquire atomic_sub_return -#define atomic_sub_return_release atomic_sub_return -#define atomic_sub_return_relaxed atomic_sub_return -#else /* atomic_sub_return_relaxed */ - -#ifndef atomic_sub_return_acquire -static __always_inline int -atomic_sub_return_acquire(int i, atomic_t *v) -{ - int ret = atomic_sub_return_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define atomic_sub_return_acquire atomic_sub_return_acquire -#endif - -#ifndef atomic_sub_return_release -static __always_inline int -atomic_sub_return_release(int i, atomic_t *v) -{ - __atomic_release_fence(); - return atomic_sub_return_relaxed(i, v); -} -#define atomic_sub_return_release atomic_sub_return_release -#endif - -#ifndef atomic_sub_return -static __always_inline int -atomic_sub_return(int i, atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = atomic_sub_return_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define atomic_sub_return atomic_sub_return -#endif - -#endif /* atomic_sub_return_relaxed */ - -#define arch_atomic_fetch_sub atomic_fetch_sub -#define arch_atomic_fetch_sub_acquire atomic_fetch_sub_acquire -#define arch_atomic_fetch_sub_release atomic_fetch_sub_release -#define arch_atomic_fetch_sub_relaxed atomic_fetch_sub_relaxed - -#ifndef atomic_fetch_sub_relaxed -#define atomic_fetch_sub_acquire atomic_fetch_sub -#define atomic_fetch_sub_release atomic_fetch_sub -#define atomic_fetch_sub_relaxed atomic_fetch_sub -#else /* atomic_fetch_sub_relaxed */ - -#ifndef atomic_fetch_sub_acquire -static __always_inline int -atomic_fetch_sub_acquire(int i, atomic_t *v) -{ - int ret = atomic_fetch_sub_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define atomic_fetch_sub_acquire atomic_fetch_sub_acquire -#endif - -#ifndef atomic_fetch_sub_release -static __always_inline int -atomic_fetch_sub_release(int i, atomic_t *v) -{ - __atomic_release_fence(); - return atomic_fetch_sub_relaxed(i, v); -} -#define atomic_fetch_sub_release atomic_fetch_sub_release -#endif - -#ifndef atomic_fetch_sub -static __always_inline int -atomic_fetch_sub(int i, atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = atomic_fetch_sub_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define atomic_fetch_sub atomic_fetch_sub -#endif - -#endif /* atomic_fetch_sub_relaxed */ - -#define arch_atomic_inc atomic_inc - -#ifndef atomic_inc -static __always_inline void -atomic_inc(atomic_t *v) -{ - atomic_add(1, v); -} -#define atomic_inc atomic_inc -#endif - -#define arch_atomic_inc_return atomic_inc_return -#define arch_atomic_inc_return_acquire atomic_inc_return_acquire -#define arch_atomic_inc_return_release atomic_inc_return_release -#define arch_atomic_inc_return_relaxed atomic_inc_return_relaxed - -#ifndef atomic_inc_return_relaxed -#ifdef atomic_inc_return -#define atomic_inc_return_acquire atomic_inc_return -#define atomic_inc_return_release atomic_inc_return -#define atomic_inc_return_relaxed atomic_inc_return -#endif /* atomic_inc_return */ - -#ifndef atomic_inc_return -static __always_inline int -atomic_inc_return(atomic_t *v) -{ - return atomic_add_return(1, v); -} -#define atomic_inc_return atomic_inc_return -#endif - -#ifndef atomic_inc_return_acquire -static __always_inline int -atomic_inc_return_acquire(atomic_t *v) -{ - return atomic_add_return_acquire(1, v); -} -#define atomic_inc_return_acquire atomic_inc_return_acquire -#endif - -#ifndef atomic_inc_return_release -static __always_inline int -atomic_inc_return_release(atomic_t *v) -{ - return atomic_add_return_release(1, v); -} -#define atomic_inc_return_release atomic_inc_return_release -#endif - -#ifndef atomic_inc_return_relaxed -static __always_inline int -atomic_inc_return_relaxed(atomic_t *v) -{ - return atomic_add_return_relaxed(1, v); -} -#define atomic_inc_return_relaxed atomic_inc_return_relaxed -#endif - -#else /* atomic_inc_return_relaxed */ - -#ifndef atomic_inc_return_acquire -static __always_inline int -atomic_inc_return_acquire(atomic_t *v) -{ - int ret = atomic_inc_return_relaxed(v); - __atomic_acquire_fence(); - return ret; -} -#define atomic_inc_return_acquire atomic_inc_return_acquire -#endif - -#ifndef atomic_inc_return_release -static __always_inline int -atomic_inc_return_release(atomic_t *v) -{ - __atomic_release_fence(); - return atomic_inc_return_relaxed(v); -} -#define atomic_inc_return_release atomic_inc_return_release -#endif - -#ifndef atomic_inc_return -static __always_inline int -atomic_inc_return(atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = atomic_inc_return_relaxed(v); - __atomic_post_full_fence(); - return ret; -} -#define atomic_inc_return atomic_inc_return -#endif - -#endif /* atomic_inc_return_relaxed */ - -#define arch_atomic_fetch_inc atomic_fetch_inc -#define arch_atomic_fetch_inc_acquire atomic_fetch_inc_acquire -#define arch_atomic_fetch_inc_release atomic_fetch_inc_release -#define arch_atomic_fetch_inc_relaxed atomic_fetch_inc_relaxed - -#ifndef atomic_fetch_inc_relaxed -#ifdef atomic_fetch_inc -#define atomic_fetch_inc_acquire atomic_fetch_inc -#define atomic_fetch_inc_release atomic_fetch_inc -#define atomic_fetch_inc_relaxed atomic_fetch_inc -#endif /* atomic_fetch_inc */ - -#ifndef atomic_fetch_inc -static __always_inline int -atomic_fetch_inc(atomic_t *v) -{ - return atomic_fetch_add(1, v); -} -#define atomic_fetch_inc atomic_fetch_inc -#endif - -#ifndef atomic_fetch_inc_acquire -static __always_inline int -atomic_fetch_inc_acquire(atomic_t *v) -{ - return atomic_fetch_add_acquire(1, v); -} -#define atomic_fetch_inc_acquire atomic_fetch_inc_acquire -#endif - -#ifndef atomic_fetch_inc_release -static __always_inline int -atomic_fetch_inc_release(atomic_t *v) -{ - return atomic_fetch_add_release(1, v); -} -#define atomic_fetch_inc_release atomic_fetch_inc_release -#endif - -#ifndef atomic_fetch_inc_relaxed -static __always_inline int -atomic_fetch_inc_relaxed(atomic_t *v) -{ - return atomic_fetch_add_relaxed(1, v); -} -#define atomic_fetch_inc_relaxed atomic_fetch_inc_relaxed -#endif - -#else /* atomic_fetch_inc_relaxed */ - -#ifndef atomic_fetch_inc_acquire -static __always_inline int -atomic_fetch_inc_acquire(atomic_t *v) -{ - int ret = atomic_fetch_inc_relaxed(v); - __atomic_acquire_fence(); - return ret; -} -#define atomic_fetch_inc_acquire atomic_fetch_inc_acquire -#endif - -#ifndef atomic_fetch_inc_release -static __always_inline int -atomic_fetch_inc_release(atomic_t *v) -{ - __atomic_release_fence(); - return atomic_fetch_inc_relaxed(v); -} -#define atomic_fetch_inc_release atomic_fetch_inc_release -#endif - -#ifndef atomic_fetch_inc -static __always_inline int -atomic_fetch_inc(atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = atomic_fetch_inc_relaxed(v); - __atomic_post_full_fence(); - return ret; -} -#define atomic_fetch_inc atomic_fetch_inc -#endif - -#endif /* atomic_fetch_inc_relaxed */ - -#define arch_atomic_dec atomic_dec - -#ifndef atomic_dec -static __always_inline void -atomic_dec(atomic_t *v) -{ - atomic_sub(1, v); -} -#define atomic_dec atomic_dec -#endif - -#define arch_atomic_dec_return atomic_dec_return -#define arch_atomic_dec_return_acquire atomic_dec_return_acquire -#define arch_atomic_dec_return_release atomic_dec_return_release -#define arch_atomic_dec_return_relaxed atomic_dec_return_relaxed - -#ifndef atomic_dec_return_relaxed -#ifdef atomic_dec_return -#define atomic_dec_return_acquire atomic_dec_return -#define atomic_dec_return_release atomic_dec_return -#define atomic_dec_return_relaxed atomic_dec_return -#endif /* atomic_dec_return */ - -#ifndef atomic_dec_return -static __always_inline int -atomic_dec_return(atomic_t *v) -{ - return atomic_sub_return(1, v); -} -#define atomic_dec_return atomic_dec_return -#endif - -#ifndef atomic_dec_return_acquire -static __always_inline int -atomic_dec_return_acquire(atomic_t *v) -{ - return atomic_sub_return_acquire(1, v); -} -#define atomic_dec_return_acquire atomic_dec_return_acquire -#endif - -#ifndef atomic_dec_return_release -static __always_inline int -atomic_dec_return_release(atomic_t *v) -{ - return atomic_sub_return_release(1, v); -} -#define atomic_dec_return_release atomic_dec_return_release -#endif - -#ifndef atomic_dec_return_relaxed -static __always_inline int -atomic_dec_return_relaxed(atomic_t *v) -{ - return atomic_sub_return_relaxed(1, v); -} -#define atomic_dec_return_relaxed atomic_dec_return_relaxed -#endif - -#else /* atomic_dec_return_relaxed */ - -#ifndef atomic_dec_return_acquire -static __always_inline int -atomic_dec_return_acquire(atomic_t *v) -{ - int ret = atomic_dec_return_relaxed(v); - __atomic_acquire_fence(); - return ret; -} -#define atomic_dec_return_acquire atomic_dec_return_acquire -#endif - -#ifndef atomic_dec_return_release -static __always_inline int -atomic_dec_return_release(atomic_t *v) -{ - __atomic_release_fence(); - return atomic_dec_return_relaxed(v); -} -#define atomic_dec_return_release atomic_dec_return_release -#endif - -#ifndef atomic_dec_return -static __always_inline int -atomic_dec_return(atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = atomic_dec_return_relaxed(v); - __atomic_post_full_fence(); - return ret; -} -#define atomic_dec_return atomic_dec_return -#endif - -#endif /* atomic_dec_return_relaxed */ - -#define arch_atomic_fetch_dec atomic_fetch_dec -#define arch_atomic_fetch_dec_acquire atomic_fetch_dec_acquire -#define arch_atomic_fetch_dec_release atomic_fetch_dec_release -#define arch_atomic_fetch_dec_relaxed atomic_fetch_dec_relaxed - -#ifndef atomic_fetch_dec_relaxed -#ifdef atomic_fetch_dec -#define atomic_fetch_dec_acquire atomic_fetch_dec -#define atomic_fetch_dec_release atomic_fetch_dec -#define atomic_fetch_dec_relaxed atomic_fetch_dec -#endif /* atomic_fetch_dec */ - -#ifndef atomic_fetch_dec -static __always_inline int -atomic_fetch_dec(atomic_t *v) -{ - return atomic_fetch_sub(1, v); -} -#define atomic_fetch_dec atomic_fetch_dec -#endif - -#ifndef atomic_fetch_dec_acquire -static __always_inline int -atomic_fetch_dec_acquire(atomic_t *v) -{ - return atomic_fetch_sub_acquire(1, v); -} -#define atomic_fetch_dec_acquire atomic_fetch_dec_acquire -#endif - -#ifndef atomic_fetch_dec_release -static __always_inline int -atomic_fetch_dec_release(atomic_t *v) -{ - return atomic_fetch_sub_release(1, v); -} -#define atomic_fetch_dec_release atomic_fetch_dec_release -#endif - -#ifndef atomic_fetch_dec_relaxed -static __always_inline int -atomic_fetch_dec_relaxed(atomic_t *v) -{ - return atomic_fetch_sub_relaxed(1, v); -} -#define atomic_fetch_dec_relaxed atomic_fetch_dec_relaxed -#endif - -#else /* atomic_fetch_dec_relaxed */ - -#ifndef atomic_fetch_dec_acquire -static __always_inline int -atomic_fetch_dec_acquire(atomic_t *v) -{ - int ret = atomic_fetch_dec_relaxed(v); - __atomic_acquire_fence(); - return ret; -} -#define atomic_fetch_dec_acquire atomic_fetch_dec_acquire -#endif - -#ifndef atomic_fetch_dec_release -static __always_inline int -atomic_fetch_dec_release(atomic_t *v) -{ - __atomic_release_fence(); - return atomic_fetch_dec_relaxed(v); -} -#define atomic_fetch_dec_release atomic_fetch_dec_release -#endif - -#ifndef atomic_fetch_dec -static __always_inline int -atomic_fetch_dec(atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = atomic_fetch_dec_relaxed(v); - __atomic_post_full_fence(); - return ret; -} -#define atomic_fetch_dec atomic_fetch_dec -#endif - -#endif /* atomic_fetch_dec_relaxed */ - -#define arch_atomic_and atomic_and - -#define arch_atomic_fetch_and atomic_fetch_and -#define arch_atomic_fetch_and_acquire atomic_fetch_and_acquire -#define arch_atomic_fetch_and_release atomic_fetch_and_release -#define arch_atomic_fetch_and_relaxed atomic_fetch_and_relaxed - -#ifndef atomic_fetch_and_relaxed -#define atomic_fetch_and_acquire atomic_fetch_and -#define atomic_fetch_and_release atomic_fetch_and -#define atomic_fetch_and_relaxed atomic_fetch_and -#else /* atomic_fetch_and_relaxed */ - -#ifndef atomic_fetch_and_acquire -static __always_inline int -atomic_fetch_and_acquire(int i, atomic_t *v) -{ - int ret = atomic_fetch_and_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define atomic_fetch_and_acquire atomic_fetch_and_acquire -#endif - -#ifndef atomic_fetch_and_release -static __always_inline int -atomic_fetch_and_release(int i, atomic_t *v) -{ - __atomic_release_fence(); - return atomic_fetch_and_relaxed(i, v); -} -#define atomic_fetch_and_release atomic_fetch_and_release -#endif - -#ifndef atomic_fetch_and -static __always_inline int -atomic_fetch_and(int i, atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = atomic_fetch_and_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define atomic_fetch_and atomic_fetch_and -#endif - -#endif /* atomic_fetch_and_relaxed */ - -#define arch_atomic_andnot atomic_andnot - -#ifndef atomic_andnot -static __always_inline void -atomic_andnot(int i, atomic_t *v) -{ - atomic_and(~i, v); -} -#define atomic_andnot atomic_andnot -#endif - -#define arch_atomic_fetch_andnot atomic_fetch_andnot -#define arch_atomic_fetch_andnot_acquire atomic_fetch_andnot_acquire -#define arch_atomic_fetch_andnot_release atomic_fetch_andnot_release -#define arch_atomic_fetch_andnot_relaxed atomic_fetch_andnot_relaxed - -#ifndef atomic_fetch_andnot_relaxed -#ifdef atomic_fetch_andnot -#define atomic_fetch_andnot_acquire atomic_fetch_andnot -#define atomic_fetch_andnot_release atomic_fetch_andnot -#define atomic_fetch_andnot_relaxed atomic_fetch_andnot -#endif /* atomic_fetch_andnot */ - -#ifndef atomic_fetch_andnot -static __always_inline int -atomic_fetch_andnot(int i, atomic_t *v) -{ - return atomic_fetch_and(~i, v); -} -#define atomic_fetch_andnot atomic_fetch_andnot -#endif - -#ifndef atomic_fetch_andnot_acquire -static __always_inline int -atomic_fetch_andnot_acquire(int i, atomic_t *v) -{ - return atomic_fetch_and_acquire(~i, v); -} -#define atomic_fetch_andnot_acquire atomic_fetch_andnot_acquire -#endif - -#ifndef atomic_fetch_andnot_release -static __always_inline int -atomic_fetch_andnot_release(int i, atomic_t *v) -{ - return atomic_fetch_and_release(~i, v); -} -#define atomic_fetch_andnot_release atomic_fetch_andnot_release -#endif - -#ifndef atomic_fetch_andnot_relaxed -static __always_inline int -atomic_fetch_andnot_relaxed(int i, atomic_t *v) -{ - return atomic_fetch_and_relaxed(~i, v); -} -#define atomic_fetch_andnot_relaxed atomic_fetch_andnot_relaxed -#endif - -#else /* atomic_fetch_andnot_relaxed */ - -#ifndef atomic_fetch_andnot_acquire -static __always_inline int -atomic_fetch_andnot_acquire(int i, atomic_t *v) -{ - int ret = atomic_fetch_andnot_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define atomic_fetch_andnot_acquire atomic_fetch_andnot_acquire -#endif - -#ifndef atomic_fetch_andnot_release -static __always_inline int -atomic_fetch_andnot_release(int i, atomic_t *v) -{ - __atomic_release_fence(); - return atomic_fetch_andnot_relaxed(i, v); -} -#define atomic_fetch_andnot_release atomic_fetch_andnot_release -#endif - -#ifndef atomic_fetch_andnot -static __always_inline int -atomic_fetch_andnot(int i, atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = atomic_fetch_andnot_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define atomic_fetch_andnot atomic_fetch_andnot -#endif - -#endif /* atomic_fetch_andnot_relaxed */ - -#define arch_atomic_or atomic_or - -#define arch_atomic_fetch_or atomic_fetch_or -#define arch_atomic_fetch_or_acquire atomic_fetch_or_acquire -#define arch_atomic_fetch_or_release atomic_fetch_or_release -#define arch_atomic_fetch_or_relaxed atomic_fetch_or_relaxed - -#ifndef atomic_fetch_or_relaxed -#define atomic_fetch_or_acquire atomic_fetch_or -#define atomic_fetch_or_release atomic_fetch_or -#define atomic_fetch_or_relaxed atomic_fetch_or -#else /* atomic_fetch_or_relaxed */ - -#ifndef atomic_fetch_or_acquire -static __always_inline int -atomic_fetch_or_acquire(int i, atomic_t *v) -{ - int ret = atomic_fetch_or_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define atomic_fetch_or_acquire atomic_fetch_or_acquire -#endif - -#ifndef atomic_fetch_or_release -static __always_inline int -atomic_fetch_or_release(int i, atomic_t *v) -{ - __atomic_release_fence(); - return atomic_fetch_or_relaxed(i, v); -} -#define atomic_fetch_or_release atomic_fetch_or_release -#endif - -#ifndef atomic_fetch_or -static __always_inline int -atomic_fetch_or(int i, atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = atomic_fetch_or_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define atomic_fetch_or atomic_fetch_or -#endif - -#endif /* atomic_fetch_or_relaxed */ - -#define arch_atomic_xor atomic_xor - -#define arch_atomic_fetch_xor atomic_fetch_xor -#define arch_atomic_fetch_xor_acquire atomic_fetch_xor_acquire -#define arch_atomic_fetch_xor_release atomic_fetch_xor_release -#define arch_atomic_fetch_xor_relaxed atomic_fetch_xor_relaxed - -#ifndef atomic_fetch_xor_relaxed -#define atomic_fetch_xor_acquire atomic_fetch_xor -#define atomic_fetch_xor_release atomic_fetch_xor -#define atomic_fetch_xor_relaxed atomic_fetch_xor -#else /* atomic_fetch_xor_relaxed */ - -#ifndef atomic_fetch_xor_acquire -static __always_inline int -atomic_fetch_xor_acquire(int i, atomic_t *v) -{ - int ret = atomic_fetch_xor_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define atomic_fetch_xor_acquire atomic_fetch_xor_acquire -#endif - -#ifndef atomic_fetch_xor_release -static __always_inline int -atomic_fetch_xor_release(int i, atomic_t *v) -{ - __atomic_release_fence(); - return atomic_fetch_xor_relaxed(i, v); -} -#define atomic_fetch_xor_release atomic_fetch_xor_release -#endif - -#ifndef atomic_fetch_xor -static __always_inline int -atomic_fetch_xor(int i, atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = atomic_fetch_xor_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define atomic_fetch_xor atomic_fetch_xor -#endif - -#endif /* atomic_fetch_xor_relaxed */ - -#define arch_atomic_xchg atomic_xchg -#define arch_atomic_xchg_acquire atomic_xchg_acquire -#define arch_atomic_xchg_release atomic_xchg_release -#define arch_atomic_xchg_relaxed atomic_xchg_relaxed - -#ifndef atomic_xchg_relaxed -#define atomic_xchg_acquire atomic_xchg -#define atomic_xchg_release atomic_xchg -#define atomic_xchg_relaxed atomic_xchg -#else /* atomic_xchg_relaxed */ - -#ifndef atomic_xchg_acquire -static __always_inline int -atomic_xchg_acquire(atomic_t *v, int i) -{ - int ret = atomic_xchg_relaxed(v, i); - __atomic_acquire_fence(); - return ret; -} -#define atomic_xchg_acquire atomic_xchg_acquire -#endif - -#ifndef atomic_xchg_release -static __always_inline int -atomic_xchg_release(atomic_t *v, int i) -{ - __atomic_release_fence(); - return atomic_xchg_relaxed(v, i); -} -#define atomic_xchg_release atomic_xchg_release -#endif - -#ifndef atomic_xchg -static __always_inline int -atomic_xchg(atomic_t *v, int i) -{ - int ret; - __atomic_pre_full_fence(); - ret = atomic_xchg_relaxed(v, i); - __atomic_post_full_fence(); - return ret; -} -#define atomic_xchg atomic_xchg -#endif - -#endif /* atomic_xchg_relaxed */ - -#define arch_atomic_cmpxchg atomic_cmpxchg -#define arch_atomic_cmpxchg_acquire atomic_cmpxchg_acquire -#define arch_atomic_cmpxchg_release atomic_cmpxchg_release -#define arch_atomic_cmpxchg_relaxed atomic_cmpxchg_relaxed - -#ifndef atomic_cmpxchg_relaxed -#define atomic_cmpxchg_acquire atomic_cmpxchg -#define atomic_cmpxchg_release atomic_cmpxchg -#define atomic_cmpxchg_relaxed atomic_cmpxchg -#else /* atomic_cmpxchg_relaxed */ - -#ifndef atomic_cmpxchg_acquire -static __always_inline int -atomic_cmpxchg_acquire(atomic_t *v, int old, int new) -{ - int ret = atomic_cmpxchg_relaxed(v, old, new); - __atomic_acquire_fence(); - return ret; -} -#define atomic_cmpxchg_acquire atomic_cmpxchg_acquire -#endif - -#ifndef atomic_cmpxchg_release -static __always_inline int -atomic_cmpxchg_release(atomic_t *v, int old, int new) -{ - __atomic_release_fence(); - return atomic_cmpxchg_relaxed(v, old, new); -} -#define atomic_cmpxchg_release atomic_cmpxchg_release -#endif - -#ifndef atomic_cmpxchg -static __always_inline int -atomic_cmpxchg(atomic_t *v, int old, int new) -{ - int ret; - __atomic_pre_full_fence(); - ret = atomic_cmpxchg_relaxed(v, old, new); - __atomic_post_full_fence(); - return ret; -} -#define atomic_cmpxchg atomic_cmpxchg -#endif - -#endif /* atomic_cmpxchg_relaxed */ - -#define arch_atomic_try_cmpxchg atomic_try_cmpxchg -#define arch_atomic_try_cmpxchg_acquire atomic_try_cmpxchg_acquire -#define arch_atomic_try_cmpxchg_release atomic_try_cmpxchg_release -#define arch_atomic_try_cmpxchg_relaxed atomic_try_cmpxchg_relaxed - -#ifndef atomic_try_cmpxchg_relaxed -#ifdef atomic_try_cmpxchg -#define atomic_try_cmpxchg_acquire atomic_try_cmpxchg -#define atomic_try_cmpxchg_release atomic_try_cmpxchg -#define atomic_try_cmpxchg_relaxed atomic_try_cmpxchg -#endif /* atomic_try_cmpxchg */ - -#ifndef atomic_try_cmpxchg -static __always_inline bool -atomic_try_cmpxchg(atomic_t *v, int *old, int new) -{ - int r, o = *old; - r = atomic_cmpxchg(v, o, new); - if (unlikely(r != o)) - *old = r; - return likely(r == o); -} -#define atomic_try_cmpxchg atomic_try_cmpxchg -#endif - -#ifndef atomic_try_cmpxchg_acquire -static __always_inline bool -atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) -{ - int r, o = *old; - r = atomic_cmpxchg_acquire(v, o, new); - if (unlikely(r != o)) - *old = r; - return likely(r == o); -} -#define atomic_try_cmpxchg_acquire atomic_try_cmpxchg_acquire -#endif - -#ifndef atomic_try_cmpxchg_release -static __always_inline bool -atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) -{ - int r, o = *old; - r = atomic_cmpxchg_release(v, o, new); - if (unlikely(r != o)) - *old = r; - return likely(r == o); -} -#define atomic_try_cmpxchg_release atomic_try_cmpxchg_release -#endif - -#ifndef atomic_try_cmpxchg_relaxed -static __always_inline bool -atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) -{ - int r, o = *old; - r = atomic_cmpxchg_relaxed(v, o, new); - if (unlikely(r != o)) - *old = r; - return likely(r == o); -} -#define atomic_try_cmpxchg_relaxed atomic_try_cmpxchg_relaxed -#endif - -#else /* atomic_try_cmpxchg_relaxed */ - -#ifndef atomic_try_cmpxchg_acquire -static __always_inline bool -atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) -{ - bool ret = atomic_try_cmpxchg_relaxed(v, old, new); - __atomic_acquire_fence(); - return ret; -} -#define atomic_try_cmpxchg_acquire atomic_try_cmpxchg_acquire -#endif - -#ifndef atomic_try_cmpxchg_release -static __always_inline bool -atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) -{ - __atomic_release_fence(); - return atomic_try_cmpxchg_relaxed(v, old, new); -} -#define atomic_try_cmpxchg_release atomic_try_cmpxchg_release -#endif - -#ifndef atomic_try_cmpxchg -static __always_inline bool -atomic_try_cmpxchg(atomic_t *v, int *old, int new) -{ - bool ret; - __atomic_pre_full_fence(); - ret = atomic_try_cmpxchg_relaxed(v, old, new); - __atomic_post_full_fence(); - return ret; -} -#define atomic_try_cmpxchg atomic_try_cmpxchg -#endif - -#endif /* atomic_try_cmpxchg_relaxed */ - -#define arch_atomic_sub_and_test atomic_sub_and_test - -#ifndef atomic_sub_and_test -/** - * atomic_sub_and_test - subtract value from variable and test result - * @i: integer value to subtract - * @v: pointer of type atomic_t - * - * Atomically subtracts @i from @v and returns - * true if the result is zero, or false for all - * other cases. - */ -static __always_inline bool -atomic_sub_and_test(int i, atomic_t *v) -{ - return atomic_sub_return(i, v) == 0; -} -#define atomic_sub_and_test atomic_sub_and_test -#endif - -#define arch_atomic_dec_and_test atomic_dec_and_test - -#ifndef atomic_dec_and_test -/** - * atomic_dec_and_test - decrement and test - * @v: pointer of type atomic_t - * - * Atomically decrements @v by 1 and - * returns true if the result is 0, or false for all other - * cases. - */ -static __always_inline bool -atomic_dec_and_test(atomic_t *v) -{ - return atomic_dec_return(v) == 0; -} -#define atomic_dec_and_test atomic_dec_and_test -#endif - -#define arch_atomic_inc_and_test atomic_inc_and_test - -#ifndef atomic_inc_and_test -/** - * atomic_inc_and_test - increment and test - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -static __always_inline bool -atomic_inc_and_test(atomic_t *v) -{ - return atomic_inc_return(v) == 0; -} -#define atomic_inc_and_test atomic_inc_and_test -#endif - -#define arch_atomic_add_negative atomic_add_negative - -#ifndef atomic_add_negative -/** - * atomic_add_negative - add and test if negative - * @i: integer value to add - * @v: pointer of type atomic_t - * - * Atomically adds @i to @v and returns true - * if the result is negative, or false when - * result is greater than or equal to zero. - */ -static __always_inline bool -atomic_add_negative(int i, atomic_t *v) -{ - return atomic_add_return(i, v) < 0; -} -#define atomic_add_negative atomic_add_negative -#endif - -#define arch_atomic_fetch_add_unless atomic_fetch_add_unless - -#ifndef atomic_fetch_add_unless -/** - * atomic_fetch_add_unless - add unless the number is already a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as @v was not already @u. - * Returns original value of @v - */ -static __always_inline int -atomic_fetch_add_unless(atomic_t *v, int a, int u) -{ - int c = atomic_read(v); - - do { - if (unlikely(c == u)) - break; - } while (!atomic_try_cmpxchg(v, &c, c + a)); - - return c; -} -#define atomic_fetch_add_unless atomic_fetch_add_unless -#endif - -#define arch_atomic_add_unless atomic_add_unless - -#ifndef atomic_add_unless -/** - * atomic_add_unless - add unless the number is already a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, if @v was not already @u. - * Returns true if the addition was done. - */ -static __always_inline bool -atomic_add_unless(atomic_t *v, int a, int u) -{ - return atomic_fetch_add_unless(v, a, u) != u; -} -#define atomic_add_unless atomic_add_unless -#endif - -#define arch_atomic_inc_not_zero atomic_inc_not_zero - -#ifndef atomic_inc_not_zero -/** - * atomic_inc_not_zero - increment unless the number is zero - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1, if @v is non-zero. - * Returns true if the increment was done. - */ -static __always_inline bool -atomic_inc_not_zero(atomic_t *v) -{ - return atomic_add_unless(v, 1, 0); -} -#define atomic_inc_not_zero atomic_inc_not_zero -#endif - -#define arch_atomic_inc_unless_negative atomic_inc_unless_negative - -#ifndef atomic_inc_unless_negative -static __always_inline bool -atomic_inc_unless_negative(atomic_t *v) -{ - int c = atomic_read(v); - - do { - if (unlikely(c < 0)) - return false; - } while (!atomic_try_cmpxchg(v, &c, c + 1)); - - return true; -} -#define atomic_inc_unless_negative atomic_inc_unless_negative -#endif - -#define arch_atomic_dec_unless_positive atomic_dec_unless_positive - -#ifndef atomic_dec_unless_positive -static __always_inline bool -atomic_dec_unless_positive(atomic_t *v) -{ - int c = atomic_read(v); - - do { - if (unlikely(c > 0)) - return false; - } while (!atomic_try_cmpxchg(v, &c, c - 1)); - - return true; -} -#define atomic_dec_unless_positive atomic_dec_unless_positive -#endif - -#define arch_atomic_dec_if_positive atomic_dec_if_positive - -#ifndef atomic_dec_if_positive -static __always_inline int -atomic_dec_if_positive(atomic_t *v) -{ - int dec, c = atomic_read(v); - - do { - dec = c - 1; - if (unlikely(dec < 0)) - break; - } while (!atomic_try_cmpxchg(v, &c, dec)); - - return dec; -} -#define atomic_dec_if_positive atomic_dec_if_positive -#endif - -#ifdef CONFIG_GENERIC_ATOMIC64 -#include -#endif - -#define arch_atomic64_read atomic64_read -#define arch_atomic64_read_acquire atomic64_read_acquire - -#ifndef atomic64_read_acquire -static __always_inline s64 -atomic64_read_acquire(const atomic64_t *v) -{ - return smp_load_acquire(&(v)->counter); -} -#define atomic64_read_acquire atomic64_read_acquire -#endif - -#define arch_atomic64_set atomic64_set -#define arch_atomic64_set_release atomic64_set_release - -#ifndef atomic64_set_release -static __always_inline void -atomic64_set_release(atomic64_t *v, s64 i) -{ - smp_store_release(&(v)->counter, i); -} -#define atomic64_set_release atomic64_set_release -#endif - -#define arch_atomic64_add atomic64_add - -#define arch_atomic64_add_return atomic64_add_return -#define arch_atomic64_add_return_acquire atomic64_add_return_acquire -#define arch_atomic64_add_return_release atomic64_add_return_release -#define arch_atomic64_add_return_relaxed atomic64_add_return_relaxed - -#ifndef atomic64_add_return_relaxed -#define atomic64_add_return_acquire atomic64_add_return -#define atomic64_add_return_release atomic64_add_return -#define atomic64_add_return_relaxed atomic64_add_return -#else /* atomic64_add_return_relaxed */ - -#ifndef atomic64_add_return_acquire -static __always_inline s64 -atomic64_add_return_acquire(s64 i, atomic64_t *v) -{ - s64 ret = atomic64_add_return_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define atomic64_add_return_acquire atomic64_add_return_acquire -#endif - -#ifndef atomic64_add_return_release -static __always_inline s64 -atomic64_add_return_release(s64 i, atomic64_t *v) -{ - __atomic_release_fence(); - return atomic64_add_return_relaxed(i, v); -} -#define atomic64_add_return_release atomic64_add_return_release -#endif - -#ifndef atomic64_add_return -static __always_inline s64 -atomic64_add_return(s64 i, atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = atomic64_add_return_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define atomic64_add_return atomic64_add_return -#endif - -#endif /* atomic64_add_return_relaxed */ - -#define arch_atomic64_fetch_add atomic64_fetch_add -#define arch_atomic64_fetch_add_acquire atomic64_fetch_add_acquire -#define arch_atomic64_fetch_add_release atomic64_fetch_add_release -#define arch_atomic64_fetch_add_relaxed atomic64_fetch_add_relaxed - -#ifndef atomic64_fetch_add_relaxed -#define atomic64_fetch_add_acquire atomic64_fetch_add -#define atomic64_fetch_add_release atomic64_fetch_add -#define atomic64_fetch_add_relaxed atomic64_fetch_add -#else /* atomic64_fetch_add_relaxed */ - -#ifndef atomic64_fetch_add_acquire -static __always_inline s64 -atomic64_fetch_add_acquire(s64 i, atomic64_t *v) -{ - s64 ret = atomic64_fetch_add_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define atomic64_fetch_add_acquire atomic64_fetch_add_acquire -#endif - -#ifndef atomic64_fetch_add_release -static __always_inline s64 -atomic64_fetch_add_release(s64 i, atomic64_t *v) -{ - __atomic_release_fence(); - return atomic64_fetch_add_relaxed(i, v); -} -#define atomic64_fetch_add_release atomic64_fetch_add_release -#endif - -#ifndef atomic64_fetch_add -static __always_inline s64 -atomic64_fetch_add(s64 i, atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = atomic64_fetch_add_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define atomic64_fetch_add atomic64_fetch_add -#endif - -#endif /* atomic64_fetch_add_relaxed */ - -#define arch_atomic64_sub atomic64_sub - -#define arch_atomic64_sub_return atomic64_sub_return -#define arch_atomic64_sub_return_acquire atomic64_sub_return_acquire -#define arch_atomic64_sub_return_release atomic64_sub_return_release -#define arch_atomic64_sub_return_relaxed atomic64_sub_return_relaxed - -#ifndef atomic64_sub_return_relaxed -#define atomic64_sub_return_acquire atomic64_sub_return -#define atomic64_sub_return_release atomic64_sub_return -#define atomic64_sub_return_relaxed atomic64_sub_return -#else /* atomic64_sub_return_relaxed */ - -#ifndef atomic64_sub_return_acquire -static __always_inline s64 -atomic64_sub_return_acquire(s64 i, atomic64_t *v) -{ - s64 ret = atomic64_sub_return_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define atomic64_sub_return_acquire atomic64_sub_return_acquire -#endif - -#ifndef atomic64_sub_return_release -static __always_inline s64 -atomic64_sub_return_release(s64 i, atomic64_t *v) -{ - __atomic_release_fence(); - return atomic64_sub_return_relaxed(i, v); -} -#define atomic64_sub_return_release atomic64_sub_return_release -#endif - -#ifndef atomic64_sub_return -static __always_inline s64 -atomic64_sub_return(s64 i, atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = atomic64_sub_return_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define atomic64_sub_return atomic64_sub_return -#endif - -#endif /* atomic64_sub_return_relaxed */ - -#define arch_atomic64_fetch_sub atomic64_fetch_sub -#define arch_atomic64_fetch_sub_acquire atomic64_fetch_sub_acquire -#define arch_atomic64_fetch_sub_release atomic64_fetch_sub_release -#define arch_atomic64_fetch_sub_relaxed atomic64_fetch_sub_relaxed - -#ifndef atomic64_fetch_sub_relaxed -#define atomic64_fetch_sub_acquire atomic64_fetch_sub -#define atomic64_fetch_sub_release atomic64_fetch_sub -#define atomic64_fetch_sub_relaxed atomic64_fetch_sub -#else /* atomic64_fetch_sub_relaxed */ - -#ifndef atomic64_fetch_sub_acquire -static __always_inline s64 -atomic64_fetch_sub_acquire(s64 i, atomic64_t *v) -{ - s64 ret = atomic64_fetch_sub_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define atomic64_fetch_sub_acquire atomic64_fetch_sub_acquire -#endif - -#ifndef atomic64_fetch_sub_release -static __always_inline s64 -atomic64_fetch_sub_release(s64 i, atomic64_t *v) -{ - __atomic_release_fence(); - return atomic64_fetch_sub_relaxed(i, v); -} -#define atomic64_fetch_sub_release atomic64_fetch_sub_release -#endif - -#ifndef atomic64_fetch_sub -static __always_inline s64 -atomic64_fetch_sub(s64 i, atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = atomic64_fetch_sub_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define atomic64_fetch_sub atomic64_fetch_sub -#endif - -#endif /* atomic64_fetch_sub_relaxed */ - -#define arch_atomic64_inc atomic64_inc - -#ifndef atomic64_inc -static __always_inline void -atomic64_inc(atomic64_t *v) -{ - atomic64_add(1, v); -} -#define atomic64_inc atomic64_inc -#endif - -#define arch_atomic64_inc_return atomic64_inc_return -#define arch_atomic64_inc_return_acquire atomic64_inc_return_acquire -#define arch_atomic64_inc_return_release atomic64_inc_return_release -#define arch_atomic64_inc_return_relaxed atomic64_inc_return_relaxed - -#ifndef atomic64_inc_return_relaxed -#ifdef atomic64_inc_return -#define atomic64_inc_return_acquire atomic64_inc_return -#define atomic64_inc_return_release atomic64_inc_return -#define atomic64_inc_return_relaxed atomic64_inc_return -#endif /* atomic64_inc_return */ - -#ifndef atomic64_inc_return -static __always_inline s64 -atomic64_inc_return(atomic64_t *v) -{ - return atomic64_add_return(1, v); -} -#define atomic64_inc_return atomic64_inc_return -#endif - -#ifndef atomic64_inc_return_acquire -static __always_inline s64 -atomic64_inc_return_acquire(atomic64_t *v) -{ - return atomic64_add_return_acquire(1, v); -} -#define atomic64_inc_return_acquire atomic64_inc_return_acquire -#endif - -#ifndef atomic64_inc_return_release -static __always_inline s64 -atomic64_inc_return_release(atomic64_t *v) -{ - return atomic64_add_return_release(1, v); -} -#define atomic64_inc_return_release atomic64_inc_return_release -#endif - -#ifndef atomic64_inc_return_relaxed -static __always_inline s64 -atomic64_inc_return_relaxed(atomic64_t *v) -{ - return atomic64_add_return_relaxed(1, v); -} -#define atomic64_inc_return_relaxed atomic64_inc_return_relaxed -#endif - -#else /* atomic64_inc_return_relaxed */ - -#ifndef atomic64_inc_return_acquire -static __always_inline s64 -atomic64_inc_return_acquire(atomic64_t *v) -{ - s64 ret = atomic64_inc_return_relaxed(v); - __atomic_acquire_fence(); - return ret; -} -#define atomic64_inc_return_acquire atomic64_inc_return_acquire -#endif - -#ifndef atomic64_inc_return_release -static __always_inline s64 -atomic64_inc_return_release(atomic64_t *v) -{ - __atomic_release_fence(); - return atomic64_inc_return_relaxed(v); -} -#define atomic64_inc_return_release atomic64_inc_return_release -#endif - -#ifndef atomic64_inc_return -static __always_inline s64 -atomic64_inc_return(atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = atomic64_inc_return_relaxed(v); - __atomic_post_full_fence(); - return ret; -} -#define atomic64_inc_return atomic64_inc_return -#endif - -#endif /* atomic64_inc_return_relaxed */ - -#define arch_atomic64_fetch_inc atomic64_fetch_inc -#define arch_atomic64_fetch_inc_acquire atomic64_fetch_inc_acquire -#define arch_atomic64_fetch_inc_release atomic64_fetch_inc_release -#define arch_atomic64_fetch_inc_relaxed atomic64_fetch_inc_relaxed - -#ifndef atomic64_fetch_inc_relaxed -#ifdef atomic64_fetch_inc -#define atomic64_fetch_inc_acquire atomic64_fetch_inc -#define atomic64_fetch_inc_release atomic64_fetch_inc -#define atomic64_fetch_inc_relaxed atomic64_fetch_inc -#endif /* atomic64_fetch_inc */ - -#ifndef atomic64_fetch_inc -static __always_inline s64 -atomic64_fetch_inc(atomic64_t *v) -{ - return atomic64_fetch_add(1, v); -} -#define atomic64_fetch_inc atomic64_fetch_inc -#endif - -#ifndef atomic64_fetch_inc_acquire -static __always_inline s64 -atomic64_fetch_inc_acquire(atomic64_t *v) -{ - return atomic64_fetch_add_acquire(1, v); -} -#define atomic64_fetch_inc_acquire atomic64_fetch_inc_acquire -#endif - -#ifndef atomic64_fetch_inc_release -static __always_inline s64 -atomic64_fetch_inc_release(atomic64_t *v) -{ - return atomic64_fetch_add_release(1, v); -} -#define atomic64_fetch_inc_release atomic64_fetch_inc_release -#endif - -#ifndef atomic64_fetch_inc_relaxed -static __always_inline s64 -atomic64_fetch_inc_relaxed(atomic64_t *v) -{ - return atomic64_fetch_add_relaxed(1, v); -} -#define atomic64_fetch_inc_relaxed atomic64_fetch_inc_relaxed -#endif - -#else /* atomic64_fetch_inc_relaxed */ - -#ifndef atomic64_fetch_inc_acquire -static __always_inline s64 -atomic64_fetch_inc_acquire(atomic64_t *v) -{ - s64 ret = atomic64_fetch_inc_relaxed(v); - __atomic_acquire_fence(); - return ret; -} -#define atomic64_fetch_inc_acquire atomic64_fetch_inc_acquire -#endif - -#ifndef atomic64_fetch_inc_release -static __always_inline s64 -atomic64_fetch_inc_release(atomic64_t *v) -{ - __atomic_release_fence(); - return atomic64_fetch_inc_relaxed(v); -} -#define atomic64_fetch_inc_release atomic64_fetch_inc_release -#endif - -#ifndef atomic64_fetch_inc -static __always_inline s64 -atomic64_fetch_inc(atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = atomic64_fetch_inc_relaxed(v); - __atomic_post_full_fence(); - return ret; -} -#define atomic64_fetch_inc atomic64_fetch_inc -#endif - -#endif /* atomic64_fetch_inc_relaxed */ - -#define arch_atomic64_dec atomic64_dec - -#ifndef atomic64_dec -static __always_inline void -atomic64_dec(atomic64_t *v) -{ - atomic64_sub(1, v); -} -#define atomic64_dec atomic64_dec -#endif - -#define arch_atomic64_dec_return atomic64_dec_return -#define arch_atomic64_dec_return_acquire atomic64_dec_return_acquire -#define arch_atomic64_dec_return_release atomic64_dec_return_release -#define arch_atomic64_dec_return_relaxed atomic64_dec_return_relaxed - -#ifndef atomic64_dec_return_relaxed -#ifdef atomic64_dec_return -#define atomic64_dec_return_acquire atomic64_dec_return -#define atomic64_dec_return_release atomic64_dec_return -#define atomic64_dec_return_relaxed atomic64_dec_return -#endif /* atomic64_dec_return */ - -#ifndef atomic64_dec_return -static __always_inline s64 -atomic64_dec_return(atomic64_t *v) -{ - return atomic64_sub_return(1, v); -} -#define atomic64_dec_return atomic64_dec_return -#endif - -#ifndef atomic64_dec_return_acquire -static __always_inline s64 -atomic64_dec_return_acquire(atomic64_t *v) -{ - return atomic64_sub_return_acquire(1, v); -} -#define atomic64_dec_return_acquire atomic64_dec_return_acquire -#endif - -#ifndef atomic64_dec_return_release -static __always_inline s64 -atomic64_dec_return_release(atomic64_t *v) -{ - return atomic64_sub_return_release(1, v); -} -#define atomic64_dec_return_release atomic64_dec_return_release -#endif - -#ifndef atomic64_dec_return_relaxed -static __always_inline s64 -atomic64_dec_return_relaxed(atomic64_t *v) -{ - return atomic64_sub_return_relaxed(1, v); -} -#define atomic64_dec_return_relaxed atomic64_dec_return_relaxed -#endif - -#else /* atomic64_dec_return_relaxed */ - -#ifndef atomic64_dec_return_acquire -static __always_inline s64 -atomic64_dec_return_acquire(atomic64_t *v) -{ - s64 ret = atomic64_dec_return_relaxed(v); - __atomic_acquire_fence(); - return ret; -} -#define atomic64_dec_return_acquire atomic64_dec_return_acquire -#endif - -#ifndef atomic64_dec_return_release -static __always_inline s64 -atomic64_dec_return_release(atomic64_t *v) -{ - __atomic_release_fence(); - return atomic64_dec_return_relaxed(v); -} -#define atomic64_dec_return_release atomic64_dec_return_release -#endif - -#ifndef atomic64_dec_return -static __always_inline s64 -atomic64_dec_return(atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = atomic64_dec_return_relaxed(v); - __atomic_post_full_fence(); - return ret; -} -#define atomic64_dec_return atomic64_dec_return -#endif - -#endif /* atomic64_dec_return_relaxed */ - -#define arch_atomic64_fetch_dec atomic64_fetch_dec -#define arch_atomic64_fetch_dec_acquire atomic64_fetch_dec_acquire -#define arch_atomic64_fetch_dec_release atomic64_fetch_dec_release -#define arch_atomic64_fetch_dec_relaxed atomic64_fetch_dec_relaxed - -#ifndef atomic64_fetch_dec_relaxed -#ifdef atomic64_fetch_dec -#define atomic64_fetch_dec_acquire atomic64_fetch_dec -#define atomic64_fetch_dec_release atomic64_fetch_dec -#define atomic64_fetch_dec_relaxed atomic64_fetch_dec -#endif /* atomic64_fetch_dec */ - -#ifndef atomic64_fetch_dec -static __always_inline s64 -atomic64_fetch_dec(atomic64_t *v) -{ - return atomic64_fetch_sub(1, v); -} -#define atomic64_fetch_dec atomic64_fetch_dec -#endif - -#ifndef atomic64_fetch_dec_acquire -static __always_inline s64 -atomic64_fetch_dec_acquire(atomic64_t *v) -{ - return atomic64_fetch_sub_acquire(1, v); -} -#define atomic64_fetch_dec_acquire atomic64_fetch_dec_acquire -#endif - -#ifndef atomic64_fetch_dec_release -static __always_inline s64 -atomic64_fetch_dec_release(atomic64_t *v) -{ - return atomic64_fetch_sub_release(1, v); -} -#define atomic64_fetch_dec_release atomic64_fetch_dec_release -#endif - -#ifndef atomic64_fetch_dec_relaxed -static __always_inline s64 -atomic64_fetch_dec_relaxed(atomic64_t *v) -{ - return atomic64_fetch_sub_relaxed(1, v); -} -#define atomic64_fetch_dec_relaxed atomic64_fetch_dec_relaxed -#endif - -#else /* atomic64_fetch_dec_relaxed */ - -#ifndef atomic64_fetch_dec_acquire -static __always_inline s64 -atomic64_fetch_dec_acquire(atomic64_t *v) -{ - s64 ret = atomic64_fetch_dec_relaxed(v); - __atomic_acquire_fence(); - return ret; -} -#define atomic64_fetch_dec_acquire atomic64_fetch_dec_acquire -#endif - -#ifndef atomic64_fetch_dec_release -static __always_inline s64 -atomic64_fetch_dec_release(atomic64_t *v) -{ - __atomic_release_fence(); - return atomic64_fetch_dec_relaxed(v); -} -#define atomic64_fetch_dec_release atomic64_fetch_dec_release -#endif - -#ifndef atomic64_fetch_dec -static __always_inline s64 -atomic64_fetch_dec(atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = atomic64_fetch_dec_relaxed(v); - __atomic_post_full_fence(); - return ret; -} -#define atomic64_fetch_dec atomic64_fetch_dec -#endif - -#endif /* atomic64_fetch_dec_relaxed */ - -#define arch_atomic64_and atomic64_and - -#define arch_atomic64_fetch_and atomic64_fetch_and -#define arch_atomic64_fetch_and_acquire atomic64_fetch_and_acquire -#define arch_atomic64_fetch_and_release atomic64_fetch_and_release -#define arch_atomic64_fetch_and_relaxed atomic64_fetch_and_relaxed - -#ifndef atomic64_fetch_and_relaxed -#define atomic64_fetch_and_acquire atomic64_fetch_and -#define atomic64_fetch_and_release atomic64_fetch_and -#define atomic64_fetch_and_relaxed atomic64_fetch_and -#else /* atomic64_fetch_and_relaxed */ - -#ifndef atomic64_fetch_and_acquire -static __always_inline s64 -atomic64_fetch_and_acquire(s64 i, atomic64_t *v) -{ - s64 ret = atomic64_fetch_and_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define atomic64_fetch_and_acquire atomic64_fetch_and_acquire -#endif - -#ifndef atomic64_fetch_and_release -static __always_inline s64 -atomic64_fetch_and_release(s64 i, atomic64_t *v) -{ - __atomic_release_fence(); - return atomic64_fetch_and_relaxed(i, v); -} -#define atomic64_fetch_and_release atomic64_fetch_and_release -#endif - -#ifndef atomic64_fetch_and -static __always_inline s64 -atomic64_fetch_and(s64 i, atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = atomic64_fetch_and_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define atomic64_fetch_and atomic64_fetch_and -#endif - -#endif /* atomic64_fetch_and_relaxed */ - -#define arch_atomic64_andnot atomic64_andnot - -#ifndef atomic64_andnot -static __always_inline void -atomic64_andnot(s64 i, atomic64_t *v) -{ - atomic64_and(~i, v); -} -#define atomic64_andnot atomic64_andnot -#endif - -#define arch_atomic64_fetch_andnot atomic64_fetch_andnot -#define arch_atomic64_fetch_andnot_acquire atomic64_fetch_andnot_acquire -#define arch_atomic64_fetch_andnot_release atomic64_fetch_andnot_release -#define arch_atomic64_fetch_andnot_relaxed atomic64_fetch_andnot_relaxed - -#ifndef atomic64_fetch_andnot_relaxed -#ifdef atomic64_fetch_andnot -#define atomic64_fetch_andnot_acquire atomic64_fetch_andnot -#define atomic64_fetch_andnot_release atomic64_fetch_andnot -#define atomic64_fetch_andnot_relaxed atomic64_fetch_andnot -#endif /* atomic64_fetch_andnot */ - -#ifndef atomic64_fetch_andnot -static __always_inline s64 -atomic64_fetch_andnot(s64 i, atomic64_t *v) -{ - return atomic64_fetch_and(~i, v); -} -#define atomic64_fetch_andnot atomic64_fetch_andnot -#endif - -#ifndef atomic64_fetch_andnot_acquire -static __always_inline s64 -atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) -{ - return atomic64_fetch_and_acquire(~i, v); -} -#define atomic64_fetch_andnot_acquire atomic64_fetch_andnot_acquire -#endif - -#ifndef atomic64_fetch_andnot_release -static __always_inline s64 -atomic64_fetch_andnot_release(s64 i, atomic64_t *v) -{ - return atomic64_fetch_and_release(~i, v); -} -#define atomic64_fetch_andnot_release atomic64_fetch_andnot_release -#endif - -#ifndef atomic64_fetch_andnot_relaxed -static __always_inline s64 -atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v) -{ - return atomic64_fetch_and_relaxed(~i, v); -} -#define atomic64_fetch_andnot_relaxed atomic64_fetch_andnot_relaxed -#endif - -#else /* atomic64_fetch_andnot_relaxed */ - -#ifndef atomic64_fetch_andnot_acquire -static __always_inline s64 -atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) -{ - s64 ret = atomic64_fetch_andnot_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define atomic64_fetch_andnot_acquire atomic64_fetch_andnot_acquire -#endif - -#ifndef atomic64_fetch_andnot_release -static __always_inline s64 -atomic64_fetch_andnot_release(s64 i, atomic64_t *v) -{ - __atomic_release_fence(); - return atomic64_fetch_andnot_relaxed(i, v); -} -#define atomic64_fetch_andnot_release atomic64_fetch_andnot_release -#endif - -#ifndef atomic64_fetch_andnot -static __always_inline s64 -atomic64_fetch_andnot(s64 i, atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = atomic64_fetch_andnot_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define atomic64_fetch_andnot atomic64_fetch_andnot -#endif - -#endif /* atomic64_fetch_andnot_relaxed */ - -#define arch_atomic64_or atomic64_or - -#define arch_atomic64_fetch_or atomic64_fetch_or -#define arch_atomic64_fetch_or_acquire atomic64_fetch_or_acquire -#define arch_atomic64_fetch_or_release atomic64_fetch_or_release -#define arch_atomic64_fetch_or_relaxed atomic64_fetch_or_relaxed - -#ifndef atomic64_fetch_or_relaxed -#define atomic64_fetch_or_acquire atomic64_fetch_or -#define atomic64_fetch_or_release atomic64_fetch_or -#define atomic64_fetch_or_relaxed atomic64_fetch_or -#else /* atomic64_fetch_or_relaxed */ - -#ifndef atomic64_fetch_or_acquire -static __always_inline s64 -atomic64_fetch_or_acquire(s64 i, atomic64_t *v) -{ - s64 ret = atomic64_fetch_or_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define atomic64_fetch_or_acquire atomic64_fetch_or_acquire -#endif - -#ifndef atomic64_fetch_or_release -static __always_inline s64 -atomic64_fetch_or_release(s64 i, atomic64_t *v) -{ - __atomic_release_fence(); - return atomic64_fetch_or_relaxed(i, v); -} -#define atomic64_fetch_or_release atomic64_fetch_or_release -#endif - -#ifndef atomic64_fetch_or -static __always_inline s64 -atomic64_fetch_or(s64 i, atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = atomic64_fetch_or_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define atomic64_fetch_or atomic64_fetch_or -#endif - -#endif /* atomic64_fetch_or_relaxed */ - -#define arch_atomic64_xor atomic64_xor - -#define arch_atomic64_fetch_xor atomic64_fetch_xor -#define arch_atomic64_fetch_xor_acquire atomic64_fetch_xor_acquire -#define arch_atomic64_fetch_xor_release atomic64_fetch_xor_release -#define arch_atomic64_fetch_xor_relaxed atomic64_fetch_xor_relaxed - -#ifndef atomic64_fetch_xor_relaxed -#define atomic64_fetch_xor_acquire atomic64_fetch_xor -#define atomic64_fetch_xor_release atomic64_fetch_xor -#define atomic64_fetch_xor_relaxed atomic64_fetch_xor -#else /* atomic64_fetch_xor_relaxed */ - -#ifndef atomic64_fetch_xor_acquire -static __always_inline s64 -atomic64_fetch_xor_acquire(s64 i, atomic64_t *v) -{ - s64 ret = atomic64_fetch_xor_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define atomic64_fetch_xor_acquire atomic64_fetch_xor_acquire -#endif - -#ifndef atomic64_fetch_xor_release -static __always_inline s64 -atomic64_fetch_xor_release(s64 i, atomic64_t *v) -{ - __atomic_release_fence(); - return atomic64_fetch_xor_relaxed(i, v); -} -#define atomic64_fetch_xor_release atomic64_fetch_xor_release -#endif - -#ifndef atomic64_fetch_xor -static __always_inline s64 -atomic64_fetch_xor(s64 i, atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = atomic64_fetch_xor_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define atomic64_fetch_xor atomic64_fetch_xor -#endif - -#endif /* atomic64_fetch_xor_relaxed */ - -#define arch_atomic64_xchg atomic64_xchg -#define arch_atomic64_xchg_acquire atomic64_xchg_acquire -#define arch_atomic64_xchg_release atomic64_xchg_release -#define arch_atomic64_xchg_relaxed atomic64_xchg_relaxed - -#ifndef atomic64_xchg_relaxed -#define atomic64_xchg_acquire atomic64_xchg -#define atomic64_xchg_release atomic64_xchg -#define atomic64_xchg_relaxed atomic64_xchg -#else /* atomic64_xchg_relaxed */ - -#ifndef atomic64_xchg_acquire -static __always_inline s64 -atomic64_xchg_acquire(atomic64_t *v, s64 i) -{ - s64 ret = atomic64_xchg_relaxed(v, i); - __atomic_acquire_fence(); - return ret; -} -#define atomic64_xchg_acquire atomic64_xchg_acquire -#endif - -#ifndef atomic64_xchg_release -static __always_inline s64 -atomic64_xchg_release(atomic64_t *v, s64 i) -{ - __atomic_release_fence(); - return atomic64_xchg_relaxed(v, i); -} -#define atomic64_xchg_release atomic64_xchg_release -#endif - -#ifndef atomic64_xchg -static __always_inline s64 -atomic64_xchg(atomic64_t *v, s64 i) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = atomic64_xchg_relaxed(v, i); - __atomic_post_full_fence(); - return ret; -} -#define atomic64_xchg atomic64_xchg -#endif - -#endif /* atomic64_xchg_relaxed */ - -#define arch_atomic64_cmpxchg atomic64_cmpxchg -#define arch_atomic64_cmpxchg_acquire atomic64_cmpxchg_acquire -#define arch_atomic64_cmpxchg_release atomic64_cmpxchg_release -#define arch_atomic64_cmpxchg_relaxed atomic64_cmpxchg_relaxed - -#ifndef atomic64_cmpxchg_relaxed -#define atomic64_cmpxchg_acquire atomic64_cmpxchg -#define atomic64_cmpxchg_release atomic64_cmpxchg -#define atomic64_cmpxchg_relaxed atomic64_cmpxchg -#else /* atomic64_cmpxchg_relaxed */ - -#ifndef atomic64_cmpxchg_acquire -static __always_inline s64 -atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) -{ - s64 ret = atomic64_cmpxchg_relaxed(v, old, new); - __atomic_acquire_fence(); - return ret; -} -#define atomic64_cmpxchg_acquire atomic64_cmpxchg_acquire -#endif - -#ifndef atomic64_cmpxchg_release -static __always_inline s64 -atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) -{ - __atomic_release_fence(); - return atomic64_cmpxchg_relaxed(v, old, new); -} -#define atomic64_cmpxchg_release atomic64_cmpxchg_release -#endif - -#ifndef atomic64_cmpxchg -static __always_inline s64 -atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = atomic64_cmpxchg_relaxed(v, old, new); - __atomic_post_full_fence(); - return ret; -} -#define atomic64_cmpxchg atomic64_cmpxchg -#endif - -#endif /* atomic64_cmpxchg_relaxed */ - -#define arch_atomic64_try_cmpxchg atomic64_try_cmpxchg -#define arch_atomic64_try_cmpxchg_acquire atomic64_try_cmpxchg_acquire -#define arch_atomic64_try_cmpxchg_release atomic64_try_cmpxchg_release -#define arch_atomic64_try_cmpxchg_relaxed atomic64_try_cmpxchg_relaxed - -#ifndef atomic64_try_cmpxchg_relaxed -#ifdef atomic64_try_cmpxchg -#define atomic64_try_cmpxchg_acquire atomic64_try_cmpxchg -#define atomic64_try_cmpxchg_release atomic64_try_cmpxchg -#define atomic64_try_cmpxchg_relaxed atomic64_try_cmpxchg -#endif /* atomic64_try_cmpxchg */ - -#ifndef atomic64_try_cmpxchg -static __always_inline bool -atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) -{ - s64 r, o = *old; - r = atomic64_cmpxchg(v, o, new); - if (unlikely(r != o)) - *old = r; - return likely(r == o); -} -#define atomic64_try_cmpxchg atomic64_try_cmpxchg -#endif - -#ifndef atomic64_try_cmpxchg_acquire -static __always_inline bool -atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) -{ - s64 r, o = *old; - r = atomic64_cmpxchg_acquire(v, o, new); - if (unlikely(r != o)) - *old = r; - return likely(r == o); -} -#define atomic64_try_cmpxchg_acquire atomic64_try_cmpxchg_acquire -#endif - -#ifndef atomic64_try_cmpxchg_release -static __always_inline bool -atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) -{ - s64 r, o = *old; - r = atomic64_cmpxchg_release(v, o, new); - if (unlikely(r != o)) - *old = r; - return likely(r == o); -} -#define atomic64_try_cmpxchg_release atomic64_try_cmpxchg_release -#endif - -#ifndef atomic64_try_cmpxchg_relaxed -static __always_inline bool -atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) -{ - s64 r, o = *old; - r = atomic64_cmpxchg_relaxed(v, o, new); - if (unlikely(r != o)) - *old = r; - return likely(r == o); -} -#define atomic64_try_cmpxchg_relaxed atomic64_try_cmpxchg_relaxed -#endif - -#else /* atomic64_try_cmpxchg_relaxed */ - -#ifndef atomic64_try_cmpxchg_acquire -static __always_inline bool -atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) -{ - bool ret = atomic64_try_cmpxchg_relaxed(v, old, new); - __atomic_acquire_fence(); - return ret; -} -#define atomic64_try_cmpxchg_acquire atomic64_try_cmpxchg_acquire -#endif - -#ifndef atomic64_try_cmpxchg_release -static __always_inline bool -atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) -{ - __atomic_release_fence(); - return atomic64_try_cmpxchg_relaxed(v, old, new); -} -#define atomic64_try_cmpxchg_release atomic64_try_cmpxchg_release -#endif - -#ifndef atomic64_try_cmpxchg -static __always_inline bool -atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) -{ - bool ret; - __atomic_pre_full_fence(); - ret = atomic64_try_cmpxchg_relaxed(v, old, new); - __atomic_post_full_fence(); - return ret; -} -#define atomic64_try_cmpxchg atomic64_try_cmpxchg -#endif - -#endif /* atomic64_try_cmpxchg_relaxed */ - -#define arch_atomic64_sub_and_test atomic64_sub_and_test - -#ifndef atomic64_sub_and_test -/** - * atomic64_sub_and_test - subtract value from variable and test result - * @i: integer value to subtract - * @v: pointer of type atomic64_t - * - * Atomically subtracts @i from @v and returns - * true if the result is zero, or false for all - * other cases. - */ -static __always_inline bool -atomic64_sub_and_test(s64 i, atomic64_t *v) -{ - return atomic64_sub_return(i, v) == 0; -} -#define atomic64_sub_and_test atomic64_sub_and_test -#endif - -#define arch_atomic64_dec_and_test atomic64_dec_and_test - -#ifndef atomic64_dec_and_test -/** - * atomic64_dec_and_test - decrement and test - * @v: pointer of type atomic64_t - * - * Atomically decrements @v by 1 and - * returns true if the result is 0, or false for all other - * cases. - */ -static __always_inline bool -atomic64_dec_and_test(atomic64_t *v) -{ - return atomic64_dec_return(v) == 0; -} -#define atomic64_dec_and_test atomic64_dec_and_test -#endif - -#define arch_atomic64_inc_and_test atomic64_inc_and_test - -#ifndef atomic64_inc_and_test -/** - * atomic64_inc_and_test - increment and test - * @v: pointer of type atomic64_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -static __always_inline bool -atomic64_inc_and_test(atomic64_t *v) -{ - return atomic64_inc_return(v) == 0; -} -#define atomic64_inc_and_test atomic64_inc_and_test -#endif - -#define arch_atomic64_add_negative atomic64_add_negative - -#ifndef atomic64_add_negative -/** - * atomic64_add_negative - add and test if negative - * @i: integer value to add - * @v: pointer of type atomic64_t - * - * Atomically adds @i to @v and returns true - * if the result is negative, or false when - * result is greater than or equal to zero. - */ -static __always_inline bool -atomic64_add_negative(s64 i, atomic64_t *v) -{ - return atomic64_add_return(i, v) < 0; -} -#define atomic64_add_negative atomic64_add_negative -#endif - -#define arch_atomic64_fetch_add_unless atomic64_fetch_add_unless - -#ifndef atomic64_fetch_add_unless -/** - * atomic64_fetch_add_unless - add unless the number is already a given value - * @v: pointer of type atomic64_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as @v was not already @u. - * Returns original value of @v - */ -static __always_inline s64 -atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) -{ - s64 c = atomic64_read(v); - - do { - if (unlikely(c == u)) - break; - } while (!atomic64_try_cmpxchg(v, &c, c + a)); - - return c; -} -#define atomic64_fetch_add_unless atomic64_fetch_add_unless -#endif - -#define arch_atomic64_add_unless atomic64_add_unless - -#ifndef atomic64_add_unless -/** - * atomic64_add_unless - add unless the number is already a given value - * @v: pointer of type atomic64_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, if @v was not already @u. - * Returns true if the addition was done. - */ -static __always_inline bool -atomic64_add_unless(atomic64_t *v, s64 a, s64 u) -{ - return atomic64_fetch_add_unless(v, a, u) != u; -} -#define atomic64_add_unless atomic64_add_unless -#endif - -#define arch_atomic64_inc_not_zero atomic64_inc_not_zero - -#ifndef atomic64_inc_not_zero -/** - * atomic64_inc_not_zero - increment unless the number is zero - * @v: pointer of type atomic64_t - * - * Atomically increments @v by 1, if @v is non-zero. - * Returns true if the increment was done. - */ -static __always_inline bool -atomic64_inc_not_zero(atomic64_t *v) -{ - return atomic64_add_unless(v, 1, 0); -} -#define atomic64_inc_not_zero atomic64_inc_not_zero -#endif - -#define arch_atomic64_inc_unless_negative atomic64_inc_unless_negative - -#ifndef atomic64_inc_unless_negative -static __always_inline bool -atomic64_inc_unless_negative(atomic64_t *v) -{ - s64 c = atomic64_read(v); - - do { - if (unlikely(c < 0)) - return false; - } while (!atomic64_try_cmpxchg(v, &c, c + 1)); - - return true; -} -#define atomic64_inc_unless_negative atomic64_inc_unless_negative -#endif - -#define arch_atomic64_dec_unless_positive atomic64_dec_unless_positive - -#ifndef atomic64_dec_unless_positive -static __always_inline bool -atomic64_dec_unless_positive(atomic64_t *v) -{ - s64 c = atomic64_read(v); - - do { - if (unlikely(c > 0)) - return false; - } while (!atomic64_try_cmpxchg(v, &c, c - 1)); - - return true; -} -#define atomic64_dec_unless_positive atomic64_dec_unless_positive -#endif - -#define arch_atomic64_dec_if_positive atomic64_dec_if_positive - -#ifndef atomic64_dec_if_positive -static __always_inline s64 -atomic64_dec_if_positive(atomic64_t *v) -{ - s64 dec, c = atomic64_read(v); - - do { - dec = c - 1; - if (unlikely(dec < 0)) - break; - } while (!atomic64_try_cmpxchg(v, &c, dec)); - - return dec; -} -#define atomic64_dec_if_positive atomic64_dec_if_positive -#endif - -#endif /* _LINUX_ATOMIC_FALLBACK_H */ -// d78e6c293c661c15188f0ec05bce45188c8d5892 diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 4f8d83f9e480..ed1d3ffd5b9d 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -77,12 +77,8 @@ __ret; \ }) -#ifdef CONFIG_ARCH_ATOMIC #include #include -#else -#include -#endif #include -- cgit v1.2.3 From 10e96f8b4e7521197a50b370ce0923ab6a8d0ca0 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 26 May 2021 11:32:39 +0200 Subject: mtd: rawnand: Move struct gpio_desc declaration to the top The struct gpio_desc is declared in the middle of the rawnand.h header, right before the first function using it (nand_gpio_waitrdy). Before adding a new function and to make it clear: move the declaration to the top of the file. Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210526093242.183847-2-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 89b9c52c7387..d41d39360fff 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -24,6 +24,7 @@ #include struct nand_chip; +struct gpio_desc; /* The maximum number of NAND chips in an array */ #define NAND_MAX_CHIPS 8 @@ -1562,7 +1563,6 @@ void nand_cleanup(struct nand_chip *chip); * instruction and have no physical pin to check it. */ int nand_soft_waitrdy(struct nand_chip *chip, unsigned long timeout_ms); -struct gpio_desc; int nand_gpio_waitrdy(struct nand_chip *chip, struct gpio_desc *gpiod, unsigned long timeout_ms); -- cgit v1.2.3 From b85c943d181ac58e3a34a5f79c73d421f4da7b00 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 26 May 2021 11:32:40 +0200 Subject: mtd: rawnand: Add a helper to parse the gpio-cs DT property New chips may feature a lot of CS because of their extended length. As many controllers have been designed a decade ago, they usually only feature just a couple. This does not mean that the entire range of these chips cannot be accessed: it is just a matter of adding more GPIO CS in the hardware design. A DT property has been added to describe the CS array: cs-gpios. Here is the code parsing it this new property, allocating what needs to be, requesting the GPIOs and returning an array with the additional available CS. The first entries of this array are left empty and are reserved for native CS. Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210526093242.183847-3-miquel.raynal@bootlin.com --- include/linux/mtd/rawnand.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index d41d39360fff..b2f9dd3cbd69 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1595,4 +1595,8 @@ static inline void *nand_get_data_buf(struct nand_chip *chip) return chip->data_buf; } +/* Parse the gpio-cs property */ +int rawnand_dt_parse_gpio_cs(struct device *dev, struct gpio_desc ***cs_array, + unsigned int *ncs_array); + #endif /* __LINUX_MTD_RAWNAND_H */ -- cgit v1.2.3 From 3fdc0cb59d97f87e2cc708d424f1538e31744286 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 18 May 2021 17:36:18 +0100 Subject: arm64: smccc: Add support for SMCCCv1.2 extended input/output registers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit SMCCC v1.2 allows x8-x17 to be used as parameter registers and x4—x17 to be used as result registers in SMC64/HVC64. Arm Firmware Framework for Armv8-A specification makes use of x0-x7 as parameter and result registers. There are other users like Hyper-V who intend to use beyond x0-x7 as well. Current SMCCC interface in the kernel just use x0-x7 as parameter and x0-x3 as result registers as required by SMCCCv1.0. Let us add new interface to support this extended set of input/output registers namely x0-x17 as both parameter and result registers. Acked-by: Mark Rutland Tested-by: Michael Kelley Reviewed-by: Michael Kelley Cc: Will Deacon Cc: Catalin Marinas Signed-off-by: Sudeep Holla Reviewed-by: Mark Brown Link: https://lore.kernel.org/r/20210518163618.43950-1-sudeep.holla@arm.com Signed-off-by: Will Deacon --- include/linux/arm-smccc.h | 55 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 55 insertions(+) (limited to 'include/linux') diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 6861489a1890..5cef2b8b0479 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -227,6 +227,61 @@ struct arm_smccc_res { unsigned long a3; }; +#ifdef CONFIG_ARM64 +/** + * struct arm_smccc_1_2_regs - Arguments for or Results from SMC/HVC call + * @a0-a17 argument values from registers 0 to 17 + */ +struct arm_smccc_1_2_regs { + unsigned long a0; + unsigned long a1; + unsigned long a2; + unsigned long a3; + unsigned long a4; + unsigned long a5; + unsigned long a6; + unsigned long a7; + unsigned long a8; + unsigned long a9; + unsigned long a10; + unsigned long a11; + unsigned long a12; + unsigned long a13; + unsigned long a14; + unsigned long a15; + unsigned long a16; + unsigned long a17; +}; + +/** + * arm_smccc_1_2_hvc() - make HVC calls + * @args: arguments passed via struct arm_smccc_1_2_regs + * @res: result values via struct arm_smccc_1_2_regs + * + * This function is used to make HVC calls following SMC Calling Convention + * v1.2 or above. The content of the supplied param are copied from the + * structure to registers prior to the HVC instruction. The return values + * are updated with the content from registers on return from the HVC + * instruction. + */ +asmlinkage void arm_smccc_1_2_hvc(const struct arm_smccc_1_2_regs *args, + struct arm_smccc_1_2_regs *res); + +/** + * arm_smccc_1_2_smc() - make SMC calls + * @args: arguments passed via struct arm_smccc_1_2_regs + * @res: result values via struct arm_smccc_1_2_regs + * + * This function is used to make SMC calls following SMC Calling Convention + * v1.2 or above. The content of the supplied param are copied from the + * structure to registers prior to the SMC instruction. The return values + * are updated with the content from registers on return from the SMC + * instruction. + */ +asmlinkage void arm_smccc_1_2_smc(const struct arm_smccc_1_2_regs *args, + struct arm_smccc_1_2_regs *res); +#endif + /** * struct arm_smccc_quirk - Contains quirk information * @id: quirk identification -- cgit v1.2.3 From e781858488b918e30a6ff28e9eab6058b787e3b3 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Fri, 21 May 2021 16:10:29 +0100 Subject: firmware: arm_ffa: Add initial FFA bus support for device enumeration The Arm FF for Armv8-A specification has concept of endpoints or partitions. In the Normal world, a partition could be a VM when the Virtualization extension is enabled or the kernel itself. In order to handle multiple partitions, we can create a FFA device for each such partition on a dedicated FFA bus. Similarly, different drivers requiring FFA transport can be registered on the same bus. We can match the device and drivers using UUID. This is mostly for the in-kernel users with FFA drivers. Link: https://lore.kernel.org/r/20210521151033.181846-2-sudeep.holla@arm.com Tested-by: Jens Wiklander Signed-off-by: Sudeep Holla --- include/linux/arm_ffa.h | 91 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 91 insertions(+) create mode 100644 include/linux/arm_ffa.h (limited to 'include/linux') diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h new file mode 100644 index 000000000000..331ff62c9873 --- /dev/null +++ b/include/linux/arm_ffa.h @@ -0,0 +1,91 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2021 ARM Ltd. + */ + +#ifndef _LINUX_ARM_FFA_H +#define _LINUX_ARM_FFA_H + +#include +#include +#include +#include +#include + +/* FFA Bus/Device/Driver related */ +struct ffa_device { + int vm_id; + uuid_t uuid; + struct device dev; +}; + +#define to_ffa_dev(d) container_of(d, struct ffa_device, dev) + +struct ffa_device_id { + uuid_t uuid; +}; + +struct ffa_driver { + const char *name; + int (*probe)(struct ffa_device *sdev); + void (*remove)(struct ffa_device *sdev); + const struct ffa_device_id *id_table; + + struct device_driver driver; +}; + +#define to_ffa_driver(d) container_of(d, struct ffa_driver, driver) + +static inline void ffa_dev_set_drvdata(struct ffa_device *fdev, void *data) +{ + fdev->dev.driver_data = data; +} + +#if IS_REACHABLE(CONFIG_ARM_FFA_TRANSPORT) +struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id); +void ffa_device_unregister(struct ffa_device *ffa_dev); +int ffa_driver_register(struct ffa_driver *driver, struct module *owner, + const char *mod_name); +void ffa_driver_unregister(struct ffa_driver *driver); +bool ffa_device_is_valid(struct ffa_device *ffa_dev); + +#else +static inline +struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id) +{ + return NULL; +} + +static inline void ffa_device_unregister(struct ffa_device *dev) {} + +static inline int +ffa_driver_register(struct ffa_driver *driver, struct module *owner, + const char *mod_name) +{ + return -EINVAL; +} + +static inline void ffa_driver_unregister(struct ffa_driver *driver) {} + +static inline +bool ffa_device_is_valid(struct ffa_device *ffa_dev) { return false; } + +#endif /* CONFIG_ARM_FFA_TRANSPORT */ + +#define ffa_register(driver) \ + ffa_driver_register(driver, THIS_MODULE, KBUILD_MODNAME) +#define ffa_unregister(driver) \ + ffa_driver_unregister(driver) + +/** + * module_ffa_driver() - Helper macro for registering a psa_ffa driver + * @__ffa_driver: ffa_driver structure + * + * Helper macro for psa_ffa drivers to set up proper module init / exit + * functions. Replaces module_init() and module_exit() and keeps people from + * printing pointless things to the kernel log when their driver is loaded. + */ +#define module_ffa_driver(__ffa_driver) \ + module_driver(__ffa_driver, ffa_register, ffa_unregister) + +#endif /* _LINUX_ARM_FFA_H */ -- cgit v1.2.3 From d0c0bce831223b08e5bade2cefc93c3ddb790796 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Fri, 21 May 2021 16:10:32 +0100 Subject: firmware: arm_ffa: Setup in-kernel users of FFA partitions Parse the FFA nodes from the device-tree and register all the partitions whose services will be used in the kernel. In order to also enable in-kernel users of FFA interface, let us add simple set of operations for such devices. The in-kernel users are registered without the character device interface. Link: https://lore.kernel.org/r/20210521151033.181846-5-sudeep.holla@arm.com Tested-by: Jens Wiklander Reviewed-by: Jens Wiklander Signed-off-by: Sudeep Holla --- include/linux/arm_ffa.h | 39 ++++++++++++++++++++++++++++++++++++++- 1 file changed, 38 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index 331ff62c9873..d672673fc621 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -6,7 +6,6 @@ #ifndef _LINUX_ARM_FFA_H #define _LINUX_ARM_FFA_H -#include #include #include #include @@ -15,6 +14,7 @@ /* FFA Bus/Device/Driver related */ struct ffa_device { int vm_id; + bool mode_32bit; uuid_t uuid; struct device dev; }; @@ -48,6 +48,7 @@ int ffa_driver_register(struct ffa_driver *driver, struct module *owner, const char *mod_name); void ffa_driver_unregister(struct ffa_driver *driver); bool ffa_device_is_valid(struct ffa_device *ffa_dev); +const struct ffa_dev_ops *ffa_dev_ops_get(struct ffa_device *dev); #else static inline @@ -70,6 +71,11 @@ static inline void ffa_driver_unregister(struct ffa_driver *driver) {} static inline bool ffa_device_is_valid(struct ffa_device *ffa_dev) { return false; } +static inline +const struct ffa_dev_ops *ffa_dev_ops_get(struct ffa_device *dev) +{ + return NULL; +} #endif /* CONFIG_ARM_FFA_TRANSPORT */ #define ffa_register(driver) \ @@ -88,4 +94,35 @@ bool ffa_device_is_valid(struct ffa_device *ffa_dev) { return false; } #define module_ffa_driver(__ffa_driver) \ module_driver(__ffa_driver, ffa_register, ffa_unregister) +/* FFA transport related */ +struct ffa_partition_info { + u16 id; + u16 exec_ctxt; +/* partition supports receipt of direct requests */ +#define FFA_PARTITION_DIRECT_RECV BIT(0) +/* partition can send direct requests. */ +#define FFA_PARTITION_DIRECT_SEND BIT(1) +/* partition can send and receive indirect messages. */ +#define FFA_PARTITION_INDIRECT_MSG BIT(2) + u32 properties; +}; + +/* For use with FFA_MSG_SEND_DIRECT_{REQ,RESP} which pass data via registers */ +struct ffa_send_direct_data { + unsigned long data0; /* w3/x3 */ + unsigned long data1; /* w4/x4 */ + unsigned long data2; /* w5/x5 */ + unsigned long data3; /* w6/x6 */ + unsigned long data4; /* w7/x7 */ +}; + +struct ffa_dev_ops { + u32 (*api_version_get)(void); + int (*partition_info_get)(const char *uuid_str, + struct ffa_partition_info *buffer); + void (*mode_32bit_set)(struct ffa_device *dev); + int (*sync_send_receive)(struct ffa_device *dev, + struct ffa_send_direct_data *data); +}; + #endif /* _LINUX_ARM_FFA_H */ -- cgit v1.2.3 From cc2195fe536c28e192df5d07e6dd277af36814b4 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Fri, 21 May 2021 16:10:33 +0100 Subject: firmware: arm_ffa: Add support for MEM_* interfaces Most of the MEM_* APIs share the same parameters, so they can be generalised. Currently only MEM_SHARE is implemented and the user space interface for that is not added yet. Link: https://lore.kernel.org/r/20210521151033.181846-6-sudeep.holla@arm.com Tested-by: Jens Wiklander Signed-off-by: Sudeep Holla --- include/linux/arm_ffa.h | 139 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 139 insertions(+) (limited to 'include/linux') diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index d672673fc621..505c679b6a9b 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -116,6 +116,142 @@ struct ffa_send_direct_data { unsigned long data4; /* w7/x7 */ }; +struct ffa_mem_region_addr_range { + /* The base IPA of the constituent memory region, aligned to 4 kiB */ + u64 address; + /* The number of 4 kiB pages in the constituent memory region. */ + u32 pg_cnt; + u32 reserved; +}; + +struct ffa_composite_mem_region { + /* + * The total number of 4 kiB pages included in this memory region. This + * must be equal to the sum of page counts specified in each + * `struct ffa_mem_region_addr_range`. + */ + u32 total_pg_cnt; + /* The number of constituents included in this memory region range */ + u32 addr_range_cnt; + u64 reserved; + /** An array of `addr_range_cnt` memory region constituents. */ + struct ffa_mem_region_addr_range constituents[]; +}; + +struct ffa_mem_region_attributes { + /* The ID of the VM to which the memory is being given or shared. */ + u16 receiver; + /* + * The permissions with which the memory region should be mapped in the + * receiver's page table. + */ +#define FFA_MEM_EXEC BIT(3) +#define FFA_MEM_NO_EXEC BIT(2) +#define FFA_MEM_RW BIT(1) +#define FFA_MEM_RO BIT(0) + u8 attrs; + /* + * Flags used during FFA_MEM_RETRIEVE_REQ and FFA_MEM_RETRIEVE_RESP + * for memory regions with multiple borrowers. + */ +#define FFA_MEM_RETRIEVE_SELF_BORROWER BIT(0) + u8 flag; + u32 composite_off; + /* + * Offset in bytes from the start of the outer `ffa_memory_region` to + * an `struct ffa_mem_region_addr_range`. + */ + u64 reserved; +}; + +struct ffa_mem_region { + /* The ID of the VM/owner which originally sent the memory region */ + u16 sender_id; +#define FFA_MEM_NORMAL BIT(5) +#define FFA_MEM_DEVICE BIT(4) + +#define FFA_MEM_WRITE_BACK (3 << 2) +#define FFA_MEM_NON_CACHEABLE (1 << 2) + +#define FFA_DEV_nGnRnE (0 << 2) +#define FFA_DEV_nGnRE (1 << 2) +#define FFA_DEV_nGRE (2 << 2) +#define FFA_DEV_GRE (3 << 2) + +#define FFA_MEM_NON_SHAREABLE (0) +#define FFA_MEM_OUTER_SHAREABLE (2) +#define FFA_MEM_INNER_SHAREABLE (3) + u8 attributes; + u8 reserved_0; +/* + * Clear memory region contents after unmapping it from the sender and + * before mapping it for any receiver. + */ +#define FFA_MEM_CLEAR BIT(0) +/* + * Whether the hypervisor may time slice the memory sharing or retrieval + * operation. + */ +#define FFA_TIME_SLICE_ENABLE BIT(1) + +#define FFA_MEM_RETRIEVE_TYPE_IN_RESP (0 << 3) +#define FFA_MEM_RETRIEVE_TYPE_SHARE (1 << 3) +#define FFA_MEM_RETRIEVE_TYPE_LEND (2 << 3) +#define FFA_MEM_RETRIEVE_TYPE_DONATE (3 << 3) + +#define FFA_MEM_RETRIEVE_ADDR_ALIGN_HINT BIT(9) +#define FFA_MEM_RETRIEVE_ADDR_ALIGN(x) ((x) << 5) + /* Flags to control behaviour of the transaction. */ + u32 flags; +#define HANDLE_LOW_MASK GENMASK_ULL(31, 0) +#define HANDLE_HIGH_MASK GENMASK_ULL(63, 32) +#define HANDLE_LOW(x) ((u32)(FIELD_GET(HANDLE_LOW_MASK, (x)))) +#define HANDLE_HIGH(x) ((u32)(FIELD_GET(HANDLE_HIGH_MASK, (x)))) + +#define PACK_HANDLE(l, h) \ + (FIELD_PREP(HANDLE_LOW_MASK, (l)) | FIELD_PREP(HANDLE_HIGH_MASK, (h))) + /* + * A globally-unique ID assigned by the hypervisor for a region + * of memory being sent between VMs. + */ + u64 handle; + /* + * An implementation defined value associated with the receiver and the + * memory region. + */ + u64 tag; + u32 reserved_1; + /* + * The number of `ffa_mem_region_attributes` entries included in this + * transaction. + */ + u32 ep_count; + /* + * An array of endpoint memory access descriptors. + * Each one specifies a memory region offset, an endpoint and the + * attributes with which this memory region should be mapped in that + * endpoint's page table. + */ + struct ffa_mem_region_attributes ep_mem_access[]; +}; + +#define COMPOSITE_OFFSET(x) \ + (offsetof(struct ffa_mem_region, ep_mem_access[x])) +#define CONSTITUENTS_OFFSET(x) \ + (offsetof(struct ffa_composite_mem_region, constituents[x])) +#define COMPOSITE_CONSTITUENTS_OFFSET(x, y) \ + (COMPOSITE_OFFSET(x) + CONSTITUENTS_OFFSET(y)) + +struct ffa_mem_ops_args { + bool use_txbuf; + u32 nattrs; + u32 flags; + u64 tag; + u64 g_handle; + struct scatterlist *sg; + struct ffa_mem_region_attributes *attrs; +}; + struct ffa_dev_ops { u32 (*api_version_get)(void); int (*partition_info_get)(const char *uuid_str, @@ -123,6 +259,9 @@ struct ffa_dev_ops { void (*mode_32bit_set)(struct ffa_device *dev); int (*sync_send_receive)(struct ffa_device *dev, struct ffa_send_direct_data *data); + int (*memory_reclaim)(u64 g_handle, u32 flags); + int (*memory_share)(struct ffa_device *dev, + struct ffa_mem_ops_args *args); }; #endif /* _LINUX_ARM_FFA_H */ -- cgit v1.2.3 From 125217e0967fc905be35a3b2c9ba4db9a8616b92 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 25 May 2021 18:00:38 -0500 Subject: i40e: Replace one-element array with flexible-array member MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a regular need in the kernel to provide a way to declare having a dynamically sized set of trailing elements in a structure. Kernel code should always use “flexible array members”[1] for these cases. The older style of one-element or zero-length arrays should no longer be used[2]. Refactor the code according to the use of a flexible-array member in struct i40e_qvlist_info instead of one-element array, and use the struct_size() helper. [1] https://en.wikipedia.org/wiki/Flexible_array_member [2] https://www.kernel.org/doc/html/v5.10/process/deprecated.html#zero-length-and-one-element-arrays Link: https://github.com/KSPP/linux/issues/79 Signed-off-by: Gustavo A. R. Silva Acked-by: Shiraz Saleem Signed-off-by: Tony Nguyen --- include/linux/net/intel/i40e_client.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/net/intel/i40e_client.h b/include/linux/net/intel/i40e_client.h index f41387a8969f..fd7bc860a241 100644 --- a/include/linux/net/intel/i40e_client.h +++ b/include/linux/net/intel/i40e_client.h @@ -48,7 +48,7 @@ struct i40e_qv_info { struct i40e_qvlist_info { u32 num_vectors; - struct i40e_qv_info qv_info[1]; + struct i40e_qv_info qv_info[]; }; -- cgit v1.2.3 From 73e33008e865e5a7b79282331c2d6e920d5d47f8 Mon Sep 17 00:00:00 2001 From: Chunfeng Yun Date: Tue, 25 May 2021 16:53:05 +0800 Subject: usb: roles: add helper usb_role_string() Introduces usb_role_string() function, which returns a human-readable name of provided usb role, it's useful to make the log readable. Reviewed-by: Heikki Krogerus Signed-off-by: Chunfeng Yun Link: https://lore.kernel.org/r/1621932786-9335-1-git-send-email-chunfeng.yun@mediatek.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/role.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/role.h b/include/linux/usb/role.h index 0164fed31b06..031f148ab373 100644 --- a/include/linux/usb/role.h +++ b/include/linux/usb/role.h @@ -65,6 +65,7 @@ void usb_role_switch_unregister(struct usb_role_switch *sw); void usb_role_switch_set_drvdata(struct usb_role_switch *sw, void *data); void *usb_role_switch_get_drvdata(struct usb_role_switch *sw); +const char *usb_role_string(enum usb_role role); #else static inline int usb_role_switch_set_role(struct usb_role_switch *sw, enum usb_role role) @@ -109,6 +110,11 @@ static inline void *usb_role_switch_get_drvdata(struct usb_role_switch *sw) return NULL; } +static inline const char *usb_role_string(enum usb_role role) +{ + return "unknown"; +} + #endif #endif /* __LINUX_USB_ROLE_H */ -- cgit v1.2.3 From 70f400d4d957c2453c8689552ff212bc59f88938 Mon Sep 17 00:00:00 2001 From: Rajat Jain Date: Mon, 24 May 2021 10:18:11 -0700 Subject: driver core: Move the "removable" attribute from USB to core Move the "removable" attribute from USB to core in order to allow it to be supported by other subsystem / buses. Individual buses that want to support this attribute can populate the removable property of the device while enumerating it with the 3 possible values - - "unknown" - "fixed" - "removable" Leaving the field unchanged (i.e. "not supported") would mean that the attribute would not show up in sysfs for that device. The UAPI (location, symantics etc) for the attribute remains unchanged. Move the "removable" attribute from USB to the device core so it can be used by other subsystems / buses. By default, devices do not have a "removable" attribute in sysfs. If a subsystem or bus driver wants to support a "removable" attribute, it should call device_set_removable() before calling device_register() or device_add(), e.g.: device_set_removable(dev, DEVICE_REMOVABLE); device_register(dev); The possible values and the resulting sysfs attribute contents are: DEVICE_REMOVABLE_UNKNOWN -> "unknown" DEVICE_REMOVABLE -> "removable" DEVICE_FIXED -> "fixed" Convert the USB "removable" attribute to use this new device core functionality. There should be no user-visible change in the location or semantics of attribute for USB devices. Reviewed-by: Bjorn Helgaas Signed-off-by: Rajat Jain Link: https://lore.kernel.org/r/20210524171812.18095-1-rajatja@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 37 +++++++++++++++++++++++++++++++++++++ include/linux/usb.h | 7 ------- 2 files changed, 37 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 38a2071cf776..8566fa98b239 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -350,6 +350,22 @@ enum dl_dev_state { DL_DEV_UNBINDING, }; +/** + * enum device_removable - Whether the device is removable. The criteria for a + * device to be classified as removable is determined by its subsystem or bus. + * @DEVICE_REMOVABLE_NOT_SUPPORTED: This attribute is not supported for this + * device (default). + * @DEVICE_REMOVABLE_UNKNOWN: Device location is Unknown. + * @DEVICE_FIXED: Device is not removable by the user. + * @DEVICE_REMOVABLE: Device is removable by the user. + */ +enum device_removable { + DEVICE_REMOVABLE_NOT_SUPPORTED = 0, /* must be 0 */ + DEVICE_REMOVABLE_UNKNOWN, + DEVICE_FIXED, + DEVICE_REMOVABLE, +}; + /** * struct dev_links_info - Device data related to device links. * @suppliers: List of links to supplier devices. @@ -431,6 +447,9 @@ struct dev_links_info { * device (i.e. the bus driver that discovered the device). * @iommu_group: IOMMU group the device belongs to. * @iommu: Per device generic IOMMU runtime data + * @removable: Whether the device can be removed from the system. This + * should be set by the subsystem / bus driver that discovered + * the device. * * @offline_disabled: If set, the device is permanently online. * @offline: Set after successful invocation of bus type's .offline(). @@ -544,6 +563,8 @@ struct device { struct iommu_group *iommu_group; struct dev_iommu *iommu; + enum device_removable removable; + bool offline_disabled:1; bool offline:1; bool of_node_reused:1; @@ -782,6 +803,22 @@ static inline bool dev_has_sync_state(struct device *dev) return false; } +static inline void dev_set_removable(struct device *dev, + enum device_removable removable) +{ + dev->removable = removable; +} + +static inline bool dev_is_removable(struct device *dev) +{ + return dev->removable == DEVICE_REMOVABLE; +} + +static inline bool dev_removable_is_valid(struct device *dev) +{ + return dev->removable != DEVICE_REMOVABLE_NOT_SUPPORTED; +} + /* * High level routines for use by the bus drivers */ diff --git a/include/linux/usb.h b/include/linux/usb.h index 4db6b824af5c..7ccaa76a9a96 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -473,12 +473,6 @@ struct usb_dev_state; struct usb_tt; -enum usb_device_removable { - USB_DEVICE_REMOVABLE_UNKNOWN = 0, - USB_DEVICE_REMOVABLE, - USB_DEVICE_FIXED, -}; - enum usb_port_connect_type { USB_PORT_CONNECT_TYPE_UNKNOWN = 0, USB_PORT_CONNECT_TYPE_HOT_PLUG, @@ -703,7 +697,6 @@ struct usb_device { #endif struct wusb_dev *wusb_dev; int slot_id; - enum usb_device_removable removable; struct usb2_lpm_parameters l1_params; struct usb3_lpm_parameters u1_params; struct usb3_lpm_parameters u2_params; -- cgit v1.2.3 From d327ea15a305024ef0085252fa3657bbb1ce25f5 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Tue, 25 May 2021 13:20:12 +0100 Subject: random32: Fix implicit truncation warning in prandom_seed_state() sparse generates the following warning: include/linux/prandom.h:114:45: sparse: sparse: cast truncates bits from constant value This is because the 64-bit seed value is manipulated and then placed in a u32, causing an implicit cast and truncation. A forced cast to u32 doesn't prevent this warning, which is reasonable because a typecast doesn't prove that truncation was expected. Logical-AND the value with 0xffffffff to make explicit that truncation to 32-bit is intended. Reported-by: kernel test robot Signed-off-by: Richard Fitzgerald Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20210525122012.6336-3-rf@opensource.cirrus.com --- include/linux/prandom.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/prandom.h b/include/linux/prandom.h index bbf4b4ad61df..056d31317e49 100644 --- a/include/linux/prandom.h +++ b/include/linux/prandom.h @@ -111,7 +111,7 @@ static inline u32 __seed(u32 x, u32 m) */ static inline void prandom_seed_state(struct rnd_state *state, u64 seed) { - u32 i = (seed >> 32) ^ (seed << 10) ^ seed; + u32 i = ((seed >> 32) ^ (seed << 10) ^ seed) & 0xffffffffUL; state->s1 = __seed(i, 2U); state->s2 = __seed(i, 8U); -- cgit v1.2.3 From 39b27e89a76f3827ad93aed9213a6daf2b91f819 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 25 May 2021 12:37:11 +0200 Subject: driver core: Drop helper devm_platform_ioremap_resource_wc() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since the macro was introduced in 2019 (commit bb6243b4f73d ("drivers: platform: provide devm_platform_ioremap_resource_wc()") there is only a single user which hardly justifies the function for the small task it provides. So drop the helper and open-code it in the only user. Adapt the non-wc case accordingly. For a all-mod-config build on amd64 this change introduces the following changes according to bloat-o-meter: add/remove: 0/1 grow/shrink: 1/0 up/down: 20/-252 (-232) Function old new delta devm_platform_ioremap_resource_wc 252 - -252 sram_probe 796 816 +20 Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20210525103711.956438-1-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_device.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index cd81e060863c..ed42ea9f60ba 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -66,9 +66,6 @@ extern void __iomem * devm_platform_ioremap_resource(struct platform_device *pdev, unsigned int index); extern void __iomem * -devm_platform_ioremap_resource_wc(struct platform_device *pdev, - unsigned int index); -extern void __iomem * devm_platform_ioremap_resource_byname(struct platform_device *pdev, const char *name); extern int platform_get_irq(struct platform_device *, unsigned int); -- cgit v1.2.3 From 16b79a1e083371a38f72872345866e81abb7ca18 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 25 May 2021 14:47:16 -0400 Subject: soc: samsung: pmu: drop EXYNOS_CENTRAL_SEQ_OPTION defines The defines for Exynos5 CENTRAL_SEQ_OPTION (e.g. EXYNOS5_USE_STANDBYWFI_ARM_CORE1) are not used. Signed-off-by: Krzysztof Kozlowski Reviewed-by: Alim Akhtar Link: https://lore.kernel.org/r/20210525184716.119663-1-krzysztof.kozlowski@canonical.com --- include/linux/soc/samsung/exynos-regs-pmu.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soc/samsung/exynos-regs-pmu.h b/include/linux/soc/samsung/exynos-regs-pmu.h index fc9250fb3133..aa840ed043e1 100644 --- a/include/linux/soc/samsung/exynos-regs-pmu.h +++ b/include/linux/soc/samsung/exynos-regs-pmu.h @@ -611,12 +611,6 @@ #define EXYNOS5420_FSYS2_OPTION 0x4168 #define EXYNOS5420_PSGEN_OPTION 0x4188 -/* For EXYNOS_CENTRAL_SEQ_OPTION */ -#define EXYNOS5_USE_STANDBYWFI_ARM_CORE0 BIT(16) -#define EXYNOS5_USE_STANDBYWFI_ARM_CORE1 BUT(17) -#define EXYNOS5_USE_STANDBYWFE_ARM_CORE0 BIT(24) -#define EXYNOS5_USE_STANDBYWFE_ARM_CORE1 BIT(25) - #define EXYNOS5420_ARM_USE_STANDBY_WFI0 BIT(4) #define EXYNOS5420_ARM_USE_STANDBY_WFI1 BIT(5) #define EXYNOS5420_ARM_USE_STANDBY_WFI2 BIT(6) -- cgit v1.2.3 From b973cf32453f78d8661a640d0a0167d1d41ea331 Mon Sep 17 00:00:00 2001 From: Huy Nguyen Date: Mon, 23 Nov 2020 14:48:22 -0600 Subject: net/mlx5e: TC: Reserved bit 31 of REG_C1 for IPsec offload Currently ASAP features fully utilize all the bits of the CQE's flow tag and ft_metadata field. The flow tag field cannot be used because the flow table tagging in FTE does not allow partial write. We agree to reserve bit 31 of CQE's ft_metadata for IPsec to avoid ASAP CT from dropping IPsec offloaded packet Here is the new bit layout of REG_C1. Tunnel option id is reduced to 11 bits: < IPSEC MARKER (1) | ESW_TUN_ID(12) | ESW_TUN_OPTS(11) | ESW_ZONE_ID(8) > Signed-off-by: Huy Nguyen Signed-off-by: Raed Salem Reviewed-by: Paul Blakey Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed Signed-off-by: Paul Blakey --- include/linux/mlx5/eswitch.h | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index 17109b65c1ac..bc7db2e059eb 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -98,10 +98,11 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw, u16 vport_num); /* Reg C1 usage: - * Reg C1 = < ESW_TUN_ID(12) | ESW_TUN_OPTS(12) | ESW_ZONE_ID(8) > + * Reg C1 = < Reserved(1) | ESW_TUN_ID(12) | ESW_TUN_OPTS(11) | ESW_ZONE_ID(8) > * - * Highest 12 bits of reg c1 is the encapsulation tunnel id, next 12 bits is - * encapsulation tunnel options, and the lowest 8 bits are used for zone id. + * Highest bit is reserved for other offloads as marker bit, next 12 bits of reg c1 + * is the encapsulation tunnel id, next 11 bits is encapsulation tunnel options, + * and the lowest 8 bits are used for zone id. * * Zone id is used to restore CT flow when packet misses on chain. * @@ -109,16 +110,18 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw, * on miss and to support inner header rewrite by means of implicit chain 0 * flows. */ +#define ESW_RESERVED_BITS 1 #define ESW_ZONE_ID_BITS 8 -#define ESW_TUN_OPTS_BITS 12 +#define ESW_TUN_OPTS_BITS 11 #define ESW_TUN_ID_BITS 12 #define ESW_TUN_OPTS_OFFSET ESW_ZONE_ID_BITS #define ESW_TUN_OFFSET ESW_TUN_OPTS_OFFSET #define ESW_ZONE_ID_MASK GENMASK(ESW_ZONE_ID_BITS - 1, 0) -#define ESW_TUN_OPTS_MASK GENMASK(32 - ESW_TUN_ID_BITS - 1, ESW_TUN_OPTS_OFFSET) -#define ESW_TUN_MASK GENMASK(31, ESW_TUN_OFFSET) +#define ESW_TUN_OPTS_MASK GENMASK(31 - ESW_TUN_ID_BITS - ESW_RESERVED_BITS, ESW_TUN_OPTS_OFFSET) +#define ESW_TUN_MASK GENMASK(31 - ESW_RESERVED_BITS, ESW_TUN_OFFSET) #define ESW_TUN_ID_SLOW_TABLE_GOTO_VPORT 0 /* 0 is not a valid tunnel id */ -#define ESW_TUN_OPTS_SLOW_TABLE_GOTO_VPORT 0xFFF /* 0xFFF is a reserved mapping */ +/* 0x7FF is a reserved mapping */ +#define ESW_TUN_OPTS_SLOW_TABLE_GOTO_VPORT GENMASK(ESW_TUN_OPTS_BITS - 1, 0) #define ESW_TUN_SLOW_TABLE_GOTO_VPORT ((ESW_TUN_ID_SLOW_TABLE_GOTO_VPORT << ESW_TUN_OPTS_BITS) | \ ESW_TUN_OPTS_SLOW_TABLE_GOTO_VPORT) #define ESW_TUN_SLOW_TABLE_GOTO_VPORT_MARK ESW_TUN_OPTS_MASK -- cgit v1.2.3 From 4a98544d182761873381d46bb1a498703ca85bf0 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Mon, 8 Mar 2021 14:16:02 +0200 Subject: net/mlx5: Move chains ft pool to be used by all firmware steering Firmware FT pool is per device, but the software tracking of this pool only services fs_chains users, and if another layer takes a flow table, the pool will not be updated, and fs_chains will fail creating a flow table, with no recovery till the flow table is returned. Move FT pool to be global per device, and stored at the cmd level, so all layers can use it. Signed-off-by: Paul Blakey Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f8e8d7e90616..6a7749c21b82 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -550,6 +550,7 @@ struct mlx5_adev { int idx; }; +struct mlx5_ft_pool; struct mlx5_priv { /* IRQ table valid only for real pci devices PF or VF */ struct mlx5_irq_table *irq_table; @@ -602,6 +603,7 @@ struct mlx5_priv { struct mlx5_core_roce roce; struct mlx5_fc_stats fc_stats; struct mlx5_rl_table rl_table; + struct mlx5_ft_pool *ft_pool; struct mlx5_bfreg_data bfregs; struct mlx5_uars_page *uar; -- cgit v1.2.3 From f2867434002387c9739494041ac81c17a3808150 Mon Sep 17 00:00:00 2001 From: Suman Anna Date: Wed, 19 May 2021 13:03:04 -0500 Subject: remoteproc: Fix various kernel-doc warnings Fix all the kernel-doc warnings in various remoteproc core files. Some of them just needed a formatting cleanup change, while others needed the Return statement to be added, or documenting the missed structure elements. Reviewed-by: Mathieu Poirier Signed-off-by: Suman Anna Link: https://lore.kernel.org/r/20210519180304.23563-3-s-anna@ti.com Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 50 +++++++++++++++++++++++++--------------------- 1 file changed, 27 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 8b795b544f75..a5b37bc10865 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -243,7 +243,7 @@ struct fw_rsc_trace { * @da: device address * @align: the alignment between the consumer and producer parts of the vring * @num: num of buffers supported by this vring (must be power of two) - * @notifyid is a unique rproc-wide notify index for this vring. This notify + * @notifyid: a unique rproc-wide notify index for this vring. This notify * index is used when kicking a remote processor, to let it know that this * vring is triggered. * @pa: physical address @@ -266,18 +266,18 @@ struct fw_rsc_vdev_vring { /** * struct fw_rsc_vdev - virtio device header * @id: virtio device id (as in virtio_ids.h) - * @notifyid is a unique rproc-wide notify index for this vdev. This notify + * @notifyid: a unique rproc-wide notify index for this vdev. This notify * index is used when kicking a remote processor, to let it know that the * status/features of this vdev have changes. - * @dfeatures specifies the virtio device features supported by the firmware - * @gfeatures is a place holder used by the host to write back the + * @dfeatures: specifies the virtio device features supported by the firmware + * @gfeatures: a place holder used by the host to write back the * negotiated features that are supported by both sides. - * @config_len is the size of the virtio config space of this vdev. The config + * @config_len: the size of the virtio config space of this vdev. The config * space lies in the resource table immediate after this vdev header. - * @status is a place holder where the host will indicate its virtio progress. - * @num_of_vrings indicates how many vrings are described in this vdev header + * @status: a place holder where the host will indicate its virtio progress. + * @num_of_vrings: indicates how many vrings are described in this vdev header * @reserved: reserved (must be zero) - * @vring is an array of @num_of_vrings entries of 'struct fw_rsc_vdev_vring'. + * @vring: an array of @num_of_vrings entries of 'struct fw_rsc_vdev_vring'. * * This resource is a virtio device header: it provides information about * the vdev, and is then used by the host and its peer remote processors @@ -287,16 +287,17 @@ struct fw_rsc_vdev_vring { * to statically allocate a vdev upon registration of the rproc (dynamic vdev * allocation is not yet supported). * - * Note: unlike virtualization systems, the term 'host' here means - * the Linux side which is running remoteproc to control the remote - * processors. We use the name 'gfeatures' to comply with virtio's terms, - * though there isn't really any virtualized guest OS here: it's the host - * which is responsible for negotiating the final features. - * Yeah, it's a bit confusing. - * - * Note: immediately following this structure is the virtio config space for - * this vdev (which is specific to the vdev; for more info, read the virtio - * spec). the size of the config space is specified by @config_len. + * Note: + * 1. unlike virtualization systems, the term 'host' here means + * the Linux side which is running remoteproc to control the remote + * processors. We use the name 'gfeatures' to comply with virtio's terms, + * though there isn't really any virtualized guest OS here: it's the host + * which is responsible for negotiating the final features. + * Yeah, it's a bit confusing. + * + * 2. immediately following this structure is the virtio config space for + * this vdev (which is specific to the vdev; for more info, read the virtio + * spec). The size of the config space is specified by @config_len. */ struct fw_rsc_vdev { u32 id; @@ -440,7 +441,7 @@ enum rproc_state { * enum rproc_crash_type - remote processor crash types * @RPROC_MMUFAULT: iommu fault * @RPROC_WATCHDOG: watchdog bite - * @RPROC_FATAL_ERROR fatal error + * @RPROC_FATAL_ERROR: fatal error * * Each element of the enum is used as an array index. So that, the value of * the elements should be always something sane. @@ -457,9 +458,9 @@ enum rproc_crash_type { * enum rproc_dump_mechanism - Coredump options for core * @RPROC_COREDUMP_DISABLED: Don't perform any dump * @RPROC_COREDUMP_ENABLED: Copy dump to separate buffer and carry on with - recovery + * recovery * @RPROC_COREDUMP_INLINE: Read segments directly from device memory. Stall - recovery until all segments are read + * recovery until all segments are read */ enum rproc_dump_mechanism { RPROC_COREDUMP_DISABLED, @@ -475,6 +476,7 @@ enum rproc_dump_mechanism { * @priv: private data associated with the dump_segment * @dump: custom dump function to fill device memory segment associated * with coredump + * @offset: offset of the segment */ struct rproc_dump_segment { struct list_head node; @@ -524,7 +526,9 @@ struct rproc_dump_segment { * @auto_boot: flag to indicate if remote processor should be auto-started * @dump_segments: list of segments in the firmware * @nb_vdev: number of vdev currently handled by rproc - * @char_dev: character device of the rproc + * @elf_class: firmware ELF class + * @elf_machine: firmware ELF machine + * @cdev: character device of the rproc * @cdev_put_on_release: flag to indicate if remoteproc should be shutdown on @char_dev release */ struct rproc { @@ -613,10 +617,10 @@ struct rproc_vring { * struct rproc_vdev - remoteproc state for a supported virtio device * @refcount: reference counter for the vdev and vring allocations * @subdev: handle for registering the vdev as a rproc subdevice + * @dev: device struct used for reference count semantics * @id: virtio device id (as in virtio_ids.h) * @node: list node * @rproc: the rproc handle - * @vdev: the virio device * @vring: the vrings for this vdev * @rsc_offset: offset of the vdev's resource entry * @index: vdev position versus other vdev declared in resource table -- cgit v1.2.3 From 5c350aa11b441b32baf3bfe4018168cb8d10cef7 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 28 May 2021 11:24:15 +0200 Subject: fcntl: remove unused VALID_UPGRADE_FLAGS We currently do not maky use of this feature and should we implement something like this in the future it's trivial to add it back. Link: https://lore.kernel.org/r/20210528092417.3942079-2-brauner@kernel.org Cc: Christoph Hellwig Cc: Aleksa Sarai Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Suggested-by: Richard Guy Briggs Reviewed-by: Richard Guy Briggs Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner --- include/linux/fcntl.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h index 766fcd973beb..a332e79b3207 100644 --- a/include/linux/fcntl.h +++ b/include/linux/fcntl.h @@ -12,10 +12,6 @@ FASYNC | O_DIRECT | O_LARGEFILE | O_DIRECTORY | O_NOFOLLOW | \ O_NOATIME | O_CLOEXEC | O_PATH | __O_TMPFILE) -/* List of all valid flags for the how->upgrade_mask argument: */ -#define VALID_UPGRADE_FLAGS \ - (UPGRADE_NOWRITE | UPGRADE_NOREAD) - /* List of all valid flags for the how->resolve argument: */ #define VALID_RESOLVE_FLAGS \ (RESOLVE_NO_XDEV | RESOLVE_NO_MAGICLINKS | RESOLVE_NO_SYMLINKS | \ -- cgit v1.2.3 From 5a7b95fb993ec399c8a685552aa6a8fc995c40bd Mon Sep 17 00:00:00 2001 From: Bibby Hsieh Date: Thu, 27 May 2021 15:55:53 +0800 Subject: i2c: core: support bus regulator controlling in adapter Although in the most platforms, the bus power of i2c are alway on, some platforms disable the i2c bus power in order to meet low power request. We can control bulk regulator if it is provided in i2c adapter device. Signed-off-by: Bibby Hsieh Signed-off-by: Marek Szyprowski Signed-off-by: Hsin-Yi Wang Reviewed-by: Matthias Brugger Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index e8f2ac8c9c3d..953a4eecb88f 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -15,6 +15,7 @@ #include /* for struct device */ #include /* for completion */ #include +#include #include #include /* for Host Notify IRQ */ #include /* for struct device_node */ @@ -729,6 +730,7 @@ struct i2c_adapter { const struct i2c_adapter_quirks *quirks; struct irq_domain *host_notify_domain; + struct regulator *bus_regulator; }; #define to_i2c_adapter(d) container_of(d, struct i2c_adapter, dev) -- cgit v1.2.3 From 586d5a8bcede47fda7bebf4b36be917c5010db16 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 28 May 2021 12:30:03 +0200 Subject: netfilter: x_tables: reduce xt_action_param by 8 byte The fragment offset in ipv4/ipv6 is a 16bit field, so use u16 instead of unsigned int. On 64bit: 40 bytes to 32 bytes. By extension this also reduces nft_pktinfo (56 to 48 byte). Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/x_tables.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 07c6ad8f2a02..28d7027cd460 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -36,8 +36,8 @@ struct xt_action_param { const void *matchinfo, *targinfo; }; const struct nf_hook_state *state; - int fragoff; unsigned int thoff; + u16 fragoff; bool hotdrop; }; -- cgit v1.2.3 From 6802db48fc27b8d7f601e96a85771f2205702941 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 28 May 2021 12:30:04 +0200 Subject: netfilter: reduce size of nf_hook_state on 32bit platforms Reduce size from 28 to 24 bytes on 32bit platforms. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index f0f3a8354c3c..f161569fbe2f 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -65,8 +65,8 @@ struct nf_hook_ops; struct sock; struct nf_hook_state { - unsigned int hook; - u_int8_t pf; + u8 hook; + u8 pf; struct net_device *in; struct net_device *out; struct sock *sk; -- cgit v1.2.3 From e860fa9b69e1bf077ba4725ee4be7b9443a3682a Mon Sep 17 00:00:00 2001 From: Dave Ertman Date: Thu, 20 May 2021 09:37:48 -0500 Subject: iidc: Introduce iidc.h Introduce a shared header file used by the 'ice' Intel networking driver providing RDMA support and the 'irdma' driver to provide a private interface. Signed-off-by: Dave Ertman Signed-off-by: Shiraz Saleem Signed-off-by: Tony Nguyen --- include/linux/net/intel/iidc.h | 100 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 100 insertions(+) create mode 100644 include/linux/net/intel/iidc.h (limited to 'include/linux') diff --git a/include/linux/net/intel/iidc.h b/include/linux/net/intel/iidc.h new file mode 100644 index 000000000000..e32f6712aee0 --- /dev/null +++ b/include/linux/net/intel/iidc.h @@ -0,0 +1,100 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2021, Intel Corporation. */ + +#ifndef _IIDC_H_ +#define _IIDC_H_ + +#include +#include +#include +#include +#include +#include + +enum iidc_event_type { + IIDC_EVENT_BEFORE_MTU_CHANGE, + IIDC_EVENT_AFTER_MTU_CHANGE, + IIDC_EVENT_BEFORE_TC_CHANGE, + IIDC_EVENT_AFTER_TC_CHANGE, + IIDC_EVENT_CRIT_ERR, + IIDC_EVENT_NBITS /* must be last */ +}; + +enum iidc_reset_type { + IIDC_PFR, + IIDC_CORER, + IIDC_GLOBR, +}; + +#define IIDC_MAX_USER_PRIORITY 8 + +/* Struct to hold per RDMA Qset info */ +struct iidc_rdma_qset_params { + /* Qset TEID returned to the RDMA driver in + * ice_add_rdma_qset and used by RDMA driver + * for calls to ice_del_rdma_qset + */ + u32 teid; /* Qset TEID */ + u16 qs_handle; /* RDMA driver provides this */ + u16 vport_id; /* VSI index */ + u8 tc; /* TC branch the Qset should belong to */ +}; + +struct iidc_qos_info { + u64 tc_ctx; + u8 rel_bw; + u8 prio_type; + u8 egress_virt_up; + u8 ingress_virt_up; +}; + +/* Struct to pass QoS info */ +struct iidc_qos_params { + struct iidc_qos_info tc_info[IEEE_8021QAZ_MAX_TCS]; + u8 up2tc[IIDC_MAX_USER_PRIORITY]; + u8 vport_relative_bw; + u8 vport_priority_type; + u8 num_tc; +}; + +struct iidc_event { + DECLARE_BITMAP(type, IIDC_EVENT_NBITS); + u32 reg; +}; + +struct ice_pf; + +int ice_add_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset); +int ice_del_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset); +int ice_rdma_request_reset(struct ice_pf *pf, enum iidc_reset_type reset_type); +int ice_rdma_update_vsi_filter(struct ice_pf *pf, u16 vsi_id, bool enable); +void ice_get_qos_params(struct ice_pf *pf, struct iidc_qos_params *qos); + +#define IIDC_RDMA_ROCE_NAME "roce" + +/* Structure representing auxiliary driver tailored information about the core + * PCI dev, each auxiliary driver using the IIDC interface will have an + * instance of this struct dedicated to it. + */ + +struct iidc_auxiliary_dev { + struct auxiliary_device adev; + struct ice_pf *pf; +}; + +/* structure representing the auxiliary driver. This struct is to be + * allocated and populated by the auxiliary driver's owner. The core PCI + * driver will access these ops by performing a container_of on the + * auxiliary_device->dev.driver. + */ +struct iidc_auxiliary_drv { + struct auxiliary_driver adrv; + /* This event_handler is meant to be a blocking call. For instance, + * when a BEFORE_MTU_CHANGE event comes in, the event_handler will not + * return until the auxiliary driver is ready for the MTU change to + * happen. + */ + void (*event_handler)(struct ice_pf *pf, struct iidc_event *event); +}; + +#endif /* _IIDC_H_*/ -- cgit v1.2.3 From 9ed7533121219cb25408888cf7fbb929cedc033c Mon Sep 17 00:00:00 2001 From: Shiraz Saleem Date: Fri, 21 May 2021 10:10:59 -0700 Subject: i40e: Prep i40e header for aux bus conversion Add the definitions to the i40e client header file in preparation to convert i40e to use the new auxiliary bus infrastructure. This header is shared between the 'i40e' Intel networking driver providing RDMA support and the 'irdma' driver. Signed-off-by: Shiraz Saleem Signed-off-by: Tony Nguyen --- include/linux/net/intel/i40e_client.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/net/intel/i40e_client.h b/include/linux/net/intel/i40e_client.h index fd7bc860a241..41f24b5241ab 100644 --- a/include/linux/net/intel/i40e_client.h +++ b/include/linux/net/intel/i40e_client.h @@ -4,6 +4,8 @@ #ifndef _I40E_CLIENT_H_ #define _I40E_CLIENT_H_ +#include + #define I40E_CLIENT_STR_LENGTH 10 /* Client interface version should be updated anytime there is a change in the @@ -78,6 +80,7 @@ struct i40e_info { u8 lanmac[6]; struct net_device *netdev; struct pci_dev *pcidev; + struct auxiliary_device *aux_dev; u8 __iomem *hw_addr; u8 fid; /* function id, PF id or VF id */ #define I40E_CLIENT_FTYPE_PF 0 @@ -100,6 +103,11 @@ struct i40e_info { u32 fw_build; /* firmware build number */ }; +struct i40e_auxiliary_device { + struct auxiliary_device aux_dev; + struct i40e_info *ldev; +}; + #define I40E_CLIENT_RESET_LEVEL_PF 1 #define I40E_CLIENT_RESET_LEVEL_CORE 2 #define I40E_CLIENT_VSI_FLAG_TCP_ENABLE BIT(1) @@ -187,6 +195,8 @@ static inline bool i40e_client_is_registered(struct i40e_client *client) return test_bit(__I40E_CLIENT_REGISTERED, &client->state); } +void i40e_client_device_register(struct i40e_info *ldev, struct i40e_client *client); +void i40e_client_device_unregister(struct i40e_info *ldev); /* used by clients */ int i40e_register_client(struct i40e_client *client); int i40e_unregister_client(struct i40e_client *client); -- cgit v1.2.3 From acfbb1911dc907f5f2f1096e88feeaff433bba81 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 18 May 2021 13:43:22 +0300 Subject: dmaengine: Move kdoc description of struct dma_chan_percpu closer to it We have split by unknown reason of kdoc and struct dma_chan_percpu definition. Join them back. No functional change. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20210518104323.37632-1-andriy.shevchenko@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 004736b6a9c8..93c3ca5fdafd 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -229,12 +229,6 @@ enum sum_check_flags { */ typedef struct { DECLARE_BITMAP(bits, DMA_TX_TYPE_END); } dma_cap_mask_t; -/** - * struct dma_chan_percpu - the per-CPU part of struct dma_chan - * @memcpy_count: transaction counter - * @bytes_transferred: byte counter - */ - /** * enum dma_desc_metadata_mode - per descriptor metadata mode types supported * @DESC_METADATA_CLIENT - the metadata buffer is allocated/provided by the @@ -291,6 +285,11 @@ enum dma_desc_metadata_mode { DESC_METADATA_ENGINE = BIT(1), }; +/** + * struct dma_chan_percpu - the per-CPU part of struct dma_chan + * @memcpy_count: transaction counter + * @bytes_transferred: byte counter + */ struct dma_chan_percpu { /* stats */ unsigned long memcpy_count; -- cgit v1.2.3 From c58e7ed28b4534ed073371843d03c433d6a9fe34 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 26 May 2021 12:22:51 -0400 Subject: PM: runtime: document common mistake with pm_runtime_get_sync() pm_runtime_get_sync(), contradictory to intuition, does not drop the runtime PM usage counter on errors which lead to several wrong usages in drivers (missing the put). pm_runtime_resume_and_get() was added as a better implementation so document the preference of using it, hoping it will stop bad patterns. Suggested-by: Marek Szyprowski Signed-off-by: Krzysztof Kozlowski [ rjw: Documentation change edits ] Signed-off-by: Rafael J. Wysocki --- include/linux/pm_runtime.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 6c08a085367b..aab8b35e9f8a 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -380,6 +380,9 @@ static inline int pm_runtime_get(struct device *dev) * The possible return values of this function are the same as for * pm_runtime_resume() and the runtime PM usage counter of @dev remains * incremented in all cases, even if it returns an error code. + * Consider using pm_runtime_resume_and_get() instead of it, especially + * if its return value is checked by the caller, as this is likely to result + * in cleaner code. */ static inline int pm_runtime_get_sync(struct device *dev) { -- cgit v1.2.3 From 220a31b091fb77886eb224ce2d7a5d890e43de63 Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Sat, 29 May 2021 19:03:03 +0800 Subject: kgdb: Fix spelling mistakes Fix some spelling mistakes in comments: initalization ==> initialization detatch ==> detach represntation ==> representation hexidecimal ==> hexadecimal delimeter ==> delimiter architecure ==> architecture Signed-off-by: Zhen Lei Link: https://lore.kernel.org/r/20210529110305.9446-3-thunder.leizhen@huawei.com Signed-off-by: Daniel Thompson --- include/linux/kgdb.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index 392a3670944c..258cdde8d356 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -105,9 +105,9 @@ extern int dbg_set_reg(int regno, void *mem, struct pt_regs *regs); */ /** - * kgdb_arch_init - Perform any architecture specific initalization. + * kgdb_arch_init - Perform any architecture specific initialization. * - * This function will handle the initalization of any architecture + * This function will handle the initialization of any architecture * specific callbacks. */ extern int kgdb_arch_init(void); @@ -229,9 +229,9 @@ extern int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt); extern int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt); /** - * kgdb_arch_late - Perform any architecture specific initalization. + * kgdb_arch_late - Perform any architecture specific initialization. * - * This function will handle the late initalization of any + * This function will handle the late initialization of any * architecture specific callbacks. This is an optional function for * handling things like late initialization of hw breakpoints. The * default implementation does nothing. -- cgit v1.2.3 From 0e5cb7770684b4c81bcc63f4675e488f9a0e31eb Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sat, 27 Feb 2021 10:23:45 +0000 Subject: irqchip/gic: Split vGIC probing information from the GIC code The vGIC advertising code is unsurprisingly very much tied to the GIC implementations. However, we are about to extend the support to lesser implementations. Let's dissociate the vgic registration from the GIC code and move it into KVM, where it makes a bit more sense. This also allows us to mark the gic_kvm_info structures as __initdata. Reviewed-by: Alexandru Elisei Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-common.h | 25 +-------------------- include/linux/irqchip/arm-vgic-info.h | 41 ++++++++++++++++++++++++++++++++++ 2 files changed, 42 insertions(+), 24 deletions(-) create mode 100644 include/linux/irqchip/arm-vgic-info.h (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-common.h b/include/linux/irqchip/arm-gic-common.h index fa8c0455c352..1177f3a1aed5 100644 --- a/include/linux/irqchip/arm-gic-common.h +++ b/include/linux/irqchip/arm-gic-common.h @@ -7,8 +7,7 @@ #ifndef __LINUX_IRQCHIP_ARM_GIC_COMMON_H #define __LINUX_IRQCHIP_ARM_GIC_COMMON_H -#include -#include +#include #define GICD_INT_DEF_PRI 0xa0 #define GICD_INT_DEF_PRI_X4 ((GICD_INT_DEF_PRI << 24) |\ @@ -16,28 +15,6 @@ (GICD_INT_DEF_PRI << 8) |\ GICD_INT_DEF_PRI) -enum gic_type { - GIC_V2, - GIC_V3, -}; - -struct gic_kvm_info { - /* GIC type */ - enum gic_type type; - /* Virtual CPU interface */ - struct resource vcpu; - /* Interrupt number */ - unsigned int maint_irq; - /* Virtual control interface */ - struct resource vctrl; - /* vlpi support */ - bool has_v4; - /* rvpeid support */ - bool has_v4_1; -}; - -const struct gic_kvm_info *gic_get_kvm_info(void); - struct irq_domain; struct fwnode_handle; int gicv2m_init(struct fwnode_handle *parent_handle, diff --git a/include/linux/irqchip/arm-vgic-info.h b/include/linux/irqchip/arm-vgic-info.h new file mode 100644 index 000000000000..a25d4da5697d --- /dev/null +++ b/include/linux/irqchip/arm-vgic-info.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * include/linux/irqchip/arm-vgic-info.h + * + * Copyright (C) 2016 ARM Limited, All Rights Reserved. + */ +#ifndef __LINUX_IRQCHIP_ARM_VGIC_INFO_H +#define __LINUX_IRQCHIP_ARM_VGIC_INFO_H + +#include +#include + +enum gic_type { + /* Full GICv2 */ + GIC_V2, + /* Full GICv3, optionally with v2 compat */ + GIC_V3, +}; + +struct gic_kvm_info { + /* GIC type */ + enum gic_type type; + /* Virtual CPU interface */ + struct resource vcpu; + /* Interrupt number */ + unsigned int maint_irq; + /* Virtual control interface */ + struct resource vctrl; + /* vlpi support */ + bool has_v4; + /* rvpeid support */ + bool has_v4_1; +}; + +#ifdef CONFIG_KVM +void vgic_set_kvm_info(const struct gic_kvm_info *info); +#else +static inline void vgic_set_kvm_info(const struct gic_kvm_info *info) {} +#endif + +#endif -- cgit v1.2.3 From 669062d2a1aa36661b490683fe17810aa24a9cfb Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sun, 28 Feb 2021 11:09:59 +0000 Subject: KVM: arm64: vgic: Be tolerant to the lack of maintenance interrupt masking As it turns out, not all the interrupt controllers are able to expose a vGIC maintenance interrupt that can be independently enabled/disabled. And to be fair, it doesn't really matter as all we require is for the interrupt to kick us out of guest mode out way or another. To that effect, add gic_kvm_info.no_maint_irq_mask for an interrupt controller to advertise the lack of masking. Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-vgic-info.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-vgic-info.h b/include/linux/irqchip/arm-vgic-info.h index a25d4da5697d..7c0d08ebb82c 100644 --- a/include/linux/irqchip/arm-vgic-info.h +++ b/include/linux/irqchip/arm-vgic-info.h @@ -24,6 +24,8 @@ struct gic_kvm_info { struct resource vcpu; /* Interrupt number */ unsigned int maint_irq; + /* No interrupt mask, no need to use the above field */ + bool no_maint_irq_mask; /* Virtual control interface */ struct resource vctrl; /* vlpi support */ -- cgit v1.2.3 From f6c3e24fb721dda247f6691c809d6e6c413f22c7 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 15 Mar 2021 21:56:47 +0000 Subject: KVM: arm64: vgic: Let an interrupt controller advertise lack of HW deactivation The vGIC, as architected by ARM, allows a virtual interrupt to trigger the deactivation of a physical interrupt. This allows the following interrupt to be delivered without requiring an exit. However, some implementations have choosen not to implement this, meaning that we will need some unsavoury workarounds to deal with this. On detecting such a case, taint the kernel and spit a nastygram. We'll deal with this in later patches. Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-vgic-info.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-vgic-info.h b/include/linux/irqchip/arm-vgic-info.h index 7c0d08ebb82c..a75b2c7de69d 100644 --- a/include/linux/irqchip/arm-vgic-info.h +++ b/include/linux/irqchip/arm-vgic-info.h @@ -32,6 +32,8 @@ struct gic_kvm_info { bool has_v4; /* rvpeid support */ bool has_v4_1; + /* Deactivation impared, subpar stuff */ + bool no_hw_deactivation; }; #ifdef CONFIG_KVM -- cgit v1.2.3 From 380d2b2d5a0491e47dfa250b40e3d849a922871d Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Fri, 28 May 2021 02:54:00 +0300 Subject: regulator: core: Add regulator_sync_voltage_rdev() Some NVIDIA Tegra devices use a CPU soft-reset method for the reboot and in this case we need to restore the coupled voltages to the state that is suitable for hardware during boot. Add new regulator_sync_voltage_rdev() helper which is needed by regulator drivers in order to sync voltage of a coupled regulators. Acked-by: Mark Brown Signed-off-by: Dmitry Osipenko Signed-off-by: Thierry Reding --- include/linux/regulator/driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 4ea520c248e9..35e5a611db81 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -540,6 +540,7 @@ int regulator_set_current_limit_regmap(struct regulator_dev *rdev, int regulator_get_current_limit_regmap(struct regulator_dev *rdev); void *regulator_get_init_drvdata(struct regulator_init_data *reg_init_data); int regulator_set_ramp_delay_regmap(struct regulator_dev *rdev, int ramp_delay); +int regulator_sync_voltage_rdev(struct regulator_dev *rdev); /* * Helper functions intended to be used by regulator drivers prior registering -- cgit v1.2.3 From e848edae31263d2119e7cde779d754439277fbba Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Tue, 1 Jun 2021 05:31:11 +0300 Subject: clk: tegra: Add stubs needed for compile-testing Add stubs needed for compile-testing of Tegra memory drivers. Signed-off-by: Dmitry Osipenko Signed-off-by: Thierry Reding --- include/linux/clk/tegra.h | 100 ++++++++++++++++++++++++++++++++++++---------- 1 file changed, 79 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk/tegra.h b/include/linux/clk/tegra.h index f7ff722a03dd..d128ad1570aa 100644 --- a/include/linux/clk/tegra.h +++ b/include/linux/clk/tegra.h @@ -123,20 +123,6 @@ static inline void tegra_cpu_clock_resume(void) } #endif -extern int tegra210_plle_hw_sequence_start(void); -extern bool tegra210_plle_hw_sequence_is_enabled(void); -extern void tegra210_xusb_pll_hw_control_enable(void); -extern void tegra210_xusb_pll_hw_sequence_start(void); -extern void tegra210_sata_pll_hw_control_enable(void); -extern void tegra210_sata_pll_hw_sequence_start(void); -extern void tegra210_set_sata_pll_seq_sw(bool state); -extern void tegra210_put_utmipll_in_iddq(void); -extern void tegra210_put_utmipll_out_iddq(void); -extern int tegra210_clk_handle_mbist_war(unsigned int id); -extern void tegra210_clk_emc_dll_enable(bool flag); -extern void tegra210_clk_emc_dll_update_setting(u32 emc_dll_src_value); -extern void tegra210_clk_emc_update_setting(u32 emc_src_value); - struct clk; struct tegra_emc; @@ -144,17 +130,10 @@ typedef long (tegra20_clk_emc_round_cb)(unsigned long rate, unsigned long min_rate, unsigned long max_rate, void *arg); - -void tegra20_clk_set_emc_round_callback(tegra20_clk_emc_round_cb *round_cb, - void *cb_arg); -int tegra20_clk_prepare_emc_mc_same_freq(struct clk *emc_clk, bool same); - typedef int (tegra124_emc_prepare_timing_change_cb)(struct tegra_emc *emc, unsigned long rate); typedef void (tegra124_emc_complete_timing_change_cb)(struct tegra_emc *emc, unsigned long rate); -void tegra124_clk_set_emc_callbacks(tegra124_emc_prepare_timing_change_cb *prep_cb, - tegra124_emc_complete_timing_change_cb *complete_cb); struct tegra210_clk_emc_config { unsigned long rate; @@ -176,8 +155,87 @@ struct tegra210_clk_emc_provider { const struct tegra210_clk_emc_config *config); }; +#if defined(CONFIG_ARCH_TEGRA_2x_SOC) || defined(CONFIG_ARCH_TEGRA_3x_SOC) +void tegra20_clk_set_emc_round_callback(tegra20_clk_emc_round_cb *round_cb, + void *cb_arg); +int tegra20_clk_prepare_emc_mc_same_freq(struct clk *emc_clk, bool same); +#else +static inline void +tegra20_clk_set_emc_round_callback(tegra20_clk_emc_round_cb *round_cb, + void *cb_arg) +{ +} + +static inline int +tegra20_clk_prepare_emc_mc_same_freq(struct clk *emc_clk, bool same) +{ + return 0; +} +#endif + +#ifdef CONFIG_TEGRA124_CLK_EMC +void tegra124_clk_set_emc_callbacks(tegra124_emc_prepare_timing_change_cb *prep_cb, + tegra124_emc_complete_timing_change_cb *complete_cb); +#else +static inline void +tegra124_clk_set_emc_callbacks(tegra124_emc_prepare_timing_change_cb *prep_cb, + tegra124_emc_complete_timing_change_cb *complete_cb) +{ +} +#endif + +#ifdef CONFIG_ARCH_TEGRA_210_SOC +int tegra210_plle_hw_sequence_start(void); +bool tegra210_plle_hw_sequence_is_enabled(void); +void tegra210_xusb_pll_hw_control_enable(void); +void tegra210_xusb_pll_hw_sequence_start(void); +void tegra210_sata_pll_hw_control_enable(void); +void tegra210_sata_pll_hw_sequence_start(void); +void tegra210_set_sata_pll_seq_sw(bool state); +void tegra210_put_utmipll_in_iddq(void); +void tegra210_put_utmipll_out_iddq(void); +int tegra210_clk_handle_mbist_war(unsigned int id); +void tegra210_clk_emc_dll_enable(bool flag); +void tegra210_clk_emc_dll_update_setting(u32 emc_dll_src_value); +void tegra210_clk_emc_update_setting(u32 emc_src_value); + int tegra210_clk_emc_attach(struct clk *clk, struct tegra210_clk_emc_provider *provider); void tegra210_clk_emc_detach(struct clk *clk); +#else +static inline int tegra210_plle_hw_sequence_start(void) +{ + return 0; +} + +static inline bool tegra210_plle_hw_sequence_is_enabled(void) +{ + return false; +} + +static inline int tegra210_clk_handle_mbist_war(unsigned int id) +{ + return 0; +} + +static inline int +tegra210_clk_emc_attach(struct clk *clk, + struct tegra210_clk_emc_provider *provider) +{ + return 0; +} + +static inline void tegra210_xusb_pll_hw_control_enable(void) {} +static inline void tegra210_xusb_pll_hw_sequence_start(void) {} +static inline void tegra210_sata_pll_hw_control_enable(void) {} +static inline void tegra210_sata_pll_hw_sequence_start(void) {} +static inline void tegra210_set_sata_pll_seq_sw(bool state) {} +static inline void tegra210_put_utmipll_in_iddq(void) {} +static inline void tegra210_put_utmipll_out_iddq(void) {} +static inline void tegra210_clk_emc_dll_enable(bool flag) {} +static inline void tegra210_clk_emc_dll_update_setting(u32 emc_dll_src_value) {} +static inline void tegra210_clk_emc_update_setting(u32 emc_src_value) {} +static inline void tegra210_clk_emc_detach(struct clk *clk) {} +#endif #endif /* __LINUX_CLK_TEGRA_H_ */ -- cgit v1.2.3 From 4a1c456a57c3366d736548ad4d09eb3aa0b9ddaf Mon Sep 17 00:00:00 2001 From: Chris Morgan Date: Wed, 19 May 2021 15:37:51 -0500 Subject: mfd: Add Rockchip rk817 audio CODEC support Add rk817 codec support cell to rk808 mfd driver. Signed-off-by: Chris Morgan Tested-by: Maciej Matuszczyk Signed-off-by: Lee Jones --- include/linux/mfd/rk808.h | 81 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 81 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/rk808.h b/include/linux/mfd/rk808.h index e07f6e61cd38..a96e6d43ca06 100644 --- a/include/linux/mfd/rk808.h +++ b/include/linux/mfd/rk808.h @@ -437,6 +437,87 @@ enum rk809_reg_id { #define RK817_RTC_COMP_LSB_REG 0x10 #define RK817_RTC_COMP_MSB_REG 0x11 +/* RK817 Codec Registers */ +#define RK817_CODEC_DTOP_VUCTL 0x12 +#define RK817_CODEC_DTOP_VUCTIME 0x13 +#define RK817_CODEC_DTOP_LPT_SRST 0x14 +#define RK817_CODEC_DTOP_DIGEN_CLKE 0x15 +#define RK817_CODEC_AREF_RTCFG0 0x16 +#define RK817_CODEC_AREF_RTCFG1 0x17 +#define RK817_CODEC_AADC_CFG0 0x18 +#define RK817_CODEC_AADC_CFG1 0x19 +#define RK817_CODEC_DADC_VOLL 0x1a +#define RK817_CODEC_DADC_VOLR 0x1b +#define RK817_CODEC_DADC_SR_ACL0 0x1e +#define RK817_CODEC_DADC_ALC1 0x1f +#define RK817_CODEC_DADC_ALC2 0x20 +#define RK817_CODEC_DADC_NG 0x21 +#define RK817_CODEC_DADC_HPF 0x22 +#define RK817_CODEC_DADC_RVOLL 0x23 +#define RK817_CODEC_DADC_RVOLR 0x24 +#define RK817_CODEC_AMIC_CFG0 0x27 +#define RK817_CODEC_AMIC_CFG1 0x28 +#define RK817_CODEC_DMIC_PGA_GAIN 0x29 +#define RK817_CODEC_DMIC_LMT1 0x2a +#define RK817_CODEC_DMIC_LMT2 0x2b +#define RK817_CODEC_DMIC_NG1 0x2c +#define RK817_CODEC_DMIC_NG2 0x2d +#define RK817_CODEC_ADAC_CFG0 0x2e +#define RK817_CODEC_ADAC_CFG1 0x2f +#define RK817_CODEC_DDAC_POPD_DACST 0x30 +#define RK817_CODEC_DDAC_VOLL 0x31 +#define RK817_CODEC_DDAC_VOLR 0x32 +#define RK817_CODEC_DDAC_SR_LMT0 0x35 +#define RK817_CODEC_DDAC_LMT1 0x36 +#define RK817_CODEC_DDAC_LMT2 0x37 +#define RK817_CODEC_DDAC_MUTE_MIXCTL 0x38 +#define RK817_CODEC_DDAC_RVOLL 0x39 +#define RK817_CODEC_DDAC_RVOLR 0x3a +#define RK817_CODEC_AHP_ANTI0 0x3b +#define RK817_CODEC_AHP_ANTI1 0x3c +#define RK817_CODEC_AHP_CFG0 0x3d +#define RK817_CODEC_AHP_CFG1 0x3e +#define RK817_CODEC_AHP_CP 0x3f +#define RK817_CODEC_ACLASSD_CFG1 0x40 +#define RK817_CODEC_ACLASSD_CFG2 0x41 +#define RK817_CODEC_APLL_CFG0 0x42 +#define RK817_CODEC_APLL_CFG1 0x43 +#define RK817_CODEC_APLL_CFG2 0x44 +#define RK817_CODEC_APLL_CFG3 0x45 +#define RK817_CODEC_APLL_CFG4 0x46 +#define RK817_CODEC_APLL_CFG5 0x47 +#define RK817_CODEC_DI2S_CKM 0x48 +#define RK817_CODEC_DI2S_RSD 0x49 +#define RK817_CODEC_DI2S_RXCR1 0x4a +#define RK817_CODEC_DI2S_RXCR2 0x4b +#define RK817_CODEC_DI2S_RXCMD_TSD 0x4c +#define RK817_CODEC_DI2S_TXCR1 0x4d +#define RK817_CODEC_DI2S_TXCR2 0x4e +#define RK817_CODEC_DI2S_TXCR3_TXCMD 0x4f + +/* RK817_CODEC_DI2S_CKM */ +#define RK817_I2S_MODE_MASK (0x1 << 0) +#define RK817_I2S_MODE_MST (0x1 << 0) +#define RK817_I2S_MODE_SLV (0x0 << 0) + +/* RK817_CODEC_DDAC_MUTE_MIXCTL */ +#define DACMT_MASK (0x1 << 0) +#define DACMT_ENABLE (0x1 << 0) +#define DACMT_DISABLE (0x0 << 0) + +/* RK817_CODEC_DI2S_RXCR2 */ +#define VDW_RX_24BITS (0x17) +#define VDW_RX_16BITS (0x0f) + +/* RK817_CODEC_DI2S_TXCR2 */ +#define VDW_TX_24BITS (0x17) +#define VDW_TX_16BITS (0x0f) + +/* RK817_CODEC_AMIC_CFG0 */ +#define MIC_DIFF_MASK (0x1 << 7) +#define MIC_DIFF_DIS (0x0 << 7) +#define MIC_DIFF_EN (0x1 << 7) + #define RK817_POWER_EN_REG(i) (0xb1 + (i)) #define RK817_POWER_SLP_EN_REG(i) (0xb5 + (i)) -- cgit v1.2.3 From 958229a7c55f219b1cff99f939dabbc1b6ba7161 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 21 May 2021 07:50:54 +0200 Subject: block: add a flag to make put_disk on partially initalized disks safer Add a flag to indicate that __device_add_disk did grab a queue reference so that disk_release only drops it if we actually had it. This sort out one of the major pitfals with partially initialized gendisk that a lot of drivers did get wrong or still do. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Luis Chamberlain Reviewed-by: Ulf Hansson Link: https://lore.kernel.org/r/20210521055116.1053587-5-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/genhd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 6fc26f7bdf71..4d3ee8b6b297 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -153,6 +153,7 @@ struct gendisk { unsigned long state; #define GD_NEED_PART_SCAN 0 #define GD_READ_ONLY 1 +#define GD_QUEUE_REF 2 struct kobject *slave_dir; struct timer_rand_state *random; -- cgit v1.2.3 From f525464a8000f092c20b00eead3eaa9d849c599e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 21 May 2021 07:50:55 +0200 Subject: block: add blk_alloc_disk and blk_cleanup_disk APIs Add two new APIs to allocate and free a gendisk including the request_queue for use with BIO based drivers. This is to avoid boilerplate code in drivers. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Ulf Hansson Link: https://lore.kernel.org/r/20210521055116.1053587-6-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/genhd.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 4d3ee8b6b297..782f0171d104 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -278,6 +278,28 @@ extern void put_disk(struct gendisk *disk); #define alloc_disk(minors) alloc_disk_node(minors, NUMA_NO_NODE) +/** + * blk_alloc_disk - allocate a gendisk structure + * @node_id: numa node to allocate on + * + * Allocate and pre-initialize a gendisk structure for use with BIO based + * drivers. + * + * Context: can sleep + */ +#define blk_alloc_disk(node_id) \ +({ \ + struct gendisk *__disk = __blk_alloc_disk(node_id); \ + static struct lock_class_key __key; \ + \ + if (__disk) \ + lockdep_init_map(&__disk->lockdep_map, \ + "(bio completion)", &__key, 0); \ + __disk; \ +}) +struct gendisk *__blk_alloc_disk(int node); +void blk_cleanup_disk(struct gendisk *disk); + int __register_blkdev(unsigned int major, const char *name, void (*probe)(dev_t devt)); #define register_blkdev(major, name) \ -- cgit v1.2.3 From da7ba72960ca2a9b968e47fcf414d16f3d4c0c42 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 21 May 2021 07:51:16 +0200 Subject: block: unexport blk_alloc_queue blk_alloc_queue is just an internal helper now, unexport it and remove it from the public header. Signed-off-by: Christoph Hellwig Reviewed-by: Ulf Hansson Link: https://lore.kernel.org/r/20210521055116.1053587-27-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2c28577b50f4..d66d0da72529 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1213,7 +1213,6 @@ static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq, extern void blk_dump_rq_flags(struct request *, char *); bool __must_check blk_get_queue(struct request_queue *); -struct request_queue *blk_alloc_queue(int node_id); extern void blk_put_queue(struct request_queue *); extern void blk_set_queue_dying(struct request_queue *); -- cgit v1.2.3 From a8698707a1835be3abd12a3b28079a80999f8dee Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 25 May 2021 08:12:56 +0200 Subject: block: move bd_mutex to struct gendisk MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Replace the per-block device bd_mutex with a per-gendisk open_mutex, thus simplifying locking wherever we deal with partitions. Signed-off-by: Christoph Hellwig Reviewed-by: Ming Lei Acked-by: Roger Pau Monné Link: https://lore.kernel.org/r/20210525061301.2242282-4-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 1 - include/linux/genhd.h | 3 +++ 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index db026b6ec15a..a09660671fa4 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -29,7 +29,6 @@ struct block_device { int bd_openers; struct inode * bd_inode; /* will die */ struct super_block * bd_super; - struct mutex bd_mutex; /* open/close mutex */ void * bd_claiming; struct device bd_device; void * bd_holder; diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 782f0171d104..1fabb1559110 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -154,6 +154,9 @@ struct gendisk { #define GD_NEED_PART_SCAN 0 #define GD_READ_ONLY 1 #define GD_QUEUE_REF 2 + + struct mutex open_mutex; /* open/close mutex */ + struct kobject *slave_dir; struct timer_rand_state *random; -- cgit v1.2.3 From ab4b57057d744861f670b47b163209727b26418b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 25 May 2021 08:12:59 +0200 Subject: block: move bd_part_count to struct gendisk The bd_part_count value only makes sense for whole devices, so move it to struct gendisk and give it a more descriptive name. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Ming Lei Link: https://lore.kernel.org/r/20210525061301.2242282-7-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 3 --- include/linux/genhd.h | 1 + 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index a09660671fa4..fd3860d18d7e 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -39,9 +39,6 @@ struct block_device { #endif struct kobject *bd_holder_dir; u8 bd_partno; - /* number of times partitions within this device have been opened. */ - unsigned bd_part_count; - spinlock_t bd_size_lock; /* for bd_inode->i_size updates */ struct gendisk * bd_disk; struct backing_dev_info *bd_bdi; diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 1fabb1559110..47d4605c0e7e 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -156,6 +156,7 @@ struct gendisk { #define GD_QUEUE_REF 2 struct mutex open_mutex; /* open/close mutex */ + unsigned open_partitions; /* number of open partitions */ struct kobject *slave_dir; -- cgit v1.2.3 From c97d93c31e5734a16bfe663085ec91b8c9fb20f9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 25 May 2021 08:13:00 +0200 Subject: block: factor out a part_devt helper Add a helper to find the dev_t for a disk + partno tuple. Signed-off-by: Christoph Hellwig Reviewed-by: Ming Lei Link: https://lore.kernel.org/r/20210525061301.2242282-8-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/genhd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 47d4605c0e7e..64a8431202b7 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -333,6 +333,7 @@ static inline void bd_unlink_disk_holder(struct block_device *bdev, } #endif /* CONFIG_SYSFS */ +dev_t part_devt(struct gendisk *disk, u8 partno); dev_t blk_lookup_devt(const char *name, int partno); void blk_request_module(dev_t devt); #ifdef CONFIG_BLOCK -- cgit v1.2.3 From 0e0ccdecb3cff95a350b4364e7ebbaa754d0e47d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 25 May 2021 08:13:01 +0200 Subject: block: remove bdget_disk Just opencode the xa_load in the callers, as none of them actually needs a reference to the bdev. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Ming Lei Link: https://lore.kernel.org/r/20210525061301.2242282-9-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/genhd.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 64a8431202b7..03d684f0498f 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -223,7 +223,6 @@ static inline void add_disk_no_queue_reg(struct gendisk *disk) } extern void del_gendisk(struct gendisk *gp); -extern struct block_device *bdget_disk(struct gendisk *disk, int partno); void set_disk_ro(struct gendisk *disk, bool read_only); -- cgit v1.2.3 From ec6aba3d2be1ed75b3f4c894bb64a36d40db1f55 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 25 May 2021 09:25:19 +0200 Subject: kprobes: Remove kprobe::fault_handler The reason for kprobe::fault_handler(), as given by their comment: * We come here because instructions in the pre/post * handler caused the page_fault, this could happen * if handler tries to access user space by * copy_from_user(), get_user() etc. Let the * user-specified handler try to fix it first. Is just plain bad. Those other handlers are ran from non-preemptible context and had better use _nofault() functions. Also, there is no upstream usage of this. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Christoph Hellwig Acked-by: Masami Hiramatsu Link: https://lore.kernel.org/r/20210525073213.561116662@infradead.org --- include/linux/kprobes.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 1883a4a9f16a..523ffc7bc3a8 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -54,8 +54,6 @@ struct kretprobe_instance; typedef int (*kprobe_pre_handler_t) (struct kprobe *, struct pt_regs *); typedef void (*kprobe_post_handler_t) (struct kprobe *, struct pt_regs *, unsigned long flags); -typedef int (*kprobe_fault_handler_t) (struct kprobe *, struct pt_regs *, - int trapnr); typedef int (*kretprobe_handler_t) (struct kretprobe_instance *, struct pt_regs *); @@ -83,12 +81,6 @@ struct kprobe { /* Called after addr is executed, unless... */ kprobe_post_handler_t post_handler; - /* - * ... called if executing addr causes a fault (eg. page fault). - * Return 1 if it handled fault, otherwise kernel will see it. - */ - kprobe_fault_handler_t fault_handler; - /* Saved opcode (which has been replaced with breakpoint) */ kprobe_opcode_t opcode; -- cgit v1.2.3 From d8570c182f56ca52c98734732fb9a331f7c23f9a Mon Sep 17 00:00:00 2001 From: Hsin-Hsiung Wang Date: Wed, 26 May 2021 14:52:00 +0800 Subject: mfd: mt6358: Refine interrupt code This patch refines the interrupt related code to support new chips. Signed-off-by: Hsin-Hsiung Wang Signed-off-by: Lee Jones --- include/linux/mfd/mt6358/core.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/mt6358/core.h b/include/linux/mfd/mt6358/core.h index c5a11b7458d4..68578e2019b0 100644 --- a/include/linux/mfd/mt6358/core.h +++ b/include/linux/mfd/mt6358/core.h @@ -6,12 +6,9 @@ #ifndef __MFD_MT6358_CORE_H__ #define __MFD_MT6358_CORE_H__ -#define MT6358_REG_WIDTH 16 - struct irq_top_t { int hwirq_base; unsigned int num_int_regs; - unsigned int num_int_bits; unsigned int en_reg; unsigned int en_reg_shift; unsigned int sta_reg; @@ -25,6 +22,7 @@ struct pmic_irq_data { unsigned short top_int_status_reg; bool *enable_hwirq; bool *cache_hwirq; + const struct irq_top_t *pmic_ints; }; enum mt6358_irq_top_status_shift { @@ -146,8 +144,8 @@ enum mt6358_irq_numbers { { \ .hwirq_base = MT6358_IRQ_##sp##_BASE, \ .num_int_regs = \ - ((MT6358_IRQ_##sp##_BITS - 1) / MT6358_REG_WIDTH) + 1, \ - .num_int_bits = MT6358_IRQ_##sp##_BITS, \ + ((MT6358_IRQ_##sp##_BITS - 1) / \ + MTK_PMIC_REG_WIDTH) + 1, \ .en_reg = MT6358_##sp##_TOP_INT_CON0, \ .en_reg_shift = 0x6, \ .sta_reg = MT6358_##sp##_TOP_INT_STATUS0, \ -- cgit v1.2.3 From be60652f0260c2f371670ec90f1ac55e2671f793 Mon Sep 17 00:00:00 2001 From: Hsin-Hsiung Wang Date: Wed, 26 May 2021 14:52:01 +0800 Subject: rtc: mt6397: refine RTC_TC_MTH This patch adds RTC_TC_MTH_MASK to support new chips. Signed-off-by: Yuchen Huang Signed-off-by: Hsin-Hsiung Wang Acked-by: Alexandre Belloni Signed-off-by: Lee Jones --- include/linux/mfd/mt6397/rtc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/mt6397/rtc.h b/include/linux/mfd/mt6397/rtc.h index c3748b53bf7d..068ae1c0f0e8 100644 --- a/include/linux/mfd/mt6397/rtc.h +++ b/include/linux/mfd/mt6397/rtc.h @@ -36,6 +36,7 @@ #define RTC_AL_MASK_DOW BIT(4) #define RTC_TC_SEC 0x000a +#define RTC_TC_MTH_MASK 0x000f /* Min, Hour, Dom... register offset to RTC_TC_SEC */ #define RTC_OFFSET_SEC 0 #define RTC_OFFSET_MIN 1 -- cgit v1.2.3 From e545b8f380a96174df40db4203d09156e096ee89 Mon Sep 17 00:00:00 2001 From: Hsin-Hsiung Wang Date: Wed, 26 May 2021 14:52:04 +0800 Subject: mfd: Add support for the MediaTek MT6359 PMIC This adds support for the MediaTek MT6359 PMIC. This is a multifunction device with the following sub modules: - Codec - Interrupt - Regulator - RTC It is interfaced to the host controller using SPI interface by a proprietary hardware called PMIC wrapper or pwrap. MT6359 MFD is a child device of the pwrap. Signed-off-by: Hsin-Hsiung Wang Signed-off-by: Lee Jones --- include/linux/mfd/mt6359/core.h | 133 +++++++++ include/linux/mfd/mt6359/registers.h | 529 +++++++++++++++++++++++++++++++++++ include/linux/mfd/mt6397/core.h | 1 + 3 files changed, 663 insertions(+) create mode 100644 include/linux/mfd/mt6359/core.h create mode 100644 include/linux/mfd/mt6359/registers.h (limited to 'include/linux') diff --git a/include/linux/mfd/mt6359/core.h b/include/linux/mfd/mt6359/core.h new file mode 100644 index 000000000000..8d298868126d --- /dev/null +++ b/include/linux/mfd/mt6359/core.h @@ -0,0 +1,133 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2021 MediaTek Inc. + */ + +#ifndef __MFD_MT6359_CORE_H__ +#define __MFD_MT6359_CORE_H__ + +enum mt6359_irq_top_status_shift { + MT6359_BUCK_TOP = 0, + MT6359_LDO_TOP, + MT6359_PSC_TOP, + MT6359_SCK_TOP, + MT6359_BM_TOP, + MT6359_HK_TOP, + MT6359_AUD_TOP = 7, + MT6359_MISC_TOP, +}; + +enum mt6359_irq_numbers { + MT6359_IRQ_VCORE_OC = 1, + MT6359_IRQ_VGPU11_OC, + MT6359_IRQ_VGPU12_OC, + MT6359_IRQ_VMODEM_OC, + MT6359_IRQ_VPROC1_OC, + MT6359_IRQ_VPROC2_OC, + MT6359_IRQ_VS1_OC, + MT6359_IRQ_VS2_OC, + MT6359_IRQ_VPA_OC = 9, + MT6359_IRQ_VFE28_OC = 16, + MT6359_IRQ_VXO22_OC, + MT6359_IRQ_VRF18_OC, + MT6359_IRQ_VRF12_OC, + MT6359_IRQ_VEFUSE_OC, + MT6359_IRQ_VCN33_1_OC, + MT6359_IRQ_VCN33_2_OC, + MT6359_IRQ_VCN13_OC, + MT6359_IRQ_VCN18_OC, + MT6359_IRQ_VA09_OC, + MT6359_IRQ_VCAMIO_OC, + MT6359_IRQ_VA12_OC, + MT6359_IRQ_VAUX18_OC, + MT6359_IRQ_VAUD18_OC, + MT6359_IRQ_VIO18_OC, + MT6359_IRQ_VSRAM_PROC1_OC, + MT6359_IRQ_VSRAM_PROC2_OC, + MT6359_IRQ_VSRAM_OTHERS_OC, + MT6359_IRQ_VSRAM_MD_OC, + MT6359_IRQ_VEMC_OC, + MT6359_IRQ_VSIM1_OC, + MT6359_IRQ_VSIM2_OC, + MT6359_IRQ_VUSB_OC, + MT6359_IRQ_VRFCK_OC, + MT6359_IRQ_VBBCK_OC, + MT6359_IRQ_VBIF28_OC, + MT6359_IRQ_VIBR_OC, + MT6359_IRQ_VIO28_OC, + MT6359_IRQ_VM18_OC, + MT6359_IRQ_VUFS_OC = 45, + MT6359_IRQ_PWRKEY = 48, + MT6359_IRQ_HOMEKEY, + MT6359_IRQ_PWRKEY_R, + MT6359_IRQ_HOMEKEY_R, + MT6359_IRQ_NI_LBAT_INT, + MT6359_IRQ_CHRDET_EDGE = 53, + MT6359_IRQ_RTC = 64, + MT6359_IRQ_FG_BAT_H = 80, + MT6359_IRQ_FG_BAT_L, + MT6359_IRQ_FG_CUR_H, + MT6359_IRQ_FG_CUR_L, + MT6359_IRQ_FG_ZCV = 84, + MT6359_IRQ_FG_N_CHARGE_L = 87, + MT6359_IRQ_FG_IAVG_H, + MT6359_IRQ_FG_IAVG_L = 89, + MT6359_IRQ_FG_DISCHARGE = 91, + MT6359_IRQ_FG_CHARGE, + MT6359_IRQ_BATON_LV = 96, + MT6359_IRQ_BATON_BAT_IN = 98, + MT6359_IRQ_BATON_BAT_OU, + MT6359_IRQ_BIF = 100, + MT6359_IRQ_BAT_H = 112, + MT6359_IRQ_BAT_L, + MT6359_IRQ_BAT2_H, + MT6359_IRQ_BAT2_L, + MT6359_IRQ_BAT_TEMP_H, + MT6359_IRQ_BAT_TEMP_L, + MT6359_IRQ_THR_H, + MT6359_IRQ_THR_L, + MT6359_IRQ_AUXADC_IMP, + MT6359_IRQ_NAG_C_DLTV = 121, + MT6359_IRQ_AUDIO = 128, + MT6359_IRQ_ACCDET = 133, + MT6359_IRQ_ACCDET_EINT0, + MT6359_IRQ_ACCDET_EINT1, + MT6359_IRQ_SPI_CMD_ALERT = 144, + MT6359_IRQ_NR, +}; + +#define MT6359_IRQ_BUCK_BASE MT6359_IRQ_VCORE_OC +#define MT6359_IRQ_LDO_BASE MT6359_IRQ_VFE28_OC +#define MT6359_IRQ_PSC_BASE MT6359_IRQ_PWRKEY +#define MT6359_IRQ_SCK_BASE MT6359_IRQ_RTC +#define MT6359_IRQ_BM_BASE MT6359_IRQ_FG_BAT_H +#define MT6359_IRQ_HK_BASE MT6359_IRQ_BAT_H +#define MT6359_IRQ_AUD_BASE MT6359_IRQ_AUDIO +#define MT6359_IRQ_MISC_BASE MT6359_IRQ_SPI_CMD_ALERT + +#define MT6359_IRQ_BUCK_BITS (MT6359_IRQ_VPA_OC - MT6359_IRQ_BUCK_BASE + 1) +#define MT6359_IRQ_LDO_BITS (MT6359_IRQ_VUFS_OC - MT6359_IRQ_LDO_BASE + 1) +#define MT6359_IRQ_PSC_BITS \ + (MT6359_IRQ_CHRDET_EDGE - MT6359_IRQ_PSC_BASE + 1) +#define MT6359_IRQ_SCK_BITS (MT6359_IRQ_RTC - MT6359_IRQ_SCK_BASE + 1) +#define MT6359_IRQ_BM_BITS (MT6359_IRQ_BIF - MT6359_IRQ_BM_BASE + 1) +#define MT6359_IRQ_HK_BITS (MT6359_IRQ_NAG_C_DLTV - MT6359_IRQ_HK_BASE + 1) +#define MT6359_IRQ_AUD_BITS \ + (MT6359_IRQ_ACCDET_EINT1 - MT6359_IRQ_AUD_BASE + 1) +#define MT6359_IRQ_MISC_BITS \ + (MT6359_IRQ_SPI_CMD_ALERT - MT6359_IRQ_MISC_BASE + 1) + +#define MT6359_TOP_GEN(sp) \ +{ \ + .hwirq_base = MT6359_IRQ_##sp##_BASE, \ + .num_int_regs = \ + ((MT6359_IRQ_##sp##_BITS - 1) / \ + MTK_PMIC_REG_WIDTH) + 1, \ + .en_reg = MT6359_##sp##_TOP_INT_CON0, \ + .en_reg_shift = 0x6, \ + .sta_reg = MT6359_##sp##_TOP_INT_STATUS0, \ + .sta_reg_shift = 0x2, \ + .top_offset = MT6359_##sp##_TOP, \ +} + +#endif /* __MFD_MT6359_CORE_H__ */ diff --git a/include/linux/mfd/mt6359/registers.h b/include/linux/mfd/mt6359/registers.h new file mode 100644 index 000000000000..2135c9695918 --- /dev/null +++ b/include/linux/mfd/mt6359/registers.h @@ -0,0 +1,529 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2021 MediaTek Inc. + */ + +#ifndef __MFD_MT6359_REGISTERS_H__ +#define __MFD_MT6359_REGISTERS_H__ + +/* PMIC Registers */ +#define MT6359_SWCID 0xa +#define MT6359_MISC_TOP_INT_CON0 0x188 +#define MT6359_MISC_TOP_INT_STATUS0 0x194 +#define MT6359_TOP_INT_STATUS0 0x19e +#define MT6359_SCK_TOP_INT_CON0 0x528 +#define MT6359_SCK_TOP_INT_STATUS0 0x534 +#define MT6359_EOSC_CALI_CON0 0x53a +#define MT6359_EOSC_CALI_CON1 0x53c +#define MT6359_RTC_MIX_CON0 0x53e +#define MT6359_RTC_MIX_CON1 0x540 +#define MT6359_RTC_MIX_CON2 0x542 +#define MT6359_RTC_DSN_ID 0x580 +#define MT6359_RTC_DSN_REV0 0x582 +#define MT6359_RTC_DBI 0x584 +#define MT6359_RTC_DXI 0x586 +#define MT6359_RTC_BBPU 0x588 +#define MT6359_RTC_IRQ_STA 0x58a +#define MT6359_RTC_IRQ_EN 0x58c +#define MT6359_RTC_CII_EN 0x58e +#define MT6359_RTC_AL_MASK 0x590 +#define MT6359_RTC_TC_SEC 0x592 +#define MT6359_RTC_TC_MIN 0x594 +#define MT6359_RTC_TC_HOU 0x596 +#define MT6359_RTC_TC_DOM 0x598 +#define MT6359_RTC_TC_DOW 0x59a +#define MT6359_RTC_TC_MTH 0x59c +#define MT6359_RTC_TC_YEA 0x59e +#define MT6359_RTC_AL_SEC 0x5a0 +#define MT6359_RTC_AL_MIN 0x5a2 +#define MT6359_RTC_AL_HOU 0x5a4 +#define MT6359_RTC_AL_DOM 0x5a6 +#define MT6359_RTC_AL_DOW 0x5a8 +#define MT6359_RTC_AL_MTH 0x5aa +#define MT6359_RTC_AL_YEA 0x5ac +#define MT6359_RTC_OSC32CON 0x5ae +#define MT6359_RTC_POWERKEY1 0x5b0 +#define MT6359_RTC_POWERKEY2 0x5b2 +#define MT6359_RTC_PDN1 0x5b4 +#define MT6359_RTC_PDN2 0x5b6 +#define MT6359_RTC_SPAR0 0x5b8 +#define MT6359_RTC_SPAR1 0x5ba +#define MT6359_RTC_PROT 0x5bc +#define MT6359_RTC_DIFF 0x5be +#define MT6359_RTC_CALI 0x5c0 +#define MT6359_RTC_WRTGR 0x5c2 +#define MT6359_RTC_CON 0x5c4 +#define MT6359_RTC_SEC_CTRL 0x5c6 +#define MT6359_RTC_INT_CNT 0x5c8 +#define MT6359_RTC_SEC_DAT0 0x5ca +#define MT6359_RTC_SEC_DAT1 0x5cc +#define MT6359_RTC_SEC_DAT2 0x5ce +#define MT6359_RTC_SEC_DSN_ID 0x600 +#define MT6359_RTC_SEC_DSN_REV0 0x602 +#define MT6359_RTC_SEC_DBI 0x604 +#define MT6359_RTC_SEC_DXI 0x606 +#define MT6359_RTC_TC_SEC_SEC 0x608 +#define MT6359_RTC_TC_MIN_SEC 0x60a +#define MT6359_RTC_TC_HOU_SEC 0x60c +#define MT6359_RTC_TC_DOM_SEC 0x60e +#define MT6359_RTC_TC_DOW_SEC 0x610 +#define MT6359_RTC_TC_MTH_SEC 0x612 +#define MT6359_RTC_TC_YEA_SEC 0x614 +#define MT6359_RTC_SEC_CK_PDN 0x616 +#define MT6359_RTC_SEC_WRTGR 0x618 +#define MT6359_PSC_TOP_INT_CON0 0x910 +#define MT6359_PSC_TOP_INT_STATUS0 0x91c +#define MT6359_BM_TOP_INT_CON0 0xc32 +#define MT6359_BM_TOP_INT_CON1 0xc38 +#define MT6359_BM_TOP_INT_STATUS0 0xc4a +#define MT6359_BM_TOP_INT_STATUS1 0xc4c +#define MT6359_HK_TOP_INT_CON0 0xf92 +#define MT6359_HK_TOP_INT_STATUS0 0xf9e +#define MT6359_BUCK_TOP_INT_CON0 0x1418 +#define MT6359_BUCK_TOP_INT_STATUS0 0x1424 +#define MT6359_BUCK_VPU_CON0 0x1488 +#define MT6359_BUCK_VPU_DBG0 0x14a6 +#define MT6359_BUCK_VPU_DBG1 0x14a8 +#define MT6359_BUCK_VPU_ELR0 0x14ac +#define MT6359_BUCK_VCORE_CON0 0x1508 +#define MT6359_BUCK_VCORE_DBG0 0x1526 +#define MT6359_BUCK_VCORE_DBG1 0x1528 +#define MT6359_BUCK_VCORE_SSHUB_CON0 0x152a +#define MT6359_BUCK_VCORE_ELR0 0x1534 +#define MT6359_BUCK_VGPU11_CON0 0x1588 +#define MT6359_BUCK_VGPU11_DBG0 0x15a6 +#define MT6359_BUCK_VGPU11_DBG1 0x15a8 +#define MT6359_BUCK_VGPU11_ELR0 0x15ac +#define MT6359_BUCK_VMODEM_CON0 0x1688 +#define MT6359_BUCK_VMODEM_DBG0 0x16a6 +#define MT6359_BUCK_VMODEM_DBG1 0x16a8 +#define MT6359_BUCK_VMODEM_ELR0 0x16ae +#define MT6359_BUCK_VPROC1_CON0 0x1708 +#define MT6359_BUCK_VPROC1_DBG0 0x1726 +#define MT6359_BUCK_VPROC1_DBG1 0x1728 +#define MT6359_BUCK_VPROC1_ELR0 0x172e +#define MT6359_BUCK_VPROC2_CON0 0x1788 +#define MT6359_BUCK_VPROC2_DBG0 0x17a6 +#define MT6359_BUCK_VPROC2_DBG1 0x17a8 +#define MT6359_BUCK_VPROC2_ELR0 0x17b2 +#define MT6359_BUCK_VS1_CON0 0x1808 +#define MT6359_BUCK_VS1_DBG0 0x1826 +#define MT6359_BUCK_VS1_DBG1 0x1828 +#define MT6359_BUCK_VS1_ELR0 0x1834 +#define MT6359_BUCK_VS2_CON0 0x1888 +#define MT6359_BUCK_VS2_DBG0 0x18a6 +#define MT6359_BUCK_VS2_DBG1 0x18a8 +#define MT6359_BUCK_VS2_ELR0 0x18b4 +#define MT6359_BUCK_VPA_CON0 0x1908 +#define MT6359_BUCK_VPA_CON1 0x190e +#define MT6359_BUCK_VPA_CFG0 0x1910 +#define MT6359_BUCK_VPA_CFG1 0x1912 +#define MT6359_BUCK_VPA_DBG0 0x1914 +#define MT6359_BUCK_VPA_DBG1 0x1916 +#define MT6359_VGPUVCORE_ANA_CON2 0x198e +#define MT6359_VGPUVCORE_ANA_CON13 0x19a4 +#define MT6359_VPROC1_ANA_CON3 0x19b2 +#define MT6359_VPROC2_ANA_CON3 0x1a0e +#define MT6359_VMODEM_ANA_CON3 0x1a1a +#define MT6359_VPU_ANA_CON3 0x1a26 +#define MT6359_VS1_ANA_CON0 0x1a2c +#define MT6359_VS2_ANA_CON0 0x1a34 +#define MT6359_VPA_ANA_CON0 0x1a3c +#define MT6359_LDO_TOP_INT_CON0 0x1b14 +#define MT6359_LDO_TOP_INT_CON1 0x1b1a +#define MT6359_LDO_TOP_INT_STATUS0 0x1b28 +#define MT6359_LDO_TOP_INT_STATUS1 0x1b2a +#define MT6359_LDO_VSRAM_PROC1_ELR 0x1b40 +#define MT6359_LDO_VSRAM_PROC2_ELR 0x1b42 +#define MT6359_LDO_VSRAM_OTHERS_ELR 0x1b44 +#define MT6359_LDO_VSRAM_MD_ELR 0x1b46 +#define MT6359_LDO_VFE28_CON0 0x1b88 +#define MT6359_LDO_VFE28_MON 0x1b8a +#define MT6359_LDO_VXO22_CON0 0x1b98 +#define MT6359_LDO_VXO22_MON 0x1b9a +#define MT6359_LDO_VRF18_CON0 0x1ba8 +#define MT6359_LDO_VRF18_MON 0x1baa +#define MT6359_LDO_VRF12_CON0 0x1bb8 +#define MT6359_LDO_VRF12_MON 0x1bba +#define MT6359_LDO_VEFUSE_CON0 0x1bc8 +#define MT6359_LDO_VEFUSE_MON 0x1bca +#define MT6359_LDO_VCN33_1_CON0 0x1bd8 +#define MT6359_LDO_VCN33_1_MON 0x1bda +#define MT6359_LDO_VCN33_1_MULTI_SW 0x1be8 +#define MT6359_LDO_VCN33_2_CON0 0x1c08 +#define MT6359_LDO_VCN33_2_MON 0x1c0a +#define MT6359_LDO_VCN33_2_MULTI_SW 0x1c18 +#define MT6359_LDO_VCN13_CON0 0x1c1a +#define MT6359_LDO_VCN13_MON 0x1c1c +#define MT6359_LDO_VCN18_CON0 0x1c2a +#define MT6359_LDO_VCN18_MON 0x1c2c +#define MT6359_LDO_VA09_CON0 0x1c3a +#define MT6359_LDO_VA09_MON 0x1c3c +#define MT6359_LDO_VCAMIO_CON0 0x1c4a +#define MT6359_LDO_VCAMIO_MON 0x1c4c +#define MT6359_LDO_VA12_CON0 0x1c5a +#define MT6359_LDO_VA12_MON 0x1c5c +#define MT6359_LDO_VAUX18_CON0 0x1c88 +#define MT6359_LDO_VAUX18_MON 0x1c8a +#define MT6359_LDO_VAUD18_CON0 0x1c98 +#define MT6359_LDO_VAUD18_MON 0x1c9a +#define MT6359_LDO_VIO18_CON0 0x1ca8 +#define MT6359_LDO_VIO18_MON 0x1caa +#define MT6359_LDO_VEMC_CON0 0x1cb8 +#define MT6359_LDO_VEMC_MON 0x1cba +#define MT6359_LDO_VSIM1_CON0 0x1cc8 +#define MT6359_LDO_VSIM1_MON 0x1cca +#define MT6359_LDO_VSIM2_CON0 0x1cd8 +#define MT6359_LDO_VSIM2_MON 0x1cda +#define MT6359_LDO_VUSB_CON0 0x1d08 +#define MT6359_LDO_VUSB_MON 0x1d0a +#define MT6359_LDO_VUSB_MULTI_SW 0x1d18 +#define MT6359_LDO_VRFCK_CON0 0x1d1a +#define MT6359_LDO_VRFCK_MON 0x1d1c +#define MT6359_LDO_VBBCK_CON0 0x1d2a +#define MT6359_LDO_VBBCK_MON 0x1d2c +#define MT6359_LDO_VBIF28_CON0 0x1d3a +#define MT6359_LDO_VBIF28_MON 0x1d3c +#define MT6359_LDO_VIBR_CON0 0x1d4a +#define MT6359_LDO_VIBR_MON 0x1d4c +#define MT6359_LDO_VIO28_CON0 0x1d5a +#define MT6359_LDO_VIO28_MON 0x1d5c +#define MT6359_LDO_VM18_CON0 0x1d88 +#define MT6359_LDO_VM18_MON 0x1d8a +#define MT6359_LDO_VUFS_CON0 0x1d98 +#define MT6359_LDO_VUFS_MON 0x1d9a +#define MT6359_LDO_VSRAM_PROC1_CON0 0x1e88 +#define MT6359_LDO_VSRAM_PROC1_MON 0x1e8a +#define MT6359_LDO_VSRAM_PROC1_VOSEL1 0x1e8e +#define MT6359_LDO_VSRAM_PROC2_CON0 0x1ea6 +#define MT6359_LDO_VSRAM_PROC2_MON 0x1ea8 +#define MT6359_LDO_VSRAM_PROC2_VOSEL1 0x1eac +#define MT6359_LDO_VSRAM_OTHERS_CON0 0x1f08 +#define MT6359_LDO_VSRAM_OTHERS_MON 0x1f0a +#define MT6359_LDO_VSRAM_OTHERS_VOSEL1 0x1f0e +#define MT6359_LDO_VSRAM_OTHERS_SSHUB 0x1f26 +#define MT6359_LDO_VSRAM_MD_CON0 0x1f2c +#define MT6359_LDO_VSRAM_MD_MON 0x1f2e +#define MT6359_LDO_VSRAM_MD_VOSEL1 0x1f32 +#define MT6359_VFE28_ANA_CON0 0x1f88 +#define MT6359_VAUX18_ANA_CON0 0x1f8c +#define MT6359_VUSB_ANA_CON0 0x1f90 +#define MT6359_VBIF28_ANA_CON0 0x1f94 +#define MT6359_VCN33_1_ANA_CON0 0x1f98 +#define MT6359_VCN33_2_ANA_CON0 0x1f9c +#define MT6359_VEMC_ANA_CON0 0x1fa0 +#define MT6359_VSIM1_ANA_CON0 0x1fa4 +#define MT6359_VSIM2_ANA_CON0 0x1fa8 +#define MT6359_VIO28_ANA_CON0 0x1fac +#define MT6359_VIBR_ANA_CON0 0x1fb0 +#define MT6359_VRF18_ANA_CON0 0x2008 +#define MT6359_VEFUSE_ANA_CON0 0x200c +#define MT6359_VCN18_ANA_CON0 0x2010 +#define MT6359_VCAMIO_ANA_CON0 0x2014 +#define MT6359_VAUD18_ANA_CON0 0x2018 +#define MT6359_VIO18_ANA_CON0 0x201c +#define MT6359_VM18_ANA_CON0 0x2020 +#define MT6359_VUFS_ANA_CON0 0x2024 +#define MT6359_VRF12_ANA_CON0 0x202a +#define MT6359_VCN13_ANA_CON0 0x202e +#define MT6359_VA09_ANA_CON0 0x2032 +#define MT6359_VA12_ANA_CON0 0x2036 +#define MT6359_VXO22_ANA_CON0 0x2088 +#define MT6359_VRFCK_ANA_CON0 0x208c +#define MT6359_VBBCK_ANA_CON0 0x2094 +#define MT6359_AUD_TOP_INT_CON0 0x2328 +#define MT6359_AUD_TOP_INT_STATUS0 0x2334 + +#define MT6359_RG_BUCK_VPU_EN_ADDR MT6359_BUCK_VPU_CON0 +#define MT6359_RG_BUCK_VPU_LP_ADDR MT6359_BUCK_VPU_CON0 +#define MT6359_RG_BUCK_VPU_LP_SHIFT 1 +#define MT6359_DA_VPU_VOSEL_ADDR MT6359_BUCK_VPU_DBG0 +#define MT6359_DA_VPU_VOSEL_MASK 0x7F +#define MT6359_DA_VPU_VOSEL_SHIFT 0 +#define MT6359_DA_VPU_EN_ADDR MT6359_BUCK_VPU_DBG1 +#define MT6359_RG_BUCK_VPU_VOSEL_ADDR MT6359_BUCK_VPU_ELR0 +#define MT6359_RG_BUCK_VPU_VOSEL_MASK 0x7F +#define MT6359_RG_BUCK_VPU_VOSEL_SHIFT 0 +#define MT6359_RG_BUCK_VCORE_EN_ADDR MT6359_BUCK_VCORE_CON0 +#define MT6359_RG_BUCK_VCORE_LP_ADDR MT6359_BUCK_VCORE_CON0 +#define MT6359_RG_BUCK_VCORE_LP_SHIFT 1 +#define MT6359_DA_VCORE_VOSEL_ADDR MT6359_BUCK_VCORE_DBG0 +#define MT6359_DA_VCORE_VOSEL_MASK 0x7F +#define MT6359_DA_VCORE_VOSEL_SHIFT 0 +#define MT6359_DA_VCORE_EN_ADDR MT6359_BUCK_VCORE_DBG1 +#define MT6359_RG_BUCK_VCORE_SSHUB_EN_ADDR MT6359_BUCK_VCORE_SSHUB_CON0 +#define MT6359_RG_BUCK_VCORE_SSHUB_VOSEL_ADDR MT6359_BUCK_VCORE_SSHUB_CON0 +#define MT6359_RG_BUCK_VCORE_SSHUB_VOSEL_MASK 0x7F +#define MT6359_RG_BUCK_VCORE_SSHUB_VOSEL_SHIFT 4 +#define MT6359_RG_BUCK_VCORE_VOSEL_ADDR MT6359_BUCK_VCORE_ELR0 +#define MT6359_RG_BUCK_VCORE_VOSEL_MASK 0x7F +#define MT6359_RG_BUCK_VCORE_VOSEL_SHIFT 0 +#define MT6359_RG_BUCK_VGPU11_EN_ADDR MT6359_BUCK_VGPU11_CON0 +#define MT6359_RG_BUCK_VGPU11_LP_ADDR MT6359_BUCK_VGPU11_CON0 +#define MT6359_RG_BUCK_VGPU11_LP_SHIFT 1 +#define MT6359_DA_VGPU11_VOSEL_ADDR MT6359_BUCK_VGPU11_DBG0 +#define MT6359_DA_VGPU11_VOSEL_MASK 0x7F +#define MT6359_DA_VGPU11_VOSEL_SHIFT 0 +#define MT6359_DA_VGPU11_EN_ADDR MT6359_BUCK_VGPU11_DBG1 +#define MT6359_RG_BUCK_VGPU11_VOSEL_ADDR MT6359_BUCK_VGPU11_ELR0 +#define MT6359_RG_BUCK_VGPU11_VOSEL_MASK 0x7F +#define MT6359_RG_BUCK_VGPU11_VOSEL_SHIFT 0 +#define MT6359_RG_BUCK_VMODEM_EN_ADDR MT6359_BUCK_VMODEM_CON0 +#define MT6359_RG_BUCK_VMODEM_LP_ADDR MT6359_BUCK_VMODEM_CON0 +#define MT6359_RG_BUCK_VMODEM_LP_SHIFT 1 +#define MT6359_DA_VMODEM_VOSEL_ADDR MT6359_BUCK_VMODEM_DBG0 +#define MT6359_DA_VMODEM_VOSEL_MASK 0x7F +#define MT6359_DA_VMODEM_VOSEL_SHIFT 0 +#define MT6359_DA_VMODEM_EN_ADDR MT6359_BUCK_VMODEM_DBG1 +#define MT6359_RG_BUCK_VMODEM_VOSEL_ADDR MT6359_BUCK_VMODEM_ELR0 +#define MT6359_RG_BUCK_VMODEM_VOSEL_MASK 0x7F +#define MT6359_RG_BUCK_VMODEM_VOSEL_SHIFT 0 +#define MT6359_RG_BUCK_VPROC1_EN_ADDR MT6359_BUCK_VPROC1_CON0 +#define MT6359_RG_BUCK_VPROC1_LP_ADDR MT6359_BUCK_VPROC1_CON0 +#define MT6359_RG_BUCK_VPROC1_LP_SHIFT 1 +#define MT6359_DA_VPROC1_VOSEL_ADDR MT6359_BUCK_VPROC1_DBG0 +#define MT6359_DA_VPROC1_VOSEL_MASK 0x7F +#define MT6359_DA_VPROC1_VOSEL_SHIFT 0 +#define MT6359_DA_VPROC1_EN_ADDR MT6359_BUCK_VPROC1_DBG1 +#define MT6359_RG_BUCK_VPROC1_VOSEL_ADDR MT6359_BUCK_VPROC1_ELR0 +#define MT6359_RG_BUCK_VPROC1_VOSEL_MASK 0x7F +#define MT6359_RG_BUCK_VPROC1_VOSEL_SHIFT 0 +#define MT6359_RG_BUCK_VPROC2_EN_ADDR MT6359_BUCK_VPROC2_CON0 +#define MT6359_RG_BUCK_VPROC2_LP_ADDR MT6359_BUCK_VPROC2_CON0 +#define MT6359_RG_BUCK_VPROC2_LP_SHIFT 1 +#define MT6359_DA_VPROC2_VOSEL_ADDR MT6359_BUCK_VPROC2_DBG0 +#define MT6359_DA_VPROC2_VOSEL_MASK 0x7F +#define MT6359_DA_VPROC2_VOSEL_SHIFT 0 +#define MT6359_DA_VPROC2_EN_ADDR MT6359_BUCK_VPROC2_DBG1 +#define MT6359_RG_BUCK_VPROC2_VOSEL_ADDR MT6359_BUCK_VPROC2_ELR0 +#define MT6359_RG_BUCK_VPROC2_VOSEL_MASK 0x7F +#define MT6359_RG_BUCK_VPROC2_VOSEL_SHIFT 0 +#define MT6359_RG_BUCK_VS1_EN_ADDR MT6359_BUCK_VS1_CON0 +#define MT6359_RG_BUCK_VS1_LP_ADDR MT6359_BUCK_VS1_CON0 +#define MT6359_RG_BUCK_VS1_LP_SHIFT 1 +#define MT6359_DA_VS1_VOSEL_ADDR MT6359_BUCK_VS1_DBG0 +#define MT6359_DA_VS1_VOSEL_MASK 0x7F +#define MT6359_DA_VS1_VOSEL_SHIFT 0 +#define MT6359_DA_VS1_EN_ADDR MT6359_BUCK_VS1_DBG1 +#define MT6359_RG_BUCK_VS1_VOSEL_ADDR MT6359_BUCK_VS1_ELR0 +#define MT6359_RG_BUCK_VS1_VOSEL_MASK 0x7F +#define MT6359_RG_BUCK_VS1_VOSEL_SHIFT 0 +#define MT6359_RG_BUCK_VS2_EN_ADDR MT6359_BUCK_VS2_CON0 +#define MT6359_RG_BUCK_VS2_LP_ADDR MT6359_BUCK_VS2_CON0 +#define MT6359_RG_BUCK_VS2_LP_SHIFT 1 +#define MT6359_DA_VS2_VOSEL_ADDR MT6359_BUCK_VS2_DBG0 +#define MT6359_DA_VS2_VOSEL_MASK 0x7F +#define MT6359_DA_VS2_VOSEL_SHIFT 0 +#define MT6359_DA_VS2_EN_ADDR MT6359_BUCK_VS2_DBG1 +#define MT6359_RG_BUCK_VS2_VOSEL_ADDR MT6359_BUCK_VS2_ELR0 +#define MT6359_RG_BUCK_VS2_VOSEL_MASK 0x7F +#define MT6359_RG_BUCK_VS2_VOSEL_SHIFT 0 +#define MT6359_RG_BUCK_VPA_EN_ADDR MT6359_BUCK_VPA_CON0 +#define MT6359_RG_BUCK_VPA_LP_ADDR MT6359_BUCK_VPA_CON0 +#define MT6359_RG_BUCK_VPA_LP_SHIFT 1 +#define MT6359_RG_BUCK_VPA_VOSEL_ADDR MT6359_BUCK_VPA_CON1 +#define MT6359_RG_BUCK_VPA_VOSEL_MASK 0x3F +#define MT6359_RG_BUCK_VPA_VOSEL_SHIFT 0 +#define MT6359_DA_VPA_VOSEL_ADDR MT6359_BUCK_VPA_DBG0 +#define MT6359_DA_VPA_VOSEL_MASK 0x3F +#define MT6359_DA_VPA_VOSEL_SHIFT 0 +#define MT6359_DA_VPA_EN_ADDR MT6359_BUCK_VPA_DBG1 +#define MT6359_RG_VGPU11_FCCM_ADDR MT6359_VGPUVCORE_ANA_CON2 +#define MT6359_RG_VGPU11_FCCM_SHIFT 9 +#define MT6359_RG_VCORE_FCCM_ADDR MT6359_VGPUVCORE_ANA_CON13 +#define MT6359_RG_VCORE_FCCM_SHIFT 5 +#define MT6359_RG_VPROC1_FCCM_ADDR MT6359_VPROC1_ANA_CON3 +#define MT6359_RG_VPROC1_FCCM_SHIFT 1 +#define MT6359_RG_VPROC2_FCCM_ADDR MT6359_VPROC2_ANA_CON3 +#define MT6359_RG_VPROC2_FCCM_SHIFT 1 +#define MT6359_RG_VMODEM_FCCM_ADDR MT6359_VMODEM_ANA_CON3 +#define MT6359_RG_VMODEM_FCCM_SHIFT 1 +#define MT6359_RG_VPU_FCCM_ADDR MT6359_VPU_ANA_CON3 +#define MT6359_RG_VPU_FCCM_SHIFT 1 +#define MT6359_RG_VS1_FPWM_ADDR MT6359_VS1_ANA_CON0 +#define MT6359_RG_VS1_FPWM_SHIFT 3 +#define MT6359_RG_VS2_FPWM_ADDR MT6359_VS2_ANA_CON0 +#define MT6359_RG_VS2_FPWM_SHIFT 3 +#define MT6359_RG_VPA_MODESET_ADDR MT6359_VPA_ANA_CON0 +#define MT6359_RG_VPA_MODESET_SHIFT 1 +#define MT6359_RG_LDO_VSRAM_PROC1_VOSEL_ADDR MT6359_LDO_VSRAM_PROC1_ELR +#define MT6359_RG_LDO_VSRAM_PROC1_VOSEL_MASK 0x7F +#define MT6359_RG_LDO_VSRAM_PROC1_VOSEL_SHIFT 0 +#define MT6359_RG_LDO_VSRAM_PROC2_VOSEL_ADDR MT6359_LDO_VSRAM_PROC2_ELR +#define MT6359_RG_LDO_VSRAM_PROC2_VOSEL_MASK 0x7F +#define MT6359_RG_LDO_VSRAM_PROC2_VOSEL_SHIFT 0 +#define MT6359_RG_LDO_VSRAM_OTHERS_VOSEL_ADDR MT6359_LDO_VSRAM_OTHERS_ELR +#define MT6359_RG_LDO_VSRAM_OTHERS_VOSEL_MASK 0x7F +#define MT6359_RG_LDO_VSRAM_OTHERS_VOSEL_SHIFT 0 +#define MT6359_RG_LDO_VSRAM_MD_VOSEL_ADDR MT6359_LDO_VSRAM_MD_ELR +#define MT6359_RG_LDO_VSRAM_MD_VOSEL_MASK 0x7F +#define MT6359_RG_LDO_VSRAM_MD_VOSEL_SHIFT 0 +#define MT6359_RG_LDO_VFE28_EN_ADDR MT6359_LDO_VFE28_CON0 +#define MT6359_DA_VFE28_B_EN_ADDR MT6359_LDO_VFE28_MON +#define MT6359_RG_LDO_VXO22_EN_ADDR MT6359_LDO_VXO22_CON0 +#define MT6359_RG_LDO_VXO22_EN_SHIFT 0 +#define MT6359_DA_VXO22_B_EN_ADDR MT6359_LDO_VXO22_MON +#define MT6359_RG_LDO_VRF18_EN_ADDR MT6359_LDO_VRF18_CON0 +#define MT6359_RG_LDO_VRF18_EN_SHIFT 0 +#define MT6359_DA_VRF18_B_EN_ADDR MT6359_LDO_VRF18_MON +#define MT6359_RG_LDO_VRF12_EN_ADDR MT6359_LDO_VRF12_CON0 +#define MT6359_RG_LDO_VRF12_EN_SHIFT 0 +#define MT6359_DA_VRF12_B_EN_ADDR MT6359_LDO_VRF12_MON +#define MT6359_RG_LDO_VEFUSE_EN_ADDR MT6359_LDO_VEFUSE_CON0 +#define MT6359_RG_LDO_VEFUSE_EN_SHIFT 0 +#define MT6359_DA_VEFUSE_B_EN_ADDR MT6359_LDO_VEFUSE_MON +#define MT6359_RG_LDO_VCN33_1_EN_0_ADDR MT6359_LDO_VCN33_1_CON0 +#define MT6359_RG_LDO_VCN33_1_EN_0_MASK 0x1 +#define MT6359_RG_LDO_VCN33_1_EN_0_SHIFT 0 +#define MT6359_DA_VCN33_1_B_EN_ADDR MT6359_LDO_VCN33_1_MON +#define MT6359_RG_LDO_VCN33_1_EN_1_ADDR MT6359_LDO_VCN33_1_MULTI_SW +#define MT6359_RG_LDO_VCN33_1_EN_1_SHIFT 15 +#define MT6359_RG_LDO_VCN33_2_EN_0_ADDR MT6359_LDO_VCN33_2_CON0 +#define MT6359_RG_LDO_VCN33_2_EN_0_SHIFT 0 +#define MT6359_DA_VCN33_2_B_EN_ADDR MT6359_LDO_VCN33_2_MON +#define MT6359_RG_LDO_VCN33_2_EN_1_ADDR MT6359_LDO_VCN33_2_MULTI_SW +#define MT6359_RG_LDO_VCN33_2_EN_1_MASK 0x1 +#define MT6359_RG_LDO_VCN33_2_EN_1_SHIFT 15 +#define MT6359_RG_LDO_VCN13_EN_ADDR MT6359_LDO_VCN13_CON0 +#define MT6359_RG_LDO_VCN13_EN_SHIFT 0 +#define MT6359_DA_VCN13_B_EN_ADDR MT6359_LDO_VCN13_MON +#define MT6359_RG_LDO_VCN18_EN_ADDR MT6359_LDO_VCN18_CON0 +#define MT6359_DA_VCN18_B_EN_ADDR MT6359_LDO_VCN18_MON +#define MT6359_RG_LDO_VA09_EN_ADDR MT6359_LDO_VA09_CON0 +#define MT6359_RG_LDO_VA09_EN_SHIFT 0 +#define MT6359_DA_VA09_B_EN_ADDR MT6359_LDO_VA09_MON +#define MT6359_RG_LDO_VCAMIO_EN_ADDR MT6359_LDO_VCAMIO_CON0 +#define MT6359_RG_LDO_VCAMIO_EN_SHIFT 0 +#define MT6359_DA_VCAMIO_B_EN_ADDR MT6359_LDO_VCAMIO_MON +#define MT6359_RG_LDO_VA12_EN_ADDR MT6359_LDO_VA12_CON0 +#define MT6359_RG_LDO_VA12_EN_SHIFT 0 +#define MT6359_DA_VA12_B_EN_ADDR MT6359_LDO_VA12_MON +#define MT6359_RG_LDO_VAUX18_EN_ADDR MT6359_LDO_VAUX18_CON0 +#define MT6359_DA_VAUX18_B_EN_ADDR MT6359_LDO_VAUX18_MON +#define MT6359_RG_LDO_VAUD18_EN_ADDR MT6359_LDO_VAUD18_CON0 +#define MT6359_DA_VAUD18_B_EN_ADDR MT6359_LDO_VAUD18_MON +#define MT6359_RG_LDO_VIO18_EN_ADDR MT6359_LDO_VIO18_CON0 +#define MT6359_RG_LDO_VIO18_EN_SHIFT 0 +#define MT6359_DA_VIO18_B_EN_ADDR MT6359_LDO_VIO18_MON +#define MT6359_RG_LDO_VEMC_EN_ADDR MT6359_LDO_VEMC_CON0 +#define MT6359_RG_LDO_VEMC_EN_SHIFT 0 +#define MT6359_DA_VEMC_B_EN_ADDR MT6359_LDO_VEMC_MON +#define MT6359_RG_LDO_VSIM1_EN_ADDR MT6359_LDO_VSIM1_CON0 +#define MT6359_RG_LDO_VSIM1_EN_SHIFT 0 +#define MT6359_DA_VSIM1_B_EN_ADDR MT6359_LDO_VSIM1_MON +#define MT6359_RG_LDO_VSIM2_EN_ADDR MT6359_LDO_VSIM2_CON0 +#define MT6359_RG_LDO_VSIM2_EN_SHIFT 0 +#define MT6359_DA_VSIM2_B_EN_ADDR MT6359_LDO_VSIM2_MON +#define MT6359_RG_LDO_VUSB_EN_0_ADDR MT6359_LDO_VUSB_CON0 +#define MT6359_RG_LDO_VUSB_EN_0_MASK 0x1 +#define MT6359_RG_LDO_VUSB_EN_0_SHIFT 0 +#define MT6359_DA_VUSB_B_EN_ADDR MT6359_LDO_VUSB_MON +#define MT6359_RG_LDO_VUSB_EN_1_ADDR MT6359_LDO_VUSB_MULTI_SW +#define MT6359_RG_LDO_VUSB_EN_1_MASK 0x1 +#define MT6359_RG_LDO_VUSB_EN_1_SHIFT 15 +#define MT6359_RG_LDO_VRFCK_EN_ADDR MT6359_LDO_VRFCK_CON0 +#define MT6359_RG_LDO_VRFCK_EN_SHIFT 0 +#define MT6359_DA_VRFCK_B_EN_ADDR MT6359_LDO_VRFCK_MON +#define MT6359_RG_LDO_VBBCK_EN_ADDR MT6359_LDO_VBBCK_CON0 +#define MT6359_RG_LDO_VBBCK_EN_SHIFT 0 +#define MT6359_DA_VBBCK_B_EN_ADDR MT6359_LDO_VBBCK_MON +#define MT6359_RG_LDO_VBIF28_EN_ADDR MT6359_LDO_VBIF28_CON0 +#define MT6359_DA_VBIF28_B_EN_ADDR MT6359_LDO_VBIF28_MON +#define MT6359_RG_LDO_VIBR_EN_ADDR MT6359_LDO_VIBR_CON0 +#define MT6359_RG_LDO_VIBR_EN_SHIFT 0 +#define MT6359_DA_VIBR_B_EN_ADDR MT6359_LDO_VIBR_MON +#define MT6359_RG_LDO_VIO28_EN_ADDR MT6359_LDO_VIO28_CON0 +#define MT6359_RG_LDO_VIO28_EN_SHIFT 0 +#define MT6359_DA_VIO28_B_EN_ADDR MT6359_LDO_VIO28_MON +#define MT6359_RG_LDO_VM18_EN_ADDR MT6359_LDO_VM18_CON0 +#define MT6359_RG_LDO_VM18_EN_SHIFT 0 +#define MT6359_DA_VM18_B_EN_ADDR MT6359_LDO_VM18_MON +#define MT6359_RG_LDO_VUFS_EN_ADDR MT6359_LDO_VUFS_CON0 +#define MT6359_RG_LDO_VUFS_EN_SHIFT 0 +#define MT6359_DA_VUFS_B_EN_ADDR MT6359_LDO_VUFS_MON +#define MT6359_RG_LDO_VSRAM_PROC1_EN_ADDR MT6359_LDO_VSRAM_PROC1_CON0 +#define MT6359_DA_VSRAM_PROC1_B_EN_ADDR MT6359_LDO_VSRAM_PROC1_MON +#define MT6359_DA_VSRAM_PROC1_VOSEL_ADDR MT6359_LDO_VSRAM_PROC1_VOSEL1 +#define MT6359_DA_VSRAM_PROC1_VOSEL_MASK 0x7F +#define MT6359_DA_VSRAM_PROC1_VOSEL_SHIFT 8 +#define MT6359_RG_LDO_VSRAM_PROC2_EN_ADDR MT6359_LDO_VSRAM_PROC2_CON0 +#define MT6359_DA_VSRAM_PROC2_B_EN_ADDR MT6359_LDO_VSRAM_PROC2_MON +#define MT6359_DA_VSRAM_PROC2_VOSEL_ADDR MT6359_LDO_VSRAM_PROC2_VOSEL1 +#define MT6359_DA_VSRAM_PROC2_VOSEL_MASK 0x7F +#define MT6359_DA_VSRAM_PROC2_VOSEL_SHIFT 8 +#define MT6359_RG_LDO_VSRAM_OTHERS_EN_ADDR MT6359_LDO_VSRAM_OTHERS_CON0 +#define MT6359_DA_VSRAM_OTHERS_B_EN_ADDR MT6359_LDO_VSRAM_OTHERS_MON +#define MT6359_DA_VSRAM_OTHERS_VOSEL_ADDR MT6359_LDO_VSRAM_OTHERS_VOSEL1 +#define MT6359_DA_VSRAM_OTHERS_VOSEL_MASK 0x7F +#define MT6359_DA_VSRAM_OTHERS_VOSEL_SHIFT 8 +#define MT6359_RG_LDO_VSRAM_OTHERS_SSHUB_EN_ADDR MT6359_LDO_VSRAM_OTHERS_SSHUB +#define MT6359_RG_LDO_VSRAM_OTHERS_SSHUB_VOSEL_ADDR MT6359_LDO_VSRAM_OTHERS_SSHUB +#define MT6359_RG_LDO_VSRAM_OTHERS_SSHUB_VOSEL_MASK 0x7F +#define MT6359_RG_LDO_VSRAM_OTHERS_SSHUB_VOSEL_SHIFT 1 +#define MT6359_RG_LDO_VSRAM_MD_EN_ADDR MT6359_LDO_VSRAM_MD_CON0 +#define MT6359_DA_VSRAM_MD_B_EN_ADDR MT6359_LDO_VSRAM_MD_MON +#define MT6359_DA_VSRAM_MD_VOSEL_ADDR MT6359_LDO_VSRAM_MD_VOSEL1 +#define MT6359_DA_VSRAM_MD_VOSEL_MASK 0x7F +#define MT6359_DA_VSRAM_MD_VOSEL_SHIFT 8 +#define MT6359_RG_VCN33_1_VOSEL_ADDR MT6359_VCN33_1_ANA_CON0 +#define MT6359_RG_VCN33_1_VOSEL_MASK 0xF +#define MT6359_RG_VCN33_1_VOSEL_SHIFT 8 +#define MT6359_RG_VCN33_2_VOSEL_ADDR MT6359_VCN33_2_ANA_CON0 +#define MT6359_RG_VCN33_2_VOSEL_MASK 0xF +#define MT6359_RG_VCN33_2_VOSEL_SHIFT 8 +#define MT6359_RG_VEMC_VOSEL_ADDR MT6359_VEMC_ANA_CON0 +#define MT6359_RG_VEMC_VOSEL_MASK 0xF +#define MT6359_RG_VEMC_VOSEL_SHIFT 8 +#define MT6359_RG_VSIM1_VOSEL_ADDR MT6359_VSIM1_ANA_CON0 +#define MT6359_RG_VSIM1_VOSEL_MASK 0xF +#define MT6359_RG_VSIM1_VOSEL_SHIFT 8 +#define MT6359_RG_VSIM2_VOSEL_ADDR MT6359_VSIM2_ANA_CON0 +#define MT6359_RG_VSIM2_VOSEL_MASK 0xF +#define MT6359_RG_VSIM2_VOSEL_SHIFT 8 +#define MT6359_RG_VIO28_VOSEL_ADDR MT6359_VIO28_ANA_CON0 +#define MT6359_RG_VIO28_VOSEL_MASK 0xF +#define MT6359_RG_VIO28_VOSEL_SHIFT 8 +#define MT6359_RG_VIBR_VOSEL_ADDR MT6359_VIBR_ANA_CON0 +#define MT6359_RG_VIBR_VOSEL_MASK 0xF +#define MT6359_RG_VIBR_VOSEL_SHIFT 8 +#define MT6359_RG_VRF18_VOSEL_ADDR MT6359_VRF18_ANA_CON0 +#define MT6359_RG_VRF18_VOSEL_MASK 0xF +#define MT6359_RG_VRF18_VOSEL_SHIFT 8 +#define MT6359_RG_VEFUSE_VOSEL_ADDR MT6359_VEFUSE_ANA_CON0 +#define MT6359_RG_VEFUSE_VOSEL_MASK 0xF +#define MT6359_RG_VEFUSE_VOSEL_SHIFT 8 +#define MT6359_RG_VCAMIO_VOSEL_ADDR MT6359_VCAMIO_ANA_CON0 +#define MT6359_RG_VCAMIO_VOSEL_MASK 0xF +#define MT6359_RG_VCAMIO_VOSEL_SHIFT 8 +#define MT6359_RG_VIO18_VOSEL_ADDR MT6359_VIO18_ANA_CON0 +#define MT6359_RG_VIO18_VOSEL_MASK 0xF +#define MT6359_RG_VIO18_VOSEL_SHIFT 8 +#define MT6359_RG_VM18_VOSEL_ADDR MT6359_VM18_ANA_CON0 +#define MT6359_RG_VM18_VOSEL_MASK 0xF +#define MT6359_RG_VM18_VOSEL_SHIFT 8 +#define MT6359_RG_VUFS_VOSEL_ADDR MT6359_VUFS_ANA_CON0 +#define MT6359_RG_VUFS_VOSEL_MASK 0xF +#define MT6359_RG_VUFS_VOSEL_SHIFT 8 +#define MT6359_RG_VRF12_VOSEL_ADDR MT6359_VRF12_ANA_CON0 +#define MT6359_RG_VRF12_VOSEL_MASK 0xF +#define MT6359_RG_VRF12_VOSEL_SHIFT 8 +#define MT6359_RG_VCN13_VOSEL_ADDR MT6359_VCN13_ANA_CON0 +#define MT6359_RG_VCN13_VOSEL_MASK 0xF +#define MT6359_RG_VCN13_VOSEL_SHIFT 8 +#define MT6359_RG_VA09_VOSEL_ADDR MT6359_VA09_ANA_CON0 +#define MT6359_RG_VA09_VOSEL_MASK 0xF +#define MT6359_RG_VA09_VOSEL_SHIFT 8 +#define MT6359_RG_VA12_VOSEL_ADDR MT6359_VA12_ANA_CON0 +#define MT6359_RG_VA12_VOSEL_MASK 0xF +#define MT6359_RG_VA12_VOSEL_SHIFT 8 +#define MT6359_RG_VXO22_VOSEL_ADDR MT6359_VXO22_ANA_CON0 +#define MT6359_RG_VXO22_VOSEL_MASK 0xF +#define MT6359_RG_VXO22_VOSEL_SHIFT 8 +#define MT6359_RG_VRFCK_VOSEL_ADDR MT6359_VRFCK_ANA_CON0 +#define MT6359_RG_VRFCK_VOSEL_MASK 0xF +#define MT6359_RG_VRFCK_VOSEL_SHIFT 8 +#define MT6359_RG_VBBCK_VOSEL_ADDR MT6359_VBBCK_ANA_CON0 +#define MT6359_RG_VBBCK_VOSEL_MASK 0xF +#define MT6359_RG_VBBCK_VOSEL_SHIFT 8 + +#endif /* __MFD_MT6359_REGISTERS_H__ */ diff --git a/include/linux/mfd/mt6397/core.h b/include/linux/mfd/mt6397/core.h index 949268581b36..56f210eebc54 100644 --- a/include/linux/mfd/mt6397/core.h +++ b/include/linux/mfd/mt6397/core.h @@ -13,6 +13,7 @@ enum chip_id { MT6323_CHIP_ID = 0x23, MT6358_CHIP_ID = 0x58, + MT6359_CHIP_ID = 0x59, MT6391_CHIP_ID = 0x91, MT6397_CHIP_ID = 0x97, }; -- cgit v1.2.3 From d7a58decc7049e8ca9707b63fcc2556cde3d26c5 Mon Sep 17 00:00:00 2001 From: Wen Su Date: Wed, 26 May 2021 14:52:05 +0800 Subject: regulator: mt6359: Add support for MT6359 regulator The MT6359 is a regulator found on boards based on MediaTek MT6779 and probably other SoCs. It is a so called pmic and connects as a slave to SoC using SPI, wrapped inside the pmic-wrapper. Signed-off-by: Wen Su Signed-off-by: Hsin-Hsiung Wang Acked-by: Mark Brown Signed-off-by: Lee Jones --- include/linux/regulator/mt6359-regulator.h | 58 ++++++++++++++++++++++++++++++ 1 file changed, 58 insertions(+) create mode 100644 include/linux/regulator/mt6359-regulator.h (limited to 'include/linux') diff --git a/include/linux/regulator/mt6359-regulator.h b/include/linux/regulator/mt6359-regulator.h new file mode 100644 index 000000000000..14c4b715613e --- /dev/null +++ b/include/linux/regulator/mt6359-regulator.h @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2021 MediaTek Inc. + */ + +#ifndef __LINUX_REGULATOR_MT6359_H +#define __LINUX_REGULATOR_MT6359_H + +enum { + MT6359_ID_VS1 = 0, + MT6359_ID_VGPU11, + MT6359_ID_VMODEM, + MT6359_ID_VPU, + MT6359_ID_VCORE, + MT6359_ID_VS2, + MT6359_ID_VPA, + MT6359_ID_VPROC2, + MT6359_ID_VPROC1, + MT6359_ID_VCORE_SSHUB, + MT6359_ID_VAUD18 = 10, + MT6359_ID_VSIM1, + MT6359_ID_VIBR, + MT6359_ID_VRF12, + MT6359_ID_VUSB, + MT6359_ID_VSRAM_PROC2, + MT6359_ID_VIO18, + MT6359_ID_VCAMIO, + MT6359_ID_VCN18, + MT6359_ID_VFE28, + MT6359_ID_VCN13, + MT6359_ID_VCN33_1_BT, + MT6359_ID_VCN33_1_WIFI, + MT6359_ID_VAUX18, + MT6359_ID_VSRAM_OTHERS, + MT6359_ID_VEFUSE, + MT6359_ID_VXO22, + MT6359_ID_VRFCK, + MT6359_ID_VBIF28, + MT6359_ID_VIO28, + MT6359_ID_VEMC, + MT6359_ID_VCN33_2_BT, + MT6359_ID_VCN33_2_WIFI, + MT6359_ID_VA12, + MT6359_ID_VA09, + MT6359_ID_VRF18, + MT6359_ID_VSRAM_MD, + MT6359_ID_VUFS, + MT6359_ID_VM18, + MT6359_ID_VBBCK, + MT6359_ID_VSRAM_PROC1, + MT6359_ID_VSIM2, + MT6359_ID_VSRAM_OTHERS_SSHUB, + MT6359_ID_RG_MAX, +}; + +#define MT6359_MAX_REGULATOR MT6359_ID_RG_MAX + +#endif /* __LINUX_REGULATOR_MT6359_H */ -- cgit v1.2.3 From 4cfc965475124c4eed2b7b5d8b6fc5048a21ecfd Mon Sep 17 00:00:00 2001 From: Hsin-Hsiung Wang Date: Wed, 26 May 2021 14:52:06 +0800 Subject: regulator: mt6359: Add support for MT6359P regulator The MT6359P is a eco version for MT6359 regulator. We add support based on MT6359 regulator driver. Signed-off-by: Hsin-Hsiung Wang Acked-by: Mark Brown Signed-off-by: Lee Jones --- include/linux/mfd/mt6359p/registers.h | 249 +++++++++++++++++++++++++++++ include/linux/regulator/mt6359-regulator.h | 1 + 2 files changed, 250 insertions(+) create mode 100644 include/linux/mfd/mt6359p/registers.h (limited to 'include/linux') diff --git a/include/linux/mfd/mt6359p/registers.h b/include/linux/mfd/mt6359p/registers.h new file mode 100644 index 000000000000..3d97c1885171 --- /dev/null +++ b/include/linux/mfd/mt6359p/registers.h @@ -0,0 +1,249 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2021 MediaTek Inc. + */ + +#ifndef __MFD_MT6359P_REGISTERS_H__ +#define __MFD_MT6359P_REGISTERS_H__ + +#define MT6359P_CHIP_VER 0x5930 + +/* PMIC Registers */ +#define MT6359P_HWCID 0x8 +#define MT6359P_TOP_TRAP 0x50 +#define MT6359P_TOP_TMA_KEY 0x3a8 +#define MT6359P_BUCK_VCORE_ELR_NUM 0x152a +#define MT6359P_BUCK_VCORE_ELR0 0x152c +#define MT6359P_BUCK_VGPU11_SSHUB_CON0 0x15aa +#define MT6359P_BUCK_VGPU11_ELR0 0x15b4 +#define MT6359P_LDO_VSRAM_PROC1_ELR 0x1b44 +#define MT6359P_LDO_VSRAM_PROC2_ELR 0x1b46 +#define MT6359P_LDO_VSRAM_OTHERS_ELR 0x1b48 +#define MT6359P_LDO_VSRAM_MD_ELR 0x1b4a +#define MT6359P_LDO_VEMC_ELR_0 0x1b4c +#define MT6359P_LDO_VFE28_CON0 0x1b88 +#define MT6359P_LDO_VFE28_MON 0x1b8c +#define MT6359P_LDO_VXO22_CON0 0x1b9a +#define MT6359P_LDO_VXO22_MON 0x1b9e +#define MT6359P_LDO_VRF18_CON0 0x1bac +#define MT6359P_LDO_VRF18_MON 0x1bb0 +#define MT6359P_LDO_VRF12_CON0 0x1bbe +#define MT6359P_LDO_VRF12_MON 0x1bc2 +#define MT6359P_LDO_VEFUSE_CON0 0x1bd0 +#define MT6359P_LDO_VEFUSE_MON 0x1bd4 +#define MT6359P_LDO_VCN33_1_CON0 0x1be2 +#define MT6359P_LDO_VCN33_1_MON 0x1be6 +#define MT6359P_LDO_VCN33_1_MULTI_SW 0x1bf4 +#define MT6359P_LDO_VCN33_2_CON0 0x1c08 +#define MT6359P_LDO_VCN33_2_MON 0x1c0c +#define MT6359P_LDO_VCN33_2_MULTI_SW 0x1c1a +#define MT6359P_LDO_VCN13_CON0 0x1c1c +#define MT6359P_LDO_VCN13_MON 0x1c20 +#define MT6359P_LDO_VCN18_CON0 0x1c2e +#define MT6359P_LDO_VCN18_MON 0x1c32 +#define MT6359P_LDO_VA09_CON0 0x1c40 +#define MT6359P_LDO_VA09_MON 0x1c44 +#define MT6359P_LDO_VCAMIO_CON0 0x1c52 +#define MT6359P_LDO_VCAMIO_MON 0x1c56 +#define MT6359P_LDO_VA12_CON0 0x1c64 +#define MT6359P_LDO_VA12_MON 0x1c68 +#define MT6359P_LDO_VAUX18_CON0 0x1c88 +#define MT6359P_LDO_VAUX18_MON 0x1c8c +#define MT6359P_LDO_VAUD18_CON0 0x1c9a +#define MT6359P_LDO_VAUD18_MON 0x1c9e +#define MT6359P_LDO_VIO18_CON0 0x1cac +#define MT6359P_LDO_VIO18_MON 0x1cb0 +#define MT6359P_LDO_VEMC_CON0 0x1cbe +#define MT6359P_LDO_VEMC_MON 0x1cc2 +#define MT6359P_LDO_VSIM1_CON0 0x1cd0 +#define MT6359P_LDO_VSIM1_MON 0x1cd4 +#define MT6359P_LDO_VSIM2_CON0 0x1ce2 +#define MT6359P_LDO_VSIM2_MON 0x1ce6 +#define MT6359P_LDO_VUSB_CON0 0x1d08 +#define MT6359P_LDO_VUSB_MON 0x1d0c +#define MT6359P_LDO_VUSB_MULTI_SW 0x1d1a +#define MT6359P_LDO_VRFCK_CON0 0x1d1c +#define MT6359P_LDO_VRFCK_MON 0x1d20 +#define MT6359P_LDO_VBBCK_CON0 0x1d2e +#define MT6359P_LDO_VBBCK_MON 0x1d32 +#define MT6359P_LDO_VBIF28_CON0 0x1d40 +#define MT6359P_LDO_VBIF28_MON 0x1d44 +#define MT6359P_LDO_VIBR_CON0 0x1d52 +#define MT6359P_LDO_VIBR_MON 0x1d56 +#define MT6359P_LDO_VIO28_CON0 0x1d64 +#define MT6359P_LDO_VIO28_MON 0x1d68 +#define MT6359P_LDO_VM18_CON0 0x1d88 +#define MT6359P_LDO_VM18_MON 0x1d8c +#define MT6359P_LDO_VUFS_CON0 0x1d9a +#define MT6359P_LDO_VUFS_MON 0x1d9e +#define MT6359P_LDO_VSRAM_PROC1_CON0 0x1e88 +#define MT6359P_LDO_VSRAM_PROC1_MON 0x1e8c +#define MT6359P_LDO_VSRAM_PROC1_VOSEL1 0x1e90 +#define MT6359P_LDO_VSRAM_PROC2_CON0 0x1ea8 +#define MT6359P_LDO_VSRAM_PROC2_MON 0x1eac +#define MT6359P_LDO_VSRAM_PROC2_VOSEL1 0x1eb0 +#define MT6359P_LDO_VSRAM_OTHERS_CON0 0x1f08 +#define MT6359P_LDO_VSRAM_OTHERS_MON 0x1f0c +#define MT6359P_LDO_VSRAM_OTHERS_VOSEL1 0x1f10 +#define MT6359P_LDO_VSRAM_OTHERS_SSHUB 0x1f28 +#define MT6359P_LDO_VSRAM_MD_CON0 0x1f2e +#define MT6359P_LDO_VSRAM_MD_MON 0x1f32 +#define MT6359P_LDO_VSRAM_MD_VOSEL1 0x1f36 +#define MT6359P_VFE28_ANA_CON0 0x1f88 +#define MT6359P_VAUX18_ANA_CON0 0x1f8c +#define MT6359P_VUSB_ANA_CON0 0x1f90 +#define MT6359P_VBIF28_ANA_CON0 0x1f94 +#define MT6359P_VCN33_1_ANA_CON0 0x1f98 +#define MT6359P_VCN33_2_ANA_CON0 0x1f9c +#define MT6359P_VEMC_ANA_CON0 0x1fa0 +#define MT6359P_VSIM1_ANA_CON0 0x1fa2 +#define MT6359P_VSIM2_ANA_CON0 0x1fa6 +#define MT6359P_VIO28_ANA_CON0 0x1faa +#define MT6359P_VIBR_ANA_CON0 0x1fae +#define MT6359P_VFE28_ELR_4 0x1fc0 +#define MT6359P_VRF18_ANA_CON0 0x2008 +#define MT6359P_VEFUSE_ANA_CON0 0x200c +#define MT6359P_VCN18_ANA_CON0 0x2010 +#define MT6359P_VCAMIO_ANA_CON0 0x2014 +#define MT6359P_VAUD18_ANA_CON0 0x2018 +#define MT6359P_VIO18_ANA_CON0 0x201c +#define MT6359P_VM18_ANA_CON0 0x2020 +#define MT6359P_VUFS_ANA_CON0 0x2024 +#define MT6359P_VRF12_ANA_CON0 0x202a +#define MT6359P_VCN13_ANA_CON0 0x202e +#define MT6359P_VA09_ANA_CON0 0x2032 +#define MT6359P_VRF18_ELR_3 0x204e +#define MT6359P_VXO22_ANA_CON0 0x2088 +#define MT6359P_VRFCK_ANA_CON0 0x208c +#define MT6359P_VBBCK_ANA_CON0 0x2096 + +#define MT6359P_RG_BUCK_VCORE_VOSEL_ADDR MT6359P_BUCK_VCORE_ELR0 +#define MT6359P_RG_BUCK_VGPU11_SSHUB_EN_ADDR MT6359P_BUCK_VGPU11_SSHUB_CON0 +#define MT6359P_RG_BUCK_VGPU11_VOSEL_ADDR MT6359P_BUCK_VGPU11_ELR0 +#define MT6359P_RG_BUCK_VGPU11_SSHUB_VOSEL_ADDR MT6359P_BUCK_VGPU11_SSHUB_CON0 +#define MT6359P_RG_BUCK_VGPU11_SSHUB_VOSEL_MASK 0x7F +#define MT6359P_RG_BUCK_VGPU11_SSHUB_VOSEL_SHIFT 4 +#define MT6359P_RG_LDO_VSRAM_PROC1_VOSEL_ADDR MT6359P_LDO_VSRAM_PROC1_ELR +#define MT6359P_RG_LDO_VSRAM_PROC2_VOSEL_ADDR MT6359P_LDO_VSRAM_PROC2_ELR +#define MT6359P_RG_LDO_VSRAM_OTHERS_VOSEL_ADDR MT6359P_LDO_VSRAM_OTHERS_ELR +#define MT6359P_RG_LDO_VSRAM_MD_VOSEL_ADDR MT6359P_LDO_VSRAM_MD_ELR +#define MT6359P_RG_LDO_VEMC_VOSEL_0_ADDR MT6359P_LDO_VEMC_ELR_0 +#define MT6359P_RG_LDO_VEMC_VOSEL_0_MASK 0xF +#define MT6359P_RG_LDO_VEMC_VOSEL_0_SHIFT 0 +#define MT6359P_RG_LDO_VFE28_EN_ADDR MT6359P_LDO_VFE28_CON0 +#define MT6359P_DA_VFE28_B_EN_ADDR MT6359P_LDO_VFE28_MON +#define MT6359P_RG_LDO_VXO22_EN_ADDR MT6359P_LDO_VXO22_CON0 +#define MT6359P_RG_LDO_VXO22_EN_SHIFT 0 +#define MT6359P_DA_VXO22_B_EN_ADDR MT6359P_LDO_VXO22_MON +#define MT6359P_RG_LDO_VRF18_EN_ADDR MT6359P_LDO_VRF18_CON0 +#define MT6359P_RG_LDO_VRF18_EN_SHIFT 0 +#define MT6359P_DA_VRF18_B_EN_ADDR MT6359P_LDO_VRF18_MON +#define MT6359P_RG_LDO_VRF12_EN_ADDR MT6359P_LDO_VRF12_CON0 +#define MT6359P_RG_LDO_VRF12_EN_SHIFT 0 +#define MT6359P_DA_VRF12_B_EN_ADDR MT6359P_LDO_VRF12_MON +#define MT6359P_RG_LDO_VEFUSE_EN_ADDR MT6359P_LDO_VEFUSE_CON0 +#define MT6359P_RG_LDO_VEFUSE_EN_SHIFT 0 +#define MT6359P_DA_VEFUSE_B_EN_ADDR MT6359P_LDO_VEFUSE_MON +#define MT6359P_RG_LDO_VCN33_1_EN_0_ADDR MT6359P_LDO_VCN33_1_CON0 +#define MT6359P_DA_VCN33_1_B_EN_ADDR MT6359P_LDO_VCN33_1_MON +#define MT6359P_RG_LDO_VCN33_1_EN_1_ADDR MT6359P_LDO_VCN33_1_MULTI_SW +#define MT6359P_RG_LDO_VCN33_1_EN_1_SHIFT 15 +#define MT6359P_RG_LDO_VCN33_2_EN_0_ADDR MT6359P_LDO_VCN33_2_CON0 +#define MT6359P_RG_LDO_VCN33_2_EN_0_SHIFT 0 +#define MT6359P_DA_VCN33_2_B_EN_ADDR MT6359P_LDO_VCN33_2_MON +#define MT6359P_RG_LDO_VCN33_2_EN_1_ADDR MT6359P_LDO_VCN33_2_MULTI_SW +#define MT6359P_RG_LDO_VCN13_EN_ADDR MT6359P_LDO_VCN13_CON0 +#define MT6359P_RG_LDO_VCN13_EN_SHIFT 0 +#define MT6359P_DA_VCN13_B_EN_ADDR MT6359P_LDO_VCN13_MON +#define MT6359P_RG_LDO_VCN18_EN_ADDR MT6359P_LDO_VCN18_CON0 +#define MT6359P_DA_VCN18_B_EN_ADDR MT6359P_LDO_VCN18_MON +#define MT6359P_RG_LDO_VA09_EN_ADDR MT6359P_LDO_VA09_CON0 +#define MT6359P_RG_LDO_VA09_EN_SHIFT 0 +#define MT6359P_DA_VA09_B_EN_ADDR MT6359P_LDO_VA09_MON +#define MT6359P_RG_LDO_VCAMIO_EN_ADDR MT6359P_LDO_VCAMIO_CON0 +#define MT6359P_RG_LDO_VCAMIO_EN_SHIFT 0 +#define MT6359P_DA_VCAMIO_B_EN_ADDR MT6359P_LDO_VCAMIO_MON +#define MT6359P_RG_LDO_VA12_EN_ADDR MT6359P_LDO_VA12_CON0 +#define MT6359P_RG_LDO_VA12_EN_SHIFT 0 +#define MT6359P_DA_VA12_B_EN_ADDR MT6359P_LDO_VA12_MON +#define MT6359P_RG_LDO_VAUX18_EN_ADDR MT6359P_LDO_VAUX18_CON0 +#define MT6359P_DA_VAUX18_B_EN_ADDR MT6359P_LDO_VAUX18_MON +#define MT6359P_RG_LDO_VAUD18_EN_ADDR MT6359P_LDO_VAUD18_CON0 +#define MT6359P_DA_VAUD18_B_EN_ADDR MT6359P_LDO_VAUD18_MON +#define MT6359P_RG_LDO_VIO18_EN_ADDR MT6359P_LDO_VIO18_CON0 +#define MT6359P_RG_LDO_VIO18_EN_SHIFT 0 +#define MT6359P_DA_VIO18_B_EN_ADDR MT6359P_LDO_VIO18_MON +#define MT6359P_RG_LDO_VEMC_EN_ADDR MT6359P_LDO_VEMC_CON0 +#define MT6359P_RG_LDO_VEMC_EN_SHIFT 0 +#define MT6359P_DA_VEMC_B_EN_ADDR MT6359P_LDO_VEMC_MON +#define MT6359P_RG_LDO_VSIM1_EN_ADDR MT6359P_LDO_VSIM1_CON0 +#define MT6359P_RG_LDO_VSIM1_EN_SHIFT 0 +#define MT6359P_DA_VSIM1_B_EN_ADDR MT6359P_LDO_VSIM1_MON +#define MT6359P_RG_LDO_VSIM2_EN_ADDR MT6359P_LDO_VSIM2_CON0 +#define MT6359P_RG_LDO_VSIM2_EN_SHIFT 0 +#define MT6359P_DA_VSIM2_B_EN_ADDR MT6359P_LDO_VSIM2_MON +#define MT6359P_RG_LDO_VUSB_EN_0_ADDR MT6359P_LDO_VUSB_CON0 +#define MT6359P_DA_VUSB_B_EN_ADDR MT6359P_LDO_VUSB_MON +#define MT6359P_RG_LDO_VUSB_EN_1_ADDR MT6359P_LDO_VUSB_MULTI_SW +#define MT6359P_RG_LDO_VRFCK_EN_ADDR MT6359P_LDO_VRFCK_CON0 +#define MT6359P_RG_LDO_VRFCK_EN_SHIFT 0 +#define MT6359P_DA_VRFCK_B_EN_ADDR MT6359P_LDO_VRFCK_MON +#define MT6359P_RG_LDO_VBBCK_EN_ADDR MT6359P_LDO_VBBCK_CON0 +#define MT6359P_RG_LDO_VBBCK_EN_SHIFT 0 +#define MT6359P_DA_VBBCK_B_EN_ADDR MT6359P_LDO_VBBCK_MON +#define MT6359P_RG_LDO_VBIF28_EN_ADDR MT6359P_LDO_VBIF28_CON0 +#define MT6359P_DA_VBIF28_B_EN_ADDR MT6359P_LDO_VBIF28_MON +#define MT6359P_RG_LDO_VIBR_EN_ADDR MT6359P_LDO_VIBR_CON0 +#define MT6359P_RG_LDO_VIBR_EN_SHIFT 0 +#define MT6359P_DA_VIBR_B_EN_ADDR MT6359P_LDO_VIBR_MON +#define MT6359P_RG_LDO_VIO28_EN_ADDR MT6359P_LDO_VIO28_CON0 +#define MT6359P_RG_LDO_VIO28_EN_SHIFT 0 +#define MT6359P_DA_VIO28_B_EN_ADDR MT6359P_LDO_VIO28_MON +#define MT6359P_RG_LDO_VM18_EN_ADDR MT6359P_LDO_VM18_CON0 +#define MT6359P_RG_LDO_VM18_EN_SHIFT 0 +#define MT6359P_DA_VM18_B_EN_ADDR MT6359P_LDO_VM18_MON +#define MT6359P_RG_LDO_VUFS_EN_ADDR MT6359P_LDO_VUFS_CON0 +#define MT6359P_RG_LDO_VUFS_EN_SHIFT 0 +#define MT6359P_DA_VUFS_B_EN_ADDR MT6359P_LDO_VUFS_MON +#define MT6359P_RG_LDO_VSRAM_PROC1_EN_ADDR MT6359P_LDO_VSRAM_PROC1_CON0 +#define MT6359P_DA_VSRAM_PROC1_B_EN_ADDR MT6359P_LDO_VSRAM_PROC1_MON +#define MT6359P_DA_VSRAM_PROC1_VOSEL_ADDR MT6359P_LDO_VSRAM_PROC1_VOSEL1 +#define MT6359P_RG_LDO_VSRAM_PROC2_EN_ADDR MT6359P_LDO_VSRAM_PROC2_CON0 +#define MT6359P_DA_VSRAM_PROC2_B_EN_ADDR MT6359P_LDO_VSRAM_PROC2_MON +#define MT6359P_DA_VSRAM_PROC2_VOSEL_ADDR MT6359P_LDO_VSRAM_PROC2_VOSEL1 +#define MT6359P_RG_LDO_VSRAM_OTHERS_EN_ADDR MT6359P_LDO_VSRAM_OTHERS_CON0 +#define MT6359P_DA_VSRAM_OTHERS_B_EN_ADDR MT6359P_LDO_VSRAM_OTHERS_MON +#define MT6359P_DA_VSRAM_OTHERS_VOSEL_ADDR MT6359P_LDO_VSRAM_OTHERS_VOSEL1 +#define MT6359P_RG_LDO_VSRAM_OTHERS_SSHUB_EN_ADDR MT6359P_LDO_VSRAM_OTHERS_SSHUB +#define MT6359P_RG_LDO_VSRAM_OTHERS_SSHUB_VOSEL_ADDR MT6359P_LDO_VSRAM_OTHERS_SSHUB +#define MT6359P_RG_LDO_VSRAM_MD_EN_ADDR MT6359P_LDO_VSRAM_MD_CON0 +#define MT6359P_DA_VSRAM_MD_B_EN_ADDR MT6359P_LDO_VSRAM_MD_MON +#define MT6359P_DA_VSRAM_MD_VOSEL_ADDR MT6359P_LDO_VSRAM_MD_VOSEL1 +#define MT6359P_RG_VCN33_1_VOSEL_ADDR MT6359P_VCN33_1_ANA_CON0 +#define MT6359P_RG_VCN33_2_VOSEL_ADDR MT6359P_VCN33_2_ANA_CON0 +#define MT6359P_RG_VEMC_VOSEL_ADDR MT6359P_VEMC_ANA_CON0 +#define MT6359P_RG_VSIM1_VOSEL_ADDR MT6359P_VSIM1_ANA_CON0 +#define MT6359P_RG_VSIM2_VOSEL_ADDR MT6359P_VSIM2_ANA_CON0 +#define MT6359P_RG_VIO28_VOSEL_ADDR MT6359P_VIO28_ANA_CON0 +#define MT6359P_RG_VIBR_VOSEL_ADDR MT6359P_VIBR_ANA_CON0 +#define MT6359P_RG_VRF18_VOSEL_ADDR MT6359P_VRF18_ANA_CON0 +#define MT6359P_RG_VEFUSE_VOSEL_ADDR MT6359P_VEFUSE_ANA_CON0 +#define MT6359P_RG_VCAMIO_VOSEL_ADDR MT6359P_VCAMIO_ANA_CON0 +#define MT6359P_RG_VIO18_VOSEL_ADDR MT6359P_VIO18_ANA_CON0 +#define MT6359P_RG_VM18_VOSEL_ADDR MT6359P_VM18_ANA_CON0 +#define MT6359P_RG_VUFS_VOSEL_ADDR MT6359P_VUFS_ANA_CON0 +#define MT6359P_RG_VRF12_VOSEL_ADDR MT6359P_VRF12_ANA_CON0 +#define MT6359P_RG_VCN13_VOSEL_ADDR MT6359P_VCN13_ANA_CON0 +#define MT6359P_RG_VA09_VOSEL_ADDR MT6359P_VRF18_ELR_3 +#define MT6359P_RG_VA12_VOSEL_ADDR MT6359P_VFE28_ELR_4 +#define MT6359P_RG_VXO22_VOSEL_ADDR MT6359P_VXO22_ANA_CON0 +#define MT6359P_RG_VRFCK_VOSEL_ADDR MT6359P_VRFCK_ANA_CON0 +#define MT6359P_RG_VBBCK_VOSEL_ADDR MT6359P_VBBCK_ANA_CON0 +#define MT6359P_RG_VBBCK_VOSEL_MASK 0xF +#define MT6359P_RG_VBBCK_VOSEL_SHIFT 4 +#define MT6359P_VM_MODE_ADDR MT6359P_TOP_TRAP +#define MT6359P_TMA_KEY_ADDR MT6359P_TOP_TMA_KEY + +#define TMA_KEY 0x9CA6 + +#endif /* __MFD_MT6359P_REGISTERS_H__ */ diff --git a/include/linux/regulator/mt6359-regulator.h b/include/linux/regulator/mt6359-regulator.h index 14c4b715613e..6d6e5a58f482 100644 --- a/include/linux/regulator/mt6359-regulator.h +++ b/include/linux/regulator/mt6359-regulator.h @@ -17,6 +17,7 @@ enum { MT6359_ID_VPROC2, MT6359_ID_VPROC1, MT6359_ID_VCORE_SSHUB, + MT6359_ID_VGPU11_SSHUB = MT6359_ID_VCORE_SSHUB, MT6359_ID_VAUD18 = 10, MT6359_ID_VSIM1, MT6359_ID_VIBR, -- cgit v1.2.3 From 8c7a703ec9787a1b45b024e9acd253328422dcbd Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Fri, 28 May 2021 09:38:09 +0200 Subject: evm: Verify portable signatures against all protected xattrs Currently, the evm_config_default_xattrnames array contains xattr names only related to LSMs which are enabled in the kernel configuration. However, EVM portable signatures do not depend on local information and a vendor might include in the signature calculation xattrs that are not enabled in the target platform. Just including all xattrs names in evm_config_default_xattrnames is not a safe approach, because a target system might have already calculated signatures or HMACs based only on the enabled xattrs. After applying this patch, EVM would verify those signatures and HMACs with all xattrs instead. The non-enabled ones, which could possibly exist, would cause a verification error. Thus, this patch adds a new field named enabled to the xattr_list structure, which is set to true if the LSM associated to a given xattr name is enabled in the kernel configuration. The non-enabled xattrs are taken into account only in evm_calc_hmac_or_hash(), if the passed security.evm type is EVM_XATTR_PORTABLE_DIGSIG. The new function evm_protected_xattr_if_enabled() has been defined so that IMA can include all protected xattrs and not only the enabled ones in the measurement list, if the new template fields xattrnames, xattrlengths or xattrvalues have been included in the template format. Signed-off-by: Roberto Sassu Signed-off-by: Mimi Zohar --- include/linux/evm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/evm.h b/include/linux/evm.h index 31ef1dbbb3ac..5011a299c251 100644 --- a/include/linux/evm.h +++ b/include/linux/evm.h @@ -38,6 +38,7 @@ extern int evm_inode_init_security(struct inode *inode, const struct xattr *xattr_array, struct xattr *evm); extern bool evm_revalidate_status(const char *xattr_name); +extern int evm_protected_xattr_if_enabled(const char *req_xattr_name); #ifdef CONFIG_FS_POSIX_ACL extern int posix_xattr_acl(const char *xattrname); #else @@ -114,5 +115,10 @@ static inline bool evm_revalidate_status(const char *xattr_name) return false; } +static inline int evm_protected_xattr_if_enabled(const char *req_xattr_name) +{ + return false; +} + #endif /* CONFIG_EVM */ #endif /* LINUX_EVM_H */ -- cgit v1.2.3 From 5ac712dcdfefb1a783384db85e0507d161e87812 Mon Sep 17 00:00:00 2001 From: Wong Vee Khee Date: Tue, 1 Jun 2021 21:52:35 +0800 Subject: net: stmmac: enable platform specific safety features On Intel platforms, not all safety features are enabled on the hardware. The current implementation enable all safety features by default. This will cause mass error and warning printouts after the module is loaded. Introduce platform specific safety features flag to enable or disable each safety features. Signed-off-by: Wong Vee Khee Signed-off-by: David S. Miller --- include/linux/stmmac.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index e14a12df381b..e55a4807e3ea 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -172,6 +172,18 @@ struct stmmac_fpe_cfg { enum stmmac_fpe_state lo_fpe_state; /* Local station FPE state */ }; +struct stmmac_safety_feature_cfg { + u32 tsoee; + u32 mrxpee; + u32 mestee; + u32 mrxee; + u32 mtxee; + u32 epsi; + u32 edpp; + u32 prtyen; + u32 tmouten; +}; + struct plat_stmmacenet_data { int bus_id; int phy_addr; @@ -184,6 +196,7 @@ struct plat_stmmacenet_data { struct stmmac_dma_cfg *dma_cfg; struct stmmac_est *est; struct stmmac_fpe_cfg *fpe_cfg; + struct stmmac_safety_feature_cfg *safety_feat_cfg; int clk_csr; int has_gmac; int enh_desc; -- cgit v1.2.3 From e1d9a90a9bfdb0735062d3adb16b07314b4b7b01 Mon Sep 17 00:00:00 2001 From: Sharath Chandra Vurukala Date: Wed, 2 Jun 2021 00:58:35 +0530 Subject: net: ethernet: rmnet: Support for ingress MAPv5 checksum offload Adding support for processing of MAPv5 downlink packets. It involves parsing the Mapv5 packet and checking the csum header to know whether the hardware has validated the checksum and is valid or not. Based on the checksum valid bit the corresponding stats are incremented and skb->ip_summed is marked either CHECKSUM_UNNECESSARY or left as CHEKSUM_NONE to let network stack revalidate the checksum and update the respective snmp stats. Current MAPV1 header has been modified, the reserved field in the Mapv1 header is now used for next header indication. Signed-off-by: Sharath Chandra Vurukala Signed-off-by: David S. Miller --- include/linux/if_rmnet.h | 30 +++++++++++++++++++++++++++--- 1 file changed, 27 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_rmnet.h b/include/linux/if_rmnet.h index 4efb537f57f3..be17610a981e 100644 --- a/include/linux/if_rmnet.h +++ b/include/linux/if_rmnet.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only - * Copyright (c) 2013-2019, The Linux Foundation. All rights reserved. + * Copyright (c) 2013-2019, 2021 The Linux Foundation. All rights reserved. */ #ifndef _LINUX_IF_RMNET_H_ @@ -12,10 +12,12 @@ struct rmnet_map_header { } __aligned(1); /* rmnet_map_header flags field: - * PAD_LEN: number of pad bytes following packet data - * CMD: 1 = packet contains a MAP command; 0 = packet contains data + * PAD_LEN: number of pad bytes following packet data + * CMD: 1 = packet contains a MAP command; 0 = packet contains data + * NEXT_HEADER: 1 = packet contains V5 CSUM header 0 = no V5 CSUM header */ #define MAP_PAD_LEN_MASK GENMASK(5, 0) +#define MAP_NEXT_HEADER_FLAG BIT(6) #define MAP_CMD_FLAG BIT(7) struct rmnet_map_dl_csum_trailer { @@ -45,4 +47,26 @@ struct rmnet_map_ul_csum_header { #define MAP_CSUM_UL_UDP_FLAG BIT(14) #define MAP_CSUM_UL_ENABLED_FLAG BIT(15) +/* MAP CSUM headers */ +struct rmnet_map_v5_csum_header { + u8 header_info; + u8 csum_info; + __be16 reserved; +} __aligned(1); + +/* v5 header_info field + * NEXT_HEADER: represents whether there is any next header + * HEADER_TYPE: represents the type of this header + * + * csum_info field + * CSUM_VALID_OR_REQ: + * 1 = for UL, checksum computation is requested. + * 1 = for DL, validated the checksum and has found it valid + */ + +#define MAPV5_HDRINFO_NXT_HDR_FLAG BIT(0) +#define MAPV5_HDRINFO_HDR_TYPE_FMASK GENMASK(7, 1) +#define MAPV5_CSUMINFO_VALID_FLAG BIT(7) + +#define RMNET_MAP_HEADER_TYPE_CSUM_OFFLOAD 2 #endif /* !(_LINUX_IF_RMNET_H_) */ -- cgit v1.2.3 From 9a2601ebc2e909ec2260ca224d886936f56d41e7 Mon Sep 17 00:00:00 2001 From: Mattijs Korpershoek Date: Thu, 6 May 2021 11:41:13 +0200 Subject: mfd: mt6397: Add MT6358 register definitions for power key To support power/home key detection, add definitions for two more MT6358 PMIC registers: - TOPSTATUS: homekey and powerkey debounce status - TOP_RST_MISC: controls homekey,powerkey long press reset time Signed-off-by: Mattijs Korpershoek Signed-off-by: Lee Jones --- include/linux/mfd/mt6358/registers.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/mt6358/registers.h b/include/linux/mfd/mt6358/registers.h index 2ad0b312aa28..201139b12140 100644 --- a/include/linux/mfd/mt6358/registers.h +++ b/include/linux/mfd/mt6358/registers.h @@ -8,6 +8,8 @@ /* PMIC Registers */ #define MT6358_SWCID 0xa +#define MT6358_TOPSTATUS 0x28 +#define MT6358_TOP_RST_MISC 0x14c #define MT6358_MISC_TOP_INT_CON0 0x188 #define MT6358_MISC_TOP_INT_STATUS0 0x194 #define MT6358_TOP_INT_STATUS0 0x19e -- cgit v1.2.3 From 50e4d7a2a667353321d4315fcc025e76c4fa2a89 Mon Sep 17 00:00:00 2001 From: Luca Ceresoli Date: Fri, 26 Feb 2021 15:28:52 +0100 Subject: mfd: lp87565: Handle optional reset pin Optionally handle the NRST pin (active low reset) in order to start from a known state during boot and to shut down the chip when rebooting. Signed-off-by: Luca Ceresoli Signed-off-by: Lee Jones --- include/linux/mfd/lp87565.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/lp87565.h b/include/linux/mfd/lp87565.h index 94cb581af34b..4c895072d91b 100644 --- a/include/linux/mfd/lp87565.h +++ b/include/linux/mfd/lp87565.h @@ -252,5 +252,6 @@ struct lp87565 { u8 rev; u8 dev_type; struct regmap *regmap; + struct gpio_desc *reset_gpio; }; #endif /* __LINUX_MFD_LP87565_H */ -- cgit v1.2.3 From 50e89312e39dff9e779e267fc191249a27294f39 Mon Sep 17 00:00:00 2001 From: Gene Chen Date: Tue, 18 May 2021 01:33:06 +0800 Subject: mfd: mt6360: Remove redundant brackets around raw numbers Remove redundant brackets around raw numbers. Signed-off-by: Gene Chen Signed-off-by: Lee Jones --- include/linux/mfd/mt6360.h | 410 ++++++++++++++++++++++----------------------- 1 file changed, 205 insertions(+), 205 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/mt6360.h b/include/linux/mfd/mt6360.h index ea1304035d4d..72edf1352229 100644 --- a/include/linux/mfd/mt6360.h +++ b/include/linux/mfd/mt6360.h @@ -16,10 +16,10 @@ enum { MT6360_SLAVE_MAX, }; -#define MT6360_PMU_SLAVEID (0x34) -#define MT6360_PMIC_SLAVEID (0x1A) -#define MT6360_LDO_SLAVEID (0x64) -#define MT6360_TCPC_SLAVEID (0x4E) +#define MT6360_PMU_SLAVEID 0x34 +#define MT6360_PMIC_SLAVEID 0x1A +#define MT6360_LDO_SLAVEID 0x64 +#define MT6360_TCPC_SLAVEID 0x4E struct mt6360_pmu_data { struct i2c_client *i2c[MT6360_SLAVE_MAX]; @@ -30,211 +30,211 @@ struct mt6360_pmu_data { }; /* PMU register defininition */ -#define MT6360_PMU_DEV_INFO (0x00) -#define MT6360_PMU_CORE_CTRL1 (0x01) -#define MT6360_PMU_RST1 (0x02) -#define MT6360_PMU_CRCEN (0x03) -#define MT6360_PMU_RST_PAS_CODE1 (0x04) -#define MT6360_PMU_RST_PAS_CODE2 (0x05) -#define MT6360_PMU_CORE_CTRL2 (0x06) -#define MT6360_PMU_TM_PAS_CODE1 (0x07) -#define MT6360_PMU_TM_PAS_CODE2 (0x08) -#define MT6360_PMU_TM_PAS_CODE3 (0x09) -#define MT6360_PMU_TM_PAS_CODE4 (0x0A) -#define MT6360_PMU_IRQ_IND (0x0B) -#define MT6360_PMU_IRQ_MASK (0x0C) -#define MT6360_PMU_IRQ_SET (0x0D) -#define MT6360_PMU_SHDN_CTRL (0x0E) -#define MT6360_PMU_TM_INF (0x0F) -#define MT6360_PMU_I2C_CTRL (0x10) -#define MT6360_PMU_CHG_CTRL1 (0x11) -#define MT6360_PMU_CHG_CTRL2 (0x12) -#define MT6360_PMU_CHG_CTRL3 (0x13) -#define MT6360_PMU_CHG_CTRL4 (0x14) -#define MT6360_PMU_CHG_CTRL5 (0x15) -#define MT6360_PMU_CHG_CTRL6 (0x16) -#define MT6360_PMU_CHG_CTRL7 (0x17) -#define MT6360_PMU_CHG_CTRL8 (0x18) -#define MT6360_PMU_CHG_CTRL9 (0x19) -#define MT6360_PMU_CHG_CTRL10 (0x1A) -#define MT6360_PMU_CHG_CTRL11 (0x1B) -#define MT6360_PMU_CHG_CTRL12 (0x1C) -#define MT6360_PMU_CHG_CTRL13 (0x1D) -#define MT6360_PMU_CHG_CTRL14 (0x1E) -#define MT6360_PMU_CHG_CTRL15 (0x1F) -#define MT6360_PMU_CHG_CTRL16 (0x20) -#define MT6360_PMU_CHG_AICC_RESULT (0x21) -#define MT6360_PMU_DEVICE_TYPE (0x22) -#define MT6360_PMU_QC_CONTROL1 (0x23) -#define MT6360_PMU_QC_CONTROL2 (0x24) -#define MT6360_PMU_QC30_CONTROL1 (0x25) -#define MT6360_PMU_QC30_CONTROL2 (0x26) -#define MT6360_PMU_USB_STATUS1 (0x27) -#define MT6360_PMU_QC_STATUS1 (0x28) -#define MT6360_PMU_QC_STATUS2 (0x29) -#define MT6360_PMU_CHG_PUMP (0x2A) -#define MT6360_PMU_CHG_CTRL17 (0x2B) -#define MT6360_PMU_CHG_CTRL18 (0x2C) -#define MT6360_PMU_CHRDET_CTRL1 (0x2D) -#define MT6360_PMU_CHRDET_CTRL2 (0x2E) -#define MT6360_PMU_DPDN_CTRL (0x2F) -#define MT6360_PMU_CHG_HIDDEN_CTRL1 (0x30) -#define MT6360_PMU_CHG_HIDDEN_CTRL2 (0x31) -#define MT6360_PMU_CHG_HIDDEN_CTRL3 (0x32) -#define MT6360_PMU_CHG_HIDDEN_CTRL4 (0x33) -#define MT6360_PMU_CHG_HIDDEN_CTRL5 (0x34) -#define MT6360_PMU_CHG_HIDDEN_CTRL6 (0x35) -#define MT6360_PMU_CHG_HIDDEN_CTRL7 (0x36) -#define MT6360_PMU_CHG_HIDDEN_CTRL8 (0x37) -#define MT6360_PMU_CHG_HIDDEN_CTRL9 (0x38) -#define MT6360_PMU_CHG_HIDDEN_CTRL10 (0x39) -#define MT6360_PMU_CHG_HIDDEN_CTRL11 (0x3A) -#define MT6360_PMU_CHG_HIDDEN_CTRL12 (0x3B) -#define MT6360_PMU_CHG_HIDDEN_CTRL13 (0x3C) -#define MT6360_PMU_CHG_HIDDEN_CTRL14 (0x3D) -#define MT6360_PMU_CHG_HIDDEN_CTRL15 (0x3E) -#define MT6360_PMU_CHG_HIDDEN_CTRL16 (0x3F) -#define MT6360_PMU_CHG_HIDDEN_CTRL17 (0x40) -#define MT6360_PMU_CHG_HIDDEN_CTRL18 (0x41) -#define MT6360_PMU_CHG_HIDDEN_CTRL19 (0x42) -#define MT6360_PMU_CHG_HIDDEN_CTRL20 (0x43) -#define MT6360_PMU_CHG_HIDDEN_CTRL21 (0x44) -#define MT6360_PMU_CHG_HIDDEN_CTRL22 (0x45) -#define MT6360_PMU_CHG_HIDDEN_CTRL23 (0x46) -#define MT6360_PMU_CHG_HIDDEN_CTRL24 (0x47) -#define MT6360_PMU_CHG_HIDDEN_CTRL25 (0x48) -#define MT6360_PMU_BC12_CTRL (0x49) -#define MT6360_PMU_CHG_STAT (0x4A) -#define MT6360_PMU_RESV1 (0x4B) -#define MT6360_PMU_TYPEC_OTP_TH_SEL_CODEH (0x4E) -#define MT6360_PMU_TYPEC_OTP_TH_SEL_CODEL (0x4F) -#define MT6360_PMU_TYPEC_OTP_HYST_TH (0x50) -#define MT6360_PMU_TYPEC_OTP_CTRL (0x51) -#define MT6360_PMU_ADC_BAT_DATA_H (0x52) -#define MT6360_PMU_ADC_BAT_DATA_L (0x53) -#define MT6360_PMU_IMID_BACKBST_ON (0x54) -#define MT6360_PMU_IMID_BACKBST_OFF (0x55) -#define MT6360_PMU_ADC_CONFIG (0x56) -#define MT6360_PMU_ADC_EN2 (0x57) -#define MT6360_PMU_ADC_IDLE_T (0x58) -#define MT6360_PMU_ADC_RPT_1 (0x5A) -#define MT6360_PMU_ADC_RPT_2 (0x5B) -#define MT6360_PMU_ADC_RPT_3 (0x5C) -#define MT6360_PMU_ADC_RPT_ORG1 (0x5D) -#define MT6360_PMU_ADC_RPT_ORG2 (0x5E) -#define MT6360_PMU_BAT_OVP_TH_SEL_CODEH (0x5F) -#define MT6360_PMU_BAT_OVP_TH_SEL_CODEL (0x60) -#define MT6360_PMU_CHG_CTRL19 (0x61) -#define MT6360_PMU_VDDASUPPLY (0x62) -#define MT6360_PMU_BC12_MANUAL (0x63) -#define MT6360_PMU_CHGDET_FUNC (0x64) -#define MT6360_PMU_FOD_CTRL (0x65) -#define MT6360_PMU_CHG_CTRL20 (0x66) -#define MT6360_PMU_CHG_HIDDEN_CTRL26 (0x67) -#define MT6360_PMU_CHG_HIDDEN_CTRL27 (0x68) -#define MT6360_PMU_RESV2 (0x69) -#define MT6360_PMU_USBID_CTRL1 (0x6D) -#define MT6360_PMU_USBID_CTRL2 (0x6E) -#define MT6360_PMU_USBID_CTRL3 (0x6F) -#define MT6360_PMU_FLED_CFG (0x70) -#define MT6360_PMU_RESV3 (0x71) -#define MT6360_PMU_FLED1_CTRL (0x72) -#define MT6360_PMU_FLED_STRB_CTRL (0x73) -#define MT6360_PMU_FLED1_STRB_CTRL2 (0x74) -#define MT6360_PMU_FLED1_TOR_CTRL (0x75) -#define MT6360_PMU_FLED2_CTRL (0x76) -#define MT6360_PMU_RESV4 (0x77) -#define MT6360_PMU_FLED2_STRB_CTRL2 (0x78) -#define MT6360_PMU_FLED2_TOR_CTRL (0x79) -#define MT6360_PMU_FLED_VMIDTRK_CTRL1 (0x7A) -#define MT6360_PMU_FLED_VMID_RTM (0x7B) -#define MT6360_PMU_FLED_VMIDTRK_CTRL2 (0x7C) -#define MT6360_PMU_FLED_PWSEL (0x7D) -#define MT6360_PMU_FLED_EN (0x7E) -#define MT6360_PMU_FLED_Hidden1 (0x7F) -#define MT6360_PMU_RGB_EN (0x80) -#define MT6360_PMU_RGB1_ISNK (0x81) -#define MT6360_PMU_RGB2_ISNK (0x82) -#define MT6360_PMU_RGB3_ISNK (0x83) -#define MT6360_PMU_RGB_ML_ISNK (0x84) -#define MT6360_PMU_RGB1_DIM (0x85) -#define MT6360_PMU_RGB2_DIM (0x86) -#define MT6360_PMU_RGB3_DIM (0x87) -#define MT6360_PMU_RESV5 (0x88) -#define MT6360_PMU_RGB12_Freq (0x89) -#define MT6360_PMU_RGB34_Freq (0x8A) -#define MT6360_PMU_RGB1_Tr (0x8B) -#define MT6360_PMU_RGB1_Tf (0x8C) -#define MT6360_PMU_RGB1_TON_TOFF (0x8D) -#define MT6360_PMU_RGB2_Tr (0x8E) -#define MT6360_PMU_RGB2_Tf (0x8F) -#define MT6360_PMU_RGB2_TON_TOFF (0x90) -#define MT6360_PMU_RGB3_Tr (0x91) -#define MT6360_PMU_RGB3_Tf (0x92) -#define MT6360_PMU_RGB3_TON_TOFF (0x93) -#define MT6360_PMU_RGB_Hidden_CTRL1 (0x94) -#define MT6360_PMU_RGB_Hidden_CTRL2 (0x95) -#define MT6360_PMU_RESV6 (0x97) -#define MT6360_PMU_SPARE1 (0x9A) -#define MT6360_PMU_SPARE2 (0xA0) -#define MT6360_PMU_SPARE3 (0xB0) -#define MT6360_PMU_SPARE4 (0xC0) -#define MT6360_PMU_CHG_IRQ1 (0xD0) -#define MT6360_PMU_CHG_IRQ2 (0xD1) -#define MT6360_PMU_CHG_IRQ3 (0xD2) -#define MT6360_PMU_CHG_IRQ4 (0xD3) -#define MT6360_PMU_CHG_IRQ5 (0xD4) -#define MT6360_PMU_CHG_IRQ6 (0xD5) -#define MT6360_PMU_QC_IRQ (0xD6) -#define MT6360_PMU_FOD_IRQ (0xD7) -#define MT6360_PMU_BASE_IRQ (0xD8) -#define MT6360_PMU_FLED_IRQ1 (0xD9) -#define MT6360_PMU_FLED_IRQ2 (0xDA) -#define MT6360_PMU_RGB_IRQ (0xDB) -#define MT6360_PMU_BUCK1_IRQ (0xDC) -#define MT6360_PMU_BUCK2_IRQ (0xDD) -#define MT6360_PMU_LDO_IRQ1 (0xDE) -#define MT6360_PMU_LDO_IRQ2 (0xDF) -#define MT6360_PMU_CHG_STAT1 (0xE0) -#define MT6360_PMU_CHG_STAT2 (0xE1) -#define MT6360_PMU_CHG_STAT3 (0xE2) -#define MT6360_PMU_CHG_STAT4 (0xE3) -#define MT6360_PMU_CHG_STAT5 (0xE4) -#define MT6360_PMU_CHG_STAT6 (0xE5) -#define MT6360_PMU_QC_STAT (0xE6) -#define MT6360_PMU_FOD_STAT (0xE7) -#define MT6360_PMU_BASE_STAT (0xE8) -#define MT6360_PMU_FLED_STAT1 (0xE9) -#define MT6360_PMU_FLED_STAT2 (0xEA) -#define MT6360_PMU_RGB_STAT (0xEB) -#define MT6360_PMU_BUCK1_STAT (0xEC) -#define MT6360_PMU_BUCK2_STAT (0xED) -#define MT6360_PMU_LDO_STAT1 (0xEE) -#define MT6360_PMU_LDO_STAT2 (0xEF) -#define MT6360_PMU_CHG_MASK1 (0xF0) -#define MT6360_PMU_CHG_MASK2 (0xF1) -#define MT6360_PMU_CHG_MASK3 (0xF2) -#define MT6360_PMU_CHG_MASK4 (0xF3) -#define MT6360_PMU_CHG_MASK5 (0xF4) -#define MT6360_PMU_CHG_MASK6 (0xF5) -#define MT6360_PMU_QC_MASK (0xF6) -#define MT6360_PMU_FOD_MASK (0xF7) -#define MT6360_PMU_BASE_MASK (0xF8) -#define MT6360_PMU_FLED_MASK1 (0xF9) -#define MT6360_PMU_FLED_MASK2 (0xFA) -#define MT6360_PMU_FAULTB_MASK (0xFB) -#define MT6360_PMU_BUCK1_MASK (0xFC) -#define MT6360_PMU_BUCK2_MASK (0xFD) -#define MT6360_PMU_LDO_MASK1 (0xFE) -#define MT6360_PMU_LDO_MASK2 (0xFF) -#define MT6360_PMU_MAXREG (MT6360_PMU_LDO_MASK2) +#define MT6360_PMU_DEV_INFO 0x00 +#define MT6360_PMU_CORE_CTRL1 0x01 +#define MT6360_PMU_RST1 0x02 +#define MT6360_PMU_CRCEN 0x03 +#define MT6360_PMU_RST_PAS_CODE1 0x04 +#define MT6360_PMU_RST_PAS_CODE2 0x05 +#define MT6360_PMU_CORE_CTRL2 0x06 +#define MT6360_PMU_TM_PAS_CODE1 0x07 +#define MT6360_PMU_TM_PAS_CODE2 0x08 +#define MT6360_PMU_TM_PAS_CODE3 0x09 +#define MT6360_PMU_TM_PAS_CODE4 0x0A +#define MT6360_PMU_IRQ_IND 0x0B +#define MT6360_PMU_IRQ_MASK 0x0C +#define MT6360_PMU_IRQ_SET 0x0D +#define MT6360_PMU_SHDN_CTRL 0x0E +#define MT6360_PMU_TM_INF 0x0F +#define MT6360_PMU_I2C_CTRL 0x10 +#define MT6360_PMU_CHG_CTRL1 0x11 +#define MT6360_PMU_CHG_CTRL2 0x12 +#define MT6360_PMU_CHG_CTRL3 0x13 +#define MT6360_PMU_CHG_CTRL4 0x14 +#define MT6360_PMU_CHG_CTRL5 0x15 +#define MT6360_PMU_CHG_CTRL6 0x16 +#define MT6360_PMU_CHG_CTRL7 0x17 +#define MT6360_PMU_CHG_CTRL8 0x18 +#define MT6360_PMU_CHG_CTRL9 0x19 +#define MT6360_PMU_CHG_CTRL10 0x1A +#define MT6360_PMU_CHG_CTRL11 0x1B +#define MT6360_PMU_CHG_CTRL12 0x1C +#define MT6360_PMU_CHG_CTRL13 0x1D +#define MT6360_PMU_CHG_CTRL14 0x1E +#define MT6360_PMU_CHG_CTRL15 0x1F +#define MT6360_PMU_CHG_CTRL16 0x20 +#define MT6360_PMU_CHG_AICC_RESULT 0x21 +#define MT6360_PMU_DEVICE_TYPE 0x22 +#define MT6360_PMU_QC_CONTROL1 0x23 +#define MT6360_PMU_QC_CONTROL2 0x24 +#define MT6360_PMU_QC30_CONTROL1 0x25 +#define MT6360_PMU_QC30_CONTROL2 0x26 +#define MT6360_PMU_USB_STATUS1 0x27 +#define MT6360_PMU_QC_STATUS1 0x28 +#define MT6360_PMU_QC_STATUS2 0x29 +#define MT6360_PMU_CHG_PUMP 0x2A +#define MT6360_PMU_CHG_CTRL17 0x2B +#define MT6360_PMU_CHG_CTRL18 0x2C +#define MT6360_PMU_CHRDET_CTRL1 0x2D +#define MT6360_PMU_CHRDET_CTRL2 0x2E +#define MT6360_PMU_DPDN_CTRL 0x2F +#define MT6360_PMU_CHG_HIDDEN_CTRL1 0x30 +#define MT6360_PMU_CHG_HIDDEN_CTRL2 0x31 +#define MT6360_PMU_CHG_HIDDEN_CTRL3 0x32 +#define MT6360_PMU_CHG_HIDDEN_CTRL4 0x33 +#define MT6360_PMU_CHG_HIDDEN_CTRL5 0x34 +#define MT6360_PMU_CHG_HIDDEN_CTRL6 0x35 +#define MT6360_PMU_CHG_HIDDEN_CTRL7 0x36 +#define MT6360_PMU_CHG_HIDDEN_CTRL8 0x37 +#define MT6360_PMU_CHG_HIDDEN_CTRL9 0x38 +#define MT6360_PMU_CHG_HIDDEN_CTRL10 0x39 +#define MT6360_PMU_CHG_HIDDEN_CTRL11 0x3A +#define MT6360_PMU_CHG_HIDDEN_CTRL12 0x3B +#define MT6360_PMU_CHG_HIDDEN_CTRL13 0x3C +#define MT6360_PMU_CHG_HIDDEN_CTRL14 0x3D +#define MT6360_PMU_CHG_HIDDEN_CTRL15 0x3E +#define MT6360_PMU_CHG_HIDDEN_CTRL16 0x3F +#define MT6360_PMU_CHG_HIDDEN_CTRL17 0x40 +#define MT6360_PMU_CHG_HIDDEN_CTRL18 0x41 +#define MT6360_PMU_CHG_HIDDEN_CTRL19 0x42 +#define MT6360_PMU_CHG_HIDDEN_CTRL20 0x43 +#define MT6360_PMU_CHG_HIDDEN_CTRL21 0x44 +#define MT6360_PMU_CHG_HIDDEN_CTRL22 0x45 +#define MT6360_PMU_CHG_HIDDEN_CTRL23 0x46 +#define MT6360_PMU_CHG_HIDDEN_CTRL24 0x47 +#define MT6360_PMU_CHG_HIDDEN_CTRL25 0x48 +#define MT6360_PMU_BC12_CTRL 0x49 +#define MT6360_PMU_CHG_STAT 0x4A +#define MT6360_PMU_RESV1 0x4B +#define MT6360_PMU_TYPEC_OTP_TH_SEL_CODEH 0x4E +#define MT6360_PMU_TYPEC_OTP_TH_SEL_CODEL 0x4F +#define MT6360_PMU_TYPEC_OTP_HYST_TH 0x50 +#define MT6360_PMU_TYPEC_OTP_CTRL 0x51 +#define MT6360_PMU_ADC_BAT_DATA_H 0x52 +#define MT6360_PMU_ADC_BAT_DATA_L 0x53 +#define MT6360_PMU_IMID_BACKBST_ON 0x54 +#define MT6360_PMU_IMID_BACKBST_OFF 0x55 +#define MT6360_PMU_ADC_CONFIG 0x56 +#define MT6360_PMU_ADC_EN2 0x57 +#define MT6360_PMU_ADC_IDLE_T 0x58 +#define MT6360_PMU_ADC_RPT_1 0x5A +#define MT6360_PMU_ADC_RPT_2 0x5B +#define MT6360_PMU_ADC_RPT_3 0x5C +#define MT6360_PMU_ADC_RPT_ORG1 0x5D +#define MT6360_PMU_ADC_RPT_ORG2 0x5E +#define MT6360_PMU_BAT_OVP_TH_SEL_CODEH 0x5F +#define MT6360_PMU_BAT_OVP_TH_SEL_CODEL 0x60 +#define MT6360_PMU_CHG_CTRL19 0x61 +#define MT6360_PMU_VDDASUPPLY 0x62 +#define MT6360_PMU_BC12_MANUAL 0x63 +#define MT6360_PMU_CHGDET_FUNC 0x64 +#define MT6360_PMU_FOD_CTRL 0x65 +#define MT6360_PMU_CHG_CTRL20 0x66 +#define MT6360_PMU_CHG_HIDDEN_CTRL26 0x67 +#define MT6360_PMU_CHG_HIDDEN_CTRL27 0x68 +#define MT6360_PMU_RESV2 0x69 +#define MT6360_PMU_USBID_CTRL1 0x6D +#define MT6360_PMU_USBID_CTRL2 0x6E +#define MT6360_PMU_USBID_CTRL3 0x6F +#define MT6360_PMU_FLED_CFG 0x70 +#define MT6360_PMU_RESV3 0x71 +#define MT6360_PMU_FLED1_CTRL 0x72 +#define MT6360_PMU_FLED_STRB_CTRL 0x73 +#define MT6360_PMU_FLED1_STRB_CTRL2 0x74 +#define MT6360_PMU_FLED1_TOR_CTRL 0x75 +#define MT6360_PMU_FLED2_CTRL 0x76 +#define MT6360_PMU_RESV4 0x77 +#define MT6360_PMU_FLED2_STRB_CTRL2 0x78 +#define MT6360_PMU_FLED2_TOR_CTRL 0x79 +#define MT6360_PMU_FLED_VMIDTRK_CTRL1 0x7A +#define MT6360_PMU_FLED_VMID_RTM 0x7B +#define MT6360_PMU_FLED_VMIDTRK_CTRL2 0x7C +#define MT6360_PMU_FLED_PWSEL 0x7D +#define MT6360_PMU_FLED_EN 0x7E +#define MT6360_PMU_FLED_Hidden1 0x7F +#define MT6360_PMU_RGB_EN 0x80 +#define MT6360_PMU_RGB1_ISNK 0x81 +#define MT6360_PMU_RGB2_ISNK 0x82 +#define MT6360_PMU_RGB3_ISNK 0x83 +#define MT6360_PMU_RGB_ML_ISNK 0x84 +#define MT6360_PMU_RGB1_DIM 0x85 +#define MT6360_PMU_RGB2_DIM 0x86 +#define MT6360_PMU_RGB3_DIM 0x87 +#define MT6360_PMU_RESV5 0x88 +#define MT6360_PMU_RGB12_Freq 0x89 +#define MT6360_PMU_RGB34_Freq 0x8A +#define MT6360_PMU_RGB1_Tr 0x8B +#define MT6360_PMU_RGB1_Tf 0x8C +#define MT6360_PMU_RGB1_TON_TOFF 0x8D +#define MT6360_PMU_RGB2_Tr 0x8E +#define MT6360_PMU_RGB2_Tf 0x8F +#define MT6360_PMU_RGB2_TON_TOFF 0x90 +#define MT6360_PMU_RGB3_Tr 0x91 +#define MT6360_PMU_RGB3_Tf 0x92 +#define MT6360_PMU_RGB3_TON_TOFF 0x93 +#define MT6360_PMU_RGB_Hidden_CTRL1 0x94 +#define MT6360_PMU_RGB_Hidden_CTRL2 0x95 +#define MT6360_PMU_RESV6 0x97 +#define MT6360_PMU_SPARE1 0x9A +#define MT6360_PMU_SPARE2 0xA0 +#define MT6360_PMU_SPARE3 0xB0 +#define MT6360_PMU_SPARE4 0xC0 +#define MT6360_PMU_CHG_IRQ1 0xD0 +#define MT6360_PMU_CHG_IRQ2 0xD1 +#define MT6360_PMU_CHG_IRQ3 0xD2 +#define MT6360_PMU_CHG_IRQ4 0xD3 +#define MT6360_PMU_CHG_IRQ5 0xD4 +#define MT6360_PMU_CHG_IRQ6 0xD5 +#define MT6360_PMU_QC_IRQ 0xD6 +#define MT6360_PMU_FOD_IRQ 0xD7 +#define MT6360_PMU_BASE_IRQ 0xD8 +#define MT6360_PMU_FLED_IRQ1 0xD9 +#define MT6360_PMU_FLED_IRQ2 0xDA +#define MT6360_PMU_RGB_IRQ 0xDB +#define MT6360_PMU_BUCK1_IRQ 0xDC +#define MT6360_PMU_BUCK2_IRQ 0xDD +#define MT6360_PMU_LDO_IRQ1 0xDE +#define MT6360_PMU_LDO_IRQ2 0xDF +#define MT6360_PMU_CHG_STAT1 0xE0 +#define MT6360_PMU_CHG_STAT2 0xE1 +#define MT6360_PMU_CHG_STAT3 0xE2 +#define MT6360_PMU_CHG_STAT4 0xE3 +#define MT6360_PMU_CHG_STAT5 0xE4 +#define MT6360_PMU_CHG_STAT6 0xE5 +#define MT6360_PMU_QC_STAT 0xE6 +#define MT6360_PMU_FOD_STAT 0xE7 +#define MT6360_PMU_BASE_STAT 0xE8 +#define MT6360_PMU_FLED_STAT1 0xE9 +#define MT6360_PMU_FLED_STAT2 0xEA +#define MT6360_PMU_RGB_STAT 0xEB +#define MT6360_PMU_BUCK1_STAT 0xEC +#define MT6360_PMU_BUCK2_STAT 0xED +#define MT6360_PMU_LDO_STAT1 0xEE +#define MT6360_PMU_LDO_STAT2 0xEF +#define MT6360_PMU_CHG_MASK1 0xF0 +#define MT6360_PMU_CHG_MASK2 0xF1 +#define MT6360_PMU_CHG_MASK3 0xF2 +#define MT6360_PMU_CHG_MASK4 0xF3 +#define MT6360_PMU_CHG_MASK5 0xF4 +#define MT6360_PMU_CHG_MASK6 0xF5 +#define MT6360_PMU_QC_MASK 0xF6 +#define MT6360_PMU_FOD_MASK 0xF7 +#define MT6360_PMU_BASE_MASK 0xF8 +#define MT6360_PMU_FLED_MASK1 0xF9 +#define MT6360_PMU_FLED_MASK2 0xFA +#define MT6360_PMU_FAULTB_MASK 0xFB +#define MT6360_PMU_BUCK1_MASK 0xFC +#define MT6360_PMU_BUCK2_MASK 0xFD +#define MT6360_PMU_LDO_MASK1 0xFE +#define MT6360_PMU_LDO_MASK2 0xFF +#define MT6360_PMU_MAXREG MT6360_PMU_LDO_MASK2 /* MT6360_PMU_IRQ_SET */ #define MT6360_PMU_IRQ_REGNUM (MT6360_PMU_LDO_IRQ2 - MT6360_PMU_CHG_IRQ1 + 1) #define MT6360_IRQ_RETRIG BIT(2) -#define CHIP_VEN_MASK (0xF0) -#define CHIP_VEN_MT6360 (0x50) -#define CHIP_REV_MASK (0x0F) +#define CHIP_VEN_MASK 0xF0 +#define CHIP_VEN_MT6360 0x50 +#define CHIP_REV_MASK 0x0F #endif /* __MT6360_H__ */ -- cgit v1.2.3 From e63ce9a5b3edad84e5f1b3ffb081da7c9847c641 Mon Sep 17 00:00:00 2001 From: Gene Chen Date: Tue, 18 May 2021 01:33:09 +0800 Subject: mfd: mt6360: Rename mt6360_pmu_data by mt6360_ddata Rename mt6360_pmu_data by mt6360_ddata because of including not only PMU part, but also entire MT6360 IC. Signed-off-by: Gene Chen Signed-off-by: Lee Jones --- include/linux/mfd/mt6360.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/mt6360.h b/include/linux/mfd/mt6360.h index 72edf1352229..81bca7c2ad4d 100644 --- a/include/linux/mfd/mt6360.h +++ b/include/linux/mfd/mt6360.h @@ -21,7 +21,7 @@ enum { #define MT6360_LDO_SLAVEID 0x64 #define MT6360_TCPC_SLAVEID 0x4E -struct mt6360_pmu_data { +struct mt6360_ddata { struct i2c_client *i2c[MT6360_SLAVE_MAX]; struct device *dev; struct regmap *regmap; -- cgit v1.2.3 From a75a2d56dc2f1a95a0b481eec74f60ff81a1b291 Mon Sep 17 00:00:00 2001 From: Gene Chen Date: Tue, 18 May 2021 01:33:11 +0800 Subject: mfd: mt6360: Remove handle_post_irq callback function Remove handle_post_irq which is used to retrigger IRQ. Set IRQ level low trigger in dtsi to keep IRQ always be handled. Signed-off-by: Gene Chen Signed-off-by: Lee Jones --- include/linux/mfd/mt6360.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/mt6360.h b/include/linux/mfd/mt6360.h index 81bca7c2ad4d..ef8257dffe3f 100644 --- a/include/linux/mfd/mt6360.h +++ b/include/linux/mfd/mt6360.h @@ -230,7 +230,7 @@ struct mt6360_ddata { #define MT6360_PMU_MAXREG MT6360_PMU_LDO_MASK2 /* MT6360_PMU_IRQ_SET */ -#define MT6360_PMU_IRQ_REGNUM (MT6360_PMU_LDO_IRQ2 - MT6360_PMU_CHG_IRQ1 + 1) +#define MT6360_PMU_IRQ_REGNUM 16 #define MT6360_IRQ_RETRIG BIT(2) #define CHIP_VEN_MASK 0xF0 -- cgit v1.2.3 From b042c085de7aa89eedfe8df8388b19a0e6679a39 Mon Sep 17 00:00:00 2001 From: Gene Chen Date: Tue, 18 May 2021 01:33:13 +0800 Subject: mfd: mt6360: Merge header file into driver and remove unuse register define Merge header file into driver and remove unuse register define Signed-off-by: Gene Chen Signed-off-by: Lee Jones --- include/linux/mfd/mt6360.h | 240 --------------------------------------------- 1 file changed, 240 deletions(-) delete mode 100644 include/linux/mfd/mt6360.h (limited to 'include/linux') diff --git a/include/linux/mfd/mt6360.h b/include/linux/mfd/mt6360.h deleted file mode 100644 index ef8257dffe3f..000000000000 --- a/include/linux/mfd/mt6360.h +++ /dev/null @@ -1,240 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (c) 2020 MediaTek Inc. - */ - -#ifndef __MT6360_H__ -#define __MT6360_H__ - -#include - -enum { - MT6360_SLAVE_PMU = 0, - MT6360_SLAVE_PMIC, - MT6360_SLAVE_LDO, - MT6360_SLAVE_TCPC, - MT6360_SLAVE_MAX, -}; - -#define MT6360_PMU_SLAVEID 0x34 -#define MT6360_PMIC_SLAVEID 0x1A -#define MT6360_LDO_SLAVEID 0x64 -#define MT6360_TCPC_SLAVEID 0x4E - -struct mt6360_ddata { - struct i2c_client *i2c[MT6360_SLAVE_MAX]; - struct device *dev; - struct regmap *regmap; - struct regmap_irq_chip_data *irq_data; - unsigned int chip_rev; -}; - -/* PMU register defininition */ -#define MT6360_PMU_DEV_INFO 0x00 -#define MT6360_PMU_CORE_CTRL1 0x01 -#define MT6360_PMU_RST1 0x02 -#define MT6360_PMU_CRCEN 0x03 -#define MT6360_PMU_RST_PAS_CODE1 0x04 -#define MT6360_PMU_RST_PAS_CODE2 0x05 -#define MT6360_PMU_CORE_CTRL2 0x06 -#define MT6360_PMU_TM_PAS_CODE1 0x07 -#define MT6360_PMU_TM_PAS_CODE2 0x08 -#define MT6360_PMU_TM_PAS_CODE3 0x09 -#define MT6360_PMU_TM_PAS_CODE4 0x0A -#define MT6360_PMU_IRQ_IND 0x0B -#define MT6360_PMU_IRQ_MASK 0x0C -#define MT6360_PMU_IRQ_SET 0x0D -#define MT6360_PMU_SHDN_CTRL 0x0E -#define MT6360_PMU_TM_INF 0x0F -#define MT6360_PMU_I2C_CTRL 0x10 -#define MT6360_PMU_CHG_CTRL1 0x11 -#define MT6360_PMU_CHG_CTRL2 0x12 -#define MT6360_PMU_CHG_CTRL3 0x13 -#define MT6360_PMU_CHG_CTRL4 0x14 -#define MT6360_PMU_CHG_CTRL5 0x15 -#define MT6360_PMU_CHG_CTRL6 0x16 -#define MT6360_PMU_CHG_CTRL7 0x17 -#define MT6360_PMU_CHG_CTRL8 0x18 -#define MT6360_PMU_CHG_CTRL9 0x19 -#define MT6360_PMU_CHG_CTRL10 0x1A -#define MT6360_PMU_CHG_CTRL11 0x1B -#define MT6360_PMU_CHG_CTRL12 0x1C -#define MT6360_PMU_CHG_CTRL13 0x1D -#define MT6360_PMU_CHG_CTRL14 0x1E -#define MT6360_PMU_CHG_CTRL15 0x1F -#define MT6360_PMU_CHG_CTRL16 0x20 -#define MT6360_PMU_CHG_AICC_RESULT 0x21 -#define MT6360_PMU_DEVICE_TYPE 0x22 -#define MT6360_PMU_QC_CONTROL1 0x23 -#define MT6360_PMU_QC_CONTROL2 0x24 -#define MT6360_PMU_QC30_CONTROL1 0x25 -#define MT6360_PMU_QC30_CONTROL2 0x26 -#define MT6360_PMU_USB_STATUS1 0x27 -#define MT6360_PMU_QC_STATUS1 0x28 -#define MT6360_PMU_QC_STATUS2 0x29 -#define MT6360_PMU_CHG_PUMP 0x2A -#define MT6360_PMU_CHG_CTRL17 0x2B -#define MT6360_PMU_CHG_CTRL18 0x2C -#define MT6360_PMU_CHRDET_CTRL1 0x2D -#define MT6360_PMU_CHRDET_CTRL2 0x2E -#define MT6360_PMU_DPDN_CTRL 0x2F -#define MT6360_PMU_CHG_HIDDEN_CTRL1 0x30 -#define MT6360_PMU_CHG_HIDDEN_CTRL2 0x31 -#define MT6360_PMU_CHG_HIDDEN_CTRL3 0x32 -#define MT6360_PMU_CHG_HIDDEN_CTRL4 0x33 -#define MT6360_PMU_CHG_HIDDEN_CTRL5 0x34 -#define MT6360_PMU_CHG_HIDDEN_CTRL6 0x35 -#define MT6360_PMU_CHG_HIDDEN_CTRL7 0x36 -#define MT6360_PMU_CHG_HIDDEN_CTRL8 0x37 -#define MT6360_PMU_CHG_HIDDEN_CTRL9 0x38 -#define MT6360_PMU_CHG_HIDDEN_CTRL10 0x39 -#define MT6360_PMU_CHG_HIDDEN_CTRL11 0x3A -#define MT6360_PMU_CHG_HIDDEN_CTRL12 0x3B -#define MT6360_PMU_CHG_HIDDEN_CTRL13 0x3C -#define MT6360_PMU_CHG_HIDDEN_CTRL14 0x3D -#define MT6360_PMU_CHG_HIDDEN_CTRL15 0x3E -#define MT6360_PMU_CHG_HIDDEN_CTRL16 0x3F -#define MT6360_PMU_CHG_HIDDEN_CTRL17 0x40 -#define MT6360_PMU_CHG_HIDDEN_CTRL18 0x41 -#define MT6360_PMU_CHG_HIDDEN_CTRL19 0x42 -#define MT6360_PMU_CHG_HIDDEN_CTRL20 0x43 -#define MT6360_PMU_CHG_HIDDEN_CTRL21 0x44 -#define MT6360_PMU_CHG_HIDDEN_CTRL22 0x45 -#define MT6360_PMU_CHG_HIDDEN_CTRL23 0x46 -#define MT6360_PMU_CHG_HIDDEN_CTRL24 0x47 -#define MT6360_PMU_CHG_HIDDEN_CTRL25 0x48 -#define MT6360_PMU_BC12_CTRL 0x49 -#define MT6360_PMU_CHG_STAT 0x4A -#define MT6360_PMU_RESV1 0x4B -#define MT6360_PMU_TYPEC_OTP_TH_SEL_CODEH 0x4E -#define MT6360_PMU_TYPEC_OTP_TH_SEL_CODEL 0x4F -#define MT6360_PMU_TYPEC_OTP_HYST_TH 0x50 -#define MT6360_PMU_TYPEC_OTP_CTRL 0x51 -#define MT6360_PMU_ADC_BAT_DATA_H 0x52 -#define MT6360_PMU_ADC_BAT_DATA_L 0x53 -#define MT6360_PMU_IMID_BACKBST_ON 0x54 -#define MT6360_PMU_IMID_BACKBST_OFF 0x55 -#define MT6360_PMU_ADC_CONFIG 0x56 -#define MT6360_PMU_ADC_EN2 0x57 -#define MT6360_PMU_ADC_IDLE_T 0x58 -#define MT6360_PMU_ADC_RPT_1 0x5A -#define MT6360_PMU_ADC_RPT_2 0x5B -#define MT6360_PMU_ADC_RPT_3 0x5C -#define MT6360_PMU_ADC_RPT_ORG1 0x5D -#define MT6360_PMU_ADC_RPT_ORG2 0x5E -#define MT6360_PMU_BAT_OVP_TH_SEL_CODEH 0x5F -#define MT6360_PMU_BAT_OVP_TH_SEL_CODEL 0x60 -#define MT6360_PMU_CHG_CTRL19 0x61 -#define MT6360_PMU_VDDASUPPLY 0x62 -#define MT6360_PMU_BC12_MANUAL 0x63 -#define MT6360_PMU_CHGDET_FUNC 0x64 -#define MT6360_PMU_FOD_CTRL 0x65 -#define MT6360_PMU_CHG_CTRL20 0x66 -#define MT6360_PMU_CHG_HIDDEN_CTRL26 0x67 -#define MT6360_PMU_CHG_HIDDEN_CTRL27 0x68 -#define MT6360_PMU_RESV2 0x69 -#define MT6360_PMU_USBID_CTRL1 0x6D -#define MT6360_PMU_USBID_CTRL2 0x6E -#define MT6360_PMU_USBID_CTRL3 0x6F -#define MT6360_PMU_FLED_CFG 0x70 -#define MT6360_PMU_RESV3 0x71 -#define MT6360_PMU_FLED1_CTRL 0x72 -#define MT6360_PMU_FLED_STRB_CTRL 0x73 -#define MT6360_PMU_FLED1_STRB_CTRL2 0x74 -#define MT6360_PMU_FLED1_TOR_CTRL 0x75 -#define MT6360_PMU_FLED2_CTRL 0x76 -#define MT6360_PMU_RESV4 0x77 -#define MT6360_PMU_FLED2_STRB_CTRL2 0x78 -#define MT6360_PMU_FLED2_TOR_CTRL 0x79 -#define MT6360_PMU_FLED_VMIDTRK_CTRL1 0x7A -#define MT6360_PMU_FLED_VMID_RTM 0x7B -#define MT6360_PMU_FLED_VMIDTRK_CTRL2 0x7C -#define MT6360_PMU_FLED_PWSEL 0x7D -#define MT6360_PMU_FLED_EN 0x7E -#define MT6360_PMU_FLED_Hidden1 0x7F -#define MT6360_PMU_RGB_EN 0x80 -#define MT6360_PMU_RGB1_ISNK 0x81 -#define MT6360_PMU_RGB2_ISNK 0x82 -#define MT6360_PMU_RGB3_ISNK 0x83 -#define MT6360_PMU_RGB_ML_ISNK 0x84 -#define MT6360_PMU_RGB1_DIM 0x85 -#define MT6360_PMU_RGB2_DIM 0x86 -#define MT6360_PMU_RGB3_DIM 0x87 -#define MT6360_PMU_RESV5 0x88 -#define MT6360_PMU_RGB12_Freq 0x89 -#define MT6360_PMU_RGB34_Freq 0x8A -#define MT6360_PMU_RGB1_Tr 0x8B -#define MT6360_PMU_RGB1_Tf 0x8C -#define MT6360_PMU_RGB1_TON_TOFF 0x8D -#define MT6360_PMU_RGB2_Tr 0x8E -#define MT6360_PMU_RGB2_Tf 0x8F -#define MT6360_PMU_RGB2_TON_TOFF 0x90 -#define MT6360_PMU_RGB3_Tr 0x91 -#define MT6360_PMU_RGB3_Tf 0x92 -#define MT6360_PMU_RGB3_TON_TOFF 0x93 -#define MT6360_PMU_RGB_Hidden_CTRL1 0x94 -#define MT6360_PMU_RGB_Hidden_CTRL2 0x95 -#define MT6360_PMU_RESV6 0x97 -#define MT6360_PMU_SPARE1 0x9A -#define MT6360_PMU_SPARE2 0xA0 -#define MT6360_PMU_SPARE3 0xB0 -#define MT6360_PMU_SPARE4 0xC0 -#define MT6360_PMU_CHG_IRQ1 0xD0 -#define MT6360_PMU_CHG_IRQ2 0xD1 -#define MT6360_PMU_CHG_IRQ3 0xD2 -#define MT6360_PMU_CHG_IRQ4 0xD3 -#define MT6360_PMU_CHG_IRQ5 0xD4 -#define MT6360_PMU_CHG_IRQ6 0xD5 -#define MT6360_PMU_QC_IRQ 0xD6 -#define MT6360_PMU_FOD_IRQ 0xD7 -#define MT6360_PMU_BASE_IRQ 0xD8 -#define MT6360_PMU_FLED_IRQ1 0xD9 -#define MT6360_PMU_FLED_IRQ2 0xDA -#define MT6360_PMU_RGB_IRQ 0xDB -#define MT6360_PMU_BUCK1_IRQ 0xDC -#define MT6360_PMU_BUCK2_IRQ 0xDD -#define MT6360_PMU_LDO_IRQ1 0xDE -#define MT6360_PMU_LDO_IRQ2 0xDF -#define MT6360_PMU_CHG_STAT1 0xE0 -#define MT6360_PMU_CHG_STAT2 0xE1 -#define MT6360_PMU_CHG_STAT3 0xE2 -#define MT6360_PMU_CHG_STAT4 0xE3 -#define MT6360_PMU_CHG_STAT5 0xE4 -#define MT6360_PMU_CHG_STAT6 0xE5 -#define MT6360_PMU_QC_STAT 0xE6 -#define MT6360_PMU_FOD_STAT 0xE7 -#define MT6360_PMU_BASE_STAT 0xE8 -#define MT6360_PMU_FLED_STAT1 0xE9 -#define MT6360_PMU_FLED_STAT2 0xEA -#define MT6360_PMU_RGB_STAT 0xEB -#define MT6360_PMU_BUCK1_STAT 0xEC -#define MT6360_PMU_BUCK2_STAT 0xED -#define MT6360_PMU_LDO_STAT1 0xEE -#define MT6360_PMU_LDO_STAT2 0xEF -#define MT6360_PMU_CHG_MASK1 0xF0 -#define MT6360_PMU_CHG_MASK2 0xF1 -#define MT6360_PMU_CHG_MASK3 0xF2 -#define MT6360_PMU_CHG_MASK4 0xF3 -#define MT6360_PMU_CHG_MASK5 0xF4 -#define MT6360_PMU_CHG_MASK6 0xF5 -#define MT6360_PMU_QC_MASK 0xF6 -#define MT6360_PMU_FOD_MASK 0xF7 -#define MT6360_PMU_BASE_MASK 0xF8 -#define MT6360_PMU_FLED_MASK1 0xF9 -#define MT6360_PMU_FLED_MASK2 0xFA -#define MT6360_PMU_FAULTB_MASK 0xFB -#define MT6360_PMU_BUCK1_MASK 0xFC -#define MT6360_PMU_BUCK2_MASK 0xFD -#define MT6360_PMU_LDO_MASK1 0xFE -#define MT6360_PMU_LDO_MASK2 0xFF -#define MT6360_PMU_MAXREG MT6360_PMU_LDO_MASK2 - -/* MT6360_PMU_IRQ_SET */ -#define MT6360_PMU_IRQ_REGNUM 16 -#define MT6360_IRQ_RETRIG BIT(2) - -#define CHIP_VEN_MASK 0xF0 -#define CHIP_VEN_MT6360 0x50 -#define CHIP_REV_MASK 0x0F - -#endif /* __MT6360_H__ */ -- cgit v1.2.3 From 07a0b7d6f1543b45068ba427a1f0ee5375a259c9 Mon Sep 17 00:00:00 2001 From: Hao Fang Date: Sat, 22 May 2021 18:25:15 +0800 Subject: mfd: hisilicon: Use the correct HiSilicon copyright s/Hisilicon/HiSilicon/ It should use capital S, according to the official website https://www.hisilicon.com/en. Signed-off-by: Hao Fang Signed-off-by: Lee Jones --- include/linux/mfd/hi655x-pmic.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/hi655x-pmic.h b/include/linux/mfd/hi655x-pmic.h index b06171322178..af5d97239c0d 100644 --- a/include/linux/mfd/hi655x-pmic.h +++ b/include/linux/mfd/hi655x-pmic.h @@ -2,7 +2,7 @@ /* * Device driver for regulators in hi655x IC * - * Copyright (c) 2016 Hisilicon. + * Copyright (c) 2016 HiSilicon Ltd. * * Authors: * Chen Feng -- cgit v1.2.3 From 6f1b660731d841aa429a836c4ba04af551628050 Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Sun, 23 May 2021 15:10:45 +0800 Subject: mfd: bd71828: Fix .n_voltages settings Current .n_voltages settings do not cover the latest 2 valid selectors, so it fails to set voltage for the hightest voltage support. The latest linear range has step_uV = 0, so it does not matter if we count the .n_voltages to maximum selector + 1 or the first selector of latest linear range + 1. To simplify calculating the n_voltages, let's just set the .n_voltages to maximum selector + 1. Fixes: 522498f8cb8c ("regulator: bd71828: Basic support for ROHM bd71828 PMIC regulators") Signed-off-by: Axel Lin Reviewed-by: Matti Vaittinen Signed-off-by: Lee Jones --- include/linux/mfd/rohm-bd71828.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/rohm-bd71828.h b/include/linux/mfd/rohm-bd71828.h index c7ab69c87ee8..3b5f3a7db4bd 100644 --- a/include/linux/mfd/rohm-bd71828.h +++ b/include/linux/mfd/rohm-bd71828.h @@ -26,11 +26,11 @@ enum { BD71828_REGULATOR_AMOUNT, }; -#define BD71828_BUCK1267_VOLTS 0xEF -#define BD71828_BUCK3_VOLTS 0x10 -#define BD71828_BUCK4_VOLTS 0x20 -#define BD71828_BUCK5_VOLTS 0x10 -#define BD71828_LDO_VOLTS 0x32 +#define BD71828_BUCK1267_VOLTS 0x100 +#define BD71828_BUCK3_VOLTS 0x20 +#define BD71828_BUCK4_VOLTS 0x40 +#define BD71828_BUCK5_VOLTS 0x20 +#define BD71828_LDO_VOLTS 0x40 /* LDO6 is fixed 1.8V voltage */ #define BD71828_LDO_6_VOLTAGE 1800000 -- cgit v1.2.3 From 12e1a41952c08fda89f6b14188ec6cdf31462907 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 26 May 2021 08:47:07 -0400 Subject: mfd: sec: Remove unused cfg_pmic_irq in platform data The 'cfg_pmic_irq' field of platform data structure is not used and can be safely dropped. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Lee Jones --- include/linux/mfd/samsung/core.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/samsung/core.h b/include/linux/mfd/samsung/core.h index f1631a39acfc..68afc2b97a41 100644 --- a/include/linux/mfd/samsung/core.h +++ b/include/linux/mfd/samsung/core.h @@ -85,7 +85,6 @@ struct sec_platform_data { int num_regulators; int irq_base; - int (*cfg_pmic_irq)(void); bool wakeup; bool buck_voltage_lock; -- cgit v1.2.3 From 294fb2ce2de246e126f9f3a4568bfd8e568a2b5b Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 26 May 2021 08:47:08 -0400 Subject: mfd: sec: Remove unused device_type in platform data The 'device_type' field of platform data structure is not used and can be safely dropped. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Lee Jones --- include/linux/mfd/samsung/core.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/samsung/core.h b/include/linux/mfd/samsung/core.h index 68afc2b97a41..bfde1b7c6303 100644 --- a/include/linux/mfd/samsung/core.h +++ b/include/linux/mfd/samsung/core.h @@ -81,7 +81,6 @@ int sec_irq_resume(struct sec_pmic_dev *sec_pmic); struct sec_platform_data { struct sec_regulator_data *regulators; struct sec_opmode_data *opmode; - int device_type; int num_regulators; int irq_base; -- cgit v1.2.3 From c1d3ab31e7356cb54de35991ac70176379d4caed Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 26 May 2021 08:47:09 -0400 Subject: mfd: sec: Remove unused irq_base in platform data The 'irq_base' field of platform data structure is not assigned, therefore its default value of 0 has no impact and can be safely dropped. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Lee Jones --- include/linux/mfd/samsung/core.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/samsung/core.h b/include/linux/mfd/samsung/core.h index bfde1b7c6303..9864f13b7814 100644 --- a/include/linux/mfd/samsung/core.h +++ b/include/linux/mfd/samsung/core.h @@ -67,7 +67,6 @@ struct sec_pmic_dev { struct i2c_client *i2c; unsigned long device_type; - int irq_base; int irq; struct regmap_irq_chip_data *irq_data; @@ -83,8 +82,6 @@ struct sec_platform_data { struct sec_opmode_data *opmode; int num_regulators; - int irq_base; - bool wakeup; bool buck_voltage_lock; -- cgit v1.2.3 From 2056f024c89cf2c7cd5eeab47592e3c397efb468 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 26 May 2021 08:47:10 -0400 Subject: mfd: sec: Enable wakeup from suspend via devicetree property Set device wakeup capability from devicetree property (done by drivers core), instead of always setting it to 0 (because value in platform data is not assigned). This should not have visible effect on actual resuming from suspend because the child device - S5M RTC driver - is responsible for waking up and sets device wakeup unconditionally. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Lee Jones --- include/linux/mfd/samsung/core.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/samsung/core.h b/include/linux/mfd/samsung/core.h index 9864f13b7814..b0d049a56d16 100644 --- a/include/linux/mfd/samsung/core.h +++ b/include/linux/mfd/samsung/core.h @@ -69,8 +69,6 @@ struct sec_pmic_dev { unsigned long device_type; int irq; struct regmap_irq_chip_data *irq_data; - - bool wakeup; }; int sec_irq_init(struct sec_pmic_dev *sec_pmic); @@ -82,7 +80,6 @@ struct sec_platform_data { struct sec_opmode_data *opmode; int num_regulators; - bool wakeup; bool buck_voltage_lock; int buck_gpios[3]; -- cgit v1.2.3 From 39cdbe8d2bc61d70efa22b06b14b129ebd9d0bc5 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 26 May 2021 08:47:11 -0400 Subject: mfd: sec: Remove unused platform data members The Samsung PMIC drivers for early chipsets like S5M8767 stored quite a lot in platform data (struct sec_platform_data). The s5m8767 regulator driver currently references only some of its fields. Newer regulator drivers (e.g. s2mps11) use even less platform data fields. Clean up the structure to reduce memory footprint and source code size. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Lee Jones --- include/linux/mfd/samsung/core.h | 25 ------------------------- 1 file changed, 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/samsung/core.h b/include/linux/mfd/samsung/core.h index b0d049a56d16..f92fe090473d 100644 --- a/include/linux/mfd/samsung/core.h +++ b/include/linux/mfd/samsung/core.h @@ -80,8 +80,6 @@ struct sec_platform_data { struct sec_opmode_data *opmode; int num_regulators; - bool buck_voltage_lock; - int buck_gpios[3]; int buck_ds[3]; unsigned int buck2_voltage[8]; @@ -91,35 +89,12 @@ struct sec_platform_data { unsigned int buck4_voltage[8]; bool buck4_gpiodvs; - int buck_set1; - int buck_set2; - int buck_set3; - int buck2_enable; - int buck3_enable; - int buck4_enable; int buck_default_idx; - int buck2_default_idx; - int buck3_default_idx; - int buck4_default_idx; - int buck_ramp_delay; - int buck2_ramp_delay; - int buck34_ramp_delay; - int buck5_ramp_delay; - int buck16_ramp_delay; - int buck7810_ramp_delay; - int buck9_ramp_delay; - int buck24_ramp_delay; - int buck3_ramp_delay; - int buck7_ramp_delay; - int buck8910_ramp_delay; - - bool buck1_ramp_enable; bool buck2_ramp_enable; bool buck3_ramp_enable; bool buck4_ramp_enable; - bool buck6_ramp_enable; int buck2_init; int buck3_init; -- cgit v1.2.3 From 8314b6732ae4e600bb933e108f96ce0176acb09c Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Tue, 1 Jun 2021 10:23:38 +0200 Subject: ima: Define new template fields xattrnames, xattrlengths and xattrvalues This patch defines the new template fields xattrnames, xattrlengths and xattrvalues, which contain respectively a list of xattr names (strings, separated by |), lengths (u32, hex) and values (hex). If an xattr is not present, the name and length are not displayed in the measurement list. Reported-by: kernel test robot (Missing prototype def) Signed-off-by: Roberto Sassu Signed-off-by: Mimi Zohar --- include/linux/evm.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/evm.h b/include/linux/evm.h index 5011a299c251..4c374be70247 100644 --- a/include/linux/evm.h +++ b/include/linux/evm.h @@ -39,6 +39,9 @@ extern int evm_inode_init_security(struct inode *inode, struct xattr *evm); extern bool evm_revalidate_status(const char *xattr_name); extern int evm_protected_xattr_if_enabled(const char *req_xattr_name); +extern int evm_read_protected_xattrs(struct dentry *dentry, u8 *buffer, + int buffer_size, char type, + bool canonical_fmt); #ifdef CONFIG_FS_POSIX_ACL extern int posix_xattr_acl(const char *xattrname); #else @@ -120,5 +123,12 @@ static inline int evm_protected_xattr_if_enabled(const char *req_xattr_name) return false; } +static inline int evm_read_protected_xattrs(struct dentry *dentry, u8 *buffer, + int buffer_size, char type, + bool canonical_fmt) +{ + return -EOPNOTSUPP; +} + #endif /* CONFIG_EVM */ #endif /* LINUX_EVM_H */ -- cgit v1.2.3 From fa0cf568fd76550c1ddb806c03a65a1a4a1ea909 Mon Sep 17 00:00:00 2001 From: Shiraz Saleem Date: Wed, 2 Jun 2021 15:51:37 -0500 Subject: RDMA/irdma: Add irdma Kconfig/Makefile and remove i40iw Add Kconfig and Makefile to build irdma driver. Remove i40iw driver and add an alias in irdma. Remove legacy exported symbols i40e_register_client and i40e_unregister_client from i40e as they are no longer used. irdma is the replacement driver that supports X722. Link: https://lore.kernel.org/r/20210602205138.889-16-shiraz.saleem@intel.com Signed-off-by: Shiraz Saleem Signed-off-by: Jason Gunthorpe --- include/linux/net/intel/i40e_client.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/net/intel/i40e_client.h b/include/linux/net/intel/i40e_client.h index 41f24b5241ab..6b3267b49755 100644 --- a/include/linux/net/intel/i40e_client.h +++ b/include/linux/net/intel/i40e_client.h @@ -197,8 +197,5 @@ static inline bool i40e_client_is_registered(struct i40e_client *client) void i40e_client_device_register(struct i40e_info *ldev, struct i40e_client *client); void i40e_client_device_unregister(struct i40e_info *ldev); -/* used by clients */ -int i40e_register_client(struct i40e_client *client); -int i40e_unregister_client(struct i40e_client *client); #endif /* _I40E_CLIENT_H_ */ -- cgit v1.2.3 From 12d55d3b5370448f6568d0031b5e401cc050c29e Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 27 May 2021 14:38:41 -0500 Subject: of: Move reserved memory private function declarations fdt_init_reserved_mem() and fdt_reserved_mem_save_node() are private to the DT code, so move there declarations to of_private.h. There's no need for the dummy functions as CONFIG_OF_RESERVED_MEM is always enabled for CONFIG_OF_EARLY_FLATTREE. Cc: Frank Rowand Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20210527193841.1284169-1-robh@kernel.org --- include/linux/of_reserved_mem.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_reserved_mem.h b/include/linux/of_reserved_mem.h index 8216a4156263..76e4a0fffba4 100644 --- a/include/linux/of_reserved_mem.h +++ b/include/linux/of_reserved_mem.h @@ -39,9 +39,6 @@ int of_reserved_mem_device_init_by_name(struct device *dev, const char *name); void of_reserved_mem_device_release(struct device *dev); -void fdt_init_reserved_mem(void); -void fdt_reserved_mem_save_node(unsigned long node, const char *uname, - phys_addr_t base, phys_addr_t size); struct reserved_mem *of_reserved_mem_lookup(struct device_node *np); #else static inline int of_reserved_mem_device_init_by_idx(struct device *dev, @@ -59,9 +56,6 @@ static inline int of_reserved_mem_device_init_by_name(struct device *dev, static inline void of_reserved_mem_device_release(struct device *pdev) { } -static inline void fdt_init_reserved_mem(void) { } -static inline void fdt_reserved_mem_save_node(unsigned long node, - const char *uname, phys_addr_t base, phys_addr_t size) { } static inline struct reserved_mem *of_reserved_mem_lookup(struct device_node *np) { return NULL; -- cgit v1.2.3 From 00dcc7cf1a49f93efaa281cc85c88005995ecf63 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 27 May 2021 14:45:44 -0500 Subject: PCI: Add empty stub for pci_register_io_range() Add an empty stub for pci_register_io_range() when !CONFIG_PCI. It's needed to convert of_pci_range_to_resource() to use IS_ENABLED(CONFIG_PCI). Cc: Bjorn Helgaas Cc: linux-pci@vger.kernel.org Signed-off-by: Rob Herring Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20210527194547.1287934-2-robh@kernel.org --- include/linux/pci.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index c20211e59a57..29da7598f8d0 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1772,6 +1772,10 @@ static inline int pci_request_regions(struct pci_dev *dev, const char *res_name) { return -EIO; } static inline void pci_release_regions(struct pci_dev *dev) { } +static inline int pci_register_io_range(struct fwnode_handle *fwnode, + phys_addr_t addr, resource_size_t size) +{ return -EINVAL; } + static inline unsigned long pci_address_to_pio(phys_addr_t addr) { return -1; } static inline struct pci_bus *pci_find_next_bus(const struct pci_bus *from) -- cgit v1.2.3 From 050a2c62dfc7d9ef457405f6ab4b715e9a2e32d7 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 27 May 2021 14:45:45 -0500 Subject: of: Merge of_get_address() and of_get_pci_address() implementations of_get_address() and of_get_pci_address() are the same implementation except of_get_pci_address() takes the PCI BAR number rather than an index. Modify the of_get_address() implementation to work on either index or BAR and provide wrapper functions for the existing functions. Cc: Frank Rowand Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20210527194547.1287934-3-robh@kernel.org --- include/linux/of_address.h | 27 ++++++++++++++++----------- 1 file changed, 16 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_address.h b/include/linux/of_address.h index 88bc943405cd..b72807faf037 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -51,8 +51,8 @@ void __iomem *of_io_request_and_map(struct device_node *device, * the address space flags too. The PCI version uses a BAR number * instead of an absolute index */ -extern const __be32 *of_get_address(struct device_node *dev, int index, - u64 *size, unsigned int *flags); +extern const __be32 *__of_get_address(struct device_node *dev, int index, int bar_no, + u64 *size, unsigned int *flags); extern int of_pci_range_parser_init(struct of_pci_range_parser *parser, struct device_node *node); @@ -75,8 +75,8 @@ static inline u64 of_translate_address(struct device_node *np, return OF_BAD_ADDR; } -static inline const __be32 *of_get_address(struct device_node *dev, int index, - u64 *size, unsigned int *flags) +static inline const __be32 *__of_get_address(struct device_node *dev, int index, int bar_no, + u64 *size, unsigned int *flags) { return NULL; } @@ -125,8 +125,6 @@ static inline void __iomem *of_iomap(struct device_node *device, int index) #define of_range_parser_init of_pci_range_parser_init #if defined(CONFIG_OF_ADDRESS) && defined(CONFIG_PCI) -extern const __be32 *of_get_pci_address(struct device_node *dev, int bar_no, - u64 *size, unsigned int *flags); extern int of_pci_address_to_resource(struct device_node *dev, int bar, struct resource *r); extern int of_pci_range_to_resource(struct of_pci_range *range, @@ -139,11 +137,6 @@ static inline int of_pci_address_to_resource(struct device_node *dev, int bar, return -ENOSYS; } -static inline const __be32 *of_get_pci_address(struct device_node *dev, - int bar_no, u64 *size, unsigned int *flags) -{ - return NULL; -} static inline int of_pci_range_to_resource(struct of_pci_range *range, struct device_node *np, struct resource *res) @@ -152,4 +145,16 @@ static inline int of_pci_range_to_resource(struct of_pci_range *range, } #endif /* CONFIG_OF_ADDRESS && CONFIG_PCI */ +static inline const __be32 *of_get_address(struct device_node *dev, int index, + u64 *size, unsigned int *flags) +{ + return __of_get_address(dev, index, -1, size, flags); +} + +static inline const __be32 *of_get_pci_address(struct device_node *dev, int bar_no, + u64 *size, unsigned int *flags) +{ + return __of_get_address(dev, -1, bar_no, size, flags); +} + #endif /* __OF_ADDRESS_H */ -- cgit v1.2.3 From c3c0dc75774b488770f33598109161040d291367 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 27 May 2021 14:45:46 -0500 Subject: of: address: Use IS_ENABLED() for !CONFIG_PCI Convert address.c to use IS_ENABLED() instead of ifdefs for the public PCI functions. This simplifies the ifdefs in of_address.h. Cc: Frank Rowand Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20210527194547.1287934-4-robh@kernel.org --- include/linux/of_address.h | 39 ++++++++++++++++++--------------------- 1 file changed, 18 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_address.h b/include/linux/of_address.h index b72807faf037..45598dbec269 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -61,6 +61,11 @@ extern int of_pci_dma_range_parser_init(struct of_pci_range_parser *parser, extern struct of_pci_range *of_pci_range_parser_one( struct of_pci_range_parser *parser, struct of_pci_range *range); +extern int of_pci_address_to_resource(struct device_node *dev, int bar, + struct resource *r); +extern int of_pci_range_to_resource(struct of_pci_range *range, + struct device_node *np, + struct resource *res); extern bool of_dma_is_coherent(struct device_node *np); #else /* CONFIG_OF_ADDRESS */ static inline void __iomem *of_io_request_and_map(struct device_node *device, @@ -100,6 +105,19 @@ static inline struct of_pci_range *of_pci_range_parser_one( return NULL; } +static inline int of_pci_address_to_resource(struct device_node *dev, int bar, + struct resource *r) +{ + return -ENOSYS; +} + +static inline int of_pci_range_to_resource(struct of_pci_range *range, + struct device_node *np, + struct resource *res) +{ + return -ENOSYS; +} + static inline bool of_dma_is_coherent(struct device_node *np) { return false; @@ -124,27 +142,6 @@ static inline void __iomem *of_iomap(struct device_node *device, int index) #endif #define of_range_parser_init of_pci_range_parser_init -#if defined(CONFIG_OF_ADDRESS) && defined(CONFIG_PCI) -extern int of_pci_address_to_resource(struct device_node *dev, int bar, - struct resource *r); -extern int of_pci_range_to_resource(struct of_pci_range *range, - struct device_node *np, - struct resource *res); -#else /* CONFIG_OF_ADDRESS && CONFIG_PCI */ -static inline int of_pci_address_to_resource(struct device_node *dev, int bar, - struct resource *r) -{ - return -ENOSYS; -} - -static inline int of_pci_range_to_resource(struct of_pci_range *range, - struct device_node *np, - struct resource *res) -{ - return -ENOSYS; -} -#endif /* CONFIG_OF_ADDRESS && CONFIG_PCI */ - static inline const __be32 *of_get_address(struct device_node *dev, int index, u64 *size, unsigned int *flags) { -- cgit v1.2.3 From c545a90567125b874d817509036ec7d6698097ac Mon Sep 17 00:00:00 2001 From: JC Kuo Date: Wed, 20 Jan 2021 15:34:06 +0800 Subject: phy: tegra: xusb: Add sleepwalk and suspend/resume This commit adds sleepwalk/wake and suspend/resume interfaces to Tegra XUSB PHY driver. Tegra XUSB host controller driver makes use of sleepwalk functions to enable/disable sleepwalk circuit which is in always-on partition and can respond to USB resume signals when controller is not powered. Sleepwalk can be enabled/disabled for any USB UPHY individually. - tegra_xusb_padctl_enable_phy_sleepwalk() - tegra_xusb_padctl_disable_phy_sleepwalk() Tegra XUSB host controller driver makes use of wake functions to enable/disable/query wake circuit which is in always-on partition can wake system up when USB resume happens. Wake circuit can be enabled/disabled for any USB PHY individually. - tegra_xusb_padctl_enable_phy_wake() - tegra_xusb_padctl_disable_phy_wake() - tegra_xusb_padctl_remote_wake_detected() This commit also adds two system suspend stubs that can be used to save and restore XUSB PADCTL context during system suspend and resume. - tegra_xusb_padctl_suspend_noirq() - tegra_xusb_padctl_resume_noirq() Signed-off-by: JC Kuo Acked-By: Vinod Koul Signed-off-by: Thierry Reding --- include/linux/phy/tegra/xusb.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/phy/tegra/xusb.h b/include/linux/phy/tegra/xusb.h index 71d956935405..3a35e74cdc61 100644 --- a/include/linux/phy/tegra/xusb.h +++ b/include/linux/phy/tegra/xusb.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved. + * Copyright (c) 2016-2020, NVIDIA CORPORATION. All rights reserved. */ #ifndef PHY_TEGRA_XUSB_H @@ -8,6 +8,7 @@ struct tegra_xusb_padctl; struct device; +enum usb_device_speed; struct tegra_xusb_padctl *tegra_xusb_padctl_get(struct device *dev); void tegra_xusb_padctl_put(struct tegra_xusb_padctl *padctl); @@ -23,4 +24,11 @@ int tegra_xusb_padctl_set_vbus_override(struct tegra_xusb_padctl *padctl, int tegra_phy_xusb_utmi_port_reset(struct phy *phy); int tegra_xusb_padctl_get_usb3_companion(struct tegra_xusb_padctl *padctl, unsigned int port); +int tegra_xusb_padctl_enable_phy_sleepwalk(struct tegra_xusb_padctl *padctl, struct phy *phy, + enum usb_device_speed speed); +int tegra_xusb_padctl_disable_phy_sleepwalk(struct tegra_xusb_padctl *padctl, struct phy *phy); +int tegra_xusb_padctl_enable_phy_wake(struct tegra_xusb_padctl *padctl, struct phy *phy); +int tegra_xusb_padctl_disable_phy_wake(struct tegra_xusb_padctl *padctl, struct phy *phy); +bool tegra_xusb_padctl_remote_wake_detected(struct tegra_xusb_padctl *padctl, struct phy *phy); + #endif /* PHY_TEGRA_XUSB_H */ -- cgit v1.2.3 From c955a0cc8a286e5da1ebb88c19201e9bab8c2422 Mon Sep 17 00:00:00 2001 From: Patrice Chotard Date: Tue, 18 May 2021 18:27:52 +0200 Subject: spi: spi-mem: add automatic poll status functions With STM32 QSPI, it is possible to poll the status register of the device. This could be done to offload the CPU during an operation (erase or program a SPI NAND for example). spi_mem_poll_status API has been added to handle this feature. This new function take care of the offload/non-offload cases. For the non-offload case, use read_poll_timeout() to poll the status in order to release CPU during this phase. For example, previously, when erasing large area, in non-offload case, CPU load can reach ~50%, now it decrease to ~35%. Signed-off-by: Patrice Chotard Signed-off-by: Christophe Kerello Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/r/20210518162754.15940-2-patrice.chotard@foss.st.com Signed-off-by: Mark Brown --- include/linux/spi/spi-mem.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index 2b65c9edc34e..85e2ff7b840d 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -250,6 +250,9 @@ static inline void *spi_mem_get_drvdata(struct spi_mem *mem) * the currently mapped area), and the caller of * spi_mem_dirmap_write() is responsible for calling it again in * this case. + * @poll_status: poll memory device status until (status & mask) == match or + * when the timeout has expired. It fills the data buffer with + * the last status value. * * This interface should be implemented by SPI controllers providing an * high-level interface to execute SPI memory operation, which is usually the @@ -274,6 +277,12 @@ struct spi_controller_mem_ops { u64 offs, size_t len, void *buf); ssize_t (*dirmap_write)(struct spi_mem_dirmap_desc *desc, u64 offs, size_t len, const void *buf); + int (*poll_status)(struct spi_mem *mem, + const struct spi_mem_op *op, + u16 mask, u16 match, + unsigned long initial_delay_us, + unsigned long polling_rate_us, + unsigned long timeout_ms); }; /** @@ -369,6 +378,13 @@ devm_spi_mem_dirmap_create(struct device *dev, struct spi_mem *mem, void devm_spi_mem_dirmap_destroy(struct device *dev, struct spi_mem_dirmap_desc *desc); +int spi_mem_poll_status(struct spi_mem *mem, + const struct spi_mem_op *op, + u16 mask, u16 match, + unsigned long initial_delay_us, + unsigned long polling_delay_us, + u16 timeout_ms); + int spi_mem_driver_register_with_owner(struct spi_mem_driver *drv, struct module *owner); -- cgit v1.2.3 From 8941cd8d295e40f8ea1c0a5045d6d068b8e33eec Mon Sep 17 00:00:00 2001 From: Patrice Chotard Date: Tue, 18 May 2021 18:27:53 +0200 Subject: mtd: spinand: use the spi-mem poll status APIs Make use of spi-mem poll status APIs to let advanced controllers optimize wait operations. This should also fix the high CPU usage for system that don't have a dedicated STATUS poll block logic. Signed-off-by: Patrice Chotard Signed-off-by: Christophe Kerello Reviewed-by: Boris Brezillon Acked-by: Miquel Raynal Link: https://lore.kernel.org/r/20210518162754.15940-3-patrice.chotard@foss.st.com Signed-off-by: Mark Brown --- include/linux/mtd/spinand.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index 6bb92f26833e..6988956b8492 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -170,6 +170,28 @@ struct spinand_op; struct spinand_device; #define SPINAND_MAX_ID_LEN 4 +/* + * For erase, write and read operation, we got the following timings : + * tBERS (erase) 1ms to 4ms + * tPROG 300us to 400us + * tREAD 25us to 100us + * In order to minimize latency, the min value is divided by 4 for the + * initial delay, and dividing by 20 for the poll delay. + * For reset, 5us/10us/500us if the device is respectively + * reading/programming/erasing when the RESET occurs. Since we always + * issue a RESET when the device is IDLE, 5us is selected for both initial + * and poll delay. + */ +#define SPINAND_READ_INITIAL_DELAY_US 6 +#define SPINAND_READ_POLL_DELAY_US 5 +#define SPINAND_RESET_INITIAL_DELAY_US 5 +#define SPINAND_RESET_POLL_DELAY_US 5 +#define SPINAND_WRITE_INITIAL_DELAY_US 75 +#define SPINAND_WRITE_POLL_DELAY_US 15 +#define SPINAND_ERASE_INITIAL_DELAY_US 250 +#define SPINAND_ERASE_POLL_DELAY_US 50 + +#define SPINAND_WAITRDY_TIMEOUT_MS 400 /** * struct spinand_id - SPI NAND id structure -- cgit v1.2.3 From 66cd071a1f839b4834d45aa7dde622151041b1a0 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 9 Apr 2021 19:10:53 +0100 Subject: iov_iter: Remove iov_iter_for_each_range() Remove iov_iter_for_each_range() as it's no longer used with the removal of lustre. Signed-off-by: David Howells Signed-off-by: Al Viro --- include/linux/uio.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index d3ec87706d75..74a401f04bd3 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -294,8 +294,4 @@ ssize_t __import_iovec(int type, const struct iovec __user *uvec, int import_single_range(int type, void __user *buf, size_t len, struct iovec *iov, struct iov_iter *i); -int iov_iter_for_each_range(struct iov_iter *i, size_t bytes, - int (*f)(struct kvec *vec, void *context), - void *context); - #endif -- cgit v1.2.3 From 066ebe8ca1e4734471772df734233af5c53d21ae Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 1 Jun 2021 15:35:59 +0200 Subject: power: ab8500: remove unused header The ab8500.h header in linux/power is not referenced/included, so can be safely removed. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Sebastian Reichel --- include/linux/power/ab8500.h | 16 ---------------- 1 file changed, 16 deletions(-) delete mode 100644 include/linux/power/ab8500.h (limited to 'include/linux') diff --git a/include/linux/power/ab8500.h b/include/linux/power/ab8500.h deleted file mode 100644 index 51976b52f373..000000000000 --- a/include/linux/power/ab8500.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) ST-Ericsson 2013 - * Author: Hongbo Zhang - */ - -#ifndef PWR_AB8500_H -#define PWR_AB8500_H - -extern const struct abx500_res_to_temp ab8500_temp_tbl_a_thermistor[]; -extern const int ab8500_temp_tbl_a_size; - -extern const struct abx500_res_to_temp ab8500_temp_tbl_b_thermistor[]; -extern const int ab8500_temp_tbl_b_size; - -#endif /* PWR_AB8500_H */ -- cgit v1.2.3 From aa8c8bf64b6e11f846087301f033b0e5977b1342 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sat, 29 May 2021 01:59:52 +0200 Subject: power: supply: pm2301_charger: Delete driver The PM2301 was only used in tandem with AB9540, part of U9540, a platform that was cancelled and never deployed in products. Delete it. Signed-off-by: Linus Walleij Signed-off-by: Sebastian Reichel --- include/linux/pm2301_charger.h | 48 ------------------------------------------ 1 file changed, 48 deletions(-) delete mode 100644 include/linux/pm2301_charger.h (limited to 'include/linux') diff --git a/include/linux/pm2301_charger.h b/include/linux/pm2301_charger.h deleted file mode 100644 index b8fac96f05aa..000000000000 --- a/include/linux/pm2301_charger.h +++ /dev/null @@ -1,48 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * PM2301 charger driver. - * - * Copyright (C) 2012 ST Ericsson Corporation - * - * Contact: Olivier LAUNAY (olivier.launay@stericsson.com - */ - -#ifndef __LINUX_PM2301_H -#define __LINUX_PM2301_H - -/** - * struct pm2xxx_bm_charger_parameters - Charger specific parameters - * @ac_volt_max: maximum allowed AC charger voltage in mV - * @ac_curr_max: maximum allowed AC charger current in mA - */ -struct pm2xxx_bm_charger_parameters { - int ac_volt_max; - int ac_curr_max; -}; - -/** - * struct pm2xxx_bm_data - pm2xxx battery management data - * @enable_overshoot flag to enable VBAT overshoot control - * @chg_params charger parameters - */ -struct pm2xxx_bm_data { - bool enable_overshoot; - const struct pm2xxx_bm_charger_parameters *chg_params; -}; - -struct pm2xxx_charger_platform_data { - char **supplied_to; - size_t num_supplicants; - int i2c_bus; - const char *label; - int gpio_irq_number; - unsigned int lpn_gpio; - int irq_type; -}; - -struct pm2xxx_platform_data { - struct pm2xxx_charger_platform_data *wall_charger; - struct pm2xxx_bm_data *battery; -}; - -#endif /* __LINUX_PM2301_H */ -- cgit v1.2.3 From b892770a2c553fd905ebd3ced55d5a437669b54d Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 18 May 2021 14:25:46 +0300 Subject: iio: Drop Duplicated "mount-matrix" parameter All of the users of iio_read_mount_matrix() are using the very same property name. Moreover, the property name is hard coded in the API documentation. Make this clear and avoid duplication now and in the future. Signed-off-by: Andy Shevchenko Reviewed-by: Sean Nyekjaer Reviewed-by: Linus Walleij Link: https://lore.kernel.org/r/20210518112546.44592-1-andriy.shevchenko@linux.intel.com Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 5606a3f4c4cb..324561b7a5e8 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -127,8 +127,7 @@ struct iio_mount_matrix { ssize_t iio_show_mount_matrix(struct iio_dev *indio_dev, uintptr_t priv, const struct iio_chan_spec *chan, char *buf); -int iio_read_mount_matrix(struct device *dev, const char *propname, - struct iio_mount_matrix *matrix); +int iio_read_mount_matrix(struct device *dev, struct iio_mount_matrix *matrix); typedef const struct iio_mount_matrix * (iio_get_mount_matrix_t)(const struct iio_dev *indio_dev, -- cgit v1.2.3 From 42ef8aa2263b19b06e69a318dbd8f1639013ded3 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 19 May 2021 01:07:18 +0200 Subject: iio: st_sensors: Create extended attr macro Extend ST_SENSORS_LSM_CHANNELS() to a version that will accept extended attributes named ST_SENSORS_LSM_CHANNELS_EXT() and wrap the former as a specialized version of the former. Cc: Hans de Goede Cc: Denis Ciocca Cc: Daniel Drake Reviewed-by: Andy Shevchenko Signed-off-by: Stephan Gerhold Signed-off-by: Linus Walleij Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20210518230722.522446-1-linus.walleij@linaro.org Signed-off-by: Jonathan Cameron --- include/linux/iio/common/st_sensors.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index 0b9aeb479f48..8e0d76b42db9 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -48,8 +48,8 @@ #define ST_SENSORS_MAX_NAME 17 #define ST_SENSORS_MAX_4WAI 8 -#define ST_SENSORS_LSM_CHANNELS(device_type, mask, index, mod, \ - ch2, s, endian, rbits, sbits, addr) \ +#define ST_SENSORS_LSM_CHANNELS_EXT(device_type, mask, index, mod, \ + ch2, s, endian, rbits, sbits, addr, ext) \ { \ .type = device_type, \ .modified = mod, \ @@ -65,8 +65,14 @@ .storagebits = sbits, \ .endianness = endian, \ }, \ + .ext_info = ext, \ } +#define ST_SENSORS_LSM_CHANNELS(device_type, mask, index, mod, \ + ch2, s, endian, rbits, sbits, addr) \ + ST_SENSORS_LSM_CHANNELS_EXT(device_type, mask, index, mod, \ + ch2, s, endian, rbits, sbits, addr, NULL) + #define ST_SENSORS_DEV_ATTR_SAMP_FREQ_AVAIL() \ IIO_DEV_ATTR_SAMP_FREQ_AVAIL( \ st_sensors_sysfs_sampling_frequency_avail) -- cgit v1.2.3 From 3d8ad94bb175c2de7200569bb706d67c45903838 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 19 May 2021 01:07:19 +0200 Subject: iio: accel: st_sensors: Support generic mounting matrix The ST accelerators support a special type of quirky mounting matrix found in ACPI systems, but not a generic mounting matrix such as from the device tree. Augment the ACPI hack to be a bit more generic and accept a mounting matrix from device properties. This makes it possible to fix orientation on the Ux500 HREF device. Cc: Hans de Goede Cc: Denis Ciocca Cc: Daniel Drake Reviewed-by: Andy Shevchenko Signed-off-by: Stephan Gerhold Signed-off-by: Linus Walleij Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20210518230722.522446-2-linus.walleij@linaro.org Signed-off-by: Jonathan Cameron --- include/linux/iio/common/st_sensors.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index 8e0d76b42db9..8bdbaf3f3796 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -221,6 +222,7 @@ struct st_sensor_settings { * struct st_sensor_data - ST sensor device status * @dev: Pointer to instance of struct device (I2C or SPI). * @trig: The trigger in use by the core driver. + * @mount_matrix: The mounting matrix of the sensor. * @sensor_settings: Pointer to the specific sensor settings in use. * @current_fullscale: Maximum range of measure by the sensor. * @vdd: Pointer to sensor's Vdd power supply @@ -240,7 +242,7 @@ struct st_sensor_settings { struct st_sensor_data { struct device *dev; struct iio_trigger *trig; - struct iio_mount_matrix *mount_matrix; + struct iio_mount_matrix mount_matrix; struct st_sensor_settings *sensor_settings; struct st_sensor_fullscale_avl *current_fullscale; struct regulator *vdd; -- cgit v1.2.3 From 490dcecabbf93e705006af498fa6815251404a54 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 19 May 2021 10:18:25 -0700 Subject: mlx5: count all link events mlx5 devices were observed generating MLX5_PORT_CHANGE_SUBTYPE_ACTIVE events without an intervening MLX5_PORT_CHANGE_SUBTYPE_DOWN. This breaks link flap detection based on Linux carrier state transition count as netif_carrier_on() does nothing if carrier is already on. Make sure we count such events. netif_carrier_event() increments the counters and fires the linkwatch events. The latter is not necessary for the use case but seems like the right thing to do. Signed-off-by: Jakub Kicinski Signed-off-by: Saeed Mahameed --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5cbc950b34df..be1dcceda5e4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4187,8 +4187,8 @@ unsigned long dev_trans_start(struct net_device *dev); void __netdev_watchdog_up(struct net_device *dev); void netif_carrier_on(struct net_device *dev); - void netif_carrier_off(struct net_device *dev); +void netif_carrier_event(struct net_device *dev); /** * netif_dormant_on - mark device as dormant. -- cgit v1.2.3 From b81017aeee4eb9159296cdb68889932649317b9b Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 2 Jun 2021 19:20:11 +0300 Subject: net: pcs: xpcs: delete shim definition for mdio_xpcs_get_ops() CONFIG_STMMAC_ETH selects CONFIG_PCS_XPCS, so there should be no situation where the shim should be needed. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/pcs/pcs-xpcs.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index 5938ced805f4..c4d0a2c469c7 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -36,13 +36,6 @@ struct mdio_xpcs_ops { int enable); }; -#if IS_ENABLED(CONFIG_PCS_XPCS) struct mdio_xpcs_ops *mdio_xpcs_get_ops(void); -#else -static inline struct mdio_xpcs_ops *mdio_xpcs_get_ops(void) -{ - return NULL; -} -#endif #endif /* __LINUX_PCS_XPCS_H */ -- cgit v1.2.3 From 9900074ecccec472c9d89929c3d37c235f45d33a Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 2 Jun 2021 19:20:13 +0300 Subject: net: pcs: xpcs: make the checks related to the PHY interface mode stateless The operating mode of the driver is currently to populate its struct mdio_xpcs_args::supported and struct mdio_xpcs_args::an_mode statically in xpcs_probe(), based on the passed phy_interface_t, and work with those. However this is not the operation that phylink expects from a PCS driver, because the port might be attached to an SFP cage that triggers changes of the phy_interface_t dynamically as one SFP module is unpluggged and another is plugged. To migrate towards that model, the struct mdio_xpcs_args should not cache anything related to the phy_interface_t, but just look up the statically defined, const struct xpcs_compat structure corresponding to the detected PCS OUI/model number. So we delete the "supported" and "an_mode" members of struct mdio_xpcs_args, and add the "id" structure there (since the ID is not expected to change at runtime). Since xpcs->supported is used deep in the code in _xpcs_config_aneg_c73(), we need to modify some function headers to pass the xpcs_compat from all callers. In turn, the xpcs_compat is always supplied externally to the xpcs module: - Most of the time by phylink - In xpcs_probe() it is needed because xpcs_soft_reset() writes to MDIO_MMD_PCS or to MDIO_MMD_VEND2 depending on whether an_mode is clause 37 or clause 73. In order to not introduce functional changes related to when the soft reset is issued, we continue to require the initial phy_interface_t argument to be passed to xpcs_probe() so we can pass this on to xpcs_soft_reset(). - stmmac_open() wants to know whether to call stmmac_init_phy() or not, and for that it looks inside xpcs->an_mode, because the clause 73 (backplane) AN modes supposedly do not have a PHY. Because we moved an_mode outside of struct mdio_xpcs_args, this is now no longer directly possible, so we introduce a helper function xpcs_get_an_mode() which protects the data encapsulation of the xpcs module and requires a phy_interface_t to be passed as argument. This function can look up the appropriate compat based on the phy_interface_t. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/pcs/pcs-xpcs.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index c4d0a2c469c7..c2ec440d2c5d 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -14,11 +14,12 @@ #define DW_AN_C73 1 #define DW_AN_C37_SGMII 2 +struct xpcs_id; + struct mdio_xpcs_args { - __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); struct mii_bus *bus; + const struct xpcs_id *id; int addr; - int an_mode; }; struct mdio_xpcs_ops { @@ -36,6 +37,7 @@ struct mdio_xpcs_ops { int enable); }; +int xpcs_get_an_mode(struct mdio_xpcs_args *xpcs, phy_interface_t interface); struct mdio_xpcs_ops *mdio_xpcs_get_ops(void); #endif /* __LINUX_PCS_XPCS_H */ -- cgit v1.2.3 From a1a753ed1d4ae46c1c1874fb1af899f6579a7547 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 2 Jun 2021 19:20:14 +0300 Subject: net: pcs: xpcs: export xpcs_validate Calling a function pointer with a single implementation through struct mdio_xpcs_ops is clunky, and the stmmac_do_callback system forces this to return int, even though it always returns zero. Simply remove the "validate" function pointer from struct mdio_xpcs_ops and replace it with an exported xpcs_validate symbol which is called directly by stmmac. priv->hw->xpcs is of the type "const struct mdio_xpcs_ops *" and is used as a placeholder/synonym for priv->plat->mdio_bus_data->has_xpcs. It is done that way because the mdio_bus_data pointer might or might not be populated in all stmmac instantiations. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/pcs/pcs-xpcs.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index c2ec440d2c5d..5ec9aaca01fe 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -23,9 +23,6 @@ struct mdio_xpcs_args { }; struct mdio_xpcs_ops { - int (*validate)(struct mdio_xpcs_args *xpcs, - unsigned long *supported, - struct phylink_link_state *state); int (*config)(struct mdio_xpcs_args *xpcs, const struct phylink_link_state *state); int (*get_state)(struct mdio_xpcs_args *xpcs, @@ -39,5 +36,7 @@ struct mdio_xpcs_ops { int xpcs_get_an_mode(struct mdio_xpcs_args *xpcs, phy_interface_t interface); struct mdio_xpcs_ops *mdio_xpcs_get_ops(void); +void xpcs_validate(struct mdio_xpcs_args *xpcs, unsigned long *supported, + struct phylink_link_state *state); #endif /* __LINUX_PCS_XPCS_H */ -- cgit v1.2.3 From 14b517cb62d6efc8866f176c922de03dfe1564f3 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 2 Jun 2021 19:20:15 +0300 Subject: net: pcs: xpcs: export xpcs_config_eee There is no good reason why we need to go through: stmmac_xpcs_config_eee -> stmmac_do_callback -> mdio_xpcs_ops->config_eee -> xpcs_config_eee when we can simply call xpcs_config_eee. priv->hw->xpcs is of the type "const struct mdio_xpcs_ops *" and is used as a placeholder/synonym for priv->plat->mdio_bus_data->has_xpcs. It is done that way because the mdio_bus_data pointer might or might not be populated in all stmmac instantiations. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/pcs/pcs-xpcs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index 5ec9aaca01fe..ae74a336dcb9 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -30,13 +30,13 @@ struct mdio_xpcs_ops { int (*link_up)(struct mdio_xpcs_args *xpcs, int speed, phy_interface_t interface); int (*probe)(struct mdio_xpcs_args *xpcs, phy_interface_t interface); - int (*config_eee)(struct mdio_xpcs_args *xpcs, int mult_fact_100ns, - int enable); }; int xpcs_get_an_mode(struct mdio_xpcs_args *xpcs, phy_interface_t interface); struct mdio_xpcs_ops *mdio_xpcs_get_ops(void); void xpcs_validate(struct mdio_xpcs_args *xpcs, unsigned long *supported, struct phylink_link_state *state); +int xpcs_config_eee(struct mdio_xpcs_args *xpcs, int mult_fact_100ns, + int enable); #endif /* __LINUX_PCS_XPCS_H */ -- cgit v1.2.3 From 8e2bb9569942f9cb2ef816dbf66fbf3e8d722720 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 2 Jun 2021 19:20:16 +0300 Subject: net: pcs: xpcs: export xpcs_probe Similar to the other recently functions, it is not necessary for xpcs_probe to be a function pointer, so export it so that it can be called directly. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/pcs/pcs-xpcs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index ae74a336dcb9..1d8581b74d81 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -29,7 +29,6 @@ struct mdio_xpcs_ops { struct phylink_link_state *state); int (*link_up)(struct mdio_xpcs_args *xpcs, int speed, phy_interface_t interface); - int (*probe)(struct mdio_xpcs_args *xpcs, phy_interface_t interface); }; int xpcs_get_an_mode(struct mdio_xpcs_args *xpcs, phy_interface_t interface); @@ -38,5 +37,6 @@ void xpcs_validate(struct mdio_xpcs_args *xpcs, unsigned long *supported, struct phylink_link_state *state); int xpcs_config_eee(struct mdio_xpcs_args *xpcs, int mult_fact_100ns, int enable); +int xpcs_probe(struct mdio_xpcs_args *xpcs, phy_interface_t interface); #endif /* __LINUX_PCS_XPCS_H */ -- cgit v1.2.3 From 2cac15dae2f6e2f86bef1acc2a7f78fc97a0a060 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 2 Jun 2021 19:20:18 +0300 Subject: net: pcs: xpcs: convert to mdio_device Unify the 2 existing PCS drivers (lynx and xpcs) by doing a similar thing on probe, which is to have a *_create function that takes a struct mdio_device * given by the caller, and builds a private PCS structure around that. This changes stmmac to hold only a pointer to the xpcs, as opposed to the full structure. This will be used in the next patch when struct mdio_xpcs_ops is removed. Currently a pointer to struct mdio_xpcs_ops is used as a shorthand to determine whether the port has an XPCS or not. We can do the same now with the mdio_xpcs_args pointer. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/pcs/pcs-xpcs.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index 1d8581b74d81..57a199393d63 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -17,9 +17,8 @@ struct xpcs_id; struct mdio_xpcs_args { - struct mii_bus *bus; + struct mdio_device *mdiodev; const struct xpcs_id *id; - int addr; }; struct mdio_xpcs_ops { @@ -37,6 +36,8 @@ void xpcs_validate(struct mdio_xpcs_args *xpcs, unsigned long *supported, struct phylink_link_state *state); int xpcs_config_eee(struct mdio_xpcs_args *xpcs, int mult_fact_100ns, int enable); -int xpcs_probe(struct mdio_xpcs_args *xpcs, phy_interface_t interface); +struct mdio_xpcs_args *xpcs_create(struct mdio_device *mdiodev, + phy_interface_t interface); +void xpcs_destroy(struct mdio_xpcs_args *xpcs); #endif /* __LINUX_PCS_XPCS_H */ -- cgit v1.2.3 From 11059740e616f4d83d8d9e3f8a63dafefdc2ae5d Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 2 Jun 2021 19:20:19 +0300 Subject: net: pcs: xpcs: convert to phylink_pcs_ops Since all the remaining members of struct mdio_xpcs_ops have direct equivalents in struct phylink_pcs_ops, it is about time we remove it altogether. Since the phylink ops return void, we need to remove the error propagation from the various xpcs methods and simply print an error message where appropriate. Since xpcs_get_state_c73() detects link faults and attempts to reset the link on its own by calling xpcs_config(), but xpcs_config() now has a lot of phylink arguments which are not needed and cannot be simply fabricated by anybody else except phylink, the actual implementation has been moved into a smaller xpcs_do_config(). The const struct mdio_xpcs_ops *priv->hw->xpcs has been removed, so we need to look at the struct mdio_xpcs_args pointer now as an indication whether the port has an XPCS or not. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/pcs/pcs-xpcs.h | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index 57a199393d63..0860a5b59f10 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -19,19 +19,10 @@ struct xpcs_id; struct mdio_xpcs_args { struct mdio_device *mdiodev; const struct xpcs_id *id; -}; - -struct mdio_xpcs_ops { - int (*config)(struct mdio_xpcs_args *xpcs, - const struct phylink_link_state *state); - int (*get_state)(struct mdio_xpcs_args *xpcs, - struct phylink_link_state *state); - int (*link_up)(struct mdio_xpcs_args *xpcs, int speed, - phy_interface_t interface); + struct phylink_pcs pcs; }; int xpcs_get_an_mode(struct mdio_xpcs_args *xpcs, phy_interface_t interface); -struct mdio_xpcs_ops *mdio_xpcs_get_ops(void); void xpcs_validate(struct mdio_xpcs_args *xpcs, unsigned long *supported, struct phylink_link_state *state); int xpcs_config_eee(struct mdio_xpcs_args *xpcs, int mult_fact_100ns, -- cgit v1.2.3 From 1bd4f5716fc3bb4882033fbeeb97472503f1c7e2 Mon Sep 17 00:00:00 2001 From: Omkar Kulkarni Date: Wed, 2 Jun 2021 20:16:49 +0300 Subject: qed: Add TCP_ULP FW resource layout Add TCP_ULP as a storage common TCP offload FW resource layout. This will be used by the core driver (QED) for both the NVMeTCP and iSCSI. Acked-by: Igor Russkikh Signed-off-by: Prabhakar Kushwaha Signed-off-by: Omkar Kulkarni Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Signed-off-by: Shai Malin Reviewed-by: Hannes Reinecke Signed-off-by: David S. Miller --- include/linux/qed/common_hsi.h | 2 +- include/linux/qed/qed_ll2_if.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 977807e1be53..0a3807e927c5 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -702,7 +702,7 @@ enum mf_mode { /* Per-protocol connection types */ enum protocol_type { - PROTOCOLID_ISCSI, + PROTOCOLID_TCP_ULP, PROTOCOLID_FCOE, PROTOCOLID_ROCE, PROTOCOLID_CORE, diff --git a/include/linux/qed/qed_ll2_if.h b/include/linux/qed/qed_ll2_if.h index ea273ba1c991..ff808d248883 100644 --- a/include/linux/qed/qed_ll2_if.h +++ b/include/linux/qed/qed_ll2_if.h @@ -18,7 +18,7 @@ enum qed_ll2_conn_type { QED_LL2_TYPE_FCOE, - QED_LL2_TYPE_ISCSI, + QED_LL2_TYPE_TCP_ULP, QED_LL2_TYPE_TEST, QED_LL2_TYPE_OOO, QED_LL2_TYPE_RESERVED2, -- cgit v1.2.3 From 897e87a10c35fb37a20886af6f731748d92c1836 Mon Sep 17 00:00:00 2001 From: Shai Malin Date: Wed, 2 Jun 2021 20:16:50 +0300 Subject: qed: Add NVMeTCP Offload PF Level FW and HW HSI This patch introduces the NVMeTCP device and PF level HSI and HSI functionality in order to initialize and interact with the HW device. The patch also adds qed NVMeTCP personality. This patch is based on the qede, qedr, qedi, qedf drivers HSI. Acked-by: Igor Russkikh Signed-off-by: Dean Balandin Signed-off-by: Prabhakar Kushwaha Signed-off-by: Omkar Kulkarni Signed-off-by: Shai Malin Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Reviewed-by: Hannes Reinecke Signed-off-by: David S. Miller --- include/linux/qed/nvmetcp_common.h | 54 +++++++++++++++++++++++++++++ include/linux/qed/qed_if.h | 18 ++++++++++ include/linux/qed/qed_nvmetcp_if.h | 71 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 143 insertions(+) create mode 100644 include/linux/qed/nvmetcp_common.h create mode 100644 include/linux/qed/qed_nvmetcp_if.h (limited to 'include/linux') diff --git a/include/linux/qed/nvmetcp_common.h b/include/linux/qed/nvmetcp_common.h new file mode 100644 index 000000000000..e9ccfc07041d --- /dev/null +++ b/include/linux/qed/nvmetcp_common.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ +/* Copyright 2021 Marvell. All rights reserved. */ + +#ifndef __NVMETCP_COMMON__ +#define __NVMETCP_COMMON__ + +#include "tcp_common.h" + +/* NVMeTCP firmware function init parameters */ +struct nvmetcp_spe_func_init { + __le16 half_way_close_timeout; + u8 num_sq_pages_in_ring; + u8 num_r2tq_pages_in_ring; + u8 num_uhq_pages_in_ring; + u8 ll2_rx_queue_id; + u8 flags; +#define NVMETCP_SPE_FUNC_INIT_COUNTERS_EN_MASK 0x1 +#define NVMETCP_SPE_FUNC_INIT_COUNTERS_EN_SHIFT 0 +#define NVMETCP_SPE_FUNC_INIT_NVMETCP_MODE_MASK 0x1 +#define NVMETCP_SPE_FUNC_INIT_NVMETCP_MODE_SHIFT 1 +#define NVMETCP_SPE_FUNC_INIT_RESERVED0_MASK 0x3F +#define NVMETCP_SPE_FUNC_INIT_RESERVED0_SHIFT 2 + u8 debug_flags; + __le16 reserved1; + u8 params; +#define NVMETCP_SPE_FUNC_INIT_MAX_SYN_RT_MASK 0xF +#define NVMETCP_SPE_FUNC_INIT_MAX_SYN_RT_SHIFT 0 +#define NVMETCP_SPE_FUNC_INIT_RESERVED1_MASK 0xF +#define NVMETCP_SPE_FUNC_INIT_RESERVED1_SHIFT 4 + u8 reserved2[5]; + struct scsi_init_func_params func_params; + struct scsi_init_func_queues q_params; +}; + +/* NVMeTCP init params passed by driver to FW in NVMeTCP init ramrod. */ +struct nvmetcp_init_ramrod_params { + struct nvmetcp_spe_func_init nvmetcp_init_spe; + struct tcp_init_params tcp_init; +}; + +/* NVMeTCP Ramrod Command IDs */ +enum nvmetcp_ramrod_cmd_id { + NVMETCP_RAMROD_CMD_ID_UNUSED = 0, + NVMETCP_RAMROD_CMD_ID_INIT_FUNC = 1, + NVMETCP_RAMROD_CMD_ID_DESTROY_FUNC = 2, + MAX_NVMETCP_RAMROD_CMD_ID +}; + +struct nvmetcp_glbl_queue_entry { + struct regpair cq_pbl_addr; + struct regpair reserved; +}; + +#endif /* __NVMETCP_COMMON__ */ diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 68d17a4fbf20..850b98991670 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -542,6 +542,22 @@ struct qed_iscsi_pf_params { u8 bdq_pbl_num_entries[3]; }; +struct qed_nvmetcp_pf_params { + u64 glbl_q_params_addr; + u16 cq_num_entries; + u16 num_cons; + u16 num_tasks; + u8 num_sq_pages_in_ring; + u8 num_r2tq_pages_in_ring; + u8 num_uhq_pages_in_ring; + u8 num_queues; + u8 gl_rq_pi; + u8 gl_cmd_pi; + u8 debug_mode; + u8 ll2_ooo_queue_id; + u16 min_rto; +}; + struct qed_rdma_pf_params { /* Supplied to QED during resource allocation (may affect the ILT and * the doorbell BAR). @@ -560,6 +576,7 @@ struct qed_pf_params { struct qed_eth_pf_params eth_pf_params; struct qed_fcoe_pf_params fcoe_pf_params; struct qed_iscsi_pf_params iscsi_pf_params; + struct qed_nvmetcp_pf_params nvmetcp_pf_params; struct qed_rdma_pf_params rdma_pf_params; }; @@ -662,6 +679,7 @@ enum qed_sb_type { enum qed_protocol { QED_PROTOCOL_ETH, QED_PROTOCOL_ISCSI, + QED_PROTOCOL_NVMETCP = QED_PROTOCOL_ISCSI, QED_PROTOCOL_FCOE, }; diff --git a/include/linux/qed/qed_nvmetcp_if.h b/include/linux/qed/qed_nvmetcp_if.h new file mode 100644 index 000000000000..76868bdf0883 --- /dev/null +++ b/include/linux/qed/qed_nvmetcp_if.h @@ -0,0 +1,71 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ +/* Copyright 2021 Marvell. All rights reserved. */ + +#ifndef _QED_NVMETCP_IF_H +#define _QED_NVMETCP_IF_H +#include +#include + +#define QED_NVMETCP_MAX_IO_SIZE 0x800000 + +typedef int (*nvmetcp_event_cb_t) (void *context, + u8 fw_event_code, void *fw_handle); + +struct qed_dev_nvmetcp_info { + struct qed_dev_info common; + u8 port_id; /* Physical port */ + u8 num_cqs; +}; + +#define MAX_TID_BLOCKS_NVMETCP (512) +struct qed_nvmetcp_tid { + u32 size; /* In bytes per task */ + u32 num_tids_per_block; + u8 *blocks[MAX_TID_BLOCKS_NVMETCP]; +}; + +struct qed_nvmetcp_cb_ops { + struct qed_common_cb_ops common; +}; + +/** + * struct qed_nvmetcp_ops - qed NVMeTCP operations. + * @common: common operations pointer + * @ll2: light L2 operations pointer + * @fill_dev_info: fills NVMeTCP specific information + * @param cdev + * @param info + * @return 0 on success, otherwise error value. + * @register_ops: register nvmetcp operations + * @param cdev + * @param ops - specified using qed_nvmetcp_cb_ops + * @param cookie - driver private + * @start: nvmetcp in FW + * @param cdev + * @param tasks - qed will fill information about tasks + * return 0 on success, otherwise error value. + * @stop: nvmetcp in FW + * @param cdev + * return 0 on success, otherwise error value. + */ +struct qed_nvmetcp_ops { + const struct qed_common_ops *common; + + const struct qed_ll2_ops *ll2; + + int (*fill_dev_info)(struct qed_dev *cdev, + struct qed_dev_nvmetcp_info *info); + + void (*register_ops)(struct qed_dev *cdev, + struct qed_nvmetcp_cb_ops *ops, void *cookie); + + int (*start)(struct qed_dev *cdev, + struct qed_nvmetcp_tid *tasks, + void *event_context, nvmetcp_event_cb_t async_event_cb); + + int (*stop)(struct qed_dev *cdev); +}; + +const struct qed_nvmetcp_ops *qed_get_nvmetcp_ops(void); +void qed_put_nvmetcp_ops(void); +#endif -- cgit v1.2.3 From 76684ab8f4f95394df6a752cee37b197b4c8732b Mon Sep 17 00:00:00 2001 From: Shai Malin Date: Wed, 2 Jun 2021 20:16:51 +0300 Subject: qed: Add NVMeTCP Offload Connection Level FW and HW HSI This patch introduces the NVMeTCP HSI and HSI functionality in order to initialize and interact with the HW device as part of the connection level HSI. This includes: - Connection offload: offload a TCP connection to the FW. - Connection update: update the ICReq-ICResp params - Connection clear SQ: outstanding IOs FW flush. - Connection termination: terminate the TCP connection and flush the FW. Acked-by: Igor Russkikh Signed-off-by: Prabhakar Kushwaha Signed-off-by: Omkar Kulkarni Signed-off-by: Shai Malin Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Reviewed-by: Hannes Reinecke Signed-off-by: David S. Miller --- include/linux/qed/nvmetcp_common.h | 143 +++++++++++++++++++++++++++++++++++++ include/linux/qed/qed_nvmetcp_if.h | 94 ++++++++++++++++++++++++ 2 files changed, 237 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/nvmetcp_common.h b/include/linux/qed/nvmetcp_common.h index e9ccfc07041d..c8836b71b866 100644 --- a/include/linux/qed/nvmetcp_common.h +++ b/include/linux/qed/nvmetcp_common.h @@ -6,6 +6,8 @@ #include "tcp_common.h" +#define NVMETCP_SLOW_PATH_LAYER_CODE (6) + /* NVMeTCP firmware function init parameters */ struct nvmetcp_spe_func_init { __le16 half_way_close_timeout; @@ -43,6 +45,10 @@ enum nvmetcp_ramrod_cmd_id { NVMETCP_RAMROD_CMD_ID_UNUSED = 0, NVMETCP_RAMROD_CMD_ID_INIT_FUNC = 1, NVMETCP_RAMROD_CMD_ID_DESTROY_FUNC = 2, + NVMETCP_RAMROD_CMD_ID_OFFLOAD_CONN = 3, + NVMETCP_RAMROD_CMD_ID_UPDATE_CONN = 4, + NVMETCP_RAMROD_CMD_ID_TERMINATION_CONN = 5, + NVMETCP_RAMROD_CMD_ID_CLEAR_SQ = 6, MAX_NVMETCP_RAMROD_CMD_ID }; @@ -51,4 +57,141 @@ struct nvmetcp_glbl_queue_entry { struct regpair reserved; }; +/* NVMeTCP conn level EQEs */ +enum nvmetcp_eqe_opcode { + NVMETCP_EVENT_TYPE_INIT_FUNC = 0, /* Response after init Ramrod */ + NVMETCP_EVENT_TYPE_DESTROY_FUNC, /* Response after destroy Ramrod */ + NVMETCP_EVENT_TYPE_OFFLOAD_CONN,/* Response after option 2 offload Ramrod */ + NVMETCP_EVENT_TYPE_UPDATE_CONN, /* Response after update Ramrod */ + NVMETCP_EVENT_TYPE_CLEAR_SQ, /* Response after clear sq Ramrod */ + NVMETCP_EVENT_TYPE_TERMINATE_CONN, /* Response after termination Ramrod */ + NVMETCP_EVENT_TYPE_RESERVED0, + NVMETCP_EVENT_TYPE_RESERVED1, + NVMETCP_EVENT_TYPE_ASYN_CONNECT_COMPLETE, /* Connect completed (A-syn EQE) */ + NVMETCP_EVENT_TYPE_ASYN_TERMINATE_DONE, /* Termination completed (A-syn EQE) */ + NVMETCP_EVENT_TYPE_START_OF_ERROR_TYPES = 10, /* Separate EQs from err EQs */ + NVMETCP_EVENT_TYPE_ASYN_ABORT_RCVD, /* TCP RST packet receive (A-syn EQE) */ + NVMETCP_EVENT_TYPE_ASYN_CLOSE_RCVD, /* TCP FIN packet receive (A-syn EQE) */ + NVMETCP_EVENT_TYPE_ASYN_SYN_RCVD, /* TCP SYN+ACK packet receive (A-syn EQE) */ + NVMETCP_EVENT_TYPE_ASYN_MAX_RT_TIME, /* TCP max retransmit time (A-syn EQE) */ + NVMETCP_EVENT_TYPE_ASYN_MAX_RT_CNT, /* TCP max retransmit count (A-syn EQE) */ + NVMETCP_EVENT_TYPE_ASYN_MAX_KA_PROBES_CNT, /* TCP ka probes count (A-syn EQE) */ + NVMETCP_EVENT_TYPE_ASYN_FIN_WAIT2, /* TCP fin wait 2 (A-syn EQE) */ + NVMETCP_EVENT_TYPE_NVMETCP_CONN_ERROR, /* NVMeTCP error response (A-syn EQE) */ + NVMETCP_EVENT_TYPE_TCP_CONN_ERROR, /* NVMeTCP error - tcp error (A-syn EQE) */ + MAX_NVMETCP_EQE_OPCODE +}; + +struct nvmetcp_conn_offload_section { + struct regpair cccid_itid_table_addr; /* CCCID to iTID table address */ + __le16 cccid_max_range; /* CCCID max value - used for validation */ + __le16 reserved[3]; +}; + +/* NVMe TCP connection offload params passed by driver to FW in NVMeTCP offload ramrod */ +struct nvmetcp_conn_offload_params { + struct regpair sq_pbl_addr; + struct regpair r2tq_pbl_addr; + struct regpair xhq_pbl_addr; + struct regpair uhq_pbl_addr; + __le16 physical_q0; + __le16 physical_q1; + u8 flags; +#define NVMETCP_CONN_OFFLOAD_PARAMS_TCP_ON_CHIP_1B_MASK 0x1 +#define NVMETCP_CONN_OFFLOAD_PARAMS_TCP_ON_CHIP_1B_SHIFT 0 +#define NVMETCP_CONN_OFFLOAD_PARAMS_TARGET_MODE_MASK 0x1 +#define NVMETCP_CONN_OFFLOAD_PARAMS_TARGET_MODE_SHIFT 1 +#define NVMETCP_CONN_OFFLOAD_PARAMS_RESTRICTED_MODE_MASK 0x1 +#define NVMETCP_CONN_OFFLOAD_PARAMS_RESTRICTED_MODE_SHIFT 2 +#define NVMETCP_CONN_OFFLOAD_PARAMS_NVMETCP_MODE_MASK 0x1 +#define NVMETCP_CONN_OFFLOAD_PARAMS_NVMETCP_MODE_SHIFT 3 +#define NVMETCP_CONN_OFFLOAD_PARAMS_RESERVED1_MASK 0xF +#define NVMETCP_CONN_OFFLOAD_PARAMS_RESERVED1_SHIFT 4 + u8 default_cq; + __le16 reserved0; + __le32 reserved1; + __le32 initial_ack; + + struct nvmetcp_conn_offload_section nvmetcp; /* NVMe/TCP section */ +}; + +/* NVMe TCP and TCP connection offload params passed by driver to FW in NVMeTCP offload ramrod. */ +struct nvmetcp_spe_conn_offload { + __le16 reserved; + __le16 conn_id; + __le32 fw_cid; + struct nvmetcp_conn_offload_params nvmetcp; + struct tcp_offload_params_opt2 tcp; +}; + +/* NVMeTCP connection update params passed by driver to FW in NVMETCP update ramrod. */ +struct nvmetcp_conn_update_ramrod_params { + __le16 reserved0; + __le16 conn_id; + __le32 reserved1; + u8 flags; +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_HD_EN_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_HD_EN_SHIFT 0 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_DD_EN_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_DD_EN_SHIFT 1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED0_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED0_SHIFT 2 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_DATA_SHIFT 3 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED2_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED2_SHIFT 4 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED3_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED3_SHIFT 5 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED4_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED4_SHIFT 6 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED5_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED5_SHIFT 7 + u8 reserved3[3]; + __le32 max_seq_size; + __le32 max_send_pdu_length; + __le32 max_recv_pdu_length; + __le32 first_seq_length; + __le32 reserved4[5]; +}; + +/* NVMeTCP connection termination request */ +struct nvmetcp_spe_conn_termination { + __le16 reserved0; + __le16 conn_id; + __le32 reserved1; + u8 abortive; + u8 reserved2[7]; + struct regpair reserved3; + struct regpair reserved4; +}; + +struct nvmetcp_dif_flags { + u8 flags; +}; + +enum nvmetcp_wqe_type { + NVMETCP_WQE_TYPE_NORMAL, + NVMETCP_WQE_TYPE_TASK_CLEANUP, + NVMETCP_WQE_TYPE_MIDDLE_PATH, + NVMETCP_WQE_TYPE_IC, + MAX_NVMETCP_WQE_TYPE +}; + +struct nvmetcp_wqe { + __le16 task_id; + u8 flags; +#define NVMETCP_WQE_WQE_TYPE_MASK 0x7 /* [use nvmetcp_wqe_type] */ +#define NVMETCP_WQE_WQE_TYPE_SHIFT 0 +#define NVMETCP_WQE_NUM_SGES_MASK 0xF +#define NVMETCP_WQE_NUM_SGES_SHIFT 3 +#define NVMETCP_WQE_RESPONSE_MASK 0x1 +#define NVMETCP_WQE_RESPONSE_SHIFT 7 + struct nvmetcp_dif_flags prot_flags; + __le32 contlen_cdbsize; +#define NVMETCP_WQE_CONT_LEN_MASK 0xFFFFFF +#define NVMETCP_WQE_CONT_LEN_SHIFT 0 +#define NVMETCP_WQE_CDB_SIZE_OR_NVMETCP_CMD_MASK 0xFF +#define NVMETCP_WQE_CDB_SIZE_OR_NVMETCP_CMD_SHIFT 24 +}; + #endif /* __NVMETCP_COMMON__ */ diff --git a/include/linux/qed/qed_nvmetcp_if.h b/include/linux/qed/qed_nvmetcp_if.h index 76868bdf0883..5baf1c5ce798 100644 --- a/include/linux/qed/qed_nvmetcp_if.h +++ b/include/linux/qed/qed_nvmetcp_if.h @@ -24,6 +24,50 @@ struct qed_nvmetcp_tid { u8 *blocks[MAX_TID_BLOCKS_NVMETCP]; }; +struct qed_nvmetcp_id_params { + u8 mac[ETH_ALEN]; + u32 ip[4]; + u16 port; +}; + +struct qed_nvmetcp_params_offload { + /* FW initializations */ + dma_addr_t sq_pbl_addr; + dma_addr_t nvmetcp_cccid_itid_table_addr; + u16 nvmetcp_cccid_max_range; + u8 default_cq; + + /* Networking and TCP stack initializations */ + struct qed_nvmetcp_id_params src; + struct qed_nvmetcp_id_params dst; + u32 ka_timeout; + u32 ka_interval; + u32 max_rt_time; + u32 cwnd; + u16 mss; + u16 vlan_id; + bool timestamp_en; + bool delayed_ack_en; + bool tcp_keep_alive_en; + bool ecn_en; + u8 ip_version; + u8 ka_max_probe_cnt; + u8 ttl; + u8 tos_or_tc; + u8 rcv_wnd_scale; +}; + +struct qed_nvmetcp_params_update { + u32 max_io_size; + u32 max_recv_pdu_length; + u32 max_send_pdu_length; + + /* Placeholder: pfv, cpda, hpda */ + + bool hdr_digest_en; + bool data_digest_en; +}; + struct qed_nvmetcp_cb_ops { struct qed_common_cb_ops common; }; @@ -47,6 +91,38 @@ struct qed_nvmetcp_cb_ops { * @stop: nvmetcp in FW * @param cdev * return 0 on success, otherwise error value. + * @acquire_conn: acquire a new nvmetcp connection + * @param cdev + * @param handle - qed will fill handle that should be + * used henceforth as identifier of the + * connection. + * @param p_doorbell - qed will fill the address of the + * doorbell. + * @return 0 on sucesss, otherwise error value. + * @release_conn: release a previously acquired nvmetcp connection + * @param cdev + * @param handle - the connection handle. + * @return 0 on success, otherwise error value. + * @offload_conn: configures an offloaded connection + * @param cdev + * @param handle - the connection handle. + * @param conn_info - the configuration to use for the + * offload. + * @return 0 on success, otherwise error value. + * @update_conn: updates an offloaded connection + * @param cdev + * @param handle - the connection handle. + * @param conn_info - the configuration to use for the + * offload. + * @return 0 on success, otherwise error value. + * @destroy_conn: stops an offloaded connection + * @param cdev + * @param handle - the connection handle. + * @return 0 on success, otherwise error value. + * @clear_sq: clear all task in sq + * @param cdev + * @param handle - the connection handle. + * @return 0 on success, otherwise error value. */ struct qed_nvmetcp_ops { const struct qed_common_ops *common; @@ -64,6 +140,24 @@ struct qed_nvmetcp_ops { void *event_context, nvmetcp_event_cb_t async_event_cb); int (*stop)(struct qed_dev *cdev); + + int (*acquire_conn)(struct qed_dev *cdev, + u32 *handle, + u32 *fw_cid, void __iomem **p_doorbell); + + int (*release_conn)(struct qed_dev *cdev, u32 handle); + + int (*offload_conn)(struct qed_dev *cdev, + u32 handle, + struct qed_nvmetcp_params_offload *conn_info); + + int (*update_conn)(struct qed_dev *cdev, + u32 handle, + struct qed_nvmetcp_params_update *conn_info); + + int (*destroy_conn)(struct qed_dev *cdev, u32 handle, u8 abrt_conn); + + int (*clear_sq)(struct qed_dev *cdev, u32 handle); }; const struct qed_nvmetcp_ops *qed_get_nvmetcp_ops(void); -- cgit v1.2.3 From 203d136e8958a7c65834601f669bdd0fcaa6fcbd Mon Sep 17 00:00:00 2001 From: Prabhakar Kushwaha Date: Wed, 2 Jun 2021 20:16:52 +0300 Subject: qed: Add support of HW filter block This patch introduces the functionality of HW filter block. It adds and removes filters based on source and target TCP port. It also add functionality to clear all filters at once. Acked-by: Igor Russkikh Signed-off-by: Prabhakar Kushwaha Signed-off-by: Omkar Kulkarni Signed-off-by: Shai Malin Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Reviewed-by: Hannes Reinecke Signed-off-by: David S. Miller --- include/linux/qed/qed_nvmetcp_if.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_nvmetcp_if.h b/include/linux/qed/qed_nvmetcp_if.h index 5baf1c5ce798..5180edad24e5 100644 --- a/include/linux/qed/qed_nvmetcp_if.h +++ b/include/linux/qed/qed_nvmetcp_if.h @@ -123,6 +123,20 @@ struct qed_nvmetcp_cb_ops { * @param cdev * @param handle - the connection handle. * @return 0 on success, otherwise error value. + * @add_src_tcp_port_filter: Add source tcp port filter + * @param cdev + * @param src_port + * @remove_src_tcp_port_filter: Remove source tcp port filter + * @param cdev + * @param src_port + * @add_dst_tcp_port_filter: Add destination tcp port filter + * @param cdev + * @param dest_port + * @remove_dst_tcp_port_filter: Remove destination tcp port filter + * @param cdev + * @param dest_port + * @clear_all_filters: Clear all filters. + * @param cdev */ struct qed_nvmetcp_ops { const struct qed_common_ops *common; @@ -158,6 +172,16 @@ struct qed_nvmetcp_ops { int (*destroy_conn)(struct qed_dev *cdev, u32 handle, u8 abrt_conn); int (*clear_sq)(struct qed_dev *cdev, u32 handle); + + int (*add_src_tcp_port_filter)(struct qed_dev *cdev, u16 src_port); + + void (*remove_src_tcp_port_filter)(struct qed_dev *cdev, u16 src_port); + + int (*add_dst_tcp_port_filter)(struct qed_dev *cdev, u16 dest_port); + + void (*remove_dst_tcp_port_filter)(struct qed_dev *cdev, u16 dest_port); + + void (*clear_all_filters)(struct qed_dev *cdev); }; const struct qed_nvmetcp_ops *qed_get_nvmetcp_ops(void); -- cgit v1.2.3 From ab47bdfd2e2e9670172a737d12ebfc94bf9d299d Mon Sep 17 00:00:00 2001 From: Shai Malin Date: Wed, 2 Jun 2021 20:16:53 +0300 Subject: qed: Add NVMeTCP Offload IO Level FW and HW HSI This patch introduces the NVMeTCP Offload FW and HW HSI in order to initialize the IO level configuration into a per IO HW resource ("task") as part of the IO path flow. Acked-by: Igor Russkikh Signed-off-by: Prabhakar Kushwaha Signed-off-by: Omkar Kulkarni Signed-off-by: Shai Malin Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Reviewed-by: Hannes Reinecke Signed-off-by: David S. Miller --- include/linux/qed/nvmetcp_common.h | 335 ++++++++++++++++++++++++++++++++++++- include/linux/qed/qed_nvmetcp_if.h | 31 ++++ 2 files changed, 365 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/qed/nvmetcp_common.h b/include/linux/qed/nvmetcp_common.h index c8836b71b866..ad745a9c2264 100644 --- a/include/linux/qed/nvmetcp_common.h +++ b/include/linux/qed/nvmetcp_common.h @@ -7,6 +7,7 @@ #include "tcp_common.h" #define NVMETCP_SLOW_PATH_LAYER_CODE (6) +#define NVMETCP_WQE_NUM_SGES_SLOWIO (0xf) /* NVMeTCP firmware function init parameters */ struct nvmetcp_spe_func_init { @@ -194,4 +195,336 @@ struct nvmetcp_wqe { #define NVMETCP_WQE_CDB_SIZE_OR_NVMETCP_CMD_SHIFT 24 }; -#endif /* __NVMETCP_COMMON__ */ +struct nvmetcp_host_cccid_itid_entry { + __le16 itid; +}; + +struct nvmetcp_connect_done_results { + __le16 icid; + __le16 conn_id; + struct tcp_ulp_connect_done_params params; +}; + +struct nvmetcp_eqe_data { + __le16 icid; + __le16 conn_id; + __le16 reserved; + u8 error_code; + u8 error_pdu_opcode_reserved; +#define NVMETCP_EQE_DATA_ERROR_PDU_OPCODE_MASK 0x3F +#define NVMETCP_EQE_DATA_ERROR_PDU_OPCODE_SHIFT 0 +#define NVMETCP_EQE_DATA_ERROR_PDU_OPCODE_VALID_MASK 0x1 +#define NVMETCP_EQE_DATA_ERROR_PDU_OPCODE_VALID_SHIFT 6 +#define NVMETCP_EQE_DATA_RESERVED0_MASK 0x1 +#define NVMETCP_EQE_DATA_RESERVED0_SHIFT 7 +}; + +enum nvmetcp_task_type { + NVMETCP_TASK_TYPE_HOST_WRITE, + NVMETCP_TASK_TYPE_HOST_READ, + NVMETCP_TASK_TYPE_INIT_CONN_REQUEST, + NVMETCP_TASK_TYPE_RESERVED0, + NVMETCP_TASK_TYPE_CLEANUP, + NVMETCP_TASK_TYPE_HOST_READ_NO_CQE, + MAX_NVMETCP_TASK_TYPE +}; + +struct nvmetcp_db_data { + u8 params; +#define NVMETCP_DB_DATA_DEST_MASK 0x3 /* destination of doorbell (use enum db_dest) */ +#define NVMETCP_DB_DATA_DEST_SHIFT 0 +#define NVMETCP_DB_DATA_AGG_CMD_MASK 0x3 /* aggregative command to CM (use enum db_agg_cmd_sel) */ +#define NVMETCP_DB_DATA_AGG_CMD_SHIFT 2 +#define NVMETCP_DB_DATA_BYPASS_EN_MASK 0x1 /* enable QM bypass */ +#define NVMETCP_DB_DATA_BYPASS_EN_SHIFT 4 +#define NVMETCP_DB_DATA_RESERVED_MASK 0x1 +#define NVMETCP_DB_DATA_RESERVED_SHIFT 5 +#define NVMETCP_DB_DATA_AGG_VAL_SEL_MASK 0x3 /* aggregative value selection */ +#define NVMETCP_DB_DATA_AGG_VAL_SEL_SHIFT 6 + u8 agg_flags; /* bit for every DQ counter flags in CM context that DQ can increment */ + __le16 sq_prod; +}; + +struct nvmetcp_fw_nvmf_cqe { + __le32 reserved[4]; +}; + +struct nvmetcp_icresp_mdata { + u8 digest; + u8 cpda; + __le16 pfv; + __le32 maxdata; + __le16 rsvd[4]; +}; + +union nvmetcp_fw_cqe_data { + struct nvmetcp_fw_nvmf_cqe nvme_cqe; + struct nvmetcp_icresp_mdata icresp_mdata; +}; + +struct nvmetcp_fw_cqe { + __le16 conn_id; + u8 cqe_type; + u8 cqe_error_status_bits; +#define CQE_ERROR_BITMAP_DIF_ERR_BITS_MASK 0x7 +#define CQE_ERROR_BITMAP_DIF_ERR_BITS_SHIFT 0 +#define CQE_ERROR_BITMAP_DATA_DIGEST_ERR_MASK 0x1 +#define CQE_ERROR_BITMAP_DATA_DIGEST_ERR_SHIFT 3 +#define CQE_ERROR_BITMAP_RCV_ON_INVALID_CONN_MASK 0x1 +#define CQE_ERROR_BITMAP_RCV_ON_INVALID_CONN_SHIFT 4 + __le16 itid; + u8 task_type; + u8 fw_dbg_field; + u8 caused_conn_err; + u8 reserved0[3]; + __le32 reserved1; + union nvmetcp_fw_cqe_data cqe_data; + struct regpair task_opaque; + __le32 reserved[6]; +}; + +enum nvmetcp_fw_cqes_type { + NVMETCP_FW_CQE_TYPE_NORMAL = 1, + NVMETCP_FW_CQE_TYPE_RESERVED0, + NVMETCP_FW_CQE_TYPE_RESERVED1, + NVMETCP_FW_CQE_TYPE_CLEANUP, + NVMETCP_FW_CQE_TYPE_DUMMY, + MAX_NVMETCP_FW_CQES_TYPE +}; + +struct ystorm_nvmetcp_task_state { + struct scsi_cached_sges data_desc; + struct scsi_sgl_params sgl_params; + __le32 resrved0; + __le32 buffer_offset; + __le16 cccid; + struct nvmetcp_dif_flags dif_flags; + u8 flags; +#define YSTORM_NVMETCP_TASK_STATE_LOCAL_COMP_MASK 0x1 +#define YSTORM_NVMETCP_TASK_STATE_LOCAL_COMP_SHIFT 0 +#define YSTORM_NVMETCP_TASK_STATE_SLOW_IO_MASK 0x1 +#define YSTORM_NVMETCP_TASK_STATE_SLOW_IO_SHIFT 1 +#define YSTORM_NVMETCP_TASK_STATE_SET_DIF_OFFSET_MASK 0x1 +#define YSTORM_NVMETCP_TASK_STATE_SET_DIF_OFFSET_SHIFT 2 +#define YSTORM_NVMETCP_TASK_STATE_SEND_W_RSP_MASK 0x1 +#define YSTORM_NVMETCP_TASK_STATE_SEND_W_RSP_SHIFT 3 +}; + +struct ystorm_nvmetcp_task_rxmit_opt { + __le32 reserved[4]; +}; + +struct nvmetcp_task_hdr { + __le32 reg[18]; +}; + +struct nvmetcp_task_hdr_aligned { + struct nvmetcp_task_hdr task_hdr; + __le32 reserved[2]; /* HSI_COMMENT: Align to QREG */ +}; + +struct e5_tdif_task_context { + __le32 reserved[16]; +}; + +struct e5_rdif_task_context { + __le32 reserved[12]; +}; + +struct ystorm_nvmetcp_task_st_ctx { + struct ystorm_nvmetcp_task_state state; + struct ystorm_nvmetcp_task_rxmit_opt rxmit_opt; + struct nvmetcp_task_hdr_aligned pdu_hdr; +}; + +struct mstorm_nvmetcp_task_st_ctx { + struct scsi_cached_sges data_desc; + struct scsi_sgl_params sgl_params; + __le32 rem_task_size; + __le32 data_buffer_offset; + u8 task_type; + struct nvmetcp_dif_flags dif_flags; + __le16 dif_task_icid; + struct regpair reserved0; + __le32 expected_itt; + __le32 reserved1; +}; + +struct ustorm_nvmetcp_task_st_ctx { + __le32 rem_rcv_len; + __le32 exp_data_transfer_len; + __le32 exp_data_sn; + struct regpair reserved0; + __le32 reg1_map; +#define REG1_NUM_SGES_MASK 0xF +#define REG1_NUM_SGES_SHIFT 0 +#define REG1_RESERVED1_MASK 0xFFFFFFF +#define REG1_RESERVED1_SHIFT 4 + u8 flags2; +#define USTORM_NVMETCP_TASK_ST_CTX_AHS_EXIST_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_AHS_EXIST_SHIFT 0 +#define USTORM_NVMETCP_TASK_ST_CTX_RESERVED1_MASK 0x7F +#define USTORM_NVMETCP_TASK_ST_CTX_RESERVED1_SHIFT 1 + struct nvmetcp_dif_flags dif_flags; + __le16 reserved3; + __le16 tqe_opaque[2]; + __le32 reserved5; + __le32 nvme_tcp_opaque_lo; + __le32 nvme_tcp_opaque_hi; + u8 task_type; + u8 error_flags; +#define USTORM_NVMETCP_TASK_ST_CTX_DATA_DIGEST_ERROR_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_DATA_DIGEST_ERROR_SHIFT 0 +#define USTORM_NVMETCP_TASK_ST_CTX_DATA_TRUNCATED_ERROR_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_DATA_TRUNCATED_ERROR_SHIFT 1 +#define USTORM_NVMETCP_TASK_ST_CTX_UNDER_RUN_ERROR_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_UNDER_RUN_ERROR_SHIFT 2 +#define USTORM_NVMETCP_TASK_ST_CTX_NVME_TCP_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_NVME_TCP_SHIFT 3 + u8 flags; +#define USTORM_NVMETCP_TASK_ST_CTX_CQE_WRITE_MASK 0x3 +#define USTORM_NVMETCP_TASK_ST_CTX_CQE_WRITE_SHIFT 0 +#define USTORM_NVMETCP_TASK_ST_CTX_LOCAL_COMP_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_LOCAL_COMP_SHIFT 2 +#define USTORM_NVMETCP_TASK_ST_CTX_Q0_R2TQE_WRITE_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_Q0_R2TQE_WRITE_SHIFT 3 +#define USTORM_NVMETCP_TASK_ST_CTX_TOTAL_DATA_ACKED_DONE_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_TOTAL_DATA_ACKED_DONE_SHIFT 4 +#define USTORM_NVMETCP_TASK_ST_CTX_HQ_SCANNED_DONE_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_HQ_SCANNED_DONE_SHIFT 5 +#define USTORM_NVMETCP_TASK_ST_CTX_R2T2RECV_DONE_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_R2T2RECV_DONE_SHIFT 6 + u8 cq_rss_number; +}; + +struct e5_ystorm_nvmetcp_task_ag_ctx { + u8 reserved /* cdu_validation */; + u8 byte1 /* state_and_core_id */; + __le16 word0 /* icid */; + u8 flags0; + u8 flags1; + u8 flags2; + u8 flags3; + __le32 TTT; + u8 byte2; + u8 byte3; + u8 byte4; + u8 e4_reserved7; +}; + +struct e5_mstorm_nvmetcp_task_ag_ctx { + u8 cdu_validation; + u8 byte1; + __le16 task_cid; + u8 flags0; +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CONNECTION_TYPE_MASK 0xF +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_MASK 0x1 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_SHIFT 5 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_VALID_MASK 0x1 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_VALID_SHIFT 6 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_TASK_CLEANUP_FLAG_MASK 0x1 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_TASK_CLEANUP_FLAG_SHIFT 7 + u8 flags1; +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_TASK_CLEANUP_CF_MASK 0x3 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_TASK_CLEANUP_CF_SHIFT 0 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CF1_MASK 0x3 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CF1_SHIFT 2 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CF2_MASK 0x3 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CF2_SHIFT 4 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_TASK_CLEANUP_CF_EN_MASK 0x1 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_TASK_CLEANUP_CF_EN_SHIFT 6 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CF1EN_MASK 0x1 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CF1EN_SHIFT 7 + u8 flags2; + u8 flags3; + __le32 reg0; + u8 byte2; + u8 byte3; + u8 byte4; + u8 e4_reserved7; +}; + +struct e5_ustorm_nvmetcp_task_ag_ctx { + u8 reserved; + u8 state_and_core_id; + __le16 icid; + u8 flags0; +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CONNECTION_TYPE_MASK 0xF +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_SHIFT 5 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_HQ_SCANNED_CF_MASK 0x3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_HQ_SCANNED_CF_SHIFT 6 + u8 flags1; +#define E5_USTORM_NVMETCP_TASK_AG_CTX_RESERVED1_MASK 0x3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_RESERVED1_SHIFT 0 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_R2T2RECV_MASK 0x3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_R2T2RECV_SHIFT 2 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CF3_MASK 0x3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CF3_SHIFT 4 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_CF_MASK 0x3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_CF_SHIFT 6 + u8 flags2; +#define E5_USTORM_NVMETCP_TASK_AG_CTX_HQ_SCANNED_CF_EN_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_HQ_SCANNED_CF_EN_SHIFT 0 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DISABLE_DATA_ACKED_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DISABLE_DATA_ACKED_SHIFT 1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_R2T2RECV_EN_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_R2T2RECV_EN_SHIFT 2 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CF3EN_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CF3EN_SHIFT 3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_CF_EN_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_CF_EN_SHIFT 4 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CMP_DATA_TOTAL_EXP_EN_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CMP_DATA_TOTAL_EXP_EN_SHIFT 5 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_RULE1EN_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_RULE1EN_SHIFT 6 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CMP_CONT_RCV_EXP_EN_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CMP_CONT_RCV_EXP_EN_SHIFT 7 + u8 flags3; + u8 flags4; +#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED5_MASK 0x3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED5_SHIFT 0 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED6_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED6_SHIFT 2 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED7_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED7_SHIFT 3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_TYPE_MASK 0xF +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_TYPE_SHIFT 4 + u8 byte2; + u8 byte3; + u8 e4_reserved8; + __le32 dif_err_intervals; + __le32 dif_error_1st_interval; + __le32 rcv_cont_len; + __le32 exp_cont_len; + __le32 total_data_acked; + __le32 exp_data_acked; + __le16 word1; + __le16 next_tid; + __le32 hdr_residual_count; + __le32 exp_r2t_sn; +}; + +struct e5_nvmetcp_task_context { + struct ystorm_nvmetcp_task_st_ctx ystorm_st_context; + struct e5_ystorm_nvmetcp_task_ag_ctx ystorm_ag_context; + struct regpair ystorm_ag_padding[2]; + struct e5_tdif_task_context tdif_context; + struct e5_mstorm_nvmetcp_task_ag_ctx mstorm_ag_context; + struct regpair mstorm_ag_padding[2]; + struct e5_ustorm_nvmetcp_task_ag_ctx ustorm_ag_context; + struct regpair ustorm_ag_padding[2]; + struct mstorm_nvmetcp_task_st_ctx mstorm_st_context; + struct regpair mstorm_st_padding[2]; + struct ustorm_nvmetcp_task_st_ctx ustorm_st_context; + struct regpair ustorm_st_padding[2]; + struct e5_rdif_task_context rdif_context; +}; + +#endif /* __NVMETCP_COMMON__*/ diff --git a/include/linux/qed/qed_nvmetcp_if.h b/include/linux/qed/qed_nvmetcp_if.h index 5180edad24e5..606427ebb63c 100644 --- a/include/linux/qed/qed_nvmetcp_if.h +++ b/include/linux/qed/qed_nvmetcp_if.h @@ -5,6 +5,8 @@ #define _QED_NVMETCP_IF_H #include #include +#include +#include #define QED_NVMETCP_MAX_IO_SIZE 0x800000 @@ -72,6 +74,35 @@ struct qed_nvmetcp_cb_ops { struct qed_common_cb_ops common; }; +struct nvmetcp_sge { + struct regpair sge_addr; /* SGE address */ + __le32 sge_len; /* SGE length */ + __le32 reserved; +}; + +/* IO path HSI function SGL params */ +struct storage_sgl_task_params { + struct nvmetcp_sge *sgl; + struct regpair sgl_phys_addr; + u32 total_buffer_size; + u16 num_sges; + bool small_mid_sge; +}; + +/* IO path HSI function FW task context params */ +struct nvmetcp_task_params { + void *context; /* Output parameter - set/filled by the HSI function */ + struct nvmetcp_wqe *sqe; + u32 tx_io_size; /* in bytes (Without DIF, if exists) */ + u32 rx_io_size; /* in bytes (Without DIF, if exists) */ + u16 conn_icid; + u16 itid; + struct regpair opq; /* qedn_task_ctx address */ + u16 host_cccid; + u8 cq_rss_number; + bool send_write_incapsule; +}; + /** * struct qed_nvmetcp_ops - qed NVMeTCP operations. * @common: common operations pointer -- cgit v1.2.3 From 826da4861430898495fa49f072335e795e8adfd3 Mon Sep 17 00:00:00 2001 From: Shai Malin Date: Wed, 2 Jun 2021 20:16:54 +0300 Subject: qed: Add NVMeTCP Offload IO Level FW Initializations This patch introduces the NVMeTCP FW initializations which is used to initialize the IO level configuration into a per IO HW resource ("task") as part of the IO path flow. This includes: - Write IO FW initialization - Read IO FW initialization. - IC-Req and IC-Resp FW exchange. - FW Cleanup flow (Flush IO). Acked-by: Igor Russkikh Signed-off-by: Prabhakar Kushwaha Signed-off-by: Omkar Kulkarni Signed-off-by: Shai Malin Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Reviewed-by: Hannes Reinecke Signed-off-by: David S. Miller --- include/linux/qed/nvmetcp_common.h | 1 + include/linux/qed/qed_nvmetcp_if.h | 20 ++++++++++++++++++++ 2 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/nvmetcp_common.h b/include/linux/qed/nvmetcp_common.h index ad745a9c2264..5a2ab0606308 100644 --- a/include/linux/qed/nvmetcp_common.h +++ b/include/linux/qed/nvmetcp_common.h @@ -5,6 +5,7 @@ #define __NVMETCP_COMMON__ #include "tcp_common.h" +#include #define NVMETCP_SLOW_PATH_LAYER_CODE (6) #define NVMETCP_WQE_NUM_SGES_SLOWIO (0xf) diff --git a/include/linux/qed/qed_nvmetcp_if.h b/include/linux/qed/qed_nvmetcp_if.h index 606427ebb63c..14671bc19ed1 100644 --- a/include/linux/qed/qed_nvmetcp_if.h +++ b/include/linux/qed/qed_nvmetcp_if.h @@ -9,6 +9,9 @@ #include #define QED_NVMETCP_MAX_IO_SIZE 0x800000 +#define QED_NVMETCP_CMN_HDR_SIZE (sizeof(struct nvme_tcp_hdr)) +#define QED_NVMETCP_CMD_HDR_SIZE (sizeof(struct nvme_tcp_cmd_pdu)) +#define QED_NVMETCP_NON_IO_HDR_SIZE ((QED_NVMETCP_CMN_HDR_SIZE + 16)) typedef int (*nvmetcp_event_cb_t) (void *context, u8 fw_event_code, void *fw_handle); @@ -213,6 +216,23 @@ struct qed_nvmetcp_ops { void (*remove_dst_tcp_port_filter)(struct qed_dev *cdev, u16 dest_port); void (*clear_all_filters)(struct qed_dev *cdev); + + void (*init_read_io)(struct nvmetcp_task_params *task_params, + struct nvme_tcp_cmd_pdu *cmd_pdu_header, + struct nvme_command *nvme_cmd, + struct storage_sgl_task_params *sgl_task_params); + + void (*init_write_io)(struct nvmetcp_task_params *task_params, + struct nvme_tcp_cmd_pdu *cmd_pdu_header, + struct nvme_command *nvme_cmd, + struct storage_sgl_task_params *sgl_task_params); + + void (*init_icreq_exchange)(struct nvmetcp_task_params *task_params, + struct nvme_tcp_icreq_pdu *init_conn_req_pdu_hdr, + struct storage_sgl_task_params *tx_sgl_task_params, + struct storage_sgl_task_params *rx_sgl_task_params); + + void (*init_task_cleanup)(struct nvmetcp_task_params *task_params); }; const struct qed_nvmetcp_ops *qed_get_nvmetcp_ops(void); -- cgit v1.2.3 From 806ee7f81a2b037e3f57275adcdf974453cc3254 Mon Sep 17 00:00:00 2001 From: Nikolay Assa Date: Wed, 2 Jun 2021 20:16:55 +0300 Subject: qed: Add IP services APIs support This patch introduces APIs which the NVMeTCP Offload device (qedn) will use through the paired net-device (qede). It includes APIs for: - ipv4/ipv6 routing - get VLAN from net-device - TCP ports reservation Acked-by: Igor Russkikh Signed-off-by: Nikolay Assa Signed-off-by: Prabhakar Kushwaha Signed-off-by: Omkar Kulkarni Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Signed-off-by: Shai Malin Reviewed-by: Hannes Reinecke Signed-off-by: David S. Miller --- include/linux/qed/qed_nvmetcp_ip_services_if.h | 29 ++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) create mode 100644 include/linux/qed/qed_nvmetcp_ip_services_if.h (limited to 'include/linux') diff --git a/include/linux/qed/qed_nvmetcp_ip_services_if.h b/include/linux/qed/qed_nvmetcp_ip_services_if.h new file mode 100644 index 000000000000..3604aee53796 --- /dev/null +++ b/include/linux/qed/qed_nvmetcp_ip_services_if.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ +/* + * Copyright 2021 Marvell. All rights reserved. + */ + +#ifndef _QED_IP_SERVICES_IF_H +#define _QED_IP_SERVICES_IF_H + +#include +#include +#include +#include + +int qed_route_ipv4(struct sockaddr_storage *local_addr, + struct sockaddr_storage *remote_addr, + struct sockaddr *hardware_address, + struct net_device **ndev); +int qed_route_ipv6(struct sockaddr_storage *local_addr, + struct sockaddr_storage *remote_addr, + struct sockaddr *hardware_address, + struct net_device **ndev); +void qed_vlan_get_ndev(struct net_device **ndev, u16 *vlan_id); +struct pci_dev *qed_validate_ndev(struct net_device *ndev); +void qed_return_tcp_port(struct socket *sock); +int qed_fetch_tcp_port(struct sockaddr_storage local_ip_addr, + struct socket **sock, u16 *port); +__be16 qed_get_in_port(struct sockaddr_storage *sa); + +#endif /* _QED_IP_SERVICES_IF_H */ -- cgit v1.2.3 From 9e40ee18a1dc1623a5368d6232aaed52fd29dada Mon Sep 17 00:00:00 2001 From: Clemens Gruber Date: Fri, 7 May 2021 15:18:42 +0200 Subject: pwm: core: Support new usage_power setting in PWM state If usage_power is set, the PWM driver is only required to maintain the power output but has more freedom regarding signal form. If supported, the signal can be optimized, for example to improve EMI by phase shifting individual channels. Signed-off-by: Clemens Gruber Signed-off-by: Thierry Reding --- include/linux/pwm.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 5bb90af4997e..5a73251d28e3 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -54,12 +54,17 @@ enum { * @duty_cycle: PWM duty cycle (in nanoseconds) * @polarity: PWM polarity * @enabled: PWM enabled status + * @usage_power: If set, the PWM driver is only required to maintain the power + * output but has more freedom regarding signal form. + * If supported, the signal can be optimized, for example to + * improve EMI by phase shifting individual channels. */ struct pwm_state { u64 period; u64 duty_cycle; enum pwm_polarity polarity; bool enabled; + bool usage_power; }; /** @@ -188,6 +193,7 @@ static inline void pwm_init_state(const struct pwm_device *pwm, state->period = args.period; state->polarity = args.polarity; state->duty_cycle = 0; + state->usage_power = false; } /** @@ -558,6 +564,7 @@ static inline void pwm_apply_args(struct pwm_device *pwm) state.enabled = false; state.polarity = pwm->args.polarity; state.period = pwm->args.period; + state.usage_power = false; pwm_apply_state(pwm, &state); } -- cgit v1.2.3 From cd70c85c5752f060b09b0cf5b7694717471ce998 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 May 2021 12:19:27 -0400 Subject: power: supply: max17040: drop unused platform data support There are no platforms using the driver with platform data (no board files with the driver), so the dead code can be dropped. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Sebastian Reichel --- include/linux/max17040_battery.h | 16 ---------------- 1 file changed, 16 deletions(-) delete mode 100644 include/linux/max17040_battery.h (limited to 'include/linux') diff --git a/include/linux/max17040_battery.h b/include/linux/max17040_battery.h deleted file mode 100644 index 593602fc9317..000000000000 --- a/include/linux/max17040_battery.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2009 Samsung Electronics - * Minkyu Kang - */ - -#ifndef __MAX17040_BATTERY_H_ -#define __MAX17040_BATTERY_H_ - -struct max17040_platform_data { - int (*battery_online)(void); - int (*charger_online)(void); - int (*charger_enable)(void); -}; - -#endif -- cgit v1.2.3 From 7dc0c55e9f302e7048e040ee4437437bbea1e2cd Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Thu, 20 May 2021 16:21:44 -0400 Subject: USB: UDC core: Add udc_async_callbacks gadget op The Gadget API has a theoretical race when a gadget driver is unbound. Although the pull-up is turned off before the driver's ->unbind callback runs, if the USB cable were to be unplugged at just the wrong moment there would be nothing to prevent the UDC driver from invoking the ->disconnect callback after the unbind has finished. In theory, other asynchronous callbacks could also happen during the time before the UDC driver's udc_stop routine is called, and the gadget driver would not be prepared to handle any of them. We need a way to tell UDC drivers to stop issuing asynchronous (that is, ->suspend, ->resume, ->disconnect, ->reset, or ->setup) callbacks at some point after the pull-up has been turned off and before the ->unbind callback runs. This patch adds a new ->udc_async_callbacks callback to the usb_gadget_ops structure for precisely this purpose, and it adds the corresponding support to the UDC core. Later patches in this series add support for udc_async_callbacks to several UDC drivers. Acked-by: Felipe Balbi Signed-off-by: Alan Stern Link: https://lore.kernel.org/r/20210520202144.GC1216852@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/gadget.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 8811eb96e5cc..75c7538e350a 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -325,6 +325,7 @@ struct usb_gadget_ops { void (*udc_set_speed)(struct usb_gadget *, enum usb_device_speed); void (*udc_set_ssp_rate)(struct usb_gadget *gadget, enum usb_ssp_rate rate); + void (*udc_async_callbacks)(struct usb_gadget *gadget, bool enable); struct usb_ep *(*match_ep)(struct usb_gadget *, struct usb_endpoint_descriptor *, struct usb_ss_ep_comp_descriptor *); -- cgit v1.2.3 From 0c6b522abc2a592468992780babd3c3629c7ceac Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Thu, 6 May 2021 14:16:01 +0200 Subject: dma-buf: cleanup dma-resv shared fence debugging a bit v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Make that a function instead of inline. v2: improve the kerneldoc wording as suggested by Daniel Signed-off-by: Christian König Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210602111714.212426-3-christian.koenig@amd.com --- include/linux/dma-resv.h | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index d44a77e8a7e3..f32a3d176513 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -92,6 +92,12 @@ static inline struct dma_resv_list *dma_resv_get_list(struct dma_resv *obj) dma_resv_held(obj)); } +#ifdef CONFIG_DEBUG_MUTEXES +void dma_resv_reset_shared_max(struct dma_resv *obj); +#else +static inline void dma_resv_reset_shared_max(struct dma_resv *obj) {} +#endif + /** * dma_resv_lock - lock the reservation object * @obj: the reservation object @@ -215,14 +221,7 @@ static inline struct ww_acquire_ctx *dma_resv_locking_ctx(struct dma_resv *obj) */ static inline void dma_resv_unlock(struct dma_resv *obj) { -#ifdef CONFIG_DEBUG_MUTEXES - /* Test shared fence slot reservation */ - if (rcu_access_pointer(obj->fence)) { - struct dma_resv_list *fence = dma_resv_get_list(obj); - - fence->shared_max = fence->shared_count; - } -#endif + dma_resv_reset_shared_max(obj); ww_mutex_unlock(&obj->lock); } -- cgit v1.2.3 From 43582f29b161d820717bc13f562bca27af12e3cf Mon Sep 17 00:00:00 2001 From: Daniel Scally Date: Thu, 3 Jun 2021 23:40:04 +0100 Subject: gpiolib: acpi: Introduce acpi_get_and_request_gpiod() helper We need to be able to translate GPIO resources in an ACPI device's _CRS into GPIO descriptor array. Those are represented in _CRS as a pathname to a GPIO device plus the pin's index number: the acpi_get_gpiod() function is perfect for that purpose. As it's currently only used internally within the GPIO layer, provide and export a wrapper function that additionally holds a reference to the GPIO device. Reviewed-by: Andy Shevchenko Signed-off-by: Daniel Scally Signed-off-by: Andy Shevchenko --- include/linux/gpio/consumer.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index c73b25bc9213..566feb56601f 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -692,6 +692,8 @@ int devm_acpi_dev_add_driver_gpios(struct device *dev, const struct acpi_gpio_mapping *gpios); void devm_acpi_dev_remove_driver_gpios(struct device *dev); +struct gpio_desc *acpi_get_and_request_gpiod(char *path, int pin, char *label); + #else /* CONFIG_GPIOLIB && CONFIG_ACPI */ struct acpi_device; -- cgit v1.2.3 From 043d7f09bf614809c10c4acbf0695ef731958300 Mon Sep 17 00:00:00 2001 From: Daniel Scally Date: Thu, 3 Jun 2021 23:40:05 +0100 Subject: gpiolib: acpi: Add acpi_gpio_get_io_resource() Add a function to verify that a given ACPI resource represents a GpioIo() type of resource, and return it if so. Reviewed-by: Andy Shevchenko Signed-off-by: Daniel Scally Signed-off-by: Andy Shevchenko --- include/linux/acpi.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index c60745f657e9..a74d37a3b618 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1096,6 +1096,8 @@ void __acpi_handle_debug(struct _ddebug *descriptor, acpi_handle handle, const c #if defined(CONFIG_ACPI) && defined(CONFIG_GPIOLIB) bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio); +bool acpi_gpio_get_io_resource(struct acpi_resource *ares, + struct acpi_resource_gpio **agpio); int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, const char *name, int index); #else static inline bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, @@ -1103,6 +1105,11 @@ static inline bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, { return false; } +static inline bool acpi_gpio_get_io_resource(struct acpi_resource *ares, + struct acpi_resource_gpio **agpio) +{ + return false; +} static inline int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, const char *name, int index) { -- cgit v1.2.3 From 603e4922f1c81fc2ed3a87b4f91a8d3aafc7e093 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 31 May 2021 10:25:26 +0300 Subject: remove the raw driver The raw driver used to provide direct unbuffered access to block devices before O_DIRECT was invented. It has been obsolete for more than a decade. Acked-by: Greg Kroah-Hartman Acked-by: Arnd Bergmann Link: https://lore.kernel.org/lkml/Pine.LNX.4.64.0703180754060.6605@CPE00045a9c397f-CM001225dbafb6/ Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20210531072526.97052-1-hch@lst.de Signed-off-by: Greg Kroah-Hartman --- include/linux/fs.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index c3c88fdb9b2a..8652ed7cdce8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3242,11 +3242,8 @@ ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, struct iov_iter *iter); /* fs/block_dev.c */ -extern ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to); -extern ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from); extern int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync); -extern void block_sync_page(struct page *page); /* fs/splice.c */ extern ssize_t generic_file_splice_read(struct file *, loff_t *, -- cgit v1.2.3 From 9fb9b1690f0ba6b2c9ced91facc1fc44f5a0d5c1 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Fri, 4 Jun 2021 12:52:29 +0100 Subject: ASoC: codecs: wcd934x: add mbhc support WCD934x has Multi Button Headset Control hardware to support Headset insertion, type detection, 8 headset buttons detection, Over Current detection and Impedence measurements. This patch adds support for this feature via common mbhc layer. Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20210604115230.23259-4-srinivas.kandagatla@linaro.org Signed-off-by: Mark Brown --- include/linux/mfd/wcd934x/registers.h | 57 +++++++++++++++++++++++++++++++++++ 1 file changed, 57 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/wcd934x/registers.h b/include/linux/mfd/wcd934x/registers.h index bb8d2e276668..76a943c83c63 100644 --- a/include/linux/mfd/wcd934x/registers.h +++ b/include/linux/mfd/wcd934x/registers.h @@ -18,6 +18,8 @@ #define WCD934X_EFUSE_SENSE_STATE_DEF 0x10 #define WCD934X_EFUSE_SENSE_EN_MASK BIT(0) #define WCD934X_EFUSE_SENSE_ENABLE BIT(0) +#define WCD934X_CHIP_TIER_CTRL_EFUSE_VAL_OUT1 0x002a +#define WCD934X_CHIP_TIER_CTRL_EFUSE_VAL_OUT2 0x002b #define WCD934X_CHIP_TIER_CTRL_EFUSE_VAL_OUT14 0x0037 #define WCD934X_CHIP_TIER_CTRL_EFUSE_VAL_OUT15 0x0038 #define WCD934X_CHIP_TIER_CTRL_EFUSE_STATUS 0x0039 @@ -103,21 +105,58 @@ #define WCD934X_ANA_AMIC3 0x0610 #define WCD934X_ANA_AMIC4 0x0611 #define WCD934X_ANA_MBHC_MECH 0x0614 +#define WCD934X_MBHC_L_DET_EN_MASK BIT(7) +#define WCD934X_MBHC_L_DET_EN BIT(7) +#define WCD934X_MBHC_GND_DET_EN_MASK BIT(6) +#define WCD934X_MBHC_MECH_DETECT_TYPE_MASK BIT(5) +#define WCD934X_MBHC_MECH_DETECT_TYPE_INS 1 +#define WCD934X_MBHC_HPHL_PLUG_TYPE_MASK BIT(4) +#define WCD934X_MBHC_HPHL_PLUG_TYPE_NO 1 +#define WCD934X_MBHC_GND_PLUG_TYPE_MASK BIT(3) +#define WCD934X_MBHC_GND_PLUG_TYPE_NO 1 +#define WCD934X_MBHC_HSL_PULLUP_COMP_EN BIT(2) +#define WCD934X_MBHC_HSG_PULLUP_COMP_EN BIT(1) +#define WCD934X_MBHC_HPHL_100K_TO_GND_EN BIT(0) #define WCD934X_ANA_MBHC_ELECT 0x0615 +#define WCD934X_ANA_MBHC_BIAS_EN_MASK BIT(0) +#define WCD934X_ANA_MBHC_BIAS_EN BIT(0) #define WCD934X_ANA_MBHC_ZDET 0x0616 #define WCD934X_ANA_MBHC_RESULT_1 0x0617 #define WCD934X_ANA_MBHC_RESULT_2 0x0618 #define WCD934X_ANA_MBHC_RESULT_3 0x0619 +#define WCD934X_ANA_MBHC_BTN0 0x061a +#define WCD934X_VTH_MASK GENMASK(7, 2) +#define WCD934X_ANA_MBHC_BTN1 0x061b +#define WCD934X_ANA_MBHC_BTN2 0x061c +#define WCD934X_ANA_MBHC_BTN3 0x061d +#define WCD934X_ANA_MBHC_BTN4 0x061e +#define WCD934X_ANA_MBHC_BTN5 0x061f +#define WCD934X_ANA_MBHC_BTN6 0x0620 +#define WCD934X_ANA_MBHC_BTN7 0x0621 +#define WCD934X_MBHC_BTN_VTH_MASK GENMASK(7, 2) #define WCD934X_ANA_MICB1 0x0622 #define WCD934X_MICB_VAL_MASK GENMASK(5, 0) #define WCD934X_ANA_MICB_EN_MASK GENMASK(7, 6) +#define WCD934X_MICB_DISABLE 0 +#define WCD934X_MICB_ENABLE 1 +#define WCD934X_MICB_PULL_UP 2 +#define WCD934X_MICB_PULL_DOWN 3 #define WCD934X_ANA_MICB_PULL_UP 0x80 #define WCD934X_ANA_MICB_ENABLE 0x40 #define WCD934X_ANA_MICB_DISABLE 0x0 #define WCD934X_ANA_MICB2 0x0623 +#define WCD934X_ANA_MICB2_ENABLE BIT(6) +#define WCD934X_ANA_MICB2_ENABLE_MASK GENMASK(7, 6) +#define WCD934X_ANA_MICB2_VOUT_MASK GENMASK(5, 0) +#define WCD934X_ANA_MICB2_RAMP 0x0624 +#define WCD934X_RAMP_EN_MASK BIT(7) +#define WCD934X_RAMP_SHIFT_CTRL_MASK GENMASK(4, 2) #define WCD934X_ANA_MICB3 0x0625 #define WCD934X_ANA_MICB4 0x0626 #define WCD934X_BIAS_VBG_FINE_ADJ 0x0629 +#define WCD934X_MBHC_CTL_CLK 0x0656 +#define WCD934X_MBHC_CTL_BCS 0x065a +#define WCD934X_MBHC_STATUS_SPARE_1 0x065b #define WCD934X_MICB1_TEST_CTL_1 0x066b #define WCD934X_MICB1_TEST_CTL_2 0x066c #define WCD934X_MICB2_TEST_CTL_1 0x066e @@ -141,7 +180,11 @@ #define WCD934X_HPH_CNP_WG_CTL 0x06cc #define WCD934X_HPH_GM3_BOOST_EN_MASK BIT(7) #define WCD934X_HPH_GM3_BOOST_ENABLE BIT(7) +#define WCD934X_HPH_CNP_WG_TIME 0x06cd #define WCD934X_HPH_OCP_CTL 0x06ce +#define WCD934X_HPH_PA_CTL2 0x06d2 +#define WCD934X_HPHPA_GND_R_MASK BIT(6) +#define WCD934X_HPHPA_GND_L_MASK BIT(4) #define WCD934X_HPH_L_EN 0x06d3 #define WCD934X_HPH_GAIN_SRC_SEL_MASK BIT(5) #define WCD934X_HPH_GAIN_SRC_SEL_COMPANDER 0 @@ -152,6 +195,8 @@ #define WCD934X_HPH_OCP_DET_MASK BIT(0) #define WCD934X_HPH_OCP_DET_ENABLE BIT(0) #define WCD934X_HPH_OCP_DET_DISABLE 0 +#define WCD934X_HPH_R_ATEST 0x06d8 +#define WCD934X_HPHPA_GND_OVR_MASK BIT(1) #define WCD934X_DIFF_LO_LO2_COMPANDER 0x06ea #define WCD934X_DIFF_LO_LO1_COMPANDER 0x06eb #define WCD934X_CLK_SYS_MCLK_PRG 0x0711 @@ -172,7 +217,19 @@ #define WCD934X_SIDO_NEW_VOUT_D_FREQ2 0x071e #define WCD934X_SIDO_RIPPLE_FREQ_EN_MASK BIT(0) #define WCD934X_SIDO_RIPPLE_FREQ_ENABLE BIT(0) +#define WCD934X_MBHC_NEW_CTL_1 0x0720 +#define WCD934X_MBHC_CTL_RCO_EN_MASK BIT(7) +#define WCD935X_MBHC_CTL_RCO_EN BIT(7) #define WCD934X_MBHC_NEW_CTL_2 0x0721 +#define WCD934X_M_RTH_CTL_MASK GENMASK(3, 2) +#define WCD934X_MBHC_NEW_PLUG_DETECT_CTL 0x0722 +#define WCD934X_HSDET_PULLUP_C_MASK GENMASK(7, 6) +#define WCD934X_MBHC_NEW_ZDET_ANA_CTL 0x0723 +#define WCD934X_ZDET_RANGE_CTL_MASK GENMASK(3, 0) +#define WCD934X_ZDET_MAXV_CTL_MASK GENMASK(6, 4) +#define WCD934X_MBHC_NEW_ZDET_RAMP_CTL 0x0724 +#define WCD934X_MBHC_NEW_FSM_STATUS 0x0725 +#define WCD934X_MBHC_NEW_ADC_RESULT 0x0726 #define WCD934X_TX_NEW_AMIC_4_5_SEL 0x0727 #define WCD934X_HPH_NEW_INT_RDAC_HD2_CTL_L 0x0733 #define WCD934X_HPH_NEW_INT_RDAC_OVERRIDE_CTL 0x0735 -- cgit v1.2.3 From 912e887505a07123917e537b657859723ce5d472 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Wed, 26 May 2021 06:24:57 +0900 Subject: dm: Introduce dm_report_zones() To simplify the implementation of the report_zones operation of a zoned target, introduce the function dm_report_zones() to set a target mapping start sector in struct dm_report_zones_args and call blkdev_report_zones(). This new function is exported and the report zones callback function dm_report_zones_cb() is not. dm-linear, dm-flakey and dm-crypt are modified to use dm_report_zones(). Signed-off-by: Damien Le Moal Reviewed-by: Johannes Thumshirn Reviewed-by: Hannes Reinecke Reviewed-by: Himanshu Madhani Signed-off-by: Mike Snitzer --- include/linux/device-mapper.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index ff700fb6ce1d..caea0a079d2d 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -478,7 +478,8 @@ struct dm_report_zones_args { /* must be filled by ->report_zones before calling dm_report_zones_cb */ sector_t start; }; -int dm_report_zones_cb(struct blk_zone *zone, unsigned int idx, void *data); +int dm_report_zones(struct block_device *bdev, sector_t start, sector_t sector, + struct dm_report_zones_args *args, unsigned int nr_zones); #endif /* CONFIG_BLK_DEV_ZONED */ /* -- cgit v1.2.3 From d0ea6bde141df9311bc36e7b07ad37b449f2c4f5 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Wed, 26 May 2021 06:24:52 +0900 Subject: block: introduce bio zone helpers Introduce the helper functions bio_zone_no() and bio_zone_is_seq(). Both are the BIO counterparts of the request helpers blk_rq_zone_no() and blk_rq_zone_is_seq(), respectively returning the number of the target zone of a bio and true if the BIO target zone is sequential. Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Reviewed-by: Chaitanya Kulkarni Reviewed-by: Christoph Hellwig Reviewed-by: Himanshu Madhani Acked-by: Jens Axboe Signed-off-by: Mike Snitzer --- include/linux/blkdev.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f69c75bd6d27..2db0f376f5d9 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1008,6 +1008,18 @@ static inline unsigned int blk_rq_stats_sectors(const struct request *rq) /* Helper to convert BLK_ZONE_ZONE_XXX to its string format XXX */ const char *blk_zone_cond_str(enum blk_zone_cond zone_cond); +static inline unsigned int bio_zone_no(struct bio *bio) +{ + return blk_queue_zone_no(bdev_get_queue(bio->bi_bdev), + bio->bi_iter.bi_sector); +} + +static inline unsigned int bio_zone_is_seq(struct bio *bio) +{ + return blk_queue_zone_is_seq(bdev_get_queue(bio->bi_bdev), + bio->bi_iter.bi_sector); +} + static inline unsigned int blk_rq_zone_no(struct request *rq) { return blk_queue_zone_no(rq->q, blk_rq_pos(rq)); -- cgit v1.2.3 From 9ffbbb435d8f566a0924ce4b5dc7fc1bceb6dbf8 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Wed, 26 May 2021 06:24:53 +0900 Subject: block: introduce BIO_ZONE_WRITE_LOCKED bio flag Introduce the BIO flag BIO_ZONE_WRITE_LOCKED to indicate that a BIO owns the write lock of the zone it is targeting. This is the counterpart of the struct request flag RQF_ZONE_WRITE_LOCKED. This new BIO flag is reserved for now for zone write locking control for device mapper targets exposing a zoned block device. Since in this case, the lock flag must not be propagated to the struct request that will be used to process the BIO, a BIO private flag is used rather than changing the RQF_ZONE_WRITE_LOCKED request flag into a common REQ_XXX flag that could be used for both BIO and request. This avoids conflicts down the stack with the block IO scheduler zone write locking (in mq-deadline). Signed-off-by: Damien Le Moal Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Chaitanya Kulkarni Reviewed-by: Himanshu Madhani Acked-by: Jens Axboe Signed-off-by: Mike Snitzer --- include/linux/blk_types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index db026b6ec15a..e5cf12f102a2 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -304,6 +304,7 @@ enum { BIO_CGROUP_ACCT, /* has been accounted to a cgroup */ BIO_TRACKED, /* set if bio goes through the rq_qos path */ BIO_REMAPPED, + BIO_ZONE_WRITE_LOCKED, /* Owns a zoned device zone write lock */ BIO_FLAG_LAST }; -- cgit v1.2.3 From bb37d77239af25cde59693dbe3fac04dd17d7b29 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Wed, 26 May 2021 06:25:00 +0900 Subject: dm: introduce zone append emulation For zoned targets that cannot support zone append operations, implement an emulation using regular write operations. If the original BIO submitted by the user is a zone append operation, change its clone into a regular write operation directed at the target zone write pointer position. To do so, an array of write pointer offsets (write pointer position relative to the start of a zone) is added to struct mapped_device. All operations that modify a sequential zone write pointer (writes, zone reset, zone finish and zone append) are intersepted in __map_bio() and processed using the new functions dm_zone_map_bio(). Detection of the target ability to natively support zone append operations is done from dm_table_set_restrictions() by calling the function dm_set_zones_restrictions(). A target that does not support zone append operation, either by explicitly declaring it using the new struct dm_target field zone_append_not_supported, or because the device table contains a non-zoned device, has its mapped device marked with the new flag DMF_ZONE_APPEND_EMULATED. The helper function dm_emulate_zone_append() is introduced to test a mapped device for this new flag. Atomicity of the zones write pointer tracking and updates is done using a zone write locking mechanism based on a bitmap. This is similar to the block layer method but based on BIOs rather than struct request. A zone write lock is taken in dm_zone_map_bio() for any clone BIO with an operation type that changes the BIO target zone write pointer position. The zone write lock is released if the clone BIO is failed before submission or when dm_zone_endio() is called when the clone BIO completes. The zone write lock bitmap of the mapped device, together with a bitmap indicating zone types (conv_zones_bitmap) and the write pointer offset array (zwp_offset) are allocated and initialized with a full device zone report in dm_set_zones_restrictions() using the function dm_revalidate_zones(). For failed operations that may have modified a zone write pointer, the zone write pointer offset is marked as invalid in dm_zone_endio(). Zones with an invalid write pointer offset are checked and the write pointer updated using an internal report zone operation when the faulty zone is accessed again by the user. All functions added for this emulation have a minimal overhead for zoned targets natively supporting zone append operations. Regular device targets are also not affected. The added code also does not impact builds with CONFIG_BLK_DEV_ZONED disabled by stubbing out all dm zone related functions. Signed-off-by: Damien Le Moal Reviewed-by: Himanshu Madhani Reviewed-by: Hannes Reinecke Signed-off-by: Mike Snitzer --- include/linux/device-mapper.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index caea0a079d2d..7457d49acf9a 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -361,6 +361,12 @@ struct dm_target { * Set if we need to limit the number of in-flight bios when swapping. */ bool limit_swap_bios:1; + + /* + * Set if this target implements a a zoned device and needs emulation of + * zone append operations using regular writes. + */ + bool emulate_zone_append:1; }; void *dm_per_bio_data(struct bio *bio, size_t data_size); -- cgit v1.2.3 From 92638b4e1b47f97d7269e74465dedf73096f777d Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Wed, 2 Jun 2021 16:52:27 -0700 Subject: mm: arch: remove indirection level in alloc_zeroed_user_highpage_movable() In an upcoming change we would like to add a flag to GFP_HIGHUSER_MOVABLE so that it would no longer be an OR of GFP_HIGHUSER and __GFP_MOVABLE. This poses a problem for alloc_zeroed_user_highpage_movable() which passes __GFP_MOVABLE into an arch-specific __alloc_zeroed_user_highpage() hook which ORs in GFP_HIGHUSER. Since __alloc_zeroed_user_highpage() is only ever called from alloc_zeroed_user_highpage_movable(), we can remove one level of indirection here. Remove __alloc_zeroed_user_highpage(), make alloc_zeroed_user_highpage_movable() the hook, and use GFP_HIGHUSER_MOVABLE in the hook implementations so that they will pick up the new flag that we are going to add. Signed-off-by: Peter Collingbourne Link: https://linux-review.googlesource.com/id/Ic6361c657b2cdcd896adbe0cf7cb5a7fbb1ed7bf Acked-by: Catalin Marinas Link: https://lore.kernel.org/r/20210602235230.3928842-2-pcc@google.com Signed-off-by: Will Deacon --- include/linux/highmem.h | 35 ++++++++--------------------------- 1 file changed, 8 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 832b49b50c7b..54d0643b8fcf 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -152,28 +152,24 @@ static inline void clear_user_highpage(struct page *page, unsigned long vaddr) } #endif -#ifndef __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE +#ifndef __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE /** - * __alloc_zeroed_user_highpage - Allocate a zeroed HIGHMEM page for a VMA with caller-specified movable GFP flags - * @movableflags: The GFP flags related to the pages future ability to move like __GFP_MOVABLE + * alloc_zeroed_user_highpage_movable - Allocate a zeroed HIGHMEM page for a VMA that the caller knows can move * @vma: The VMA the page is to be allocated for * @vaddr: The virtual address the page will be inserted into * - * This function will allocate a page for a VMA but the caller is expected - * to specify via movableflags whether the page will be movable in the - * future or not + * This function will allocate a page for a VMA that the caller knows will + * be able to migrate in the future using move_pages() or reclaimed * * An architecture may override this function by defining - * __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE and providing their own + * __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE and providing their own * implementation. */ static inline struct page * -__alloc_zeroed_user_highpage(gfp_t movableflags, - struct vm_area_struct *vma, - unsigned long vaddr) +alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma, + unsigned long vaddr) { - struct page *page = alloc_page_vma(GFP_HIGHUSER | movableflags, - vma, vaddr); + struct page *page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr); if (page) clear_user_highpage(page, vaddr); @@ -182,21 +178,6 @@ __alloc_zeroed_user_highpage(gfp_t movableflags, } #endif -/** - * alloc_zeroed_user_highpage_movable - Allocate a zeroed HIGHMEM page for a VMA that the caller knows can move - * @vma: The VMA the page is to be allocated for - * @vaddr: The virtual address the page will be inserted into - * - * This function will allocate a page for a VMA that the caller knows will - * be able to migrate in the future using move_pages() or reclaimed - */ -static inline struct page * -alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma, - unsigned long vaddr) -{ - return __alloc_zeroed_user_highpage(__GFP_MOVABLE, vma, vaddr); -} - static inline void clear_highpage(struct page *page) { void *kaddr = kmap_atomic(page); -- cgit v1.2.3 From 7a3b835371883558eb63e069d891bd87f562380d Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Wed, 2 Jun 2021 16:52:28 -0700 Subject: kasan: use separate (un)poison implementation for integrated init Currently with integrated init page_alloc.c needs to know whether kasan_alloc_pages() will zero initialize memory, but this will start becoming more complicated once we start adding tag initialization support for user pages. To avoid page_alloc.c needing to know more details of what integrated init will do, move the unpoisoning logic for integrated init into the HW tags implementation. Currently the logic is identical but it will diverge in subsequent patches. For symmetry do the same for poisoning although this logic will be unaffected by subsequent patches. Signed-off-by: Peter Collingbourne Reviewed-by: Andrey Konovalov Link: https://linux-review.googlesource.com/id/I2c550234c6c4a893c48c18ff0c6ce658c7c67056 Link: https://lore.kernel.org/r/20210602235230.3928842-3-pcc@google.com Signed-off-by: Will Deacon --- include/linux/kasan.h | 64 ++++++++++++++++++++++++++++++--------------------- 1 file changed, 38 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index b1678a61e6a7..a1c7ce5f3e4f 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -2,6 +2,7 @@ #ifndef _LINUX_KASAN_H #define _LINUX_KASAN_H +#include #include #include @@ -79,14 +80,6 @@ static inline void kasan_disable_current(void) {} #endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ -#ifdef CONFIG_KASAN - -struct kasan_cache { - int alloc_meta_offset; - int free_meta_offset; - bool is_kmalloc; -}; - #ifdef CONFIG_KASAN_HW_TAGS DECLARE_STATIC_KEY_FALSE(kasan_flag_enabled); @@ -101,11 +94,14 @@ static inline bool kasan_has_integrated_init(void) return kasan_enabled(); } +void kasan_alloc_pages(struct page *page, unsigned int order, gfp_t flags); +void kasan_free_pages(struct page *page, unsigned int order); + #else /* CONFIG_KASAN_HW_TAGS */ static inline bool kasan_enabled(void) { - return true; + return IS_ENABLED(CONFIG_KASAN); } static inline bool kasan_has_integrated_init(void) @@ -113,8 +109,30 @@ static inline bool kasan_has_integrated_init(void) return false; } +static __always_inline void kasan_alloc_pages(struct page *page, + unsigned int order, gfp_t flags) +{ + /* Only available for integrated init. */ + BUILD_BUG(); +} + +static __always_inline void kasan_free_pages(struct page *page, + unsigned int order) +{ + /* Only available for integrated init. */ + BUILD_BUG(); +} + #endif /* CONFIG_KASAN_HW_TAGS */ +#ifdef CONFIG_KASAN + +struct kasan_cache { + int alloc_meta_offset; + int free_meta_offset; + bool is_kmalloc; +}; + slab_flags_t __kasan_never_merge(void); static __always_inline slab_flags_t kasan_never_merge(void) { @@ -130,20 +148,20 @@ static __always_inline void kasan_unpoison_range(const void *addr, size_t size) __kasan_unpoison_range(addr, size); } -void __kasan_alloc_pages(struct page *page, unsigned int order, bool init); -static __always_inline void kasan_alloc_pages(struct page *page, +void __kasan_poison_pages(struct page *page, unsigned int order, bool init); +static __always_inline void kasan_poison_pages(struct page *page, unsigned int order, bool init) { if (kasan_enabled()) - __kasan_alloc_pages(page, order, init); + __kasan_poison_pages(page, order, init); } -void __kasan_free_pages(struct page *page, unsigned int order, bool init); -static __always_inline void kasan_free_pages(struct page *page, - unsigned int order, bool init) +void __kasan_unpoison_pages(struct page *page, unsigned int order, bool init); +static __always_inline void kasan_unpoison_pages(struct page *page, + unsigned int order, bool init) { if (kasan_enabled()) - __kasan_free_pages(page, order, init); + __kasan_unpoison_pages(page, order, init); } void __kasan_cache_create(struct kmem_cache *cache, unsigned int *size, @@ -285,21 +303,15 @@ void kasan_restore_multi_shot(bool enabled); #else /* CONFIG_KASAN */ -static inline bool kasan_enabled(void) -{ - return false; -} -static inline bool kasan_has_integrated_init(void) -{ - return false; -} static inline slab_flags_t kasan_never_merge(void) { return 0; } static inline void kasan_unpoison_range(const void *address, size_t size) {} -static inline void kasan_alloc_pages(struct page *page, unsigned int order, bool init) {} -static inline void kasan_free_pages(struct page *page, unsigned int order, bool init) {} +static inline void kasan_poison_pages(struct page *page, unsigned int order, + bool init) {} +static inline void kasan_unpoison_pages(struct page *page, unsigned int order, + bool init) {} static inline void kasan_cache_create(struct kmem_cache *cache, unsigned int *size, slab_flags_t *flags) {} -- cgit v1.2.3 From 013bb59dbb7cf876449df860946458a595a96d51 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Wed, 2 Jun 2021 16:52:29 -0700 Subject: arm64: mte: handle tags zeroing at page allocation time Currently, on an anonymous page fault, the kernel allocates a zeroed page and maps it in user space. If the mapping is tagged (PROT_MTE), set_pte_at() additionally clears the tags. It is, however, more efficient to clear the tags at the same time as zeroing the data on allocation. To avoid clearing the tags on any page (which may not be mapped as tagged), only do this if the vma flags contain VM_MTE. This requires introducing a new GFP flag that is used to determine whether to clear the tags. The DC GZVA instruction with a 0 top byte (and 0 tag) requires top-byte-ignore. Set the TCR_EL1.{TBI1,TBID1} bits irrespective of whether KASAN_HW is enabled. Signed-off-by: Peter Collingbourne Co-developed-by: Catalin Marinas Signed-off-by: Catalin Marinas Link: https://linux-review.googlesource.com/id/Id46dc94e30fe11474f7e54f5d65e7658dbdddb26 Reviewed-by: Catalin Marinas Reviewed-by: Andrey Konovalov Link: https://lore.kernel.org/r/20210602235230.3928842-4-pcc@google.com Signed-off-by: Will Deacon --- include/linux/gfp.h | 9 +++++++-- include/linux/highmem.h | 8 ++++++++ 2 files changed, 15 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 11da8af06704..68ba237365dc 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -53,8 +53,9 @@ struct vm_area_struct; #define ___GFP_HARDWALL 0x100000u #define ___GFP_THISNODE 0x200000u #define ___GFP_ACCOUNT 0x400000u +#define ___GFP_ZEROTAGS 0x800000u #ifdef CONFIG_LOCKDEP -#define ___GFP_NOLOCKDEP 0x800000u +#define ___GFP_NOLOCKDEP 0x1000000u #else #define ___GFP_NOLOCKDEP 0 #endif @@ -229,16 +230,20 @@ struct vm_area_struct; * %__GFP_COMP address compound page metadata. * * %__GFP_ZERO returns a zeroed page on success. + * + * %__GFP_ZEROTAGS returns a page with zeroed memory tags on success, if + * __GFP_ZERO is set. */ #define __GFP_NOWARN ((__force gfp_t)___GFP_NOWARN) #define __GFP_COMP ((__force gfp_t)___GFP_COMP) #define __GFP_ZERO ((__force gfp_t)___GFP_ZERO) +#define __GFP_ZEROTAGS ((__force gfp_t)___GFP_ZEROTAGS) /* Disable lockdep for GFP context tracking */ #define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP) /* Room for N __GFP_FOO bits */ -#define __GFP_BITS_SHIFT (23 + IS_ENABLED(CONFIG_LOCKDEP)) +#define __GFP_BITS_SHIFT (24 + IS_ENABLED(CONFIG_LOCKDEP)) #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) /** diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 54d0643b8fcf..8c6e8e996c87 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -185,6 +185,14 @@ static inline void clear_highpage(struct page *page) kunmap_atomic(kaddr); } +#ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGE + +static inline void tag_clear_highpage(struct page *page) +{ +} + +#endif + /* * If we pass in a base or tail page, we can zero up to PAGE_SIZE. * If we pass in a head page, we can zero up to the size of the compound page. -- cgit v1.2.3 From c275c5c6d50a0518cdb0584e85905d10e7cefc6e Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Wed, 2 Jun 2021 16:52:30 -0700 Subject: kasan: disable freed user page poisoning with HW tags Poisoning freed pages protects against kernel use-after-free. The likelihood of such a bug involving kernel pages is significantly higher than that for user pages. At the same time, poisoning freed pages can impose a significant performance cost, which cannot always be justified for user pages given the lower probability of finding a bug. Therefore, disable freed user page poisoning when using HW tags. We identify "user" pages via the flag set GFP_HIGHUSER_MOVABLE, which indicates a strong likelihood of not being directly accessible to the kernel. Signed-off-by: Peter Collingbourne Reviewed-by: Andrey Konovalov Link: https://linux-review.googlesource.com/id/I716846e2de8ef179f44e835770df7e6307be96c9 Link: https://lore.kernel.org/r/20210602235230.3928842-5-pcc@google.com Signed-off-by: Will Deacon --- include/linux/gfp.h | 13 ++++++++++--- include/linux/page-flags.h | 9 +++++++++ 2 files changed, 19 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 68ba237365dc..e6102dfa4faa 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -54,8 +54,9 @@ struct vm_area_struct; #define ___GFP_THISNODE 0x200000u #define ___GFP_ACCOUNT 0x400000u #define ___GFP_ZEROTAGS 0x800000u +#define ___GFP_SKIP_KASAN_POISON 0x1000000u #ifdef CONFIG_LOCKDEP -#define ___GFP_NOLOCKDEP 0x1000000u +#define ___GFP_NOLOCKDEP 0x2000000u #else #define ___GFP_NOLOCKDEP 0 #endif @@ -233,17 +234,22 @@ struct vm_area_struct; * * %__GFP_ZEROTAGS returns a page with zeroed memory tags on success, if * __GFP_ZERO is set. + * + * %__GFP_SKIP_KASAN_POISON returns a page which does not need to be poisoned + * on deallocation. Typically used for userspace pages. Currently only has an + * effect in HW tags mode. */ #define __GFP_NOWARN ((__force gfp_t)___GFP_NOWARN) #define __GFP_COMP ((__force gfp_t)___GFP_COMP) #define __GFP_ZERO ((__force gfp_t)___GFP_ZERO) #define __GFP_ZEROTAGS ((__force gfp_t)___GFP_ZEROTAGS) +#define __GFP_SKIP_KASAN_POISON ((__force gfp_t)___GFP_SKIP_KASAN_POISON) /* Disable lockdep for GFP context tracking */ #define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP) /* Room for N __GFP_FOO bits */ -#define __GFP_BITS_SHIFT (24 + IS_ENABLED(CONFIG_LOCKDEP)) +#define __GFP_BITS_SHIFT (25 + IS_ENABLED(CONFIG_LOCKDEP)) #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) /** @@ -324,7 +330,8 @@ struct vm_area_struct; #define GFP_DMA __GFP_DMA #define GFP_DMA32 __GFP_DMA32 #define GFP_HIGHUSER (GFP_USER | __GFP_HIGHMEM) -#define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE) +#define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE | \ + __GFP_SKIP_KASAN_POISON) #define GFP_TRANSHUGE_LIGHT ((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \ __GFP_NOMEMALLOC | __GFP_NOWARN) & ~__GFP_RECLAIM) #define GFP_TRANSHUGE (GFP_TRANSHUGE_LIGHT | __GFP_DIRECT_RECLAIM) diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 04a34c08e0a6..40e2c5000585 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -137,6 +137,9 @@ enum pageflags { #endif #ifdef CONFIG_64BIT PG_arch_2, +#endif +#ifdef CONFIG_KASAN_HW_TAGS + PG_skip_kasan_poison, #endif __NR_PAGEFLAGS, @@ -443,6 +446,12 @@ TESTCLEARFLAG(Young, young, PF_ANY) PAGEFLAG(Idle, idle, PF_ANY) #endif +#ifdef CONFIG_KASAN_HW_TAGS +PAGEFLAG(SkipKASanPoison, skip_kasan_poison, PF_HEAD) +#else +PAGEFLAG_FALSE(SkipKASanPoison) +#endif + /* * PageReported() is used to track reported free pages within the Buddy * allocator. We can use the non-atomic version of the test and set -- cgit v1.2.3 From c7c90e121e992eefdf07945e5a6e9cf097b29463 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 1 Jun 2021 16:31:43 -0500 Subject: kconfig.h: explain IS_MODULE(), IS_ENABLED() Extend IS_MODULE() and IS_ENABLED comments to explain why one might use "#if IS_ENABLED(CONFIG_FOO)" instead of "#ifdef CONFIG_FOO". To wit, "#ifdef CONFIG_FOO" is true only for CONFIG_FOO=y, while "#if IS_ENABLED(CONFIG_FOO)" is true for both CONFIG_FOO=y and CONFIG_FOO=m. This is because "CONFIG_FOO=m" in .config does not result in "CONFIG_FOO" being defined. The actual definitions are in autoconf.h, where: CONFIG_FOO=y results in #define CONFIG_FOO 1 CONFIG_FOO=m results in #define CONFIG_FOO_MODULE 1 Signed-off-by: Bjorn Helgaas Acked-by: Randy Dunlap Signed-off-by: Masahiro Yamada --- include/linux/kconfig.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kconfig.h b/include/linux/kconfig.h index cc8fa109cfa3..20d1079e92b4 100644 --- a/include/linux/kconfig.h +++ b/include/linux/kconfig.h @@ -51,7 +51,8 @@ /* * IS_MODULE(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'm', 0 - * otherwise. + * otherwise. CONFIG_FOO=m results in "#define CONFIG_FOO_MODULE 1" in + * autoconf.h. */ #define IS_MODULE(option) __is_defined(option##_MODULE) @@ -66,7 +67,8 @@ /* * IS_ENABLED(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y' or 'm', - * 0 otherwise. + * 0 otherwise. Note that CONFIG_FOO=y results in "#define CONFIG_FOO 1" in + * autoconf.h, while CONFIG_FOO=m results in "#define CONFIG_FOO_MODULE 1". */ #define IS_ENABLED(option) __or(IS_BUILTIN(option), IS_MODULE(option)) -- cgit v1.2.3 From 4d5c8aedc8aa6a1f5d1b06eb4f5517dc60dd9440 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Wed, 2 Jun 2021 18:09:30 -0700 Subject: mm, memcg: introduce mem_cgroup_kmem_disabled() Introduce a new mem_cgroup_kmem_disabled() helper, similar to mem_cgroup_disabled(), to check whether the kernel memory accounting is off. A user could disable it using a boot option to eliminate some associated costs. The helper can be used outside of memcontrol.c to dynamically disable the kmem-related code. The returned value is stable after the kernel initialization is finished. Signed-off-by: Roman Gushchin Signed-off-by: Dennis Zhou --- include/linux/memcontrol.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 0c04d39a7967..8ef51c58f470 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1583,6 +1583,7 @@ static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg, #endif #ifdef CONFIG_MEMCG_KMEM +bool mem_cgroup_kmem_disabled(void); int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order); void __memcg_kmem_uncharge_page(struct page *page, int order); @@ -1636,6 +1637,10 @@ static inline int memcg_cache_id(struct mem_cgroup *memcg) struct mem_cgroup *mem_cgroup_from_obj(void *p); #else +static inline bool mem_cgroup_kmem_disabled(void) +{ + return true; +} static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) -- cgit v1.2.3 From 6edbd6abb783d54f6ac4c3ed5cd9e50cff6c15e9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Mon, 10 May 2021 16:14:09 +0200 Subject: dma-buf: rename and cleanup dma_resv_get_excl v3 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When the comment needs to state explicitly that this doesn't get a reference to the object then the function is named rather badly. Rename the function and use rcu_dereference_check(), this way it can be used from both rcu as well as lock protected critical sections. v2: improve kerneldoc as suggested by Daniel v3: use dma_resv_excl_fence as function name Signed-off-by: Christian König Acked-by: Daniel Vetter Reviewed-by: Jason Ekstrand Link: https://patchwork.freedesktop.org/patch/msgid/20210602111714.212426-4-christian.koenig@amd.com --- include/linux/dma-resv.h | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index f32a3d176513..e3a7f740bb06 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -226,22 +226,20 @@ static inline void dma_resv_unlock(struct dma_resv *obj) } /** - * dma_resv_get_excl - get the reservation object's - * exclusive fence, with update-side lock held + * dma_resv_exclusive - return the object's exclusive fence * @obj: the reservation object * - * Returns the exclusive fence (if any). Does NOT take a - * reference. Writers must hold obj->lock, readers may only - * hold a RCU read side lock. + * Returns the exclusive fence (if any). Caller must either hold the objects + * through dma_resv_lock() or the RCU read side lock through rcu_read_lock(), + * or one of the variants of each * * RETURNS * The exclusive fence or NULL */ static inline struct dma_fence * -dma_resv_get_excl(struct dma_resv *obj) +dma_resv_excl_fence(struct dma_resv *obj) { - return rcu_dereference_protected(obj->fence_excl, - dma_resv_held(obj)); + return rcu_dereference_check(obj->fence_excl, dma_resv_held(obj)); } /** -- cgit v1.2.3 From fb5ce730f21434d8100942cf1dbe1acda255fbeb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Tue, 11 May 2021 14:11:41 +0200 Subject: dma-buf: rename and cleanup dma_resv_get_list v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When the comment needs to state explicitly that this is doesn't get a reference to the object then the function is named rather badly. Rename the function and use it in even more places. v2: use dma_resv_shared_list as new name Signed-off-by: Christian König Acked-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210602111714.212426-5-christian.koenig@amd.com --- include/linux/dma-resv.h | 27 +++++++++++++-------------- 1 file changed, 13 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index e3a7f740bb06..8dc19d65a217 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -78,20 +78,6 @@ struct dma_resv { #define dma_resv_held(obj) lockdep_is_held(&(obj)->lock.base) #define dma_resv_assert_held(obj) lockdep_assert_held(&(obj)->lock.base) -/** - * dma_resv_get_list - get the reservation object's - * shared fence list, with update-side lock held - * @obj: the reservation object - * - * Returns the shared fence list. Does NOT take references to - * the fence. The obj->lock must be held. - */ -static inline struct dma_resv_list *dma_resv_get_list(struct dma_resv *obj) -{ - return rcu_dereference_protected(obj->fence, - dma_resv_held(obj)); -} - #ifdef CONFIG_DEBUG_MUTEXES void dma_resv_reset_shared_max(struct dma_resv *obj); #else @@ -268,6 +254,19 @@ dma_resv_get_excl_rcu(struct dma_resv *obj) return fence; } +/** + * dma_resv_shared_list - get the reservation object's shared fence list + * @obj: the reservation object + * + * Returns the shared fence list. Caller must either hold the objects + * through dma_resv_lock() or the RCU read side lock through rcu_read_lock(), + * or one of the variants of each + */ +static inline struct dma_resv_list *dma_resv_shared_list(struct dma_resv *obj) +{ + return rcu_dereference_check(obj->fence, dma_resv_held(obj)); +} + void dma_resv_init(struct dma_resv *obj); void dma_resv_fini(struct dma_resv *obj); int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences); -- cgit v1.2.3 From 6b41323a265a02b7af906c6d6fd93f6cddd7ac12 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Wed, 2 Jun 2021 12:44:32 +0200 Subject: dma-buf: rename dma_resv_get_excl_rcu to _unlocked MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit That describes much better what the function is doing here. Signed-off-by: Christian König Reviewed-by: Jason Ekstrand Acked-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210602111714.212426-6-christian.koenig@amd.com --- include/linux/dma-resv.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index 8dc19d65a217..3e0eefcead44 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -229,7 +229,7 @@ dma_resv_excl_fence(struct dma_resv *obj) } /** - * dma_resv_get_excl_rcu - get the reservation object's + * dma_resv_get_excl_unlocked - get the reservation object's * exclusive fence, without lock held. * @obj: the reservation object * @@ -240,7 +240,7 @@ dma_resv_excl_fence(struct dma_resv *obj) * The exclusive fence or NULL if none */ static inline struct dma_fence * -dma_resv_get_excl_rcu(struct dma_resv *obj) +dma_resv_get_excl_unlocked(struct dma_resv *obj) { struct dma_fence *fence; -- cgit v1.2.3 From d3fae3b3daac09961ab871a25093b0ae404282d5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Wed, 2 Jun 2021 13:01:15 +0200 Subject: dma-buf: drop the _rcu postfix on function names v3 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The functions can be called both in _rcu context as well as while holding the lock. v2: add some kerneldoc as suggested by Daniel v3: fix indentation Signed-off-by: Christian König Reviewed-by: Jason Ekstrand Acked-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210602111714.212426-7-christian.koenig@amd.com --- include/linux/dma-resv.h | 17 +++++------------ 1 file changed, 5 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index 3e0eefcead44..562b885cf9c3 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -271,19 +271,12 @@ void dma_resv_init(struct dma_resv *obj); void dma_resv_fini(struct dma_resv *obj); int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences); void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence); - void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence); - -int dma_resv_get_fences_rcu(struct dma_resv *obj, - struct dma_fence **pfence_excl, - unsigned *pshared_count, - struct dma_fence ***pshared); - +int dma_resv_get_fences(struct dma_resv *obj, struct dma_fence **pfence_excl, + unsigned *pshared_count, struct dma_fence ***pshared); int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src); - -long dma_resv_wait_timeout_rcu(struct dma_resv *obj, bool wait_all, bool intr, - unsigned long timeout); - -bool dma_resv_test_signaled_rcu(struct dma_resv *obj, bool test_all); +long dma_resv_wait_timeout(struct dma_resv *obj, bool wait_all, bool intr, + unsigned long timeout); +bool dma_resv_test_signaled(struct dma_resv *obj, bool test_all); #endif /* _LINUX_RESERVATION_H */ -- cgit v1.2.3 From aa5c8b25392800bbefa82dd19eeff8ebbf261ace Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Thu, 3 Jun 2021 17:58:35 +0100 Subject: i2c: core: Add stub for i2c_verify_client() if !CONFIG_I2C If I2C is not compiled, there is no way we should see a call to i2c_verify_client() on a device that is an i2c client. As such, provide a stub to return NULL to resolve an associated build failure. The build is failing with this link error ld: fxls8962af-core.o: in function `fxls8962af_fifo_transfer': fxls8962af-core.c: undefined reference to `i2c_verify_client' Reported-by: Tom Rix Signed-off-by: Jonathan Cameron Fixes: af959b7b96b8 ("iio: accel: fxls8962af: fix errata bug E3 - I2C burst reads") Reviewed-by: Sean Nyekjaer Acked-by: Wolfram Sang Link: https://lore.kernel.org/r/20210603165835.3594557-1-jic23@kernel.org --- include/linux/i2c.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index e8f2ac8c9c3d..7d71131c394e 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -343,7 +343,6 @@ struct i2c_client { }; #define to_i2c_client(d) container_of(d, struct i2c_client, dev) -struct i2c_client *i2c_verify_client(struct device *dev); struct i2c_adapter *i2c_verify_adapter(struct device *dev); const struct i2c_device_id *i2c_match_id(const struct i2c_device_id *id, const struct i2c_client *client); @@ -477,6 +476,13 @@ i2c_new_ancillary_device(struct i2c_client *client, u16 default_addr); void i2c_unregister_device(struct i2c_client *client); + +struct i2c_client *i2c_verify_client(struct device *dev); +#else +static inline struct i2c_client *i2c_verify_client(struct device *dev) +{ + return NULL; +} #endif /* I2C */ /* Mainboard arch_initcall() code should register all its I2C devices. -- cgit v1.2.3 From 64c2c2c62f92339b176ea24403d8db16db36f9e6 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 25 May 2021 16:07:48 +0200 Subject: quota: Change quotactl_path() systcall to an fd-based one Some users have pointed out that path-based syscalls are problematic in some environments and at least directory fd argument and possibly also resolve flags are desirable for such syscalls. Rather than reimplementing all details of pathname lookup and following where it may eventually evolve, let's go for full file descriptor based syscall similar to how ioctl(2) works since the beginning. Managing of quotas isn't performance sensitive so the extra overhead of open does not matter and we are able to consume O_PATH descriptors as well which makes open cheap anyway. Also for frequent operations (such as retrieving usage information for all users) we can reuse single fd and in fact get even better performance as well as avoiding races with possible remounts etc. Tested-by: Sascha Hauer Acked-by: Christian Brauner Reviewed-by: Christoph Hellwig Signed-off-by: Jan Kara --- include/linux/syscalls.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 050511e8f1f8..586128d5c3b8 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -485,8 +485,8 @@ asmlinkage long sys_pipe2(int __user *fildes, int flags); /* fs/quota.c */ asmlinkage long sys_quotactl(unsigned int cmd, const char __user *special, qid_t id, void __user *addr); -asmlinkage long sys_quotactl_path(unsigned int cmd, const char __user *mountpoint, - qid_t id, void __user *addr); +asmlinkage long sys_quotactl_fd(unsigned int fd, unsigned int cmd, qid_t id, + void __user *addr); /* fs/readdir.c */ asmlinkage long sys_getdents64(unsigned int fd, -- cgit v1.2.3 From ef4b65e53cc77e2b3ca4667b461047ad04fb45fa Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 31 May 2021 00:08:09 +0200 Subject: netfilter: nfnetlink: add struct nfgenmsg to struct nfnl_info and use it Update the nfnl_info structure to add a pointer to the nfnetlink header. This simplifies the existing codebase since this header is usually accessed. Update existing clients to use this new field. Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 515ce53aa20d..241e005f290a 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -11,6 +11,7 @@ struct nfnl_info { struct net *net; struct sock *sk; const struct nlmsghdr *nlh; + const struct nfgenmsg *nfmsg; struct netlink_ext_ack *extack; }; -- cgit v1.2.3 From 7b4b2fa37587394fb89fa51a4bea0820a1b37a5d Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 4 Jun 2021 12:27:06 +0200 Subject: netfilter: annotate nf_tables base hook ops This will allow a followup patch to treat the 'ops->priv' pointer as nft_chain argument without having to first walk the table/chains to check if there is a matching base chain pointer. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index f161569fbe2f..3fda1a508733 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -77,12 +77,18 @@ struct nf_hook_state { typedef unsigned int nf_hookfn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); +enum nf_hook_ops_type { + NF_HOOK_OP_UNDEFINED, + NF_HOOK_OP_NF_TABLES, +}; + struct nf_hook_ops { /* User fills in from here down. */ nf_hookfn *hook; struct net_device *dev; void *priv; - u_int8_t pf; + u8 pf; + enum nf_hook_ops_type hook_ops_type:8; unsigned int hooknum; /* Hooks are ordered in ascending priority. */ int priority; -- cgit v1.2.3 From 5c1a72a0fbe1b02c3ce0537f85f92ea935e0beec Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 4 Jun 2021 19:50:45 +0300 Subject: ACPI: property: Constify stubs for CONFIG_ACPI=n case There is a few stubs that left untouched during constification of the fwnode related APIs. Constify three more stubs here. Fixes: 8b9d6802583a ("ACPI: Constify acpi_bus helper functions, switch to macros") Reported-by: kernel test robot Signed-off-by: Andy Shevchenko [ rjw: Subject edit ] Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index c60745f657e9..40657f220f8b 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -765,7 +765,7 @@ static inline bool is_acpi_device_node(const struct fwnode_handle *fwnode) return false; } -static inline struct acpi_device *to_acpi_device_node(struct fwnode_handle *fwnode) +static inline struct acpi_device *to_acpi_device_node(const struct fwnode_handle *fwnode) { return NULL; } @@ -775,12 +775,12 @@ static inline bool is_acpi_data_node(const struct fwnode_handle *fwnode) return false; } -static inline struct acpi_data_node *to_acpi_data_node(struct fwnode_handle *fwnode) +static inline struct acpi_data_node *to_acpi_data_node(const struct fwnode_handle *fwnode) { return NULL; } -static inline bool acpi_data_node_match(struct fwnode_handle *fwnode, +static inline bool acpi_data_node_match(const struct fwnode_handle *fwnode, const char *name) { return false; -- cgit v1.2.3 From 3d7c821c1d8071e517048c8b4afdf33109441c0f Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 4 Jun 2021 19:50:46 +0300 Subject: ACPI: scan: Constify acpi_dma_supported() helper function Constify arguments to acpi_dma_supported(). The function doesn't need to change the content of the passed argument and when it's const it allows to supply the result of other functions that may return a pointer to a constant object. Signed-off-by: Andy Shevchenko [ rjw: Subject edit ] Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 40657f220f8b..97f1c5588b5a 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -911,7 +911,7 @@ acpi_create_platform_device(struct acpi_device *adev, return NULL; } -static inline bool acpi_dma_supported(struct acpi_device *adev) +static inline bool acpi_dma_supported(const struct acpi_device *adev) { return false; } -- cgit v1.2.3 From fb38f314fbd173e2e9f9f0f2e720a5f4889562da Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 4 Jun 2021 19:50:47 +0300 Subject: device property: Unify access to of_node Historically we have a few variants how we access dev->fwnode and dev->of_node. Some of the functions during development gained different versions of the getters. Unify access to of_node and as a side change slightly refactor ACPI specific branches. Signed-off-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- include/linux/property.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index 0d876316e61d..073e680c35e2 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -119,7 +119,7 @@ struct fwnode_handle *device_get_named_child_node(struct device *dev, struct fwnode_handle *fwnode_handle_get(struct fwnode_handle *fwnode); void fwnode_handle_put(struct fwnode_handle *fwnode); -int fwnode_irq_get(struct fwnode_handle *fwnode, unsigned int index); +int fwnode_irq_get(const struct fwnode_handle *fwnode, unsigned int index); unsigned int device_get_child_node_count(struct device *dev); -- cgit v1.2.3 From 9b3c47f124b60770f7738710e95801284d69d24f Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Sat, 5 Jun 2021 00:58:57 +0200 Subject: gpio: regmap: move drvdata to config data Drop gpio_regmap_set_drvdata() and instead add it to the configuration data passed to gpio_regmap_register(). gpio_regmap_set_drvdata() can't really be used in a race free way. This is because the gpio_regmap object which is needed by _set_drvdata() is returned by gpio_regmap_register(). On the other hand, the callbacks which use the drvdata might already be called right after the gpiochip_add() call in gpio_regmap_register(). Therefore, we have to provide the drvdata early before we call gpiochip_add(). Signed-off-by: Matti Vaittinen Signed-off-by: Michael Walle Reviewed-by: Linus Walleij Signed-off-by: Bartosz Golaszewski --- include/linux/gpio/regmap.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gpio/regmap.h b/include/linux/gpio/regmap.h index 334dd928042b..a9f7b7faf57b 100644 --- a/include/linux/gpio/regmap.h +++ b/include/linux/gpio/regmap.h @@ -37,6 +37,9 @@ struct regmap; * offset to a register/bitmask pair. If not * given the default gpio_regmap_simple_xlate() * is used. + * @drvdata: (Optional) Pointer to driver specific data which is + * not used by gpio-remap but is provided "as is" to the + * driver callback(s). * * The ->reg_mask_xlate translates a given base address and GPIO offset to * register and mask pair. The base address is one of the given register @@ -78,13 +81,14 @@ struct gpio_regmap_config { int (*reg_mask_xlate)(struct gpio_regmap *gpio, unsigned int base, unsigned int offset, unsigned int *reg, unsigned int *mask); + + void *drvdata; }; struct gpio_regmap *gpio_regmap_register(const struct gpio_regmap_config *config); void gpio_regmap_unregister(struct gpio_regmap *gpio); struct gpio_regmap *devm_gpio_regmap_register(struct device *dev, const struct gpio_regmap_config *config); -void gpio_regmap_set_drvdata(struct gpio_regmap *gpio, void *data); void *gpio_regmap_get_drvdata(struct gpio_regmap *gpio); #endif /* _LINUX_GPIO_REGMAP_H */ -- cgit v1.2.3 From a9e10e58730432e5de840eb3ddd55c75f29341b3 Mon Sep 17 00:00:00 2001 From: Daniel Scally Date: Thu, 3 Jun 2021 23:40:02 +0100 Subject: ACPI: scan: Extend acpi_walk_dep_device_list() The acpi_walk_dep_device_list() function is not as generic as its name implies, serving only to decrement the dependency count for each dependent device of the input. Extend it to accept a callback which can be applied to all the dependencies in acpi_dep_list. Replace all existing calls to the function with calls to a wrapper, passing a callback that applies the same dependency reduction. Reviewed-by: Andy Shevchenko Acked-by: Maximilian Luz # for platform/surface parts Signed-off-by: Daniel Scally [ rjw: Changelog edits ] Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index c60745f657e9..170b9bebdb2b 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -666,7 +666,9 @@ extern bool acpi_driver_match_device(struct device *dev, const struct device_driver *drv); int acpi_device_uevent_modalias(struct device *, struct kobj_uevent_env *); int acpi_device_modalias(struct device *, char *, int); -void acpi_walk_dep_device_list(acpi_handle handle); +int acpi_walk_dep_device_list(acpi_handle handle, + int (*callback)(struct acpi_dep_data *, void *), + void *data); struct platform_device *acpi_create_platform_device(struct acpi_device *, struct property_entry *); -- cgit v1.2.3 From bcd23f93d3984a94d64ce0b6bbfa3789c0e8ebaf Mon Sep 17 00:00:00 2001 From: Maxim Kochetkov Date: Tue, 25 May 2021 06:42:03 +0300 Subject: regmap-irq: Introduce inverted status registers support Some interrupt controllers have inverted status register: cleared bits is active interrupts and set bits is inactive interrupts, so add inverted status support to the framework. Signed-off-by: Maxim Kochetkov Link: https://lore.kernel.org/r/20210525034204.5272-1-fido_max@inbox.ru Signed-off-by: Mark Brown --- include/linux/regmap.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index bf5a834d1774..f5f08dd0a116 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -1449,6 +1449,7 @@ struct regmap_irq_sub_irq_map { * @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. + * @status_invert: Inverted status register: cleared bits are active interrupts. * @runtime_pm: Hold a runtime PM lock on the device when accessing it. * * @num_regs: Number of registers in each control bank. @@ -1501,6 +1502,7 @@ struct regmap_irq_chip { bool type_in_mask:1; bool clear_on_unmask:1; bool not_fixed_stride:1; + bool status_invert:1; int num_regs; -- cgit v1.2.3 From eb550f53099bf5ff8dc5de93e275378510c891c9 Mon Sep 17 00:00:00 2001 From: Brett Creeley Date: Thu, 17 Sep 2020 13:13:33 -0700 Subject: virtchnl: Use pad byte in virtchnl_ether_addr to specify MAC type Currently, there is no way for a VF driver to specify that it wants to change its device/primary unicast MAC address. This makes it difficult/impossible for the PF driver to track the VF's device/primary unicast MAC address, which is used for VM/VF reboot and displaying on the host. Fix this by using 2 bits of a pad byte in the virtchnl_ether_addr structure so the VF can specify what type of MAC it's adding/deleting. Below are the values that should be used by all VF drivers going forward. VIRTCHNL_ETHER_ADDR_LEGACY(0): - The type should only ever be 0 for legacy AVF drivers (i.e. drivers that don't support the new type bits). The PF drivers will track VF's device/primary unicast MAC, but this will only be a best effort. VIRTCHNL_ETHER_ADDR_PRIMARY(1): - This type should only be used when the VF is changing their device/primary unicast MAC. It should be used for both delete and add cases related to the device/primary unicast MAC. VIRTCHNL_ETHER_ADDR_EXTRA(2): - This type should be used when the VF is adding and/or deleting MAC addresses that are not the device/primary unicast MAC. For example, extra unicast addresses and multicast addresses assuming the PF supports "extra" addresses at all. If a PF is parsing the type field of the virtchnl_ether_addr, then it should use the VIRTCHNL_ETHER_ADDR_TYPE_MASK to mask the first two bits of the type field since 0, 1, and 2 are the only valid values. Signed-off-by: Brett Creeley Signed-off-by: Tony Nguyen --- include/linux/avf/virtchnl.h | 29 ++++++++++++++++++++++++++++- 1 file changed, 28 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 565deea6ffe8..1fc07f3f99ab 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -412,9 +412,36 @@ VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_queue_select); * PF removes the filters and returns status. */ +/* VIRTCHNL_ETHER_ADDR_LEGACY + * Prior to adding the @type member to virtchnl_ether_addr, there were 2 pad + * bytes. Moving forward all VF drivers should not set type to + * VIRTCHNL_ETHER_ADDR_LEGACY. This is only here to not break previous/legacy + * behavior. The control plane function (i.e. PF) can use a best effort method + * of tracking the primary/device unicast in this case, but there is no + * guarantee and functionality depends on the implementation of the PF. + */ + +/* VIRTCHNL_ETHER_ADDR_PRIMARY + * All VF drivers should set @type to VIRTCHNL_ETHER_ADDR_PRIMARY for the + * primary/device unicast MAC address filter for VIRTCHNL_OP_ADD_ETH_ADDR and + * VIRTCHNL_OP_DEL_ETH_ADDR. This allows for the underlying control plane + * function (i.e. PF) to accurately track and use this MAC address for + * displaying on the host and for VM/function reset. + */ + +/* VIRTCHNL_ETHER_ADDR_EXTRA + * All VF drivers should set @type to VIRTCHNL_ETHER_ADDR_EXTRA for any extra + * unicast and/or multicast filters that are being added/deleted via + * VIRTCHNL_OP_DEL_ETH_ADDR/VIRTCHNL_OP_ADD_ETH_ADDR respectively. + */ struct virtchnl_ether_addr { u8 addr[ETH_ALEN]; - u8 pad[2]; + u8 type; +#define VIRTCHNL_ETHER_ADDR_LEGACY 0 +#define VIRTCHNL_ETHER_ADDR_PRIMARY 1 +#define VIRTCHNL_ETHER_ADDR_EXTRA 2 +#define VIRTCHNL_ETHER_ADDR_TYPE_MASK 3 /* first two bits of type are valid */ + u8 pad; }; VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_ether_addr); -- cgit v1.2.3 From c858d436be8b949c368de0e079084acaff3d4aaf Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 4 Jun 2021 17:01:48 +0300 Subject: net: phy: introduce PHY_INTERFACE_MODE_REVRMII The "reverse RMII" protocol name is a personal invention, derived from "reverse MII". Just like MII, RMII is an asymmetric protocol in that a PHY behaves differently than a MAC. In the case of RMII, for example: - the 50 MHz clock signals are either driven by the MAC or by an external oscillator (but never by the PHY). - the PHY can transmit extra in-band control symbols via RXD[1:0] which the MAC is supposed to understand, but a PHY isn't. The "reverse MII" protocol is not standardized either, except for this web document: https://www.eetimes.com/reverse-media-independent-interface-revmii-block-architecture/# In short, it means that the Ethernet controller speaks the 4-bit data parallel protocol from the perspective of a PHY (it acts like a PHY). This might mean that it implements clause 22 compatible registers, although that is optional - the important bit is that its pins can be connected to an MII MAC and it will 'just work'. In this discussion thread: https://lore.kernel.org/netdev/20210201214515.cx6ivvme2tlquge2@skbuf/ we agreed that it would be an abuse of terms to use the "RevMII" name for anything than the 4-bit parallel MII protocol. But since all the same concepts can be applied to the 2-bit Reduced MII protocol as well, here we are introducing a "Reverse RMII" protocol. This means: "behave like an RMII PHY". Signed-off-by: Vladimir Oltean Acked-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 852743f07e3e..ed332ac92e25 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -93,6 +93,7 @@ extern const int phy_10gbit_features_array[1]; * @PHY_INTERFACE_MODE_TBI: Ten Bit Interface * @PHY_INTERFACE_MODE_REVMII: Reverse Media Independent Interface * @PHY_INTERFACE_MODE_RMII: Reduced Media Independent Interface + * @PHY_INTERFACE_MODE_REVRMII: Reduced Media Independent Interface in PHY role * @PHY_INTERFACE_MODE_RGMII: Reduced gigabit media-independent interface * @PHY_INTERFACE_MODE_RGMII_ID: RGMII with Internal RX+TX delay * @PHY_INTERFACE_MODE_RGMII_RXID: RGMII with Internal RX delay @@ -126,6 +127,7 @@ typedef enum { PHY_INTERFACE_MODE_TBI, PHY_INTERFACE_MODE_REVMII, PHY_INTERFACE_MODE_RMII, + PHY_INTERFACE_MODE_REVRMII, PHY_INTERFACE_MODE_RGMII, PHY_INTERFACE_MODE_RGMII_ID, PHY_INTERFACE_MODE_RGMII_RXID, @@ -185,6 +187,8 @@ static inline const char *phy_modes(phy_interface_t interface) return "rev-mii"; case PHY_INTERFACE_MODE_RMII: return "rmii"; + case PHY_INTERFACE_MODE_REVRMII: + return "rev-rmii"; case PHY_INTERFACE_MODE_RGMII: return "rgmii"; case PHY_INTERFACE_MODE_RGMII_ID: -- cgit v1.2.3 From c07aea3ef4d4076f18f567b98ed01e082e02ed51 Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Mon, 7 Jun 2021 21:02:36 +0200 Subject: mm: add a signature in struct page This is needed by the page_pool to avoid recycling a page not allocated via page_pool. The page->signature field is aliased to page->lru.next and page->compound_head, but it can't be set by mistake because the signature value is a bad pointer, and can't trigger a false positive in PageTail() because the last bit is 0. Co-developed-by: Matthew Wilcox (Oracle) Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Matteo Croce Signed-off-by: David S. Miller --- include/linux/mm.h | 11 ++++++----- include/linux/mm_types.h | 7 +++++++ include/linux/poison.h | 3 +++ 3 files changed, 16 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index c274f75efcf9..a0434e8c2617 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1668,10 +1668,11 @@ struct address_space *page_mapping(struct page *page); static inline bool page_is_pfmemalloc(const struct page *page) { /* - * Page index cannot be this large so this must be - * a pfmemalloc page. + * lru.next has bit 1 set if the page is allocated from the + * pfmemalloc reserves. Callers may simply overwrite it if + * they do not need to preserve that information. */ - return page->index == -1UL; + return (uintptr_t)page->lru.next & BIT(1); } /* @@ -1680,12 +1681,12 @@ static inline bool page_is_pfmemalloc(const struct page *page) */ static inline void set_page_pfmemalloc(struct page *page) { - page->index = -1UL; + page->lru.next = (void *)BIT(1); } static inline void clear_page_pfmemalloc(struct page *page) { - page->index = 0; + page->lru.next = NULL; } /* diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 5aacc1c10a45..ed6862eacb52 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -96,6 +96,13 @@ struct page { unsigned long private; }; struct { /* page_pool used by netstack */ + /** + * @pp_magic: magic value to avoid recycling non + * page_pool allocated pages. + */ + unsigned long pp_magic; + struct page_pool *pp; + unsigned long _pp_mapping_pad; /** * @dma_addr: might require a 64-bit value on * 32-bit architectures. diff --git a/include/linux/poison.h b/include/linux/poison.h index aff1c9250c82..d62ef5a6b4e9 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -78,4 +78,7 @@ /********** security/ **********/ #define KEY_DESTROY 0xbd +/********** net/core/page_pool.c **********/ +#define PP_SIGNATURE (0x40 + POISON_POINTER_DELTA) + #endif -- cgit v1.2.3 From c420c98982fa9e749c99e022845d5f323d098b72 Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Mon, 7 Jun 2021 21:02:37 +0200 Subject: skbuff: add a parameter to __skb_frag_unref This is a prerequisite patch, the next one is enabling recycling of skbs and fragments. Add an extra argument on __skb_frag_unref() to handle recycling, and update the current users of the function with that. Signed-off-by: Matteo Croce Signed-off-by: David S. Miller --- include/linux/skbuff.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index dbf820a50a39..7fcfea7e7b21 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3081,10 +3081,12 @@ static inline void skb_frag_ref(struct sk_buff *skb, int f) /** * __skb_frag_unref - release a reference on a paged fragment. * @frag: the paged fragment + * @recycle: recycle the page if allocated via page_pool * - * Releases a reference on the paged fragment @frag. + * Releases a reference on the paged fragment @frag + * or recycles the page via the page_pool API. */ -static inline void __skb_frag_unref(skb_frag_t *frag) +static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle) { put_page(skb_frag_page(frag)); } @@ -3098,7 +3100,7 @@ static inline void __skb_frag_unref(skb_frag_t *frag) */ static inline void skb_frag_unref(struct sk_buff *skb, int f) { - __skb_frag_unref(&skb_shinfo(skb)->frags[f]); + __skb_frag_unref(&skb_shinfo(skb)->frags[f], false); } /** -- cgit v1.2.3 From 6a5bcd84e886a9a91982e515c539529c28acdcc2 Mon Sep 17 00:00:00 2001 From: Ilias Apalodimas Date: Mon, 7 Jun 2021 21:02:38 +0200 Subject: page_pool: Allow drivers to hint on SKB recycling Up to now several high speed NICs have custom mechanisms of recycling the allocated memory they use for their payloads. Our page_pool API already has recycling capabilities that are always used when we are running in 'XDP mode'. So let's tweak the API and the kernel network stack slightly and allow the recycling to happen even during the standard operation. The API doesn't take into account 'split page' policies used by those drivers currently, but can be extended once we have users for that. The idea is to be able to intercept the packet on skb_release_data(). If it's a buffer coming from our page_pool API recycle it back to the pool for further usage or just release the packet entirely. To achieve that we introduce a bit in struct sk_buff (pp_recycle:1) and a field in struct page (page->pp) to store the page_pool pointer. Storing the information in page->pp allows us to recycle both SKBs and their fragments. We could have skipped the skb bit entirely, since identical information can bederived from struct page. However, in an effort to affect the free path as less as possible, reading a single bit in the skb which is already in cache, is better that trying to derive identical information for the page stored data. The driver or page_pool has to take care of the sync operations on it's own during the buffer recycling since the buffer is, after opting-in to the recycling, never unmapped. Since the gain on the drivers depends on the architecture, we are not enabling recycling by default if the page_pool API is used on a driver. In order to enable recycling the driver must call skb_mark_for_recycle() to store the information we need for recycling in page->pp and enabling the recycling bit, or page_pool_store_mem_info() for a fragment. Co-developed-by: Jesper Dangaard Brouer Signed-off-by: Jesper Dangaard Brouer Co-developed-by: Matteo Croce Signed-off-by: Matteo Croce Signed-off-by: Ilias Apalodimas Signed-off-by: David S. Miller --- include/linux/skbuff.h | 33 ++++++++++++++++++++++++++++++--- 1 file changed, 30 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7fcfea7e7b21..b2db9cd9a73f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -37,6 +37,7 @@ #include #include #include +#include #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include #endif @@ -667,6 +668,8 @@ typedef unsigned char *sk_buff_data_t; * @head_frag: skb was allocated from page fragments, * not allocated by kmalloc() or vmalloc(). * @pfmemalloc: skbuff was allocated from PFMEMALLOC reserves + * @pp_recycle: mark the packet for recycling instead of freeing (implies + * page_pool support on driver) * @active_extensions: active extensions (skb_ext_id types) * @ndisc_nodetype: router type (from link layer) * @ooo_okay: allow the mapping of a socket to a queue to be changed @@ -791,10 +794,12 @@ struct sk_buff { fclone:2, peeked:1, head_frag:1, - pfmemalloc:1; + pfmemalloc:1, + pp_recycle:1; /* page_pool recycle indicator */ #ifdef CONFIG_SKB_EXTENSIONS __u8 active_extensions; #endif + /* fields enclosed in headers_start/headers_end are copied * using a single memcpy() in __copy_skb_header() */ @@ -3088,7 +3093,13 @@ static inline void skb_frag_ref(struct sk_buff *skb, int f) */ static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle) { - put_page(skb_frag_page(frag)); + struct page *page = skb_frag_page(frag); + +#ifdef CONFIG_PAGE_POOL + if (recycle && page_pool_return_skb_page(page)) + return; +#endif + put_page(page); } /** @@ -3100,7 +3111,7 @@ static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle) */ static inline void skb_frag_unref(struct sk_buff *skb, int f) { - __skb_frag_unref(&skb_shinfo(skb)->frags[f], false); + __skb_frag_unref(&skb_shinfo(skb)->frags[f], skb->pp_recycle); } /** @@ -4699,5 +4710,21 @@ static inline u64 skb_get_kcov_handle(struct sk_buff *skb) #endif } +#ifdef CONFIG_PAGE_POOL +static inline void skb_mark_for_recycle(struct sk_buff *skb, struct page *page, + struct page_pool *pp) +{ + skb->pp_recycle = 1; + page_pool_store_mem_info(page, pp); +} +#endif + +static inline bool skb_pp_recycle(struct sk_buff *skb, void *data) +{ + if (!IS_ENABLED(CONFIG_PAGE_POOL) || !skb->pp_recycle) + return false; + return page_pool_return_skb_page(virt_to_page(data)); +} + #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ -- cgit v1.2.3 From bb6bfd79d9bc69f0808a4156ec3ca9fb78694039 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 27 May 2021 14:37:09 -0500 Subject: iommu: Remove unused of_get_dma_window() of_get_dma_window() was added in 2012 and removed in 2014 in commit 891846516317 ("memory: Add NVIDIA Tegra memory controller support"). Remove it and simplify the header to use forward declarations for structs rather than includes. Cc: Joerg Roedel Cc: Will Deacon Cc: Frank Rowand Cc: iommu@lists.linux-foundation.org Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20210527193710.1281746-1-robh@kernel.org Signed-off-by: Joerg Roedel --- include/linux/of_iommu.h | 17 +++-------------- 1 file changed, 3 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_iommu.h b/include/linux/of_iommu.h index 16f4b3e87f20..55c1eb300a86 100644 --- a/include/linux/of_iommu.h +++ b/include/linux/of_iommu.h @@ -2,29 +2,18 @@ #ifndef __OF_IOMMU_H #define __OF_IOMMU_H -#include -#include -#include +struct device; +struct device_node; +struct iommu_ops; #ifdef CONFIG_OF_IOMMU -extern int of_get_dma_window(struct device_node *dn, const char *prefix, - int index, unsigned long *busno, dma_addr_t *addr, - size_t *size); - extern const struct iommu_ops *of_iommu_configure(struct device *dev, struct device_node *master_np, const u32 *id); #else -static inline int of_get_dma_window(struct device_node *dn, const char *prefix, - int index, unsigned long *busno, dma_addr_t *addr, - size_t *size) -{ - return -EINVAL; -} - static inline const struct iommu_ops *of_iommu_configure(struct device *dev, struct device_node *master_np, const u32 *id) -- cgit v1.2.3 From cfa7ff959a789a953eac40c8ac793e2cfc2db931 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 3 Jun 2021 19:41:18 +0100 Subject: arm64: smccc: Support SMCCC v1.3 SVE register saving hint SMCCC v1.2 requires that all SVE state be preserved over SMC calls which introduces substantial overhead in the common case where there is no SVE state in the registers. To avoid this SMCCC v1.3 introduces a flag which allows the caller to say that there is no state that needs to be preserved in the registers. Make use of this flag, setting it if the SMCCC version indicates support for it and the TIF_ flags indicate that there is no live SVE state in the registers, this avoids placing any constraints on when SMCCC calls can be done or triggering extra saving and reloading of SVE register state in the kernel. This would be straightforward enough except for the rather entertaining inline assembly we use to do SMCCC v1.1 calls to allow us to take advantage of the limited number of registers it clobbers. Deal with this by having a function which we call immediately before issuing the SMCCC call to make our checks and set the flag. Using alternatives the overhead if SVE is supported but not detected at runtime can be reduced to a single NOP. Signed-off-by: Mark Brown Reviewed-by: Ard Biesheuvel Reviewed-by: Marc Zyngier Link: https://lore.kernel.org/r/20210603184118.15090-1-broonie@kernel.org Signed-off-by: Will Deacon --- include/linux/arm-smccc.h | 33 +++++++++++++++++++++++++++++++-- 1 file changed, 31 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 5cef2b8b0479..7d1cabe15262 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -63,6 +63,9 @@ #define ARM_SMCCC_VERSION_1_0 0x10000 #define ARM_SMCCC_VERSION_1_1 0x10001 #define ARM_SMCCC_VERSION_1_2 0x10002 +#define ARM_SMCCC_VERSION_1_3 0x10003 + +#define ARM_SMCCC_1_3_SVE_HINT 0x10000 #define ARM_SMCCC_VERSION_FUNC_ID \ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ @@ -216,6 +219,8 @@ u32 arm_smccc_get_version(void); void __init arm_smccc_version_init(u32 version, enum arm_smccc_conduit conduit); +extern u64 smccc_has_sve_hint; + /** * struct arm_smccc_res - Result from SMC/HVC call * @a0-a3 result values from registers 0 to 3 @@ -295,6 +300,15 @@ struct arm_smccc_quirk { } state; }; +/** + * __arm_smccc_sve_check() - Set the SVE hint bit when doing SMC calls + * + * Sets the SMCCC hint bit to indicate if there is live state in the SVE + * registers, this modifies x0 in place and should never be called from C + * code. + */ +asmlinkage unsigned long __arm_smccc_sve_check(unsigned long x0); + /** * __arm_smccc_smc() - make SMC calls * @a0-a7: arguments passed in registers 0 to 7 @@ -352,6 +366,20 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, #endif +/* nVHE hypervisor doesn't have a current thread so needs separate checks */ +#if defined(CONFIG_ARM64_SVE) && !defined(__KVM_NVHE_HYPERVISOR__) + +#define SMCCC_SVE_CHECK ALTERNATIVE("nop \n", "bl __arm_smccc_sve_check \n", \ + ARM64_SVE) +#define smccc_sve_clobbers "x16", "x30", "cc", + +#else + +#define SMCCC_SVE_CHECK +#define smccc_sve_clobbers + +#endif + #define ___count_args(_0, _1, _2, _3, _4, _5, _6, _7, _8, x, ...) x #define __count_args(...) \ @@ -419,7 +447,7 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, #define ___constraints(count) \ : __constraint_read_ ## count \ - : "memory" + : smccc_sve_clobbers "memory" #define __constraints(count) ___constraints(count) /* @@ -434,7 +462,8 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, register unsigned long r2 asm("r2"); \ register unsigned long r3 asm("r3"); \ __declare_args(__count_args(__VA_ARGS__), __VA_ARGS__); \ - asm volatile(inst "\n" : \ + asm volatile(SMCCC_SVE_CHECK \ + inst "\n" : \ "=r" (r0), "=r" (r1), "=r" (r2), "=r" (r3) \ __constraints(__count_args(__VA_ARGS__))); \ if (___res) \ -- cgit v1.2.3 From 5617c9125bb66a923f3560d5739eb7f3a21c00b5 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sat, 29 May 2021 16:52:32 +0200 Subject: clkdev: remove unused clkdev_alloc() interfaces The last user of clkdev_alloc() and clkdev_hw_alloc() was removed last year, so everything now calls clkdev_create() and clkdev_hw_create() instead. Removing the unused functions lets the compiler optimize the remaining ones slightly better. Fixes: e5006671acc7 ("clk: versatile: Drop the legacy IM-PD1 clock code") Reviewed-by: Stephen Boyd Signed-off-by: Arnd Bergmann --- include/linux/clkdev.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clkdev.h b/include/linux/clkdev.h index fd06b2780a22..8a8423eb8e9a 100644 --- a/include/linux/clkdev.h +++ b/include/linux/clkdev.h @@ -30,11 +30,6 @@ struct clk_lookup { .clk = c, \ } -struct clk_lookup *clkdev_alloc(struct clk *clk, const char *con_id, - const char *dev_fmt, ...) __printf(3, 4); -struct clk_lookup *clkdev_hw_alloc(struct clk_hw *hw, const char *con_id, - const char *dev_fmt, ...) __printf(3, 4); - void clkdev_add(struct clk_lookup *cl); void clkdev_drop(struct clk_lookup *cl); -- cgit v1.2.3 From 149876d96877eedce0ae3ffbd64edb56360b8926 Mon Sep 17 00:00:00 2001 From: Huilong Deng Date: Sat, 5 Jun 2021 12:53:02 +0800 Subject: seqlock: Remove trailing semicolon in macros Macros should not use a trailing semicolon. Signed-off-by: Huilong Deng Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210605045302.37154-1-denghuilong@cdjrlc.com --- include/linux/seqlock.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index f61e34fbaaea..37ded6b8fee6 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -182,9 +182,9 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s) #define seqcount_raw_spinlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, raw_spinlock) #define seqcount_spinlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, spinlock) -#define seqcount_rwlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, rwlock); -#define seqcount_mutex_init(s, lock) seqcount_LOCKNAME_init(s, lock, mutex); -#define seqcount_ww_mutex_init(s, lock) seqcount_LOCKNAME_init(s, lock, ww_mutex); +#define seqcount_rwlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, rwlock) +#define seqcount_mutex_init(s, lock) seqcount_LOCKNAME_init(s, lock, mutex) +#define seqcount_ww_mutex_init(s, lock) seqcount_LOCKNAME_init(s, lock, ww_mutex) /* * SEQCOUNT_LOCKNAME() - Instantiate seqcount_LOCKNAME_t and helpers -- cgit v1.2.3 From 3958e2d0c34e18c41b60dc01832bd670a59ef70f Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 24 May 2021 12:53:39 -0700 Subject: cgroup: make per-cgroup pressure stall tracking configurable PSI accounts stalls for each cgroup separately and aggregates it at each level of the hierarchy. This causes additional overhead with psi_avgs_work being called for each cgroup in the hierarchy. psi_avgs_work has been highly optimized, however on systems with large number of cgroups the overhead becomes noticeable. Systems which use PSI only at the system level could avoid this overhead if PSI can be configured to skip per-cgroup stall accounting. Add "cgroup_disable=pressure" kernel command-line option to allow requesting system-wide only pressure stall accounting. When set, it keeps system-wide accounting under /proc/pressure/ but skips accounting for individual cgroups and does not expose PSI nodes in cgroup hierarchy. Signed-off-by: Suren Baghdasaryan Acked-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Signed-off-by: Tejun Heo --- include/linux/cgroup-defs.h | 1 + include/linux/cgroup.h | 7 +++++++ 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 1a1f3e8faceb..e1c705fdfa7c 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -113,6 +113,7 @@ enum { CFTYPE_NO_PREFIX = (1 << 3), /* (DON'T USE FOR NEW FILES) no subsys prefix */ CFTYPE_WORLD_WRITABLE = (1 << 4), /* (DON'T USE FOR NEW FILES) S_IWUGO */ CFTYPE_DEBUG = (1 << 5), /* create when cgroup_debug */ + CFTYPE_PRESSURE = (1 << 6), /* only if pressure feature is enabled */ /* internal flags, do not use outside cgroup core proper */ __CFTYPE_ONLY_ON_DFL = (1 << 16), /* only on default hierarchy */ diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 9047fa853dd3..2cc237e3e8b3 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -676,6 +676,8 @@ static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) return &cgrp->psi; } +bool cgroup_psi_enabled(void); + static inline void cgroup_init_kthreadd(void) { /* @@ -735,6 +737,11 @@ static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) return NULL; } +static inline bool cgroup_psi_enabled(void) +{ + return false; +} + static inline bool task_under_cgroup_hierarchy(struct task_struct *task, struct cgroup *ancestor) { -- cgit v1.2.3 From c9c9762d4d44dcb1b2ba90cfb4122dc11ceebf31 Mon Sep 17 00:00:00 2001 From: Long Li Date: Mon, 7 Jun 2021 12:34:05 -0700 Subject: block: return the correct bvec when checking for gaps After commit 07173c3ec276 ("block: enable multipage bvecs"), a bvec can have multiple pages. But bio_will_gap() still assumes one page bvec while checking for merging. If the pages in the bvec go across the seg_boundary_mask, this check for merging can potentially succeed if only the 1st page is tested, and can fail if all the pages are tested. Later, when SCSI builds the SG list the same check for merging is done in __blk_segment_map_sg_merge() with all the pages in the bvec tested. This time the check may fail if the pages in bvec go across the seg_boundary_mask (but tested okay in bio_will_gap() earlier, so those BIOs were merged). If this check fails, we end up with a broken SG list for drivers assuming the SG list not having offsets in intermediate pages. This results in incorrect pages written to the disk. Fix this by returning the multi-page bvec when testing gaps for merging. Cc: Jens Axboe Cc: Johannes Thumshirn Cc: Pavel Begunkov Cc: Ming Lei Cc: Tejun Heo Cc: "Matthew Wilcox (Oracle)" Cc: Jeffle Xu Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org Fixes: 07173c3ec276 ("block: enable multipage bvecs") Signed-off-by: Long Li Reviewed-by: Ming Lei Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/1623094445-22332-1-git-send-email-longli@linuxonhyperv.com Signed-off-by: Jens Axboe --- include/linux/bio.h | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index a0b4cfdf62a4..d2b98efb5cc5 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -44,9 +44,6 @@ static inline unsigned int bio_max_segs(unsigned int nr_segs) #define bio_offset(bio) bio_iter_offset((bio), (bio)->bi_iter) #define bio_iovec(bio) bio_iter_iovec((bio), (bio)->bi_iter) -#define bio_multiple_segments(bio) \ - ((bio)->bi_iter.bi_size != bio_iovec(bio).bv_len) - #define bvec_iter_sectors(iter) ((iter).bi_size >> 9) #define bvec_iter_end_sector(iter) ((iter).bi_sector + bvec_iter_sectors((iter))) @@ -271,7 +268,7 @@ static inline void bio_clear_flag(struct bio *bio, unsigned int bit) static inline void bio_get_first_bvec(struct bio *bio, struct bio_vec *bv) { - *bv = bio_iovec(bio); + *bv = mp_bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter); } static inline void bio_get_last_bvec(struct bio *bio, struct bio_vec *bv) @@ -279,10 +276,9 @@ static inline void bio_get_last_bvec(struct bio *bio, struct bio_vec *bv) struct bvec_iter iter = bio->bi_iter; int idx; - if (unlikely(!bio_multiple_segments(bio))) { - *bv = bio_iovec(bio); - return; - } + bio_get_first_bvec(bio, bv); + if (bv->bv_len == bio->bi_iter.bi_size) + return; /* this bio only has a single bvec */ bio_advance_iter(bio, &iter, iter.bi_size); -- cgit v1.2.3 From 11c7aa0ddea8611007768d3e6b58d45dc60a19e1 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 7 Jun 2021 13:26:13 +0200 Subject: rq-qos: fix missed wake-ups in rq_qos_throttle try two Commit 545fbd0775ba ("rq-qos: fix missed wake-ups in rq_qos_throttle") tried to fix a problem that a process could be sleeping in rq_qos_wait() without anyone to wake it up. However the fix is not complete and the following can still happen: CPU1 (waiter1) CPU2 (waiter2) CPU3 (waker) rq_qos_wait() rq_qos_wait() acquire_inflight_cb() -> fails acquire_inflight_cb() -> fails completes IOs, inflight decreased prepare_to_wait_exclusive() prepare_to_wait_exclusive() has_sleeper = !wq_has_single_sleeper() -> true as there are two sleepers has_sleeper = !wq_has_single_sleeper() -> true io_schedule() io_schedule() Deadlock as now there's nobody to wakeup the two waiters. The logic automatically blocking when there are already sleepers is really subtle and the only way to make it work reliably is that we check whether there are some waiters in the queue when adding ourselves there. That way, we are guaranteed that at least the first process to enter the wait queue will recheck the waiting condition before going to sleep and thus guarantee forward progress. Fixes: 545fbd0775ba ("rq-qos: fix missed wake-ups in rq_qos_throttle") CC: stable@vger.kernel.org Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20210607112613.25344-1-jack@suse.cz Signed-off-by: Jens Axboe --- include/linux/wait.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index fe10e8570a52..6598ae35e1b5 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -1136,7 +1136,7 @@ do { \ * Waitqueues which are removed from the waitqueue_head at wakeup time */ void prepare_to_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); -void prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); +bool prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); long prepare_to_wait_event(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); void finish_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout); -- cgit v1.2.3 From f27abde3042ab4d30d0003eaf5e6641baef94a56 Mon Sep 17 00:00:00 2001 From: Voon Weifeng Date: Tue, 8 Jun 2021 11:51:57 +0800 Subject: net: pcs: add 2500BASEX support for Intel mGbE controller XPCS IP supports 2500BASEX as PHY interface. It is configured as autonegotiation disable to cater for PHYs that does not supports 2500BASEX autonegotiation. v2: Add supported link speed masking. v3: Restructure to introduce xpcs_config_2500basex() used to configure the xpcs for 2.5G speeds. Added 2500BASEX specific information for configuration. v4: Fix indentation error Signed-off-by: Voon Weifeng Signed-off-by: Michael Sit Wei Hong Signed-off-by: David S. Miller --- include/linux/pcs/pcs-xpcs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index 0860a5b59f10..4d815f03b4b2 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -13,6 +13,7 @@ /* AN mode */ #define DW_AN_C73 1 #define DW_AN_C37_SGMII 2 +#define DW_2500BASEX 3 struct xpcs_id; -- cgit v1.2.3 From 46682cb86a37da435e5668db98555a1de0f0448b Mon Sep 17 00:00:00 2001 From: Voon Weifeng Date: Tue, 8 Jun 2021 11:51:58 +0800 Subject: net: stmmac: enable Intel mGbE 2.5Gbps link speed The Intel mGbE supports 2.5Gbps link speed by increasing the clock rate by 2.5 times of the original rate. In this mode, the serdes/PHY operates at a serial baud rate of 3.125 Gbps and the PCS data path and GMII interface of the MAC operate at 312.5 MHz instead of 125 MHz. For Intel mGbE, the overclocking of 2.5 times clock rate to support 2.5G is only able to be configured in the BIOS during boot time. Kernel driver has no access to modify the clock rate for 1Gbps/2.5G mode. The way to determined the current 1G/2.5G mode is by reading a dedicated adhoc register through mdio bus. In short, after the system boot up, it is either in 1G mode or 2.5G mode which not able to be changed on the fly. Compared to 1G mode, the 2.5G mode selects the 2500BASEX as PHY interface and disables the xpcs_an_inband. This is to cater for some PHYs that only supports 2500BASEX PHY interface with no autonegotiation. v2: remove MAC supported link speed masking v3: Restructure to introduce intel_speed_mode_2500() to read serdes registers for max speed supported and select the appropritate configuration. Use max_speed to determine the supported link speed mask. Signed-off-by: Voon Weifeng Signed-off-by: Michael Sit Wei Hong Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/stmmac.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index e55a4807e3ea..b10be3385a30 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -223,6 +223,7 @@ struct plat_stmmacenet_data { void (*fix_mac_speed)(void *priv, unsigned int speed); int (*serdes_powerup)(struct net_device *ndev, void *priv); void (*serdes_powerdown)(struct net_device *ndev, void *priv); + void (*speed_mode_2500)(struct net_device *ndev, void *priv); void (*ptp_clk_freq_config)(void *priv); int (*init)(struct platform_device *pdev, void *priv); void (*exit)(struct platform_device *pdev, void *priv); -- cgit v1.2.3 From b64d76b782264aa91c236c11c72646459b04c301 Mon Sep 17 00:00:00 2001 From: Sergey Ryazanov Date: Tue, 8 Jun 2021 07:02:34 +0300 Subject: net: wwan: make WWAN_PORT_MAX meaning less surprised It is quite unusual when some value can not be equal to a defined range max value. Also most subsystems defines FOO_TYPE_MAX as a maximum valid value. So turn the WAN_PORT_MAX meaning from the number of supported port types to the maximum valid port type. Signed-off-by: Sergey Ryazanov Reviewed-by: Loic Poulain Signed-off-by: David S. Miller --- include/linux/wwan.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/wwan.h b/include/linux/wwan.h index 7216c114d758..fa33cc16d931 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -15,8 +15,10 @@ * @WWAN_PORT_QMI: Qcom modem/MSM interface for modem control * @WWAN_PORT_QCDM: Qcom Modem diagnostic interface * @WWAN_PORT_FIREHOSE: XML based command protocol - * @WWAN_PORT_UNKNOWN: Unknown port type - * @WWAN_PORT_MAX: Number of supported port types + * + * @WWAN_PORT_MAX: Highest supported port types + * @WWAN_PORT_UNKNOWN: Special value to indicate an unknown port type + * @__WWAN_PORT_MAX: Internal use */ enum wwan_port_type { WWAN_PORT_AT, @@ -24,8 +26,12 @@ enum wwan_port_type { WWAN_PORT_QMI, WWAN_PORT_QCDM, WWAN_PORT_FIREHOSE, + + /* Add new port types above this line */ + + __WWAN_PORT_MAX, + WWAN_PORT_MAX = __WWAN_PORT_MAX - 1, WWAN_PORT_UNKNOWN, - WWAN_PORT_MAX = WWAN_PORT_UNKNOWN, }; struct wwan_port; -- cgit v1.2.3 From e67f325e9cd67562b761e884680c0fec03a6f404 Mon Sep 17 00:00:00 2001 From: Matthew Hagan Date: Tue, 8 Jun 2021 19:59:06 +0100 Subject: net: stmmac: explicitly deassert GMAC_AHB_RESET We are currently assuming that GMAC_AHB_RESET will already be deasserted by the bootloader. However if this has not been done, probing of the GMAC will fail. To remedy this we must ensure GMAC_AHB_RESET has been deasserted prior to probing. v2 changes: - remove NULL condition check for stmmac_ahb_rst in stmmac_main.c - unwrap dev_err() message in stmmac_main.c - add PTR_ERR() around plat->stmmac_ahb_rst in stmmac_platform.c v3 changes: - add error pointer to dev_err() output - add reset_control_assert(stmmac_ahb_rst) in stmmac_dvr_remove - revert PTR_ERR() around plat->stmmac_ahb_rst since this is performed on the returned value of ret by the calling function Signed-off-by: Matthew Hagan Signed-off-by: David S. Miller --- include/linux/stmmac.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index b10be3385a30..3867980d1447 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -240,6 +240,7 @@ struct plat_stmmacenet_data { unsigned int mult_fact_100ns; s32 ptp_max_adj; struct reset_control *stmmac_rst; + struct reset_control *stmmac_ahb_rst; struct stmmac_axi *axi; int has_gmac4; bool has_sun8i; -- cgit v1.2.3 From 0899431f95a7a695f342527548b24ffd902c68ab Mon Sep 17 00:00:00 2001 From: Dario Binacchi Date: Sun, 6 Jun 2021 22:22:53 +0200 Subject: clk: ti: add am33xx/am43xx spread spectrum clock support The patch enables spread spectrum clocking (SSC) for MPU and LCD PLLs. As reported by the TI spruh73x/spruhl7x RM, SSC is only supported for the DISP/LCD and MPU PLLs on am33xx/am43xx. SSC is not supported for DDR, PER, and CORE PLLs. Calculating the required values and setting the registers accordingly was taken from the set_mpu_spreadspectrum routine contained in the arch/arm/mach-omap2/am33xx/clock_am33xx.c file of the u-boot project. In locked condition, DPLL output clock = CLKINP *[M/N]. In case of SSC enabled, the reference manual explains that there is a restriction of range of M values. Since the omap2_dpll_round_rate routine attempts to select the minimum possible N, the value of M obtained is not guaranteed to be within the range required. With the new "ti,min-div" parameter it is possible to increase N and consequently M to satisfy the constraint imposed by SSC. Signed-off-by: Dario Binacchi Reviewed-by: Tero Kristo Link: https://lore.kernel.org/r/20210606202253.31649-6-dariobin@libero.it Signed-off-by: Stephen Boyd --- include/linux/clk/ti.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index c62f6fa6763d..3486f20a3753 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -63,6 +63,17 @@ struct clk_omap_reg { * @auto_recal_bit: bitshift of the driftguard enable bit in @control_reg * @recal_en_bit: bitshift of the PRM_IRQENABLE_* bit for recalibration IRQs * @recal_st_bit: bitshift of the PRM_IRQSTATUS_* bit for recalibration IRQs + * @ssc_deltam_reg: register containing the DPLL SSC frequency spreading + * @ssc_modfreq_reg: register containing the DPLL SSC modulation frequency + * @ssc_modfreq_mant_mask: mask of the mantissa component in @ssc_modfreq_reg + * @ssc_modfreq_exp_mask: mask of the exponent component in @ssc_modfreq_reg + * @ssc_enable_mask: mask of the DPLL SSC enable bit in @control_reg + * @ssc_downspread_mask: mask of the DPLL SSC low frequency only bit in + * @control_reg + * @ssc_modfreq: the DPLL SSC frequency modulation in kHz + * @ssc_deltam: the DPLL SSC frequency spreading in permille (10th of percent) + * @ssc_downspread: require the only low frequency spread of the DPLL in SSC + * mode * @flags: DPLL type/features (see below) * * Possible values for @flags: @@ -110,6 +121,17 @@ struct dpll_data { u8 auto_recal_bit; u8 recal_en_bit; u8 recal_st_bit; + struct clk_omap_reg ssc_deltam_reg; + struct clk_omap_reg ssc_modfreq_reg; + u32 ssc_deltam_int_mask; + u32 ssc_deltam_frac_mask; + u32 ssc_modfreq_mant_mask; + u32 ssc_modfreq_exp_mask; + u32 ssc_enable_mask; + u32 ssc_downspread_mask; + u32 ssc_modfreq; + u32 ssc_deltam; + bool ssc_downspread; u8 flags; }; -- cgit v1.2.3 From 4ccf359849ce709f4bf0214b4b5b8b6891d38770 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 9 Jun 2021 09:19:18 +0200 Subject: spi: remove spi_set_cs_timing() No one seems to be using this global and exported function, so remove it as it is no longer needed. Cc: Mark Brown Signed-off-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20210609071918.2852069-1-gregkh@linuxfoundation.org Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 74239d65c7fd..f924160e995f 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -1108,11 +1108,6 @@ static inline void spi_message_free(struct spi_message *m) kfree(m); } -extern int spi_set_cs_timing(struct spi_device *spi, - struct spi_delay *setup, - struct spi_delay *hold, - struct spi_delay *inactive); - extern int spi_setup(struct spi_device *spi); extern int spi_async(struct spi_device *spi, struct spi_message *message); extern int spi_async_locked(struct spi_device *spi, -- cgit v1.2.3 From 48a74b1147f7db4623eaed591cc01eb740b871c0 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Wed, 9 Jun 2021 13:28:06 +0200 Subject: reset: Add compile-test stubs Add stubs for the reset controller registration functions to allow building reset controller provider drivers with the COMPILE_TEST Kconfig option enabled. Reported-by: Krzysztof Kozlowski Suggested-by: Dmitry Osipenko Signed-off-by: Thierry Reding Link: https://lore.kernel.org/r/20210609112806.3565057-3-thierry.reding@gmail.com Signed-off-by: Philipp Zabel --- include/linux/reset-controller.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/reset-controller.h b/include/linux/reset-controller.h index ec35814e0bbb..0fa4f60e1186 100644 --- a/include/linux/reset-controller.h +++ b/include/linux/reset-controller.h @@ -79,6 +79,7 @@ struct reset_controller_dev { unsigned int nr_resets; }; +#if IS_ENABLED(CONFIG_RESET_CONTROLLER) int reset_controller_register(struct reset_controller_dev *rcdev); void reset_controller_unregister(struct reset_controller_dev *rcdev); @@ -88,5 +89,26 @@ int devm_reset_controller_register(struct device *dev, void reset_controller_add_lookup(struct reset_control_lookup *lookup, unsigned int num_entries); +#else +static inline int reset_controller_register(struct reset_controller_dev *rcdev) +{ + return 0; +} + +static inline void reset_controller_unregister(struct reset_controller_dev *rcdev) +{ +} + +static inline int devm_reset_controller_register(struct device *dev, + struct reset_controller_dev *rcdev) +{ + return 0; +} + +static inline void reset_controller_add_lookup(struct reset_control_lookup *lookup, + unsigned int num_entries) +{ +} +#endif #endif -- cgit v1.2.3 From a69008475fc565cec5a760f1997f326773c84aac Mon Sep 17 00:00:00 2001 From: Shaokun Zhang Date: Mon, 7 Jun 2021 18:48:53 +0800 Subject: vt: vt_kern.h, remove the repeated declaration Function 'vt_set_led_state' is declared twice, so remove the repeated declaration. Cc: Jiri Slaby Signed-off-by: Shaokun Zhang Link: https://lore.kernel.org/r/1623062933-52943-1-git-send-email-zhangshaokun@hisilicon.com Signed-off-by: Greg Kroah-Hartman --- include/linux/vt_kern.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h index 94e7a315479c..0da94a6dee15 100644 --- a/include/linux/vt_kern.h +++ b/include/linux/vt_kern.h @@ -166,7 +166,6 @@ int vt_get_kbd_mode_bit(int console, int bit); void vt_set_kbd_mode_bit(int console, int bit); void vt_clr_kbd_mode_bit(int console, int bit); void vt_set_led_state(int console, int leds); -void vt_set_led_state(int console, int leds); void vt_kbd_con_start(int console); void vt_kbd_con_stop(int console); -- cgit v1.2.3 From e7555cf6c263d95d2bb2bddb5bb57c240f0d608a Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Tue, 8 Jun 2021 14:23:45 -0700 Subject: fpga: bridge: change FPGA indirect article to an Change use of 'a fpga' to 'an fpga' Signed-off-by: Tom Rix Link: https://lore.kernel.org/r/20210608212350.3029742-8-trix@redhat.com Signed-off-by: Greg Kroah-Hartman --- include/linux/fpga/fpga-bridge.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fpga/fpga-bridge.h b/include/linux/fpga/fpga-bridge.h index 817600a32c93..6c3c28806ff1 100644 --- a/include/linux/fpga/fpga-bridge.h +++ b/include/linux/fpga/fpga-bridge.h @@ -11,7 +11,7 @@ struct fpga_bridge; /** * struct fpga_bridge_ops - ops for low level FPGA bridge drivers * @enable_show: returns the FPGA bridge's status - * @enable_set: set a FPGA bridge as enabled or disabled + * @enable_set: set an FPGA bridge as enabled or disabled * @fpga_bridge_remove: set FPGA into a specific state during driver remove * @groups: optional attribute groups. */ -- cgit v1.2.3 From 895ec9c09aa77e9f0129576995cb21191d3958f1 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Tue, 8 Jun 2021 14:23:46 -0700 Subject: fpga-mgr: change FPGA indirect article to an Change use of 'a fpga' to 'an fpga' Signed-off-by: Tom Rix Link: https://lore.kernel.org/r/20210608212350.3029742-9-trix@redhat.com Signed-off-by: Greg Kroah-Hartman --- include/linux/fpga/fpga-mgr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fpga/fpga-mgr.h b/include/linux/fpga/fpga-mgr.h index 2bc3030a69e5..ec2cd8bfceb0 100644 --- a/include/linux/fpga/fpga-mgr.h +++ b/include/linux/fpga/fpga-mgr.h @@ -75,7 +75,7 @@ enum fpga_mgr_states { #define FPGA_MGR_COMPRESSED_BITSTREAM BIT(4) /** - * struct fpga_image_info - information specific to a FPGA image + * struct fpga_image_info - information specific to an FPGA image * @flags: boolean flags as defined above * @enable_timeout_us: maximum time to enable traffic through bridge (uSec) * @disable_timeout_us: maximum time to disable traffic through bridge (uSec) -- cgit v1.2.3 From 67133eaa93e810f5c510cd0ec6e2e7ca76fc1340 Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Tue, 9 Mar 2021 03:29:16 +0200 Subject: net/mlx5: mlx5_ifc support for header insert/remove Add support for HCA caps 2 that contains capabilities for the new insert/remove header actions. Added the required definitions for supporting the new reformat type: added packet reformat parameters, reformat anchors and definitions to allow copy/set into the inserted EMD (Embedded MetaData) tag. Signed-off-by: Yevgeny Kliteynik Signed-off-by: Vlad Buslov Reviewed-by: Jianbo Liu Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 10 ++++++++++ include/linux/mlx5/mlx5_ifc.h | 40 ++++++++++++++++++++++++++++++++++------ 2 files changed, 44 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 578c4ccae91c..0025913505ab 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1179,6 +1179,7 @@ enum mlx5_cap_type { MLX5_CAP_VDPA_EMULATION = 0x13, MLX5_CAP_DEV_EVENT = 0x14, MLX5_CAP_IPSEC, + MLX5_CAP_GENERAL_2 = 0x20, /* NUM OF CAP Types */ MLX5_CAP_NUM }; @@ -1220,6 +1221,15 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_GEN_MAX(mdev, cap) \ MLX5_GET(cmd_hca_cap, mdev->caps.hca_max[MLX5_CAP_GENERAL], cap) +#define MLX5_CAP_GEN_2(mdev, cap) \ + MLX5_GET(cmd_hca_cap_2, mdev->caps.hca_cur[MLX5_CAP_GENERAL_2], cap) + +#define MLX5_CAP_GEN_2_64(mdev, cap) \ + MLX5_GET64(cmd_hca_cap_2, mdev->caps.hca_cur[MLX5_CAP_GENERAL_2], cap) + +#define MLX5_CAP_GEN_2_MAX(mdev, cap) \ + MLX5_GET(cmd_hca_cap_2, mdev->caps.hca_max[MLX5_CAP_GENERAL_2], cap) + #define MLX5_CAP_ETH(mdev, cap) \ MLX5_GET(per_protocol_networking_offload_caps,\ mdev->caps.hca_cur[MLX5_CAP_ETHERNET_OFFLOADS], cap) diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index eb86e80e4643..057db0eaf195 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -435,7 +435,10 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 reserved_at_40[0x20]; - u8 reserved_at_60[0x18]; + u8 reserved_at_60[0x2]; + u8 reformat_insert[0x1]; + u8 reformat_remove[0x1]; + u8 reserver_at_64[0x14]; u8 log_max_ft_num[0x8]; u8 reserved_at_80[0x10]; @@ -1312,7 +1315,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_0[0x1f]; u8 vhca_resource_manager[0x1]; - u8 reserved_at_20[0x3]; + u8 hca_cap_2[0x1]; + u8 reserved_at_21[0x2]; u8 event_on_vhca_state_teardown_request[0x1]; u8 event_on_vhca_state_in_use[0x1]; u8 event_on_vhca_state_active[0x1]; @@ -1732,6 +1736,17 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_7c0[0x40]; }; +struct mlx5_ifc_cmd_hca_cap_2_bits { + u8 reserved_at_0[0xa0]; + + u8 max_reformat_insert_size[0x8]; + u8 max_reformat_insert_offset[0x8]; + u8 max_reformat_remove_size[0x8]; + u8 max_reformat_remove_offset[0x8]; + + u8 reserved_at_c0[0x740]; +}; + enum mlx5_flow_destination_type { MLX5_FLOW_DESTINATION_TYPE_VPORT = 0x0, MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE = 0x1, @@ -3105,6 +3120,7 @@ struct mlx5_ifc_roce_addr_layout_bits { union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_cmd_hca_cap_bits cmd_hca_cap; + struct mlx5_ifc_cmd_hca_cap_2_bits cmd_hca_cap_2; struct mlx5_ifc_odp_cap_bits odp_cap; struct mlx5_ifc_atomic_caps_bits atomic_caps; struct mlx5_ifc_roce_cap_bits roce_cap; @@ -5785,12 +5801,14 @@ struct mlx5_ifc_query_eq_in_bits { }; struct mlx5_ifc_packet_reformat_context_in_bits { - u8 reserved_at_0[0x5]; - u8 reformat_type[0x3]; - u8 reserved_at_8[0xe]; + u8 reformat_type[0x8]; + u8 reserved_at_8[0x4]; + u8 reformat_param_0[0x4]; + u8 reserved_at_10[0x6]; u8 reformat_data_size[0xa]; - u8 reserved_at_20[0x10]; + u8 reformat_param_1[0x8]; + u8 reserved_at_28[0x8]; u8 reformat_data[2][0x8]; u8 more_reformat_data[][0x8]; @@ -5830,12 +5848,20 @@ struct mlx5_ifc_alloc_packet_reformat_context_out_bits { u8 reserved_at_60[0x20]; }; +enum { + MLX5_REFORMAT_CONTEXT_ANCHOR_MAC_START = 0x1, + MLX5_REFORMAT_CONTEXT_ANCHOR_IP_START = 0x7, + MLX5_REFORMAT_CONTEXT_ANCHOR_TCP_UDP_START = 0x9, +}; + enum mlx5_reformat_ctx_type { MLX5_REFORMAT_TYPE_L2_TO_VXLAN = 0x0, MLX5_REFORMAT_TYPE_L2_TO_NVGRE = 0x1, MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL = 0x2, MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2 = 0x3, MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL = 0x4, + MLX5_REFORMAT_TYPE_INSERT_HDR = 0xf, + MLX5_REFORMAT_TYPE_REMOVE_HDR = 0x10, }; struct mlx5_ifc_alloc_packet_reformat_context_in_bits { @@ -5956,6 +5982,8 @@ enum { MLX5_ACTION_IN_FIELD_OUT_TCP_SEQ_NUM = 0x59, MLX5_ACTION_IN_FIELD_OUT_TCP_ACK_NUM = 0x5B, MLX5_ACTION_IN_FIELD_IPSEC_SYNDROME = 0x5D, + MLX5_ACTION_IN_FIELD_OUT_EMD_47_32 = 0x6F, + MLX5_ACTION_IN_FIELD_OUT_EMD_31_0 = 0x70, }; struct mlx5_ifc_alloc_modify_header_context_out_bits { -- cgit v1.2.3 From 3f3f05ab88722224fef5b0b78a0969f6b54f2cba Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Tue, 9 Mar 2021 03:30:44 +0200 Subject: net/mlx5: Added new parameters to reformat context Adding new reformat context type (INSERT_HEADER) requires adding two new parameters to reformat context - reformat_param_0 and reformat_param_1. As defined by HW spec, these parameters have different meaning for different reformat context type. The first parameter (reformat_param_0) is not new to HW spec, but it wasn't used by any of the supported reformats. The second parameter (reformat_param_1) is new to the HW spec - it was added to allow supporting INSERT_HEADER. For NSERT_HEADER, reformat_param_0 indicates the header used to reference the location of the inserted header, and reformat_param_1 indicates the offset of the inserted header from the reference point defined by reformat_param_0. Signed-off-by: Yevgeny Kliteynik Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 1f51f4c3b1af..f69f68fba946 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -254,10 +254,16 @@ struct mlx5_modify_hdr *mlx5_modify_header_alloc(struct mlx5_core_dev *dev, void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, struct mlx5_modify_hdr *modify_hdr); +struct mlx5_pkt_reformat_params { + int type; + u8 param_0; + u8 param_1; + size_t size; + void *data; +}; + struct mlx5_pkt_reformat *mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, - int reformat_type, - size_t size, - void *reformat_data, + struct mlx5_pkt_reformat_params *params, enum mlx5_flow_namespace_type ns_type); void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev, struct mlx5_pkt_reformat *reformat); -- cgit v1.2.3 From ec3be8873df3bf467ead27f7cedc896cbb2bd819 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Thu, 4 Mar 2021 13:09:53 +0200 Subject: net/mlx5: Create TC-miss priority and table In order to adhere to kernel software datapath model bridge offloads must come after TC and NF FDBs. Following patches in this series add new FDB priority for bridge after FDB_FT_OFFLOAD. However, since netfilter offload is implemented with unmanaged tables, its miss path is not automatically connected to next priority and requires the code to manually connect with slow table. To keep bridge offloads encapsulated and not mix it with eswitch offloads, create a new FDB_TC_MISS priority between FDB_FT_OFFLOAD and FDB_SLOW_PATH: + | +---------v----------+ | | | FDB_TC_OFFLOAD | | | +---------+----------+ | | | +---------v----------+ | | | FDB_FT_OFFLOAD | | | +---------+----------+ | | | +---------v----------+ | | | FDB_TC_MISS | | | +---------+----------+ | | | +---------v----------+ | | | FDB_SLOW_PATH | | | +---------+----------+ | v Initialize the new priority with single default empty managed table and use the table as TC/NF miss patch instead of slow table. This approach allows bridge offloads to be created as new FDB namespace priority between FDB_TC_MISS and FDB_SLOW_PATH without exposing its internal tables to any other modules since miss path of managed TC-miss table is automatically wired to next priority. Signed-off-by: Vlad Buslov Reviewed-by: Jianbo Liu Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index f69f68fba946..271f2f4d6b60 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -87,6 +87,7 @@ enum { FDB_BYPASS_PATH, FDB_TC_OFFLOAD, FDB_FT_OFFLOAD, + FDB_TC_MISS, FDB_SLOW_PATH, FDB_PER_VPORT, }; -- cgit v1.2.3 From 19e9bfa044f32655f1c14e95784be93da34e103e Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Fri, 2 Apr 2021 15:57:02 +0300 Subject: net/mlx5: Bridge, add offload infrastructure Create new files bridge.{c|h} in en/rep directory that implement bridge interaction with representor netdevices and handle required events/notifications, bridge.{c|h} in esw directory that implement all necessary eswitch offloading infrastructure and works on vport/eswitch level. Provide new kconfig MLX5_BRIDGE which is automatically selected when both kernel bridge and mlx5 eswitch configs are enabled. Provide basic infrastructure for bridge offloads: - struct mlx5_esw_bridge_offloads - per-eswitch bridge offload structure that encapsulates generic bridge-offloads data (notifier blocks, ingress flow table/group, etc.) that is created/deleted on enable/disable eswitch offloads. - struct mlx5_esw_bridge - per-bridge structure that encapsulates per-bridge data (reference counter, FDB, egress flow table/group, etc.) that is created when first eswitch represetor is attached to new bridge and deleted when last representor is removed from the bridge as a result of NETDEV_CHANGEUPPER event. The bridge tables are created with new priority FDB_BR_OFFLOAD in FDB namespace. The new priority is between tc-miss and slow path priorities. Priority consist of two levels: the ingress table that is global per eswitch and matches incoming packets by src_mac/vid and redirects them to next level (egress table) that is chosen according to ingress port bridge membership and matches on dst_mac/vid in order to redirect packet to vport according to the following diagram: + | +---------v----------+ | | | FDB_TC_OFFLOAD | | | +---------+----------+ | | +---------v----------+ | | | FDB_FT_OFFLOAD | | | +---------+----------+ | | +---------v----------+ | | | FDB_TC_MISS | | | +---------+----------+ | +--------------------------------------+ | | | | +------+ | | | | | +------v--------+ FDB_BR_OFFLOAD | | | INGRESS_TABLE | | | +------+---+----+ | | | | match | | | +---------+ | | | | | +-------+ | | +-------v-------+ match | | | | | | EGRESS_TABLE +------------> vport | | | +-------+-------+ | | | | | | | +-------+ | | miss | | | +------+------+ | | | | +--------------------------------------+ | | +---------v----------+ | | | FDB_SLOW_PATH | | | +---------+----------+ | v Signed-off-by: Vlad Buslov Reviewed-by: Jianbo Liu Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 271f2f4d6b60..77746f7e35b8 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -88,6 +88,7 @@ enum { FDB_TC_OFFLOAD, FDB_FT_OFFLOAD, FDB_TC_MISS, + FDB_BR_OFFLOAD, FDB_SLOW_PATH, FDB_PER_VPORT, }; -- cgit v1.2.3 From 40483774141625b9685b177fb6e1f36de48d33f8 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Thu, 10 Jun 2021 10:00:59 +0800 Subject: iommu/vt-d: Use iommu_sva_alloc(free)_pasid() helpers Align the pasid alloc/free code with the generic helpers defined in the iommu core. This also refactored the SVA binding code to improve the readability. Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20210520031531.712333-1-baolu.lu@linux.intel.com Link: https://lore.kernel.org/r/20210610020115.1637656-8-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 03faf20a6817..4e8bb186daa7 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -791,7 +791,6 @@ struct intel_svm { u32 pasid; int gpasid; /* In case that guest PASID is different from host PASID */ struct list_head devs; - struct list_head list; }; #else static inline void intel_svm_check(struct intel_iommu *iommu) {} -- cgit v1.2.3 From 4c82b88696ac57810ab923b3c5b0734646b9b69f Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Thu, 10 Jun 2021 10:01:02 +0800 Subject: iommu/vt-d: Allocate/register iopf queue for sva devices This allocates and registers the iopf queue infrastructure for devices which want to support IO page fault for SVA. Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20210520031531.712333-1-baolu.lu@linux.intel.com Link: https://lore.kernel.org/r/20210610020115.1637656-11-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 4e8bb186daa7..222520d149c1 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -606,6 +606,8 @@ struct intel_iommu { struct completion prq_complete; struct ioasid_allocator_ops pasid_allocator; /* Custom allocator for PASIDs */ #endif + struct iopf_queue *iopf_queue; + unsigned char iopfq_name[16]; struct q_inval *qi; /* Queued invalidation info */ u32 *iommu_state; /* Store iommu states between suspend and resume.*/ -- cgit v1.2.3 From e93a67f5a0eef3e9ab5b4649cac5c3b831c6a9db Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Thu, 10 Jun 2021 10:01:04 +0800 Subject: iommu/vt-d: Add prq_report trace event This adds a new trace event to track the page fault request report. This event will provide almost all information defined in a page request descriptor. A sample output: | prq_report: dmar0/0000:00:0a.0 seq# 1: rid=0x50 addr=0x559ef6f97 r---- pasid=0x2 index=0x1 | prq_report: dmar0/0000:00:0a.0 seq# 2: rid=0x50 addr=0x559ef6f9c rw--l pasid=0x2 index=0x1 | prq_report: dmar0/0000:00:0a.0 seq# 3: rid=0x50 addr=0x559ef6f98 r---- pasid=0x2 index=0x1 | prq_report: dmar0/0000:00:0a.0 seq# 4: rid=0x50 addr=0x559ef6f9d rw--l pasid=0x2 index=0x1 | prq_report: dmar0/0000:00:0a.0 seq# 5: rid=0x50 addr=0x559ef6f99 r---- pasid=0x2 index=0x1 | prq_report: dmar0/0000:00:0a.0 seq# 6: rid=0x50 addr=0x559ef6f9e rw--l pasid=0x2 index=0x1 | prq_report: dmar0/0000:00:0a.0 seq# 7: rid=0x50 addr=0x559ef6f9a r---- pasid=0x2 index=0x1 | prq_report: dmar0/0000:00:0a.0 seq# 8: rid=0x50 addr=0x559ef6f9f rw--l pasid=0x2 index=0x1 This will be helpful for I/O page fault related debugging. Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20210520031531.712333-1-baolu.lu@linux.intel.com Link: https://lore.kernel.org/r/20210610020115.1637656-13-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 222520d149c1..98b04fa9373e 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -778,6 +778,7 @@ struct intel_svm_dev { struct device *dev; struct intel_iommu *iommu; struct iommu_sva sva; + unsigned long prq_seq_number; u32 pasid; int users; u16 did; @@ -828,4 +829,32 @@ static inline int iommu_calculate_max_sagaw(struct intel_iommu *iommu) #define intel_iommu_enabled (0) #endif +static inline const char *decode_prq_descriptor(char *str, size_t size, + u64 dw0, u64 dw1, u64 dw2, u64 dw3) +{ + char *buf = str; + int bytes; + + bytes = snprintf(buf, size, + "rid=0x%llx addr=0x%llx %c%c%c%c%c pasid=0x%llx index=0x%llx", + FIELD_GET(GENMASK_ULL(31, 16), dw0), + FIELD_GET(GENMASK_ULL(63, 12), dw1), + dw1 & BIT_ULL(0) ? 'r' : '-', + dw1 & BIT_ULL(1) ? 'w' : '-', + dw0 & BIT_ULL(52) ? 'x' : '-', + dw0 & BIT_ULL(53) ? 'p' : '-', + dw1 & BIT_ULL(2) ? 'l' : '-', + FIELD_GET(GENMASK_ULL(51, 32), dw0), + FIELD_GET(GENMASK_ULL(11, 3), dw1)); + + /* Private Data */ + if (dw0 & BIT_ULL(9)) { + size -= bytes; + buf += bytes; + snprintf(buf, size, " private=0x%llx/0x%llx\n", dw2, dw3); + } + + return str; +} + #endif -- cgit v1.2.3 From 55ee5e67a59a1b6f388d7a1c7b24022145f47a3e Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Thu, 10 Jun 2021 10:01:05 +0800 Subject: iommu/vt-d: Add common code for dmar latency performance monitors The execution time of some operations is very performance critical, such as cache invalidation and PRQ processing time. This adds some common code to monitor the execution time range of those operations. The interfaces include enabling/disabling, checking status, updating sampling data and providing a common string format for users. Signed-off-by: Fenghua Yu Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20210520031531.712333-1-baolu.lu@linux.intel.com Link: https://lore.kernel.org/r/20210610020115.1637656-14-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 98b04fa9373e..f5cf31dd7280 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -621,6 +621,7 @@ struct intel_iommu { u32 flags; /* Software defined flags */ struct dmar_drhd_unit *drhd; + void *perf_statistic; }; /* Per subdevice private data */ -- cgit v1.2.3 From 1f106ff0ea2782a6bc49bb927e4789681a2ec507 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Thu, 10 Jun 2021 10:01:11 +0800 Subject: iommu/vt-d: Use bitfields for DMAR capabilities IOTLB device presence, iommu coherency and snooping are boolean capabilities. Use them as bits and keep them adjacent. Structure layout before the reorg. $ pahole -C dmar_domain drivers/iommu/intel/dmar.o struct dmar_domain { int nid; /* 0 4 */ unsigned int iommu_refcnt[128]; /* 4 512 */ /* --- cacheline 8 boundary (512 bytes) was 4 bytes ago --- */ u16 iommu_did[128]; /* 516 256 */ /* --- cacheline 12 boundary (768 bytes) was 4 bytes ago --- */ bool has_iotlb_device; /* 772 1 */ /* XXX 3 bytes hole, try to pack */ struct list_head devices; /* 776 16 */ struct list_head subdevices; /* 792 16 */ struct iova_domain iovad __attribute__((__aligned__(8))); /* 808 2320 */ /* --- cacheline 48 boundary (3072 bytes) was 56 bytes ago --- */ struct dma_pte * pgd; /* 3128 8 */ /* --- cacheline 49 boundary (3136 bytes) --- */ int gaw; /* 3136 4 */ int agaw; /* 3140 4 */ int flags; /* 3144 4 */ int iommu_coherency; /* 3148 4 */ int iommu_snooping; /* 3152 4 */ int iommu_count; /* 3156 4 */ int iommu_superpage; /* 3160 4 */ /* XXX 4 bytes hole, try to pack */ u64 max_addr; /* 3168 8 */ u32 default_pasid; /* 3176 4 */ /* XXX 4 bytes hole, try to pack */ struct iommu_domain domain; /* 3184 72 */ /* size: 3256, cachelines: 51, members: 18 */ /* sum members: 3245, holes: 3, sum holes: 11 */ /* forced alignments: 1 */ /* last cacheline: 56 bytes */ } __attribute__((__aligned__(8))); After arranging it for natural padding and to make flags as u8 bits, it saves 8 bytes for the struct. struct dmar_domain { int nid; /* 0 4 */ unsigned int iommu_refcnt[128]; /* 4 512 */ /* --- cacheline 8 boundary (512 bytes) was 4 bytes ago --- */ u16 iommu_did[128]; /* 516 256 */ /* --- cacheline 12 boundary (768 bytes) was 4 bytes ago --- */ u8 has_iotlb_device:1; /* 772: 0 1 */ u8 iommu_coherency:1; /* 772: 1 1 */ u8 iommu_snooping:1; /* 772: 2 1 */ /* XXX 5 bits hole, try to pack */ /* XXX 3 bytes hole, try to pack */ struct list_head devices; /* 776 16 */ struct list_head subdevices; /* 792 16 */ struct iova_domain iovad __attribute__((__aligned__(8))); /* 808 2320 */ /* --- cacheline 48 boundary (3072 bytes) was 56 bytes ago --- */ struct dma_pte * pgd; /* 3128 8 */ /* --- cacheline 49 boundary (3136 bytes) --- */ int gaw; /* 3136 4 */ int agaw; /* 3140 4 */ int flags; /* 3144 4 */ int iommu_count; /* 3148 4 */ int iommu_superpage; /* 3152 4 */ /* XXX 4 bytes hole, try to pack */ u64 max_addr; /* 3160 8 */ u32 default_pasid; /* 3168 4 */ /* XXX 4 bytes hole, try to pack */ struct iommu_domain domain; /* 3176 72 */ /* size: 3248, cachelines: 51, members: 18 */ /* sum members: 3236, holes: 3, sum holes: 11 */ /* sum bitfield members: 3 bits, bit holes: 1, sum bit holes: 5 bits */ /* forced alignments: 1 */ /* last cacheline: 48 bytes */ } __attribute__((__aligned__(8))); Signed-off-by: Parav Pandit Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20210530075053.264218-1-parav@nvidia.com Link: https://lore.kernel.org/r/20210610020115.1637656-20-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index f5cf31dd7280..2621eff04c82 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -546,7 +546,10 @@ struct dmar_domain { * domain ids are 16 bit wide according * to VT-d spec, section 9.3 */ - bool has_iotlb_device; + u8 has_iotlb_device: 1; + u8 iommu_coherency: 1; /* indicate coherency of iommu access */ + u8 iommu_snooping: 1; /* indicate snooping control feature */ + struct list_head devices; /* all devices' list */ struct list_head subdevices; /* all subdevices' list */ struct iova_domain iovad; /* iova's that belong to this domain */ @@ -558,9 +561,6 @@ struct dmar_domain { int agaw; int flags; /* flags to find out type of domain */ - - int iommu_coherency;/* indicate coherency of iommu access */ - int iommu_snooping; /* indicate snooping control feature*/ int iommu_count; /* reference count of iommu */ int iommu_superpage;/* Level of superpages supported: 0 == 4KiB (no superpages), 1 == 2MiB, -- cgit v1.2.3 From 74f6d776ae0b8498cfdb574ab24992bd50a2a2f1 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Thu, 10 Jun 2021 10:01:12 +0800 Subject: iommu/vt-d: Removed unused iommu_count in dmar domain DMAR domain uses per DMAR refcount. It is indexed by iommu seq_id. Older iommu_count is only incremented and decremented but no decisions are taken based on this refcount. This is not of much use. Hence, remove iommu_count and further simplify domain_detach_iommu() by returning void. Signed-off-by: Parav Pandit Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20210530075053.264218-1-parav@nvidia.com Link: https://lore.kernel.org/r/20210610020115.1637656-21-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 2621eff04c82..574b932dfe86 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -561,7 +561,6 @@ struct dmar_domain { int agaw; int flags; /* flags to find out type of domain */ - int iommu_count; /* reference count of iommu */ int iommu_superpage;/* Level of superpages supported: 0 == 4KiB (no superpages), 1 == 2MiB, 2 == 1GiB, 3 == 512GiB, 4 == 1TiB */ -- cgit v1.2.3 From 9739ba327c01e26f672661ea751132c29a54d3d9 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Thu, 10 Jun 2021 10:01:14 +0800 Subject: iommu/vt-d: Define counter explicitly as unsigned int Avoid below checkpatch warning. WARNING: Prefer 'unsigned int' to bare use of 'unsigned' + unsigned iommu_refcnt[DMAR_UNITS_SUPPORTED]; Fixes: 29a27719abaa ("iommu/vt-d: Replace iommu_bmp with a refcount") Signed-off-by: Parav Pandit Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20210530075053.264218-1-parav@nvidia.com Link: https://lore.kernel.org/r/20210610020115.1637656-23-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 574b932dfe86..d0fa0b31994d 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -537,7 +537,7 @@ struct context_entry { struct dmar_domain { int nid; /* node id */ - unsigned iommu_refcnt[DMAR_UNITS_SUPPORTED]; + unsigned int iommu_refcnt[DMAR_UNITS_SUPPORTED]; /* Refcount of devices per iommu */ -- cgit v1.2.3 From 405e94e9aed2a38bdcd22efe53c36c6cd53185a6 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 13 Sep 2018 10:42:25 +0100 Subject: irqdomain: Kill irq_domain_add_legacy_isa This helper doesn't have a user anymore, let's remove it. Signed-off-by: Marc Zyngier --- include/linux/irqdomain.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 62a8e3d23829..9f884c948739 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -45,9 +45,6 @@ struct cpumask; struct seq_file; struct irq_affinity_desc; -/* Number of irqs reserved for a legacy isa controller */ -#define NUM_ISA_INTERRUPTS 16 - #define IRQ_DOMAIN_IRQ_SPEC_PARAMS 16 /** @@ -355,14 +352,6 @@ static inline struct irq_domain *irq_domain_add_nomap(struct device_node *of_nod { return __irq_domain_add(of_node_to_fwnode(of_node), 0, max_irq, max_irq, ops, host_data); } -static inline struct irq_domain *irq_domain_add_legacy_isa( - struct device_node *of_node, - const struct irq_domain_ops *ops, - void *host_data) -{ - return irq_domain_add_legacy(of_node, NUM_ISA_INTERRUPTS, 0, 0, ops, - host_data); -} static inline struct irq_domain *irq_domain_add_tree(struct device_node *of_node, const struct irq_domain_ops *ops, void *host_data) -- cgit v1.2.3 From 1da027362a7db422243601e895e6f8288389f435 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 2 Apr 2021 12:50:14 +0100 Subject: irqdomain: Reimplement irq_linear_revmap() with irq_find_mapping() irq_linear_revmap() is supposed to be a fast path for domain lookups, but it only exposes low-level details of the irqdomain implementation, details which are better kept private. The *overhead* between the two is only a function call and a couple of tests, so it is likely that noone can show any meaningful difference compared to the cost of taking an interrupt. Reimplement irq_linear_revmap() with irq_find_mapping() in order to preserve source code compatibility, and rename the internal field for a measure. Signed-off-by: Marc Zyngier --- include/linux/irqdomain.h | 22 +++++++++------------- 1 file changed, 9 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 9f884c948739..42b3f7d03a32 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -151,9 +151,9 @@ struct irq_domain_chip_generic; * Revmap data, used internally by irq_domain * @revmap_direct_max_irq: The largest hwirq that can be set for controllers that * support direct mapping - * @revmap_size: Size of the linear map table @linear_revmap[] + * @revmap_size: Size of the linear map table @revmap[] * @revmap_tree: Radix map tree for hwirqs that don't fit in the linear map - * @linear_revmap: Linear table of hwirq->virq reverse mappings + * @revmap: Linear table of hwirq->virq reverse mappings */ struct irq_domain { struct list_head link; @@ -177,7 +177,7 @@ struct irq_domain { unsigned int revmap_size; struct radix_tree_root revmap_tree; struct mutex revmap_tree_mutex; - unsigned int linear_revmap[]; + unsigned int revmap[]; }; /* Irq domain flags */ @@ -394,24 +394,20 @@ static inline unsigned int irq_create_mapping(struct irq_domain *host, return irq_create_mapping_affinity(host, hwirq, NULL); } - /** - * irq_linear_revmap() - Find a linux irq from a hw irq number. + * irq_find_mapping() - Find a linux irq from a hw irq number. * @domain: domain owning this hardware interrupt * @hwirq: hardware irq number in that domain space - * - * This is a fast path alternative to irq_find_mapping() that can be - * called directly by irq controller code to save a handful of - * instructions. It is always safe to call, but won't find irqs mapped - * using the radix tree. */ +extern unsigned int irq_find_mapping(struct irq_domain *host, + irq_hw_number_t hwirq); + static inline unsigned int irq_linear_revmap(struct irq_domain *domain, irq_hw_number_t hwirq) { - return hwirq < domain->revmap_size ? domain->linear_revmap[hwirq] : 0; + return irq_find_mapping(domain, hwirq); } -extern unsigned int irq_find_mapping(struct irq_domain *host, - irq_hw_number_t hwirq); + extern unsigned int irq_create_direct_mapping(struct irq_domain *host); extern const struct irq_domain_ops irq_domain_simple_ops; -- cgit v1.2.3 From e37af8011a9631996e6cd32dd81a152708eee7d4 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sun, 4 Apr 2021 13:06:39 +0100 Subject: powerpc: Move the use of irq_domain_add_nomap() behind a config option Only a handful of old PPC systems are still using the old 'nomap' variant of the irqdomain library. Move the associated definitions behind a configuration option, which will allow us to make some more radical changes. Signed-off-by: Marc Zyngier --- include/linux/irqdomain.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 42b3f7d03a32..723495ec5a2f 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -345,6 +345,8 @@ static inline struct irq_domain *irq_domain_add_linear(struct device_node *of_no { return __irq_domain_add(of_node_to_fwnode(of_node), size, size, 0, ops, host_data); } + +#ifdef CONFIG_IRQ_DOMAIN_NOMAP static inline struct irq_domain *irq_domain_add_nomap(struct device_node *of_node, unsigned int max_irq, const struct irq_domain_ops *ops, @@ -352,6 +354,10 @@ static inline struct irq_domain *irq_domain_add_nomap(struct device_node *of_nod { return __irq_domain_add(of_node_to_fwnode(of_node), 0, max_irq, max_irq, ops, host_data); } + +extern unsigned int irq_create_direct_mapping(struct irq_domain *host); +#endif + static inline struct irq_domain *irq_domain_add_tree(struct device_node *of_node, const struct irq_domain_ops *ops, void *host_data) @@ -408,8 +414,6 @@ static inline unsigned int irq_linear_revmap(struct irq_domain *domain, return irq_find_mapping(domain, hwirq); } -extern unsigned int irq_create_direct_mapping(struct irq_domain *host); - extern const struct irq_domain_ops irq_domain_simple_ops; /* stock xlate functions */ -- cgit v1.2.3 From 4f86a06e2d6ece5316e4c42fbf946ee22acb30f3 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 10 Sep 2018 18:33:46 +0100 Subject: irqdomain: Make normal and nomap irqdomains exclusive Direct mappings are completely exclusive of normal mappings, meaning that we can refactor the code slightly so that we can get rid of the revmap_direct_max_irq field and use the revmap_size field instead, reducing the size of the irqdomain structure. Signed-off-by: Marc Zyngier --- include/linux/irqdomain.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 723495ec5a2f..0916cf9c6e20 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -149,8 +149,6 @@ struct irq_domain_chip_generic; * @parent: Pointer to parent irq_domain to support hierarchy irq_domains * * Revmap data, used internally by irq_domain - * @revmap_direct_max_irq: The largest hwirq that can be set for controllers that - * support direct mapping * @revmap_size: Size of the linear map table @revmap[] * @revmap_tree: Radix map tree for hwirqs that don't fit in the linear map * @revmap: Linear table of hwirq->virq reverse mappings @@ -173,7 +171,6 @@ struct irq_domain { /* reverse map data. The linear map gets appended to the irq_domain */ irq_hw_number_t hwirq_max; - unsigned int revmap_direct_max_irq; unsigned int revmap_size; struct radix_tree_root revmap_tree; struct mutex revmap_tree_mutex; @@ -207,6 +204,9 @@ enum { */ IRQ_DOMAIN_MSI_NOMASK_QUIRK = (1 << 6), + /* Irq domain doesn't translate anything */ + IRQ_DOMAIN_FLAG_NO_MAP = (1 << 7), + /* * Flags starting from IRQ_DOMAIN_FLAG_NONCORE are reserved * for implementation specific purposes and ignored by the -- cgit v1.2.3 From 48b15a7921d60680babe59f64e127816585a585c Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 5 Apr 2021 11:46:53 +0100 Subject: irqdomain: Cache irq_data instead of a virq number in the revmap Caching a virq number in the revmap is pretty inefficient, as it means we will need to convert it back to either an irq_data or irq_desc to do anything with it. It is also a bit odd, as the radix tree does cache irq_data pointers. Change the revmap type to be an irq_data pointer instead of an unsigned int, and preserve the current API for now. Signed-off-by: Marc Zyngier --- include/linux/irqdomain.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 0916cf9c6e20..340cc04611dd 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -151,7 +151,7 @@ struct irq_domain_chip_generic; * Revmap data, used internally by irq_domain * @revmap_size: Size of the linear map table @revmap[] * @revmap_tree: Radix map tree for hwirqs that don't fit in the linear map - * @revmap: Linear table of hwirq->virq reverse mappings + * @revmap: Linear table of irq_data pointers */ struct irq_domain { struct list_head link; @@ -174,7 +174,7 @@ struct irq_domain { unsigned int revmap_size; struct radix_tree_root revmap_tree; struct mutex revmap_tree_mutex; - unsigned int revmap[]; + struct irq_data *revmap[]; }; /* Irq domain flags */ -- cgit v1.2.3 From d4a45c68dc81f9117ceaff9f058d5fae674181b9 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 5 Apr 2021 12:57:27 +0100 Subject: irqdomain: Protect the linear revmap with RCU It is pretty odd that the radix tree uses RCU while the linear portion doesn't, leading to potential surprises for the users, depending on how the irqdomain has been created. Fix this by moving the update of the linear revmap under the mutex, and the lookup under the RCU read-side lock. The mutex name is updated to reflect that it doesn't only cover the radix-tree anymore. Signed-off-by: Marc Zyngier --- include/linux/irqdomain.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 340cc04611dd..2b696c9bcaaf 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -151,6 +151,7 @@ struct irq_domain_chip_generic; * Revmap data, used internally by irq_domain * @revmap_size: Size of the linear map table @revmap[] * @revmap_tree: Radix map tree for hwirqs that don't fit in the linear map + * @revmap_mutex: Lock for the revmap * @revmap: Linear table of irq_data pointers */ struct irq_domain { @@ -173,8 +174,8 @@ struct irq_domain { irq_hw_number_t hwirq_max; unsigned int revmap_size; struct radix_tree_root revmap_tree; - struct mutex revmap_tree_mutex; - struct irq_data *revmap[]; + struct mutex revmap_mutex; + struct irq_data __rcu *revmap[]; }; /* Irq domain flags */ -- cgit v1.2.3 From d22558dd0a6c888b1829f9d3a0a627e330e27585 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 4 May 2021 14:00:13 +0100 Subject: irqdomain: Introduce irq_resolve_mapping() Rework irq_find_mapping() to return an both an irq_desc pointer, optionally the virtual irq number, and rename the result to __irq_resolve_mapping(). a new helper called irq_resolve_mapping() is provided for code that doesn't need the virtual irq number. irq_find_mapping() is also rewritten in terms of __irq_resolve_mapping(). Signed-off-by: Marc Zyngier --- include/linux/irqdomain.h | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 2b696c9bcaaf..23e4ee523576 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -41,6 +41,7 @@ struct fwnode_handle; struct irq_domain; struct irq_chip; struct irq_data; +struct irq_desc; struct cpumask; struct seq_file; struct irq_affinity_desc; @@ -401,13 +402,31 @@ static inline unsigned int irq_create_mapping(struct irq_domain *host, return irq_create_mapping_affinity(host, hwirq, NULL); } +extern struct irq_desc *__irq_resolve_mapping(struct irq_domain *domain, + irq_hw_number_t hwirq, + unsigned int *irq); + +static inline struct irq_desc *irq_resolve_mapping(struct irq_domain *domain, + irq_hw_number_t hwirq) +{ + return __irq_resolve_mapping(domain, hwirq, NULL); +} + /** * irq_find_mapping() - Find a linux irq from a hw irq number. * @domain: domain owning this hardware interrupt * @hwirq: hardware irq number in that domain space */ -extern unsigned int irq_find_mapping(struct irq_domain *host, - irq_hw_number_t hwirq); +static inline unsigned int irq_find_mapping(struct irq_domain *domain, + irq_hw_number_t hwirq) +{ + unsigned int irq; + + if (__irq_resolve_mapping(domain, hwirq, &irq)) + return irq; + + return 0; +} static inline unsigned int irq_linear_revmap(struct irq_domain *domain, irq_hw_number_t hwirq) -- cgit v1.2.3 From a3016b26ee6ee13d5647d701404a7912d4eaea9e Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 4 May 2021 14:24:37 +0100 Subject: genirq: Use irq_resolve_mapping() to implement __handle_domain_irq() and co In order to start reaping the benefits of irq_resolve_mapping(), start using it in __handle_domain_irq() and handle_domain_nmi(). This involves splitting generic_handle_irq() to be able to directly provide the irq_desc. Signed-off-by: Marc Zyngier --- include/linux/irqdesc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index df4651250785..cdd1cf8207f6 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -158,6 +158,7 @@ static inline void generic_handle_irq_desc(struct irq_desc *desc) desc->handle_irq(desc); } +int handle_irq_desc(struct irq_desc *desc); int generic_handle_irq(unsigned int irq); #ifdef CONFIG_HANDLE_DOMAIN_IRQ -- cgit v1.2.3 From 9626d18a20e166a864e8d1f6ed6bbb84a0fa4989 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 4 May 2021 14:33:24 +0100 Subject: irqdesc: Fix __handle_domain_irq() comment It appears that the comment about a NULL domain meaning anything has always been wrong. Fix it. Signed-off-by: Marc Zyngier --- include/linux/irqdesc.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index cdd1cf8207f6..2971eb7e65f1 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -165,8 +165,7 @@ int generic_handle_irq(unsigned int irq); /* * Convert a HW interrupt number to a logical one using a IRQ domain, * and handle the result interrupt number. Return -EINVAL if - * conversion failed. Providing a NULL domain indicates that the - * conversion has already been done. + * conversion failed. */ int __handle_domain_irq(struct irq_domain *domain, unsigned int hwirq, bool lookup, struct pt_regs *regs); -- cgit v1.2.3 From 8240ef50d4864325b346e40bb9d30cda9f22102d Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 12 May 2021 13:45:52 +0100 Subject: genirq: Add generic_handle_domain_irq() helper Provide generic_handle_domain_irq() as a pendent to handle_domain_irq() for non-root interrupt controllers Signed-off-by: Marc Zyngier --- include/linux/irqdesc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 2971eb7e65f1..0f226c6b0c70 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -170,6 +170,8 @@ int generic_handle_irq(unsigned int irq); int __handle_domain_irq(struct irq_domain *domain, unsigned int hwirq, bool lookup, struct pt_regs *regs); +int generic_handle_domain_irq(struct irq_domain *domain, unsigned int hwirq); + static inline int handle_domain_irq(struct irq_domain *domain, unsigned int hwirq, struct pt_regs *regs) { -- cgit v1.2.3 From e1c054918c6c7a30a35d2c183ed86600a071cdab Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 12 May 2021 16:18:15 +0100 Subject: genirq: Move non-irqdomain handle_domain_irq() handling into ARM's handle_IRQ() Despite the name, handle_domain_irq() deals with non-irqdomain handling for the sake of a handful of legacy ARM platforms. Move such handling into ARM's handle_IRQ(), allowing for better code generation for everyone else. This allows us get rid of some complexity, and to rearrange the guards on the various helpers in a more logical way. Signed-off-by: Marc Zyngier --- include/linux/irqdesc.h | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 0f226c6b0c70..59aea39785bf 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -161,24 +161,18 @@ static inline void generic_handle_irq_desc(struct irq_desc *desc) int handle_irq_desc(struct irq_desc *desc); int generic_handle_irq(unsigned int irq); -#ifdef CONFIG_HANDLE_DOMAIN_IRQ +#ifdef CONFIG_IRQ_DOMAIN /* * Convert a HW interrupt number to a logical one using a IRQ domain, * and handle the result interrupt number. Return -EINVAL if * conversion failed. */ -int __handle_domain_irq(struct irq_domain *domain, unsigned int hwirq, - bool lookup, struct pt_regs *regs); - int generic_handle_domain_irq(struct irq_domain *domain, unsigned int hwirq); -static inline int handle_domain_irq(struct irq_domain *domain, - unsigned int hwirq, struct pt_regs *regs) -{ - return __handle_domain_irq(domain, hwirq, true, regs); -} +#ifdef CONFIG_HANDLE_DOMAIN_IRQ +int handle_domain_irq(struct irq_domain *domain, + unsigned int hwirq, struct pt_regs *regs); -#ifdef CONFIG_IRQ_DOMAIN int handle_domain_nmi(struct irq_domain *domain, unsigned int hwirq, struct pt_regs *regs); #endif -- cgit v1.2.3 From cefc7ca46235f01d5233e3abd4b79452af01d9e9 Mon Sep 17 00:00:00 2001 From: Erik Kaneda Date: Wed, 9 Jun 2021 20:41:52 -0700 Subject: ACPI: PRM: implement OperationRegion handler for the PlatformRtMechanism subtype Platform Runtime Mechanism (PRM) is a firmware interface that exposes a set of binary executables that can either be called from the AML interpreter or device drivers by bypassing the AML interpreter. This change implements the AML interpreter path. According to the specification [1], PRM services are listed in an ACPI table called the PRMT. This patch parses module and handler information listed in the PRMT and registers the PlatformRtMechanism OpRegion handler before ACPI tables are loaded. Each service is defined by a 16-byte GUID and called from writing a 26-byte ASL buffer containing the identifier to a FieldUnit object defined inside a PlatformRtMechanism OperationRegion. OperationRegion (PRMR, PlatformRtMechanism, 0, 26) Field (PRMR, BufferAcc, NoLock, Preserve) { PRMF, 208 // Write to this field to invoke the OperationRegion Handler } The 26-byte ASL buffer is defined as the following: Byte Offset Byte Length Description ============================================================= 0 1 PRM OperationRegion handler status 1 8 PRM service status 9 1 PRM command 10 16 PRM handler GUID The ASL caller fills out a 26-byte buffer containing the PRM command and the PRM handler GUID like so: /* Local0 is the PRM data buffer */ Local0 = buffer (26){} /* Create byte fields over the buffer */ CreateByteField (Local0, 0x9, CMD) CreateField (Local0, 0x50, 0x80, GUID) /* Fill in the command and data fields of the data buffer */ CMD = 0 // run command GUID = ToUUID("xxxx-xx-xxx-xxxx") /* * Invoke PRM service with an ID that matches GUID and save the * result. */ Local0 = (\_SB.PRMT.PRMF = Local0) Byte offset 0 - 8 are written by the handler as a status passed back to AML and used by ASL like so: /* Create byte fields over the buffer */ CreateByteField (Local0, 0x0, PSTA) CreateQWordField (Local0, 0x1, USTA) In this ASL code, PSTA contains a status from the OperationRegion and USTA contains a status from the PRM service. The 26-byte buffer is recieved by acpi_platformrt_space_handler. This handler will look at the command value and the handler guid and take the approperiate actions. Command value Action ===================================================================== 0 Run the PRM service indicated by the PRM handler GUID (bytes 10-26) 1 Prevent PRM runtime updates from happening to the service's parent module 2 Allow PRM updates from happening to the service's parent module This patch enables command value 0. Link: https://uefi.org/sites/default/files/resources/Platform%20Runtime%20Mechanism%20-%20with%20legal%20notice.pdf # [1] Signed-off-by: Erik Kaneda [ rjw: Subject and changelog edits ] Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 1 + include/linux/prmt.h | 7 +++++++ 2 files changed, 8 insertions(+) create mode 100644 include/linux/prmt.h (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index c60745f657e9..4c07ac22c6ba 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -132,6 +132,7 @@ enum acpi_address_range_id { union acpi_subtable_headers { struct acpi_subtable_header common; struct acpi_hmat_structure hmat; + struct acpi_prmt_module_header prmt; }; typedef int (*acpi_tbl_table_handler)(struct acpi_table_header *table); diff --git a/include/linux/prmt.h b/include/linux/prmt.h new file mode 100644 index 000000000000..24da8364b919 --- /dev/null +++ b/include/linux/prmt.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifdef CONFIG_ACPI_PRMT +void init_prmt(void); +#else +static inline void init_prmt(void) { } +#endif -- cgit v1.2.3 From 60faa8f1ac6e0588d53eb9a345adcdbcc96a8f47 Mon Sep 17 00:00:00 2001 From: Erik Kaneda Date: Wed, 9 Jun 2021 20:41:53 -0700 Subject: ACPI: Add \_SB._OSC bit for PRM Signed-off-by: Erik Kaneda Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 4c07ac22c6ba..a618ba698a5c 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -551,6 +551,7 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); #define OSC_SB_OSLPI_SUPPORT 0x00000100 #define OSC_SB_CPC_DIVERSE_HIGH_SUPPORT 0x00001000 #define OSC_SB_GENERIC_INITIATOR_SUPPORT 0x00002000 +#define OSC_SB_PRM_SUPPORT 0x00020000 #define OSC_SB_NATIVE_USB4_SUPPORT 0x00040000 extern bool osc_sb_apei_support_acked; -- cgit v1.2.3 From 6b658c4863c15936872a93c9ee879043bf6393c9 Mon Sep 17 00:00:00 2001 From: Muneendra Kumar Date: Tue, 8 Jun 2021 10:05:44 +0530 Subject: scsi: cgroup: Add cgroup_get_from_id() Add a new function, cgroup_get_from_id(), to retrieve the cgroup associated with a cgroup id. Also export the function cgroup_get_e_css() as this is needed in blk-cgroup.h. Link: https://lore.kernel.org/r/20210608043556.274139-2-muneendra.kumar@broadcom.com Reviewed-by: Himanshu Madhani Reviewed-by: Hannes Reinecke Acked-by: Tejun Heo Signed-off-by: Muneendra Kumar Signed-off-by: Martin K. Petersen --- include/linux/cgroup.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 4f2f79de083e..d2eace88d9d1 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -696,6 +696,7 @@ static inline void cgroup_kthread_ready(void) } void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen); +struct cgroup *cgroup_get_from_id(u64 id); #else /* !CONFIG_CGROUPS */ struct cgroup_subsys_state; @@ -743,6 +744,11 @@ static inline bool task_under_cgroup_hierarchy(struct task_struct *task, static inline void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) {} + +static inline struct cgroup *cgroup_get_from_id(u64 id) +{ + return NULL; +} #endif /* !CONFIG_CGROUPS */ #ifdef CONFIG_CGROUPS -- cgit v1.2.3 From d2bcbeab4200665b694ec4f92a7a2fd58b70b1e8 Mon Sep 17 00:00:00 2001 From: Muneendra Kumar Date: Tue, 8 Jun 2021 10:05:45 +0530 Subject: scsi: blkcg: Add app identifier support for blkcg Add a unique application identifier (i.e fc_app_id member) in blkcg. This allows identification of traffic belonging to an specific both on the host and in the fabric infrastructure. As an example, this allows the storage stack to uniquely identify traffic belong to particular virtual machine. Link: https://lore.kernel.org/r/20210608043556.274139-3-muneendra.kumar@broadcom.com Reviewed-by: Himanshu Madhani Reviewed-by: Hannes Reinecke Acked-by: Tejun Heo Signed-off-by: Muneendra Kumar Signed-off-by: Martin K. Petersen --- include/linux/blk-cgroup.h | 63 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 63 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index b9f3c246c3c9..37048438872c 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -30,6 +30,8 @@ /* Max limits for throttle policy */ #define THROTL_IOPS_MAX UINT_MAX +#define FC_APPID_LEN 129 + #ifdef CONFIG_BLK_CGROUP @@ -55,6 +57,9 @@ struct blkcg { struct blkcg_policy_data *cpd[BLKCG_MAX_POLS]; struct list_head all_blkcgs_node; +#ifdef CONFIG_BLK_CGROUP_FC_APPID + char fc_app_id[FC_APPID_LEN]; +#endif #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; #endif @@ -660,4 +665,62 @@ static inline void blk_cgroup_bio_start(struct bio *bio) { } #endif /* CONFIG_BLOCK */ #endif /* CONFIG_BLK_CGROUP */ + +#ifdef CONFIG_BLK_CGROUP_FC_APPID +/* + * Sets the fc_app_id field associted to blkcg + * @app_id: application identifier + * @cgrp_id: cgroup id + * @app_id_len: size of application identifier + */ +static inline int blkcg_set_fc_appid(char *app_id, u64 cgrp_id, size_t app_id_len) +{ + struct cgroup *cgrp; + struct cgroup_subsys_state *css; + struct blkcg *blkcg; + int ret = 0; + + if (app_id_len > FC_APPID_LEN) + return -EINVAL; + + cgrp = cgroup_get_from_id(cgrp_id); + if (!cgrp) + return -ENOENT; + css = cgroup_get_e_css(cgrp, &io_cgrp_subsys); + if (!css) { + ret = -ENOENT; + goto out_cgrp_put; + } + blkcg = css_to_blkcg(css); + /* + * There is a slight race condition on setting the appid. + * Worst case an I/O may not find the right id. + * This is no different from the I/O we let pass while obtaining + * the vmid from the fabric. + * Adding the overhead of a lock is not necessary. + */ + strlcpy(blkcg->fc_app_id, app_id, app_id_len); + css_put(css); +out_cgrp_put: + cgroup_put(cgrp); + return ret; +} + +/** + * blkcg_get_fc_appid - get the fc app identifier associated with a bio + * @bio: target bio + * + * On success return the fc_app_id, on failure return NULL + */ +static inline char *blkcg_get_fc_appid(struct bio *bio) +{ + if (bio && bio->bi_blkg && + (bio->bi_blkg->blkcg->fc_app_id[0] != '\0')) + return bio->bi_blkg->blkcg->fc_app_id; + return NULL; +} +#else +static inline int blkcg_set_fc_appid(char *buf, u64 id, size_t len) { return -EINVAL; } +static inline char *blkcg_get_fc_appid(struct bio *bio) { return NULL; } +#endif /*CONFIG_BLK_CGROUP_FC_APPID*/ #endif /* _BLK_CGROUP_H */ -- cgit v1.2.3 From 493db2b05d9217da5889840ee31121856627e3c6 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 10 Jun 2021 10:20:34 +0200 Subject: memory: pl353-smc: Let lower level controller drivers handle inits There is no point in having all these definitions at the SMC bus level, these are extremely tight to the NAND controller driver implementation, are not particularly generic, imply more boilerplate than needed, do not really follow the device model by receiving no argument and some of them are actually buggy. Let's get rid of these right now as there is no current user and keep this driver at a simple level: only the SMC bare initializations. The NAND controller driver which I am going to introduce will take care of redefining properly all these helpers and using them directly. Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/r/20210610082040.2075611-13-miquel.raynal@bootlin.com Signed-off-by: Krzysztof Kozlowski --- include/linux/pl353-smc.h | 30 ------------------------------ 1 file changed, 30 deletions(-) delete mode 100644 include/linux/pl353-smc.h (limited to 'include/linux') diff --git a/include/linux/pl353-smc.h b/include/linux/pl353-smc.h deleted file mode 100644 index 0e0d3df9bf72..000000000000 --- a/include/linux/pl353-smc.h +++ /dev/null @@ -1,30 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * ARM PL353 SMC Driver Header - * - * Copyright (C) 2012 - 2018 Xilinx, Inc - */ - -#ifndef __LINUX_PL353_SMC_H -#define __LINUX_PL353_SMC_H - -enum pl353_smc_ecc_mode { - PL353_SMC_ECCMODE_BYPASS = 0, - PL353_SMC_ECCMODE_APB = 1, - PL353_SMC_ECCMODE_MEM = 2 -}; - -enum pl353_smc_mem_width { - PL353_SMC_MEM_WIDTH_8 = 0, - PL353_SMC_MEM_WIDTH_16 = 1 -}; - -u32 pl353_smc_get_ecc_val(int ecc_reg); -bool pl353_smc_ecc_is_busy(void); -int pl353_smc_get_nand_int_status_raw(void); -void pl353_smc_clr_nand_int(void); -int pl353_smc_set_ecc_mode(enum pl353_smc_ecc_mode mode); -int pl353_smc_set_ecc_pg_size(unsigned int pg_sz); -int pl353_smc_set_buswidth(unsigned int bw); -void pl353_smc_set_cycles(u32 timings[]); -#endif -- cgit v1.2.3 From 4b6c132b7da6430cf5dcc96948b04849dea0a32a Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 29 Apr 2021 21:16:56 -0400 Subject: iov_iter: switch ..._full() variants of primitives to use of iov_iter_revert() Use corresponding plain variants, revert on short copy. That's the way it should've been done from the very beginning, except that we didn't have iov_iter_revert() back then... [fixed another braino caught by Qian Cai ] Signed-off-by: Al Viro --- include/linux/uio.h | 32 +++++++++++++++++++++----------- 1 file changed, 21 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 74a401f04bd3..68079e2f34eb 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -132,9 +132,7 @@ size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i); size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i); -bool _copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i); size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i); -bool _copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i); static __always_inline __must_check size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) @@ -157,10 +155,11 @@ size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) static __always_inline __must_check bool copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i) { - if (unlikely(!check_copy_size(addr, bytes, false))) - return false; - else - return _copy_from_iter_full(addr, bytes, i); + size_t copied = copy_from_iter(addr, bytes, i); + if (likely(copied == bytes)) + return true; + iov_iter_revert(i, copied); + return false; } static __always_inline __must_check @@ -175,10 +174,11 @@ size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) static __always_inline __must_check bool copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i) { - if (unlikely(!check_copy_size(addr, bytes, false))) - return false; - else - return _copy_from_iter_full_nocache(addr, bytes, i); + size_t copied = copy_from_iter_nocache(addr, bytes, i); + if (likely(copied == bytes)) + return true; + iov_iter_revert(i, copied); + return false; } #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE @@ -278,7 +278,17 @@ struct csum_state { size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *csstate, struct iov_iter *i); size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); -bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); + +static __always_inline __must_check +bool csum_and_copy_from_iter_full(void *addr, size_t bytes, + __wsum *csum, struct iov_iter *i) +{ + size_t copied = csum_and_copy_from_iter(addr, bytes, csum, i); + if (likely(copied == bytes)) + return true; + iov_iter_revert(i, copied); + return false; +} size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp, struct iov_iter *i); -- cgit v1.2.3 From 8cd54c1c848031a87820e58d772166ffdf8c08c0 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 22 Apr 2021 14:50:39 -0400 Subject: iov_iter: separate direction from flavour Instead of having them mixed in iter->type, use separate ->iter_type and ->data_source (u8 and bool resp.) And don't bother with (pseudo-) bitmap for the former - microoptimizations from being able to check if the flavour is one of two values are not worth the confusion for optimizer. It can't prove that we never get e.g. ITER_IOVEC | ITER_PIPE, so we end up with extra headache. Signed-off-by: Al Viro --- include/linux/uio.h | 24 ++++++++++-------------- 1 file changed, 10 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 68079e2f34eb..ad76eef356b0 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -19,21 +19,17 @@ struct kvec { enum iter_type { /* iter types */ - ITER_IOVEC = 4, - ITER_KVEC = 8, - ITER_BVEC = 16, - ITER_PIPE = 32, - ITER_DISCARD = 64, - ITER_XARRAY = 128, + ITER_IOVEC, + ITER_KVEC, + ITER_BVEC, + ITER_PIPE, + ITER_XARRAY, + ITER_DISCARD, }; struct iov_iter { - /* - * Bit 0 is the read/write bit, set if we're writing. - * Bit 1 is the BVEC_FLAG_NO_REF bit, set if type is a bvec and - * the caller isn't expecting to drop a page reference when done. - */ - unsigned int type; + u8 iter_type; + bool data_source; size_t iov_offset; size_t count; union { @@ -55,7 +51,7 @@ struct iov_iter { static inline enum iter_type iov_iter_type(const struct iov_iter *i) { - return i->type & ~(READ | WRITE); + return i->iter_type; } static inline bool iter_is_iovec(const struct iov_iter *i) @@ -90,7 +86,7 @@ static inline bool iov_iter_is_xarray(const struct iov_iter *i) static inline unsigned char iov_iter_rw(const struct iov_iter *i) { - return i->type & (READ | WRITE); + return i->data_source ? WRITE : READ; } /* -- cgit v1.2.3 From 8409a0d261e20180361e7afe6d89847d1bad4ce8 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 2 May 2021 11:57:37 -0400 Subject: sanitize iov_iter_fault_in_readable() 1) constify iov_iter argument; we are not advancing it in this primitive. 2) cap the amount requested by the amount of data in iov_iter. All existing callers should've been safe, but the check is really cheap and doing it here makes for easier analysis, as well as more consistent semantics among the primitives. 3) don't bother with iterate_iovec(). Explicit loop is not any harder to follow, and we get rid of standalone iterate_iovec() users - it's only used by iterate_and_advance() and (soon to be gone) iterate_all_kinds(). Signed-off-by: Al Viro --- include/linux/uio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index ad76eef356b0..b5cf54859109 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -119,7 +119,7 @@ size_t iov_iter_copy_from_user_atomic(struct page *page, struct iov_iter *i, unsigned long offset, size_t bytes); void iov_iter_advance(struct iov_iter *i, size_t bytes); void iov_iter_revert(struct iov_iter *i, size_t bytes); -int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes); +int iov_iter_fault_in_readable(const struct iov_iter *i, size_t bytes); size_t iov_iter_single_seg_count(const struct iov_iter *i); size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); -- cgit v1.2.3 From f0b65f39ac505e8f1dcdaa165aa7b8c0bd6fd454 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 30 Apr 2021 10:26:41 -0400 Subject: iov_iter: replace iov_iter_copy_from_user_atomic() with iterator-advancing variant Replacement is called copy_page_from_iter_atomic(); unlike the old primitive the callers do *not* need to do iov_iter_advance() after it. In case when they end up consuming less than they'd been given they need to do iov_iter_revert() on everything they had not consumed. That, however, needs to be done only on slow paths. All in-tree callers converted. And that kills the last user of iterate_all_kinds() Signed-off-by: Al Viro --- include/linux/uio.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index b5cf54859109..82c3c3e819e0 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -115,8 +115,8 @@ static inline struct iovec iov_iter_iovec(const struct iov_iter *iter) }; } -size_t iov_iter_copy_from_user_atomic(struct page *page, - struct iov_iter *i, unsigned long offset, size_t bytes); +size_t copy_page_from_iter_atomic(struct page *page, unsigned offset, + size_t bytes, struct iov_iter *i); void iov_iter_advance(struct iov_iter *i, size_t bytes); void iov_iter_revert(struct iov_iter *i, size_t bytes); int iov_iter_fault_in_readable(const struct iov_iter *i, size_t bytes); -- cgit v1.2.3 From ca24306d83a125df187ad53eddb038fe0cffb8ca Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Wed, 2 Jun 2021 17:18:58 +0900 Subject: bootconfig: Change array value to use child node It is not possible to put an array value with subkeys under a key node, because both of subkeys and the array elements are using "next" field of the xbc_node. Thus this changes the array values to use "child" field in the array case. The reason why split this change is to test it easily. Link: https://lkml.kernel.org/r/162262193838.264090.16044473274501498656.stgit@devnote2 Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/bootconfig.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h index 2696eb0fc149..3178a31fdabc 100644 --- a/include/linux/bootconfig.h +++ b/include/linux/bootconfig.h @@ -71,7 +71,7 @@ static inline __init bool xbc_node_is_key(struct xbc_node *node) */ static inline __init bool xbc_node_is_array(struct xbc_node *node) { - return xbc_node_is_value(node) && node->next != 0; + return xbc_node_is_value(node) && node->child != 0; } /** @@ -140,7 +140,7 @@ static inline struct xbc_node * __init xbc_find_node(const char *key) */ #define xbc_array_for_each_value(anode, value) \ for (value = xbc_node_get_data(anode); anode != NULL ; \ - anode = xbc_node_get_next(anode), \ + anode = xbc_node_get_child(anode), \ value = anode ? xbc_node_get_data(anode) : NULL) /** @@ -171,7 +171,7 @@ static inline struct xbc_node * __init xbc_find_node(const char *key) */ #define xbc_node_for_each_array_value(node, key, anode, value) \ for (value = xbc_node_find_value(node, key, &anode); value != NULL; \ - anode = xbc_node_get_next(anode), \ + anode = xbc_node_get_child(anode), \ value = anode ? xbc_node_get_data(anode) : NULL) /** -- cgit v1.2.3 From e5efaeb8a8f527d6e91289ff1f67fbcae452b2ca Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Wed, 2 Jun 2021 17:19:07 +0900 Subject: bootconfig: Support mixing a value and subkeys under a key Support mixing a value and subkeys under a key. Since kernel cmdline options will support "aaa.bbb=value1 aaa.bbb.ccc=value2", it is better that the bootconfig supports such configuration too. Note that this does not change syntax itself but just accepts mixed value and subkeys e.g. key = value1 key.subkey = value2 But this is not accepted; key { value1 subkey = value2 } That will make value1 as a subkey. Also, the order of the value node under a key is fixed. If there are a value and subkeys, the value is always the first child node of the key. Thus if user specifies subkeys first, e.g. key.subkey = value1 key = value2 In the program (and /proc/bootconfig), it will be shown as below key = value2 key.subkey = value1 Link: https://lkml.kernel.org/r/162262194685.264090.7738574774030567419.stgit@devnote2 Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/bootconfig.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h index 3178a31fdabc..e49043ac77c9 100644 --- a/include/linux/bootconfig.h +++ b/include/linux/bootconfig.h @@ -80,6 +80,8 @@ static inline __init bool xbc_node_is_array(struct xbc_node *node) * * Test the @node is a leaf key node which is a key node and has a value node * or no child. Returns true if it is a leaf node, or false if not. + * Note that the leaf node can have subkey nodes in addition to the + * value node. */ static inline __init bool xbc_node_is_leaf(struct xbc_node *node) { @@ -129,6 +131,23 @@ static inline struct xbc_node * __init xbc_find_node(const char *key) return xbc_node_find_child(NULL, key); } +/** + * xbc_node_get_subkey() - Return the first subkey node if exists + * @node: Parent node + * + * Return the first subkey node of the @node. If the @node has no child + * or only value node, this will return NULL. + */ +static inline struct xbc_node * __init xbc_node_get_subkey(struct xbc_node *node) +{ + struct xbc_node *child = xbc_node_get_child(node); + + if (child && xbc_node_is_value(child)) + return xbc_node_get_next(child); + else + return child; +} + /** * xbc_array_for_each_value() - Iterate value nodes on an array * @anode: An XBC arraied value node @@ -149,11 +168,24 @@ static inline struct xbc_node * __init xbc_find_node(const char *key) * @child: Iterated XBC node. * * Iterate child nodes of @parent. Each child nodes are stored to @child. + * The @child can be mixture of a value node and subkey nodes. */ #define xbc_node_for_each_child(parent, child) \ for (child = xbc_node_get_child(parent); child != NULL ; \ child = xbc_node_get_next(child)) +/** + * xbc_node_for_each_subkey() - Iterate child subkey nodes + * @parent: An XBC node. + * @child: Iterated XBC node. + * + * Iterate subkey nodes of @parent. Each child nodes are stored to @child. + * The @child is only the subkey node. + */ +#define xbc_node_for_each_subkey(parent, child) \ + for (child = xbc_node_get_subkey(parent); child != NULL ; \ + child = xbc_node_get_next(child)) + /** * xbc_node_for_each_array_value() - Iterate array entries of geven key * @node: An XBC node. -- cgit v1.2.3 From 99f4f5d62338cab9dcf45735344541574daedd20 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Wed, 2 Jun 2021 17:19:34 +0900 Subject: bootconfig: Share the checksum function with tools Move the checksum calculation function into the header for sharing it with tools/bootconfig. Link: https://lkml.kernel.org/r/162262197470.264090.16325743685807878807.stgit@devnote2 Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/bootconfig.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h index e49043ac77c9..6bdd94cff4e2 100644 --- a/include/linux/bootconfig.h +++ b/include/linux/bootconfig.h @@ -16,6 +16,26 @@ #define BOOTCONFIG_ALIGN (1 << BOOTCONFIG_ALIGN_SHIFT) #define BOOTCONFIG_ALIGN_MASK (BOOTCONFIG_ALIGN - 1) +/** + * xbc_calc_checksum() - Calculate checksum of bootconfig + * @data: Bootconfig data. + * @size: The size of the bootconfig data. + * + * Calculate the checksum value of the bootconfig data. + * The checksum will be used with the BOOTCONFIG_MAGIC and the size for + * embedding the bootconfig in the initrd image. + */ +static inline __init u32 xbc_calc_checksum(void *data, u32 size) +{ + unsigned char *p = data; + u32 ret = 0; + + while (size--) + ret += *p++; + + return ret; +} + /* XBC tree node */ struct xbc_node { u16 next; -- cgit v1.2.3 From ad4e600cbf897f47525b342cd4b02e88ed300a83 Mon Sep 17 00:00:00 2001 From: Gabriel Somlo Date: Wed, 26 May 2021 06:51:26 -0400 Subject: drivers/soc/litex: remove 8-bit subregister option Since upstream LiteX recommends that Linux support be limited to designs configured with 32-bit CSR subregisters (see commit a2b71fde in upstream LiteX, https://github.com/enjoy-digital/litex), remove the option to select 8-bit subregisters, significantly reducing the complexity of LiteX CSR (MMIO register) accessor methods. NOTE: for details on the underlying mechanics of LiteX CSR registers, see https://github.com/enjoy-digital/litex/wiki/CSR-Bus or the original LiteX accessors (litex/soc/software/include/hw/common.h in the upstream repository). Signed-off-by: Gabriel Somlo Cc: Stafford Horne Cc: Florent Kermarrec Cc: Mateusz Holenko Cc: Joel Stanley Reviewed-by: Joel Stanley Signed-off-by: Stafford Horne --- include/linux/litex.h | 103 ++++++++------------------------------------------ 1 file changed, 15 insertions(+), 88 deletions(-) (limited to 'include/linux') diff --git a/include/linux/litex.h b/include/linux/litex.h index 5ea9ccf5cce4..f2edb86d5f44 100644 --- a/include/linux/litex.h +++ b/include/linux/litex.h @@ -11,18 +11,6 @@ #include -/* LiteX SoCs support 8- or 32-bit CSR Bus data width (i.e., subreg. size) */ -#if defined(CONFIG_LITEX_SUBREG_SIZE) && \ - (CONFIG_LITEX_SUBREG_SIZE == 1 || CONFIG_LITEX_SUBREG_SIZE == 4) -#define LITEX_SUBREG_SIZE CONFIG_LITEX_SUBREG_SIZE -#else -#error LiteX subregister size (LITEX_SUBREG_SIZE) must be 4 or 1! -#endif -#define LITEX_SUBREG_SIZE_BIT (LITEX_SUBREG_SIZE * 8) - -/* LiteX subregisters of any width are always aligned on a 4-byte boundary */ -#define LITEX_SUBREG_ALIGN 0x4 - static inline void _write_litex_subregister(u32 val, void __iomem *addr) { writel((u32 __force)cpu_to_le32(val), addr); @@ -42,115 +30,54 @@ static inline u32 _read_litex_subregister(void __iomem *addr) * 32-bit wide logical CSR will be laid out as four 32-bit physical * subregisters, each one containing one byte of meaningful data. * - * For details see: https://github.com/enjoy-digital/litex/wiki/CSR-Bus - */ - -/* number of LiteX subregisters needed to store a register of given reg_size */ -#define _litex_num_subregs(reg_size) \ - (((reg_size) - 1) / LITEX_SUBREG_SIZE + 1) - -/* - * since the number of 4-byte aligned subregisters required to store a single - * LiteX CSR (MMIO) register varies with LITEX_SUBREG_SIZE, the offset of the - * next adjacent LiteX CSR register w.r.t. the offset of the current one also - * depends on how many subregisters the latter is spread across - */ -#define _next_reg_off(off, size) \ - ((off) + _litex_num_subregs(size) * LITEX_SUBREG_ALIGN) - -/* - * The purpose of `_litex_[set|get]_reg()` is to implement the logic of - * writing to/reading from the LiteX CSR in a single place that can be then - * reused by all LiteX drivers via the `litex_[write|read][8|16|32|64]()` - * accessors for the appropriate data width. - * NOTE: direct use of `_litex_[set|get]_reg()` by LiteX drivers is strongly - * discouraged, as they perform no error checking on the requested data width! - */ - -/** - * _litex_set_reg() - Writes a value to the LiteX CSR (Control&Status Register) - * @reg: Address of the CSR - * @reg_size: The width of the CSR expressed in the number of bytes - * @val: Value to be written to the CSR + * For Linux support, upstream LiteX enforces a 32-bit wide CSR bus, which + * means that only larger-than-32-bit CSRs will be split across multiple + * subregisters (e.g., a 64-bit CSR will be spread across two consecutive + * 32-bit subregisters). * - * This function splits a single (possibly multi-byte) LiteX CSR write into - * a series of subregister writes with a proper offset. - * NOTE: caller is responsible for ensuring (0 < reg_size <= sizeof(u64)). - */ -static inline void _litex_set_reg(void __iomem *reg, size_t reg_size, u64 val) -{ - u8 shift = _litex_num_subregs(reg_size) * LITEX_SUBREG_SIZE_BIT; - - while (shift > 0) { - shift -= LITEX_SUBREG_SIZE_BIT; - _write_litex_subregister(val >> shift, reg); - reg += LITEX_SUBREG_ALIGN; - } -} - -/** - * _litex_get_reg() - Reads a value of the LiteX CSR (Control&Status Register) - * @reg: Address of the CSR - * @reg_size: The width of the CSR expressed in the number of bytes - * - * Return: Value read from the CSR - * - * This function generates a series of subregister reads with a proper offset - * and joins their results into a single (possibly multi-byte) LiteX CSR value. - * NOTE: caller is responsible for ensuring (0 < reg_size <= sizeof(u64)). + * For details see: https://github.com/enjoy-digital/litex/wiki/CSR-Bus */ -static inline u64 _litex_get_reg(void __iomem *reg, size_t reg_size) -{ - u64 r; - u8 i; - - r = _read_litex_subregister(reg); - for (i = 1; i < _litex_num_subregs(reg_size); i++) { - r <<= LITEX_SUBREG_SIZE_BIT; - reg += LITEX_SUBREG_ALIGN; - r |= _read_litex_subregister(reg); - } - return r; -} static inline void litex_write8(void __iomem *reg, u8 val) { - _litex_set_reg(reg, sizeof(u8), val); + _write_litex_subregister(val, reg); } static inline void litex_write16(void __iomem *reg, u16 val) { - _litex_set_reg(reg, sizeof(u16), val); + _write_litex_subregister(val, reg); } static inline void litex_write32(void __iomem *reg, u32 val) { - _litex_set_reg(reg, sizeof(u32), val); + _write_litex_subregister(val, reg); } static inline void litex_write64(void __iomem *reg, u64 val) { - _litex_set_reg(reg, sizeof(u64), val); + _write_litex_subregister(val >> 32, reg); + _write_litex_subregister(val, reg + 4); } static inline u8 litex_read8(void __iomem *reg) { - return _litex_get_reg(reg, sizeof(u8)); + return _read_litex_subregister(reg); } static inline u16 litex_read16(void __iomem *reg) { - return _litex_get_reg(reg, sizeof(u16)); + return _read_litex_subregister(reg); } static inline u32 litex_read32(void __iomem *reg) { - return _litex_get_reg(reg, sizeof(u32)); + return _read_litex_subregister(reg); } static inline u64 litex_read64(void __iomem *reg) { - return _litex_get_reg(reg, sizeof(u64)); + return ((u64)_read_litex_subregister(reg) << 32) | + _read_litex_subregister(reg + 4); } #endif /* _LINUX_LITEX_H */ -- cgit v1.2.3 From f8e6d24144d1bfbb8714faa9044e135c0c00bd89 Mon Sep 17 00:00:00 2001 From: Qi Liu Date: Wed, 9 Jun 2021 14:40:57 +0800 Subject: perf: Add EVENT_ATTR_ID to simplify event attributes Similar EVENT_ATTR macros are defined in many PMU drivers, like Arm PMU driver, Arm SMMU PMU driver. So add a generic macro to simplify code. Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Arnaldo Carvalho de Melo Cc: Mark Rutland Cc: Alexander Shishkin Signed-off-by: Qi Liu Link: https://lore.kernel.org/r/1623220863-58233-2-git-send-email-liuqi115@huawei.com Signed-off-by: Will Deacon --- include/linux/perf_event.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index f5a6a2f069ed..2d510ad750ed 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1576,6 +1576,12 @@ static struct perf_pmu_events_attr _var = { \ .event_str = _str, \ }; +#define PMU_EVENT_ATTR_ID(_name, _show, _id) \ + (&((struct perf_pmu_events_attr[]) { \ + { .attr = __ATTR(_name, 0444, _show, NULL), \ + .id = _id, } \ + })[0].attr.attr) + #define PMU_FORMAT_ATTR(_name, _format) \ static ssize_t \ _name##_show(struct device *dev, \ -- cgit v1.2.3 From fd307a4ad332ef50be5569c92490219e7cd84ce5 Mon Sep 17 00:00:00 2001 From: Jiri Prchal Date: Fri, 11 Jun 2021 11:45:58 +0200 Subject: nvmem: prepare basics for FRAM support Added enum and string for FRAM (ferroelectric RAM) to expose it as file named "fram". Added documentation of sysfs file. Signed-off-by: Jiri Prchal Link: https://lore.kernel.org/r/20210611094601.95131-2-jiri.prchal@aksignal.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-provider.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index e162b757b6d5..890003565761 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -25,6 +25,7 @@ enum nvmem_type { NVMEM_TYPE_EEPROM, NVMEM_TYPE_OTP, NVMEM_TYPE_BATTERY_BACKED, + NVMEM_TYPE_FRAM, }; #define NVMEM_DEVID_NONE (-1) -- cgit v1.2.3 From 03cb4473be92a4207a3d1df25186dafd1a5add4d Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Wed, 9 Jun 2021 09:39:49 -0700 Subject: ice: add low level PTP clock access functions Add the ice_ptp_hw.c file and some associated definitions to the ice driver folder. This file contains basic low level definitions for functions that interact with the device hardware. For now, only E810-based devices are supported. The ice hardware supports 2 major variants which have different PHYs with different procedures necessary for interacting with the device clock. Because the device captures timestamps in the PHY, each PHY has its own internal timer. The timers are synchronized in hardware by first preparing the source timer and the PHY timer shadow registers, and then issuing a synchronization command. This ensures that both the source timer and PHY timers are programmed simultaneously. The timers themselves are all driven from the same oscillator source. The functions in ice_ptp_hw.c abstract over the differences between how the PHYs in E810 are programmed vs how the PHYs in E822 devices are programmed. This series only implements E810 support, but E822 support will be added in a future change. Signed-off-by: Jacob Keller Tested-by: Tony Brelinski Signed-off-by: Tony Nguyen --- include/linux/kernel.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 15d8bad3d2f2..e73f3bc3dba5 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -71,6 +71,18 @@ */ #define lower_32_bits(n) ((u32)((n) & 0xffffffff)) +/** + * upper_16_bits - return bits 16-31 of a number + * @n: the number we're accessing + */ +#define upper_16_bits(n) ((u16)((n) >> 16)) + +/** + * lower_16_bits - return bits 0-15 of a number + * @n: the number we're accessing + */ +#define lower_16_bits(n) ((u16)((n) & 0xffff)) + struct completion; struct pt_regs; struct user; -- cgit v1.2.3 From 5937c3ce21228d33d2eb3287baa7e4cf6978dba9 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Thu, 3 Jun 2021 11:34:37 +0200 Subject: PM: domains: Drop/restore performance state votes for devices at runtime PM A subsystem/driver that need to manage OPPs for its device, should typically drop its vote for the OPP when the device becomes runtime suspended. In this way, the corresponding aggregation of the performance state votes that is managed in genpd for the attached PM domain, may find that the aggregated vote can be decreased. Hence, it may allow genpd to set the lower performance state for the PM domain, thus avoiding to waste energy. To accomplish this, typically a subsystem/driver would need to call dev_pm_opp_set_rate|opp() for its device from its ->runtime_suspend() callback, to drop the vote for the OPP. Accordingly, it needs another call to dev_pm_opp_set_rate|opp() to restore the vote for the OPP from its ->runtime_resume() callback. To avoid boilerplate code in subsystems/driver to deal with these things, let's instead manage this internally in genpd. Signed-off-by: Ulf Hansson Tested-by: Dmitry Osipenko Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index dfcfbcecc34b..21a0577305ef 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -198,6 +198,7 @@ struct generic_pm_domain_data { struct notifier_block *power_nb; int cpu; unsigned int performance_state; + unsigned int rpm_pstate; ktime_t next_wakeup; void *data; }; -- cgit v1.2.3 From cdb14e0f7775e767484843e8ecd736bb21754c58 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 2 Jun 2021 09:53:16 +0300 Subject: blk-mq: factor out a blk_mq_alloc_sq_tag_set helper Factour out a helper to initialize a simple single hw queue tag_set from blk_mq_init_sq_queue. This will allow to phase out blk_mq_init_sq_queue in favor of a more symmetric and general API. Signed-off-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20210602065345.355274-2-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 359486940fa0..bb950fc669ef 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -439,6 +439,9 @@ struct request_queue *blk_mq_init_sq_queue(struct blk_mq_tag_set *set, void blk_mq_unregister_dev(struct device *, struct request_queue *); int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set); +int blk_mq_alloc_sq_tag_set(struct blk_mq_tag_set *set, + const struct blk_mq_ops *ops, unsigned int queue_depth, + unsigned int set_flags); void blk_mq_free_tag_set(struct blk_mq_tag_set *set); void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule); -- cgit v1.2.3 From 26a9750aa875126e4b7fc5ee6de652a529c5b7ee Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 2 Jun 2021 09:53:17 +0300 Subject: blk-mq: improve the blk_mq_init_allocated_queue interface Don't return the passed in request_queue but a normal error code, and drop the elevator_init argument in favor of just calling elevator_init_mq directly from dm-rq. Signed-off-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20210602065345.355274-3-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 5 ++--- include/linux/elevator.h | 1 + 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index bb950fc669ef..73750b2838d2 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -429,9 +429,8 @@ enum { struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *); struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set, void *queuedata); -struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, - struct request_queue *q, - bool elevator_init); +int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, + struct request_queue *q); struct request_queue *blk_mq_init_sq_queue(struct blk_mq_tag_set *set, const struct blk_mq_ops *ops, unsigned int queue_depth, diff --git a/include/linux/elevator.h b/include/linux/elevator.h index dcb2f9022c1d..783ecb3cb77a 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -120,6 +120,7 @@ extern void elv_merged_request(struct request_queue *, struct request *, extern bool elv_attempt_insert_merge(struct request_queue *, struct request *); extern struct request *elv_former_request(struct request_queue *, struct request *); extern struct request *elv_latter_request(struct request_queue *, struct request *); +void elevator_init_mq(struct request_queue *q); /* * io scheduler registration -- cgit v1.2.3 From b461dfc49eb6fbabc60b9dad476e787ada56b7b4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 2 Jun 2021 09:53:18 +0300 Subject: blk-mq: add the blk_mq_alloc_disk APIs Add a new API to allocate a gendisk including the request_queue for use with blk-mq based drivers. This is to avoid boilerplate code in drivers. Signed-off-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20210602065345.355274-4-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 73750b2838d2..f496c6c5b5d2 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -426,6 +426,18 @@ enum { ((policy & ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) \ << BLK_MQ_F_ALLOC_POLICY_START_BIT) +#define blk_mq_alloc_disk(set, queuedata) \ +({ \ + static struct lock_class_key __key; \ + struct gendisk *__disk = __blk_mq_alloc_disk(set, queuedata); \ + \ + if (__disk) \ + lockdep_init_map(&__disk->lockdep_map, \ + "(bio completion)", &__key, 0); \ + __disk; \ +}) +struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, + void *queuedata); struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *); struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set, void *queuedata); -- cgit v1.2.3 From 08c1d480ed38995690a7d83f2c6a505f6cbbed9f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 2 Jun 2021 09:53:30 +0300 Subject: blk-mq: remove blk_mq_init_sq_queue All users are gone now. Signed-off-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20210602065345.355274-16-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index f496c6c5b5d2..02a4aab0aeac 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -443,10 +443,6 @@ struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set, void *queuedata); int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, struct request_queue *q); -struct request_queue *blk_mq_init_sq_queue(struct blk_mq_tag_set *set, - const struct blk_mq_ops *ops, - unsigned int queue_depth, - unsigned int set_flags); void blk_mq_unregister_dev(struct device *, struct request_queue *); int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set); -- cgit v1.2.3 From ab6a303c5440156dd475b5884cff26a7245630f8 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 11 Jun 2021 22:01:26 +0300 Subject: net: dsa: tag_8021q: remove shim declarations All users of tag_8021q select it in Kconfig, so shim functions are not needed because it is not possible for it to be disabled and its callers enabled. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/dsa/8021q.h | 76 ----------------------------------------------- 1 file changed, 76 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index b12b05f1c8b4..cbf2c9b1ee4f 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -37,8 +37,6 @@ struct dsa_8021q_context { #define DSA_8021Q_N_SUBVLAN 8 -#if IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q) - int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled); int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port, @@ -70,78 +68,4 @@ bool vid_is_dsa_8021q_txvlan(u16 vid); bool vid_is_dsa_8021q(u16 vid); -#else - -int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled) -{ - return 0; -} - -int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port, - struct dsa_8021q_context *other_ctx, - int other_port) -{ - return 0; -} - -int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port, - struct dsa_8021q_context *other_ctx, - int other_port) -{ - return 0; -} - -struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, - u16 tpid, u16 tci) -{ - return NULL; -} - -u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port) -{ - return 0; -} - -u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port) -{ - return 0; -} - -u16 dsa_8021q_rx_vid_subvlan(struct dsa_switch *ds, int port, u16 subvlan) -{ - return 0; -} - -int dsa_8021q_rx_switch_id(u16 vid) -{ - return 0; -} - -int dsa_8021q_rx_source_port(u16 vid) -{ - return 0; -} - -u16 dsa_8021q_rx_subvlan(u16 vid) -{ - return 0; -} - -bool vid_is_dsa_8021q_rxvlan(u16 vid) -{ - return false; -} - -bool vid_is_dsa_8021q_txvlan(u16 vid) -{ - return false; -} - -bool vid_is_dsa_8021q(u16 vid) -{ - return false; -} - -#endif /* IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q) */ - #endif /* _NET_DSA_8021Q_H */ -- cgit v1.2.3 From 233697b3b3f60b17d02ca2a35230aee0ac6f1759 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 11 Jun 2021 22:01:27 +0300 Subject: net: dsa: tag_8021q: refactor RX VLAN parsing into a dedicated function The added value of this function is that it can deal with both the case where the VLAN header is in the skb head, as well as in the offload field. This is something I was not able to do using other functions in the network stack. Since both ocelot-8021q and sja1105 need to do the same stuff, let's make it a common service provided by tag_8021q. This is done as refactoring for the new SJA1110 tagger, which partly uses tag_8021q as well (just like SJA1105), and will be the third caller. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/dsa/8021q.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index cbf2c9b1ee4f..1587961f1a7b 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -50,6 +50,9 @@ int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port, struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, u16 tpid, u16 tci); +void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id, + int *subvlan); + u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port); u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port); -- cgit v1.2.3 From 617ef8d9377b9aac381c023cd0823da264c2f463 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 11 Jun 2021 22:01:28 +0300 Subject: net: dsa: sja1105: make SJA1105_SKB_CB fit a full timestamp In SJA1105, RX timestamps for packets sent to the CPU are transmitted in separate follow-up packets (metadata frames). These contain partial timestamps (24 or 32 bits) which are kept in SJA1105_SKB_CB(skb)->meta_tstamp. Thankfully, SJA1110 improved that, and the RX timestamps are now transmitted in-band with the actual packet, in the timestamp trailer. The RX timestamps are now full-width 64 bits. Because we process the RX DSA tags in the rcv() method in the tagger, but we would like to preserve the DSA code structure in that we populate the skb timestamp in the port_rxtstamp() call which only happens later, the implication is that we must somehow pass the 64-bit timestamp from the rcv() method all the way to port_rxtstamp(). We can use the skb->cb for that. Rename the meta_tstamp from struct sja1105_skb_cb from "meta_tstamp" to "tstamp", and increase its size to 64 bits. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/dsa/sja1105.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index 1eb84562b311..865a548a6ef2 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -48,7 +48,7 @@ struct sja1105_tagger_data { struct sja1105_skb_cb { struct sk_buff *clone; - u32 meta_tstamp; + u64 tstamp; }; #define SJA1105_SKB_CB(skb) \ -- cgit v1.2.3 From 4913b8ebf8a9c56ce66466b4daa07d7d4678cdd8 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 11 Jun 2021 22:01:29 +0300 Subject: net: dsa: add support for the SJA1110 native tagging protocol The SJA1110 has improved a few things compared to SJA1105: - To send a control packet from the host port with SJA1105, one needed to program a one-shot "management route" over SPI. This is no longer true with SJA1110, you can actually send "in-band control extensions" in the packets sent by DSA, these are in fact DSA tags which contain the destination port and switch ID. - When receiving a control packet from the switch with SJA1105, the source port and switch ID were written in bytes 3 and 4 of the destination MAC address of the frame (which was a very poor shot at a DSA header). If the control packet also had an RX timestamp, that timestamp was sent in an actual follow-up packet, so there were reordering concerns on multi-core/multi-queue DSA masters, where the metadata frame with the RX timestamp might get processed before the actual packet to which that timestamp belonged (there is no way to pair a packet to its timestamp other than the order in which they were received). On SJA1110, this is no longer true, control packets have the source port, switch ID and timestamp all in the DSA tags. - Timestamps from the switch were partial: to get a 64-bit timestamp as required by PTP stacks, one would need to take the partial 24-bit or 32-bit timestamp from the packet, then read the current PTP time very quickly, and then patch in the high bits of the current PTP time into the captured partial timestamp, to reconstruct what the full 64-bit timestamp must have been. That is awful because packet processing is done in NAPI context, but reading the current PTP time is done over SPI and therefore needs sleepable context. But it also aggravated a few things: - Not only is there a DSA header in SJA1110, but there is a DSA trailer in fact, too. So DSA needs to be extended to support taggers which have both a header and a trailer. Very unconventional - my understanding is that the trailer exists because the timestamps couldn't be prepared in time for putting them in the header area. - Like SJA1105, not all packets sent to the CPU have the DSA tag added to them, only control packets do: * the ones which match the destination MAC filters/traps in MAC_FLTRES1 and MAC_FLTRES0 * the ones which match FDB entries which have TRAP or TAKETS bits set So we could in theory hack something up to request the switch to take timestamps for all packets that reach the CPU, and those would be DSA-tagged and contain the source port / switch ID by virtue of the fact that there needs to be a timestamp trailer provided. BUT: - The SJA1110 does not parse its own DSA tags in a way that is useful for routing in cross-chip topologies, a la Marvell. And the sja1105 driver already supports cross-chip bridging from the SJA1105 days. It does that by automatically setting up the DSA links as VLAN trunks which contain all the necessary tag_8021q RX VLANs that must be communicated between the switches that span the same bridge. So when using tag_8021q on sja1105, it is possible to have 2 switches with ports sw0p0, sw0p1, sw1p0, sw1p1, and 2 VLAN-unaware bridges br0 and br1, and br0 can take sw0p0 and sw1p0, and br1 can take sw0p1 and sw1p1, and forwarding will happen according to the expected rules of the Linux bridge. We like that, and we don't want that to go away, so as a matter of fact, the SJA1110 tagger still needs to support tag_8021q. So the sja1110 tagger is a hybrid between tag_8021q for data packets, and the native hardware support for control packets. On RX, packets have a 13-byte trailer if they contain an RX timestamp. That trailer is padded in such a way that its byte 8 (the start of the "residence time" field - not parsed by Linux because we don't care) is aligned on a 16 byte boundary. So the padding has a variable length between 0 and 15 bytes. The DSA header contains the offset of the beginning of the padding relative to the beginning of the frame (and the end of the padding is obviously the end of the packet minus 13 bytes, the length of the trailer). So we discard it. Packets which don't have a trailer contain the source port and switch ID information in the header (they are "trap-to-host" packets). Packets which have a trailer contain the source port and switch ID in the trailer. On TX, the destination port mask and switch ID is always in the trailer, so we always need to say in the header that a trailer is present. The header needs a custom EtherType and this was chosen as 0xdadc, after 0xdada which is for Marvell and 0xdadb which is for VLANs in VLAN-unaware mode on SJA1105 (and SJA1110 in fact too). Because we use tag_8021q in concert with the native tagging protocol, control packets will have 2 DSA tags. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/dsa/sja1105.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index 865a548a6ef2..b02cf7b515ae 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -14,6 +14,7 @@ #define ETH_P_SJA1105 ETH_P_DSA_8021Q #define ETH_P_SJA1105_META 0x0008 +#define ETH_P_SJA1110 0xdadc /* IEEE 802.3 Annex 57A: Slow Protocols PDUs (01:80:C2:xx:xx:xx) */ #define SJA1105_LINKLOCAL_FILTER_A 0x0180C2000000ull -- cgit v1.2.3 From 566b18c8b752f67c4e82f0eb4563dd71f84a8799 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 11 Jun 2021 22:01:31 +0300 Subject: net: dsa: sja1105: implement TX timestamping for SJA1110 The TX timestamping procedure for SJA1105 is a bit unconventional because the transmit procedure itself is unconventional. Control packets (and therefore PTP as well) are transmitted to a specific port in SJA1105 using "management routes" which must be written over SPI to the switch. These are one-shot rules that match by destination MAC address on traffic coming from the CPU port, and select the precise destination port for that packet. So to transmit a packet from NET_TX softirq context, we actually need to defer to a process context so that we can perform that SPI write before we send the packet. The DSA master dev_queue_xmit() runs in process context, and we poll until the switch confirms it took the TX timestamp, then we annotate the skb clone with that TX timestamp. This is why the sja1105 driver does not need an skb queue for TX timestamping. But the SJA1110 is a bit (not much!) more conventional, and you can request 2-step TX timestamping through the DSA header, as well as give the switch a cookie (timestamp ID) which it will give back to you when it has the timestamp. So now we do need a queue for keeping the skb clones until their TX timestamps become available. The interesting part is that the metadata frames from SJA1105 haven't disappeared completely. On SJA1105 they were used as follow-ups which contained RX timestamps, but on SJA1110 they are actually TX completion packets, which contain a variable (up to 32) array of timestamps. Why an array? Because: - not only is the TX timestamp on the egress port being communicated, but also the RX timestamp on the CPU port. Nice, but we don't care about that, so we ignore it. - because a packet could be multicast to multiple egress ports, each port takes its own timestamp, and the TX completion packet contains the individual timestamps on each port. This is unconventional because switches typically have a timestamping FIFO and raise an interrupt, but this one doesn't. So the tagger needs to detect and parse meta frames, and call into the main switch driver, which pairs the timestamps with the skbs in the TX timestamping queue which are waiting for one. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/dsa/sja1105.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index b02cf7b515ae..b6089b88314c 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -45,11 +45,14 @@ struct sja1105_tagger_data { */ spinlock_t meta_lock; unsigned long state; + u8 ts_id; }; struct sja1105_skb_cb { struct sk_buff *clone; u64 tstamp; + /* Only valid for packets cloned for 2-step TX timestamping */ + u8 ts_id; }; #define SJA1105_SKB_CB(skb) \ @@ -66,4 +69,24 @@ struct sja1105_port { u16 xmit_tpid; }; +enum sja1110_meta_tstamp { + SJA1110_META_TSTAMP_TX = 0, + SJA1110_META_TSTAMP_RX = 1, +}; + +#if IS_ENABLED(CONFIG_NET_DSA_SJA1105_PTP) + +void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, u8 ts_id, + enum sja1110_meta_tstamp dir, u64 tstamp); + +#else + +static inline void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, + u8 ts_id, enum sja1110_meta_tstamp dir, + u64 tstamp) +{ +} + +#endif /* IS_ENABLED(CONFIG_NET_DSA_SJA1105_PTP) */ + #endif /* _NET_DSA_SJA1105_H */ -- cgit v1.2.3 From 0fb16976765143cf0d7d0dd78b3f406ab135c494 Mon Sep 17 00:00:00 2001 From: Calvin Johnson Date: Fri, 11 Jun 2021 13:53:48 +0300 Subject: net: phy: Introduce fwnode_mdio_find_device() Define fwnode_mdio_find_device() to get a pointer to the mdio_device from fwnode passed to the function. Refactor of_mdio_find_device() to use fwnode_mdio_find_device(). Signed-off-by: Calvin Johnson Signed-off-by: Ioana Ciornei Acked-by: Grant Likely Signed-off-by: David S. Miller --- include/linux/phy.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index ed332ac92e25..7aa97f4e5387 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1377,10 +1377,17 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id, bool is_c45, struct phy_c45_device_ids *c45_ids); #if IS_ENABLED(CONFIG_PHYLIB) +struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode); struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45); int phy_device_register(struct phy_device *phy); void phy_device_free(struct phy_device *phydev); #else +static inline +struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode) +{ + return 0; +} + static inline struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45) { -- cgit v1.2.3 From 425775ed31a6fac8b66ab077f7936fafad895ef6 Mon Sep 17 00:00:00 2001 From: Calvin Johnson Date: Fri, 11 Jun 2021 13:53:49 +0300 Subject: net: phy: Introduce phy related fwnode functions Define fwnode_phy_find_device() to iterate an mdiobus and find the phy device of the provided phy fwnode. Additionally define device_phy_find_device() to find phy device of provided device. Define fwnode_get_phy_node() to get phy_node using named reference. Signed-off-by: Calvin Johnson Signed-off-by: Ioana Ciornei Acked-by: Grant Likely Signed-off-by: David S. Miller --- include/linux/phy.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 7aa97f4e5387..f9b5fb099fa6 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1378,6 +1378,9 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id, struct phy_c45_device_ids *c45_ids); #if IS_ENABLED(CONFIG_PHYLIB) struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode); +struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode); +struct phy_device *device_phy_find_device(struct device *dev); +struct fwnode_handle *fwnode_get_phy_node(struct fwnode_handle *fwnode); struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45); int phy_device_register(struct phy_device *phy); void phy_device_free(struct phy_device *phydev); @@ -1388,6 +1391,23 @@ struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode) return 0; } +static inline +struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode) +{ + return NULL; +} + +static inline struct phy_device *device_phy_find_device(struct device *dev) +{ + return NULL; +} + +static inline +struct fwnode_handle *fwnode_get_phy_node(struct fwnode_handle *fwnode) +{ + return NULL; +} + static inline struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45) { -- cgit v1.2.3 From 114dea60043b8f0c82c67dd281719ef8919c2416 Mon Sep 17 00:00:00 2001 From: Calvin Johnson Date: Fri, 11 Jun 2021 13:53:51 +0300 Subject: net: phy: Introduce fwnode_get_phy_id() Extract phy_id from compatible string. This will be used by fwnode_mdiobus_register_phy() to create phy device using the phy_id. Signed-off-by: Calvin Johnson Signed-off-by: Ioana Ciornei Acked-by: Grant Likely Signed-off-by: David S. Miller --- include/linux/phy.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index f9b5fb099fa6..b60694734b07 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1377,6 +1377,7 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id, bool is_c45, struct phy_c45_device_ids *c45_ids); #if IS_ENABLED(CONFIG_PHYLIB) +int fwnode_get_phy_id(struct fwnode_handle *fwnode, u32 *phy_id); struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode); struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode); struct phy_device *device_phy_find_device(struct device *dev); @@ -1385,6 +1386,10 @@ struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45); int phy_device_register(struct phy_device *phy); void phy_device_free(struct phy_device *phydev); #else +static inline int fwnode_get_phy_id(struct fwnode_handle *fwnode, u32 *phy_id) +{ + return 0; +} static inline struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode) { -- cgit v1.2.3 From bc1bee3b87ee48bd97ef7fd306445132ba2041b0 Mon Sep 17 00:00:00 2001 From: Calvin Johnson Date: Fri, 11 Jun 2021 13:53:54 +0300 Subject: net: mdiobus: Introduce fwnode_mdiobus_register_phy() Introduce fwnode_mdiobus_register_phy() to register PHYs on the mdiobus. From the compatible string, identify whether the PHY is c45 and based on this create a PHY device instance which is registered on the mdiobus. Along with fwnode_mdiobus_register_phy() also introduce fwnode_find_mii_timestamper() and fwnode_mdiobus_phy_device_register() since they are needed. While at it, also use the newly introduced fwnode operation in of_mdiobus_phy_device_register(). Signed-off-by: Calvin Johnson Signed-off-by: Ioana Ciornei Acked-by: Grant Likely Signed-off-by: David S. Miller --- include/linux/fwnode_mdio.h | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) create mode 100644 include/linux/fwnode_mdio.h (limited to 'include/linux') diff --git a/include/linux/fwnode_mdio.h b/include/linux/fwnode_mdio.h new file mode 100644 index 000000000000..faf603c48c86 --- /dev/null +++ b/include/linux/fwnode_mdio.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * FWNODE helper for the MDIO (Ethernet PHY) API + */ + +#ifndef __LINUX_FWNODE_MDIO_H +#define __LINUX_FWNODE_MDIO_H + +#include + +#if IS_ENABLED(CONFIG_FWNODE_MDIO) +int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, + struct phy_device *phy, + struct fwnode_handle *child, u32 addr); + +int fwnode_mdiobus_register_phy(struct mii_bus *bus, + struct fwnode_handle *child, u32 addr); + +#else /* CONFIG_FWNODE_MDIO */ +int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, + struct phy_device *phy, + struct fwnode_handle *child, u32 addr) +{ + return -EINVAL; +} + +static inline int fwnode_mdiobus_register_phy(struct mii_bus *bus, + struct fwnode_handle *child, + u32 addr) +{ + return -EINVAL; +} +#endif + +#endif /* __LINUX_FWNODE_MDIO_H */ -- cgit v1.2.3 From 7ec16433cf1e97cfc823e50e9ee4e2fd3abfc4ee Mon Sep 17 00:00:00 2001 From: Calvin Johnson Date: Fri, 11 Jun 2021 13:53:56 +0300 Subject: ACPI: utils: Introduce acpi_get_local_address() Introduce a wrapper around the _ADR evaluation. Signed-off-by: Calvin Johnson Reviewed-by: Andy Shevchenko Signed-off-by: Ioana Ciornei Acked-by: Rafael J. Wysocki Acked-by: Grant Likely Signed-off-by: David S. Miller --- include/linux/acpi.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index c60745f657e9..6ace3a0f1415 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -710,6 +710,8 @@ static inline u64 acpi_arch_get_root_pointer(void) } #endif +int acpi_get_local_address(acpi_handle handle, u32 *addr); + #else /* !CONFIG_ACPI */ #define acpi_disabled 1 @@ -965,6 +967,11 @@ static inline struct acpi_device *acpi_resource_consumer(struct resource *res) return NULL; } +static inline int acpi_get_local_address(acpi_handle handle, u32 *addr) +{ + return -ENODEV; +} + #endif /* !CONFIG_ACPI */ #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC -- cgit v1.2.3 From 803ca24d2f92e2cf393df4705423f7b09a5eabd9 Mon Sep 17 00:00:00 2001 From: Calvin Johnson Date: Fri, 11 Jun 2021 13:53:57 +0300 Subject: net: mdio: Add ACPI support code for mdio Define acpi_mdiobus_register() to Register mii_bus and create PHYs for each ACPI child node. Signed-off-by: Calvin Johnson Signed-off-by: Ioana Ciornei Acked-by: Rafael J. Wysocki Acked-by: Grant Likely Signed-off-by: David S. Miller --- include/linux/acpi_mdio.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) create mode 100644 include/linux/acpi_mdio.h (limited to 'include/linux') diff --git a/include/linux/acpi_mdio.h b/include/linux/acpi_mdio.h new file mode 100644 index 000000000000..0a24ab7cb66f --- /dev/null +++ b/include/linux/acpi_mdio.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * ACPI helper for the MDIO (Ethernet PHY) API + */ + +#ifndef __LINUX_ACPI_MDIO_H +#define __LINUX_ACPI_MDIO_H + +#include + +#if IS_ENABLED(CONFIG_ACPI_MDIO) +int acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode); +#else /* CONFIG_ACPI_MDIO */ +static inline int +acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode) +{ + /* + * Fall back to mdiobus_register() function to register a bus. + * This way, we don't have to keep compat bits around in drivers. + */ + + return mdiobus_register(mdio); +} +#endif + +#endif /* __LINUX_ACPI_MDIO_H */ -- cgit v1.2.3 From 25396f680dd6257096c5dc6ceb90ce57caba8de1 Mon Sep 17 00:00:00 2001 From: Calvin Johnson Date: Fri, 11 Jun 2021 13:53:59 +0300 Subject: net: phylink: introduce phylink_fwnode_phy_connect() Define phylink_fwnode_phy_connect() to connect phy specified by a fwnode to a phylink instance. Signed-off-by: Calvin Johnson Signed-off-by: Ioana Ciornei Acked-by: Grant Likely Reviewed-by: Russell King (Oracle) Signed-off-by: David S. Miller --- include/linux/phylink.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index fd2acfd9b597..afb3ded0b691 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -441,6 +441,9 @@ void phylink_destroy(struct phylink *); 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, + u32 flags); void phylink_disconnect_phy(struct phylink *); void phylink_mac_change(struct phylink *, bool up); -- cgit v1.2.3 From 44931195a5412a97c46d299227fbabad4e09010d Mon Sep 17 00:00:00 2001 From: Arseny Krasnov Date: Fri, 11 Jun 2021 14:12:38 +0300 Subject: virtio/vsock: dequeue callback for SOCK_SEQPACKET Callback fetches RW packets from rx queue of socket until whole record is copied(if user's buffer is full, user is not woken up). This is done to not stall sender, because if we wake up user and it leaves syscall, nobody will send credit update for rest of record, and sender will wait for next enter of read syscall at receiver's side. So if user buffer is full, we just send credit update and drop data. Signed-off-by: Arseny Krasnov Signed-off-by: David S. Miller --- include/linux/virtio_vsock.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index dc636b727179..1d9a302cb91d 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -36,6 +36,7 @@ struct virtio_vsock_sock { u32 rx_bytes; u32 buf_alloc; struct list_head rx_queue; + u32 msg_count; }; struct virtio_vsock_pkt { @@ -80,6 +81,10 @@ virtio_transport_dgram_dequeue(struct vsock_sock *vsk, struct msghdr *msg, size_t len, int flags); +ssize_t +virtio_transport_seqpacket_dequeue(struct vsock_sock *vsk, + struct msghdr *msg, + int flags); s64 virtio_transport_stream_has_data(struct vsock_sock *vsk); s64 virtio_transport_stream_has_space(struct vsock_sock *vsk); -- cgit v1.2.3 From 9ac841f5e9f261245d9d2841ad123566bd160a6e Mon Sep 17 00:00:00 2001 From: Arseny Krasnov Date: Fri, 11 Jun 2021 14:13:06 +0300 Subject: virtio/vsock: rest of SOCK_SEQPACKET support Small updates to make SOCK_SEQPACKET work: 1) Send SHUTDOWN on socket close for SEQPACKET type. 2) Set SEQPACKET packet type during send. 3) Set 'VIRTIO_VSOCK_SEQ_EOR' bit in flags for last packet of message. 4) Implement data check function for SEQPACKET. 5) Check for max datagram size. Signed-off-by: Arseny Krasnov Signed-off-by: David S. Miller --- include/linux/virtio_vsock.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 1d9a302cb91d..35d7eedb5e8e 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -81,12 +81,17 @@ virtio_transport_dgram_dequeue(struct vsock_sock *vsk, struct msghdr *msg, size_t len, int flags); +int +virtio_transport_seqpacket_enqueue(struct vsock_sock *vsk, + struct msghdr *msg, + size_t len); ssize_t virtio_transport_seqpacket_dequeue(struct vsock_sock *vsk, struct msghdr *msg, int flags); s64 virtio_transport_stream_has_data(struct vsock_sock *vsk); s64 virtio_transport_stream_has_space(struct vsock_sock *vsk); +u32 virtio_transport_seqpacket_has_data(struct vsock_sock *vsk); int virtio_transport_do_socket_init(struct vsock_sock *vsk, struct vsock_sock *psk); -- cgit v1.2.3 From 5673ef86380414be1702ba2f1ef92526a14dd1e0 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 11 Jun 2021 23:05:19 +0300 Subject: net: pcs: xpcs: rename mdio_xpcs_args to dw_xpcs The struct mdio_xpcs_args is reminiscent of when a similarly named struct mdio_xpcs_ops existed. Now that that is removed, we can shorten the name to dw_xpcs (dw for DesignWare). Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/pcs/pcs-xpcs.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index 4d815f03b4b2..4f1cdf6f3d4c 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -17,19 +17,19 @@ struct xpcs_id; -struct mdio_xpcs_args { +struct dw_xpcs { struct mdio_device *mdiodev; const struct xpcs_id *id; struct phylink_pcs pcs; }; -int xpcs_get_an_mode(struct mdio_xpcs_args *xpcs, phy_interface_t interface); -void xpcs_validate(struct mdio_xpcs_args *xpcs, unsigned long *supported, +int xpcs_get_an_mode(struct dw_xpcs *xpcs, phy_interface_t interface); +void xpcs_validate(struct dw_xpcs *xpcs, unsigned long *supported, struct phylink_link_state *state); -int xpcs_config_eee(struct mdio_xpcs_args *xpcs, int mult_fact_100ns, +int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, int enable); -struct mdio_xpcs_args *xpcs_create(struct mdio_device *mdiodev, - phy_interface_t interface); -void xpcs_destroy(struct mdio_xpcs_args *xpcs); +struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev, + phy_interface_t interface); +void xpcs_destroy(struct dw_xpcs *xpcs); #endif /* __LINUX_PCS_XPCS_H */ -- cgit v1.2.3 From dd0721ea4c7a6c2ec8b309ff57d74d88f08d4c23 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 11 Jun 2021 23:05:25 +0300 Subject: net: pcs: xpcs: add support for NXP SJA1105 The NXP SJA1105 DSA switch integrates a Synopsys SGMII XPCS on port 4. The generic code works fine, except there is an integration issue which needs to be dealt with: in this switch, the XPCS is integrated with a PMA that has the TX lane polarity inverted by default (PLUS is MINUS, MINUS is PLUS). To obtain normal non-inverted behavior, the TX lane polarity must be inverted in the PCS, via the DIGITAL_CONTROL_2 register. We introduce a pma_config() method in xpcs_compat which is called by the phylink_pcs_config() implementation. Also, the NXP SJA1105 returns all zeroes in the PHY ID registers 2 and 3. We need to hack up an ad-hoc PHY ID (OUI is zero, device ID is 1) in order for the XPCS driver to recognize it. This PHY ID is added to the public include/linux/pcs/pcs-xpcs.h for that reason (for the sja1105 driver to be able to use it in a later patch). Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/pcs/pcs-xpcs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index 4f1cdf6f3d4c..c594f7cdc304 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -10,6 +10,8 @@ #include #include +#define NXP_SJA1105_XPCS_ID 0x00000010 + /* AN mode */ #define DW_AN_C73 1 #define DW_AN_C37_SGMII 2 -- cgit v1.2.3 From f7380bba42fd0654bf8195fb741d5f92b0f46df9 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 11 Jun 2021 23:05:26 +0300 Subject: net: pcs: xpcs: add support for NXP SJA1110 The NXP SJA1110 switch integrates its own, non-Synopsys PMA, but it manages it through the register space of the XPCS itself, in a small register window inside MDIO_MMD_VEND2 from address 0x8030 to 0x806e. This coincides with where the registers for the default Synopsys PMA are, but the register definitions are of course not the same. This situation is an odd hardware quirk, but the simplest way to manage it is to drive the SJA1110's PMA from within the XPCS driver. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/pcs/pcs-xpcs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index c594f7cdc304..dae7dd8ac683 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -11,6 +11,7 @@ #include #define NXP_SJA1105_XPCS_ID 0x00000010 +#define NXP_SJA1110_XPCS_ID 0x00000020 /* AN mode */ #define DW_AN_C73 1 -- cgit v1.2.3 From a853c68e29bb974ca0cc0a8eaf88c333217556aa Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 11 Jun 2021 23:05:27 +0300 Subject: net: pcs: xpcs: export xpcs_do_config and xpcs_link_up The sja1105 hardware has a quirk in that some changes require a switch reset, which loses all configuration. When the reset is initiated, everything needs to be reprogrammed, including the MACs and the PCS. This is currently done in sja1105_static_config_reload() - we manually call sja1105_adjust_port_config(), sja1105_sgmii_pcs_config() and sja1105_sgmii_pcs_force_speed() which are all internal functions. There is a desire for sja1105 to use the common xpcs driver, and that means that the equivalents of those functions, xpcs_do_config() and xpcs_link_up() respectively, will no longer be local functions. Forcing phylink to retrigger a resolve somehow, say by doing dev_close() followed by dev_open() is not really an option, because the CPU port might have a PCS as well, and there is no net device which we can close and reopen for that. Additionally, the dev_close/dev_open sequence might force a renegotiation of the copper-side link for SGMII ports connected to a PHY, and this is undesirable as well, because the switch reset is much quicker than a PHY autoneg, so we would have a lot more downtime. The only solution I see is for the sja1105 driver to keep doing what it's doing, and that means we need to export the equivalents from xpcs for sja1105_sgmii_pcs_config and sja1105_sgmii_pcs_force_speed, and call them directly in sja1105_static_config_reload(). This will be done during the conversion patch. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/pcs/pcs-xpcs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index dae7dd8ac683..add077a81b21 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -27,6 +27,10 @@ struct dw_xpcs { }; int xpcs_get_an_mode(struct dw_xpcs *xpcs, phy_interface_t interface); +void xpcs_link_up(struct phylink_pcs *pcs, unsigned int mode, + phy_interface_t interface, int speed, int duplex); +int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface, + unsigned int mode); void xpcs_validate(struct dw_xpcs *xpcs, unsigned long *supported, struct phylink_link_state *state); int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, -- cgit v1.2.3 From a56c286865692ac12291afe4c66198915c6b08f9 Mon Sep 17 00:00:00 2001 From: Steen Hegelund Date: Fri, 11 Jun 2021 14:54:51 +0200 Subject: net: phy: Add 25G BASE-R interface mode Add 25gbase-r phy interface mode Signed-off-by: Steen Hegelund Signed-off-by: Bjarni Jonasson Reviewed-by: Andrew Lunn Reviewed-by: Russell King (Oracle) Signed-off-by: David S. Miller --- include/linux/phy.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index b60694734b07..3b80dc3ed68b 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -112,6 +112,7 @@ extern const int phy_10gbit_features_array[1]; * @PHY_INTERFACE_MODE_RXAUI: Reduced XAUI * @PHY_INTERFACE_MODE_XAUI: 10 Gigabit Attachment Unit Interface * @PHY_INTERFACE_MODE_10GBASER: 10G BaseR + * @PHY_INTERFACE_MODE_25GBASER: 25G BaseR * @PHY_INTERFACE_MODE_USXGMII: Universal Serial 10GE MII * @PHY_INTERFACE_MODE_10GKR: 10GBASE-KR - with Clause 73 AN * @PHY_INTERFACE_MODE_MAX: Book keeping @@ -147,6 +148,7 @@ typedef enum { PHY_INTERFACE_MODE_XAUI, /* 10GBASE-R, XFI, SFI - single lane 10G Serdes */ PHY_INTERFACE_MODE_10GBASER, + PHY_INTERFACE_MODE_25GBASER, PHY_INTERFACE_MODE_USXGMII, /* 10GBASE-KR - with Clause 73 AN */ PHY_INTERFACE_MODE_10GKR, @@ -223,6 +225,8 @@ static inline const char *phy_modes(phy_interface_t interface) return "xaui"; case PHY_INTERFACE_MODE_10GBASER: return "10gbase-r"; + case PHY_INTERFACE_MODE_25GBASER: + return "25gbase-r"; case PHY_INTERFACE_MODE_USXGMII: return "usxgmii"; case PHY_INTERFACE_MODE_10GKR: -- cgit v1.2.3 From 88b710532e53de2466d1033fb1d5125aabf3215a Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sat, 12 Jun 2021 10:20:56 +0200 Subject: wwan: add interface creation support Add support to create (and destroy) interfaces via a new rtnetlink kind "wwan". The responsible driver has to use the new wwan_register_ops() to make this possible. Signed-off-by: Johannes Berg Signed-off-by: Sergey Ryazanov Signed-off-by: Loic Poulain Signed-off-by: David S. Miller --- include/linux/wwan.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/wwan.h b/include/linux/wwan.h index fa33cc16d931..430a3a0817de 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -7,6 +7,7 @@ #include #include #include +#include /** * enum wwan_port_type - WWAN port types @@ -116,4 +117,27 @@ void wwan_port_txon(struct wwan_port *port); */ void *wwan_port_get_drvdata(struct wwan_port *port); +/** + * struct wwan_ops - WWAN device ops + * @owner: module owner of the WWAN ops + * @priv_size: size of private netdev data area + * @setup: set up a new netdev + * @newlink: register the new netdev + * @dellink: remove the given netdev + */ +struct wwan_ops { + struct module *owner; + unsigned int priv_size; + void (*setup)(struct net_device *dev); + int (*newlink)(void *ctxt, struct net_device *dev, + u32 if_id, struct netlink_ext_ack *extack); + void (*dellink)(void *ctxt, struct net_device *dev, + struct list_head *head); +}; + +int wwan_register_ops(struct device *parent, const struct wwan_ops *ops, + void *ctxt); + +void wwan_unregister_ops(struct device *parent); + #endif /* __WWAN_H */ -- cgit v1.2.3 From be754f6435936e78dafe0ebb9d1e9d52c3bde842 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Sat, 12 Jun 2021 09:37:34 -0500 Subject: net: qualcomm: rmnet: trailer value is a checksum The csum_value field in the rmnet_map_dl_csum_trailer structure is a "real" Internet checksum. It is a 16 bit value, in big endian format, which represents an inverted ones' complement sum over pairs of bytes. Make that clear by changing its type to __sum16. This makes a typecast in rmnet_map_ipv4_dl_csum_trailer() and another in rmnet_map_ipv6_dl_csum_trailer() unnecessary. Signed-off-by: Alex Elder Signed-off-by: David S. Miller --- include/linux/if_rmnet.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/if_rmnet.h b/include/linux/if_rmnet.h index be17610a981e..10e7521ecb6c 100644 --- a/include/linux/if_rmnet.h +++ b/include/linux/if_rmnet.h @@ -25,7 +25,7 @@ struct rmnet_map_dl_csum_trailer { u8 flags; /* MAP_CSUM_DL_VALID_FLAG */ __be16 csum_start_offset; __be16 csum_length; - __be16 csum_value; + __sum16 csum_value; } __aligned(1); /* rmnet_map_dl_csum_trailer flags field: -- cgit v1.2.3 From 718fb2bcf1034232599045fc710644d903c2af4b Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Thu, 13 May 2021 15:07:45 +0300 Subject: iio: adc: ad_sigma_delta: introduct devm_ad_sd_setup_buffer_and_trigger() This is a version of ad_sd_setup_buffer_and_trigger() with all underlying functions (that are used) being replaced with their device-managed variants. One thing to take care here is with {devm_}iio_trigger_alloc(), where both functions take a parent-device object as the first parameter. To make sure nothing quirky is happening, the devm_ad_sd_probe_trigger() function is checking that the provided 'dev' reference is the same as the one stored on the 'struct ad_sigma_delta' driver data. Signed-off-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20210513120752.90074-6-aardelean@deviqon.com Signed-off-by: Jonathan Cameron --- include/linux/iio/adc/ad_sigma_delta.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h index 7199280d89ca..be81ad39fb7a 100644 --- a/include/linux/iio/adc/ad_sigma_delta.h +++ b/include/linux/iio/adc/ad_sigma_delta.h @@ -26,6 +26,7 @@ struct ad_sd_calib_data { }; struct ad_sigma_delta; +struct device; struct iio_dev; /** @@ -135,6 +136,8 @@ int ad_sd_init(struct ad_sigma_delta *sigma_delta, struct iio_dev *indio_dev, int ad_sd_setup_buffer_and_trigger(struct iio_dev *indio_dev); void ad_sd_cleanup_buffer_and_trigger(struct iio_dev *indio_dev); +int devm_ad_sd_setup_buffer_and_trigger(struct device *dev, struct iio_dev *indio_dev); + int ad_sd_validate_trigger(struct iio_dev *indio_dev, struct iio_trigger *trig); #endif -- cgit v1.2.3 From 4b36151d7482654ec50ddc831f19a3e76c8ba4dd Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Thu, 13 May 2021 15:07:52 +0300 Subject: iio: adc: ad_sigma_delta: remove ad_sd_{setup,cleanup}_buffer_and_trigger() Since all AD Sigma-Delta drivers now use the devm_ad_sd_setup_buffer_and_trigger() function, we can remove the old ad_sd_{setup,cleanup}_buffer_and_trigger() functions. This way we can discourage new drivers that use the ad_sigma_delta lib-driver to use these (older functions). Signed-off-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20210513120752.90074-13-aardelean@deviqon.com Signed-off-by: Jonathan Cameron --- include/linux/iio/adc/ad_sigma_delta.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h index be81ad39fb7a..c525fd51652f 100644 --- a/include/linux/iio/adc/ad_sigma_delta.h +++ b/include/linux/iio/adc/ad_sigma_delta.h @@ -133,9 +133,6 @@ int ad_sd_calibrate_all(struct ad_sigma_delta *sigma_delta, int ad_sd_init(struct ad_sigma_delta *sigma_delta, struct iio_dev *indio_dev, struct spi_device *spi, const struct ad_sigma_delta_info *info); -int ad_sd_setup_buffer_and_trigger(struct iio_dev *indio_dev); -void ad_sd_cleanup_buffer_and_trigger(struct iio_dev *indio_dev); - int devm_ad_sd_setup_buffer_and_trigger(struct device *dev, struct iio_dev *indio_dev); int ad_sd_validate_trigger(struct iio_dev *indio_dev, struct iio_trigger *trig); -- cgit v1.2.3 From 29a269c6f54825c643a5c35762a2829ba5be67f6 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 11 May 2021 13:21:32 +0800 Subject: soundwire: intel: move to auxiliary bus Now that the auxiliary_bus exists, there's no reason to use platform devices as children of a PCI device any longer. This patch refactors the code by extending a basic auxiliary device with Intel link-specific structures that need to be passed between controller and link levels. This refactoring is much cleaner with no need for cross-pointers between device and link structures. Note that the auxiliary bus API has separate init and add steps, which requires more attention in the error unwinding paths. The main loop needs to deal with kfree() and auxiliary_device_uninit() for the current iteration before jumping to the common label which releases everything allocated in prior iterations. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Guennadi Liakhovetski Reviewed-by: Ranjani Sridharan Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20210511052132.28150-1-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw_intel.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 3a5446ac014a..1ebea7764011 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -58,7 +58,7 @@ struct sdw_intel_acpi_info { u32 link_mask; }; -struct sdw_intel_link_res; +struct sdw_intel_link_dev; /* Intel clock-stop/pm_runtime quirk definitions */ @@ -109,7 +109,7 @@ struct sdw_intel_slave_id { * Controller * @num_slaves: total number of devices exposed across all enabled links * @handle: ACPI parent handle - * @links: information for each link (controller-specific and kept + * @ldev: information for each link (controller-specific and kept * opaque here) * @ids: array of slave_id, representing Slaves exposed across all enabled * links @@ -123,7 +123,7 @@ struct sdw_intel_ctx { u32 link_mask; int num_slaves; acpi_handle handle; - struct sdw_intel_link_res *links; + struct sdw_intel_link_dev **ldev; struct sdw_intel_slave_id *ids; struct list_head link_list; struct mutex shim_lock; /* lock for access to shared SHIM registers */ -- cgit v1.2.3 From 307773f525eb9217090bd4b11748d880f7f99355 Mon Sep 17 00:00:00 2001 From: Aswath Govindraju Date: Mon, 10 May 2021 10:40:03 +0530 Subject: phy: core: Reword the comment specifying the units of max_link_rate to be Mbps In some subsystems (eg. CAN, SPI), the max link rate supported can be less than 1 Mbps and if the unit for max_link_rate is Mbps then it can't be used. Therefore, leave the decision of units to be used, to the producer and consumer. Signed-off-by: Aswath Govindraju Acked-by: Marc Kleine-Budde Acked-by: Kishon Vijay Abraham I Link: https://lore.kernel.org/r/20210510051006.11393-2-a-govindraju@ti.com Signed-off-by: Vinod Koul --- include/linux/phy/phy.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index 0ed434d02196..f3286f4cd306 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -125,7 +125,7 @@ struct phy_ops { /** * struct phy_attrs - represents phy attributes * @bus_width: Data path width implemented by PHY - * @max_link_rate: Maximum link rate supported by PHY (in Mbps) + * @max_link_rate: Maximum link rate supported by PHY (units to be decided by producer and consumer) * @mode: PHY mode */ struct phy_attrs { -- cgit v1.2.3 From dbea8ae9febdea11cb74d094e6b730987079679e Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 4 May 2021 18:12:19 +0200 Subject: mmc: core: Parse the SD SCR register for support of CMD48/49 and CMD58/59 In SD spec v4.x the support for CMD48/49 and CMD58/59 were introduced as optional features. To let the card announce whether it supports the commands, the SCR register has been extended with corresponding support bits. Let's parse and store this information for later use. Signed-off-by: Ulf Hansson Reviewed-by: Linus Walleij Reviewed-by: Shawn Lin Acked-by: Avri Altman Link: https://lore.kernel.org/r/20210504161222.101536-9-ulf.hansson@linaro.org --- include/linux/mmc/card.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index f9ad35dd6012..858fc4d11240 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -139,6 +139,8 @@ struct sd_scr { unsigned char cmds; #define SD_SCR_CMD20_SUPPORT (1<<0) #define SD_SCR_CMD23_SUPPORT (1<<1) +#define SD_SCR_CMD48_SUPPORT (1<<2) +#define SD_SCR_CMD58_SUPPORT (1<<3) }; struct sd_ssr { -- cgit v1.2.3 From c784f92769ae8eafb2eb489408757528ff7525df Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 4 May 2021 18:12:20 +0200 Subject: mmc: core: Read the SD function extension registers for power management In the SD spec v4.0 the CMD48/49 and CMD58/59 were introduced as optional commands. In the SD spec v4.1 the SD function extension registers were introduced, which requires support for CMD48/49/58/59 to be read/written from/to. Moreover, a specific function extension register were added to let the card announce support for optional features in regards to power management. The features that were added are "Power Off Notification", "Power Down Mode" and "Power Sustenance". As a first step to support this, let's read and parse the register for power management during the SD card initialization and store the information about the supported features in the struct mmc_card. In this way, we prepare for subsequent changes to implement the complete support for the new features. Signed-off-by: Ulf Hansson Reviewed-by: Linus Walleij Reviewed-by: Shawn Lin Acked-by: Avri Altman Link: https://lore.kernel.org/r/20210504161222.101536-10-ulf.hansson@linaro.org --- include/linux/mmc/card.h | 13 +++++++++++++ include/linux/mmc/sd.h | 3 +++ 2 files changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 858fc4d11240..03a862e93594 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -191,6 +191,18 @@ struct sd_switch_caps { #define SD_MAX_CURRENT_800 (1 << SD_SET_CURRENT_LIMIT_800) }; +struct sd_ext_reg { + u8 fno; + u8 page; + u16 offset; + u8 rev; + u8 feature_support; +/* Power Management Function. */ +#define SD_EXT_POWER_OFF_NOTIFY (1<<0) +#define SD_EXT_POWER_SUSTENANCE (1<<1) +#define SD_EXT_POWER_DOWN_MODE (1<<2) +}; + struct sdio_cccr { unsigned int sdio_vsn; unsigned int sd_vsn; @@ -292,6 +304,7 @@ struct mmc_card { struct sd_scr scr; /* extra SD information */ struct sd_ssr ssr; /* yet more SD information */ struct sd_switch_caps sw_caps; /* switch (CMD6) caps */ + struct sd_ext_reg ext_power; /* SD extension reg for PM */ unsigned int sdio_funcs; /* number of SDIO functions */ atomic_t sdio_funcs_probed; /* number of probed SDIO funcs */ diff --git a/include/linux/mmc/sd.h b/include/linux/mmc/sd.h index 2236aa540faa..43bfc5c39ad4 100644 --- a/include/linux/mmc/sd.h +++ b/include/linux/mmc/sd.h @@ -29,6 +29,9 @@ #define SD_APP_OP_COND 41 /* bcr [31:0] OCR R3 */ #define SD_APP_SEND_SCR 51 /* adtc R1 */ + /* class 11 */ +#define SD_READ_EXTR_SINGLE 48 /* adtc [31:0] R1 */ + /* OCR bit definitions */ #define SD_OCR_S18R (1 << 24) /* 1.8V switching request */ #define SD_ROCR_S18A SD_OCR_S18R /* 1.8V switching accepted by card */ -- cgit v1.2.3 From 4e6306e0b83c6251699c2202e859b55ddf7b8c5f Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 4 May 2021 18:12:21 +0200 Subject: mmc: core: Read performance enhancements registers for SD cards In SD spec v6.x the SD function extension registers for performance enhancements were introduced. These registers let the SD card announce supports for various performance related features, like "self-maintenance", "cache" and "command queuing". Let's extend the parsing of SD function extension registers and store the information in the struct mmc_card. This prepares for subsequent changes to implement the complete support for new the performance enhancement features. Signed-off-by: Ulf Hansson Acked-by: Avri Altman Reviewed-by: Linus Walleij Reviewed-by: Shawn Lin Link: https://lore.kernel.org/r/20210504161222.101536-11-ulf.hansson@linaro.org --- include/linux/mmc/card.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 03a862e93594..2867af0635f8 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -201,6 +201,12 @@ struct sd_ext_reg { #define SD_EXT_POWER_OFF_NOTIFY (1<<0) #define SD_EXT_POWER_SUSTENANCE (1<<1) #define SD_EXT_POWER_DOWN_MODE (1<<2) +/* Performance Enhancement Function. */ +#define SD_EXT_PERF_FX_EVENT (1<<0) +#define SD_EXT_PERF_CARD_MAINT (1<<1) +#define SD_EXT_PERF_HOST_MAINT (1<<2) +#define SD_EXT_PERF_CACHE (1<<3) +#define SD_EXT_PERF_CMD_QUEUE (1<<4) }; struct sdio_cccr { @@ -305,6 +311,7 @@ struct mmc_card { struct sd_ssr ssr; /* yet more SD information */ struct sd_switch_caps sw_caps; /* switch (CMD6) caps */ struct sd_ext_reg ext_power; /* SD extension reg for PM */ + struct sd_ext_reg ext_perf; /* SD extension reg for PERF */ unsigned int sdio_funcs; /* number of SDIO functions */ atomic_t sdio_funcs_probed; /* number of probed SDIO funcs */ -- cgit v1.2.3 From 2c5d42769038045b92160a849aad43c4b3170e2a Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 4 May 2021 18:12:22 +0200 Subject: mmc: core: Add support for Power Off Notification for SD cards Rather than only deselecting the SD card via a CMD7, before we cut power to it at system suspend, at runtime suspend or at shutdown, let's add support for a graceful power off sequence via enabling the SD Power Off Notification feature. Note that, the Power Off Notification feature was added in the SD spec v4.x, which is several years ago. However, it's still a bit unclear how often the SD card vendors decides to implement support for it. To validate these changes a Sandisk Extreme PRO A2 64GB has been used, which seems to work nicely. Signed-off-by: Ulf Hansson Acked-by: Avri Altman Reviewed-by: Linus Walleij Reviewed-by: Shawn Lin Link: https://lore.kernel.org/r/20210504161222.101536-12-ulf.hansson@linaro.org --- include/linux/mmc/sd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sd.h b/include/linux/mmc/sd.h index 43bfc5c39ad4..6727576a8755 100644 --- a/include/linux/mmc/sd.h +++ b/include/linux/mmc/sd.h @@ -31,6 +31,7 @@ /* class 11 */ #define SD_READ_EXTR_SINGLE 48 /* adtc [31:0] R1 */ +#define SD_WRITE_EXTR_SINGLE 49 /* adtc [31:0] R1 */ /* OCR bit definitions */ #define SD_OCR_S18R (1 << 24) /* 1.8V switching request */ -- cgit v1.2.3 From 130206a615a9831a65e186484a5a332f9f6d29c8 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 11 May 2021 12:13:59 +0200 Subject: mmc: core: Add support for cache ctrl for SD cards In SD spec v6.x the SD function extension registers for performance enhancements were introduced. As a part of this an optional internal cache on the SD card, can be used to improve performance. The let the SD card use the cache, the host needs to enable it and manage flushing of the cache, so let's add support for this. Note that for an SD card supporting the cache it's mandatory for it, to also support the poweroff notification feature. According to the SD spec, if the cache has been enabled and a poweroff notification is sent to the card, that implicitly also means that the card should flush its internal cache. Therefore, dealing with cache flushing for REQ_OP_FLUSH block requests is sufficient. Reviewed-by: Linus Walleij Signed-off-by: Ulf Hansson Reviewed-by: Avri Altman Link: https://lore.kernel.org/r/20210511101359.83521-1-ulf.hansson@linaro.org --- include/linux/mmc/card.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 2867af0635f8..74e6c0624d27 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -196,6 +196,7 @@ struct sd_ext_reg { u8 page; u16 offset; u8 rev; + u8 feature_enabled; u8 feature_support; /* Power Management Function. */ #define SD_EXT_POWER_OFF_NOTIFY (1<<0) -- cgit v1.2.3 From 21adc2e45f4ef32786807375107543797ff68615 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 8 Jun 2021 20:06:20 +0200 Subject: mmc: Improve function name when aborting a tuning cmd MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 'mmc_abort_tuning()' made me think tuning gets completely aborted. However, it sends only a STOP cmd to cancel the current tuning cmd. Tuning process may still continue after that. So, rename the function to 'mmc_send_abort_tuning()' to better reflect all this. Signed-off-by: Wolfram Sang Reviewed-by: Niklas Söderlund Link: https://lore.kernel.org/r/20210608180620.40059-1-wsa+renesas@sang-engineering.com Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index c7e7b43600e9..0abd47e9ef9b 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -632,6 +632,6 @@ static inline enum dma_data_direction mmc_get_dma_dir(struct mmc_data *data) } int mmc_send_tuning(struct mmc_host *host, u32 opcode, int *cmd_error); -int mmc_abort_tuning(struct mmc_host *host, u32 opcode); +int mmc_send_abort_tuning(struct mmc_host *host, u32 opcode); #endif /* LINUX_MMC_HOST_H */ -- cgit v1.2.3 From 590e8a082a5772071d7bcfea2b8e5a2453cecad2 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 2 Jun 2021 16:37:01 +0100 Subject: CFI: Move function_nocfi() into compiler.h Currently the common definition of function_nocfi() is provided by , and architectures are expected to provide a definition in . Due to header dependencies, this can make it hard to use function_nocfi() in low-level headers. As function_nocfi() has no dependency on any mm code, nor on any memory definitions, it doesn't need to live in or . Generally, it would make more sense for it to live in , where an architecture can override it in . Move the definitions accordingly. Signed-off-by: Mark Rutland Cc: Catalin Marinas Cc: Kees Cook Cc: Nathan Chancellor Cc: Sami Tolvanen Cc: Will Deacon Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20210602153701.35957-1-mark.rutland@arm.com --- include/linux/compiler.h | 10 ++++++++++ include/linux/mm.h | 10 ---------- 2 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index df5b405e6305..099e529a5d25 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -213,6 +213,16 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, __v; \ }) +/* + * With CONFIG_CFI_CLANG, the compiler replaces function addresses in + * instrumented C code with jump table addresses. Architectures that + * support CFI can define this macro to return the actual function address + * when needed. + */ +#ifndef function_nocfi +#define function_nocfi(x) (x) +#endif + #endif /* __KERNEL__ */ /* diff --git a/include/linux/mm.h b/include/linux/mm.h index c274f75efcf9..b8c28b10f25d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -124,16 +124,6 @@ extern int mmap_rnd_compat_bits __read_mostly; #define lm_alias(x) __va(__pa_symbol(x)) #endif -/* - * With CONFIG_CFI_CLANG, the compiler replaces function addresses in - * instrumented C code with jump table addresses. Architectures that - * support CFI can define this macro to return the actual function address - * when needed. - */ -#ifndef function_nocfi -#define function_nocfi(x) (x) -#endif - /* * To prevent common memory management code establishing * a zero page mapping on a read fault. -- cgit v1.2.3 From 9c61e789546810ee63708568737cb990d2b86605 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Wed, 5 May 2021 11:40:54 +0200 Subject: dma-buf: some dma_fence_chain improvements MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The callback and the irq work are never used at the same time. Putting them into an union saves us 24 bytes and makes the structure only 120 bytes in size. Signed-off-by: Christian König Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210611120301.10595-2-christian.koenig@amd.com --- include/linux/dma-fence-chain.h | 27 +++++++++++++++++++++------ 1 file changed, 21 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h index 10462a029da2..c6eb3aa45668 100644 --- a/include/linux/dma-fence-chain.h +++ b/include/linux/dma-fence-chain.h @@ -16,21 +16,36 @@ /** * struct dma_fence_chain - fence to represent an node of a fence chain * @base: fence base class - * @lock: spinlock for fence handling * @prev: previous fence of the chain * @prev_seqno: original previous seqno before garbage collection * @fence: encapsulated fence - * @cb: callback structure for signaling - * @work: irq work item for signaling + * @lock: spinlock for fence handling */ struct dma_fence_chain { struct dma_fence base; - spinlock_t lock; struct dma_fence __rcu *prev; u64 prev_seqno; struct dma_fence *fence; - struct dma_fence_cb cb; - struct irq_work work; + union { + /** + * @cb: callback for signaling + * + * This is used to add the callback for signaling the + * complection of the fence chain. Never used at the same time + * as the irq work. + */ + struct dma_fence_cb cb; + + /** + * @work: irq work item for signaling + * + * Irq work structure to allow us to add the callback without + * running into lock inversion. Never used at the same time as + * the callback. + */ + struct irq_work work; + }; + spinlock_t lock; }; extern const struct dma_fence_ops dma_fence_chain_ops; -- cgit v1.2.3 From 440d0f12b52a920f4c78376b3ce7039ba59244c5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Wed, 5 May 2021 13:38:12 +0200 Subject: dma-buf: add dma_fence_chain_alloc/free v3 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a common allocation helper. Cleaning up the mix of kzalloc/kmalloc and some unused code in the selftest. v2: polish kernel doc a bit v3: polish kernel doc even a bit more Signed-off-by: Christian König Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210611120301.10595-3-christian.koenig@amd.com --- include/linux/dma-fence-chain.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h index c6eb3aa45668..54fe3443fd2c 100644 --- a/include/linux/dma-fence-chain.h +++ b/include/linux/dma-fence-chain.h @@ -12,6 +12,7 @@ #include #include +#include /** * struct dma_fence_chain - fence to represent an node of a fence chain @@ -66,6 +67,30 @@ to_dma_fence_chain(struct dma_fence *fence) return container_of(fence, struct dma_fence_chain, base); } +/** + * dma_fence_chain_alloc + * + * Returns a new struct dma_fence_chain object or NULL on failure. + */ +static inline struct dma_fence_chain *dma_fence_chain_alloc(void) +{ + return kmalloc(sizeof(struct dma_fence_chain), GFP_KERNEL); +}; + +/** + * dma_fence_chain_free + * @chain: chain node to free + * + * Frees up an allocated but not used struct dma_fence_chain object. This + * doesn't need an RCU grace period since the fence was never initialized nor + * published. After dma_fence_chain_init() has been called the fence must be + * released by calling dma_fence_put(), and not through this function. + */ +static inline void dma_fence_chain_free(struct dma_fence_chain *chain) +{ + kfree(chain); +}; + /** * dma_fence_chain_for_each - iterate over all fences in chain * @iter: current fence -- cgit v1.2.3 From ec4b94f9b37bf028cb9b9c39cd1c1cb5dd1ab40c Mon Sep 17 00:00:00 2001 From: Michael Grzeschik Date: Mon, 14 Jun 2021 06:31:18 +0200 Subject: net: phy: micrel: move phy reg offsets to common header Some micrel devices share the same PHY register defines. This patch moves them to one common header so other drivers can reuse them. And reuse generic MII_* defines where possible. Signed-off-by: Michael Grzeschik Signed-off-by: Oleksij Rempel Reviewed-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/micrel_phy.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index 416ee6dd2574..b03e2afcb53f 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -45,4 +45,17 @@ #define MICREL_KSZ9021_RGMII_CLK_CTRL_PAD_SCEW 0x104 #define MICREL_KSZ9021_RGMII_RX_DATA_PAD_SCEW 0x105 +/* Device specific MII_BMCR (Reg 0) bits */ +/* 1 = HP Auto MDI/MDI-X mode, 0 = Microchip Auto MDI/MDI-X mode */ +#define KSZ886X_BMCR_HP_MDIX BIT(5) +/* 1 = Force MDI (transmit on RXP/RXM pins), 0 = Normal operation + * (transmit on TXP/TXM pins) + */ +#define KSZ886X_BMCR_FORCE_MDI BIT(4) +/* 1 = Disable auto MDI-X */ +#define KSZ886X_BMCR_DISABLE_AUTO_MDIX BIT(3) +#define KSZ886X_BMCR_DISABLE_FAR_END_FAULT BIT(2) +#define KSZ886X_BMCR_DISABLE_TRANSMIT BIT(1) +#define KSZ886X_BMCR_DISABLE_LED BIT(0) + #endif /* _MICREL_PHY_H */ -- cgit v1.2.3 From 52939393bd682248a415de4c0439280aafaccd66 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Mon, 14 Jun 2021 06:31:21 +0200 Subject: net: phy/dsa micrel/ksz886x add MDI-X support Add support for MDI-X status and configuration Signed-off-by: Oleksij Rempel Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/micrel_phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index b03e2afcb53f..58370abd9f4f 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -58,4 +58,6 @@ #define KSZ886X_BMCR_DISABLE_TRANSMIT BIT(1) #define KSZ886X_BMCR_DISABLE_LED BIT(0) +#define KSZ886X_CTRL_MDIX_STAT BIT(4) + #endif /* _MICREL_PHY_H */ -- cgit v1.2.3 From 49011e0c1555dd7a689d0f32fd78c1ecd43e59cd Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Mon, 14 Jun 2021 06:31:25 +0200 Subject: net: phy: micrel: ksz886x/ksz8081: add cabletest support This patch support for cable test for the ksz886x switches and the ksz8081 PHY. The patch was tested on a KSZ8873RLL switch with following results: - port 1: - provides invalid values, thus return -ENOTSUPP (Errata: DS80000830A: "LinkMD does not work on Port 1", http://ww1.microchip.com/downloads/en/DeviceDoc/KSZ8873-Errata-DS80000830A.pdf) - port 2: - can detect distance - can detect open on each wire of pair A (wire 1 and 2) - can detect open only on one wire of pair B (only wire 3) - can detect short between wires of a pair (wires 1 + 2 or 3 + 6) - short between pairs is detected as open. For example short between wires 2 + 3 is detected as open. Signed-off-by: Oleksij Rempel Signed-off-by: David S. Miller --- include/linux/micrel_phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index 58370abd9f4f..3d43c60b49fa 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -39,6 +39,7 @@ /* struct phy_device dev_flags definitions */ #define MICREL_PHY_50MHZ_CLK 0x00000001 #define MICREL_PHY_FXEN 0x00000002 +#define MICREL_KSZ8_P1_ERRATA 0x00000003 #define MICREL_KSZ9021_EXTREG_CTRL 0xB #define MICREL_KSZ9021_EXTREG_DATA_WRITE 0xC -- cgit v1.2.3 From e4e3f24b822f9dc9ae2427a8d686e8c1d80d6bd2 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 23 Feb 2021 10:37:05 +0200 Subject: net/mlx5: Provide cpumask at EQ creation phase The users of EQ are running their code on different CPUs and with various affinity patterns. Move the cpumask setting close to their actual usage. Signed-off-by: Leon Romanovsky Reviewed-by: Shay Drory Signed-off-by: Saeed Mahameed --- include/linux/mlx5/eq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/eq.h b/include/linux/mlx5/eq.h index e49d8c0d4f26..cea6ecb4b73e 100644 --- a/include/linux/mlx5/eq.h +++ b/include/linux/mlx5/eq.h @@ -16,6 +16,7 @@ struct mlx5_eq_param { u8 irq_index; int nent; u64 mask[4]; + cpumask_var_t affinity; }; struct mlx5_eq * -- cgit v1.2.3 From 3af26495a2473c95ada3674c6b4dfc658be0a6ec Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Mon, 10 May 2021 09:10:43 +0300 Subject: net/mlx5: Enlarge interrupt field in CREATE_EQ FW is now supporting more than 256 MSI-X per PF (up to 2K). Hence, enlarge interrupt field in CREATE_EQ to make use of the new MSI-X's. Signed-off-by: Shay Drory Reviewed-by: Maor Gottlieb Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 057db0eaf195..2d1ed78289ff 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -3806,8 +3806,8 @@ struct mlx5_ifc_eqc_bits { u8 reserved_at_80[0x20]; - u8 reserved_at_a0[0x18]; - u8 intr[0x8]; + u8 reserved_at_a0[0x14]; + u8 intr[0xc]; u8 reserved_at_c0[0x3]; u8 log_page_size[0x5]; -- cgit v1.2.3 From 341466b64f301dabaed791c5862d2ae5a9e72849 Mon Sep 17 00:00:00 2001 From: Russ Weight Date: Mon, 14 Jun 2021 10:09:02 -0700 Subject: fpga: altera-pr-ip: Remove function alt_pr_unregister Remove the alt_pr_unregister() function; it is no longer used. Signed-off-by: Russ Weight Reviewed-by: Xu Yilun Signed-off-by: Moritz Fischer Link: https://lore.kernel.org/r/20210614170909.232415-2-mdf@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/fpga/altera-pr-ip-core.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fpga/altera-pr-ip-core.h b/include/linux/fpga/altera-pr-ip-core.h index 0b08ac20ab16..a6b4c07858cc 100644 --- a/include/linux/fpga/altera-pr-ip-core.h +++ b/include/linux/fpga/altera-pr-ip-core.h @@ -13,6 +13,5 @@ #include int alt_pr_register(struct device *dev, void __iomem *reg_base); -void alt_pr_unregister(struct device *dev); #endif /* _ALT_PR_IP_CORE_H */ -- cgit v1.2.3 From bdb8d06dfefd666d5981d884b535b04105869fcc Mon Sep 17 00:00:00 2001 From: Hridya Valsaraju Date: Thu, 3 Jun 2021 14:47:51 -0700 Subject: dmabuf: Add the capability to expose DMA-BUF stats in sysfs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Overview ======== The patch adds DMA-BUF statistics to /sys/kernel/dmabuf/buffers. It allows statistics to be enabled for each DMA-BUF in sysfs by enabling the config CONFIG_DMABUF_SYSFS_STATS. The following stats will be exposed by the interface: /sys/kernel/dmabuf/buffers//exporter_name /sys/kernel/dmabuf/buffers//size /sys/kernel/dmabuf/buffers//attachments//device /sys/kernel/dmabuf/buffers//attachments//map_counter The inode_number is unique for each DMA-BUF and was added earlier [1] in order to allow userspace to track DMA-BUF usage across different processes. Use Cases ========= The interface provides a way to gather DMA-BUF per-buffer statistics from production devices. These statistics will be used to derive DMA-BUF per-exporter stats and per-device usage stats for Android Bug reports. The corresponding userspace changes can be found at [2]. Telemetry tools will also capture this information(along with other memory metrics) periodically as well as on important events like a foreground app kill (which might have been triggered by Low Memory Killer). It will also contribute to provide a snapshot of the system memory usage on other events such as OOM kills and Application Not Responding events. Background ========== Currently, there are two existing interfaces that provide information about DMA-BUFs. 1) /sys/kernel/debug/dma_buf/bufinfo debugfs is however unsuitable to be mounted in production systems and cannot be considered as an alternative to the sysfs interface being proposed. 2) proc//fdinfo/ The proc//fdinfo/ files expose information about DMA-BUF fds. However, the existing procfs interfaces can only provide information about the buffers for which processes hold fds or have the buffers mmapped into their address space. Since the procfs interfaces alone cannot provide a full picture of all DMA-BUFs in the system, there is the need for an alternate interface to provide this information on production systems. The patch contains the following major improvements over v1: 1) Each attachment is represented by its own directory to allow creating a symlink to the importing device and to also provide room for future expansion. 2) The number of distinct mappings of each attachment is exposed in a separate file. 3) The per-buffer statistics are now in /sys/kernel/dmabuf/buffers inorder to make the interface expandable in future. All of the improvements above are based on suggestions/feedback from Daniel Vetter and Christian König. A shell script that can be run on a classic Linux environment to read out the DMA-BUF statistics can be found at [3](suggested by John Stultz). [1]: https://lore.kernel.org/patchwork/patch/1088791/ [2]: https://android-review.googlesource.com/q/topic:%22dmabuf-sysfs%22+(status:open%20OR%20status:merged) [3]: https://android-review.googlesource.com/c/platform/system/memory/libmeminfo/+/1549734 Reviewed-by: Greg Kroah-Hartman Signed-off-by: Hridya Valsaraju Reported-by: kernel test robot Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210603214758.2955251-1-hridya@google.com --- include/linux/dma-buf.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index efdc56b9d95f..342585bd6dff 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -295,6 +295,9 @@ struct dma_buf_ops { * @poll: for userspace poll support * @cb_excl: for userspace poll support * @cb_shared: for userspace poll support + * @sysfs_entry: for exposing information about this buffer in sysfs. + * The attachment_uid member of @sysfs_entry is protected by dma_resv lock + * and is incremented on each attach. * * This represents a shared buffer, created by calling dma_buf_export(). The * userspace representation is a normal file descriptor, which can be created by @@ -330,6 +333,15 @@ struct dma_buf { __poll_t active; } cb_excl, cb_shared; +#ifdef CONFIG_DMABUF_SYSFS_STATS + /* for sysfs stats */ + struct dma_buf_sysfs_entry { + struct kobject kobj; + struct dma_buf *dmabuf; + unsigned int attachment_uid; + struct kset *attach_stats_kset; + } *sysfs_entry; +#endif }; /** @@ -379,6 +391,7 @@ struct dma_buf_attach_ops { * @importer_ops: importer operations for this attachment, if provided * dma_buf_map/unmap_attachment() must be called with the dma_resv lock held. * @importer_priv: importer specific attachment data. + * @sysfs_entry: For exposing information about this attachment in sysfs. * * This structure holds the attachment information between the dma_buf buffer * and its user device(s). The list contains one attachment struct per device @@ -399,6 +412,13 @@ struct dma_buf_attachment { const struct dma_buf_attach_ops *importer_ops; void *importer_priv; void *priv; +#ifdef CONFIG_DMABUF_SYSFS_STATS + /* for sysfs stats */ + struct dma_buf_attach_sysfs_entry { + struct kobject kobj; + unsigned int map_counter; + } *sysfs_entry; +#endif }; /** -- cgit v1.2.3 From 654ee49b7e0883e660be6e6e20876fc4cbdaadd1 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Thu, 10 Jun 2021 11:02:44 +0200 Subject: tty: make tty_get_{char,frame}_size available Many tty drivers contain code to compute bits count depending on termios cflags. So extract this code from serial core to two separate tty helper functions: * tty_get_char_size -- only size of a character, without flags, * tty_get_frame_size -- complete size of a frame including flags. In the next patch, calls to these new functions replace many copies of this code. Note that we accept only cflag as a parameter. That's because some callers like pch_uart_startup or sunsab_console_setup don't have at hand termios which we could pass around. Cc: Joe Perches Cc: Johan Hovold Reviewed-by: Andy Shevchenko Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210610090247.2593-1-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 4c0c7ca1d9a4..19dc1097e09c 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -495,6 +495,9 @@ static inline speed_t tty_get_baud_rate(struct tty_struct *tty) return tty_termios_baud_rate(&tty->termios); } +unsigned char tty_get_char_size(unsigned int cflag); +unsigned char tty_get_frame_size(unsigned int cflag); + extern void tty_termios_copy_hw(struct ktermios *new, struct ktermios *old); extern int tty_termios_hw_change(const struct ktermios *a, const struct ktermios *b); extern int tty_set_termios(struct tty_struct *tty, struct ktermios *kt); -- cgit v1.2.3 From b4e326165e21d6a11483f6a4de2174b933413554 Mon Sep 17 00:00:00 2001 From: Matthias Kaehlcke Date: Wed, 9 Jun 2021 15:02:46 -0700 Subject: USB: misc: Add onboard_usb_hub driver The main issue this driver addresses is that a USB hub needs to be powered before it can be discovered. For discrete onboard hubs (an example for such a hub is the Realtek RTS5411) this is often solved by supplying the hub with an 'always-on' regulator, which is kind of a hack. Some onboard hubs may require further initialization steps, like changing the state of a GPIO or enabling a clock, which requires even more hacks. This driver creates a platform device representing the hub which performs the necessary initialization. Currently it only supports switching on a single regulator, support for multiple regulators or other actions can be added as needed. Different initialization sequences can be supported based on the compatible string. Besides performing the initialization the driver can be configured to power the hub off during system suspend. This can help to extend battery life on battery powered devices which have no requirements to keep the hub powered during suspend. The driver can also be configured to leave the hub powered when a wakeup capable USB device is connected when suspending, and power it off otherwise. Technically the driver consists of two drivers, the platform driver described above and a very thin USB driver that subclasses the generic driver. The purpose of this driver is to provide the platform driver with the USB devices corresponding to the hub(s) (a hub controller may provide multiple 'logical' hubs, e.g. one to support USB 2.0 and another for USB 3.x). Note: the current series only supports hubs connected directly to a root hub (through xhci-plat), support for other configurations could be added if needed. Co-developed-by: Ravi Chandra Sadineni Acked-by: Alan Stern Signed-off-by: Ravi Chandra Sadineni Signed-off-by: Matthias Kaehlcke Link: https://lore.kernel.org/r/20210609150159.v12.2.I7c9a1f1d6ced41dd8310e8a03da666a32364e790@changeid Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/onboard_hub.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) create mode 100644 include/linux/usb/onboard_hub.h (limited to 'include/linux') diff --git a/include/linux/usb/onboard_hub.h b/include/linux/usb/onboard_hub.h new file mode 100644 index 000000000000..d9373230556e --- /dev/null +++ b/include/linux/usb/onboard_hub.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __LINUX_USB_ONBOARD_HUB_H +#define __LINUX_USB_ONBOARD_HUB_H + +struct usb_device; +struct list_head; + +#if IS_ENABLED(CONFIG_USB_ONBOARD_HUB) +void onboard_hub_create_pdevs(struct usb_device *parent_hub, struct list_head *pdev_list); +void onboard_hub_destroy_pdevs(struct list_head *pdev_list); +#else +static inline void onboard_hub_create_pdevs(struct usb_device *parent_hub, + struct list_head *pdev_list) {} +static inline void onboard_hub_destroy_pdevs(struct list_head *pdev_list) {} +#endif + +#endif /* __LINUX_USB_ONBOARD_HUB_H */ -- cgit v1.2.3 From 412981e06294dac3254d83bbf71d4184ea911d05 Mon Sep 17 00:00:00 2001 From: Matthias Kaehlcke Date: Wed, 9 Jun 2021 15:02:47 -0700 Subject: of/platform: Add stubs for of_platform_device_create/destroy() Code for platform_device_create() and of_platform_device_destroy() is only generated if CONFIG_OF_ADDRESS=y. Add stubs to avoid unresolved symbols when CONFIG_OF_ADDRESS is not set. Acked-by: Rob Herring Signed-off-by: Matthias Kaehlcke Link: https://lore.kernel.org/r/20210609150159.v12.3.I08fd2e1c775af04f663730e9fb4d00e6bbb38541@changeid Signed-off-by: Greg Kroah-Hartman --- include/linux/of_platform.h | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index 84a966623e78..d15b6cd5e1c3 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -61,16 +61,18 @@ static inline struct platform_device *of_find_device_by_node(struct device_node } #endif +extern int of_platform_bus_probe(struct device_node *root, + const struct of_device_id *matches, + struct device *parent); + +#ifdef CONFIG_OF_ADDRESS /* Platform devices and busses creation */ extern struct platform_device *of_platform_device_create(struct device_node *np, const char *bus_id, struct device *parent); extern int of_platform_device_destroy(struct device *dev, void *data); -extern int of_platform_bus_probe(struct device_node *root, - const struct of_device_id *matches, - struct device *parent); -#ifdef CONFIG_OF_ADDRESS + extern int of_platform_populate(struct device_node *root, const struct of_device_id *matches, const struct of_dev_auxdata *lookup, @@ -84,6 +86,18 @@ extern int devm_of_platform_populate(struct device *dev); extern void devm_of_platform_depopulate(struct device *dev); #else +/* Platform devices and busses creation */ +static inline struct platform_device *of_platform_device_create(struct device_node *np, + const char *bus_id, + struct device *parent) +{ + return NULL; +} +static inline int of_platform_device_destroy(struct device *dev, void *data) +{ + return -ENODEV; +} + static inline int of_platform_populate(struct device_node *root, const struct of_device_id *matches, const struct of_dev_auxdata *lookup, -- cgit v1.2.3 From 09705dcb63d269000595284b5dd7f5c938d647b9 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 17 May 2021 15:29:46 +0300 Subject: devres: Enable trace events In some cases the printf() mechanism is too heavy and can't be used. For example, when debugging a race condition involving devres API. When CONFIG_DEBUG_DEVRES is enabled I can't reproduce an issue, and otherwise it's quite visible with a useful information being collected. Enable trace events for devres part of the driver core. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20210517122946.53161-4-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index f1a00040fa53..b630f183f504 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -165,21 +165,12 @@ void device_remove_bin_file(struct device *dev, typedef void (*dr_release_t)(struct device *dev, void *res); typedef int (*dr_match_t)(struct device *dev, void *res, void *match_data); -#ifdef CONFIG_DEBUG_DEVRES void *__devres_alloc_node(dr_release_t release, size_t size, gfp_t gfp, int nid, const char *name) __malloc; #define devres_alloc(release, size, gfp) \ __devres_alloc_node(release, size, gfp, NUMA_NO_NODE, #release) #define devres_alloc_node(release, size, gfp, nid) \ __devres_alloc_node(release, size, gfp, nid, #release) -#else -void *devres_alloc_node(dr_release_t release, size_t size, - gfp_t gfp, int nid) __malloc; -static inline void *devres_alloc(dr_release_t release, size_t size, gfp_t gfp) -{ - return devres_alloc_node(release, size, gfp, NUMA_NO_NODE); -} -#endif void devres_for_each_res(struct device *dev, dr_release_t release, dr_match_t match, void *match_data, -- cgit v1.2.3 From 60f86b9a1c0d81507133173ba3dcfc3edd4d89a5 Mon Sep 17 00:00:00 2001 From: Huilong Deng Date: Tue, 15 Jun 2021 23:55:30 +0900 Subject: mcb: Remove trailing semicolon in macros Macros should not use a trailing semicolon. Signed-off-by: Huilong Deng Signed-off-by: Johannes Thumshirn Link: https://lore.kernel.org/r/fe520620eeddaa2ed8c669125f9b673c89d6b5a5.1623768541.git.johannes.thumshirn@wdc.com Signed-off-by: Greg Kroah-Hartman --- include/linux/mcb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mcb.h b/include/linux/mcb.h index 71dd10a3d928..f6efb16f9d1b 100644 --- a/include/linux/mcb.h +++ b/include/linux/mcb.h @@ -120,7 +120,7 @@ extern int __must_check __mcb_register_driver(struct mcb_driver *drv, __mcb_register_driver(driver, THIS_MODULE, KBUILD_MODNAME) extern void mcb_unregister_driver(struct mcb_driver *driver); #define module_mcb_driver(__mcb_driver) \ - module_driver(__mcb_driver, mcb_register_driver, mcb_unregister_driver); + module_driver(__mcb_driver, mcb_register_driver, mcb_unregister_driver) extern void mcb_bus_add_devices(const struct mcb_bus *bus); extern int mcb_device_register(struct mcb_bus *bus, struct mcb_device *dev); extern struct mcb_bus *mcb_alloc_bus(struct device *carrier); -- cgit v1.2.3 From d5e4ddaeb6ab2c3c7fbb7b247a6d34bb0b18d87e Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Sat, 12 Jun 2021 21:32:22 +0900 Subject: bpf: Support socket migration by eBPF. This patch introduces a new bpf_attach_type for BPF_PROG_TYPE_SK_REUSEPORT to check if the attached eBPF program is capable of migrating sockets. When the eBPF program is attached, we run it for socket migration if the expected_attach_type is BPF_SK_REUSEPORT_SELECT_OR_MIGRATE or net.ipv4.tcp_migrate_req is enabled. Currently, the expected_attach_type is not enforced for the BPF_PROG_TYPE_SK_REUSEPORT type of program. Thus, this commit follows the earlier idea in the commit aac3fc320d94 ("bpf: Post-hooks for sys_bind") to fix up the zero expected_attach_type in bpf_prog_load_fixup_attach_type(). Moreover, this patch adds a new field (migrating_sk) to sk_reuseport_md to select a new listener based on the child socket. migrating_sk varies depending on if it is migrating a request in the accept queue or during 3WHS. - accept_queue : sock (ESTABLISHED/SYN_RECV) - 3WHS : request_sock (NEW_SYN_RECV) In the eBPF program, we can select a new listener by BPF_FUNC_sk_select_reuseport(). Also, we can cancel migration by returning SK_DROP. This feature is useful when listeners have different settings at the socket API level or when we want to free resources as soon as possible. - SK_PASS with selected_sk, select it as a new listener - SK_PASS with selected_sk NULL, fallbacks to the random selection - SK_DROP, cancel the migration. There is a noteworthy point. We select a listening socket in three places, but we do not have struct skb at closing a listener or retransmitting a SYN+ACK. On the other hand, some helper functions do not expect skb is NULL (e.g. skb_header_pointer() in BPF_FUNC_skb_load_bytes(), skb_tail_pointer() in BPF_FUNC_skb_load_bytes_relative()). So we allocate an empty skb temporarily before running the eBPF program. Suggested-by: Martin KaFai Lau Signed-off-by: Kuniyuki Iwashima Signed-off-by: Daniel Borkmann Reviewed-by: Eric Dumazet Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/netdev/20201123003828.xjpjdtk4ygl6tg6h@kafai-mbp.dhcp.thefacebook.com/ Link: https://lore.kernel.org/netdev/20201203042402.6cskdlit5f3mw4ru@kafai-mbp.dhcp.thefacebook.com/ Link: https://lore.kernel.org/netdev/20201209030903.hhow5r53l6fmozjn@kafai-mbp.dhcp.thefacebook.com/ Link: https://lore.kernel.org/bpf/20210612123224.12525-10-kuniyu@amazon.co.jp --- include/linux/bpf.h | 1 + include/linux/filter.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 86dec5001ae2..f309fc1509f2 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2048,6 +2048,7 @@ struct sk_reuseport_kern { struct sk_buff *skb; struct sock *sk; struct sock *selected_sk; + struct sock *migrating_sk; void *data_end; u32 hash; u32 reuseport_id; diff --git a/include/linux/filter.h b/include/linux/filter.h index c5ad7df029ed..688856e0b28a 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -996,11 +996,13 @@ void bpf_warn_invalid_xdp_action(u32 act); #ifdef CONFIG_INET struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, + struct sock *migrating_sk, u32 hash); #else static inline struct sock * bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, + struct sock *migrating_sk, u32 hash) { return NULL; -- cgit v1.2.3 From 65b6d89d45a77256b743f421d109d469baefa688 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Mon, 3 May 2021 17:56:50 +0200 Subject: mtd: spi-nor: sfdp: save a copy of the SFDP data Due to possible mode switching to 8D-8D-8D, it might not be possible to read the SFDP after the initial probe. To be able to dump the SFDP via sysfs afterwards, make a complete copy of it. Signed-off-by: Michael Walle Signed-off-by: Vignesh Raghavendra Tested-by: Heiko Thiery Reviewed-by: Pratyush Yadav --- include/linux/mtd/spi-nor.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 98ed91b529ea..f67457748ed8 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -383,6 +383,7 @@ struct spi_nor_flash_parameter; * @read_proto: the SPI protocol for read operations * @write_proto: the SPI protocol for write operations * @reg_proto: the SPI protocol for read_reg/write_reg/erase operations + * @sfdp: the SFDP data of the flash * @controller_ops: SPI NOR controller driver specific operations. * @params: [FLASH-SPECIFIC] SPI NOR flash parameters and settings. * The structure includes legacy flash parameters and @@ -412,6 +413,7 @@ struct spi_nor { bool sst_write_second; u32 flags; enum spi_nor_cmd_ext cmd_ext_type; + struct sfdp *sfdp; const struct spi_nor_controller_ops *controller_ops; -- cgit v1.2.3 From 293128b1ef5ae2cfa7403d54e183fe689ed5d303 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Tue, 15 Jun 2021 14:17:35 -0400 Subject: dm writecache: have ssd writeback wait if the kcopyd workqueue is busy Make dm-writecache wait if the kcopyd workqueue is busy (as will happen if waiting for page allocation or inside submit_bio). This change improves performance of "mkfs.ext2" by approximately 20% on one testbed. Signed-off-by: Mikulas Patocka Signed-off-by: Mike Snitzer --- include/linux/dm-kcopyd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dm-kcopyd.h b/include/linux/dm-kcopyd.h index e42de7750c88..c1707ee5b540 100644 --- a/include/linux/dm-kcopyd.h +++ b/include/linux/dm-kcopyd.h @@ -51,6 +51,7 @@ MODULE_PARM_DESC(name, description) struct dm_kcopyd_client; struct dm_kcopyd_client *dm_kcopyd_client_create(struct dm_kcopyd_throttle *throttle); void dm_kcopyd_client_destroy(struct dm_kcopyd_client *kc); +void dm_kcopyd_client_flush(struct dm_kcopyd_client *kc); /* * Submit a copy job to kcopyd. This is built on top of the -- cgit v1.2.3 From 9c54cd10e43947caa64920aaa7a30858193f8ef5 Mon Sep 17 00:00:00 2001 From: Charles Rose Date: Tue, 15 Jun 2021 14:08:01 -0500 Subject: ahci: Add support for Dell S140 and later controllers This patch enables support for Dell S140 and later controllers that use Intel's PCHs configured as PCI_CLASS_STORAGE_RAID. Reviewed-by: Mika Westerberg Signed-off-by: Charles Rose Link: https://lore.kernel.org/r/20210615190801.1744466-1-charles.rose@dell.com Signed-off-by: Jens Axboe --- 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 4c3fa5293d76..803ec446a729 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -631,6 +631,8 @@ #define PCI_DEVICE_ID_DELL_RAC4 0x0012 #define PCI_DEVICE_ID_DELL_PERC5 0x0015 +#define PCI_SUBVENDOR_ID_DELL 0x1028 + #define PCI_VENDOR_ID_MATROX 0x102B #define PCI_DEVICE_ID_MATROX_MGA_2 0x0518 #define PCI_DEVICE_ID_MATROX_MIL 0x0519 -- cgit v1.2.3 From fd14602d05229671be81018fa226f9afdafdba88 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 15 Jun 2021 16:18:22 -0700 Subject: libnvdimm: Export nvdimm shutdown helper, nvdimm_delete() CXL is a hotplug bus and arranges for nvdimm devices to be dynamically discovered and removed. The libnvdimm core manages shutdown of nvdimm security operations when the device is unregistered. That functionality is moved to nvdimm_delete() and invoked by the CXL-to-nvdimm glue code. Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/162379910271.2993820.2955889139842401250.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- include/linux/libnvdimm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 89b69e645ac7..7074aa9af525 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -278,6 +278,7 @@ static inline struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus, return __nvdimm_create(nvdimm_bus, provider_data, groups, flags, cmd_mask, num_flush, flush_wpq, NULL, NULL, NULL); } +void nvdimm_delete(struct nvdimm *nvdimm); const struct nd_cmd_desc *nd_cmd_dimm_desc(int cmd); const struct nd_cmd_desc *nd_cmd_bus_desc(int cmd); -- cgit v1.2.3 From 2744d7a0733503931b71c00d156119ced002f22c Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Wed, 9 Jun 2021 13:40:17 -0500 Subject: ACPI: Check StorageD3Enable _DSD property in ACPI code Although first implemented for NVME, this check may be usable by other drivers as well. Microsoft's specification explicitly mentions that is may be usable by SATA and AHCI devices. Google also indicates that they have used this with SDHCI in a downstream kernel tree that a user can plug a storage device into. Link: https://docs.microsoft.com/en-us/windows-hardware/design/component-guidelines/power-management-for-storage-hardware-devices-intro Suggested-by: Keith Busch CC: Shyam-sundar S-k CC: Alexander Deucher CC: Rafael J. Wysocki CC: Prike Liang Signed-off-by: Mario Limonciello Reviewed-by: Rafael J. Wysocki Signed-off-by: Christoph Hellwig --- include/linux/acpi.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index c60745f657e9..dd0dafd21e33 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1004,6 +1004,7 @@ int acpi_dev_resume(struct device *dev); int acpi_subsys_runtime_suspend(struct device *dev); int acpi_subsys_runtime_resume(struct device *dev); int acpi_dev_pm_attach(struct device *dev, bool power_on); +bool acpi_storage_d3(struct device *dev); #else static inline int acpi_subsys_runtime_suspend(struct device *dev) { return 0; } static inline int acpi_subsys_runtime_resume(struct device *dev) { return 0; } @@ -1011,6 +1012,10 @@ static inline int acpi_dev_pm_attach(struct device *dev, bool power_on) { return 0; } +static inline bool acpi_storage_d3(struct device *dev) +{ + return false; +} #endif #if defined(CONFIG_ACPI) && defined(CONFIG_PM_SLEEP) -- cgit v1.2.3 From 4e7dba070b1f44da9bef4a61fd633f6b73a2e853 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Fri, 28 May 2021 10:04:52 +0100 Subject: ata: include: libata: Move fields commonly over-written to separate MACRO This is a pre-cursor to some upcoming W=1 fix-ups. Fixes the following W=1 kernel build warning(s): Cc: Jens Axboe Cc: Mark Lord Cc: Philipp Zabel Cc: Tejun Heo Cc: linux-ide@vger.kernel.org Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20210528090502.1799866-2-lee.jones@linaro.org Signed-off-by: Jens Axboe --- include/linux/libata.h | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 5f550eb27f81..3fcd24236793 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1397,25 +1397,28 @@ extern struct device_attribute *ata_common_sdev_attrs[]; ATA_SCSI_COMPAT_IOCTL \ .queuecommand = ata_scsi_queuecmd, \ .dma_need_drain = ata_scsi_dma_need_drain, \ - .can_queue = ATA_DEF_QUEUE, \ - .tag_alloc_policy = BLK_TAG_ALLOC_RR, \ .this_id = ATA_SHT_THIS_ID, \ .emulated = ATA_SHT_EMULATED, \ .proc_name = drv_name, \ - .slave_configure = ata_scsi_slave_config, \ .slave_destroy = ata_scsi_slave_destroy, \ .bios_param = ata_std_bios_param, \ .unlock_native_capacity = ata_scsi_unlock_native_capacity -#define ATA_BASE_SHT(drv_name) \ +#define ATA_SUBBASE_SHT(drv_name) \ __ATA_BASE_SHT(drv_name), \ + .can_queue = ATA_DEF_QUEUE, \ + .tag_alloc_policy = BLK_TAG_ALLOC_RR, \ + .slave_configure = ata_scsi_slave_config + +#define ATA_BASE_SHT(drv_name) \ + ATA_SUBBASE_SHT(drv_name), \ .sdev_attrs = ata_common_sdev_attrs #ifdef CONFIG_SATA_HOST extern struct device_attribute *ata_ncq_sdev_attrs[]; #define ATA_NCQ_SHT(drv_name) \ - __ATA_BASE_SHT(drv_name), \ + ATA_SUBBASE_SHT(drv_name), \ .sdev_attrs = ata_ncq_sdev_attrs, \ .change_queue_depth = ata_scsi_change_queue_depth #endif -- cgit v1.2.3 From b7fb14d3ac63117e0e8beabe75f4ea52051fbe3a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 16 Jun 2021 15:46:58 +0200 Subject: ide: remove the legacy ide driver The legay ide driver has been replace with libata starting in 2003 and has been scheduled for removal for a while. Finally kill it off so that we can start cleaning up various bits of cruft it forced on the block layer. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/ide.h | 1623 --------------------------------------------------- 1 file changed, 1623 deletions(-) delete mode 100644 include/linux/ide.h (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h deleted file mode 100644 index 2c300689a51a..000000000000 --- a/include/linux/ide.h +++ /dev/null @@ -1,1623 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _IDE_H -#define _IDE_H -/* - * linux/include/linux/ide.h - * - * Copyright (C) 1994-2002 Linus Torvalds & authors - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -/* for request_sense */ -#include -#include -#include -#include - -/* - * Probably not wise to fiddle with these - */ -#define SUPPORT_VLB_SYNC 1 -#define IDE_DEFAULT_MAX_FAILURES 1 -#define ERROR_MAX 8 /* Max read/write errors per sector */ -#define ERROR_RESET 3 /* Reset controller every 4th retry */ -#define ERROR_RECAL 1 /* Recalibrate every 2nd retry */ - -struct device; - -/* values for ide_request.type */ -enum ata_priv_type { - ATA_PRIV_MISC, - ATA_PRIV_TASKFILE, - ATA_PRIV_PC, - ATA_PRIV_SENSE, /* sense request */ - ATA_PRIV_PM_SUSPEND, /* suspend request */ - ATA_PRIV_PM_RESUME, /* resume request */ -}; - -struct ide_request { - struct scsi_request sreq; - u8 sense[SCSI_SENSE_BUFFERSIZE]; - u8 type; - void *special; -}; - -static inline struct ide_request *ide_req(struct request *rq) -{ - return blk_mq_rq_to_pdu(rq); -} - -static inline bool ata_misc_request(struct request *rq) -{ - return blk_rq_is_private(rq) && ide_req(rq)->type == ATA_PRIV_MISC; -} - -static inline bool ata_taskfile_request(struct request *rq) -{ - return blk_rq_is_private(rq) && ide_req(rq)->type == ATA_PRIV_TASKFILE; -} - -static inline bool ata_pc_request(struct request *rq) -{ - return blk_rq_is_private(rq) && ide_req(rq)->type == ATA_PRIV_PC; -} - -static inline bool ata_sense_request(struct request *rq) -{ - return blk_rq_is_private(rq) && ide_req(rq)->type == ATA_PRIV_SENSE; -} - -static inline bool ata_pm_request(struct request *rq) -{ - return blk_rq_is_private(rq) && - (ide_req(rq)->type == ATA_PRIV_PM_SUSPEND || - ide_req(rq)->type == ATA_PRIV_PM_RESUME); -} - -/* Error codes returned in result to the higher part of the driver. */ -enum { - IDE_DRV_ERROR_GENERAL = 101, - IDE_DRV_ERROR_FILEMARK = 102, - IDE_DRV_ERROR_EOD = 103, -}; - -/* - * Definitions for accessing IDE controller registers - */ -#define IDE_NR_PORTS (10) - -struct ide_io_ports { - unsigned long data_addr; - - union { - unsigned long error_addr; /* read: error */ - unsigned long feature_addr; /* write: feature */ - }; - - unsigned long nsect_addr; - unsigned long lbal_addr; - unsigned long lbam_addr; - unsigned long lbah_addr; - - unsigned long device_addr; - - union { - unsigned long status_addr; /*  read: status  */ - unsigned long command_addr; /* write: command */ - }; - - unsigned long ctl_addr; - - unsigned long irq_addr; -}; - -#define OK_STAT(stat,good,bad) (((stat)&((good)|(bad)))==(good)) - -#define BAD_R_STAT (ATA_BUSY | ATA_ERR) -#define BAD_W_STAT (BAD_R_STAT | ATA_DF) -#define BAD_STAT (BAD_R_STAT | ATA_DRQ) -#define DRIVE_READY (ATA_DRDY | ATA_DSC) - -#define BAD_CRC (ATA_ABORTED | ATA_ICRC) - -#define SATA_NR_PORTS (3) /* 16 possible ?? */ - -#define SATA_STATUS_OFFSET (0) -#define SATA_ERROR_OFFSET (1) -#define SATA_CONTROL_OFFSET (2) - -/* - * Our Physical Region Descriptor (PRD) table should be large enough - * to handle the biggest I/O request we are likely to see. Since requests - * can have no more than 256 sectors, and since the typical blocksize is - * two or more sectors, we could get by with a limit of 128 entries here for - * the usual worst case. Most requests seem to include some contiguous blocks, - * further reducing the number of table entries required. - * - * The driver reverts to PIO mode for individual requests that exceed - * this limit (possible with 512 byte blocksizes, eg. MSDOS f/s), so handling - * 100% of all crazy scenarios here is not necessary. - * - * As it turns out though, we must allocate a full 4KB page for this, - * so the two PRD tables (ide0 & ide1) will each get half of that, - * allowing each to have about 256 entries (8 bytes each) from this. - */ -#define PRD_BYTES 8 -#define PRD_ENTRIES 256 - -/* - * Some more useful definitions - */ -#define PARTN_BITS 6 /* number of minor dev bits for partitions */ -#define MAX_DRIVES 2 /* per interface; 2 assumed by lots of code */ - -/* - * Timeouts for various operations: - */ -enum { - /* spec allows up to 20ms, but CF cards and SSD drives need more */ - WAIT_DRQ = 1 * HZ, /* 1s */ - /* some laptops are very slow */ - WAIT_READY = 5 * HZ, /* 5s */ - /* should be less than 3ms (?), if all ATAPI CD is closed at boot */ - WAIT_PIDENTIFY = 10 * HZ, /* 10s */ - /* worst case when spinning up */ - WAIT_WORSTCASE = 30 * HZ, /* 30s */ - /* maximum wait for an IRQ to happen */ - WAIT_CMD = 10 * HZ, /* 10s */ - /* Some drives require a longer IRQ timeout. */ - WAIT_FLOPPY_CMD = 50 * HZ, /* 50s */ - /* - * Some drives (for example, Seagate STT3401A Travan) require a very - * long timeout, because they don't return an interrupt or clear their - * BSY bit until after the command completes (even retension commands). - */ - WAIT_TAPE_CMD = 900 * HZ, /* 900s */ - /* minimum sleep time */ - WAIT_MIN_SLEEP = HZ / 50, /* 20ms */ -}; - -/* - * Op codes for special requests to be handled by ide_special_rq(). - * Values should be in the range of 0x20 to 0x3f. - */ -#define REQ_DRIVE_RESET 0x20 -#define REQ_DEVSET_EXEC 0x21 -#define REQ_PARK_HEADS 0x22 -#define REQ_UNPARK_HEADS 0x23 - -/* - * hwif_chipset_t is used to keep track of the specific hardware - * chipset used by each IDE interface, if known. - */ -enum { ide_unknown, ide_generic, ide_pci, - ide_cmd640, ide_dtc2278, ide_ali14xx, - ide_qd65xx, ide_umc8672, ide_ht6560b, - ide_4drives, ide_pmac, ide_acorn, - ide_au1xxx, ide_palm3710 -}; - -typedef u8 hwif_chipset_t; - -/* - * Structure to hold all information about the location of this port - */ -struct ide_hw { - union { - struct ide_io_ports io_ports; - unsigned long io_ports_array[IDE_NR_PORTS]; - }; - - int irq; /* our irq number */ - struct device *dev, *parent; - unsigned long config; -}; - -static inline void ide_std_init_ports(struct ide_hw *hw, - unsigned long io_addr, - unsigned long ctl_addr) -{ - unsigned int i; - - for (i = 0; i <= 7; i++) - hw->io_ports_array[i] = io_addr++; - - hw->io_ports.ctl_addr = ctl_addr; -} - -#define MAX_HWIFS 10 - -/* - * Now for the data we need to maintain per-drive: ide_drive_t - */ - -#define ide_scsi 0x21 -#define ide_disk 0x20 -#define ide_optical 0x7 -#define ide_cdrom 0x5 -#define ide_tape 0x1 -#define ide_floppy 0x0 - -/* - * Special Driver Flags - */ -enum { - IDE_SFLAG_SET_GEOMETRY = BIT(0), - IDE_SFLAG_RECALIBRATE = BIT(1), - IDE_SFLAG_SET_MULTMODE = BIT(2), -}; - -/* - * Status returned from various ide_ functions - */ -typedef enum { - ide_stopped, /* no drive operation was started */ - ide_started, /* a drive operation was started, handler was set */ -} ide_startstop_t; - -enum { - IDE_VALID_ERROR = BIT(1), - IDE_VALID_FEATURE = IDE_VALID_ERROR, - IDE_VALID_NSECT = BIT(2), - IDE_VALID_LBAL = BIT(3), - IDE_VALID_LBAM = BIT(4), - IDE_VALID_LBAH = BIT(5), - IDE_VALID_DEVICE = BIT(6), - IDE_VALID_LBA = IDE_VALID_LBAL | - IDE_VALID_LBAM | - IDE_VALID_LBAH, - IDE_VALID_OUT_TF = IDE_VALID_FEATURE | - IDE_VALID_NSECT | - IDE_VALID_LBA, - IDE_VALID_IN_TF = IDE_VALID_NSECT | - IDE_VALID_LBA, - IDE_VALID_OUT_HOB = IDE_VALID_OUT_TF, - IDE_VALID_IN_HOB = IDE_VALID_ERROR | - IDE_VALID_NSECT | - IDE_VALID_LBA, -}; - -enum { - IDE_TFLAG_LBA48 = BIT(0), - IDE_TFLAG_WRITE = BIT(1), - IDE_TFLAG_CUSTOM_HANDLER = BIT(2), - IDE_TFLAG_DMA_PIO_FALLBACK = BIT(3), - /* force 16-bit I/O operations */ - IDE_TFLAG_IO_16BIT = BIT(4), - /* struct ide_cmd was allocated using kmalloc() */ - IDE_TFLAG_DYN = BIT(5), - IDE_TFLAG_FS = BIT(6), - IDE_TFLAG_MULTI_PIO = BIT(7), - IDE_TFLAG_SET_XFER = BIT(8), -}; - -enum { - IDE_FTFLAG_FLAGGED = BIT(0), - IDE_FTFLAG_SET_IN_FLAGS = BIT(1), - IDE_FTFLAG_OUT_DATA = BIT(2), - IDE_FTFLAG_IN_DATA = BIT(3), -}; - -struct ide_taskfile { - u8 data; /* 0: data byte (for TASKFILE ioctl) */ - union { /* 1: */ - u8 error; /* read: error */ - u8 feature; /* write: feature */ - }; - u8 nsect; /* 2: number of sectors */ - u8 lbal; /* 3: LBA low */ - u8 lbam; /* 4: LBA mid */ - u8 lbah; /* 5: LBA high */ - u8 device; /* 6: device select */ - union { /* 7: */ - u8 status; /* read: status */ - u8 command; /* write: command */ - }; -}; - -struct ide_cmd { - struct ide_taskfile tf; - struct ide_taskfile hob; - struct { - struct { - u8 tf; - u8 hob; - } out, in; - } valid; - - u16 tf_flags; - u8 ftf_flags; /* for TASKFILE ioctl */ - int protocol; - - int sg_nents; /* number of sg entries */ - int orig_sg_nents; - int sg_dma_direction; /* DMA transfer direction */ - - unsigned int nbytes; - unsigned int nleft; - unsigned int last_xfer_len; - - struct scatterlist *cursg; - unsigned int cursg_ofs; - - struct request *rq; /* copy of request */ -}; - -/* ATAPI packet command flags */ -enum { - /* set when an error is considered normal - no retry (ide-tape) */ - PC_FLAG_ABORT = BIT(0), - PC_FLAG_SUPPRESS_ERROR = BIT(1), - PC_FLAG_WAIT_FOR_DSC = BIT(2), - PC_FLAG_DMA_OK = BIT(3), - PC_FLAG_DMA_IN_PROGRESS = BIT(4), - PC_FLAG_DMA_ERROR = BIT(5), - PC_FLAG_WRITING = BIT(6), -}; - -#define ATAPI_WAIT_PC (60 * HZ) - -struct ide_atapi_pc { - /* actual packet bytes */ - u8 c[12]; - /* incremented on each retry */ - int retries; - int error; - - /* bytes to transfer */ - int req_xfer; - - /* the corresponding request */ - struct request *rq; - - unsigned long flags; - - /* - * those are more or less driver-specific and some of them are subject - * to change/removal later. - */ - unsigned long timeout; -}; - -struct ide_devset; -struct ide_driver; - -#ifdef CONFIG_BLK_DEV_IDEACPI -struct ide_acpi_drive_link; -struct ide_acpi_hwif_link; -#endif - -struct ide_drive_s; - -struct ide_disk_ops { - int (*check)(struct ide_drive_s *, const char *); - int (*get_capacity)(struct ide_drive_s *); - void (*unlock_native_capacity)(struct ide_drive_s *); - void (*setup)(struct ide_drive_s *); - void (*flush)(struct ide_drive_s *); - int (*init_media)(struct ide_drive_s *, struct gendisk *); - int (*set_doorlock)(struct ide_drive_s *, struct gendisk *, - int); - ide_startstop_t (*do_request)(struct ide_drive_s *, struct request *, - sector_t); - int (*ioctl)(struct ide_drive_s *, struct block_device *, - fmode_t, unsigned int, unsigned long); - int (*compat_ioctl)(struct ide_drive_s *, struct block_device *, - fmode_t, unsigned int, unsigned long); -}; - -/* ATAPI device flags */ -enum { - IDE_AFLAG_DRQ_INTERRUPT = BIT(0), - - /* ide-cd */ - /* Drive cannot eject the disc. */ - IDE_AFLAG_NO_EJECT = BIT(1), - /* Drive is a pre ATAPI 1.2 drive. */ - IDE_AFLAG_PRE_ATAPI12 = BIT(2), - /* TOC addresses are in BCD. */ - IDE_AFLAG_TOCADDR_AS_BCD = BIT(3), - /* TOC track numbers are in BCD. */ - IDE_AFLAG_TOCTRACKS_AS_BCD = BIT(4), - /* Saved TOC information is current. */ - IDE_AFLAG_TOC_VALID = BIT(6), - /* We think that the drive door is locked. */ - IDE_AFLAG_DOOR_LOCKED = BIT(7), - /* SET_CD_SPEED command is unsupported. */ - IDE_AFLAG_NO_SPEED_SELECT = BIT(8), - IDE_AFLAG_VERTOS_300_SSD = BIT(9), - IDE_AFLAG_VERTOS_600_ESD = BIT(10), - IDE_AFLAG_SANYO_3CD = BIT(11), - IDE_AFLAG_FULL_CAPS_PAGE = BIT(12), - IDE_AFLAG_PLAY_AUDIO_OK = BIT(13), - IDE_AFLAG_LE_SPEED_FIELDS = BIT(14), - - /* ide-floppy */ - /* Avoid commands not supported in Clik drive */ - IDE_AFLAG_CLIK_DRIVE = BIT(15), - /* Requires BH algorithm for packets */ - IDE_AFLAG_ZIP_DRIVE = BIT(16), - /* Supports format progress report */ - IDE_AFLAG_SRFP = BIT(17), - - /* ide-tape */ - IDE_AFLAG_IGNORE_DSC = BIT(18), - /* 0 When the tape position is unknown */ - IDE_AFLAG_ADDRESS_VALID = BIT(19), - /* Device already opened */ - IDE_AFLAG_BUSY = BIT(20), - /* Attempt to auto-detect the current user block size */ - IDE_AFLAG_DETECT_BS = BIT(21), - /* Currently on a filemark */ - IDE_AFLAG_FILEMARK = BIT(22), - /* 0 = no tape is loaded, so we don't rewind after ejecting */ - IDE_AFLAG_MEDIUM_PRESENT = BIT(23), - - IDE_AFLAG_NO_AUTOCLOSE = BIT(24), -}; - -/* device flags */ -enum { - /* restore settings after device reset */ - IDE_DFLAG_KEEP_SETTINGS = BIT(0), - /* device is using DMA for read/write */ - IDE_DFLAG_USING_DMA = BIT(1), - /* okay to unmask other IRQs */ - IDE_DFLAG_UNMASK = BIT(2), - /* don't attempt flushes */ - IDE_DFLAG_NOFLUSH = BIT(3), - /* DSC overlap */ - IDE_DFLAG_DSC_OVERLAP = BIT(4), - /* give potential excess bandwidth */ - IDE_DFLAG_NICE1 = BIT(5), - /* device is physically present */ - IDE_DFLAG_PRESENT = BIT(6), - /* disable Host Protected Area */ - IDE_DFLAG_NOHPA = BIT(7), - /* id read from device (synthetic if not set) */ - IDE_DFLAG_ID_READ = BIT(8), - IDE_DFLAG_NOPROBE = BIT(9), - /* need to do check_media_change() */ - IDE_DFLAG_REMOVABLE = BIT(10), - IDE_DFLAG_FORCED_GEOM = BIT(12), - /* disallow setting unmask bit */ - IDE_DFLAG_NO_UNMASK = BIT(13), - /* disallow enabling 32-bit I/O */ - IDE_DFLAG_NO_IO_32BIT = BIT(14), - /* for removable only: door lock/unlock works */ - IDE_DFLAG_DOORLOCKING = BIT(15), - /* disallow DMA */ - IDE_DFLAG_NODMA = BIT(16), - /* powermanagement told us not to do anything, so sleep nicely */ - IDE_DFLAG_BLOCKED = BIT(17), - /* sleeping & sleep field valid */ - IDE_DFLAG_SLEEPING = BIT(18), - IDE_DFLAG_POST_RESET = BIT(19), - IDE_DFLAG_UDMA33_WARNED = BIT(20), - IDE_DFLAG_LBA48 = BIT(21), - /* status of write cache */ - IDE_DFLAG_WCACHE = BIT(22), - /* used for ignoring ATA_DF */ - IDE_DFLAG_NOWERR = BIT(23), - /* retrying in PIO */ - IDE_DFLAG_DMA_PIO_RETRY = BIT(24), - IDE_DFLAG_LBA = BIT(25), - /* don't unload heads */ - IDE_DFLAG_NO_UNLOAD = BIT(26), - /* heads unloaded, please don't reset port */ - IDE_DFLAG_PARKED = BIT(27), - IDE_DFLAG_MEDIA_CHANGED = BIT(28), - /* write protect */ - IDE_DFLAG_WP = BIT(29), - IDE_DFLAG_FORMAT_IN_PROGRESS = BIT(30), - IDE_DFLAG_NIEN_QUIRK = BIT(31), -}; - -struct ide_drive_s { - char name[4]; /* drive name, such as "hda" */ - char driver_req[10]; /* requests specific driver */ - - struct request_queue *queue; /* request queue */ - - bool (*prep_rq)(struct ide_drive_s *, struct request *); - - struct blk_mq_tag_set tag_set; - - struct request *rq; /* current request */ - void *driver_data; /* extra driver data */ - u16 *id; /* identification info */ -#ifdef CONFIG_IDE_PROC_FS - struct proc_dir_entry *proc; /* /proc/ide/ directory entry */ - const struct ide_proc_devset *settings; /* /proc/ide/ drive settings */ -#endif - struct hwif_s *hwif; /* actually (ide_hwif_t *) */ - - const struct ide_disk_ops *disk_ops; - - unsigned long dev_flags; - - unsigned long sleep; /* sleep until this time */ - unsigned long timeout; /* max time to wait for irq */ - - u8 special_flags; /* special action flags */ - - u8 select; /* basic drive/head select reg value */ - u8 retry_pio; /* retrying dma capable host in pio */ - u8 waiting_for_dma; /* dma currently in progress */ - u8 dma; /* atapi dma flag */ - - u8 init_speed; /* transfer rate set at boot */ - u8 current_speed; /* current transfer rate set */ - u8 desired_speed; /* desired transfer rate set */ - u8 pio_mode; /* for ->set_pio_mode _only_ */ - u8 dma_mode; /* for ->set_dma_mode _only_ */ - u8 dn; /* now wide spread use */ - u8 acoustic; /* acoustic management */ - u8 media; /* disk, cdrom, tape, floppy, ... */ - u8 ready_stat; /* min status value for drive ready */ - u8 mult_count; /* current multiple sector setting */ - u8 mult_req; /* requested multiple sector setting */ - u8 io_32bit; /* 0=16-bit, 1=32-bit, 2/3=32bit+sync */ - u8 bad_wstat; /* used for ignoring ATA_DF */ - u8 head; /* "real" number of heads */ - u8 sect; /* "real" sectors per track */ - u8 bios_head; /* BIOS/fdisk/LILO number of heads */ - u8 bios_sect; /* BIOS/fdisk/LILO sectors per track */ - - /* delay this long before sending packet command */ - u8 pc_delay; - - unsigned int bios_cyl; /* BIOS/fdisk/LILO number of cyls */ - unsigned int cyl; /* "real" number of cyls */ - void *drive_data; /* used by set_pio_mode/dev_select() */ - unsigned int failures; /* current failure count */ - unsigned int max_failures; /* maximum allowed failure count */ - u64 probed_capacity;/* initial/native media capacity */ - u64 capacity64; /* total number of sectors */ - - int lun; /* logical unit */ - int crc_count; /* crc counter to reduce drive speed */ - - unsigned long debug_mask; /* debugging levels switch */ - -#ifdef CONFIG_BLK_DEV_IDEACPI - struct ide_acpi_drive_link *acpidata; -#endif - struct list_head list; - struct device gendev; - struct completion gendev_rel_comp; /* to deal with device release() */ - - /* current packet command */ - struct ide_atapi_pc *pc; - - /* last failed packet command */ - struct ide_atapi_pc *failed_pc; - - /* callback for packet commands */ - int (*pc_callback)(struct ide_drive_s *, int); - - ide_startstop_t (*irq_handler)(struct ide_drive_s *); - - unsigned long atapi_flags; - - struct ide_atapi_pc request_sense_pc; - - /* current sense rq and buffer */ - bool sense_rq_armed; - bool sense_rq_active; - struct request *sense_rq; - struct request_sense sense_data; - - /* async sense insertion */ - struct work_struct rq_work; - struct list_head rq_list; -}; - -typedef struct ide_drive_s ide_drive_t; - -#define to_ide_device(dev) container_of(dev, ide_drive_t, gendev) - -#define to_ide_drv(obj, cont_type) \ - container_of(obj, struct cont_type, dev) - -#define ide_drv_g(disk, cont_type) \ - container_of((disk)->private_data, struct cont_type, driver) - -struct ide_port_info; - -struct ide_tp_ops { - void (*exec_command)(struct hwif_s *, u8); - u8 (*read_status)(struct hwif_s *); - u8 (*read_altstatus)(struct hwif_s *); - void (*write_devctl)(struct hwif_s *, u8); - - void (*dev_select)(ide_drive_t *); - void (*tf_load)(ide_drive_t *, struct ide_taskfile *, u8); - void (*tf_read)(ide_drive_t *, struct ide_taskfile *, u8); - - void (*input_data)(ide_drive_t *, struct ide_cmd *, - void *, unsigned int); - void (*output_data)(ide_drive_t *, struct ide_cmd *, - void *, unsigned int); -}; - -extern const struct ide_tp_ops default_tp_ops; - -/** - * struct ide_port_ops - IDE port operations - * - * @init_dev: host specific initialization of a device - * @set_pio_mode: routine to program host for PIO mode - * @set_dma_mode: routine to program host for DMA mode - * @reset_poll: chipset polling based on hba specifics - * @pre_reset: chipset specific changes to default for device-hba resets - * @resetproc: routine to reset controller after a disk reset - * @maskproc: special host masking for drive selection - * @quirkproc: check host's drive quirk list - * @clear_irq: clear IRQ - * - * @mdma_filter: filter MDMA modes - * @udma_filter: filter UDMA modes - * - * @cable_detect: detect cable type - */ -struct ide_port_ops { - void (*init_dev)(ide_drive_t *); - void (*set_pio_mode)(struct hwif_s *, ide_drive_t *); - void (*set_dma_mode)(struct hwif_s *, ide_drive_t *); - blk_status_t (*reset_poll)(ide_drive_t *); - void (*pre_reset)(ide_drive_t *); - void (*resetproc)(ide_drive_t *); - void (*maskproc)(ide_drive_t *, int); - void (*quirkproc)(ide_drive_t *); - void (*clear_irq)(ide_drive_t *); - int (*test_irq)(struct hwif_s *); - - u8 (*mdma_filter)(ide_drive_t *); - u8 (*udma_filter)(ide_drive_t *); - - u8 (*cable_detect)(struct hwif_s *); -}; - -struct ide_dma_ops { - void (*dma_host_set)(struct ide_drive_s *, int); - int (*dma_setup)(struct ide_drive_s *, struct ide_cmd *); - void (*dma_start)(struct ide_drive_s *); - int (*dma_end)(struct ide_drive_s *); - int (*dma_test_irq)(struct ide_drive_s *); - void (*dma_lost_irq)(struct ide_drive_s *); - /* below ones are optional */ - int (*dma_check)(struct ide_drive_s *, struct ide_cmd *); - int (*dma_timer_expiry)(struct ide_drive_s *); - void (*dma_clear)(struct ide_drive_s *); - /* - * The following method is optional and only required to be - * implemented for the SFF-8038i compatible controllers. - */ - u8 (*dma_sff_read_status)(struct hwif_s *); -}; - -enum { - IDE_PFLAG_PROBING = BIT(0), -}; - -struct ide_host; - -typedef struct hwif_s { - struct hwif_s *mate; /* other hwif from same PCI chip */ - struct proc_dir_entry *proc; /* /proc/ide/ directory entry */ - - struct ide_host *host; - - char name[6]; /* name of interface, eg. "ide0" */ - - struct ide_io_ports io_ports; - - unsigned long sata_scr[SATA_NR_PORTS]; - - ide_drive_t *devices[MAX_DRIVES + 1]; - - unsigned long port_flags; - - u8 major; /* our major number */ - u8 index; /* 0 for ide0; 1 for ide1; ... */ - u8 channel; /* for dual-port chips: 0=primary, 1=secondary */ - - u32 host_flags; - - u8 pio_mask; - - u8 ultra_mask; - u8 mwdma_mask; - u8 swdma_mask; - - u8 cbl; /* cable type */ - - hwif_chipset_t chipset; /* sub-module for tuning.. */ - - struct device *dev; - - void (*rw_disk)(ide_drive_t *, struct request *); - - const struct ide_tp_ops *tp_ops; - const struct ide_port_ops *port_ops; - const struct ide_dma_ops *dma_ops; - - /* dma physical region descriptor table (cpu view) */ - unsigned int *dmatable_cpu; - /* dma physical region descriptor table (dma view) */ - dma_addr_t dmatable_dma; - - /* maximum number of PRD table entries */ - int prd_max_nents; - /* PRD entry size in bytes */ - int prd_ent_size; - - /* Scatter-gather list used to build the above */ - struct scatterlist *sg_table; - int sg_max_nents; /* Maximum number of entries in it */ - - struct ide_cmd cmd; /* current command */ - - int rqsize; /* max sectors per request */ - int irq; /* our irq number */ - - unsigned long dma_base; /* base addr for dma ports */ - - unsigned long config_data; /* for use by chipset-specific code */ - unsigned long select_data; /* for use by chipset-specific code */ - - unsigned long extra_base; /* extra addr for dma ports */ - unsigned extra_ports; /* number of extra dma ports */ - - unsigned present : 1; /* this interface exists */ - unsigned busy : 1; /* serializes devices on a port */ - - struct device gendev; - struct device *portdev; - - struct completion gendev_rel_comp; /* To deal with device release() */ - - void *hwif_data; /* extra hwif data */ - -#ifdef CONFIG_BLK_DEV_IDEACPI - struct ide_acpi_hwif_link *acpidata; -#endif - - /* IRQ handler, if active */ - ide_startstop_t (*handler)(ide_drive_t *); - - /* BOOL: polling active & poll_timeout field valid */ - unsigned int polling : 1; - - /* current drive */ - ide_drive_t *cur_dev; - - /* current request */ - struct request *rq; - - /* failsafe timer */ - struct timer_list timer; - /* timeout value during long polls */ - unsigned long poll_timeout; - /* queried upon timeouts */ - int (*expiry)(ide_drive_t *); - - int req_gen; - int req_gen_timer; - - spinlock_t lock; -} ____cacheline_internodealigned_in_smp ide_hwif_t; - -#define MAX_HOST_PORTS 4 - -struct ide_host { - ide_hwif_t *ports[MAX_HOST_PORTS + 1]; - unsigned int n_ports; - struct device *dev[2]; - - int (*init_chipset)(struct pci_dev *); - - void (*get_lock)(irq_handler_t, void *); - void (*release_lock)(void); - - irq_handler_t irq_handler; - - unsigned long host_flags; - - int irq_flags; - - void *host_priv; - ide_hwif_t *cur_port; /* for hosts requiring serialization */ - - /* used for hosts requiring serialization */ - volatile unsigned long host_busy; -}; - -#define IDE_HOST_BUSY 0 - -/* - * internal ide interrupt handler type - */ -typedef ide_startstop_t (ide_handler_t)(ide_drive_t *); -typedef int (ide_expiry_t)(ide_drive_t *); - -/* used by ide-cd, ide-floppy, etc. */ -typedef void (xfer_func_t)(ide_drive_t *, struct ide_cmd *, void *, unsigned); - -extern struct mutex ide_setting_mtx; - -/* - * configurable drive settings - */ - -#define DS_SYNC BIT(0) - -struct ide_devset { - int (*get)(ide_drive_t *); - int (*set)(ide_drive_t *, int); - unsigned int flags; -}; - -#define __DEVSET(_flags, _get, _set) { \ - .flags = _flags, \ - .get = _get, \ - .set = _set, \ -} - -#define ide_devset_get(name, field) \ -static int get_##name(ide_drive_t *drive) \ -{ \ - return drive->field; \ -} - -#define ide_devset_set(name, field) \ -static int set_##name(ide_drive_t *drive, int arg) \ -{ \ - drive->field = arg; \ - return 0; \ -} - -#define ide_devset_get_flag(name, flag) \ -static int get_##name(ide_drive_t *drive) \ -{ \ - return !!(drive->dev_flags & flag); \ -} - -#define ide_devset_set_flag(name, flag) \ -static int set_##name(ide_drive_t *drive, int arg) \ -{ \ - if (arg) \ - drive->dev_flags |= flag; \ - else \ - drive->dev_flags &= ~flag; \ - return 0; \ -} - -#define __IDE_DEVSET(_name, _flags, _get, _set) \ -const struct ide_devset ide_devset_##_name = \ - __DEVSET(_flags, _get, _set) - -#define IDE_DEVSET(_name, _flags, _get, _set) \ -static __IDE_DEVSET(_name, _flags, _get, _set) - -#define ide_devset_rw(_name, _func) \ -IDE_DEVSET(_name, 0, get_##_func, set_##_func) - -#define ide_devset_w(_name, _func) \ -IDE_DEVSET(_name, 0, NULL, set_##_func) - -#define ide_ext_devset_rw(_name, _func) \ -__IDE_DEVSET(_name, 0, get_##_func, set_##_func) - -#define ide_ext_devset_rw_sync(_name, _func) \ -__IDE_DEVSET(_name, DS_SYNC, get_##_func, set_##_func) - -#define ide_decl_devset(_name) \ -extern const struct ide_devset ide_devset_##_name - -ide_decl_devset(io_32bit); -ide_decl_devset(keepsettings); -ide_decl_devset(pio_mode); -ide_decl_devset(unmaskirq); -ide_decl_devset(using_dma); - -#ifdef CONFIG_IDE_PROC_FS -/* - * /proc/ide interface - */ - -#define ide_devset_rw_field(_name, _field) \ -ide_devset_get(_name, _field); \ -ide_devset_set(_name, _field); \ -IDE_DEVSET(_name, DS_SYNC, get_##_name, set_##_name) - -#define ide_devset_ro_field(_name, _field) \ -ide_devset_get(_name, _field); \ -IDE_DEVSET(_name, 0, get_##_name, NULL) - -#define ide_devset_rw_flag(_name, _field) \ -ide_devset_get_flag(_name, _field); \ -ide_devset_set_flag(_name, _field); \ -IDE_DEVSET(_name, DS_SYNC, get_##_name, set_##_name) - -struct ide_proc_devset { - const char *name; - const struct ide_devset *setting; - int min, max; - int (*mulf)(ide_drive_t *); - int (*divf)(ide_drive_t *); -}; - -#define __IDE_PROC_DEVSET(_name, _min, _max, _mulf, _divf) { \ - .name = __stringify(_name), \ - .setting = &ide_devset_##_name, \ - .min = _min, \ - .max = _max, \ - .mulf = _mulf, \ - .divf = _divf, \ -} - -#define IDE_PROC_DEVSET(_name, _min, _max) \ -__IDE_PROC_DEVSET(_name, _min, _max, NULL, NULL) - -typedef struct { - const char *name; - umode_t mode; - int (*show)(struct seq_file *, void *); -} ide_proc_entry_t; - -void proc_ide_create(void); -void proc_ide_destroy(void); -void ide_proc_register_port(ide_hwif_t *); -void ide_proc_port_register_devices(ide_hwif_t *); -void ide_proc_unregister_device(ide_drive_t *); -void ide_proc_unregister_port(ide_hwif_t *); -void ide_proc_register_driver(ide_drive_t *, struct ide_driver *); -void ide_proc_unregister_driver(ide_drive_t *, struct ide_driver *); - -int ide_capacity_proc_show(struct seq_file *m, void *v); -int ide_geometry_proc_show(struct seq_file *m, void *v); -#else -static inline void proc_ide_create(void) { ; } -static inline void proc_ide_destroy(void) { ; } -static inline void ide_proc_register_port(ide_hwif_t *hwif) { ; } -static inline void ide_proc_port_register_devices(ide_hwif_t *hwif) { ; } -static inline void ide_proc_unregister_device(ide_drive_t *drive) { ; } -static inline void ide_proc_unregister_port(ide_hwif_t *hwif) { ; } -static inline void ide_proc_register_driver(ide_drive_t *drive, - struct ide_driver *driver) { ; } -static inline void ide_proc_unregister_driver(ide_drive_t *drive, - struct ide_driver *driver) { ; } -#endif - -enum { - /* enter/exit functions */ - IDE_DBG_FUNC = BIT(0), - /* sense key/asc handling */ - IDE_DBG_SENSE = BIT(1), - /* packet commands handling */ - IDE_DBG_PC = BIT(2), - /* request handling */ - IDE_DBG_RQ = BIT(3), - /* driver probing/setup */ - IDE_DBG_PROBE = BIT(4), -}; - -/* DRV_NAME has to be defined in the driver before using the macro below */ -#define __ide_debug_log(lvl, fmt, args...) \ -{ \ - if (unlikely(drive->debug_mask & lvl)) \ - printk(KERN_INFO DRV_NAME ": %s: " fmt "\n", \ - __func__, ## args); \ -} - -/* - * Power Management state machine (rq->pm->pm_step). - * - * For each step, the core calls ide_start_power_step() first. - * This can return: - * - ide_stopped : In this case, the core calls us back again unless - * step have been set to ide_power_state_completed. - * - ide_started : In this case, the channel is left busy until an - * async event (interrupt) occurs. - * Typically, ide_start_power_step() will issue a taskfile request with - * do_rw_taskfile(). - * - * Upon reception of the interrupt, the core will call ide_complete_power_step() - * with the error code if any. This routine should update the step value - * and return. It should not start a new request. The core will call - * ide_start_power_step() for the new step value, unless step have been - * set to IDE_PM_COMPLETED. - */ -enum { - IDE_PM_START_SUSPEND, - IDE_PM_FLUSH_CACHE = IDE_PM_START_SUSPEND, - IDE_PM_STANDBY, - - IDE_PM_START_RESUME, - IDE_PM_RESTORE_PIO = IDE_PM_START_RESUME, - IDE_PM_IDLE, - IDE_PM_RESTORE_DMA, - - IDE_PM_COMPLETED, -}; - -int generic_ide_suspend(struct device *, pm_message_t); -int generic_ide_resume(struct device *); - -void ide_complete_power_step(ide_drive_t *, struct request *); -ide_startstop_t ide_start_power_step(ide_drive_t *, struct request *); -void ide_complete_pm_rq(ide_drive_t *, struct request *); -void ide_check_pm_state(ide_drive_t *, struct request *); - -/* - * Subdrivers support. - * - * The gendriver.owner field should be set to the module owner of this driver. - * The gendriver.name field should be set to the name of this driver - */ -struct ide_driver { - const char *version; - ide_startstop_t (*do_request)(ide_drive_t *, struct request *, sector_t); - struct device_driver gen_driver; - int (*probe)(ide_drive_t *); - void (*remove)(ide_drive_t *); - void (*resume)(ide_drive_t *); - void (*shutdown)(ide_drive_t *); -#ifdef CONFIG_IDE_PROC_FS - ide_proc_entry_t * (*proc_entries)(ide_drive_t *); - const struct ide_proc_devset * (*proc_devsets)(ide_drive_t *); -#endif -}; - -#define to_ide_driver(drv) container_of(drv, struct ide_driver, gen_driver) - -int ide_device_get(ide_drive_t *); -void ide_device_put(ide_drive_t *); - -struct ide_ioctl_devset { - unsigned int get_ioctl; - unsigned int set_ioctl; - const struct ide_devset *setting; -}; - -int ide_setting_ioctl(ide_drive_t *, struct block_device *, unsigned int, - unsigned long, const struct ide_ioctl_devset *); - -int generic_ide_ioctl(ide_drive_t *, struct block_device *, unsigned, unsigned long); - -extern int ide_vlb_clk; -extern int ide_pci_clk; - -int ide_end_rq(ide_drive_t *, struct request *, blk_status_t, unsigned int); -void ide_kill_rq(ide_drive_t *, struct request *); -void ide_insert_request_head(ide_drive_t *, struct request *); - -void __ide_set_handler(ide_drive_t *, ide_handler_t *, unsigned int); -void ide_set_handler(ide_drive_t *, ide_handler_t *, unsigned int); - -void ide_execute_command(ide_drive_t *, struct ide_cmd *, ide_handler_t *, - unsigned int); - -void ide_pad_transfer(ide_drive_t *, int, int); - -ide_startstop_t ide_error(ide_drive_t *, const char *, u8); - -void ide_fix_driveid(u16 *); - -extern void ide_fixstring(u8 *, const int, const int); - -int ide_busy_sleep(ide_drive_t *, unsigned long, int); - -int __ide_wait_stat(ide_drive_t *, u8, u8, unsigned long, u8 *); -int ide_wait_stat(ide_startstop_t *, ide_drive_t *, u8, u8, unsigned long); - -ide_startstop_t ide_do_park_unpark(ide_drive_t *, struct request *); -ide_startstop_t ide_do_devset(ide_drive_t *, struct request *); - -extern ide_startstop_t ide_do_reset (ide_drive_t *); - -extern int ide_devset_execute(ide_drive_t *drive, - const struct ide_devset *setting, int arg); - -void ide_complete_cmd(ide_drive_t *, struct ide_cmd *, u8, u8); -int ide_complete_rq(ide_drive_t *, blk_status_t, unsigned int); - -void ide_tf_readback(ide_drive_t *drive, struct ide_cmd *cmd); -void ide_tf_dump(const char *, struct ide_cmd *); - -void ide_exec_command(ide_hwif_t *, u8); -u8 ide_read_status(ide_hwif_t *); -u8 ide_read_altstatus(ide_hwif_t *); -void ide_write_devctl(ide_hwif_t *, u8); - -void ide_dev_select(ide_drive_t *); -void ide_tf_load(ide_drive_t *, struct ide_taskfile *, u8); -void ide_tf_read(ide_drive_t *, struct ide_taskfile *, u8); - -void ide_input_data(ide_drive_t *, struct ide_cmd *, void *, unsigned int); -void ide_output_data(ide_drive_t *, struct ide_cmd *, void *, unsigned int); - -void SELECT_MASK(ide_drive_t *, int); - -u8 ide_read_error(ide_drive_t *); -void ide_read_bcount_and_ireason(ide_drive_t *, u16 *, u8 *); - -int ide_check_ireason(ide_drive_t *, struct request *, int, int, int); - -int ide_check_atapi_device(ide_drive_t *, const char *); - -void ide_init_pc(struct ide_atapi_pc *); - -/* Disk head parking */ -extern wait_queue_head_t ide_park_wq; -ssize_t ide_park_show(struct device *dev, struct device_attribute *attr, - char *buf); -ssize_t ide_park_store(struct device *dev, struct device_attribute *attr, - const char *buf, size_t len); - -/* - * Special requests for ide-tape block device strategy routine. - * - * In order to service a character device command, we add special requests to - * the tail of our block device request queue and wait for their completion. - */ -enum { - REQ_IDETAPE_PC1 = BIT(0), /* packet command (first stage) */ - REQ_IDETAPE_PC2 = BIT(1), /* packet command (second stage) */ - REQ_IDETAPE_READ = BIT(2), - REQ_IDETAPE_WRITE = BIT(3), -}; - -int ide_queue_pc_tail(ide_drive_t *, struct gendisk *, struct ide_atapi_pc *, - void *, unsigned int); - -int ide_do_test_unit_ready(ide_drive_t *, struct gendisk *); -int ide_do_start_stop(ide_drive_t *, struct gendisk *, int); -int ide_set_media_lock(ide_drive_t *, struct gendisk *, int); -void ide_create_request_sense_cmd(ide_drive_t *, struct ide_atapi_pc *); -void ide_retry_pc(ide_drive_t *drive); - -void ide_prep_sense(ide_drive_t *drive, struct request *rq); -int ide_queue_sense_rq(ide_drive_t *drive, void *special); - -int ide_cd_expiry(ide_drive_t *); - -int ide_cd_get_xferlen(struct request *); - -ide_startstop_t ide_issue_pc(ide_drive_t *, struct ide_cmd *); - -ide_startstop_t do_rw_taskfile(ide_drive_t *, struct ide_cmd *); - -void ide_pio_bytes(ide_drive_t *, struct ide_cmd *, unsigned int, unsigned int); - -void ide_finish_cmd(ide_drive_t *, struct ide_cmd *, u8); - -int ide_raw_taskfile(ide_drive_t *, struct ide_cmd *, u8 *, u16); -int ide_no_data_taskfile(ide_drive_t *, struct ide_cmd *); - -int ide_taskfile_ioctl(ide_drive_t *, unsigned long); - -int ide_dev_read_id(ide_drive_t *, u8, u16 *, int); - -extern int ide_driveid_update(ide_drive_t *); -extern int ide_config_drive_speed(ide_drive_t *, u8); -extern u8 eighty_ninty_three (ide_drive_t *); -extern int taskfile_lib_get_identify(ide_drive_t *drive, u8 *); - -extern int ide_wait_not_busy(ide_hwif_t *hwif, unsigned long timeout); - -extern void ide_stall_queue(ide_drive_t *drive, unsigned long timeout); - -extern void ide_timer_expiry(struct timer_list *t); -extern irqreturn_t ide_intr(int irq, void *dev_id); -extern blk_status_t ide_queue_rq(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *); -extern blk_status_t ide_issue_rq(ide_drive_t *, struct request *, bool); -extern void ide_requeue_and_plug(ide_drive_t *drive, struct request *rq); - -void ide_init_disk(struct gendisk *, ide_drive_t *); - -#ifdef CONFIG_IDEPCI_PCIBUS_ORDER -extern int __ide_pci_register_driver(struct pci_driver *driver, struct module *owner, const char *mod_name); -#define ide_pci_register_driver(d) __ide_pci_register_driver(d, THIS_MODULE, KBUILD_MODNAME) -#else -#define ide_pci_register_driver(d) pci_register_driver(d) -#endif - -static inline int ide_pci_is_in_compatibility_mode(struct pci_dev *dev) -{ - if ((dev->class >> 8) == PCI_CLASS_STORAGE_IDE && (dev->class & 5) != 5) - return 1; - return 0; -} - -void ide_pci_setup_ports(struct pci_dev *, const struct ide_port_info *, - struct ide_hw *, struct ide_hw **); -void ide_setup_pci_noise(struct pci_dev *, const struct ide_port_info *); - -#ifdef CONFIG_BLK_DEV_IDEDMA_PCI -int ide_pci_set_master(struct pci_dev *, const char *); -unsigned long ide_pci_dma_base(ide_hwif_t *, const struct ide_port_info *); -int ide_pci_check_simplex(ide_hwif_t *, const struct ide_port_info *); -int ide_hwif_setup_dma(ide_hwif_t *, const struct ide_port_info *); -#else -static inline int ide_hwif_setup_dma(ide_hwif_t *hwif, - const struct ide_port_info *d) -{ - return -EINVAL; -} -#endif - -struct ide_pci_enablebit { - u8 reg; /* byte pci reg holding the enable-bit */ - u8 mask; /* mask to isolate the enable-bit */ - u8 val; /* value of masked reg when "enabled" */ -}; - -enum { - /* Uses ISA control ports not PCI ones. */ - IDE_HFLAG_ISA_PORTS = BIT(0), - /* single port device */ - IDE_HFLAG_SINGLE = BIT(1), - /* don't use legacy PIO blacklist */ - IDE_HFLAG_PIO_NO_BLACKLIST = BIT(2), - /* set for the second port of QD65xx */ - IDE_HFLAG_QD_2ND_PORT = BIT(3), - /* use PIO8/9 for prefetch off/on */ - IDE_HFLAG_ABUSE_PREFETCH = BIT(4), - /* use PIO6/7 for fast-devsel off/on */ - IDE_HFLAG_ABUSE_FAST_DEVSEL = BIT(5), - /* use 100-102 and 200-202 PIO values to set DMA modes */ - IDE_HFLAG_ABUSE_DMA_MODES = BIT(6), - /* - * keep DMA setting when programming PIO mode, may be used only - * for hosts which have separate PIO and DMA timings (ie. PMAC) - */ - IDE_HFLAG_SET_PIO_MODE_KEEP_DMA = BIT(7), - /* program host for the transfer mode after programming device */ - IDE_HFLAG_POST_SET_MODE = BIT(8), - /* don't program host/device for the transfer mode ("smart" hosts) */ - IDE_HFLAG_NO_SET_MODE = BIT(9), - /* trust BIOS for programming chipset/device for DMA */ - IDE_HFLAG_TRUST_BIOS_FOR_DMA = BIT(10), - /* host is CS5510/CS5520 */ - IDE_HFLAG_CS5520 = BIT(11), - /* ATAPI DMA is unsupported */ - IDE_HFLAG_NO_ATAPI_DMA = BIT(12), - /* set if host is a "non-bootable" controller */ - IDE_HFLAG_NON_BOOTABLE = BIT(13), - /* host doesn't support DMA */ - IDE_HFLAG_NO_DMA = BIT(14), - /* check if host is PCI IDE device before allowing DMA */ - IDE_HFLAG_NO_AUTODMA = BIT(15), - /* host uses MMIO */ - IDE_HFLAG_MMIO = BIT(16), - /* no LBA48 */ - IDE_HFLAG_NO_LBA48 = BIT(17), - /* no LBA48 DMA */ - IDE_HFLAG_NO_LBA48_DMA = BIT(18), - /* data FIFO is cleared by an error */ - IDE_HFLAG_ERROR_STOPS_FIFO = BIT(19), - /* serialize ports */ - IDE_HFLAG_SERIALIZE = BIT(20), - /* host is DTC2278 */ - IDE_HFLAG_DTC2278 = BIT(21), - /* 4 devices on a single set of I/O ports */ - IDE_HFLAG_4DRIVES = BIT(22), - /* host is TRM290 */ - IDE_HFLAG_TRM290 = BIT(23), - /* use 32-bit I/O ops */ - IDE_HFLAG_IO_32BIT = BIT(24), - /* unmask IRQs */ - IDE_HFLAG_UNMASK_IRQS = BIT(25), - IDE_HFLAG_BROKEN_ALTSTATUS = BIT(26), - /* serialize ports if DMA is possible (for sl82c105) */ - IDE_HFLAG_SERIALIZE_DMA = BIT(27), - /* force host out of "simplex" mode */ - IDE_HFLAG_CLEAR_SIMPLEX = BIT(28), - /* DSC overlap is unsupported */ - IDE_HFLAG_NO_DSC = BIT(29), - /* never use 32-bit I/O ops */ - IDE_HFLAG_NO_IO_32BIT = BIT(30), - /* never unmask IRQs */ - IDE_HFLAG_NO_UNMASK_IRQS = BIT(31), -}; - -#ifdef CONFIG_BLK_DEV_OFFBOARD -# define IDE_HFLAG_OFF_BOARD 0 -#else -# define IDE_HFLAG_OFF_BOARD IDE_HFLAG_NON_BOOTABLE -#endif - -struct ide_port_info { - char *name; - - int (*init_chipset)(struct pci_dev *); - - void (*get_lock)(irq_handler_t, void *); - void (*release_lock)(void); - - void (*init_iops)(ide_hwif_t *); - void (*init_hwif)(ide_hwif_t *); - int (*init_dma)(ide_hwif_t *, - const struct ide_port_info *); - - const struct ide_tp_ops *tp_ops; - const struct ide_port_ops *port_ops; - const struct ide_dma_ops *dma_ops; - - struct ide_pci_enablebit enablebits[2]; - - hwif_chipset_t chipset; - - u16 max_sectors; /* if < than the default one */ - - u32 host_flags; - - int irq_flags; - - u8 pio_mask; - u8 swdma_mask; - u8 mwdma_mask; - u8 udma_mask; -}; - -/* - * State information carried for REQ_TYPE_ATA_PM_SUSPEND and REQ_TYPE_ATA_PM_RESUME - * requests. - */ -struct ide_pm_state { - /* PM state machine step value, currently driver specific */ - int pm_step; - /* requested PM state value (S1, S2, S3, S4, ...) */ - u32 pm_state; - void* data; /* for driver use */ -}; - - -int ide_pci_init_one(struct pci_dev *, const struct ide_port_info *, void *); -int ide_pci_init_two(struct pci_dev *, struct pci_dev *, - const struct ide_port_info *, void *); -void ide_pci_remove(struct pci_dev *); - -#ifdef CONFIG_PM -int ide_pci_suspend(struct pci_dev *, pm_message_t); -int ide_pci_resume(struct pci_dev *); -#else -#define ide_pci_suspend NULL -#define ide_pci_resume NULL -#endif - -void ide_map_sg(ide_drive_t *, struct ide_cmd *); -void ide_init_sg_cmd(struct ide_cmd *, unsigned int); - -#define BAD_DMA_DRIVE 0 -#define GOOD_DMA_DRIVE 1 - -struct drive_list_entry { - const char *id_model; - const char *id_firmware; -}; - -int ide_in_drive_list(u16 *, const struct drive_list_entry *); - -#ifdef CONFIG_BLK_DEV_IDEDMA -int ide_dma_good_drive(ide_drive_t *); -int __ide_dma_bad_drive(ide_drive_t *); - -u8 ide_find_dma_mode(ide_drive_t *, u8); - -static inline u8 ide_max_dma_mode(ide_drive_t *drive) -{ - return ide_find_dma_mode(drive, XFER_UDMA_6); -} - -void ide_dma_off_quietly(ide_drive_t *); -void ide_dma_off(ide_drive_t *); -void ide_dma_on(ide_drive_t *); -int ide_set_dma(ide_drive_t *); -void ide_check_dma_crc(ide_drive_t *); -ide_startstop_t ide_dma_intr(ide_drive_t *); - -int ide_allocate_dma_engine(ide_hwif_t *); -void ide_release_dma_engine(ide_hwif_t *); - -int ide_dma_prepare(ide_drive_t *, struct ide_cmd *); -void ide_dma_unmap_sg(ide_drive_t *, struct ide_cmd *); - -#ifdef CONFIG_BLK_DEV_IDEDMA_SFF -int config_drive_for_dma(ide_drive_t *); -int ide_build_dmatable(ide_drive_t *, struct ide_cmd *); -void ide_dma_host_set(ide_drive_t *, int); -int ide_dma_setup(ide_drive_t *, struct ide_cmd *); -extern void ide_dma_start(ide_drive_t *); -int ide_dma_end(ide_drive_t *); -int ide_dma_test_irq(ide_drive_t *); -int ide_dma_sff_timer_expiry(ide_drive_t *); -u8 ide_dma_sff_read_status(ide_hwif_t *); -extern const struct ide_dma_ops sff_dma_ops; -#else -static inline int config_drive_for_dma(ide_drive_t *drive) { return 0; } -#endif /* CONFIG_BLK_DEV_IDEDMA_SFF */ - -void ide_dma_lost_irq(ide_drive_t *); -ide_startstop_t ide_dma_timeout_retry(ide_drive_t *, int); - -#else -static inline u8 ide_find_dma_mode(ide_drive_t *drive, u8 speed) { return 0; } -static inline u8 ide_max_dma_mode(ide_drive_t *drive) { return 0; } -static inline void ide_dma_off_quietly(ide_drive_t *drive) { ; } -static inline void ide_dma_off(ide_drive_t *drive) { ; } -static inline void ide_dma_on(ide_drive_t *drive) { ; } -static inline void ide_dma_verbose(ide_drive_t *drive) { ; } -static inline int ide_set_dma(ide_drive_t *drive) { return 1; } -static inline void ide_check_dma_crc(ide_drive_t *drive) { ; } -static inline ide_startstop_t ide_dma_intr(ide_drive_t *drive) { return ide_stopped; } -static inline ide_startstop_t ide_dma_timeout_retry(ide_drive_t *drive, int error) { return ide_stopped; } -static inline void ide_release_dma_engine(ide_hwif_t *hwif) { ; } -static inline int ide_dma_prepare(ide_drive_t *drive, - struct ide_cmd *cmd) { return 1; } -static inline void ide_dma_unmap_sg(ide_drive_t *drive, - struct ide_cmd *cmd) { ; } -#endif /* CONFIG_BLK_DEV_IDEDMA */ - -#ifdef CONFIG_BLK_DEV_IDEACPI -int ide_acpi_init(void); -bool ide_port_acpi(ide_hwif_t *hwif); -extern int ide_acpi_exec_tfs(ide_drive_t *drive); -extern void ide_acpi_get_timing(ide_hwif_t *hwif); -extern void ide_acpi_push_timing(ide_hwif_t *hwif); -void ide_acpi_init_port(ide_hwif_t *); -void ide_acpi_port_init_devices(ide_hwif_t *); -extern void ide_acpi_set_state(ide_hwif_t *hwif, int on); -#else -static inline int ide_acpi_init(void) { return 0; } -static inline bool ide_port_acpi(ide_hwif_t *hwif) { return 0; } -static inline int ide_acpi_exec_tfs(ide_drive_t *drive) { return 0; } -static inline void ide_acpi_get_timing(ide_hwif_t *hwif) { ; } -static inline void ide_acpi_push_timing(ide_hwif_t *hwif) { ; } -static inline void ide_acpi_init_port(ide_hwif_t *hwif) { ; } -static inline void ide_acpi_port_init_devices(ide_hwif_t *hwif) { ; } -static inline void ide_acpi_set_state(ide_hwif_t *hwif, int on) {} -#endif - -void ide_check_nien_quirk_list(ide_drive_t *); -void ide_undecoded_slave(ide_drive_t *); - -void ide_port_apply_params(ide_hwif_t *); -int ide_sysfs_register_port(ide_hwif_t *); - -struct ide_host *ide_host_alloc(const struct ide_port_info *, struct ide_hw **, - unsigned int); -void ide_host_free(struct ide_host *); -int ide_host_register(struct ide_host *, const struct ide_port_info *, - struct ide_hw **); -int ide_host_add(const struct ide_port_info *, struct ide_hw **, unsigned int, - struct ide_host **); -void ide_host_remove(struct ide_host *); -int ide_legacy_device_add(const struct ide_port_info *, unsigned long); -void ide_port_unregister_devices(ide_hwif_t *); -void ide_port_scan(ide_hwif_t *); - -static inline void *ide_get_hwifdata (ide_hwif_t * hwif) -{ - return hwif->hwif_data; -} - -static inline void ide_set_hwifdata (ide_hwif_t * hwif, void *data) -{ - hwif->hwif_data = data; -} - -u64 ide_get_lba_addr(struct ide_cmd *, int); -u8 ide_dump_status(ide_drive_t *, const char *, u8); - -struct ide_timing { - u8 mode; - u8 setup; /* t1 */ - u16 act8b; /* t2 for 8-bit io */ - u16 rec8b; /* t2i for 8-bit io */ - u16 cyc8b; /* t0 for 8-bit io */ - u16 active; /* t2 or tD */ - u16 recover; /* t2i or tK */ - u16 cycle; /* t0 */ - u16 udma; /* t2CYCTYP/2 */ -}; - -enum { - IDE_TIMING_SETUP = BIT(0), - IDE_TIMING_ACT8B = BIT(1), - IDE_TIMING_REC8B = BIT(2), - IDE_TIMING_CYC8B = BIT(3), - IDE_TIMING_8BIT = IDE_TIMING_ACT8B | IDE_TIMING_REC8B | - IDE_TIMING_CYC8B, - IDE_TIMING_ACTIVE = BIT(4), - IDE_TIMING_RECOVER = BIT(5), - IDE_TIMING_CYCLE = BIT(6), - IDE_TIMING_UDMA = BIT(7), - IDE_TIMING_ALL = IDE_TIMING_SETUP | IDE_TIMING_8BIT | - IDE_TIMING_ACTIVE | IDE_TIMING_RECOVER | - IDE_TIMING_CYCLE | IDE_TIMING_UDMA, -}; - -struct ide_timing *ide_timing_find_mode(u8); -u16 ide_pio_cycle_time(ide_drive_t *, u8); -void ide_timing_merge(struct ide_timing *, struct ide_timing *, - struct ide_timing *, unsigned int); -int ide_timing_compute(ide_drive_t *, u8, struct ide_timing *, int, int); - -#ifdef CONFIG_IDE_XFER_MODE -int ide_scan_pio_blacklist(char *); -const char *ide_xfer_verbose(u8); -int ide_pio_need_iordy(ide_drive_t *, const u8); -int ide_set_pio_mode(ide_drive_t *, u8); -int ide_set_dma_mode(ide_drive_t *, u8); -void ide_set_pio(ide_drive_t *, u8); -int ide_set_xfer_rate(ide_drive_t *, u8); -#else -static inline void ide_set_pio(ide_drive_t *drive, u8 pio) { ; } -static inline int ide_set_xfer_rate(ide_drive_t *drive, u8 rate) { return -1; } -#endif - -static inline void ide_set_max_pio(ide_drive_t *drive) -{ - ide_set_pio(drive, 255); -} - -char *ide_media_string(ide_drive_t *); - -extern const struct attribute_group *ide_dev_groups[]; -extern struct bus_type ide_bus_type; -extern struct class *ide_port_class; - -static inline void ide_dump_identify(u8 *id) -{ - print_hex_dump(KERN_INFO, "", DUMP_PREFIX_NONE, 16, 2, id, 512, 0); -} - -static inline int hwif_to_node(ide_hwif_t *hwif) -{ - return hwif->dev ? dev_to_node(hwif->dev) : -1; -} - -static inline ide_drive_t *ide_get_pair_dev(ide_drive_t *drive) -{ - ide_drive_t *peer = drive->hwif->devices[(drive->dn ^ 1) & 1]; - - return (peer->dev_flags & IDE_DFLAG_PRESENT) ? peer : NULL; -} - -static inline void *ide_get_drivedata(ide_drive_t *drive) -{ - return drive->drive_data; -} - -static inline void ide_set_drivedata(ide_drive_t *drive, void *data) -{ - drive->drive_data = data; -} - -#define ide_port_for_each_dev(i, dev, port) \ - for ((i) = 0; ((dev) = (port)->devices[i]) || (i) < MAX_DRIVES; (i)++) - -#define ide_port_for_each_present_dev(i, dev, port) \ - for ((i) = 0; ((dev) = (port)->devices[i]) || (i) < MAX_DRIVES; (i)++) \ - if ((dev)->dev_flags & IDE_DFLAG_PRESENT) - -#define ide_host_for_each_port(i, port, host) \ - for ((i) = 0; ((port) = (host)->ports[i]) || (i) < MAX_HOST_PORTS; (i)++) - - -#endif /* _IDE_H */ -- cgit v1.2.3 From 0e8512fab9fd6d78e88931c02a43b04d15566d6b Mon Sep 17 00:00:00 2001 From: Maximilian Luz Date: Fri, 4 Jun 2021 15:47:49 +0200 Subject: platform/surface: aggregator: Allow registering notifiers without enabling events Currently, each SSAM event notifier is directly tied to one group of events. This makes sense as registering a notifier will automatically take care of enabling the corresponding event group and normally drivers only need notifications for a very limited number of events, associated with different callbacks for each group. However, there are rare cases, especially for debugging, when we want to get notifications for a whole event target category instead of just a single group of events in that category. Registering multiple notifiers, i.e. one per group, may be infeasible due to two issues: a) we might not know every event enable/disable specification as some events are auto-enabled by the EC and b) forwarding this to the same callback will lead to duplicate events as we might not know the full event specification to perform the appropriate filtering. This commit introduces observer-notifiers, which are notifiers that are not tied to a specific event group and do not attempt to manage any events. In other words, they can be registered without enabling any event group or incrementing the corresponding reference count and just act as silent observers, listening to all currently/previously enabled events based on their match-specification. Essentially, this allows us to register one single notifier for a full event target category, meaning that we can process all events of that target category in a single callback without duplication. Specifically, this will be used in the cdev debug interface to forward events to user-space via a device file from which the events can be read. Signed-off-by: Maximilian Luz Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20210604134755.535590-2-luzmaximilian@gmail.com Signed-off-by: Hans de Goede --- include/linux/surface_aggregator/controller.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/surface_aggregator/controller.h b/include/linux/surface_aggregator/controller.h index 0806796eabcb..cf4bb48a850e 100644 --- a/include/linux/surface_aggregator/controller.h +++ b/include/linux/surface_aggregator/controller.h @@ -795,6 +795,20 @@ enum ssam_event_mask { #define SSAM_EVENT_REGISTRY_REG \ SSAM_EVENT_REGISTRY(SSAM_SSH_TC_REG, 0x02, 0x01, 0x02) +/** + * enum ssam_event_notifier_flags - Flags for event notifiers. + * @SSAM_EVENT_NOTIFIER_OBSERVER: + * The corresponding notifier acts as observer. Registering a notifier + * with this flag set will not attempt to enable any event. Equally, + * unregistering will not attempt to disable any event. Note that a + * notifier with this flag may not even correspond to a certain event at + * all, only to a specific event target category. Event matching will not + * be influenced by this flag. + */ +enum ssam_event_notifier_flags { + SSAM_EVENT_NOTIFIER_OBSERVER = BIT(0), +}; + /** * struct ssam_event_notifier - Notifier block for SSAM events. * @base: The base notifier block with callback function and priority. @@ -803,6 +817,7 @@ enum ssam_event_mask { * @event.id: ID specifying the event. * @event.mask: Flags determining how events are matched to the notifier. * @event.flags: Flags used for enabling the event. + * @flags: Notifier flags (see &enum ssam_event_notifier_flags). */ struct ssam_event_notifier { struct ssam_notifier_block base; @@ -813,6 +828,8 @@ struct ssam_event_notifier { enum ssam_event_mask mask; u8 flags; } event; + + unsigned long flags; }; int ssam_notifier_register(struct ssam_controller *ctrl, -- cgit v1.2.3 From 4b38a1dcf378f5075884b54dc5afeb9d0dfe7681 Mon Sep 17 00:00:00 2001 From: Maximilian Luz Date: Fri, 4 Jun 2021 15:47:50 +0200 Subject: platform/surface: aggregator: Allow enabling of events without notifiers We can already enable and disable SAM events via one of two ways: either via a (non-observer) notifier tied to a specific event group, or a generic event enable/disable request. In some instances, however, neither method may be desirable. The first method will tie the event enable request to a specific notifier, however, when we want to receive notifications for multiple event groups of the same target category and forward this to the same notifier callback, we may receive duplicate events, i.e. one event per registered notifier. The second method will bypass the internal reference counting mechanism, meaning that a disable request will disable the event regardless of any other client driver using it, which may break the functionality of that driver. To address this problem, add new functions that allow enabling and disabling of events via the event reference counting mechanism built into the controller, without needing to register a notifier. This can then be used in combination with observer notifiers to process multiple events of the same target category without duplication in the same callback function. Signed-off-by: Maximilian Luz Link: https://lore.kernel.org/r/20210604134755.535590-3-luzmaximilian@gmail.com Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede --- include/linux/surface_aggregator/controller.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/surface_aggregator/controller.h b/include/linux/surface_aggregator/controller.h index cf4bb48a850e..7965bdc669c5 100644 --- a/include/linux/surface_aggregator/controller.h +++ b/include/linux/surface_aggregator/controller.h @@ -838,4 +838,12 @@ int ssam_notifier_register(struct ssam_controller *ctrl, int ssam_notifier_unregister(struct ssam_controller *ctrl, struct ssam_event_notifier *n); +int ssam_controller_event_enable(struct ssam_controller *ctrl, + struct ssam_event_registry reg, + struct ssam_event_id id, u8 flags); + +int ssam_controller_event_disable(struct ssam_controller *ctrl, + struct ssam_event_registry reg, + struct ssam_event_id id, u8 flags); + #endif /* _LINUX_SURFACE_AGGREGATOR_CONTROLLER_H */ -- cgit v1.2.3 From b2763358feb28590f6b52a4c95c94a645dadfb26 Mon Sep 17 00:00:00 2001 From: Maximilian Luz Date: Fri, 4 Jun 2021 15:47:51 +0200 Subject: platform/surface: aggregator: Update copyright It's 2021, update the copyright accordingly. Signed-off-by: Maximilian Luz Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20210604134755.535590-4-luzmaximilian@gmail.com Signed-off-by: Hans de Goede --- include/linux/surface_aggregator/controller.h | 2 +- include/linux/surface_aggregator/device.h | 2 +- include/linux/surface_aggregator/serial_hub.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/surface_aggregator/controller.h b/include/linux/surface_aggregator/controller.h index 7965bdc669c5..068e1982ad37 100644 --- a/include/linux/surface_aggregator/controller.h +++ b/include/linux/surface_aggregator/controller.h @@ -6,7 +6,7 @@ * managing access and communication to and from the SSAM EC, as well as main * communication structures and definitions. * - * Copyright (C) 2019-2020 Maximilian Luz + * Copyright (C) 2019-2021 Maximilian Luz */ #ifndef _LINUX_SURFACE_AGGREGATOR_CONTROLLER_H diff --git a/include/linux/surface_aggregator/device.h b/include/linux/surface_aggregator/device.h index 6ff9c58b3e17..f636c5310321 100644 --- a/include/linux/surface_aggregator/device.h +++ b/include/linux/surface_aggregator/device.h @@ -7,7 +7,7 @@ * Provides support for non-platform/non-ACPI SSAM clients via dedicated * subsystem. * - * Copyright (C) 2019-2020 Maximilian Luz + * Copyright (C) 2019-2021 Maximilian Luz */ #ifndef _LINUX_SURFACE_AGGREGATOR_DEVICE_H diff --git a/include/linux/surface_aggregator/serial_hub.h b/include/linux/surface_aggregator/serial_hub.h index 64276fbfa1d5..c3de43edcffa 100644 --- a/include/linux/surface_aggregator/serial_hub.h +++ b/include/linux/surface_aggregator/serial_hub.h @@ -6,7 +6,7 @@ * Surface System Aggregator Module (SSAM). Provides the interface for basic * packet- and request-based communication with the SSAM EC via SSH. * - * Copyright (C) 2019-2020 Maximilian Luz + * Copyright (C) 2019-2021 Maximilian Luz */ #ifndef _LINUX_SURFACE_AGGREGATOR_SERIAL_HUB_H -- cgit v1.2.3 From 8fe55ef23387ce3c7488375b1fd539420d7654bb Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 13 May 2021 15:18:27 +0100 Subject: PCI: Dynamically map ECAM regions Attempting to boot 32-bit ARM kernels under QEMU's 3.x virt models fails when we have more than 512M of RAM in the model as we run out of vmalloc space for the PCI ECAM regions. This failure will be silent when running libvirt, as the console in that situation is a PCI device. In this configuration, the kernel maps the whole ECAM, which QEMU sets up for 256 buses, even when maybe only seven buses are in use. Each bus uses 1M of ECAM space, and ioremap() adds an additional guard page between allocations. The kernel vmap allocator will align these regions to 512K, resulting in each mapping eating 1.5M of vmalloc space. This means we need 384M of vmalloc space just to map all of these, which is very wasteful of resources. Fix this by only mapping the ECAM for buses we are going to be using. In my setups, this is around seven buses in most guests, which is 10.5M of vmalloc space - way smaller than the 384M that would otherwise be required. This also means that the kernel can boot without forcing extra RAM into highmem with the vmalloc= argument, or decreasing the virtual RAM available to the guest. Suggested-by: Arnd Bergmann Link: https://lore.kernel.org/r/E1lhCAV-0002yb-50@rmk-PC.armlinux.org.uk Signed-off-by: Russell King Signed-off-by: Bjorn Helgaas Reviewed-by: Arnd Bergmann --- include/linux/pci-ecam.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci-ecam.h b/include/linux/pci-ecam.h index fbdadd4d8377..adea5a4771cf 100644 --- a/include/linux/pci-ecam.h +++ b/include/linux/pci-ecam.h @@ -55,6 +55,7 @@ struct pci_ecam_ops { struct pci_config_window { struct resource res; struct resource busr; + unsigned int bus_shift; void *priv; const struct pci_ecam_ops *ops; union { -- cgit v1.2.3 From 1d1f6cc5818c750ac69473e4951e7165913fbf16 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 15 Jun 2021 10:19:13 -0700 Subject: pstore/blk: Include zone in pstore_device_info Information was redundant between struct pstore_zone_info and struct pstore_device_info. Use struct pstore_zone_info, with member name "zone". Additionally untangle the logic for the "best effort" block device instance. Signed-off-by: Kees Cook Fixed-by: Pu Lehui Link: https://lore.kernel.org/lkml/20210617005424.182305-1-pulehui@huawei.com --- include/linux/pstore_blk.h | 27 +++------------------------ 1 file changed, 3 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pstore_blk.h b/include/linux/pstore_blk.h index 99564f93d774..924ca07aafbd 100644 --- a/include/linux/pstore_blk.h +++ b/include/linux/pstore_blk.h @@ -10,36 +10,15 @@ /** * struct pstore_device_info - back-end pstore/blk driver structure. * - * @total_size: The total size in bytes pstore/blk can use. It must be greater - * than 4096 and be multiple of 4096. * @flags: Refer to macro starting with PSTORE_FLAGS defined in * linux/pstore.h. It means what front-ends this device support. * Zero means all backends for compatible. - * @read: The general read operation. Both of the function parameters - * @size and @offset are relative value to bock device (not the - * whole disk). - * On success, the number of bytes should be returned, others - * means error. - * @write: The same as @read, but the following error number: - * -EBUSY means try to write again later. - * -ENOMSG means to try next zone. - * @erase: The general erase operation for device with special removing - * job. Both of the function parameters @size and @offset are - * relative value to storage. - * Return 0 on success and others on failure. - * @panic_write:The write operation only used for panic case. It's optional - * if you do not care panic log. The parameters are relative - * value to storage. - * On success, the number of bytes should be returned, others - * excluding -ENOMSG mean error. -ENOMSG means to try next zone. + * @zone: The struct pstore_zone_info details. + * */ struct pstore_device_info { - unsigned long total_size; unsigned int flags; - pstore_zone_read_op read; - pstore_zone_write_op write; - pstore_zone_erase_op erase; - pstore_zone_write_op panic_write; + struct pstore_zone_info zone; }; int register_pstore_device(struct pstore_device_info *dev); -- cgit v1.2.3 From 10ff9976d06fc6a11f512755d500ab2860cbe650 Mon Sep 17 00:00:00 2001 From: Liu Shixin Date: Fri, 11 Jun 2021 10:01:00 +0800 Subject: crypto: api - remove CRYPTOA_U32 and related functions According to the advice of Eric and Herbert, type CRYPTOA_U32 has been unused for over a decade, so remove the code related to CRYPTOA_U32. After removing CRYPTOA_U32, the type of the variable attrs can be changed from union to struct. Signed-off-by: Liu Shixin Reviewed-by: Eric Biggers Signed-off-by: Herbert Xu --- include/linux/crypto.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index da5e0d74bb2f..3b9263d6122f 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -647,7 +647,6 @@ enum { CRYPTOA_UNSPEC, CRYPTOA_ALG, CRYPTOA_TYPE, - CRYPTOA_U32, __CRYPTOA_MAX, }; @@ -665,10 +664,6 @@ struct crypto_attr_type { u32 mask; }; -struct crypto_attr_u32 { - u32 num; -}; - /* * Transform user interface. */ -- cgit v1.2.3 From 7a2c4cc537fa9f05fe90812e7d789b9faf7eb869 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Tue, 8 Jun 2021 13:09:34 +0300 Subject: devm-helpers: Add resource managed version of work init A few drivers which need a work-queue must cancel work at driver detach. Some of those implement remove() solely for this purpose. Help drivers to avoid unnecessary remove and error-branch implementation by adding managed verision of work initialization. This will also help drivers to avoid mixing manual and devm based unwinding when other resources are handled by devm. Signed-off-by: Matti Vaittinen Reviewed-by: Krzysztof Kozlowski Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/94ff4175e7f2ff134ed2fa7d6e7641005cc9784b.1623146580.git.matti.vaittinen@fi.rohmeurope.com Signed-off-by: Hans de Goede --- include/linux/devm-helpers.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/devm-helpers.h b/include/linux/devm-helpers.h index f40f77717a24..74891802200d 100644 --- a/include/linux/devm-helpers.h +++ b/include/linux/devm-helpers.h @@ -51,4 +51,29 @@ static inline int devm_delayed_work_autocancel(struct device *dev, return devm_add_action(dev, devm_delayed_work_drop, w); } +static inline void devm_work_drop(void *res) +{ + cancel_work_sync(res); +} + +/** + * devm_work_autocancel - Resource-managed work allocation + * @dev: Device which lifetime work is bound to + * @w: Work to be added (and automatically cancelled) + * @worker: Worker function + * + * Initialize work which is automatically cancelled when driver is detached. + * A few drivers need to queue work which must be cancelled before driver + * is detached to avoid accessing removed resources. + * devm_work_autocancel() can be used to omit the explicit + * cancelleation when driver is detached. + */ +static inline int devm_work_autocancel(struct device *dev, + struct work_struct *w, + work_func_t worker) +{ + INIT_WORK(w, worker); + return devm_add_action(dev, devm_work_drop, w); +} + #endif -- cgit v1.2.3 From 86c908d90fb17273f5f6d15539ad3d7bf134d892 Mon Sep 17 00:00:00 2001 From: Erik Rosen Date: Fri, 7 May 2021 21:40:21 +0200 Subject: hwmon: (pmbus) Add new flag PMBUS_READ_STATUS_AFTER_FAILED_CHECK Some PMBus chips end up in an undefined state when trying to read an unsupported register. For such chips, it is necessary to reset the chip pmbus controller to a known state after a failed register check. This can be done by reading a known register. By setting this flag the driver will try to read the STATUS register after each failed register check. This read may fail, but it will put the chip into a known state. Signed-off-by: Erik Rosen Link: https://lore.kernel.org/r/20210507194023.61138-2-erik.rosen@metormote.com Signed-off-by: Guenter Roeck --- include/linux/pmbus.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pmbus.h b/include/linux/pmbus.h index 12cbbf305969..edd7c84fef65 100644 --- a/include/linux/pmbus.h +++ b/include/linux/pmbus.h @@ -43,6 +43,19 @@ */ #define PMBUS_NO_CAPABILITY BIT(2) +/* + * PMBUS_READ_STATUS_AFTER_FAILED_CHECK + * + * Some PMBus chips end up in an undefined state when trying to read an + * unsupported register. For such chips, it is necessary to reset the + * chip pmbus controller to a known state after a failed register check. + * This can be done by reading a known register. By setting this flag the + * driver will try to read the STATUS register after each failed + * register check. This read may fail, but it will put the chip in a + * known state. + */ +#define PMBUS_READ_STATUS_AFTER_FAILED_CHECK BIT(3) + struct pmbus_platform_data { u32 flags; /* Device specific flags */ -- cgit v1.2.3 From dbc0860f7a3d43604c380822a456d26ef6f70a06 Mon Sep 17 00:00:00 2001 From: Erik Rosen Date: Wed, 9 Jun 2021 11:32:05 +0200 Subject: hwmon: (pmbus) Add new pmbus flag NO_WRITE_PROTECT Some PMBus chips respond with invalid data when reading the WRITE_PROTECT register. For such chips, this flag should be set so that the PMBus core driver doesn't use the WRITE_PROTECT command to determine its behavior. Signed-off-by: Erik Rosen Signed-off-by: Guenter Roeck --- include/linux/pmbus.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pmbus.h b/include/linux/pmbus.h index edd7c84fef65..12c515a27d3a 100644 --- a/include/linux/pmbus.h +++ b/include/linux/pmbus.h @@ -56,6 +56,15 @@ */ #define PMBUS_READ_STATUS_AFTER_FAILED_CHECK BIT(3) +/* + * PMBUS_NO_WRITE_PROTECT + * + * Some PMBus chips respond with invalid data when reading the WRITE_PROTECT + * register. For such chips, this flag should be set so that the PMBus core + * driver doesn't use the WRITE_PROTECT command to determine its behavior. + */ +#define PMBUS_NO_WRITE_PROTECT BIT(4) + struct pmbus_platform_data { u32 flags; /* Device specific flags */ -- cgit v1.2.3 From e8e00c83a268d5b7d2f5bd490c2269c1ede76a07 Mon Sep 17 00:00:00 2001 From: Erik Rosen Date: Wed, 9 Jun 2021 11:32:06 +0200 Subject: hwmon: (pmbus) Add support for reading direct mode coefficients Add support for reading and decoding direct format coefficients to the PMBus core driver. If the new flag PMBUS_USE_COEFFICIENTS_CMD is set, the driver will use the COEFFICIENTS register together with the information in the pmbus_sensor_attr structs to initialize relevant coefficients for the direct mode format. Signed-off-by: Erik Rosen [groeck: Initialize ret with -EINVAL in pmbus_init_coefficients()] Signed-off-by: Guenter Roeck --- include/linux/pmbus.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pmbus.h b/include/linux/pmbus.h index 12c515a27d3a..fa9f08164c36 100644 --- a/include/linux/pmbus.h +++ b/include/linux/pmbus.h @@ -65,6 +65,14 @@ */ #define PMBUS_NO_WRITE_PROTECT BIT(4) +/* + * PMBUS_USE_COEFFICIENTS_CMD + * + * When this flag is set the PMBus core driver will use the COEFFICIENTS + * register to initialize the coefficients for the direct mode format. + */ +#define PMBUS_USE_COEFFICIENTS_CMD BIT(5) + struct pmbus_platform_data { u32 flags; /* Device specific flags */ -- cgit v1.2.3 From 8f1b971b4750e83e8fbd2f91a9efd4a38ad0ae51 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Mon, 14 Jun 2021 20:12:38 +0100 Subject: sched/cpufreq: Consider reduced CPU capacity in energy calculation Energy Aware Scheduling (EAS) needs to predict the decisions made by SchedUtil. The map_util_freq() exists to do that. There are corner cases where the max allowed frequency might be reduced (due to thermal). SchedUtil as a CPUFreq governor, is aware of that but EAS is not. This patch aims to address it. SchedUtil stores the maximum allowed frequency in 'sugov_policy::next_freq' field. EAS has to predict that value, which is the real used frequency. That value is made after a call to cpufreq_driver_resolve_freq() which clamps to the CPUFreq policy limits. In the existing code EAS is not able to predict that real frequency. This leads to energy estimation errors. To avoid wrong energy estimation in EAS (due to frequency miss prediction) make sure that the step which calculates Performance Domain frequency, is also aware of the allowed CPU capacity. Furthermore, modify map_util_freq() to not extend the frequency value. Instead, use map_util_perf() to extend the util value in both places: SchedUtil and EAS, but for EAS clamp it to max allowed CPU capacity. In the end, we achieve the same desirable behavior for both subsystems and alignment in regards to the real CPU frequency. Signed-off-by: Lukasz Luba Signed-off-by: Peter Zijlstra (Intel) Acked-by: Rafael J. Wysocki (For the schedutil part) Link: https://lore.kernel.org/r/20210614191238.23224-1-lukasz.luba@arm.com --- include/linux/energy_model.h | 16 +++++++++++++--- include/linux/sched/cpufreq.h | 2 +- 2 files changed, 14 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 757fc60658fa..3f221dbf5f95 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -91,6 +91,8 @@ void em_dev_unregister_perf_domain(struct device *dev); * @pd : performance domain for which energy has to be estimated * @max_util : highest utilization among CPUs of the domain * @sum_util : sum of the utilization of all CPUs in the domain + * @allowed_cpu_cap : maximum allowed CPU capacity for the @pd, which + might reflect reduced frequency (due to thermal) * * This function must be used only for CPU devices. There is no validation, * i.e. if the EM is a CPU type and has cpumask allocated. It is called from @@ -100,7 +102,8 @@ void em_dev_unregister_perf_domain(struct device *dev); * a capacity state satisfying the max utilization of the domain. */ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, - unsigned long max_util, unsigned long sum_util) + unsigned long max_util, unsigned long sum_util, + unsigned long allowed_cpu_cap) { unsigned long freq, scale_cpu; struct em_perf_state *ps; @@ -112,11 +115,17 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, /* * In order to predict the performance state, map the utilization of * the most utilized CPU of the performance domain to a requested - * frequency, like schedutil. + * frequency, like schedutil. Take also into account that the real + * frequency might be set lower (due to thermal capping). Thus, clamp + * max utilization to the allowed CPU capacity before calculating + * effective frequency. */ cpu = cpumask_first(to_cpumask(pd->cpus)); scale_cpu = arch_scale_cpu_capacity(cpu); ps = &pd->table[pd->nr_perf_states - 1]; + + max_util = map_util_perf(max_util); + max_util = min(max_util, allowed_cpu_cap); freq = map_util_freq(max_util, ps->frequency, scale_cpu); /* @@ -209,7 +218,8 @@ static inline struct em_perf_domain *em_pd_get(struct device *dev) return NULL; } static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, - unsigned long max_util, unsigned long sum_util) + unsigned long max_util, unsigned long sum_util, + unsigned long allowed_cpu_cap) { return 0; } diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h index 6205578ab6ee..bdd31ab93bc5 100644 --- a/include/linux/sched/cpufreq.h +++ b/include/linux/sched/cpufreq.h @@ -26,7 +26,7 @@ bool cpufreq_this_cpu_can_update(struct cpufreq_policy *policy); static inline unsigned long map_util_freq(unsigned long util, unsigned long freq, unsigned long cap) { - return (freq + (freq >> 2)) * util / cap; + return freq * util / cap; } static inline unsigned long map_util_perf(unsigned long util) -- cgit v1.2.3 From 09aa9aabdcc4966270b031816a16d4641fb45dfa Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sun, 25 Aug 2019 21:57:25 +0200 Subject: soc: ixp4xx: move cpu detection to linux/soc/ixp4xx/cpu.h Generic drivers are unable to use the feature macros from mach/cpu.h or the feature bits from mach/hardware.h, so move these into a global header file along with some dummy helpers that list these features as disabled elsewhere. Cc: David S. Miller Cc: Jakub Kicinski Cc: netdev@vger.kernel.org Cc: Zoltan HERPAI Cc: Raylynn Knight Signed-off-by: Arnd Bergmann Signed-off-by: Linus Walleij --- include/linux/soc/ixp4xx/cpu.h | 106 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 106 insertions(+) create mode 100644 include/linux/soc/ixp4xx/cpu.h (limited to 'include/linux') diff --git a/include/linux/soc/ixp4xx/cpu.h b/include/linux/soc/ixp4xx/cpu.h new file mode 100644 index 000000000000..88bd8de0e803 --- /dev/null +++ b/include/linux/soc/ixp4xx/cpu.h @@ -0,0 +1,106 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * IXP4XX cpu type detection + * + * Copyright (C) 2007 MontaVista Software, Inc. + */ + +#ifndef __SOC_IXP4XX_CPU_H__ +#define __SOC_IXP4XX_CPU_H__ + +#include +#ifdef CONFIG_ARM +#include +#endif + +/* Processor id value in CP15 Register 0 */ +#define IXP42X_PROCESSOR_ID_VALUE 0x690541c0 /* including unused 0x690541Ex */ +#define IXP42X_PROCESSOR_ID_MASK 0xffffffc0 + +#define IXP43X_PROCESSOR_ID_VALUE 0x69054040 +#define IXP43X_PROCESSOR_ID_MASK 0xfffffff0 + +#define IXP46X_PROCESSOR_ID_VALUE 0x69054200 /* including IXP455 */ +#define IXP46X_PROCESSOR_ID_MASK 0xfffffff0 + +/* "fuse" bits of IXP_EXP_CFG2 */ +/* All IXP4xx CPUs */ +#define IXP4XX_FEATURE_RCOMP (1 << 0) +#define IXP4XX_FEATURE_USB_DEVICE (1 << 1) +#define IXP4XX_FEATURE_HASH (1 << 2) +#define IXP4XX_FEATURE_AES (1 << 3) +#define IXP4XX_FEATURE_DES (1 << 4) +#define IXP4XX_FEATURE_HDLC (1 << 5) +#define IXP4XX_FEATURE_AAL (1 << 6) +#define IXP4XX_FEATURE_HSS (1 << 7) +#define IXP4XX_FEATURE_UTOPIA (1 << 8) +#define IXP4XX_FEATURE_NPEB_ETH0 (1 << 9) +#define IXP4XX_FEATURE_NPEC_ETH (1 << 10) +#define IXP4XX_FEATURE_RESET_NPEA (1 << 11) +#define IXP4XX_FEATURE_RESET_NPEB (1 << 12) +#define IXP4XX_FEATURE_RESET_NPEC (1 << 13) +#define IXP4XX_FEATURE_PCI (1 << 14) +#define IXP4XX_FEATURE_UTOPIA_PHY_LIMIT (3 << 16) +#define IXP4XX_FEATURE_XSCALE_MAX_FREQ (3 << 22) +#define IXP42X_FEATURE_MASK (IXP4XX_FEATURE_RCOMP | \ + IXP4XX_FEATURE_USB_DEVICE | \ + IXP4XX_FEATURE_HASH | \ + IXP4XX_FEATURE_AES | \ + IXP4XX_FEATURE_DES | \ + IXP4XX_FEATURE_HDLC | \ + IXP4XX_FEATURE_AAL | \ + IXP4XX_FEATURE_HSS | \ + IXP4XX_FEATURE_UTOPIA | \ + IXP4XX_FEATURE_NPEB_ETH0 | \ + IXP4XX_FEATURE_NPEC_ETH | \ + IXP4XX_FEATURE_RESET_NPEA | \ + IXP4XX_FEATURE_RESET_NPEB | \ + IXP4XX_FEATURE_RESET_NPEC | \ + IXP4XX_FEATURE_PCI | \ + IXP4XX_FEATURE_UTOPIA_PHY_LIMIT | \ + IXP4XX_FEATURE_XSCALE_MAX_FREQ) + + +/* IXP43x/46x CPUs */ +#define IXP4XX_FEATURE_ECC_TIMESYNC (1 << 15) +#define IXP4XX_FEATURE_USB_HOST (1 << 18) +#define IXP4XX_FEATURE_NPEA_ETH (1 << 19) +#define IXP43X_FEATURE_MASK (IXP42X_FEATURE_MASK | \ + IXP4XX_FEATURE_ECC_TIMESYNC | \ + IXP4XX_FEATURE_USB_HOST | \ + IXP4XX_FEATURE_NPEA_ETH) + +/* IXP46x CPU (including IXP455) only */ +#define IXP4XX_FEATURE_NPEB_ETH_1_TO_3 (1 << 20) +#define IXP4XX_FEATURE_RSA (1 << 21) +#define IXP46X_FEATURE_MASK (IXP43X_FEATURE_MASK | \ + IXP4XX_FEATURE_NPEB_ETH_1_TO_3 | \ + IXP4XX_FEATURE_RSA) + +#ifdef CONFIG_ARCH_IXP4XX +#define cpu_is_ixp42x_rev_a0() ((read_cpuid_id() & (IXP42X_PROCESSOR_ID_MASK | 0xF)) == \ + IXP42X_PROCESSOR_ID_VALUE) +#define cpu_is_ixp42x() ((read_cpuid_id() & IXP42X_PROCESSOR_ID_MASK) == \ + IXP42X_PROCESSOR_ID_VALUE) +#define cpu_is_ixp43x() ((read_cpuid_id() & IXP43X_PROCESSOR_ID_MASK) == \ + IXP43X_PROCESSOR_ID_VALUE) +#define cpu_is_ixp46x() ((read_cpuid_id() & IXP46X_PROCESSOR_ID_MASK) == \ + IXP46X_PROCESSOR_ID_VALUE) + +u32 ixp4xx_read_feature_bits(void); +void ixp4xx_write_feature_bits(u32 value); +#else +#define cpu_is_ixp42x_rev_a0() 0 +#define cpu_is_ixp42x() 0 +#define cpu_is_ixp43x() 0 +#define cpu_is_ixp46x() 0 +static inline u32 ixp4xx_read_feature_bits(void) +{ + return 0; +} +static inline void ixp4xx_write_feature_bits(u32 value) +{ +} +#endif + +#endif /* _ASM_ARCH_CPU_H */ -- cgit v1.2.3 From 55712627bffd666c9f25eb23c15c55ec85e5a73f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sun, 25 Aug 2019 22:14:01 +0200 Subject: pata: ixp4xx: split platform data to its own header Portable drivers cannot use mach/platform.h, so move the structure into its own header. With this, compile testing can be enabled. Signed-off-by: Arnd Bergmann Signed-off-by: Linus Walleij --- include/linux/platform_data/pata_ixp4xx_cf.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) create mode 100644 include/linux/platform_data/pata_ixp4xx_cf.h (limited to 'include/linux') diff --git a/include/linux/platform_data/pata_ixp4xx_cf.h b/include/linux/platform_data/pata_ixp4xx_cf.h new file mode 100644 index 000000000000..601ba97fef57 --- /dev/null +++ b/include/linux/platform_data/pata_ixp4xx_cf.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PLATFORM_DATA_PATA_IXP4XX_H +#define __PLATFORM_DATA_PATA_IXP4XX_H + +#include + +/* + * This structure provide a means for the board setup code + * to give information to th pata_ixp4xx driver. It is + * passed as platform_data. + */ +struct ixp4xx_pata_data { + volatile u32 *cs0_cfg; + volatile u32 *cs1_cfg; + unsigned long cs0_bits; + unsigned long cs1_bits; + void __iomem *cs0; + void __iomem *cs1; +}; + +#endif -- cgit v1.2.3 From c28a61471c5898e832c6e8634b2659249761b833 Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Wed, 9 Jun 2021 18:32:48 -0700 Subject: block: export blk_next_bio() The block layer provides emulation of zone management operations targeting all zones of a zoned block device only for the zone reset operation (REQ_OP_ZONE_RESET). In order to correctly implement exporting of zoned block devices with NVMeOF, emulating zone management operations targeting all zones of a device is also necessary for the open, close and finish zone operations (REQ_OP_ZONE_OPEN, REQ_OP_ZONE_CLOSE and REQ_OP_ZONE_FINISH). Instead of duplicating the code, export the existing helper from block layer so we can use a bio chaining pattern that is present in the block layer for REQ_OP_ZONE RESET all emulation in the NVMeOF zoned block device backend. Reviewed-by: Damien Le Moal Signed-off-by: Chaitanya Kulkarni Signed-off-by: Christoph Hellwig --- include/linux/bio.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index a0b4cfdf62a4..b2491ead22a0 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -822,4 +822,6 @@ static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb) bio->bi_opf |= REQ_NOWAIT; } +struct bio *blk_next_bio(struct bio *bio, unsigned int nr_pages, gfp_t gfp); + #endif /* __LINUX_BIO_H */ -- cgit v1.2.3 From ab5d0b38c0475d6ff59f1a6ccf7c668b9ec2e0a4 Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Wed, 9 Jun 2021 18:32:51 -0700 Subject: nvmet: add Command Set Identifier support NVMe TP 4056 allows controllers to support different command sets. NVMeoF target currently only supports namespaces that contain traditional logical blocks that may be randomly read and written. In some applications there is a value in exposing namespaces that contain logical blocks that have special access rules (e.g. sequentially write required namespace such as Zoned Namespace (ZNS)). In order to support the Zoned Block Devices (ZBD) backend, controllers need to have support for ZNS Command Set Identifier (CSI). In this preparation patch, we adjust the code such that it can now support the default command set identifier. We update the namespace data structure to store the CSI value which defaults to NVME_CSI_NVM that represents traditional logical blocks namespace type. The CSI support is required to implement the ZBD backend for NVMeOF with host side NVMe ZNS interface, since ZNS commands belong to the different command set than the default one. Signed-off-by: Chaitanya Kulkarni Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index edcbd60b88b9..c7ba83144d52 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -1504,6 +1504,7 @@ enum { NVME_SC_NS_WRITE_PROTECTED = 0x20, NVME_SC_CMD_INTERRUPTED = 0x21, NVME_SC_TRANSIENT_TR_ERR = 0x22, + NVME_SC_INVALID_IO_CMD_SET = 0x2C, NVME_SC_LBA_RANGE = 0x80, NVME_SC_CAP_EXCEEDED = 0x81, -- cgit v1.2.3 From aaf2e048af2704da5869f27b508b288f36d5c7b7 Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Wed, 9 Jun 2021 18:32:52 -0700 Subject: nvmet: add ZBD over ZNS backend support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit NVMe TP 4053 – Zoned Namespaces (ZNS) allows host software to communicate with a non-volatile memory subsystem using zones for NVMe protocol-based controllers. NVMeOF already support the ZNS NVMe Protocol compliant devices on the target in the passthru mode. There are generic zoned block devices like Shingled Magnetic Recording (SMR) HDDs that are not based on the NVMe protocol. This patch adds ZNS backend support for non-ZNS zoned block devices as NVMeOF targets. This support includes implementing the new command set NVME_CSI_ZNS, adding different command handlers for ZNS command set such as NVMe Identify Controller, NVMe Identify Namespace, NVMe Zone Append, NVMe Zone Management Send and NVMe Zone Management Receive. With the new command set identifier, we also update the target command effects logs to reflect the ZNS compliant commands. Signed-off-by: Chaitanya Kulkarni Reviewed-by: Damien Le Moal Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index c7ba83144d52..cb1197f1cfed 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -944,6 +944,13 @@ struct nvme_zone_mgmt_recv_cmd { enum { NVME_ZRA_ZONE_REPORT = 0, NVME_ZRASF_ZONE_REPORT_ALL = 0, + NVME_ZRASF_ZONE_STATE_EMPTY = 0x01, + NVME_ZRASF_ZONE_STATE_IMP_OPEN = 0x02, + NVME_ZRASF_ZONE_STATE_EXP_OPEN = 0x03, + NVME_ZRASF_ZONE_STATE_CLOSED = 0x04, + NVME_ZRASF_ZONE_STATE_READONLY = 0x05, + NVME_ZRASF_ZONE_STATE_FULL = 0x06, + NVME_ZRASF_ZONE_STATE_OFFLINE = 0x07, NVME_REPORT_ZONE_PARTIAL = 1, }; -- cgit v1.2.3 From 8cf486e131b351db4f224078bef8e1efedcf0340 Mon Sep 17 00:00:00 2001 From: Wesley Sheng Date: Wed, 16 Jun 2021 13:25:08 +0800 Subject: nvme.h: add missing nvme_lba_range_type endianness annotations Signed-off-by: Wesley Sheng Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index cb1197f1cfed..b7c4c4130b65 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -636,8 +636,8 @@ struct nvme_lba_range_type { __u8 type; __u8 attributes; __u8 rsvd2[14]; - __u64 slba; - __u64 nlb; + __le64 slba; + __le64 nlb; __u8 guid[16]; __u8 rsvd48[16]; }; -- cgit v1.2.3 From aff0dbd03d3b750e2331f7cb93e01fe25ed27086 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 16 Jun 2021 16:22:50 +0200 Subject: ACPI: scan: Make acpi_walk_dep_device_list() Because acpi_walk_dep_device_list() is only called by the code in the file in which it is defined, make it static, drop the export of it and drop its header from acpi.h. Signed-off-by: Rafael J. Wysocki Reviewed-by: Hans de Goede --- include/linux/acpi.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 170b9bebdb2b..0a6d2845fcaf 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -666,9 +666,6 @@ extern bool acpi_driver_match_device(struct device *dev, const struct device_driver *drv); int acpi_device_uevent_modalias(struct device *, struct kobj_uevent_env *); int acpi_device_modalias(struct device *, char *, int); -int acpi_walk_dep_device_list(acpi_handle handle, - int (*callback)(struct acpi_dep_data *, void *), - void *data); struct platform_device *acpi_create_platform_device(struct acpi_device *, struct property_entry *); -- cgit v1.2.3 From b10a038e84d188e15819058b2978b2daa9853aeb Mon Sep 17 00:00:00 2001 From: Ben Gardon Date: Tue, 18 May 2021 10:34:11 -0700 Subject: KVM: mmu: Add slots_arch_lock for memslot arch fields Add a new lock to protect the arch-specific fields of memslots if they need to be modified in a kvm->srcu read critical section. A future commit will use this lock to lazily allocate memslot rmaps for x86. Signed-off-by: Ben Gardon Message-Id: <20210518173414.450044-5-bgardon@google.com> [Add Documentation/ hunk. - Paolo] Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 8583ed3ff344..11b9b11a5e9b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -523,6 +523,15 @@ struct kvm { #endif /* KVM_HAVE_MMU_RWLOCK */ struct mutex slots_lock; + + /* + * Protects the arch-specific fields of struct kvm_memory_slots in + * use by the VM. To be used under the slots_lock (above) or in a + * kvm->srcu critical section where acquiring the slots_lock would + * lead to deadlock with the synchronize_srcu in + * install_new_memslots. + */ + struct mutex slots_arch_lock; struct mm_struct *mm; /* userspace tied to this vm */ struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM]; struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; -- cgit v1.2.3 From 605a140a49099effc069f0fd509db34d91f48496 Mon Sep 17 00:00:00 2001 From: Ilias Stamatis Date: Wed, 26 May 2021 19:44:08 +0100 Subject: math64.h: Add mul_s64_u64_shr() This function is needed for KVM's nested virtualization. The nested TSC scaling implementation requires multiplying the signed TSC offset with the unsigned TSC multiplier. Signed-off-by: Ilias Stamatis Reviewed-by: Maxim Levitsky Message-Id: <20210526184418.28881-2-ilstam@amazon.com> Signed-off-by: Paolo Bonzini --- include/linux/math64.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/math64.h b/include/linux/math64.h index 66deb1fdc2ef..2928f03d6d46 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -3,6 +3,7 @@ #define _LINUX_MATH64_H #include +#include #include #include @@ -234,6 +235,24 @@ static inline u64 mul_u64_u64_shr(u64 a, u64 b, unsigned int shift) #endif +#ifndef mul_s64_u64_shr +static inline u64 mul_s64_u64_shr(s64 a, u64 b, unsigned int shift) +{ + u64 ret; + + /* + * Extract the sign before the multiplication and put it back + * afterwards if needed. + */ + ret = mul_u64_u64_shr(abs(a), b, shift); + + if (a < 0) + ret = -((s64) ret); + + return ret; +} +#endif /* mul_s64_u64_shr */ + #ifndef mul_u64_u32_div static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 divisor) { -- cgit v1.2.3 From 2fdef3a2ae01dfd928c4b42c5a3b76546170a74c Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Sun, 6 Jun 2021 11:10:44 +0900 Subject: kvm: add PM-notifier Add KVM PM-notifier so that architectures can have arch-specific VM suspend/resume routines. Such architectures need to select CONFIG_HAVE_KVM_PM_NOTIFIER and implement kvm_arch_pm_notifier(). Signed-off-by: Sergey Senozhatsky Acked-by: Marc Zyngier Message-Id: <20210606021045.14159-1-senozhatsky@chromium.org> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 11b9b11a5e9b..37cbb56ccd09 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -28,6 +28,7 @@ #include #include #include +#include #include #include @@ -594,6 +595,10 @@ struct kvm { pid_t userspace_pid; unsigned int max_halt_poll_ns; u32 dirty_ring_size; + +#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER + struct notifier_block pm_notifier; +#endif }; #define kvm_err(fmt, ...) \ @@ -1007,6 +1012,10 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu); +#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER +int kvm_arch_pm_notifier(struct kvm *kvm, unsigned long state); +#endif + #ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu, struct dentry *debugfs_dentry); #endif -- cgit v1.2.3 From 2d8ea148e553e1dd4e80a87741abdfb229e2b323 Mon Sep 17 00:00:00 2001 From: Jian Shen Date: Thu, 17 Jun 2021 11:37:11 +0800 Subject: net: fix mistake path for netdev_features_strings Th_strings arrays netdev_features_strings, tunable_strings, and phy_tunable_strings has been moved to file net/ethtool/common.c. So fixes the comment. Signed-off-by: Jian Shen Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 3de38d6a0aea..2c6b9e416225 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -93,7 +93,7 @@ enum { /* * Add your fresh new feature above and remember to update - * netdev_features_strings[] in net/core/ethtool.c and maybe + * netdev_features_strings[] in net/ethtool/common.c and maybe * some feature mask #defines below. Please also describe it * in Documentation/networking/netdev-features.rst. */ -- cgit v1.2.3 From 43e76d463c09a0272b84775bcc727c1eb8b384b2 Mon Sep 17 00:00:00 2001 From: Ioana Ciornei Date: Thu, 17 Jun 2021 15:29:04 +0300 Subject: driver core: add a helper to setup both the of_node and fwnode of a device There are many places where both the fwnode_handle and the of_node of a device need to be populated. Add a function which does both so that we have consistency. Suggested-by: Andrew Lunn Signed-off-by: Ioana Ciornei Reviewed-by: Greg Kroah-Hartman Signed-off-by: David S. Miller --- include/linux/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 38a2071cf776..a1e7cab2c7bf 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -819,6 +819,7 @@ int device_online(struct device *dev); void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode); void set_secondary_fwnode(struct device *dev, struct fwnode_handle *fwnode); void device_set_of_node_from_dev(struct device *dev, const struct device *dev2); +void device_set_node(struct device *dev, struct fwnode_handle *fwnode); static inline int dev_num_vf(struct device *dev) { -- cgit v1.2.3 From ca2e334232b6cd4ae5af9da2df83c009d042aefb Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 5 Mar 2021 13:19:52 +0100 Subject: lib: add iomem emulation (logic_iomem) Add IO memory emulation that uses callbacks for read/write to the allocated regions. The callbacks can be registered by the users using logic_iomem_alloc(). To use, an architecture must 'select LOGIC_IOMEM' in Kconfig and then include into asm/io.h to get the __raw_read*/__raw_write* functions. Optionally, an architecture may 'select LOGIC_IOMEM_FALLBACK' in which case non-emulated regions will 'fall back' to the various real_* functions that must then be provided. Cc: Arnd Bergmann Signed-off-by: Johannes Berg Signed-off-by: Richard Weinberger --- include/linux/logic_iomem.h | 62 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 62 insertions(+) create mode 100644 include/linux/logic_iomem.h (limited to 'include/linux') diff --git a/include/linux/logic_iomem.h b/include/linux/logic_iomem.h new file mode 100644 index 000000000000..3fa65c964379 --- /dev/null +++ b/include/linux/logic_iomem.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2021 Intel Corporation + * Author: johannes@sipsolutions.net + */ +#ifndef __LOGIC_IOMEM_H +#define __LOGIC_IOMEM_H +#include +#include + +/** + * struct logic_iomem_ops - emulated IO memory ops + * @read: read an 8, 16, 32 or 64 bit quantity from the given offset, + * size is given in bytes (1, 2, 4 or 8) + * (64-bit only necessary if CONFIG_64BIT is set) + * @write: write an 8, 16 32 or 64 bit quantity to the given offset, + * size is given in bytes (1, 2, 4 or 8) + * (64-bit only necessary if CONFIG_64BIT is set) + * @set: optional, for memset_io() + * @copy_from: optional, for memcpy_fromio() + * @copy_to: optional, for memcpy_toio() + * @unmap: optional, this region is getting unmapped + */ +struct logic_iomem_ops { + unsigned long (*read)(void *priv, unsigned int offset, int size); + void (*write)(void *priv, unsigned int offset, int size, + unsigned long val); + + void (*set)(void *priv, unsigned int offset, u8 value, int size); + void (*copy_from)(void *priv, void *buffer, unsigned int offset, + int size); + void (*copy_to)(void *priv, unsigned int offset, const void *buffer, + int size); + + void (*unmap)(void *priv); +}; + +/** + * struct logic_iomem_region_ops - ops for an IO memory handler + * @map: map a range in the registered IO memory region, must + * fill *ops with the ops and may fill *priv to be passed + * to the ops. The offset is given as the offset into the + * registered resource region. + * The return value is negative for errors, or >= 0 for + * success. On success, the return value is added to the + * offset for later ops, to allow for partial mappings. + */ +struct logic_iomem_region_ops { + long (*map)(unsigned long offset, size_t size, + const struct logic_iomem_ops **ops, + void **priv); +}; + +/** + * logic_iomem_add_region - register an IO memory region + * @resource: the resource description for this region + * @ops: the IO memory mapping ops for this resource + */ +int logic_iomem_add_region(struct resource *resource, + const struct logic_iomem_region_ops *ops); + +#endif /* __LOGIC_IOMEM_H */ -- cgit v1.2.3 From 738d5ad104bbbe5d1bfb6c0553bb4a1eb91cc433 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 18 Jun 2021 08:38:47 +0200 Subject: Revert "of/platform: Add stubs for of_platform_device_create/destroy()" This reverts commit 412981e06294dac3254d83bbf71d4184ea911d05 as the patch series is causing build issues in linux-next at the moment. Cc: Matthias Kaehlcke Link: https://lore.kernel.org/r/YMuRcrE8xlWnFSWW@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/of_platform.h | 22 ++++------------------ 1 file changed, 4 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index d15b6cd5e1c3..84a966623e78 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -61,18 +61,16 @@ static inline struct platform_device *of_find_device_by_node(struct device_node } #endif -extern int of_platform_bus_probe(struct device_node *root, - const struct of_device_id *matches, - struct device *parent); - -#ifdef CONFIG_OF_ADDRESS /* Platform devices and busses creation */ extern struct platform_device *of_platform_device_create(struct device_node *np, const char *bus_id, struct device *parent); extern int of_platform_device_destroy(struct device *dev, void *data); - +extern int of_platform_bus_probe(struct device_node *root, + const struct of_device_id *matches, + struct device *parent); +#ifdef CONFIG_OF_ADDRESS extern int of_platform_populate(struct device_node *root, const struct of_device_id *matches, const struct of_dev_auxdata *lookup, @@ -86,18 +84,6 @@ extern int devm_of_platform_populate(struct device *dev); extern void devm_of_platform_depopulate(struct device *dev); #else -/* Platform devices and busses creation */ -static inline struct platform_device *of_platform_device_create(struct device_node *np, - const char *bus_id, - struct device *parent) -{ - return NULL; -} -static inline int of_platform_device_destroy(struct device *dev, void *data) -{ - return -ENODEV; -} - static inline int of_platform_populate(struct device_node *root, const struct of_device_id *matches, const struct of_dev_auxdata *lookup, -- cgit v1.2.3 From 04d72afa34edd14d99db7536d22819cdbb2b2e4c Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 18 Jun 2021 08:39:24 +0200 Subject: Revert "USB: misc: Add onboard_usb_hub driver" This reverts commit b4e326165e21d6a11483f6a4de2174b933413554 as the patch series is causing build issues in linux-next at the moment. Cc: Matthias Kaehlcke Link: https://lore.kernel.org/r/YMuRcrE8xlWnFSWW@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/onboard_hub.h | 18 ------------------ 1 file changed, 18 deletions(-) delete mode 100644 include/linux/usb/onboard_hub.h (limited to 'include/linux') diff --git a/include/linux/usb/onboard_hub.h b/include/linux/usb/onboard_hub.h deleted file mode 100644 index d9373230556e..000000000000 --- a/include/linux/usb/onboard_hub.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -#ifndef __LINUX_USB_ONBOARD_HUB_H -#define __LINUX_USB_ONBOARD_HUB_H - -struct usb_device; -struct list_head; - -#if IS_ENABLED(CONFIG_USB_ONBOARD_HUB) -void onboard_hub_create_pdevs(struct usb_device *parent_hub, struct list_head *pdev_list); -void onboard_hub_destroy_pdevs(struct list_head *pdev_list); -#else -static inline void onboard_hub_create_pdevs(struct usb_device *parent_hub, - struct list_head *pdev_list) {} -static inline void onboard_hub_destroy_pdevs(struct list_head *pdev_list) {} -#endif - -#endif /* __LINUX_USB_ONBOARD_HUB_H */ -- cgit v1.2.3 From b03fbd4ff24c5f075e58eb19261d5f8b3e40d7c6 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 11 Jun 2021 10:28:12 +0200 Subject: sched: Introduce task_is_running() Replace a bunch of 'p->state == TASK_RUNNING' with a new helper: task_is_running(p). Signed-off-by: Peter Zijlstra (Intel) Acked-by: Davidlohr Bueso Acked-by: Geert Uytterhoeven Acked-by: Will Deacon Link: https://lore.kernel.org/r/20210611082838.222401495@infradead.org --- 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 ac5a7d29fd4f..2cd56352dae1 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -113,6 +113,8 @@ struct task_group; __TASK_TRACED | EXIT_DEAD | EXIT_ZOMBIE | \ TASK_PARKED) +#define task_is_running(task) (READ_ONCE((task)->state) == TASK_RUNNING) + #define task_is_traced(task) ((task->state & __TASK_TRACED) != 0) #define task_is_stopped(task) ((task->state & __TASK_STOPPED) != 0) -- cgit v1.2.3 From d6c23bb3a2ad2f8f7dd46292b8bc54d27f2fb3f1 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 11 Jun 2021 10:28:14 +0200 Subject: sched: Add get_current_state() Remove yet another few p->state accesses. Signed-off-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Link: https://lore.kernel.org/r/20210611082838.347475156@infradead.org --- 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 2cd56352dae1..395c8906f502 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -213,6 +213,8 @@ struct task_group; #endif +#define get_current_state() READ_ONCE(current->state) + /* Task command name length: */ #define TASK_COMM_LEN 16 -- cgit v1.2.3 From 2f064a59a11ff9bc22e52e9678bc601404c7cb34 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 11 Jun 2021 10:28:17 +0200 Subject: sched: Change task_struct::state Change the type and name of task_struct::state. Drop the volatile and shrink it to an 'unsigned int'. Rename it in order to find all uses such that we can use READ_ONCE/WRITE_ONCE as appropriate. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Daniel Bristot de Oliveira Acked-by: Will Deacon Acked-by: Daniel Thompson Link: https://lore.kernel.org/r/20210611082838.550736351@infradead.org --- include/linux/sched.h | 31 +++++++++++++++---------------- include/linux/sched/debug.h | 2 +- include/linux/sched/signal.h | 2 +- 3 files changed, 17 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 395c8906f502..50db9496c99d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -113,13 +113,13 @@ struct task_group; __TASK_TRACED | EXIT_DEAD | EXIT_ZOMBIE | \ TASK_PARKED) -#define task_is_running(task) (READ_ONCE((task)->state) == TASK_RUNNING) +#define task_is_running(task) (READ_ONCE((task)->__state) == TASK_RUNNING) -#define task_is_traced(task) ((task->state & __TASK_TRACED) != 0) +#define task_is_traced(task) ((READ_ONCE(task->__state) & __TASK_TRACED) != 0) -#define task_is_stopped(task) ((task->state & __TASK_STOPPED) != 0) +#define task_is_stopped(task) ((READ_ONCE(task->__state) & __TASK_STOPPED) != 0) -#define task_is_stopped_or_traced(task) ((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0) +#define task_is_stopped_or_traced(task) ((READ_ONCE(task->__state) & (__TASK_STOPPED | __TASK_TRACED)) != 0) #ifdef CONFIG_DEBUG_ATOMIC_SLEEP @@ -134,14 +134,14 @@ struct task_group; do { \ WARN_ON_ONCE(is_special_task_state(state_value));\ current->task_state_change = _THIS_IP_; \ - current->state = (state_value); \ + WRITE_ONCE(current->__state, (state_value)); \ } while (0) #define set_current_state(state_value) \ do { \ WARN_ON_ONCE(is_special_task_state(state_value));\ current->task_state_change = _THIS_IP_; \ - smp_store_mb(current->state, (state_value)); \ + smp_store_mb(current->__state, (state_value)); \ } while (0) #define set_special_state(state_value) \ @@ -150,7 +150,7 @@ struct task_group; WARN_ON_ONCE(!is_special_task_state(state_value)); \ raw_spin_lock_irqsave(¤t->pi_lock, flags); \ current->task_state_change = _THIS_IP_; \ - current->state = (state_value); \ + WRITE_ONCE(current->__state, (state_value)); \ raw_spin_unlock_irqrestore(¤t->pi_lock, flags); \ } while (0) #else @@ -192,10 +192,10 @@ struct task_group; * Also see the comments of try_to_wake_up(). */ #define __set_current_state(state_value) \ - current->state = (state_value) + WRITE_ONCE(current->__state, (state_value)) #define set_current_state(state_value) \ - smp_store_mb(current->state, (state_value)) + smp_store_mb(current->__state, (state_value)) /* * set_special_state() should be used for those states when the blocking task @@ -207,13 +207,13 @@ struct task_group; do { \ unsigned long flags; /* may shadow */ \ raw_spin_lock_irqsave(¤t->pi_lock, flags); \ - current->state = (state_value); \ + WRITE_ONCE(current->__state, (state_value)); \ raw_spin_unlock_irqrestore(¤t->pi_lock, flags); \ } while (0) #endif -#define get_current_state() READ_ONCE(current->state) +#define get_current_state() READ_ONCE(current->__state) /* Task command name length: */ #define TASK_COMM_LEN 16 @@ -666,8 +666,7 @@ struct task_struct { */ struct thread_info thread_info; #endif - /* -1 unrunnable, 0 runnable, >0 stopped: */ - volatile long state; + unsigned int __state; /* * This begins the randomizable portion of task_struct. Only @@ -1532,7 +1531,7 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk) static inline unsigned int task_state_index(struct task_struct *tsk) { - unsigned int tsk_state = READ_ONCE(tsk->state); + unsigned int tsk_state = READ_ONCE(tsk->__state); unsigned int state = (tsk_state | tsk->exit_state) & TASK_REPORT; BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX); @@ -1840,10 +1839,10 @@ static __always_inline void scheduler_ipi(void) */ preempt_fold_need_resched(); } -extern unsigned long wait_task_inactive(struct task_struct *, long match_state); +extern unsigned long wait_task_inactive(struct task_struct *, unsigned int match_state); #else static inline void scheduler_ipi(void) { } -static inline unsigned long wait_task_inactive(struct task_struct *p, long match_state) +static inline unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state) { return 1; } diff --git a/include/linux/sched/debug.h b/include/linux/sched/debug.h index ae51f4529fc9..b5035afa2396 100644 --- a/include/linux/sched/debug.h +++ b/include/linux/sched/debug.h @@ -14,7 +14,7 @@ extern void dump_cpu_task(int cpu); /* * Only dump TASK_* tasks. (0 for all tasks) */ -extern void show_state_filter(unsigned long state_filter); +extern void show_state_filter(unsigned int state_filter); static inline void show_state(void) { diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 7f4278fa21fe..c9cf678c347d 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -382,7 +382,7 @@ static inline int fatal_signal_pending(struct task_struct *p) return task_sigpending(p) && __fatal_signal_pending(p); } -static inline int signal_pending_state(long state, struct task_struct *p) +static inline int signal_pending_state(unsigned int state, struct task_struct *p) { if (!(state & (TASK_INTERRUPTIBLE | TASK_WAKEKILL))) return 0; -- cgit v1.2.3 From 52d7e288444906aa5c99888e80a9cc1a1423ed92 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 18 Jun 2021 16:45:22 +0300 Subject: blk-mq: fix an IS_ERR() vs NULL bug The __blk_mq_alloc_disk() function doesn't return NULLs it returns error pointers. Fixes: b461dfc49eb6 ("blk-mq: add the blk_mq_alloc_disk APIs") Signed-off-by: Dan Carpenter Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/YMyjci35WBqrtqG+@mwanda Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 02a4aab0aeac..fd2de2b422ed 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -431,7 +431,7 @@ enum { static struct lock_class_key __key; \ struct gendisk *__disk = __blk_mq_alloc_disk(set, queuedata); \ \ - if (__disk) \ + if (!IS_ERR(__disk)) \ lockdep_init_map(&__disk->lockdep_map, \ "(bio completion)", &__key, 0); \ __disk; \ -- cgit v1.2.3 From 60302ce4ea075369641426ef407c110e36ea8ba1 Mon Sep 17 00:00:00 2001 From: Stephan Gerhold Date: Fri, 18 Jun 2021 19:36:09 +0200 Subject: rpmsg: core: Add driver_data for rpmsg_device_id Most device_id structs provide a driver_data field that can be used by drivers to associate data more easily for a particular device ID. Add the same for the rpmsg_device_id. Cc: Bjorn Andersson Signed-off-by: Stephan Gerhold Signed-off-by: David S. Miller --- include/linux/mod_devicetable.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 7d45b5f989b0..8e291cfdaf06 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -447,6 +447,7 @@ struct hv_vmbus_device_id { struct rpmsg_device_id { char name[RPMSG_NAME_SIZE]; + kernel_ulong_t driver_data; }; /* i2c */ -- cgit v1.2.3 From 31c143f712750143abaca396236bbe8707700111 Mon Sep 17 00:00:00 2001 From: Stephan Gerhold Date: Fri, 18 Jun 2021 19:36:11 +0200 Subject: net: wwan: Allow WWAN drivers to provide blocking tx and poll function At the moment, the WWAN core provides wwan_port_txon/off() to implement blocking writes. The tx() port operation should not block, instead wwan_port_txon/off() should be called when the TX queue is full or has free space again. However, in some cases it is not straightforward to make use of that functionality. For example, the RPMSG API used by rpmsg_wwan_ctrl.c does not provide any way to be notified when the TX queue has space again. Instead, it only provides the following operations: - rpmsg_send(): blocking write (wait until there is space) - rpmsg_trysend(): non-blocking write (return error if no space) - rpmsg_poll(): set poll flags depending on TX queue state Generally that's totally sufficient for implementing a char device, but it does not fit well to the currently provided WWAN port ops. Most of the time, using the non-blocking rpmsg_trysend() in the WWAN tx() port operation works just fine. However, with high-frequent writes to the char device it is possible to trigger a situation where this causes issues. For example, consider the following (somewhat unrealistic) example: # dd if=/dev/zero bs=1000 of=/dev/wwan0qmi0 dd: error writing '/dev/wwan0qmi0': Resource temporarily unavailable 1+0 records out This fails immediately after writing the first record. It's likely only a matter of time until this triggers issues for some real application (e.g. ModemManager sending a lot of large QMI packets). The rpmsg_char device does not have this problem, because it uses rpmsg_trysend() and rpmsg_poll() to support non-blocking operations. Make it possible to use the same in the RPMSG WWAN driver by adding two new optional wwan_port_ops: - tx_blocking(): send data blocking if allowed - tx_poll(): set additional TX poll flags This integrates nicely with the RPMSG API and does not require any change in existing WWAN drivers. With these changes, the dd example above blocks instead of exiting with an error. Cc: Loic Poulain Signed-off-by: Stephan Gerhold Signed-off-by: David S. Miller --- include/linux/wwan.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/wwan.h b/include/linux/wwan.h index 430a3a0817de..34222230360c 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -6,6 +6,7 @@ #include #include +#include #include #include @@ -40,15 +41,23 @@ struct wwan_port; /** struct wwan_port_ops - The WWAN port operations * @start: The routine for starting the WWAN port device. * @stop: The routine for stopping the WWAN port device. - * @tx: The routine that sends WWAN port protocol data to the device. + * @tx: Non-blocking routine that sends WWAN port protocol data to the device. + * @tx_blocking: Optional blocking routine that sends WWAN port protocol data + * to the device. + * @tx_poll: Optional routine that sets additional TX poll flags. * * The wwan_port_ops structure contains a list of low-level operations - * that control a WWAN port device. All functions are mandatory. + * that control a WWAN port device. All functions are mandatory unless specified. */ struct wwan_port_ops { int (*start)(struct wwan_port *port); void (*stop)(struct wwan_port *port); int (*tx)(struct wwan_port *port, struct sk_buff *skb); + + /* Optional operations */ + int (*tx_blocking)(struct wwan_port *port, struct sk_buff *skb); + __poll_t (*tx_poll)(struct wwan_port *port, struct file *filp, + poll_table *wait); }; /** -- cgit v1.2.3 From 031e668bc1ad7ccdbfb2b67b838bb6b7cc44ecf3 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Wed, 16 Jun 2021 15:59:01 +0100 Subject: soundwire: bus: Make sdw_nwrite() data pointer argument const Idiomatically, write functions should take const pointers to the data buffer, as they don't change the data. They are also likely to be called from functions that receive a const data pointer. Internally the pointer is passed to function/structs shared with the read functions, requiring a cast, but this is an implementation detail that should be hidden by the public API. Signed-off-by: Richard Fitzgerald Link: https://lore.kernel.org/r/20210616145901.29402-1-rf@opensource.cirrus.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 8ca736e92d5a..ddbeb00799e4 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -1039,7 +1039,7 @@ int sdw_write(struct sdw_slave *slave, u32 addr, u8 value); int sdw_write_no_pm(struct sdw_slave *slave, u32 addr, u8 value); int sdw_read_no_pm(struct sdw_slave *slave, u32 addr); int sdw_nread(struct sdw_slave *slave, u32 addr, size_t count, u8 *val); -int sdw_nwrite(struct sdw_slave *slave, u32 addr, size_t count, u8 *val); +int sdw_nwrite(struct sdw_slave *slave, u32 addr, size_t count, const u8 *val); int sdw_compare_devid(struct sdw_slave *slave, struct sdw_slave_id id); void sdw_extract_slave_id(struct sdw_bus *bus, u64 addr, struct sdw_slave_id *id); -- cgit v1.2.3 From 0475c3655e6ebd1d6d6f0e705eba97fce39a08e3 Mon Sep 17 00:00:00 2001 From: Hyunchul Lee Date: Tue, 8 Jun 2021 23:53:14 +0900 Subject: cifs: decoding negTokenInit with generic ASN1 decoder Decode negTokenInit with lib/asn1_decoder. For that, add OIDs in linux/oid_registry.h and a negTokenInit ASN1 file, "spnego_negtokeninit.asn1". And define decoder's callback functions, which are the gssapi_this_mech for checking SPENGO oid and the neg_token_init_mech_type for getting authentication mechanisms supported by a server. Signed-off-by: Hyunchul Lee Reviewed-by: Aurelien Aptel Reviewed-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French --- include/linux/oid_registry.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/oid_registry.h b/include/linux/oid_registry.h index 461b7aa587ba..3d8db1f6a5db 100644 --- a/include/linux/oid_registry.h +++ b/include/linux/oid_registry.h @@ -54,6 +54,10 @@ enum OID { OID_md4, /* 1.2.840.113549.2.4 */ OID_md5, /* 1.2.840.113549.2.5 */ + OID_mskrb5, /* 1.2.840.48018.1.2.2 */ + OID_krb5, /* 1.2.840.113554.1.2.2 */ + OID_krb5u2u, /* 1.2.840.113554.1.2.2.3 */ + /* Microsoft Authenticode & Software Publishing */ OID_msIndirectData, /* 1.3.6.1.4.1.311.2.1.4 */ OID_msStatementType, /* 1.3.6.1.4.1.311.2.1.11 */ @@ -62,6 +66,10 @@ enum OID { OID_msIndividualSPKeyPurpose, /* 1.3.6.1.4.1.311.2.1.21 */ OID_msOutlookExpress, /* 1.3.6.1.4.1.311.16.4 */ + OID_ntlmssp, /* 1.3.6.1.4.1.311.2.2.10 */ + + OID_spnego, /* 1.3.6.1.5.5.2 */ + OID_certAuthInfoAccess, /* 1.3.6.1.5.5.7.1.1 */ OID_sha1, /* 1.3.14.3.2.26 */ OID_id_ansip384r1, /* 1.3.132.0.34 */ -- cgit v1.2.3 From bc65baf73b68448e79e8ff797522d1976788deb1 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Thu, 18 Mar 2021 17:25:06 +0000 Subject: watchdog: Remove MV64x60 watchdog driver Commit 92c8c16f3457 ("powerpc/embedded6xx: Remove C2K board support") removed the last selector of CONFIG_MV64X60. Therefore CONFIG_MV64X60_WDT cannot be selected anymore and can be removed. Signed-off-by: Christophe Leroy Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/9c2952bcfaec3b1789909eaa36bbce2afbfab7ab.1616085654.git.christophe.leroy@csgroup.eu Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- include/linux/mv643xx.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mv643xx.h b/include/linux/mv643xx.h index 47e5679b48e1..000b126acfb6 100644 --- a/include/linux/mv643xx.h +++ b/include/linux/mv643xx.h @@ -918,12 +918,4 @@ extern void mv64340_irq_init(unsigned int base); -/* Watchdog Platform Device, Driver Data */ -#define MV64x60_WDT_NAME "mv64x60_wdt" - -struct mv64x60_wdt_pdata { - int timeout; /* watchdog expiry in seconds, default 10 */ - int bus_clk; /* bus clock in MHz, default 133 */ -}; - #endif /* __ASM_MV643XX_H */ -- cgit v1.2.3 From 4249cb7d920060dfa925d3b9f6a37f0a7c025a16 Mon Sep 17 00:00:00 2001 From: Huilong Deng Date: Sun, 20 Jun 2021 22:29:15 +0800 Subject: printk: Remove trailing semicolon in macros Macros should not use a trailing semicolon. Signed-off-by: Huilong Deng Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek --- include/linux/dev_printk.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dev_printk.h b/include/linux/dev_printk.h index 6f009559ee54..82d3d46005a1 100644 --- a/include/linux/dev_printk.h +++ b/include/linux/dev_printk.h @@ -236,7 +236,7 @@ do { \ * using WARN/WARN_ONCE to include file/line information and a backtrace. */ #define dev_WARN(dev, format, arg...) \ - WARN(1, "%s %s: " format, dev_driver_string(dev), dev_name(dev), ## arg); + WARN(1, "%s %s: " format, dev_driver_string(dev), dev_name(dev), ## arg) #define dev_WARN_ONCE(dev, condition, format, arg...) \ WARN_ONCE(condition, "%s %s: " format, \ -- cgit v1.2.3 From d38ebaf2c88442a830d402fa7805ddbb60c4cd0c Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Mon, 14 Jun 2021 13:08:11 -0500 Subject: soundwire: export sdw_update() and sdw_update_no_pm() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We currently export sdw_read() and sdw_write() but the sdw_update() and sdw_update_no_pm() are currently available only to the bus code. This was missed in an earlier contribution. Export both functions so that codec drivers can perform read-modify-write operations without duplicating the code. Fixes: b04c975e654c ('soundwire: bus: use sdw_update_no_pm when initializing a device') Signed-off-by: Pierre-Louis Bossart Reviewed-by: Bard Liao Reviewed-by: Péter Ujfalusi Acked-By: Vinod Koul Link: https://lore.kernel.org/r/20210614180815.153711-2-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- include/linux/soundwire/sdw.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index ced07f8fde87..de9802a24e7e 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -1041,6 +1041,9 @@ int sdw_write_no_pm(struct sdw_slave *slave, u32 addr, u8 value); int sdw_read_no_pm(struct sdw_slave *slave, u32 addr); int sdw_nread(struct sdw_slave *slave, u32 addr, size_t count, u8 *val); int sdw_nwrite(struct sdw_slave *slave, u32 addr, size_t count, u8 *val); +int sdw_update(struct sdw_slave *slave, u32 addr, u8 mask, u8 val); +int sdw_update_no_pm(struct sdw_slave *slave, u32 addr, u8 mask, u8 val); + int sdw_compare_devid(struct sdw_slave *slave, struct sdw_slave_id id); void sdw_extract_slave_id(struct sdw_bus *bus, u64 addr, struct sdw_slave_id *id); -- cgit v1.2.3 From dfa19b11385d4cf8f0242fd93e2073e25183c331 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Thu, 3 Jun 2021 08:40:45 +0300 Subject: reboot: Add hardware protection power-off There can be few cases when we need to shut-down the system in order to protect the hardware. Currently this is done at least by the thermal core when temperature raises over certain limit. Some PMICs can also generate interrupts for example for over-current or over-voltage, voltage drops, short-circuit, ... etc. On some systems these are a sign of hardware failure and only thing to do is try to protect the rest of the hardware by shutting down the system. Add shut-down logic which can be used by all subsystems instead of implementing the shutdown in each subsystem. The logic is stolen from thermal_core with difference of using atomic_t instead of a mutex in order to allow calls directly from IRQ context and changing the WARN() to pr_emerg() as discussed here: https://lore.kernel.org/lkml/YJuPwAZroVZ%2Fw633@alley/ and here: https://lore.kernel.org/linux-iommu/20210331093104.383705-4-geert+renesas@glider.be/ Signed-off-by: Matti Vaittinen Acked-by: Daniel Lezcano Link: https://lore.kernel.org/r/e83ec1ca9408f90c857ea9dcdc57b14d9037b03f.1622628333.git.matti.vaittinen@fi.rohmeurope.com Signed-off-by: Mark Brown --- include/linux/reboot.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/reboot.h b/include/linux/reboot.h index 3734cd8f38a8..af907a3d68d1 100644 --- a/include/linux/reboot.h +++ b/include/linux/reboot.h @@ -79,6 +79,7 @@ extern char poweroff_cmd[POWEROFF_CMD_PATH_LEN]; extern void orderly_poweroff(bool force); extern void orderly_reboot(void); +void hw_protection_shutdown(const char *reason, int ms_until_forced); /* * Emergency restart, callable from an interrupt handler. -- cgit v1.2.3 From e6c3092d43faf0aa095160cc552f8c05490d0962 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Thu, 3 Jun 2021 08:41:21 +0300 Subject: regulator: add warning flags Add 'warning' level events and error flags to regulator core. Current regulator core notifications are used to inform consumers about errors where HW is misbehaving in such way it is assumed to be broken/unrecoverable. There are PMICs which are designed for system(s) that may have use for regulator indications sent before HW is damaged so that some board/consumer specific recovery-event can be performed while continuing most of the normal operations. Add new WARNING level events and notifications to be used for that purpose. Signed-off-by: Matti Vaittinen Link: https://lore.kernel.org/r/9b54aa5589ae4b5945d53d114bac3fae55fa4818.1622628333.git.matti.vaittinen@fi.rohmeurope.com Signed-off-by: Mark Brown --- include/linux/regulator/consumer.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 20e84a84fb77..f72ca73631be 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -119,6 +119,16 @@ struct regulator_dev; #define REGULATOR_EVENT_PRE_DISABLE 0x400 #define REGULATOR_EVENT_ABORT_DISABLE 0x800 #define REGULATOR_EVENT_ENABLE 0x1000 +/* + * Following notifications should be emitted only if detected condition + * is such that the HW is likely to still be working but consumers should + * take a recovery action to prevent problems esacalating into errors. + */ +#define REGULATOR_EVENT_UNDER_VOLTAGE_WARN 0x2000 +#define REGULATOR_EVENT_OVER_CURRENT_WARN 0x4000 +#define REGULATOR_EVENT_OVER_VOLTAGE_WARN 0x8000 +#define REGULATOR_EVENT_OVER_TEMP_WARN 0x10000 +#define REGULATOR_EVENT_WARN_MASK 0x1E000 /* * Regulator errors that can be queried using regulator_get_error_flags @@ -138,6 +148,10 @@ struct regulator_dev; #define REGULATOR_ERROR_FAIL BIT(4) #define REGULATOR_ERROR_OVER_TEMP BIT(5) +#define REGULATOR_ERROR_UNDER_VOLTAGE_WARN BIT(6) +#define REGULATOR_ERROR_OVER_CURRENT_WARN BIT(7) +#define REGULATOR_ERROR_OVER_VOLTAGE_WARN BIT(8) +#define REGULATOR_ERROR_OVER_TEMP_WARN BIT(9) /** * struct pre_voltage_change_data - Data sent with PRE_VOLTAGE_CHANGE event -- cgit v1.2.3 From 157d2230193ae683fcffcc1cd0a2c3aa4479955f Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Thu, 3 Jun 2021 08:41:37 +0300 Subject: regulator: move rdev_print helpers to internal.h The rdev print helpers are a nice way to print messages related to a specific regulator device. Move them from core.c to internal.h As the rdev print helpers use rdev_get_name() export it from core.c. Also move the declaration from coupler.h to driver.h because the rdev name is not just a coupled regulator property. I guess the main audience for rdev_get_name() will be the regulator core and drivers. Signed-off-by: Matti Vaittinen Link: https://lore.kernel.org/r/dc7fd70dc31de4d0e820b7646bb78eeb04f80735.1622628333.git.matti.vaittinen@fi.rohmeurope.com Signed-off-by: Mark Brown --- include/linux/regulator/coupler.h | 5 ----- include/linux/regulator/driver.h | 10 ++++++++++ 2 files changed, 10 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/coupler.h b/include/linux/regulator/coupler.h index 5f86824bd117..73291f280a23 100644 --- a/include/linux/regulator/coupler.h +++ b/include/linux/regulator/coupler.h @@ -52,7 +52,6 @@ struct regulator_coupler { #ifdef CONFIG_REGULATOR int regulator_coupler_register(struct regulator_coupler *coupler); -const char *rdev_get_name(struct regulator_dev *rdev); int regulator_check_consumers(struct regulator_dev *rdev, int *min_uV, int *max_uV, suspend_state_t state); @@ -69,10 +68,6 @@ static inline int regulator_coupler_register(struct regulator_coupler *coupler) { return 0; } -static inline const char *rdev_get_name(struct regulator_dev *rdev) -{ - return NULL; -} static inline int regulator_check_consumers(struct regulator_dev *rdev, int *min_uV, int *max_uV, suspend_state_t state) diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 4ea520c248e9..7ec0fa79d1a8 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -550,4 +550,14 @@ int regulator_desc_list_voltage_linear_range(const struct regulator_desc *desc, int regulator_desc_list_voltage_linear(const struct regulator_desc *desc, unsigned int selector); + +#ifdef CONFIG_REGULATOR +const char *rdev_get_name(struct regulator_dev *rdev); +#else +static inline const char *rdev_get_name(struct regulator_dev *rdev) +{ + return NULL; +} +#endif + #endif -- cgit v1.2.3 From 7111c6d1b31b42c8c758f6681e895a5116e3bad6 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Thu, 3 Jun 2021 08:41:55 +0300 Subject: regulator: IRQ based event/error notification helpers Provide helper function for IC's implementing regulator notifications when an IRQ fires. The helper also works for IRQs which can not be acked. Helper can be set to disable the IRQ at handler and then re-enabling it on delayed work later. The helper also adds regulator_get_error_flags() errors in cache for the duration of IRQ disabling. Signed-off-by: Matti Vaittinen Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/ebdf86d8c22b924667ec2385330e30fcbfac0119.1622628334.git.matti.vaittinen@fi.rohmeurope.com Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 135 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 135 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 7ec0fa79d1a8..1d1a8951e740 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -413,6 +413,128 @@ struct regulator_config { struct gpio_desc *ena_gpiod; }; +/** + * struct regulator_err_state - regulator error/notification status + * + * @rdev: Regulator which status the struct indicates. + * @notifs: Events which have occurred on the regulator. + * @errors: Errors which are active on the regulator. + * @possible_errs: Errors which can be signaled (by given IRQ). + */ +struct regulator_err_state { + struct regulator_dev *rdev; + unsigned long notifs; + unsigned long errors; + int possible_errs; +}; + +/** + * struct regulator_irq_data - regulator error/notification status date + * + * @states: Status structs for each of the associated regulators. + * @num_states: Amount of associated regulators. + * @data: Driver data pointer given at regulator_irq_desc. + * @opaque: Value storage for IC driver. Core does not update this. ICs + * may want to store status register value here at map_event and + * compare contents at 'renable' callback to see if new problems + * have been added to status. If that is the case it may be + * desirable to return REGULATOR_ERROR_CLEARED and not + * REGULATOR_ERROR_ON to allow IRQ fire again and to generate + * notifications also for the new issues. + * + * This structure is passed to 'map_event' and 'renable' callbacks for + * reporting regulator status to core. + */ +struct regulator_irq_data { + struct regulator_err_state *states; + int num_states; + void *data; + long opaque; +}; + +/** + * struct regulator_irq_desc - notification sender for IRQ based events. + * + * @name: The visible name for the IRQ + * @fatal_cnt: If this IRQ is used to signal HW damaging condition it may be + * best to shut-down regulator(s) or reboot the SOC if error + * handling is repeatedly failing. If fatal_cnt is given the IRQ + * handling is aborted if it fails for fatal_cnt times and die() + * callback (if populated) or BUG() is called to try to prevent + * further damage. + * @reread_ms: The time which is waited before attempting to re-read status + * at the worker if IC reading fails. Immediate re-read is done + * if time is not specified. + * @irq_off_ms: The time which IRQ is kept disabled before re-evaluating the + * status for devices which keep IRQ disabled for duration of the + * error. If this is not given the IRQ is left enabled and renable + * is not called. + * @skip_off: If set to true the IRQ handler will attempt to check if any of + * the associated regulators are enabled prior to taking other + * actions. If no regulators are enabled and this is set to true + * a spurious IRQ is assumed and IRQ_NONE is returned. + * @high_prio: Boolean to indicate that high priority WQ should be used. + * @data: Driver private data pointer which will be passed as such to + * the renable, map_event and die callbacks in regulator_irq_data. + * @die: Protection callback. If IC status reading or recovery actions + * fail fatal_cnt times this callback or BUG() is called. This + * callback should implement a final protection attempt like + * disabling the regulator. If protection succeeded this may + * return 0. If anything else is returned the core assumes final + * protection failed and calls BUG() as a last resort. + * @map_event: Driver callback to map IRQ status into regulator devices with + * events / errors. NOTE: callback MUST initialize both the + * errors and notifs for all rdevs which it signals having + * active events as core does not clean the map data. + * REGULATOR_FAILED_RETRY can be returned to indicate that the + * status reading from IC failed. If this is repeated for + * fatal_cnt times the core will call die() callback or BUG() + * as a last resort to protect the HW. + * @renable: Optional callback to check status (if HW supports that) before + * re-enabling IRQ. If implemented this should clear the error + * flags so that errors fetched by regulator_get_error_flags() + * are updated. If callback is not implemented then errors are + * assumed to be cleared and IRQ is re-enabled. + * REGULATOR_FAILED_RETRY can be returned to + * indicate that the status reading from IC failed. If this is + * repeated for 'fatal_cnt' times the core will call die() + * callback or BUG() as a last resort to protect the HW. + * Returning zero indicates that the problem in HW has been solved + * and IRQ will be re-enabled. Returning REGULATOR_ERROR_ON + * indicates the error condition is still active and keeps IRQ + * disabled. Please note that returning REGULATOR_ERROR_ON does + * not retrigger evaluating what events are active or resending + * notifications. If this is needed you probably want to return + * zero and allow IRQ to retrigger causing events to be + * re-evaluated and re-sent. + * + * This structure is used for registering regulator IRQ notification helper. + */ +struct regulator_irq_desc { + const char *name; + int irq_flags; + int fatal_cnt; + int reread_ms; + int irq_off_ms; + bool skip_off; + bool high_prio; + void *data; + + int (*die)(struct regulator_irq_data *rid); + int (*map_event)(int irq, struct regulator_irq_data *rid, + unsigned long *dev_mask); + int (*renable)(struct regulator_irq_data *rid); +}; + +/* + * Return values for regulator IRQ helpers. + */ +enum { + REGULATOR_ERROR_CLEARED, + REGULATOR_FAILED_RETRY, + REGULATOR_ERROR_ON, +}; + /* * struct coupling_desc * @@ -477,6 +599,9 @@ struct regulator_dev { /* time when this regulator was disabled last time */ ktime_t last_off; + int cached_err; + bool use_cached_err; + spinlock_t err_lock; }; struct regulator_dev * @@ -491,6 +616,16 @@ void devm_regulator_unregister(struct device *dev, struct regulator_dev *rdev); int regulator_notifier_call_chain(struct regulator_dev *rdev, unsigned long event, void *data); +void *devm_regulator_irq_helper(struct device *dev, + const struct regulator_irq_desc *d, int irq, + int irq_flags, int common_errs, + int *per_rdev_errs, struct regulator_dev **rdev, + int rdev_amount); +void *regulator_irq_helper(struct device *dev, + const struct regulator_irq_desc *d, int irq, + int irq_flags, int common_errs, int *per_rdev_errs, + struct regulator_dev **rdev, int rdev_amount); +void regulator_irq_helper_cancel(void **handle); void *rdev_get_drvdata(struct regulator_dev *rdev); struct device *rdev_get_dev(struct regulator_dev *rdev); -- cgit v1.2.3 From 89a6a5e56c8248a077d12424a1383a6b18ea840b Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Thu, 3 Jun 2021 08:42:12 +0300 Subject: regulator: add property parsing and callbacks to set protection limits Add DT property parsing code and setting callback for regulator over/under voltage, over-current and temperature error limits. Signed-off-by: Matti Vaittinen Link: https://lore.kernel.org/r/e7b8007ba9eae7076178bf3363fb942ccb1cc9a5.1622628334.git.matti.vaittinen@fi.rohmeurope.com Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 41 +++++++++++++++++++++++++++++++++++---- include/linux/regulator/machine.h | 26 +++++++++++++++++++++++++ 2 files changed, 63 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 1d1a8951e740..4ebfaacf42b7 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -40,6 +40,15 @@ enum regulator_status { REGULATOR_STATUS_UNDEFINED, }; +enum regulator_detection_severity { + /* Hardware shut down voltage outputs if condition is detected */ + REGULATOR_SEVERITY_PROT, + /* Hardware is probably damaged/inoperable */ + REGULATOR_SEVERITY_ERR, + /* Hardware is still recoverable but recovery action must be taken */ + REGULATOR_SEVERITY_WARN, +}; + /* Initialize struct linear_range for regulators */ #define REGULATOR_LINEAR_RANGE(_min_uV, _min_sel, _max_sel, _step_uV) \ { \ @@ -78,8 +87,25 @@ enum regulator_status { * @get_current_limit: Get the configured limit for a current-limited regulator. * @set_input_current_limit: Configure an input limit. * - * @set_over_current_protection: Support capability of automatically shutting - * down when detecting an over current event. + * @set_over_current_protection: Support enabling of and setting limits for over + * current situation detection. Detection can be configured for three + * levels of severity. + * REGULATOR_SEVERITY_PROT should automatically shut down the regulator(s). + * REGULATOR_SEVERITY_ERR should indicate that over-current situation is + * caused by an unrecoverable error but HW does not perform + * automatic shut down. + * REGULATOR_SEVERITY_WARN should indicate situation where hardware is + * still believed to not be damaged but that a board sepcific + * recovery action is needed. If lim_uA is 0 the limit should not + * be changed but the detection should just be enabled/disabled as + * is requested. + * @set_over_voltage_protection: Support enabling of and setting limits for over + * voltage situation detection. Detection can be configured for same + * severities as over current protection. + * @set_under_voltage_protection: Support enabling of and setting limits for + * under situation detection. + * @set_thermal_protection: Support enabling of and setting limits for over + * temperature situation detection. * * @set_active_discharge: Set active discharge enable/disable of regulators. * @@ -143,8 +169,15 @@ struct regulator_ops { int (*get_current_limit) (struct regulator_dev *); int (*set_input_current_limit) (struct regulator_dev *, int lim_uA); - int (*set_over_current_protection) (struct regulator_dev *); - int (*set_active_discharge) (struct regulator_dev *, bool enable); + int (*set_over_current_protection)(struct regulator_dev *, int lim_uA, + int severity, bool enable); + int (*set_over_voltage_protection)(struct regulator_dev *, int lim_uV, + int severity, bool enable); + int (*set_under_voltage_protection)(struct regulator_dev *, int lim_uV, + int severity, bool enable); + int (*set_thermal_protection)(struct regulator_dev *, int lim, + int severity, bool enable); + int (*set_active_discharge)(struct regulator_dev *, bool enable); /* enable/disable regulator */ int (*enable) (struct regulator_dev *); diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h index 8a56f033b6cd..68b4a514a410 100644 --- a/include/linux/regulator/machine.h +++ b/include/linux/regulator/machine.h @@ -83,6 +83,14 @@ struct regulator_state { bool changeable; }; +#define REGULATOR_NOTIF_LIMIT_DISABLE -1 +#define REGULATOR_NOTIF_LIMIT_ENABLE -2 +struct notification_limit { + int prot; + int err; + int warn; +}; + /** * struct regulation_constraints - regulator operating constraints. * @@ -100,6 +108,11 @@ struct regulator_state { * @ilim_uA: Maximum input current. * @system_load: Load that isn't captured by any consumer requests. * + * @over_curr_limits: Limits for acting on over current. + * @over_voltage_limits: Limits for acting on over voltage. + * @under_voltage_limits: Limits for acting on under voltage. + * @temp_limits: Limits for acting on over temperature. + * @max_spread: Max possible spread between coupled regulators * @max_uV_step: Max possible step change in voltage * @valid_modes_mask: Mask of modes which may be configured by consumers. @@ -116,6 +129,11 @@ struct regulator_state { * @pull_down: Enable pull down when regulator is disabled. * @over_current_protection: Auto disable on over current event. * + * @over_current_detection: Configure over current limits. + * @over_voltage_detection: Configure over voltage limits. + * @under_voltage_detection: Configure under voltage limits. + * @over_temp_detection: Configure over temperature limits. + * * @input_uV: Input voltage for regulator when supplied by another regulator. * * @state_disk: State for regulator when system is suspended in disk mode. @@ -172,6 +190,10 @@ struct regulation_constraints { struct regulator_state state_disk; struct regulator_state state_mem; struct regulator_state state_standby; + struct notification_limit over_curr_limits; + struct notification_limit over_voltage_limits; + struct notification_limit under_voltage_limits; + struct notification_limit temp_limits; suspend_state_t initial_state; /* suspend state to set at init */ /* mode to set on startup */ @@ -193,6 +215,10 @@ struct regulation_constraints { unsigned soft_start:1; /* ramp voltage slowly */ unsigned pull_down:1; /* pull down resistor when regulator off */ unsigned over_current_protection:1; /* auto disable on over current */ + unsigned over_current_detection:1; /* notify on over current */ + unsigned over_voltage_detection:1; /* notify on over voltage */ + unsigned under_voltage_detection:1; /* notify on under voltage */ + unsigned over_temp_detection:1; /* notify on over temperature */ }; /** -- cgit v1.2.3 From 9f2470fbc4cb4583c080bb729a998933ba61aca4 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Mon, 14 Jun 2021 19:13:35 -0700 Subject: skmsg: Improve udp_bpf_recvmsg() accuracy I tried to reuse sk_msg_wait_data() for different protocols, but it turns out it can not be simply reused. For example, UDP actually uses two queues to receive skb: udp_sk(sk)->reader_queue and sk->sk_receive_queue. So we have to check both of them to know whether we have received any packet. Also, UDP does not lock the sock during BH Rx path, it makes no sense for its ->recvmsg() to lock the sock. It is always possible for ->recvmsg() to be called before packets actually arrive in the receive queue, we just use best effort to make it accurate here. Fixes: 1f5be6b3b063 ("udp: Implement udp_bpf_recvmsg() for sockmap") Signed-off-by: Cong Wang Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Acked-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/20210615021342.7416-2-xiyou.wangcong@gmail.com --- include/linux/skmsg.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index aba0f0f429be..e3d080c299f6 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -126,8 +126,6 @@ int sk_msg_zerocopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes); int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes); -int sk_msg_wait_data(struct sock *sk, struct sk_psock *psock, int flags, - long timeo, int *err); int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags); -- cgit v1.2.3 From 67a066b35765d13a55a56edd9b1f54dee9e441e1 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Thu, 10 Jun 2021 19:23:13 +0300 Subject: of: reserved-memory: Add stub for RESERVEDMEM_OF_DECLARE() The reserved-memory Kconfig could be disabled when drivers are compile-tested. In this case RESERVEDMEM_OF_DECLARE() produces a noisy warning about the orphaned __reservedmem_of_table section. Add the missing stub that fixes the warning. In particular this is needed for compile-testing of NVIDIA Tegra210 memory driver which uses reserved-memory. Reported-by: Krzysztof Kozlowski Signed-off-by: Dmitry Osipenko Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20210610162313.20942-1-digetx@gmail.com Signed-off-by: Rob Herring --- include/linux/of.h | 11 +++++++---- include/linux/of_reserved_mem.h | 8 ++++++-- 2 files changed, 13 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index d8db8d3592fd..9c2e71e202d1 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -1329,6 +1329,12 @@ static inline int of_get_available_child_count(const struct device_node *np) return num; } +#define _OF_DECLARE_STUB(table, name, compat, fn, fn_type) \ + static const struct of_device_id __of_table_##name \ + __attribute__((unused)) \ + = { .compatible = compat, \ + .data = (fn == (fn_type)NULL) ? fn : fn } + #if defined(CONFIG_OF) && !defined(MODULE) #define _OF_DECLARE(table, name, compat, fn, fn_type) \ static const struct of_device_id __of_table_##name \ @@ -1338,10 +1344,7 @@ static inline int of_get_available_child_count(const struct device_node *np) .data = (fn == (fn_type)NULL) ? fn : fn } #else #define _OF_DECLARE(table, name, compat, fn, fn_type) \ - static const struct of_device_id __of_table_##name \ - __attribute__((unused)) \ - = { .compatible = compat, \ - .data = (fn == (fn_type)NULL) ? fn : fn } + _OF_DECLARE_STUB(table, name, compat, fn, fn_type) #endif typedef int (*of_init_fn_2)(struct device_node *, struct device_node *); diff --git a/include/linux/of_reserved_mem.h b/include/linux/of_reserved_mem.h index 76e4a0fffba4..4de2a24cadc9 100644 --- a/include/linux/of_reserved_mem.h +++ b/include/linux/of_reserved_mem.h @@ -27,11 +27,11 @@ struct reserved_mem_ops { typedef int (*reservedmem_of_init_fn)(struct reserved_mem *rmem); +#ifdef CONFIG_OF_RESERVED_MEM + #define RESERVEDMEM_OF_DECLARE(name, compat, init) \ _OF_DECLARE(reservedmem, name, compat, init, reservedmem_of_init_fn) -#ifdef CONFIG_OF_RESERVED_MEM - int of_reserved_mem_device_init_by_idx(struct device *dev, struct device_node *np, int idx); int of_reserved_mem_device_init_by_name(struct device *dev, @@ -41,6 +41,10 @@ void of_reserved_mem_device_release(struct device *dev); struct reserved_mem *of_reserved_mem_lookup(struct device_node *np); #else + +#define RESERVEDMEM_OF_DECLARE(name, compat, init) \ + _OF_DECLARE_STUB(reservedmem, name, compat, init, reservedmem_of_init_fn) + static inline int of_reserved_mem_device_init_by_idx(struct device *dev, struct device_node *np, int idx) { -- cgit v1.2.3 From 0d9f837c6958a4c14e6bcb5c5edf6c851d65f507 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 17 Jun 2021 16:22:13 +0200 Subject: driver core: Export device_driver_attach() This is intended as a replacement API for device_bind_driver(). It has at least the following benefits: - Internal locking. Few of the users of device_bind_driver() follow the locking rules - Calls device driver probe() internally. Notably this means that devm support for probe works correctly as probe() error will call devres_release_all() - struct device_driver -> dev_groups is supported - Simplified calling convention, no need to manually call probe(). The general usage is for situations that already know what driver to bind and need to ensure the bind is synchronized with other logic. Call device_driver_attach() after device_add(). If probe() returns a failure then this will be preserved up through to the error return of device_driver_attach(). Signed-off-by: Jason Gunthorpe Signed-off-by: Christoph Hellwig Reviewed-by: Cornelia Huck Reviewed-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20210617142218.1877096-6-hch@lst.de Signed-off-by: Alex Williamson --- include/linux/device.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index f1a00040fa53..d8b9c9e7d493 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -845,6 +845,8 @@ static inline void *dev_get_platdata(const struct device *dev) * Manual binding of a device to driver. See drivers/base/bus.c * for information on use. */ +int __must_check device_driver_attach(struct device_driver *drv, + struct device *dev); int __must_check device_bind_driver(struct device *dev); void device_release_driver(struct device *dev); int __must_check device_attach(struct device *dev); -- cgit v1.2.3 From 88a21f265ce50a17e6e71e3fb4467625cf234c5a Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 17 Jun 2021 16:22:15 +0200 Subject: vfio/mdev: Allow the mdev_parent_ops to specify the device driver to bind This allows a mdev driver to opt out of using vfio_mdev.c, instead the driver will provide a 'struct mdev_driver' and register directly with the driver core. Much of mdev_parent_ops becomes unused in this mode: - create()/remove() are done via the mdev_driver probe()/remove() - mdev_attr_groups becomes mdev_driver driver.dev_groups - Wrapper function callbacks are replaced with the same ones from struct vfio_device_ops Signed-off-by: Jason Gunthorpe Signed-off-by: Christoph Hellwig Reviewed-by: Cornelia Huck Reviewed-by: Greg Kroah-Hartman Reviewed-by: Kirti Wankhede Link: https://lore.kernel.org/r/20210617142218.1877096-8-hch@lst.de Signed-off-by: Alex Williamson --- include/linux/mdev.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mdev.h b/include/linux/mdev.h index 1fb34ea394ad..3a38598c2605 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -55,6 +55,7 @@ struct device *mtype_get_parent_dev(struct mdev_type *mtype); * register the device to mdev module. * * @owner: The module owner. + * @device_driver: Which device driver to probe() on newly created devices * @dev_attr_groups: Attributes of the parent device. * @mdev_attr_groups: Attributes of the mediated device. * @supported_type_groups: Attributes to define supported types. It is mandatory @@ -103,6 +104,7 @@ struct device *mtype_get_parent_dev(struct mdev_type *mtype); **/ struct mdev_parent_ops { struct module *owner; + struct mdev_driver *device_driver; const struct attribute_group **dev_attr_groups; const struct attribute_group **mdev_attr_groups; struct attribute_group **supported_type_groups; -- cgit v1.2.3 From a3fa449ffcf5bcf9c3dddf62c11599cdc79ef54a Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Mon, 21 Jun 2021 22:08:49 +0200 Subject: net: handle ARPHRD_IP6GRE in dev_is_mac_header_xmit() Similar to commit 3b707c3008ca ("net: dev_is_mac_header_xmit() true for ARPHRD_RAWIP"), add ARPHRD_IP6GRE to dev_is_mac_header_xmit(), to make ip6gre compatible with act_mirred and __bpf_redirect(). Signed-off-by: Guillaume Nault Signed-off-by: David S. Miller --- include/linux/if_arp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h index bf5c5f32c65e..b712217f7030 100644 --- a/include/linux/if_arp.h +++ b/include/linux/if_arp.h @@ -48,6 +48,7 @@ static inline bool dev_is_mac_header_xmit(const struct net_device *dev) case ARPHRD_TUNNEL6: case ARPHRD_SIT: case ARPHRD_IPGRE: + case ARPHRD_IP6GRE: case ARPHRD_VOID: case ARPHRD_NONE: case ARPHRD_RAWIP: -- cgit v1.2.3 From 9a1ac95a59d0724ffac2181a98b232c3f94f49f5 Mon Sep 17 00:00:00 2001 From: Aharon Landau Date: Wed, 16 Jun 2021 10:57:38 +0300 Subject: RDMA/mlx5: Refactor get_ts_format functions to simplify code QPC, SQC and RQC timestamp formats and capabilities are always equal because they represent general hardware support. So instead of code duplication, let's merge them into general enum and logic. Signed-off-by: Aharon Landau Reviewed-by: Maor Gottlieb Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 36 ++++++------------------------------ include/linux/mlx5/qp.h | 4 ++-- 2 files changed, 8 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index eb86e80e4643..668e1d016066 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -953,9 +953,9 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { }; enum { - MLX5_QP_TIMESTAMP_FORMAT_CAP_FREE_RUNNING = 0x0, - MLX5_QP_TIMESTAMP_FORMAT_CAP_REAL_TIME = 0x1, - MLX5_QP_TIMESTAMP_FORMAT_CAP_FREE_RUNNING_AND_REAL_TIME = 0x2, + MLX5_TIMESTAMP_FORMAT_CAP_FREE_RUNNING = 0x0, + MLX5_TIMESTAMP_FORMAT_CAP_REAL_TIME = 0x1, + MLX5_TIMESTAMP_FORMAT_CAP_FREE_RUNNING_AND_REAL_TIME = 0x2, }; struct mlx5_ifc_roce_cap_bits { @@ -1296,18 +1296,6 @@ enum { MLX5_STEERING_FORMAT_CONNECTX_6DX = 1, }; -enum { - MLX5_SQ_TIMESTAMP_FORMAT_CAP_FREE_RUNNING = 0x0, - MLX5_SQ_TIMESTAMP_FORMAT_CAP_REAL_TIME = 0x1, - MLX5_SQ_TIMESTAMP_FORMAT_CAP_FREE_RUNNING_AND_REAL_TIME = 0x2, -}; - -enum { - MLX5_RQ_TIMESTAMP_FORMAT_CAP_FREE_RUNNING = 0x0, - MLX5_RQ_TIMESTAMP_FORMAT_CAP_REAL_TIME = 0x1, - MLX5_RQ_TIMESTAMP_FORMAT_CAP_FREE_RUNNING_AND_REAL_TIME = 0x2, -}; - struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_0[0x1f]; u8 vhca_resource_manager[0x1]; @@ -2944,9 +2932,9 @@ enum { }; enum { - MLX5_QPC_TIMESTAMP_FORMAT_FREE_RUNNING = 0x0, - MLX5_QPC_TIMESTAMP_FORMAT_DEFAULT = 0x1, - MLX5_QPC_TIMESTAMP_FORMAT_REAL_TIME = 0x2, + MLX5_TIMESTAMP_FORMAT_FREE_RUNNING = 0x0, + MLX5_TIMESTAMP_FORMAT_DEFAULT = 0x1, + MLX5_TIMESTAMP_FORMAT_REAL_TIME = 0x2, }; struct mlx5_ifc_qpc_bits { @@ -3396,12 +3384,6 @@ enum { MLX5_SQC_STATE_ERR = 0x3, }; -enum { - MLX5_SQC_TIMESTAMP_FORMAT_FREE_RUNNING = 0x0, - MLX5_SQC_TIMESTAMP_FORMAT_DEFAULT = 0x1, - MLX5_SQC_TIMESTAMP_FORMAT_REAL_TIME = 0x2, -}; - struct mlx5_ifc_sqc_bits { u8 rlky[0x1]; u8 cd_master[0x1]; @@ -3507,12 +3489,6 @@ enum { MLX5_RQC_STATE_ERR = 0x3, }; -enum { - MLX5_RQC_TIMESTAMP_FORMAT_FREE_RUNNING = 0x0, - MLX5_RQC_TIMESTAMP_FORMAT_DEFAULT = 0x1, - MLX5_RQC_TIMESTAMP_FORMAT_REAL_TIME = 0x2, -}; - struct mlx5_ifc_rqc_bits { u8 rlky[0x1]; u8 delay_drop_en[0x1]; diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index b7deb790f257..61e48d459b23 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -550,8 +550,8 @@ static inline const char *mlx5_qp_state_str(int state) static inline int mlx5_get_qp_default_ts(struct mlx5_core_dev *dev) { return !MLX5_CAP_ROCE(dev, qp_ts_format) ? - MLX5_QPC_TIMESTAMP_FORMAT_FREE_RUNNING : - MLX5_QPC_TIMESTAMP_FORMAT_DEFAULT; + MLX5_TIMESTAMP_FORMAT_FREE_RUNNING : + MLX5_TIMESTAMP_FORMAT_DEFAULT; } #endif /* MLX5_QP_H */ -- cgit v1.2.3 From 766c268bc6d39b8124e50d075a36b8a3305bc8e2 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Thu, 17 Jun 2021 11:56:50 +0206 Subject: lib/dump_stack: move cpu lock to printk.c dump_stack() implements its own cpu-reentrant spinning lock to best-effort serialize stack traces in the printk log. However, there are other functions (such as show_regs()) that can also benefit from this serialization. Move the cpu-reentrant spinning lock (cpu lock) into new helper functions printk_cpu_lock_irqsave()/printk_cpu_unlock_irqrestore() so that it is available for others as well. For !CONFIG_SMP the cpu lock is a NOP. Note that having multiple cpu locks in the system can easily lead to deadlock. Code needing a cpu lock should use the printk cpu lock, since the printk cpu lock could be acquired from any code and any context. Also note that it is not necessary for a cpu lock to disable interrupts. However, in upcoming work this cpu lock will be used for emergency tasks (for example, atomic consoles during kernel crashes) and any interruptions while holding the cpu lock should be avoided if possible. Signed-off-by: John Ogness Reviewed-by: Sergey Senozhatsky Reviewed-by: Petr Mladek [pmladek@suse.com: Backported on top of 5.13-rc1.] Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20210617095051.4808-2-john.ogness@linutronix.de --- include/linux/printk.h | 41 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index fe7eb2351610..1790a5521fd9 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -282,6 +282,47 @@ static inline void printk_safe_flush_on_panic(void) } #endif +#ifdef CONFIG_SMP +extern int __printk_cpu_trylock(void); +extern void __printk_wait_on_cpu_lock(void); +extern void __printk_cpu_unlock(void); + +/** + * printk_cpu_lock_irqsave() - Acquire the printk cpu-reentrant spinning + * lock and disable interrupts. + * @flags: Stack-allocated storage for saving local interrupt state, + * to be passed to printk_cpu_unlock_irqrestore(). + * + * If the lock is owned by another CPU, spin until it becomes available. + * Interrupts are restored while spinning. + */ +#define printk_cpu_lock_irqsave(flags) \ + for (;;) { \ + local_irq_save(flags); \ + if (__printk_cpu_trylock()) \ + break; \ + local_irq_restore(flags); \ + __printk_wait_on_cpu_lock(); \ + } + +/** + * printk_cpu_unlock_irqrestore() - Release the printk cpu-reentrant spinning + * lock and restore interrupts. + * @flags: Caller's saved interrupt state, from printk_cpu_lock_irqsave(). + */ +#define printk_cpu_unlock_irqrestore(flags) \ + do { \ + __printk_cpu_unlock(); \ + local_irq_restore(flags); \ + } while (0) \ + +#else + +#define printk_cpu_lock_irqsave(flags) ((void)flags) +#define printk_cpu_unlock_irqrestore(flags) ((void)flags) + +#endif /* CONFIG_SMP */ + extern int kptr_restrict; /** -- cgit v1.2.3 From 0c79378c01999bd60057c475f163ec807c24891f Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Mon, 21 Jun 2021 19:53:55 +0200 Subject: spi: add ancillary device support Introduce support for ancillary devices, similar to existing implementation for I2C. This is useful for devices having multiple chip-selects, for example some microcontrollers provide a normal SPI interface and a flashing SPI interface. Signed-off-by: Sebastian Reichel Link: https://lore.kernel.org/r/20210621175359.126729-2-sebastian.reichel@collabora.com Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index f924160e995f..3ada36175e5f 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -299,6 +299,8 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) driver_unregister(&sdrv->driver); } +extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 chip_select); + /* use a define to avoid include chaining to get THIS_MODULE */ #define spi_register_driver(driver) \ __spi_register_driver(THIS_MODULE, driver) -- cgit v1.2.3 From 7560c02bdffb7c52d1457fa551b9e745d4b9e754 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 27 May 2021 12:01:20 -0700 Subject: clocksource: Check per-CPU clock synchronization when marked unstable Some sorts of per-CPU clock sources have a history of going out of synchronization with each other. However, this problem has purportedy been solved in the past ten years. Except that it is all too possible that the problem has instead simply been made less likely, which might mean that some of the occasional "Marking clocksource 'tsc' as unstable" messages might be due to desynchronization. How would anyone know? Therefore apply CPU-to-CPU synchronization checking to newly unstable clocksource that are marked with the new CLOCK_SOURCE_VERIFY_PERCPU flag. Lists of desynchronized CPUs are printed, with the caveat that if it is the reporting CPU that is itself desynchronized, it will appear that all the other clocks are wrong. Just like in real life. Reported-by: Chris Mason Signed-off-by: Paul E. McKenney Signed-off-by: Thomas Gleixner Acked-by: Feng Tang Link: https://lore.kernel.org/r/20210527190124.440372-2-paulmck@kernel.org --- include/linux/clocksource.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index d6ab416ee2d2..7f83d51c0fd7 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -137,7 +137,7 @@ struct clocksource { #define CLOCK_SOURCE_UNSTABLE 0x40 #define CLOCK_SOURCE_SUSPEND_NONSTOP 0x80 #define CLOCK_SOURCE_RESELECT 0x100 - +#define CLOCK_SOURCE_VERIFY_PERCPU 0x200 /* simplify initialization of mask field */ #define CLOCKSOURCE_MASK(bits) GENMASK_ULL((bits) - 1, 0) -- cgit v1.2.3 From 2e27e793e280ff12cb5c202a1214c08b0d3a0f26 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 27 May 2021 12:01:22 -0700 Subject: clocksource: Reduce clocksource-skew threshold Currently, WATCHDOG_THRESHOLD is set to detect a 62.5-millisecond skew in a 500-millisecond WATCHDOG_INTERVAL. This requires that clocks be skewed by more than 12.5% in order to be marked unstable. Except that a clock that is skewed by that much is probably destroying unsuspecting software right and left. And given that there are now checks for false-positive skews due to delays between reading the two clocks, it should be possible to greatly decrease WATCHDOG_THRESHOLD, at least for fine-grained clocks such as TSC. Therefore, add a new uncertainty_margin field to the clocksource structure that contains the maximum uncertainty in nanoseconds for the corresponding clock. This field may be initialized manually, as it is for clocksource_tsc_early and clocksource_jiffies, which is copied to refined_jiffies. If the field is not initialized manually, it will be computed at clock-registry time as the period of the clock in question based on the scale and freq parameters to __clocksource_update_freq_scale() function. If either of those two parameters are zero, the tens-of-milliseconds WATCHDOG_THRESHOLD is used as a cowardly alternative to dividing by zero. No matter how the uncertainty_margin field is calculated, it is bounded below by twice WATCHDOG_MAX_SKEW, that is, by 100 microseconds. Note that manually initialized uncertainty_margin fields are not adjusted, but there is a WARN_ON_ONCE() that triggers if any such field is less than twice WATCHDOG_MAX_SKEW. This WARN_ON_ONCE() is intended to discourage production use of the one-nanosecond uncertainty_margin values that are used to test the clock-skew code itself. The actual clock-skew check uses the sum of the uncertainty_margin fields of the two clocksource structures being compared. Integer overflow is avoided because the largest computed value of the uncertainty_margin fields is one billion (10^9), and double that value fits into an unsigned int. However, if someone manually specifies (say) UINT_MAX, they will get what they deserve. Note that the refined_jiffies uncertainty_margin field is initialized to TICK_NSEC, which means that skew checks involving this clocksource will be sufficently forgiving. In a similar vein, the clocksource_tsc_early uncertainty_margin field is initialized to 32*NSEC_PER_MSEC, which replicates the current behavior and allows custom setting if needed in order to address the rare skews detected for this clocksource in current mainline. Suggested-by: Thomas Gleixner Signed-off-by: Paul E. McKenney Signed-off-by: Thomas Gleixner Acked-by: Feng Tang Link: https://lore.kernel.org/r/20210527190124.440372-4-paulmck@kernel.org --- include/linux/clocksource.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 7f83d51c0fd7..895203727cb5 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -43,6 +43,8 @@ struct module; * @shift: Cycle to nanosecond divisor (power of two) * @max_idle_ns: Maximum idle time permitted by the clocksource (nsecs) * @maxadj: Maximum adjustment value to mult (~11%) + * @uncertainty_margin: Maximum uncertainty in nanoseconds per half second. + * Zero says to use default WATCHDOG_THRESHOLD. * @archdata: Optional arch-specific data * @max_cycles: Maximum safe cycle value which won't overflow on * multiplication @@ -98,6 +100,7 @@ struct clocksource { u32 shift; u64 max_idle_ns; u32 maxadj; + u32 uncertainty_margin; #ifdef CONFIG_ARCH_CLOCKSOURCE_DATA struct arch_clocksource_data archdata; #endif -- cgit v1.2.3 From 1253b9b87e42ab6a3d5c2cb27af2bdd67d7e50ff Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 27 May 2021 12:01:23 -0700 Subject: clocksource: Provide kernel module to test clocksource watchdog When the clocksource watchdog marks a clock as unstable, this might be due to that clock being unstable or it might be due to delays that happen to occur between the reads of the two clocks. It would be good to have a way of testing the clocksource watchdog's ability to distinguish between these two causes of clock skew and instability. Therefore, provide a new clocksource-wdtest module selected by a new TEST_CLOCKSOURCE_WATCHDOG Kconfig option. This module has a single module parameter named "holdoff" that provides the number of seconds of delay before testing should start, which defaults to zero when built as a module and to 10 seconds when built directly into the kernel. Very large systems that boot slowly may need to increase the value of this module parameter. This module uses hand-crafted clocksource structures to do its testing, thus avoiding messing up timing for the rest of the kernel and for user applications. This module first verifies that the ->uncertainty_margin field of the clocksource structures are set sanely. It then tests the delay-detection capability of the clocksource watchdog, increasing the number of consecutive delays injected, first provoking console messages complaining about the delays and finally forcing a clock-skew event. Unexpected test results cause at least one WARN_ON_ONCE() console splat. If there are no splats, the test has passed. Finally, it fuzzes the value returned from a clocksource to test the clocksource watchdog's ability to detect time skew. This module checks the state of its clocksource after each test, and uses WARN_ON_ONCE() to emit a console splat if there are any failures. This should enable all types of test frameworks to detect any such failures. This facility is intended for diagnostic use only, and should be avoided on production systems. Reported-by: Chris Mason Suggested-by: Thomas Gleixner Signed-off-by: Paul E. McKenney Signed-off-by: Thomas Gleixner Tested-by: Feng Tang Link: https://lore.kernel.org/r/20210527190124.440372-5-paulmck@kernel.org --- include/linux/clocksource.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 895203727cb5..1d42d4b17327 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -291,4 +291,7 @@ static inline void timer_probe(void) {} #define TIMER_ACPI_DECLARE(name, table_id, fn) \ ACPI_DECLARE_PROBE_ENTRY(timer, name, table_id, 0, NULL, 0, fn) +extern ulong max_cswd_read_retries; +void clocksource_verify_percpu(struct clocksource *cs); + #endif /* _LINUX_CLOCKSOURCE_H */ -- cgit v1.2.3 From 89bcadc8f94bd6e6361b5c803ec6f40132e8bace Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Mon, 21 Jun 2021 17:17:58 +0200 Subject: dma-buf: Document non-dynamic exporter expectations better MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Christian and me realized we have a pretty massive disconnect about different interpretations of what dma_resv is used for by different drivers. The discussion is much, much bigger than this change here, but this is an important one: Non-dynamic exporters must guarantee that the memory they return is ready for use. They cannot expect importers to wait for the exclusive fence. Only dynamic importers are required to obey the dma_resv fences strictly (and more patches are needed to define exactly what this means). Christian has patches to update nouvea, radeon and amdgpu. The only other driver using both ttm and supporting dma-buf export is qxl, which only uses synchronous ttm_bo_move. v2: To hammer this in document that dynamic importers _must_ wait for the exclusive fence after having called dma_buf_map_attachment. Reviewed-by: Christian König Cc: Christian König Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210621151758.2347474-1-daniel.vetter@ffwll.ch --- include/linux/dma-buf.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 342585bd6dff..92eec38a03aa 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -96,6 +96,12 @@ struct dma_buf_ops { * This is called automatically for non-dynamic importers from * dma_buf_attach(). * + * Note that similar to non-dynamic exporters in their @map_dma_buf + * callback the driver must guarantee that the memory is available for + * use and cleared of any old data by the time this function returns. + * Drivers which pipeline their buffer moves internally must wait for + * all moves and clears to complete. + * * Returns: * * 0 on success, negative error code on failure. @@ -144,6 +150,15 @@ struct dma_buf_ops { * This is always called with the dmabuf->resv object locked when * the dynamic_mapping flag is true. * + * Note that for non-dynamic exporters the driver must guarantee that + * that the memory is available for use and cleared of any old data by + * the time this function returns. Drivers which pipeline their buffer + * moves internally must wait for all moves and clears to complete. + * Dynamic exporters do not need to follow this rule: For non-dynamic + * importers the buffer is already pinned through @pin, which has the + * same requirements. Dynamic importers otoh are required to obey the + * dma_resv fences. + * * Returns: * * A &sg_table scatter list of or the backing storage of the DMA buffer, -- cgit v1.2.3 From 62a6ef6a996f5eec73d30d079573a1fa8f95fcd9 Mon Sep 17 00:00:00 2001 From: Marcin Wojtas Date: Mon, 21 Jun 2021 19:30:24 +0200 Subject: net: mdiobus: Introduce fwnode_mdbiobus_register() This patch introduces a new helper function that wraps acpi_/of_ mdiobus_register() and allows its usage via common fwnode_ interface. Fall back to raw mdiobus_register() in case CONFIG_FWNODE_MDIO is not enabled, in order to satisfy compatibility in all future user drivers. Signed-off-by: Marcin Wojtas Signed-off-by: David S. Miller --- include/linux/fwnode_mdio.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fwnode_mdio.h b/include/linux/fwnode_mdio.h index faf603c48c86..13d4ae8fee0a 100644 --- a/include/linux/fwnode_mdio.h +++ b/include/linux/fwnode_mdio.h @@ -16,6 +16,7 @@ int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, int fwnode_mdiobus_register_phy(struct mii_bus *bus, struct fwnode_handle *child, u32 addr); +int fwnode_mdiobus_register(struct mii_bus *bus, struct fwnode_handle *fwnode); #else /* CONFIG_FWNODE_MDIO */ int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, struct phy_device *phy, @@ -30,6 +31,17 @@ static inline int fwnode_mdiobus_register_phy(struct mii_bus *bus, { return -EINVAL; } + +static inline int fwnode_mdiobus_register(struct mii_bus *bus, + struct fwnode_handle *fwnode) +{ + /* + * Fall back to mdiobus_register() function to register a bus. + * This way, we don't have to keep compat bits around in drivers. + */ + + return mdiobus_register(mdio); +} #endif #endif /* __LINUX_FWNODE_MDIO_H */ -- cgit v1.2.3 From 9f0248ea476ee59d336d7c8bf1a5d0919d93d030 Mon Sep 17 00:00:00 2001 From: Sergey Ryazanov Date: Tue, 22 Jun 2021 01:50:57 +0300 Subject: wwan: core: no more hold netdev ops owning module The WWAN netdev ops owner holding was used to protect from the unexpected memory disappear. This approach causes a dependency cycle (driver -> core -> driver) and effectively prevents a WWAN driver unloading. E.g. WWAN hwsim could not be unloaded until all simulated devices are removed: ~# modprobe wwan_hwsim devices=2 ~# lsmod | grep wwan wwan_hwsim 16384 2 wwan 20480 1 wwan_hwsim ~# rmmod wwan_hwsim rmmod: ERROR: Module wwan_hwsim is in use ~# echo > /sys/kernel/debug/wwan_hwsim/hwsim0/destroy ~# echo > /sys/kernel/debug/wwan_hwsim/hwsim1/destroy ~# lsmod | grep wwan wwan_hwsim 16384 0 wwan 20480 1 wwan_hwsim ~# rmmod wwan_hwsim For a real device driver this will cause an inability to unload module until a served device is physically detached. Since the last commit we are removing all child netdev(s) when a driver unregister the netdev ops. This allows us to permit the driver unloading, since any sane driver will call ops unregistering on a device deinitialization. So, remove the holding of an ops owner to make it easier to unload a driver module. The owner field has also beed removed from the ops structure as there are no more users of this field. Signed-off-by: Sergey Ryazanov Reviewed-by: Loic Poulain Signed-off-by: David S. Miller --- include/linux/wwan.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/wwan.h b/include/linux/wwan.h index 34222230360c..e1981ea3a2fd 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -128,14 +128,12 @@ void *wwan_port_get_drvdata(struct wwan_port *port); /** * struct wwan_ops - WWAN device ops - * @owner: module owner of the WWAN ops * @priv_size: size of private netdev data area * @setup: set up a new netdev * @newlink: register the new netdev * @dellink: remove the given netdev */ struct wwan_ops { - struct module *owner; unsigned int priv_size; void (*setup)(struct net_device *dev); int (*newlink)(void *ctxt, struct net_device *dev, -- cgit v1.2.3 From ca374290aaade741a4781ae5f6e1ba7515e4e5fa Mon Sep 17 00:00:00 2001 From: Sergey Ryazanov Date: Tue, 22 Jun 2021 01:50:58 +0300 Subject: wwan: core: support default netdev creation Most, if not each WWAN device driver will create a netdev for the default data channel. Therefore, add an option for the WWAN netdev ops registration function to create a default netdev for the WWAN device. A WWAN device driver should pass a default data channel link id to the ops registering function to request the creation of a default netdev, or a special value WWAN_NO_DEFAULT_LINK to inform the WWAN core that the default netdev should not be created. For now, only wwan_hwsim utilize the default link creation option. Other drivers will be reworked next. Signed-off-by: Sergey Ryazanov CC: M Chetan Kumar CC: Intel Corporation Signed-off-by: David S. Miller --- include/linux/wwan.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/wwan.h b/include/linux/wwan.h index e1981ea3a2fd..91590db70a12 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -126,6 +126,12 @@ void wwan_port_txon(struct wwan_port *port); */ void *wwan_port_get_drvdata(struct wwan_port *port); +/* + * Used to indicate that the WWAN core should not create a default network + * link. + */ +#define WWAN_NO_DEFAULT_LINK U32_MAX + /** * struct wwan_ops - WWAN device ops * @priv_size: size of private netdev data area @@ -143,7 +149,7 @@ struct wwan_ops { }; int wwan_register_ops(struct device *parent, const struct wwan_ops *ops, - void *ctxt); + void *ctxt, u32 def_link_id); void wwan_unregister_ops(struct device *parent); -- cgit v1.2.3 From 699409240389c2994e5fa1cb7d7599129bc7cfdf Mon Sep 17 00:00:00 2001 From: Sergey Ryazanov Date: Tue, 22 Jun 2021 01:51:00 +0300 Subject: wwan: core: add WWAN common private data for netdev The WWAN core not only multiplex the netdev configuration data, but process it too, and needs some space to store its private data associated with the netdev. Add a structure to keep common WWAN core data. The structure will be stored inside the netdev private data before WWAN driver private data and have a field to make it easier to access the driver data. Also add a helper function that simplifies drivers access to their data. At the moment we use the common WWAN private data to store the WWAN data link (channel) id at the time the link is created, and report it back to user using the .fill_info() RTNL callback. This should help the user to be aware which network interface is bound to which WWAN device data channel. Signed-off-by: Sergey Ryazanov CC: M Chetan Kumar CC: Intel Corporation Signed-off-by: David S. Miller --- include/linux/wwan.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/wwan.h b/include/linux/wwan.h index 91590db70a12..9fac819f92e3 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -9,6 +9,7 @@ #include #include #include +#include /** * enum wwan_port_type - WWAN port types @@ -126,6 +127,23 @@ void wwan_port_txon(struct wwan_port *port); */ void *wwan_port_get_drvdata(struct wwan_port *port); +/** + * struct wwan_netdev_priv - WWAN core network device private data + * @link_id: WWAN device data link id + * @drv_priv: driver private data area, size is determined in &wwan_ops + */ +struct wwan_netdev_priv { + u32 link_id; + + /* must be last */ + u8 drv_priv[] __aligned(sizeof(void *)); +}; + +static inline void *wwan_netdev_drvpriv(struct net_device *dev) +{ + return ((struct wwan_netdev_priv *)netdev_priv(dev))->drv_priv; +} + /* * Used to indicate that the WWAN core should not create a default network * link. -- cgit v1.2.3 From b8c48be23c2d03834fe01c3ea757d9df8b97013d Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 22 Jun 2021 09:50:50 +0300 Subject: ethtool: Use kernel data types for internal EEPROM struct The struct is not visible to user space and therefore should not use the user visible data types. Instead, use internal data types like other structures in the file. Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/linux/ethtool.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index e030f7510cd3..29dbb603bc91 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -401,12 +401,12 @@ struct ethtool_rmon_stats { * required information to the driver. */ struct ethtool_module_eeprom { - __u32 offset; - __u32 length; - __u8 page; - __u8 bank; - __u8 i2c_address; - __u8 *data; + u32 offset; + u32 length; + u8 page; + u8 bank; + u8 i2c_address; + u8 *data; }; /** -- cgit v1.2.3 From 380d53c45ff21f66870ee965b62613137f9d010d Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Mon, 21 Jun 2021 16:18:20 -0700 Subject: compiler_attributes.h: define __no_profile, add to noinstr noinstr implies that we would like the compiler to avoid instrumenting a function. Add support for the compiler attribute no_profile_instrument_function to compiler_attributes.h, then add __no_profile to the definition of noinstr. Link: https://lore.kernel.org/lkml/20210614162018.GD68749@worktop.programming.kicks-ass.net/ Link: https://reviews.llvm.org/D104257 Link: https://reviews.llvm.org/D104475 Link: https://reviews.llvm.org/D104658 Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=80223 Reviewed-by: Fangrui Song Reviewed-by: Miguel Ojeda Suggested-by: Peter Zijlstra Signed-off-by: Nick Desaulniers Reviewed-by: Nathan Chancellor Acked-by: Peter Zijlstra (Intel) Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20210621231822.2848305-2-ndesaulniers@google.com --- include/linux/compiler_attributes.h | 13 +++++++++++++ include/linux/compiler_types.h | 2 +- 2 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index c043b8d2b17b..225511b17223 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -33,6 +33,7 @@ # define __GCC4_has_attribute___externally_visible__ 1 # define __GCC4_has_attribute___no_caller_saved_registers__ 0 # define __GCC4_has_attribute___noclone__ 1 +# define __GCC4_has_attribute___no_profile_instrument_function__ 0 # define __GCC4_has_attribute___nonstring__ 0 # define __GCC4_has_attribute___no_sanitize_address__ (__GNUC_MINOR__ >= 8) # define __GCC4_has_attribute___no_sanitize_undefined__ (__GNUC_MINOR__ >= 9) @@ -237,6 +238,18 @@ # define __nonstring #endif +/* + * Optional: only supported since GCC >= 7.1, clang >= 13.0. + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-no_005fprofile_005finstrument_005ffunction-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#no-profile-instrument-function + */ +#if __has_attribute(__no_profile_instrument_function__) +# define __no_profile __attribute__((__no_profile_instrument_function__)) +#else +# define __no_profile +#endif + /* * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-noreturn-function-attribute * clang: https://clang.llvm.org/docs/AttributeReference.html#noreturn diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index d29bda7f6ebd..d509169860f1 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -210,7 +210,7 @@ struct ftrace_likely_data { /* Section for code which can't be instrumented at all */ #define noinstr \ noinline notrace __attribute((__section__(".noinstr.text"))) \ - __no_kcsan __no_sanitize_address + __no_kcsan __no_sanitize_address __no_profile #endif /* __KERNEL__ */ -- cgit v1.2.3 From ae4d682dfd3350d9836dafeed1fc5aa1e27c4963 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Mon, 21 Jun 2021 16:18:21 -0700 Subject: compiler_attributes.h: cleanups for GCC 4.9+ Since commit 6ec4476ac825 ("Raise gcc version requirement to 4.9") we no longer support building the kernel with GCC 4.8; drop the preprocess checks for __GNUC_MINOR__ version. It's implied that if __GNUC_MAJOR__ is 4, then the only supported version of __GNUC_MINOR__ left is 9. Signed-off-by: Nick Desaulniers Reviewed-by: Nathan Chancellor Acked-by: Peter Zijlstra (Intel) Reviewed-by: Miguel Ojeda Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20210621231822.2848305-3-ndesaulniers@google.com --- include/linux/compiler_attributes.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 225511b17223..84b1c970acb3 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -27,7 +27,7 @@ */ #ifndef __has_attribute # define __has_attribute(x) __GCC4_has_attribute_##x -# define __GCC4_has_attribute___assume_aligned__ (__GNUC_MINOR__ >= 9) +# define __GCC4_has_attribute___assume_aligned__ 1 # define __GCC4_has_attribute___copy__ 0 # define __GCC4_has_attribute___designated_init__ 0 # define __GCC4_has_attribute___externally_visible__ 1 @@ -35,8 +35,8 @@ # define __GCC4_has_attribute___noclone__ 1 # define __GCC4_has_attribute___no_profile_instrument_function__ 0 # define __GCC4_has_attribute___nonstring__ 0 -# define __GCC4_has_attribute___no_sanitize_address__ (__GNUC_MINOR__ >= 8) -# define __GCC4_has_attribute___no_sanitize_undefined__ (__GNUC_MINOR__ >= 9) +# define __GCC4_has_attribute___no_sanitize_address__ 1 +# define __GCC4_has_attribute___no_sanitize_undefined__ 1 # define __GCC4_has_attribute___fallthrough__ 0 #endif -- cgit v1.2.3 From 745a32117b5a0799ce1dd28d5a74dc2b7bf37692 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Tue, 22 Jun 2021 14:04:47 -0400 Subject: sctp: add pad chunk and its make function and event table This chunk is defined in rfc4820#section-3, and used to pad an SCTP packet. The receiver must discard this chunk and continue processing the rest of the chunks in the packet. Add it now, as it will be bundled with a heartbeat chunk to probe pmtu in the following patches. Signed-off-by: Xin Long Acked-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/linux/sctp.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index bb1926589693..a86e852507b3 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -98,6 +98,7 @@ enum sctp_cid { SCTP_CID_I_FWD_TSN = 0xC2, SCTP_CID_ASCONF_ACK = 0x80, SCTP_CID_RECONF = 0x82, + SCTP_CID_PAD = 0x84, }; /* enum */ @@ -410,6 +411,12 @@ struct sctp_heartbeat_chunk { }; +/* PAD chunk could be bundled with heartbeat chunk to probe pmtu */ +struct sctp_pad_chunk { + struct sctp_chunkhdr uh; +}; + + /* For the abort and shutdown ACK we must carry the init tag in the * common header. Just the common header is all that is needed with a * chunk descriptor. -- cgit v1.2.3 From 01d5d96542fd4e383da79593f8a3450995ce2257 Mon Sep 17 00:00:00 2001 From: Leah Rumancik Date: Tue, 18 May 2021 15:13:25 +0000 Subject: ext4: add discard/zeroout flags to journal flush Add a flags argument to jbd2_journal_flush to enable discarding or zero-filling the journal blocks while flushing the journal. Signed-off-by: Leah Rumancik Link: https://lore.kernel.org/r/20210518151327.130198-1-leah.rumancik@gmail.com Signed-off-by: Theodore Ts'o --- include/linux/jbd2.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index db0e1920cb12..8543233b0388 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1370,6 +1370,10 @@ JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit, FAST_COMMIT) * mode */ #define JBD2_FAST_COMMIT_ONGOING 0x100 /* Fast commit is ongoing */ #define JBD2_FULL_COMMIT_ONGOING 0x200 /* Full commit is ongoing */ +#define JBD2_JOURNAL_FLUSH_DISCARD 0x0001 +#define JBD2_JOURNAL_FLUSH_ZEROOUT 0x0002 +#define JBD2_JOURNAL_FLUSH_VALID (JBD2_JOURNAL_FLUSH_DISCARD | \ + JBD2_JOURNAL_FLUSH_ZEROOUT) /* * Function declarations for the journaling transaction and buffer @@ -1500,7 +1504,7 @@ extern int jbd2_journal_invalidatepage(journal_t *, struct page *, unsigned int, unsigned int); extern int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page); extern int jbd2_journal_stop(handle_t *); -extern int jbd2_journal_flush (journal_t *); +extern int jbd2_journal_flush(journal_t *journal, unsigned int flags); extern void jbd2_journal_lock_updates (journal_t *); extern void jbd2_journal_unlock_updates (journal_t *); -- cgit v1.2.3 From c61404153eb683da9c35aad133131554861ed561 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Tue, 25 May 2021 11:39:35 -0700 Subject: f2fs: introduce FI_COMPRESS_RELEASED instead of using IMMUTABLE bit Once we release compressed blocks, we used to set IMMUTABLE bit. But it turned out it disallows every fs operations which we don't need for compression. Let's just prevent writing data only. Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 5487a80617a3..f93000c3a127 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -229,6 +229,7 @@ struct f2fs_extent { #define F2FS_INLINE_DOTS 0x10 /* file having implicit dot dentries */ #define F2FS_EXTRA_ATTR 0x20 /* file having extra attribute */ #define F2FS_PIN_FILE 0x40 /* file should not be gced */ +#define F2FS_COMPRESS_RELEASED 0x80 /* file released compressed blocks */ struct f2fs_inode { __le16 i_mode; /* file mode */ -- cgit v1.2.3 From 6ce19aff0b8cd386860855185c6cd79337fc4d2b Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Thu, 20 May 2021 19:51:50 +0800 Subject: f2fs: compress: add compress_inode to cache compressed blocks Support to use address space of inner inode to cache compressed block, in order to improve cache hit ratio of random read. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index f93000c3a127..d445150c5350 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -34,6 +34,7 @@ #define F2FS_ROOT_INO(sbi) ((sbi)->root_ino_num) #define F2FS_NODE_INO(sbi) ((sbi)->node_ino_num) #define F2FS_META_INO(sbi) ((sbi)->meta_ino_num) +#define F2FS_COMPRESS_INO(sbi) (NM_I(sbi)->max_nid) #define F2FS_MAX_QUOTAS 3 -- cgit v1.2.3 From 1806239dec0dacde373f0b53f076319f6c6d95cb Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 19 Jun 2021 15:36:30 +0200 Subject: ieee80211: add the value for Category '6' in "rtw_ieee80211_category" Preparation work for removing the "enum rtw_ieee80211_category" in "drivers/staging/rtl8188eu/include/ieee80211.h" and "drivers/staging/rtl8723bs/include/ieee80211.h". This enum is similar to "enum ieee80211_category" from "include/linux/ieee80211.h". However it defines the value '6' as RTW_WLAN_CATEGORY_FT. So add a corresponding value in "ieee80211_category" Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/66be0187869bd7dae1c0b0785a32db695ee9872e.1624108556.git.christophe.jaillet@wanadoo.fr Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 2967437f1b11..67f3e51e7ecc 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2933,6 +2933,7 @@ enum ieee80211_category { WLAN_CATEGORY_BACK = 3, WLAN_CATEGORY_PUBLIC = 4, WLAN_CATEGORY_RADIO_MEASUREMENT = 5, + WLAN_CATEGORY_FAST_BBS_TRANSITION = 6, WLAN_CATEGORY_HT = 7, WLAN_CATEGORY_SA_QUERY = 8, WLAN_CATEGORY_PROTECTED_DUAL_OF_ACTION = 9, -- cgit v1.2.3 From 7da70d6cdf0dbc2c62e4a5759db9b63ef8d90c32 Mon Sep 17 00:00:00 2001 From: Krishnanand Prabhu Date: Fri, 18 Jun 2021 13:41:28 +0300 Subject: ieee80211: define timing measurement in extended capabilities IE Define the bit used for timing measurement support in extended capabilities IE, used for time synchronization. Signed-off-by: Krishnanand Prabhu Signed-off-by: Luca Coelho Link: https://lore.kernel.org/r/iwlwifi.20210618133832.b75f40765538.I92b50e43e29272c97d17ed5f37f216f4caf0f205@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 67f3e51e7ecc..0a0aaa2d5d9e 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -9,7 +9,7 @@ * Copyright (c) 2006, Michael Wu * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH * Copyright (c) 2016 - 2017 Intel Deutschland GmbH - * Copyright (c) 2018 - 2020 Intel Corporation + * Copyright (c) 2018 - 2021 Intel Corporation */ #ifndef LINUX_IEEE80211_H @@ -3111,6 +3111,11 @@ enum ieee80211_tdls_actioncode { */ #define WLAN_EXT_CAPA3_MULTI_BSSID_SUPPORT BIT(6) +/* Timing Measurement protocol for time sync is set in the 7th bit of 3rd byte + * of the @WLAN_EID_EXT_CAPABILITY information element + */ +#define WLAN_EXT_CAPA3_TIMING_MEASUREMENT_SUPPORT BIT(7) + /* TDLS capabilities in the 4th byte of @WLAN_EID_EXT_CAPABILITY */ #define WLAN_EXT_CAPA4_TDLS_BUFFER_STA BIT(4) #define WLAN_EXT_CAPA4_TDLS_PEER_PSM BIT(5) -- cgit v1.2.3 From 9c7c637050b42b6e368bb39b8d0edff728268341 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 18 Jun 2021 13:41:38 +0300 Subject: ieee80211: add defines for HE PHY cap byte 10 One bit out of the previously completely reserved byte 10 in the PHY capabilities is used since 802.11ax D7.0, add a new define for it. Signed-off-by: Johannes Berg Signed-off-by: Luca Coelho Link: https://lore.kernel.org/r/iwlwifi.20210618133832.c026feb3873d.I380f52a05ddb4153bc77ff7f276a3484819f69b2@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 0a0aaa2d5d9e..a6730072d13a 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2179,6 +2179,8 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, #define IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_RESERVED 0xc0 #define IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_MASK 0xc0 +#define IEEE80211_HE_PHY_CAP10_HE_MU_M1RU_MAX_LTF 0x01 + /* 802.11ax HE TX/RX MCS NSS Support */ #define IEEE80211_TX_RX_MCS_NSS_SUPP_HIGHEST_MCS_POS (3) #define IEEE80211_TX_RX_MCS_NSS_SUPP_TX_BITMAP_POS (6) -- cgit v1.2.3 From ab5df7b953d87efddba4f9df83862f7dcb39b8d5 Mon Sep 17 00:00:00 2001 From: Jordan Crouse Date: Thu, 10 Jun 2021 14:44:10 -0700 Subject: iommu/arm-smmu-qcom: Add an adreno-smmu-priv callback to get pagefault info Add a callback in adreno-smmu-priv to read interesting SMMU registers to provide an opportunity for a richer debug experience in the GPU driver. Signed-off-by: Jordan Crouse Signed-off-by: Rob Clark Reviewed-by: Bjorn Andersson Link: https://lore.kernel.org/r/20210610214431.539029-3-robdclark@gmail.com Signed-off-by: Rob Clark --- include/linux/adreno-smmu-priv.h | 31 ++++++++++++++++++++++++++++++- 1 file changed, 30 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/adreno-smmu-priv.h b/include/linux/adreno-smmu-priv.h index a889f28afb42..53fe32fb9214 100644 --- a/include/linux/adreno-smmu-priv.h +++ b/include/linux/adreno-smmu-priv.h @@ -8,6 +8,32 @@ #include +/** + * struct adreno_smmu_fault_info - container for key fault information + * + * @far: The faulting IOVA from ARM_SMMU_CB_FAR + * @ttbr0: The current TTBR0 pagetable from ARM_SMMU_CB_TTBR0 + * @contextidr: The value of ARM_SMMU_CB_CONTEXTIDR + * @fsr: The fault status from ARM_SMMU_CB_FSR + * @fsynr0: The value of FSYNR0 from ARM_SMMU_CB_FSYNR0 + * @fsynr1: The value of FSYNR1 from ARM_SMMU_CB_FSYNR0 + * @cbfrsynra: The value of CBFRSYNRA from ARM_SMMU_GR1_CBFRSYNRA(idx) + * + * This struct passes back key page fault information to the GPU driver + * through the get_fault_info function pointer. + * The GPU driver can use this information to print informative + * log messages and provide deeper GPU specific insight into the fault. + */ +struct adreno_smmu_fault_info { + u64 far; + u64 ttbr0; + u32 contextidr; + u32 fsr; + u32 fsynr0; + u32 fsynr1; + u32 cbfrsynra; +}; + /** * struct adreno_smmu_priv - private interface between adreno-smmu and GPU * @@ -17,6 +43,8 @@ * @set_ttbr0_cfg: Set the TTBR0 config for the GPUs context bank. A * NULL config disables TTBR0 translation, otherwise * TTBR0 translation is enabled with the specified cfg + * @get_fault_info: Called by the GPU fault handler to get information about + * the fault * * The GPU driver (drm/msm) and adreno-smmu work together for controlling * the GPU's SMMU instance. This is by necessity, as the GPU is directly @@ -31,6 +59,7 @@ struct adreno_smmu_priv { const void *cookie; const struct io_pgtable_cfg *(*get_ttbr1_cfg)(const void *cookie); int (*set_ttbr0_cfg)(const void *cookie, const struct io_pgtable_cfg *cfg); + void (*get_fault_info)(const void *cookie, struct adreno_smmu_fault_info *info); }; -#endif /* __ADRENO_SMMU_PRIV_H */ \ No newline at end of file +#endif /* __ADRENO_SMMU_PRIV_H */ -- cgit v1.2.3 From ba6014a4e480c3c2b169438c47273a113c35ba4e Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Thu, 10 Jun 2021 14:44:12 -0700 Subject: iommu/arm-smmu-qcom: Add stall support Add, via the adreno-smmu-priv interface, a way for the GPU to request the SMMU to stall translation on faults, and then later resume the translation, either retrying or terminating the current translation. This will be used on the GPU side to "freeze" the GPU while we snapshot useful state for devcoredump. Signed-off-by: Rob Clark Acked-by: Jordan Crouse Reviewed-by: Bjorn Andersson Link: https://lore.kernel.org/r/20210610214431.539029-5-robdclark@gmail.com Signed-off-by: Rob Clark --- include/linux/adreno-smmu-priv.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/adreno-smmu-priv.h b/include/linux/adreno-smmu-priv.h index 53fe32fb9214..c637e0997f6d 100644 --- a/include/linux/adreno-smmu-priv.h +++ b/include/linux/adreno-smmu-priv.h @@ -45,6 +45,11 @@ struct adreno_smmu_fault_info { * TTBR0 translation is enabled with the specified cfg * @get_fault_info: Called by the GPU fault handler to get information about * the fault + * @set_stall: Configure whether stall on fault (CFCFG) is enabled. Call + * before set_ttbr0_cfg(). If stalling on fault is enabled, + * the GPU driver must call resume_translation() + * @resume_translation: Resume translation after a fault + * * * The GPU driver (drm/msm) and adreno-smmu work together for controlling * the GPU's SMMU instance. This is by necessity, as the GPU is directly @@ -60,6 +65,8 @@ struct adreno_smmu_priv { const struct io_pgtable_cfg *(*get_ttbr1_cfg)(const void *cookie); int (*set_ttbr0_cfg)(const void *cookie, const struct io_pgtable_cfg *cfg); void (*get_fault_info)(const void *cookie, struct adreno_smmu_fault_info *info); + void (*set_stall)(const void *cookie, bool enabled); + void (*resume_translation)(const void *cookie, bool terminate); }; #endif /* __ADRENO_SMMU_PRIV_H */ -- cgit v1.2.3 From 371071131cd1032c1e9172c51234a2a324841cab Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 23 Jun 2021 14:02:11 +0200 Subject: x86/fpu: Use pkru_write_default() in copy_init_fpstate_to_fpregs() There is no point in using copy_init_pkru_to_fpregs() which in turn calls write_pkru(). write_pkru() tries to fiddle with the task's xstate buffer for nothing because the XRSTOR[S](init_fpstate) just cleared the xfeature flag in the xstate header which makes get_xsave_addr() fail. It's a useless exercise anyway because the reinitialization activates the FPU so before the task's xstate buffer can be used again a XRSTOR[S] must happen which in turn dumps the PKRU value. Get rid of the now unused copy_init_pkru_to_fpregs(). Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210623121455.732508792@linutronix.de --- include/linux/pkeys.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pkeys.h b/include/linux/pkeys.h index 2955ba976048..6beb26b7151d 100644 --- a/include/linux/pkeys.h +++ b/include/linux/pkeys.h @@ -44,10 +44,6 @@ static inline bool arch_pkeys_enabled(void) return false; } -static inline void copy_init_pkru_to_fpregs(void) -{ -} - #endif /* ! CONFIG_ARCH_HAS_PKEYS */ #endif /* _LINUX_PKEYS_H */ -- cgit v1.2.3 From 61d1961adf4bd57d1b2c6d94d97323263c470cb2 Mon Sep 17 00:00:00 2001 From: Stephan Gerhold Date: Fri, 18 Jun 2021 13:15:54 +0200 Subject: soc: qcom: smem_state: Add devm_qcom_smem_state_get() It is easy to forget to call qcom_smem_state_put() after a qcom_smem_state_get(). Introduce a devm_qcom_smem_state_get() helper function that automates this so that qcom_smem_state_put() is automatically called when a device is removed. Signed-off-by: Stephan Gerhold Reviewed-by: Bjorn Andersson Link: https://lore.kernel.org/r/20210618111556.53416-1-stephan@gerhold.net Signed-off-by: Bjorn Andersson --- include/linux/soc/qcom/smem_state.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/qcom/smem_state.h b/include/linux/soc/qcom/smem_state.h index 63ad8cddad14..652c0158baac 100644 --- a/include/linux/soc/qcom/smem_state.h +++ b/include/linux/soc/qcom/smem_state.h @@ -14,6 +14,7 @@ struct qcom_smem_state_ops { #ifdef CONFIG_QCOM_SMEM_STATE struct qcom_smem_state *qcom_smem_state_get(struct device *dev, const char *con_id, unsigned *bit); +struct qcom_smem_state *devm_qcom_smem_state_get(struct device *dev, const char *con_id, unsigned *bit); void qcom_smem_state_put(struct qcom_smem_state *); int qcom_smem_state_update_bits(struct qcom_smem_state *state, u32 mask, u32 value); @@ -29,6 +30,13 @@ static inline struct qcom_smem_state *qcom_smem_state_get(struct device *dev, return ERR_PTR(-EINVAL); } +static inline struct qcom_smem_state *devm_qcom_smem_state_get(struct device *dev, + const char *con_id, + unsigned *bit) +{ + return ERR_PTR(-EINVAL); +} + static inline void qcom_smem_state_put(struct qcom_smem_state *state) { } -- cgit v1.2.3 From 2254e49cef7015d7697bd1617d19e620e2788ec5 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Tue, 22 Jun 2021 18:54:57 +0200 Subject: dma-resv: Fix kerneldoc MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Oversight from commit 6edbd6abb783d54f6ac4c3ed5cd9e50cff6c15e9 Author: Christian König Date: Mon May 10 16:14:09 2021 +0200 dma-buf: rename and cleanup dma_resv_get_excl v3 Reviewed-by: Alex Deucher Reviewed-by: Christian König Signed-off-by: Daniel Vetter Cc: Sumit Semwal Cc: "Christian König" Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Link: https://patchwork.freedesktop.org/patch/msgid/20210622165511.3169559-2-daniel.vetter@ffwll.ch --- include/linux/dma-resv.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index 562b885cf9c3..e1ca2080a1ff 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -212,7 +212,7 @@ static inline void dma_resv_unlock(struct dma_resv *obj) } /** - * dma_resv_exclusive - return the object's exclusive fence + * dma_resv_excl_fence - return the object's exclusive fence * @obj: the reservation object * * Returns the exclusive fence (if any). Caller must either hold the objects -- cgit v1.2.3 From 5163ab505e489400b4738b2a5547ec83d2dff7bb Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 17 Jun 2021 15:28:10 +0800 Subject: crypto: api - Move crypto attr definitions out of crypto.h The definitions for crypto_attr-related types and enums are not needed by most Crypto API users. This patch moves them out of crypto.h and into algapi.h/internal.h depending on the extent of their use. Signed-off-by: Herbert Xu --- include/linux/crypto.h | 21 --------------------- 1 file changed, 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 3b9263d6122f..855869e1fd32 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -643,27 +643,6 @@ struct crypto_comp { struct crypto_tfm base; }; -enum { - CRYPTOA_UNSPEC, - CRYPTOA_ALG, - CRYPTOA_TYPE, - __CRYPTOA_MAX, -}; - -#define CRYPTOA_MAX (__CRYPTOA_MAX - 1) - -/* Maximum number of (rtattr) parameters for each template. */ -#define CRYPTO_MAX_ATTRS 32 - -struct crypto_attr_alg { - char name[CRYPTO_MAX_ALG_NAME]; -}; - -struct crypto_attr_type { - u32 type; - u32 mask; -}; - /* * Transform user interface. */ -- cgit v1.2.3 From 2309a05d2abe713f7debc951640b010370c8befb Mon Sep 17 00:00:00 2001 From: Beata Michalska Date: Thu, 3 Jun 2021 15:06:25 +0100 Subject: sched/core: Introduce SD_ASYM_CPUCAPACITY_FULL sched_domain flag Introducing new, complementary to SD_ASYM_CPUCAPACITY, sched_domain topology flag, to distinguish between shed_domains where any CPU capacity asymmetry is detected (SD_ASYM_CPUCAPACITY) and ones where a full set of CPU capacities is visible to all domain members (SD_ASYM_CPUCAPACITY_FULL). With the distinction between full and partial CPU capacity asymmetry, brought in by the newly introduced flag, the scope of the original SD_ASYM_CPUCAPACITY flag gets shifted, still maintaining the existing behaviour when one is detected on a given sched domain, allowing misfit migrations within sched domains that do not observe full range of CPU capacities but still do have members with different capacity values. It loses though it's meaning when it comes to the lowest CPU asymmetry sched_domain level per-cpu pointer, which is to be now denoted by SD_ASYM_CPUCAPACITY_FULL flag. Signed-off-by: Beata Michalska Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Valentin Schneider Reviewed-by: Dietmar Eggemann Link: https://lore.kernel.org/r/20210603140627.8409-2-beata.michalska@arm.com --- include/linux/sched/sd_flags.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h index 34b21e971d77..57bde66d95f7 100644 --- a/include/linux/sched/sd_flags.h +++ b/include/linux/sched/sd_flags.h @@ -90,6 +90,16 @@ SD_FLAG(SD_WAKE_AFFINE, SDF_SHARED_CHILD) */ SD_FLAG(SD_ASYM_CPUCAPACITY, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS) +/* + * Domain members have different CPU capacities spanning all unique CPU + * capacity values. + * + * SHARED_PARENT: Set from the topmost domain down to the first domain where + * all available CPU capacities are visible + * NEEDS_GROUPS: Per-CPU capacity is asymmetric between groups. + */ +SD_FLAG(SD_ASYM_CPUCAPACITY_FULL, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS) + /* * Domain members share CPU capacity (i.e. SMT) * -- cgit v1.2.3 From 8d11cfb0c37547bd6b1cdc7c2653c1e6b5ec5abb Mon Sep 17 00:00:00 2001 From: Vladimir Zapolskiy Date: Sun, 20 Jun 2021 22:11:03 +0300 Subject: dmaengine: imx-sdma: Remove platform data header Since commit 6c5f05a6cd88 ("ARM: imx3: Remove imx3 soc_init()") there are no more users of struct sdma_script_start_addrs outside of the driver itself, thus let's move the struct declaration just to the driver source code and remove the header file as unused one. Signed-off-by: Vladimir Zapolskiy Cc: Fabio Estevam Cc: Shawn Guo Cc: Arnd Bergmann Reviewed-by: Fabio Estevam Link: https://lore.kernel.org/r/20210620191103.156626-1-vz@mleia.com Signed-off-by: Vinod Koul --- include/linux/platform_data/dma-imx-sdma.h | 60 ------------------------------ 1 file changed, 60 deletions(-) delete mode 100644 include/linux/platform_data/dma-imx-sdma.h (limited to 'include/linux') diff --git a/include/linux/platform_data/dma-imx-sdma.h b/include/linux/platform_data/dma-imx-sdma.h deleted file mode 100644 index 725602d9df91..000000000000 --- a/include/linux/platform_data/dma-imx-sdma.h +++ /dev/null @@ -1,60 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __MACH_MXC_SDMA_H__ -#define __MACH_MXC_SDMA_H__ - -/** - * struct sdma_script_start_addrs - SDMA script start pointers - * - * start addresses of the different functions in the physical - * address space of the SDMA engine. - */ -struct sdma_script_start_addrs { - s32 ap_2_ap_addr; - s32 ap_2_bp_addr; - s32 ap_2_ap_fixed_addr; - s32 bp_2_ap_addr; - s32 loopback_on_dsp_side_addr; - s32 mcu_interrupt_only_addr; - s32 firi_2_per_addr; - s32 firi_2_mcu_addr; - s32 per_2_firi_addr; - s32 mcu_2_firi_addr; - s32 uart_2_per_addr; - s32 uart_2_mcu_addr; - s32 per_2_app_addr; - s32 mcu_2_app_addr; - s32 per_2_per_addr; - s32 uartsh_2_per_addr; - s32 uartsh_2_mcu_addr; - s32 per_2_shp_addr; - s32 mcu_2_shp_addr; - s32 ata_2_mcu_addr; - s32 mcu_2_ata_addr; - s32 app_2_per_addr; - s32 app_2_mcu_addr; - s32 shp_2_per_addr; - s32 shp_2_mcu_addr; - s32 mshc_2_mcu_addr; - s32 mcu_2_mshc_addr; - s32 spdif_2_mcu_addr; - s32 mcu_2_spdif_addr; - s32 asrc_2_mcu_addr; - s32 ext_mem_2_ipu_addr; - s32 descrambler_addr; - s32 dptc_dvfs_addr; - s32 utra_addr; - s32 ram_code_start_addr; - /* End of v1 array */ - s32 mcu_2_ssish_addr; - s32 ssish_2_mcu_addr; - s32 hdmi_dma_addr; - /* End of v2 array */ - s32 zcanfd_2_mcu_addr; - s32 zqspi_2_mcu_addr; - s32 mcu_2_ecspi_addr; - /* End of v3 array */ - s32 mcu_2_zqspi_addr; - /* End of v4 array */ -}; - -#endif /* __MACH_MXC_SDMA_H__ */ -- cgit v1.2.3 From d6abed2ad168dbc3f9aac986b3b89ba6d3535e01 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 23 Jun 2021 18:17:12 +0200 Subject: dma-buf: Switch to inline kerneldoc MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Also review & update everything while we're at it. This is prep work to smash a ton of stuff into the kerneldoc for @resv. v2: Move the doc for sysfs_entry.attachment_uid to the right place too (Sam) Reviewed-by: Sam Ravnborg Acked-by: Christian König Cc: Sam Ravnborg Reviewed-by: Alex Deucher Signed-off-by: Daniel Vetter Cc: Sumit Semwal Cc: "Christian König" Cc: Alex Deucher Cc: Daniel Vetter Cc: Dave Airlie Cc: Nirmoy Das Cc: Deepak R Varma Cc: Chen Li Cc: Kevin Wang Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Link: https://patchwork.freedesktop.org/patch/msgid/20210623161712.3370885-1-daniel.vetter@ffwll.ch --- include/linux/dma-buf.h | 116 +++++++++++++++++++++++++++++++++++++----------- 1 file changed, 90 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 92eec38a03aa..81cebf414505 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -289,30 +289,6 @@ struct dma_buf_ops { /** * struct dma_buf - shared buffer object - * @size: size of the buffer; invariant over the lifetime of the buffer. - * @file: file pointer used for sharing buffers across, and for refcounting. - * @attachments: list of dma_buf_attachment that denotes all devices attached, - * protected by dma_resv lock. - * @ops: dma_buf_ops associated with this buffer object. - * @lock: used internally to serialize list manipulation, attach/detach and - * vmap/unmap - * @vmapping_counter: used internally to refcnt the vmaps - * @vmap_ptr: the current vmap ptr if vmapping_counter > 0 - * @exp_name: name of the exporter; useful for debugging. - * @name: userspace-provided name; useful for accounting and debugging, - * protected by @resv. - * @name_lock: spinlock to protect name access - * @owner: pointer to exporter module; used for refcounting when exporter is a - * kernel module. - * @list_node: node for dma_buf accounting and debugging. - * @priv: exporter specific private data for this buffer object. - * @resv: reservation object linked to this dma-buf - * @poll: for userspace poll support - * @cb_excl: for userspace poll support - * @cb_shared: for userspace poll support - * @sysfs_entry: for exposing information about this buffer in sysfs. - * The attachment_uid member of @sysfs_entry is protected by dma_resv lock - * and is incremented on each attach. * * This represents a shared buffer, created by calling dma_buf_export(). The * userspace representation is a normal file descriptor, which can be created by @@ -324,24 +300,100 @@ struct dma_buf_ops { * Device DMA access is handled by the separate &struct dma_buf_attachment. */ struct dma_buf { + /** + * @size: + * + * Size of the buffer; invariant over the lifetime of the buffer. + */ size_t size; + + /** + * @file: + * + * File pointer used for sharing buffers across, and for refcounting. + * See dma_buf_get() and dma_buf_put(). + */ struct file *file; + + /** + * @attachments: + * + * List of dma_buf_attachment that denotes all devices attached, + * protected by &dma_resv lock @resv. + */ struct list_head attachments; + + /** @ops: dma_buf_ops associated with this buffer object. */ const struct dma_buf_ops *ops; + + /** + * @lock: + * + * Used internally to serialize list manipulation, attach/detach and + * vmap/unmap. Note that in many cases this is superseeded by + * dma_resv_lock() on @resv. + */ struct mutex lock; + + /** + * @vmapping_counter: + * + * Used internally to refcnt the vmaps returned by dma_buf_vmap(). + * Protected by @lock. + */ unsigned vmapping_counter; + + /** + * @vmap_ptr: + * The current vmap ptr if @vmapping_counter > 0. Protected by @lock. + */ struct dma_buf_map vmap_ptr; + + /** + * @exp_name: + * + * Name of the exporter; useful for debugging. See the + * DMA_BUF_SET_NAME IOCTL. + */ const char *exp_name; + + /** + * @name: + * + * Userspace-provided name; useful for accounting and debugging, + * protected by dma_resv_lock() on @resv and @name_lock for read access. + */ const char *name; + + /** @name_lock: Spinlock to protect name acces for read access. */ spinlock_t name_lock; + + /** + * @owner: + * + * Pointer to exporter module; used for refcounting when exporter is a + * kernel module. + */ struct module *owner; + + /** @list_node: node for dma_buf accounting and debugging. */ struct list_head list_node; + + /** @priv: exporter specific private data for this buffer object. */ void *priv; + + /** + * @resv: + * + * Reservation object linked to this dma-buf. + */ struct dma_resv *resv; - /* poll support */ + /** @poll: for userspace poll support */ wait_queue_head_t poll; + /** @cb_excl: for userspace poll support */ + /** @cb_shared: for userspace poll support */ struct dma_buf_poll_cb_t { struct dma_fence_cb cb; wait_queue_head_t *poll; @@ -349,10 +401,22 @@ struct dma_buf { __poll_t active; } cb_excl, cb_shared; #ifdef CONFIG_DMABUF_SYSFS_STATS - /* for sysfs stats */ + /** + * @sysfs_entry: + * + * For exposing information about this buffer in sysfs. See also + * `DMA-BUF statistics`_ for the uapi this enables. + */ struct dma_buf_sysfs_entry { struct kobject kobj; struct dma_buf *dmabuf; + + /** + * @sysfs_entry.attachment_uid: + * + * This is protected by the dma_resv_lock() on @resv and is + * incremented on each attach. + */ unsigned int attachment_uid; struct kset *attach_stats_kset; } *sysfs_entry; -- cgit v1.2.3 From 05459351ce307f6ba0e0221968b1e15b97d3b075 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Thu, 24 Jun 2021 14:52:46 +0200 Subject: dma-buf: Document dma-buf implicit fencing/resv fencing rules MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Docs for struct dma_resv are fairly clear: "A reservation object can have attached one exclusive fence (normally associated with write operations) or N shared fences (read operations)." https://dri.freedesktop.org/docs/drm/driver-api/dma-buf.html#reservation-objects Furthermore a review across all of upstream. First of render drivers and how they set implicit fences: - nouveau follows this contract, see in validate_fini_no_ticket() nouveau_bo_fence(nvbo, fence, !!b->write_domains); and that last boolean controls whether the exclusive or shared fence slot is used. - radeon follows this contract by setting p->relocs[i].tv.num_shared = !r->write_domain; in radeon_cs_parser_relocs(), which ensures that the call to ttm_eu_fence_buffer_objects() in radeon_cs_parser_fini() will do the right thing. - vmwgfx seems to follow this contract with the shotgun approach of always setting ttm_val_buf->num_shared = 0, which means ttm_eu_fence_buffer_objects() will only use the exclusive slot. - etnaviv follows this contract, as can be trivially seen by looking at submit_attach_object_fences() - i915 is a bit a convoluted maze with multiple paths leading to i915_vma_move_to_active(). Which sets the exclusive flag if EXEC_OBJECT_WRITE is set. This can either come as a buffer flag for softpin mode, or through the write_domain when using relocations. It follows this contract. - lima follows this contract, see lima_gem_submit() which sets the exclusive fence when the LIMA_SUBMIT_BO_WRITE flag is set for that bo - msm follows this contract, see msm_gpu_submit() which sets the exclusive flag when the MSM_SUBMIT_BO_WRITE is set for that buffer - panfrost follows this contract with the shotgun approach of just always setting the exclusive fence, see panfrost_attach_object_fences(). Benefits of a single engine I guess - v3d follows this contract with the same shotgun approach in v3d_attach_fences_and_unlock_reservation(), but it has at least an XXX comment that maybe this should be improved - v4c uses the same shotgun approach of always setting an exclusive fence, see vc4_update_bo_seqnos() - vgem also follows this contract, see vgem_fence_attach_ioctl() and the VGEM_FENCE_WRITE. This is used in some igts to validate prime sharing with i915.ko without the need of a 2nd gpu - vritio follows this contract again with the shotgun approach of always setting an exclusive fence, see virtio_gpu_array_add_fence() This covers the setting of the exclusive fences when writing. Synchronizing against the exclusive fence is a lot more tricky, and I only spot checked a few: - i915 does it, with the optional EXEC_OBJECT_ASYNC to skip all implicit dependencies (which is used by vulkan) - etnaviv does this. Implicit dependencies are collected in submit_fence_sync(), again with an opt-out flag ETNA_SUBMIT_NO_IMPLICIT. These are then picked up in etnaviv_sched_dependency which is the drm_sched_backend_ops->dependency callback. - v4c seems to not do much here, maybe gets away with it by not having a scheduler and only a single engine. Since all newer broadcom chips than the OG vc4 use v3d for rendering, which follows this contract, the impact of this issue is fairly small. - v3d does this using the drm_gem_fence_array_add_implicit() helper, which then it's drm_sched_backend_ops->dependency callback v3d_job_dependency() picks up. - panfrost is nice here and tracks the implicit fences in panfrost_job->implicit_fences, which again the drm_sched_backend_ops->dependency callback panfrost_job_dependency() picks up. It is mildly questionable though since it only picks up exclusive fences in panfrost_acquire_object_fences(), but not buggy in practice because it also always sets the exclusive fence. It should pick up both sets of fences, just in case there's ever going to be a 2nd gpu in a SoC with a mali gpu. Or maybe a mali SoC with a pcie port and a real gpu, which might actually happen eventually. A bug, but easy to fix. Should probably use the drm_gem_fence_array_add_implicit() helper. - lima is nice an easy, uses drm_gem_fence_array_add_implicit() and the same schema as v3d. - msm is mildly entertaining. It also supports MSM_SUBMIT_NO_IMPLICIT, but because it doesn't use the drm/scheduler it handles fences from the wrong context with a synchronous dma_fence_wait. See submit_fence_sync() leading to msm_gem_sync_object(). Investing into a scheduler might be a good idea. - all the remaining drivers are ttm based, where I hope they do appropriately obey implicit fences already. I didn't do the full audit there because a) not follow the contract would confuse ttm quite well and b) reading non-standard scheduler and submit code which isn't based on drm/scheduler is a pain. Onwards to the display side. - Any driver using the drm_gem_plane_helper_prepare_fb() helper will correctly. Overwhelmingly most drivers get this right, except a few totally dont. I'll follow up with a patch to make this the default and avoid a bunch of bugs. - I didn't audit the ttm drivers, but given that dma_resv started there I hope they get this right. In conclusion this IS the contract, both as documented and overwhelmingly implemented, specically as implemented by all render drivers except amdgpu. Amdgpu tried to fix this already in commit 049aca4363d8af87cab8d53de5401602db3b9999 Author: Christian König Date: Wed Sep 19 16:54:35 2018 +0200 drm/amdgpu: fix using shared fence for exported BOs v2 but this fix falls short on a number of areas: - It's racy, by the time the buffer is shared it might be too late. To make sure there's definitely never a problem we need to set the fences correctly for any buffer that's potentially exportable. - It's breaking uapi, dma-buf fds support poll() and differentitiate between, which was introduced in commit 9b495a5887994a6d74d5c261d012083a92b94738 Author: Maarten Lankhorst Date: Tue Jul 1 12:57:43 2014 +0200 dma-buf: add poll support, v3 - Christian König wants to nack new uapi building further on this dma_resv contract because it breaks amdgpu, quoting "Yeah, and that is exactly the reason why I will NAK this uAPI change. "This doesn't works for amdgpu at all for the reasons outlined above." https://lore.kernel.org/dri-devel/f2eb6751-2f82-9b23-f57e-548de5b729de@gmail.com/ Rejecting new development because your own driver is broken and violates established cross driver contracts and uapi is really not how upstream works. Now this patch will have a severe performance impact on anything that runs on multiple engines. So we can't just merge it outright, but need a bit a plan: - amdgpu needs a proper uapi for handling implicit fencing. The funny thing is that to do it correctly, implicit fencing must be treated as a very strange IPC mechanism for transporting fences, where both setting the fence and dependency intercepts must be handled explicitly. Current best practices is a per-bo flag to indicate writes, and a per-bo flag to to skip implicit fencing in the CS ioctl as a new chunk. - Since amdgpu has been shipping with broken behaviour we need an opt-out flag from the butchered implicit fencing model to enable the proper explicit implicit fencing model. - for kernel memory fences due to bo moves at least the i915 idea is to use ttm_bo->moving. amdgpu probably needs the same. - since the current p2p dma-buf interface assumes the kernel memory fence is in the exclusive dma_resv fence slot we need to add a new fence slot for kernel fences, which must never be ignored. Since currently only amdgpu supports this there's no real problem here yet, until amdgpu gains a NO_IMPLICIT CS flag. - New userspace needs to ship in enough desktop distros so that users wont notice the perf impact. I think we can ignore LTS distros who upgrade their kernels but not their mesa3d snapshot. - Then when this is all in place we can merge this patch here. What is not a solution to this problem here is trying to make the dma_resv rules in the kernel more clever. The fundamental issue here is that the amdgpu CS uapi is the least expressive one across all drivers (only equalled by panfrost, which has an actual excuse) by not allowing any userspace control over how implicit sync is conducted. Until this is fixed it's completely pointless to make the kernel more clever to improve amdgpu, because all we're doing is papering over this uapi design issue. amdgpu needs to attain the status quo established by other drivers first, once that's achieved we can tackle the remaining issues in a consistent way across drivers. v2: Bas pointed me at AMDGPU_GEM_CREATE_EXPLICIT_SYNC, which I entirely missed. This is great because it means the amdgpu specific piece for proper implicit fence handling exists already, and that since a while. The only thing that's now missing is - fishing the implicit fences out of a shared object at the right time - setting the exclusive implicit fence slot at the right time. Jason has a patch series to fill that gap with a bunch of generic ioctl on the dma-buf fd: https://lore.kernel.org/dri-devel/20210520190007.534046-1-jason@jlekstrand.net/ v3: Since Christian has fixed amdgpu now in commit 8c505bdc9c8b955223b054e34a0be9c3d841cd20 (drm-misc/drm-misc-next) Author: Christian König Date: Wed Jun 9 13:51:36 2021 +0200 drm/amdgpu: rework dma_resv handling v3 Use the audit covered in this commit message as the excuse to update the dma-buf docs around dma_buf.resv usage across drivers. Since dynamic importers have different rules also hammer these in again while we're at it. v4: - Add the missing "through the device" in the dynamic section that I overlooked. - Fix a kerneldoc markup mistake, the link didn't connect v5: - A few s/should/must/ to make clear what must be done (if the driver does implicit sync) and what's more a maybe (Daniel Stone) - drop all the example api discussion, that needs to be expanded, clarified and put into a new chapter in drm-uapi.rst (Daniel Stone) Cc: Daniel Stone Acked-by: Daniel Stone Reviewed-by: Dave Airlie (v4) Reviewed-by: Christian König (v3) Cc: mesa-dev@lists.freedesktop.org Cc: Bas Nieuwenhuizen Cc: Dave Airlie Cc: Rob Clark Cc: Kristian H. Kristensen Cc: Michel Dänzer Cc: Daniel Stone Cc: Sumit Semwal Cc: "Christian König" Cc: Alex Deucher Cc: Daniel Vetter Cc: Deepak R Varma Cc: Chen Li Cc: Kevin Wang Cc: Dennis Li Cc: Luben Tuikov Cc: linaro-mm-sig@lists.linaro.org Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210624125246.166721-1-daniel.vetter@ffwll.ch --- include/linux/dma-buf.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 81cebf414505..2b814fde0d11 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -386,6 +386,40 @@ struct dma_buf { * @resv: * * Reservation object linked to this dma-buf. + * + * IMPLICIT SYNCHRONIZATION RULES: + * + * Drivers which support implicit synchronization of buffer access as + * e.g. exposed in `Implicit Fence Poll Support`_ must follow the + * below rules. + * + * - Drivers must add a shared fence through dma_resv_add_shared_fence() + * for anything the userspace API considers a read access. This highly + * depends upon the API and window system. + * + * - Similarly drivers must set the exclusive fence through + * dma_resv_add_excl_fence() for anything the userspace API considers + * write access. + * + * - Drivers may just always set the exclusive fence, since that only + * causes unecessarily synchronization, but no correctness issues. + * + * - Some drivers only expose a synchronous userspace API with no + * pipelining across drivers. These do not set any fences for their + * access. An example here is v4l. + * + * DYNAMIC IMPORTER RULES: + * + * Dynamic importers, see dma_buf_attachment_is_dynamic(), have + * additional constraints on how they set up fences: + * + * - Dynamic importers must obey the exclusive fence and wait for it to + * signal before allowing access to the buffer's underlying storage + * through the device. + * + * - Dynamic importers should set fences for any access that they can't + * disable immediately from their &dma_buf_attach_ops.move_notify + * callback. */ struct dma_resv *resv; -- cgit v1.2.3 From bcfa8d14570d85c998a9b706b074ab151b286edf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Tue, 15 Jun 2021 23:41:03 +0200 Subject: HID: input: Add support for Programmable Buttons MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Map them to KEY_MACRO# event codes. These buttons are defined by HID as follows: "The user defines the function of these buttons to control software applications or GUI objects." This matches the semantics of the KEY_MACRO# input event codes that Linux supports. Also add support for HID "Named Array" collections. Also add hid-debug support for KEY_MACRO#. Signed-off-by: Thomas Weißschuh Signed-off-by: Jiri Kosina --- include/linux/hid.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 271021e20a3f..fb0e4dde6175 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -102,6 +102,7 @@ struct hid_item { #define HID_COLLECTION_PHYSICAL 0 #define HID_COLLECTION_APPLICATION 1 #define HID_COLLECTION_LOGICAL 2 +#define HID_COLLECTION_NAMED_ARRAY 4 /* * HID report descriptor global item tags -- cgit v1.2.3 From d0b371e5fba0ef2b4e3f6a3f1b5fe7f8bd97897e Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 21 Jun 2021 18:12:43 +0300 Subject: stm class: Spelling fix Drop the repeated word "the" in a comment. Cc: Alexander Shishkin Cc: Andrew Morton Cc: Greg Kroah-Hartman [alexander.shishkin: fixed the commit message] Reviewed-by: Andy Shevchenko Signed-off-by: Randy Dunlap Signed-off-by: Alexander Shishkin Link: https://lore.kernel.org/r/20210621151246.31891-2-alexander.shishkin@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/stm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/stm.h b/include/linux/stm.h index c6f577ab6f21..3b22689512be 100644 --- a/include/linux/stm.h +++ b/include/linux/stm.h @@ -57,7 +57,7 @@ struct stm_device; * * Normally, an STM device will have a range of masters available to software * and the rest being statically assigned to various hardware trace sources. - * The former is defined by the the range [@sw_start..@sw_end] of the device + * The former is defined by the range [@sw_start..@sw_end] of the device * description. That is, the lowest master that can be allocated to software * writers is @sw_start and data from this writer will appear is @sw_start * master in the STP stream. -- cgit v1.2.3 From fcf37549ae19e904bc6a5eadf5c25eca36100c5e Mon Sep 17 00:00:00 2001 From: Zhang Yi Date: Thu, 10 Jun 2021 19:24:34 +0800 Subject: jbd2: ensure abort the journal if detect IO error when writing original buffer back Although we merged c044f3d8360 ("jbd2: abort journal if free a async write error metadata buffer"), there is a race between jbd2_journal_try_to_free_buffers() and jbd2_journal_destroy(), so the jbd2_log_do_checkpoint() may still fail to detect the buffer write io error flag which may lead to filesystem inconsistency. jbd2_journal_try_to_free_buffers() ext4_put_super() jbd2_journal_destroy() __jbd2_journal_remove_checkpoint() detect buffer write error jbd2_log_do_checkpoint() jbd2_cleanup_journal_tail() <--- lead to inconsistency jbd2_journal_abort() Fix this issue by introducing a new atomic flag which only have one JBD2_CHECKPOINT_IO_ERROR bit now, and set it in __jbd2_journal_remove_checkpoint() when freeing a checkpoint buffer which has write_io_error flag. Then jbd2_journal_destroy() will detect this mark and abort the journal to prevent updating log tail. Signed-off-by: Zhang Yi Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20210610112440.3438139-3-yi.zhang@huawei.com Signed-off-by: Theodore Ts'o --- include/linux/jbd2.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 8543233b0388..d5db408ae064 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -779,6 +779,11 @@ struct journal_s */ unsigned long j_flags; + /** + * @j_atomic_flags: Atomic journaling state flags. + */ + unsigned long j_atomic_flags; + /** * @j_errno: * @@ -1375,6 +1380,12 @@ JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit, FAST_COMMIT) #define JBD2_JOURNAL_FLUSH_VALID (JBD2_JOURNAL_FLUSH_DISCARD | \ JBD2_JOURNAL_FLUSH_ZEROOUT) +/* + * Journal atomic flag definitions + */ +#define JBD2_CHECKPOINT_IO_ERROR 0x001 /* Detect io error while writing + * buffer back to disk */ + /* * Function declarations for the journaling transaction and buffer * management -- cgit v1.2.3 From 4ba3fcdde7e36af93610ceb3cc38365b14539865 Mon Sep 17 00:00:00 2001 From: Zhang Yi Date: Thu, 10 Jun 2021 19:24:37 +0800 Subject: jbd2,ext4: add a shrinker to release checkpointed buffers Current metadata buffer release logic in bdev_try_to_free_page() have a lot of use-after-free issues when umount filesystem concurrently, and it is difficult to fix directly because ext4 is the only user of s_op->bdev_try_to_free_page callback and we may have to add more special refcount or lock that is only used by ext4 into the common vfs layer, which is unacceptable. One better solution is remove the bdev_try_to_free_page callback, but the real problem is we cannot easily release journal_head on the checkpointed buffer, so try_to_free_buffers() cannot release buffers and page under memory pressure, which is more likely to trigger out-of-memory. So we cannot remove the callback directly before we find another way to release journal_head. This patch introduce a shrinker to free journal_head on the checkpointed transaction. After the journal_head got freed, try_to_free_buffers() could free buffer properly. Signed-off-by: Zhang Yi Suggested-by: Jan Kara Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20210610112440.3438139-6-yi.zhang@huawei.com Signed-off-by: Theodore Ts'o --- include/linux/jbd2.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index d5db408ae064..6cc035321562 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -909,6 +909,29 @@ struct journal_s */ struct buffer_head *j_chkpt_bhs[JBD2_NR_BATCH]; + /** + * @j_shrinker: + * + * Journal head shrinker, reclaim buffer's journal head which + * has been written back. + */ + struct shrinker j_shrinker; + + /** + * @j_jh_shrink_count: + * + * Number of journal buffers on the checkpoint list. [j_list_lock] + */ + struct percpu_counter j_jh_shrink_count; + + /** + * @j_shrink_transaction: + * + * Record next transaction will shrink on the checkpoint list. + * [j_list_lock] + */ + transaction_t *j_shrink_transaction; + /** * @j_head: * @@ -1422,6 +1445,7 @@ extern void jbd2_journal_commit_transaction(journal_t *); /* Checkpoint list management */ void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy); +unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, unsigned long *nr_to_scan); int __jbd2_journal_remove_checkpoint(struct journal_head *); void jbd2_journal_destroy_checkpoint(journal_t *journal); void __jbd2_journal_insert_checkpoint(struct journal_head *, transaction_t *); @@ -1532,6 +1556,8 @@ extern int jbd2_journal_set_features (journal_t *, unsigned long, unsigned long, unsigned long); extern void jbd2_journal_clear_features (journal_t *, unsigned long, unsigned long, unsigned long); +extern int jbd2_journal_register_shrinker(journal_t *journal); +extern void jbd2_journal_unregister_shrinker(journal_t *journal); extern int jbd2_journal_load (journal_t *journal); extern int jbd2_journal_destroy (journal_t *); extern int jbd2_journal_recover (journal_t *journal); -- cgit v1.2.3 From acc6100d3ffa24bdd2add8ea85fb66811bcce5d4 Mon Sep 17 00:00:00 2001 From: Zhang Yi Date: Thu, 10 Jun 2021 19:24:40 +0800 Subject: fs: remove bdev_try_to_free_page callback After remove the unique user of sop->bdev_try_to_free_page() callback, we could remove the callback and the corresponding blkdev_releasepage() at all. Signed-off-by: Zhang Yi Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20210610112440.3438139-9-yi.zhang@huawei.com Signed-off-by: Theodore Ts'o --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index c3c88fdb9b2a..c3277b445f96 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2171,7 +2171,6 @@ struct super_operations { ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); struct dquot **(*get_dquots)(struct inode *); #endif - int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t); long (*nr_cached_objects)(struct super_block *, struct shrink_control *); long (*free_cached_objects)(struct super_block *, -- cgit v1.2.3 From 0193cc908b5ae8aff2e2d2997ca5d4ae26ed24d4 Mon Sep 17 00:00:00 2001 From: Jing Zhang Date: Fri, 18 Jun 2021 22:27:03 +0000 Subject: KVM: stats: Separate generic stats from architecture specific ones Generic KVM stats are those collected in architecture independent code or those supported by all architectures; put all generic statistics in a separate structure. This ensures that they are defined the same way in the statistics API which is being added, removing duplication among different architectures in the declaration of the descriptors. No functional change intended. Reviewed-by: David Matlack Reviewed-by: Ricardo Koller Reviewed-by: Krish Sadhukhan Signed-off-by: Jing Zhang Message-Id: <20210618222709.1858088-2-jingzhangos@google.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_types.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index a7580f69dda0..48db778291b7 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -76,5 +76,17 @@ struct kvm_mmu_memory_cache { }; #endif +struct kvm_vm_stat_generic { + u64 remote_tlb_flush; +}; + +struct kvm_vcpu_stat_generic { + u64 halt_successful_poll; + u64 halt_attempted_poll; + u64 halt_poll_invalid; + u64 halt_wakeup; + u64 halt_poll_success_ns; + u64 halt_poll_fail_ns; +}; #endif /* __KVM_TYPES_H__ */ -- cgit v1.2.3 From cb082bfab59a224a49ae803fed52cd03e8d6b5e0 Mon Sep 17 00:00:00 2001 From: Jing Zhang Date: Fri, 18 Jun 2021 22:27:04 +0000 Subject: KVM: stats: Add fd-based API to read binary stats data This commit defines the API for userspace and prepare the common functionalities to support per VM/VCPU binary stats data readings. The KVM stats now is only accessible by debugfs, which has some shortcomings this change series are supposed to fix: 1. The current debugfs stats solution in KVM could be disabled when kernel Lockdown mode is enabled, which is a potential rick for production. 2. The current debugfs stats solution in KVM is organized as "one stats per file", it is good for debugging, but not efficient for production. 3. The stats read/clear in current debugfs solution in KVM are protected by the global kvm_lock. Besides that, there are some other benefits with this change: 1. All KVM VM/VCPU stats can be read out in a bulk by one copy to userspace. 2. A schema is used to describe KVM statistics. From userspace's perspective, the KVM statistics are self-describing. 3. With the fd-based solution, a separate telemetry would be able to read KVM stats in a less privileged environment. 4. After the initial setup by reading in stats descriptors, a telemetry only needs to read the stats data itself, no more parsing or setup is needed. Reviewed-by: David Matlack Reviewed-by: Ricardo Koller Reviewed-by: Krish Sadhukhan Reviewed-by: Fuad Tabba Tested-by: Fuad Tabba #arm64 Signed-off-by: Jing Zhang Message-Id: <20210618222709.1858088-3-jingzhangos@google.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 82 +++++++++++++++++++++++++++++++++++++++++++++-- include/linux/kvm_types.h | 2 ++ 2 files changed, 82 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 37cbb56ccd09..9ee7f350473b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1272,16 +1272,94 @@ struct kvm_stats_debugfs_item { int mode; }; +struct _kvm_stats_desc { + struct kvm_stats_desc desc; + char name[KVM_STATS_NAME_SIZE]; +}; + #define KVM_DBGFS_GET_MODE(dbgfs_item) \ ((dbgfs_item)->mode ? (dbgfs_item)->mode : 0644) -#define VM_STAT(n, x, ...) \ +#define VM_STAT(n, x, ...) \ { n, offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__ } -#define VCPU_STAT(n, x, ...) \ +#define VCPU_STAT(n, x, ...) \ { n, offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__ } +#define STATS_DESC_COMMON(type, unit, base, exp) \ + .flags = type | unit | base | \ + BUILD_BUG_ON_ZERO(type & ~KVM_STATS_TYPE_MASK) | \ + BUILD_BUG_ON_ZERO(unit & ~KVM_STATS_UNIT_MASK) | \ + BUILD_BUG_ON_ZERO(base & ~KVM_STATS_BASE_MASK), \ + .exponent = exp, \ + .size = 1 + +#define VM_GENERIC_STATS_DESC(stat, type, unit, base, exp) \ + { \ + { \ + STATS_DESC_COMMON(type, unit, base, exp), \ + .offset = offsetof(struct kvm_vm_stat, generic.stat) \ + }, \ + .name = #stat, \ + } +#define VCPU_GENERIC_STATS_DESC(stat, type, unit, base, exp) \ + { \ + { \ + STATS_DESC_COMMON(type, unit, base, exp), \ + .offset = offsetof(struct kvm_vcpu_stat, generic.stat) \ + }, \ + .name = #stat, \ + } +#define VM_STATS_DESC(stat, type, unit, base, exp) \ + { \ + { \ + STATS_DESC_COMMON(type, unit, base, exp), \ + .offset = offsetof(struct kvm_vm_stat, stat) \ + }, \ + .name = #stat, \ + } +#define VCPU_STATS_DESC(stat, type, unit, base, exp) \ + { \ + { \ + STATS_DESC_COMMON(type, unit, base, exp), \ + .offset = offsetof(struct kvm_vcpu_stat, stat) \ + }, \ + .name = #stat, \ + } +/* SCOPE: VM, VM_GENERIC, VCPU, VCPU_GENERIC */ +#define STATS_DESC(SCOPE, stat, type, unit, base, exp) \ + SCOPE##_STATS_DESC(stat, type, unit, base, exp) + +#define STATS_DESC_CUMULATIVE(SCOPE, name, unit, base, exponent) \ + STATS_DESC(SCOPE, name, KVM_STATS_TYPE_CUMULATIVE, unit, base, exponent) +#define STATS_DESC_INSTANT(SCOPE, name, unit, base, exponent) \ + STATS_DESC(SCOPE, name, KVM_STATS_TYPE_INSTANT, unit, base, exponent) +#define STATS_DESC_PEAK(SCOPE, name, unit, base, exponent) \ + STATS_DESC(SCOPE, name, KVM_STATS_TYPE_PEAK, unit, base, exponent) + +/* Cumulative counter, read/write */ +#define STATS_DESC_COUNTER(SCOPE, name) \ + STATS_DESC_CUMULATIVE(SCOPE, name, KVM_STATS_UNIT_NONE, \ + KVM_STATS_BASE_POW10, 0) +/* Instantaneous counter, read only */ +#define STATS_DESC_ICOUNTER(SCOPE, name) \ + STATS_DESC_INSTANT(SCOPE, name, KVM_STATS_UNIT_NONE, \ + KVM_STATS_BASE_POW10, 0) +/* Peak counter, read/write */ +#define STATS_DESC_PCOUNTER(SCOPE, name) \ + STATS_DESC_PEAK(SCOPE, name, KVM_STATS_UNIT_NONE, \ + KVM_STATS_BASE_POW10, 0) + +/* Cumulative time in nanosecond */ +#define STATS_DESC_TIME_NSEC(SCOPE, name) \ + STATS_DESC_CUMULATIVE(SCOPE, name, KVM_STATS_UNIT_SECONDS, \ + KVM_STATS_BASE_POW10, -9) + extern struct kvm_stats_debugfs_item debugfs_entries[]; extern struct dentry *kvm_debugfs_dir; +ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header, + const struct _kvm_stats_desc *desc, + void *stats, size_t size_stats, + char __user *user_buffer, size_t size, loff_t *offset); #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq) diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 48db778291b7..ed6a985c5680 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -89,4 +89,6 @@ struct kvm_vcpu_stat_generic { u64 halt_poll_fail_ns; }; +#define KVM_STATS_NAME_SIZE 48 + #endif /* __KVM_TYPES_H__ */ -- cgit v1.2.3 From b9964ce74544ea6cbc4eabd2c89a531adf7f291d Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 24 Jun 2021 18:05:51 +0200 Subject: rcu: Create an unrcu_pointer() to remove __rcu from a pointer MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The xchg() and cmpxchg() functions are sometimes used to carry out RCU updates. Unfortunately, this can result in sparse warnings for both the old-value and new-value arguments, as well as for the return value. The arguments can be dealt with using RCU_INITIALIZER(): old_p = xchg(&p, RCU_INITIALIZER(new_p)); But a sparse warning still remains due to assigning the __rcu pointer returned from xchg to the (most likely) non-__rcu pointer old_p. This commit therefore provides an unrcu_pointer() macro that strips the __rcu. This macro can be used as follows: old_p = unrcu_pointer(xchg(&p, RCU_INITIALIZER(new_p))); Reported-by: Toke Høiland-Jørgensen Signed-off-by: Paul E. McKenney Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210624160609.292325-2-toke@redhat.com --- include/linux/rcupdate.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 9455476c5ba2..d7895b81264e 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -363,6 +363,20 @@ static inline void rcu_preempt_sleep_check(void) { } #define rcu_check_sparse(p, space) #endif /* #else #ifdef __CHECKER__ */ +/** + * unrcu_pointer - mark a pointer as not being RCU protected + * @p: pointer needing to lose its __rcu property + * + * Converts @p from an __rcu pointer to a __kernel pointer. + * This allows an __rcu pointer to be used with xchg() and friends. + */ +#define unrcu_pointer(p) \ +({ \ + typeof(*p) *_________p1 = (typeof(*p) *__force)(p); \ + rcu_check_sparse(p, __rcu); \ + ((typeof(*p) __force __kernel *)(_________p1)); \ +}) + #define __rcu_access_pointer(p, space) \ ({ \ typeof(*p) *_________p1 = (typeof(*p) *__force)READ_ONCE(p); \ -- cgit v1.2.3 From 782347b6bcad07ddb574422e01e22c92e05928c8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Thu, 24 Jun 2021 18:05:55 +0200 Subject: xdp: Add proper __rcu annotations to redirect map entries MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit XDP_REDIRECT works by a three-step process: the bpf_redirect() and bpf_redirect_map() helpers will lookup the target of the redirect and store it (along with some other metadata) in a per-CPU struct bpf_redirect_info. Next, when the program returns the XDP_REDIRECT return code, the driver will call xdp_do_redirect() which will use the information thus stored to actually enqueue the frame into a bulk queue structure (that differs slightly by map type, but shares the same principle). Finally, before exiting its NAPI poll loop, the driver will call xdp_do_flush(), which will flush all the different bulk queues, thus completing the redirect. Pointers to the map entries will be kept around for this whole sequence of steps, protected by RCU. However, there is no top-level rcu_read_lock() in the core code; instead drivers add their own rcu_read_lock() around the XDP portions of the code, but somewhat inconsistently as Martin discovered[0]. However, things still work because everything happens inside a single NAPI poll sequence, which means it's between a pair of calls to local_bh_disable()/local_bh_enable(). So Paul suggested[1] that we could document this intention by using rcu_dereference_check() with rcu_read_lock_bh_held() as a second parameter, thus allowing sparse and lockdep to verify that everything is done correctly. This patch does just that: we add an __rcu annotation to the map entry pointers and remove the various comments explaining the NAPI poll assurance strewn through devmap.c in favour of a longer explanation in filter.c. The goal is to have one coherent documentation of the entire flow, and rely on the RCU annotations as a "standard" way of communicating the flow in the map code (which can additionally be understood by sparse and lockdep). The RCU annotation replacements result in a fairly straight-forward replacement where READ_ONCE() becomes rcu_dereference_check(), WRITE_ONCE() becomes rcu_assign_pointer() and xchg() and cmpxchg() gets wrapped in the proper constructs to cast the pointer back and forth between __rcu and __kernel address space (for the benefit of sparse). The one complication is that xskmap has a few constructions where double-pointers are passed back and forth; these simply all gain __rcu annotations, and only the final reference/dereference to the inner-most pointer gets changed. With this, everything can be run through sparse without eliciting complaints, and lockdep can verify correctness even without the use of rcu_read_lock() in the drivers. Subsequent patches will clean these up from the drivers. [0] https://lore.kernel.org/bpf/20210415173551.7ma4slcbqeyiba2r@kafai-mbp.dhcp.thefacebook.com/ [1] https://lore.kernel.org/bpf/20210419165837.GA975577@paulmck-ThinkPad-P17-Gen-1/ Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210624160609.292325-6-toke@redhat.com --- include/linux/filter.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 688856e0b28a..472f97074da0 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -763,11 +763,9 @@ DECLARE_BPF_DISPATCHER(xdp) static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, struct xdp_buff *xdp) { - /* Caller needs to hold rcu_read_lock() (!), otherwise program - * can be released while still running, or map elements could be - * freed early while still having concurrent users. XDP fastpath - * already takes rcu_read_lock() when fetching the program, so - * it's not necessary here anymore. + /* Driver XDP hooks are invoked within a single NAPI poll cycle and thus + * under local_bh_disable(), which provides the needed RCU protection + * for accessing map entries. */ return __BPF_PROG_RUN(prog, xdp, BPF_DISPATCHER_FUNC(xdp)); } -- cgit v1.2.3 From 630161cfdf5cdc696a82b59410d1ff00b23d946e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Jun 2021 14:32:39 +0200 Subject: block: move bdev_disk_changed Move bdev_disk_changed to block/partitions/core.c, together with the rest of the partition scanning code. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20210624123240.441814-2-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/genhd.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 03d684f0498f..f5f0c9bdf1d2 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -257,7 +257,6 @@ static inline sector_t get_capacity(struct gendisk *disk) } int bdev_disk_changed(struct block_device *bdev, bool invalidate); -int blk_add_partitions(struct gendisk *disk, struct block_device *bdev); void blk_drop_partitions(struct gendisk *disk); extern struct gendisk *__alloc_disk_node(int minors, int node_id); -- cgit v1.2.3 From 0384264ea8a39bd98c9a3158060565f650c056a6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Jun 2021 14:32:40 +0200 Subject: block: pass a gendisk to bdev_disk_changed bdev_disk_changed can only operate on whole devices. Make that clear by passing a gendisk instead of the struct block_device. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20210624123240.441814-3-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/genhd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index f5f0c9bdf1d2..13b34177cc85 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -256,7 +256,7 @@ static inline sector_t get_capacity(struct gendisk *disk) return bdev_nr_sectors(disk->part0); } -int bdev_disk_changed(struct block_device *bdev, bool invalidate); +int bdev_disk_changed(struct gendisk *disk, bool invalidate); void blk_drop_partitions(struct gendisk *disk); extern struct gendisk *__alloc_disk_node(int minors, int node_id); -- cgit v1.2.3 From c88c192dc3ea209694cc08f4ccf51f920d26bdae Mon Sep 17 00:00:00 2001 From: Marcin Wojtas Date: Thu, 24 Jun 2021 02:51:51 +0200 Subject: net: mdiobus: fix fwnode_mdbiobus_register() fallback case The fallback case of fwnode_mdbiobus_register() (relevant for !CONFIG_FWNODE_MDIO) was defined with wrong argument name, causing a compilation error. Fix that. Signed-off-by: Marcin Wojtas Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/fwnode_mdio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fwnode_mdio.h b/include/linux/fwnode_mdio.h index 13d4ae8fee0a..f62817c23137 100644 --- a/include/linux/fwnode_mdio.h +++ b/include/linux/fwnode_mdio.h @@ -40,7 +40,7 @@ static inline int fwnode_mdiobus_register(struct mii_bus *bus, * This way, we don't have to keep compat bits around in drivers. */ - return mdiobus_register(mdio); + return mdiobus_register(bus); } #endif -- cgit v1.2.3 From e3a9b1212b9d6cb20751196e338f4a5138d539d3 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Tue, 22 Jun 2021 19:28:23 -0700 Subject: PCI: Export pci_dev_trylock() and pci_dev_unlock() Other places in the kernel use this form, and so just provide a common path for it. Acked-by: Bjorn Helgaas Signed-off-by: Luis Chamberlain Reviewed-by: Cornelia Huck Link: https://lore.kernel.org/r/20210623022824.308041-2-mcgrof@kernel.org Signed-off-by: Alex Williamson --- include/linux/pci.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 24306504226a..7765c325706a 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1621,6 +1621,9 @@ void pci_cfg_access_lock(struct pci_dev *dev); bool pci_cfg_access_trylock(struct pci_dev *dev); void pci_cfg_access_unlock(struct pci_dev *dev); +int pci_dev_trylock(struct pci_dev *dev); +void pci_dev_unlock(struct pci_dev *dev); + /* * PCI domain support. Sometimes called PCI segment (eg by ACPI), * a PCI domain is defined to be a set of PCI buses which share -- cgit v1.2.3 From fcfe1baeddbf1c7c448b44c82586d0cbc8abc9f5 Mon Sep 17 00:00:00 2001 From: Jing Zhang Date: Fri, 18 Jun 2021 22:27:05 +0000 Subject: KVM: stats: Support binary stats retrieval for a VM Add a VM ioctl to get a statistics file descriptor by which a read functionality is provided for userspace to read out VM stats header, descriptors and data. Define VM statistics descriptors and header for all architectures. Reviewed-by: David Matlack Reviewed-by: Ricardo Koller Reviewed-by: Krish Sadhukhan Reviewed-by: Fuad Tabba Tested-by: Fuad Tabba #arm64 Signed-off-by: Jing Zhang Message-Id: <20210618222709.1858088-4-jingzhangos@google.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9ee7f350473b..e79ce64b9f6f 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -599,6 +599,7 @@ struct kvm { #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER struct notifier_block pm_notifier; #endif + char stats_id[KVM_STATS_NAME_SIZE]; }; #define kvm_err(fmt, ...) \ @@ -1354,12 +1355,17 @@ struct _kvm_stats_desc { STATS_DESC_CUMULATIVE(SCOPE, name, KVM_STATS_UNIT_SECONDS, \ KVM_STATS_BASE_POW10, -9) +#define KVM_GENERIC_VM_STATS() \ + STATS_DESC_COUNTER(VM_GENERIC, remote_tlb_flush) + extern struct kvm_stats_debugfs_item debugfs_entries[]; extern struct dentry *kvm_debugfs_dir; ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header, const struct _kvm_stats_desc *desc, void *stats, size_t size_stats, char __user *user_buffer, size_t size, loff_t *offset); +extern const struct kvm_stats_header kvm_vm_stats_header; +extern const struct _kvm_stats_desc kvm_vm_stats_desc[]; #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq) -- cgit v1.2.3 From ce55c049459cff0034cc1bcfdce3bf343a2d6317 Mon Sep 17 00:00:00 2001 From: Jing Zhang Date: Fri, 18 Jun 2021 22:27:06 +0000 Subject: KVM: stats: Support binary stats retrieval for a VCPU Add a VCPU ioctl to get a statistics file descriptor by which a read functionality is provided for userspace to read out VCPU stats header, descriptors and data. Define VCPU statistics descriptors and header for all architectures. Reviewed-by: David Matlack Reviewed-by: Ricardo Koller Reviewed-by: Krish Sadhukhan Reviewed-by: Fuad Tabba Tested-by: Fuad Tabba #arm64 Signed-off-by: Jing Zhang Message-Id: <20210618222709.1858088-5-jingzhangos@google.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index e79ce64b9f6f..9e75afef16b0 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -305,7 +305,6 @@ struct kvm_vcpu { struct pid __rcu *pid; int sigset_active; sigset_t sigset; - struct kvm_vcpu_stat stat; unsigned int halt_poll_ns; bool valid_wakeup; @@ -342,6 +341,8 @@ struct kvm_vcpu { bool preempted; bool ready; struct kvm_vcpu_arch arch; + struct kvm_vcpu_stat stat; + char stats_id[KVM_STATS_NAME_SIZE]; struct kvm_dirty_ring dirty_ring; }; @@ -1358,6 +1359,14 @@ struct _kvm_stats_desc { #define KVM_GENERIC_VM_STATS() \ STATS_DESC_COUNTER(VM_GENERIC, remote_tlb_flush) +#define KVM_GENERIC_VCPU_STATS() \ + STATS_DESC_COUNTER(VCPU_GENERIC, halt_successful_poll), \ + STATS_DESC_COUNTER(VCPU_GENERIC, halt_attempted_poll), \ + STATS_DESC_COUNTER(VCPU_GENERIC, halt_poll_invalid), \ + STATS_DESC_COUNTER(VCPU_GENERIC, halt_wakeup), \ + STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_poll_success_ns), \ + STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_poll_fail_ns) + extern struct kvm_stats_debugfs_item debugfs_entries[]; extern struct dentry *kvm_debugfs_dir; ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header, @@ -1366,6 +1375,8 @@ ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header, char __user *user_buffer, size_t size, loff_t *offset); extern const struct kvm_stats_header kvm_vm_stats_header; extern const struct _kvm_stats_desc kvm_vm_stats_desc[]; +extern const struct kvm_stats_header kvm_vcpu_stats_header; +extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[]; #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq) -- cgit v1.2.3 From bc9e9e672df9f16f3825320c53ec01b3d44add28 Mon Sep 17 00:00:00 2001 From: Jing Zhang Date: Wed, 23 Jun 2021 17:28:46 -0400 Subject: KVM: debugfs: Reuse binary stats descriptors To remove code duplication, use the binary stats descriptors in the implementation of the debugfs interface for statistics. This unifies the definition of statistics for the binary and debugfs interfaces. Signed-off-by: Jing Zhang Message-Id: <20210618222709.1858088-8-jingzhangos@google.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 17 +---------------- 1 file changed, 1 insertion(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9e75afef16b0..ae7735b490b4 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1264,14 +1264,8 @@ enum kvm_stat_kind { struct kvm_stat_data { struct kvm *kvm; - struct kvm_stats_debugfs_item *dbgfs_item; -}; - -struct kvm_stats_debugfs_item { - const char *name; - int offset; + const struct _kvm_stats_desc *desc; enum kvm_stat_kind kind; - int mode; }; struct _kvm_stats_desc { @@ -1279,14 +1273,6 @@ struct _kvm_stats_desc { char name[KVM_STATS_NAME_SIZE]; }; -#define KVM_DBGFS_GET_MODE(dbgfs_item) \ - ((dbgfs_item)->mode ? (dbgfs_item)->mode : 0644) - -#define VM_STAT(n, x, ...) \ - { n, offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__ } -#define VCPU_STAT(n, x, ...) \ - { n, offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__ } - #define STATS_DESC_COMMON(type, unit, base, exp) \ .flags = type | unit | base | \ BUILD_BUG_ON_ZERO(type & ~KVM_STATS_TYPE_MASK) | \ @@ -1367,7 +1353,6 @@ struct _kvm_stats_desc { STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_poll_success_ns), \ STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_poll_fail_ns) -extern struct kvm_stats_debugfs_item debugfs_entries[]; extern struct dentry *kvm_debugfs_dir; ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header, const struct _kvm_stats_desc *desc, -- cgit v1.2.3 From fd2ef39cc9a6b9c4c41864ac506906c52f94b06a Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 23 Jun 2021 11:36:34 +0200 Subject: blk: Fix lock inversion between ioc lock and bfqd lock Lockdep complains about lock inversion between ioc->lock and bfqd->lock: bfqd -> ioc: put_io_context+0x33/0x90 -> ioc->lock grabbed blk_mq_free_request+0x51/0x140 blk_put_request+0xe/0x10 blk_attempt_req_merge+0x1d/0x30 elv_attempt_insert_merge+0x56/0xa0 blk_mq_sched_try_insert_merge+0x4b/0x60 bfq_insert_requests+0x9e/0x18c0 -> bfqd->lock grabbed blk_mq_sched_insert_requests+0xd6/0x2b0 blk_mq_flush_plug_list+0x154/0x280 blk_finish_plug+0x40/0x60 ext4_writepages+0x696/0x1320 do_writepages+0x1c/0x80 __filemap_fdatawrite_range+0xd7/0x120 sync_file_range+0xac/0xf0 ioc->bfqd: bfq_exit_icq+0xa3/0xe0 -> bfqd->lock grabbed put_io_context_active+0x78/0xb0 -> ioc->lock grabbed exit_io_context+0x48/0x50 do_exit+0x7e9/0xdd0 do_group_exit+0x54/0xc0 To avoid this inversion we change blk_mq_sched_try_insert_merge() to not free the merged request but rather leave that upto the caller similarly to blk_mq_sched_try_merge(). And in bfq_insert_requests() we make sure to free all the merged requests after dropping bfqd->lock. Fixes: aee69d78dec0 ("block, bfq: introduce the BFQ-v0 I/O scheduler as an extra scheduler") Reviewed-by: Ming Lei Acked-by: Paolo Valente Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20210623093634.27879-3-jack@suse.cz Signed-off-by: Jens Axboe --- include/linux/elevator.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 783ecb3cb77a..ef9ceead3db1 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -117,7 +117,8 @@ extern void elv_merge_requests(struct request_queue *, struct request *, struct request *); extern void elv_merged_request(struct request_queue *, struct request *, enum elv_merge); -extern bool elv_attempt_insert_merge(struct request_queue *, struct request *); +extern bool elv_attempt_insert_merge(struct request_queue *, struct request *, + struct list_head *); extern struct request *elv_former_request(struct request_queue *, struct request *); extern struct request *elv_latter_request(struct request_queue *, struct request *); void elevator_init_mq(struct request_queue *q); -- cgit v1.2.3 From 4834446035a1011ff1231626ef33555d64c4fd78 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 25 Jun 2021 09:35:11 +0200 Subject: tty: make linux/tty_flip.h self-contained If someone includes linux/tty_flip.h before linux/tty.h, they see many compiler errors like: include/linux/tty_flip.h:23:30: error: invalid use of undefined type 'struct tty_port' include/linux/tty_flip.h:26:14: error: invalid use of undefined type 'struct tty_buffer' tty_flip.h actually lexicographically sorts before tty.h. So if people sort includes (as I tried in amiserial), the compilation suddenly breaks. Solve this by including linux/tty.h from linux/tty_flip.h, so that everything is defined as needed. Another alternative would be to uninline tty_insert_flip_char and just insert forward declarations of tty_port and tty_buffer structs into tty_flip.h as that inline is the only real user. But that would mean slowing down the fast path without any good reason. (Provided the fix is that easy and there were no real problems with this until now.) Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210625073511.4514-1-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/tty_flip.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tty_flip.h b/include/linux/tty_flip.h index d6729281ec50..67d78dc553e1 100644 --- a/include/linux/tty_flip.h +++ b/include/linux/tty_flip.h @@ -2,6 +2,8 @@ #ifndef _LINUX_TTY_FLIP_H #define _LINUX_TTY_FLIP_H +#include + extern int tty_buffer_set_limit(struct tty_port *port, int limit); extern unsigned int tty_buffer_space_avail(struct tty_port *port); extern int tty_buffer_request_room(struct tty_port *port, size_t size); -- cgit v1.2.3 From b470e10eb43f19e08245cd87dd3192a8141cfbb5 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Fri, 25 Jun 2021 10:52:11 +0530 Subject: spi: core: add dma_map_dev for dma device Some controllers like qcom geni need the parent device to be used for dma mapping, so add a dma_map_dev field and let drivers fill this to be used as mapping device Signed-off-by: Vinod Koul Link: https://lore.kernel.org/r/20210625052213.32260-4-vkoul@kernel.org Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 3ada36175e5f..97b8d12b5f2b 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -588,6 +588,7 @@ struct spi_controller { bool (*can_dma)(struct spi_controller *ctlr, struct spi_device *spi, struct spi_transfer *xfer); + struct device *dma_map_dev; /* * These hooks are for drivers that want to use the generic -- cgit v1.2.3 From 24e166f43e93de0e9b0a460ecfe4bab1f12212d7 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 29 May 2021 17:14:21 +0200 Subject: HID: core: Add hid_hw_may_wakeup() function Add a hid_hw_may_wakeup() function, which is the equivalent of device_may_wakeup() for hid devices. In most cases this just returns device_may_wakeup(hdev->dev.parent), but for some ll-drivers this is not correct. E.g. usb_hid_driver instantiated hid devices have their parent set to the usb-interface to which the usb_hid_driver is bound, but the power/wakeup* sysfs attributes are part of the usb-device, which is the usb-interface's parent. For these special cases a new may_wakeup callback is added to hid_ll_driver, so that ll-drivers can override the default behavior. Signed-off-by: Hans de Goede Reviewed-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- include/linux/hid.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 10e922cee4eb..51a4dad3565e 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -800,6 +800,7 @@ struct hid_driver { * @raw_request: send raw report request to device (e.g. feature report) * @output_report: send output report to device * @idle: send idle request to device + * @may_wakeup: return if device may act as a wakeup source during system-suspend */ struct hid_ll_driver { int (*start)(struct hid_device *hdev); @@ -824,6 +825,7 @@ struct hid_ll_driver { int (*output_report) (struct hid_device *hdev, __u8 *buf, size_t len); int (*idle)(struct hid_device *hdev, int report, int idle, int reqtype); + bool (*may_wakeup)(struct hid_device *hdev); }; extern struct hid_ll_driver i2c_hid_ll_driver; @@ -1149,6 +1151,22 @@ static inline int hid_hw_idle(struct hid_device *hdev, int report, int idle, return 0; } +/** + * hid_may_wakeup - return if the hid device may act as a wakeup source during system-suspend + * + * @hdev: hid device + */ +static inline bool hid_hw_may_wakeup(struct hid_device *hdev) +{ + if (hdev->ll_driver->may_wakeup) + return hdev->ll_driver->may_wakeup(hdev); + + if (hdev->dev.parent) + return device_may_wakeup(hdev->dev.parent); + + return false; +} + /** * hid_hw_wait - wait for buffered io to complete * -- cgit v1.2.3 From db59e1b6e49201beacdbd0622aa3594f2de4f727 Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Fri, 18 Jun 2021 17:20:56 +0200 Subject: ACPI: arm64: Move DMA setup operations out of IORT Extract generic DMA setup code out of IORT, so it can be reused by VIOT. Keep it in drivers/acpi/arm64 for now, since it could break x86 platforms that haven't run this code so far, if they have invalid tables. Reviewed-by: Eric Auger Signed-off-by: Jean-Philippe Brucker Reviewed-by: Robin Murphy Link: https://lore.kernel.org/r/20210618152059.1194210-2-jean-philippe@linaro.org Signed-off-by: Joerg Roedel --- include/linux/acpi.h | 3 +++ include/linux/acpi_iort.h | 6 +++--- 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index c60745f657e9..7aaa9559cc19 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -259,9 +259,12 @@ void acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa); #ifdef CONFIG_ARM64 void acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa); +void acpi_arch_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size); #else static inline void acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) { } +static inline void +acpi_arch_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size) { } #endif int acpi_numa_memory_affinity_init (struct acpi_srat_mem_affinity *ma); diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index 1a12baa58e40..f7f054833afd 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -34,7 +34,7 @@ struct irq_domain *iort_get_device_domain(struct device *dev, u32 id, void acpi_configure_pmsi_domain(struct device *dev); int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id); /* IOMMU interface */ -void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *size); +int iort_dma_get_ranges(struct device *dev, u64 *size); const struct iommu_ops *iort_iommu_configure_id(struct device *dev, const u32 *id_in); int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head); @@ -48,8 +48,8 @@ static inline struct irq_domain *iort_get_device_domain( { return NULL; } static inline void acpi_configure_pmsi_domain(struct device *dev) { } /* IOMMU interface */ -static inline void iort_dma_setup(struct device *dev, u64 *dma_addr, - u64 *size) { } +static inline int iort_dma_get_ranges(struct device *dev, u64 *size) +{ return -ENODEV; } static inline const struct iommu_ops *iort_iommu_configure_id( struct device *dev, const u32 *id_in) { return NULL; } -- cgit v1.2.3 From 11a8c5e3a94b12848f24d9c63b5c175ce0b80729 Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Fri, 18 Jun 2021 17:20:57 +0200 Subject: ACPI: Move IOMMU setup code out of IORT Extract the code that sets up the IOMMU infrastructure from IORT, since it can be reused by VIOT. Move it one level up into a new acpi_iommu_configure_id() function, which calls the IORT parsing function which in turn calls the acpi_iommu_fwspec_init() helper. Signed-off-by: Jean-Philippe Brucker Reviewed-by: Eric Auger Reviewed-by: Robin Murphy Link: https://lore.kernel.org/r/20210618152059.1194210-3-jean-philippe@linaro.org Signed-off-by: Joerg Roedel --- include/linux/acpi_iort.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index f7f054833afd..f1f0842a2cb2 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -35,8 +35,7 @@ void acpi_configure_pmsi_domain(struct device *dev); int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id); /* IOMMU interface */ int iort_dma_get_ranges(struct device *dev, u64 *size); -const struct iommu_ops *iort_iommu_configure_id(struct device *dev, - const u32 *id_in); +int iort_iommu_configure_id(struct device *dev, const u32 *id_in); int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head); phys_addr_t acpi_iort_dma_get_max_cpu_address(void); #else @@ -50,9 +49,8 @@ static inline void acpi_configure_pmsi_domain(struct device *dev) { } /* IOMMU interface */ static inline int iort_dma_get_ranges(struct device *dev, u64 *size) { return -ENODEV; } -static inline const struct iommu_ops *iort_iommu_configure_id( - struct device *dev, const u32 *id_in) -{ return NULL; } +static inline int iort_iommu_configure_id(struct device *dev, const u32 *id_in) +{ return -ENODEV; } static inline int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head) { return 0; } -- cgit v1.2.3 From 3cf485540e7b8550936ce3602edf2f58e4007304 Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Fri, 18 Jun 2021 17:20:58 +0200 Subject: ACPI: Add driver for the VIOT table The ACPI Virtual I/O Translation Table describes topology of para-virtual platforms, similarly to vendor tables DMAR, IVRS and IORT. For now it describes the relation between virtio-iommu and the endpoints it manages. Three steps are needed to configure DMA of endpoints: (1) acpi_viot_init(): parse the VIOT table, find or create the fwnode associated to each vIOMMU device. This needs to happen after acpi_scan_init(), because it relies on the struct device and their fwnode to be available. (2) When probing the vIOMMU device, the driver registers its IOMMU ops within the IOMMU subsystem. This step doesn't require any intervention from the VIOT driver. (3) viot_iommu_configure(): before binding the endpoint to a driver, find the associated IOMMU ops. Register them, along with the endpoint ID, into the device's iommu_fwspec. If step (3) happens before step (2), it is deferred until the IOMMU is initialized, then retried. Tested-by: Eric Auger Reviewed-by: Eric Auger Signed-off-by: Jean-Philippe Brucker Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20210618152059.1194210-4-jean-philippe@linaro.org Signed-off-by: Joerg Roedel --- include/linux/acpi_viot.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) create mode 100644 include/linux/acpi_viot.h (limited to 'include/linux') diff --git a/include/linux/acpi_viot.h b/include/linux/acpi_viot.h new file mode 100644 index 000000000000..1eb8ee5b0e5f --- /dev/null +++ b/include/linux/acpi_viot.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __ACPI_VIOT_H__ +#define __ACPI_VIOT_H__ + +#include + +#ifdef CONFIG_ACPI_VIOT +void __init acpi_viot_init(void); +int viot_iommu_configure(struct device *dev); +#else +static inline void acpi_viot_init(void) {} +static inline int viot_iommu_configure(struct device *dev) +{ + return -ENODEV; +} +#endif + +#endif /* __ACPI_VIOT_H__ */ -- cgit v1.2.3 From ac6d704679d343e55615551f19e9b2e18d68518b Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Fri, 18 Jun 2021 17:20:59 +0200 Subject: iommu/dma: Pass address limit rather than size to iommu_setup_dma_ops() Passing a 64-bit address width to iommu_setup_dma_ops() is valid on virtual platforms, but isn't currently possible. The overflow check in iommu_dma_init_domain() prevents this even when @dma_base isn't 0. Pass a limit address instead of a size, so callers don't have to fake a size to work around the check. The base and limit parameters are being phased out, because: * they are redundant for x86 callers. dma-iommu already reserves the first page, and the upper limit is already in domain->geometry. * they can now be obtained from dev->dma_range_map on Arm. But removing them on Arm isn't completely straightforward so is left for future work. As an intermediate step, simplify the x86 callers by passing dummy limits. Signed-off-by: Jean-Philippe Brucker Reviewed-by: Eric Auger Reviewed-by: Robin Murphy Link: https://lore.kernel.org/r/20210618152059.1194210-5-jean-philippe@linaro.org Signed-off-by: Joerg Roedel --- include/linux/dma-iommu.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-iommu.h b/include/linux/dma-iommu.h index 6e75a2d689b4..758ca4694257 100644 --- a/include/linux/dma-iommu.h +++ b/include/linux/dma-iommu.h @@ -19,7 +19,7 @@ int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base); void iommu_put_dma_cookie(struct iommu_domain *domain); /* Setup call for arch DMA mapping code */ -void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size); +void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 dma_limit); /* The DMA API isn't _quite_ the whole story, though... */ /* @@ -50,7 +50,7 @@ struct msi_msg; struct device; static inline void iommu_setup_dma_ops(struct device *dev, u64 dma_base, - u64 size) + u64 dma_limit) { } -- cgit v1.2.3 From 87cf5127968ab3c543ebd98253052b928f9b47da Mon Sep 17 00:00:00 2001 From: Quan Nguyen Date: Wed, 19 May 2021 14:49:28 +0700 Subject: i2c: core-smbus: Expose PEC calculate function for generic use Expose the PEC calculation i2c_smbus_pec() for generic use. Signed-off-by: Quan Nguyen Acked-by: Matt Johnston Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 953a4eecb88f..685f8c73d99e 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -148,6 +148,7 @@ s32 __i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, /* Now follow the 'nice' access routines. These also document the calling conventions of i2c_smbus_xfer. */ +u8 i2c_smbus_pec(u8 crc, u8 *p, size_t count); s32 i2c_smbus_read_byte(const struct i2c_client *client); s32 i2c_smbus_write_byte(const struct i2c_client *client, u8 value); s32 i2c_smbus_read_byte_data(const struct i2c_client *client, u8 command); -- cgit v1.2.3 From ff70202b2d1ad522275c6aadc8c53519b6a22c57 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Thu, 24 Jun 2021 10:05:05 +0200 Subject: dev_forward_skb: do not scrub skb mark within the same name space The goal is to keep the mark during a bpf_redirect(), like it is done for legacy encapsulation / decapsulation, when there is no x-netns. This was initially done in commit 213dd74aee76 ("skbuff: Do not scrub skb mark within the same name space"). When the call to skb_scrub_packet() was added in dev_forward_skb() (commit 8b27f27797ca ("skb: allow skb_scrub_packet() to be used by tunnels")), the second argument (xnet) was set to true to force a call to skb_orphan(). At this time, the mark was always cleanned up by skb_scrub_packet(), whatever xnet value was. This call to skb_orphan() was removed later in commit 9c4c325252c5 ("skbuff: preserve sock reference when scrubbing the skb."). But this 'true' stayed here without any real reason. Let's correctly set xnet in ____dev_forward_skb(), this function has access to the previous interface and to the new interface. Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5cbc950b34df..5ab2d1917ca1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4114,7 +4114,7 @@ static __always_inline int ____dev_forward_skb(struct net_device *dev, return NET_RX_DROP; } - skb_scrub_packet(skb, true); + skb_scrub_packet(skb, !net_eq(dev_net(dev), dev_net(skb->dev))); skb->priority = 0; return 0; } -- cgit v1.2.3 From ac53c26433b51f1835ce5a935970e427d83e3ec5 Mon Sep 17 00:00:00 2001 From: Marcin Wojtas Date: Fri, 25 Jun 2021 12:38:53 +0200 Subject: net: mdiobus: withdraw fwnode_mdbiobus_register The newly implemented fwnode_mdbiobus_register turned out to be problematic - in case the fwnode_/of_/acpi_mdio are built as modules, a dependency cycle can be observed during the depmod phase of modules_install, eg.: depmod: ERROR: Cycle detected: fwnode_mdio -> of_mdio -> fwnode_mdio depmod: ERROR: Found 2 modules in dependency cycles! OR: depmod: ERROR: Cycle detected: acpi_mdio -> fwnode_mdio -> acpi_mdio depmod: ERROR: Found 2 modules in dependency cycles! A possible solution could be to rework fwnode_mdiobus_register, so that to merge the contents of acpi_mdiobus_register and of_mdiobus_register. However feasible, such change would be very intrusive and affect huge amount of the of_mdiobus_register users. Since there are currently 2 users of ACPI and MDIO (xgmac_mdio and mvmdio), withdraw the fwnode_mdbiobus_register and roll back to a simple 'if' condition in affected drivers. Fixes: 62a6ef6a996f ("net: mdiobus: Introduce fwnode_mdbiobus_register()") Signed-off-by: Marcin Wojtas Signed-off-by: David S. Miller --- include/linux/fwnode_mdio.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fwnode_mdio.h b/include/linux/fwnode_mdio.h index f62817c23137..faf603c48c86 100644 --- a/include/linux/fwnode_mdio.h +++ b/include/linux/fwnode_mdio.h @@ -16,7 +16,6 @@ int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, int fwnode_mdiobus_register_phy(struct mii_bus *bus, struct fwnode_handle *child, u32 addr); -int fwnode_mdiobus_register(struct mii_bus *bus, struct fwnode_handle *fwnode); #else /* CONFIG_FWNODE_MDIO */ int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, struct phy_device *phy, @@ -31,17 +30,6 @@ static inline int fwnode_mdiobus_register_phy(struct mii_bus *bus, { return -EINVAL; } - -static inline int fwnode_mdiobus_register(struct mii_bus *bus, - struct fwnode_handle *fwnode) -{ - /* - * Fall back to mdiobus_register() function to register a bus. - * This way, we don't have to keep compat bits around in drivers. - */ - - return mdiobus_register(bus); -} #endif #endif /* __LINUX_FWNODE_MDIO_H */ -- cgit v1.2.3 From bce29ac9ce0bb0b0b146b687ab978378c21e9078 Mon Sep 17 00:00:00 2001 From: Daniel Bristot de Oliveira Date: Tue, 22 Jun 2021 16:42:27 +0200 Subject: trace: Add osnoise tracer In the context of high-performance computing (HPC), the Operating System Noise (*osnoise*) refers to the interference experienced by an application due to activities inside the operating system. In the context of Linux, NMIs, IRQs, SoftIRQs, and any other system thread can cause noise to the system. Moreover, hardware-related jobs can also cause noise, for example, via SMIs. The osnoise tracer leverages the hwlat_detector by running a similar loop with preemption, SoftIRQs and IRQs enabled, thus allowing all the sources of *osnoise* during its execution. Using the same approach of hwlat, osnoise takes note of the entry and exit point of any source of interferences, increasing a per-cpu interference counter. The osnoise tracer also saves an interference counter for each source of interference. The interference counter for NMI, IRQs, SoftIRQs, and threads is increased anytime the tool observes these interferences' entry events. When a noise happens without any interference from the operating system level, the hardware noise counter increases, pointing to a hardware-related noise. In this way, osnoise can account for any source of interference. At the end of the period, the osnoise tracer prints the sum of all noise, the max single noise, the percentage of CPU available for the thread, and the counters for the noise sources. Usage Write the ASCII text "osnoise" into the current_tracer file of the tracing system (generally mounted at /sys/kernel/tracing). For example:: [root@f32 ~]# cd /sys/kernel/tracing/ [root@f32 tracing]# echo osnoise > current_tracer It is possible to follow the trace by reading the trace trace file:: [root@f32 tracing]# cat trace # tracer: osnoise # # _-----=> irqs-off # / _----=> need-resched # | / _---=> hardirq/softirq # || / _--=> preempt-depth MAX # || / SINGLE Interference counters: # |||| RUNTIME NOISE % OF CPU NOISE +-----------------------------+ # TASK-PID CPU# |||| TIMESTAMP IN US IN US AVAILABLE IN US HW NMI IRQ SIRQ THREAD # | | | |||| | | | | | | | | | | <...>-859 [000] .... 81.637220: 1000000 190 99.98100 9 18 0 1007 18 1 <...>-860 [001] .... 81.638154: 1000000 656 99.93440 74 23 0 1006 16 3 <...>-861 [002] .... 81.638193: 1000000 5675 99.43250 202 6 0 1013 25 21 <...>-862 [003] .... 81.638242: 1000000 125 99.98750 45 1 0 1011 23 0 <...>-863 [004] .... 81.638260: 1000000 1721 99.82790 168 7 0 1002 49 41 <...>-864 [005] .... 81.638286: 1000000 263 99.97370 57 6 0 1006 26 2 <...>-865 [006] .... 81.638302: 1000000 109 99.98910 21 3 0 1006 18 1 <...>-866 [007] .... 81.638326: 1000000 7816 99.21840 107 8 0 1016 39 19 In addition to the regular trace fields (from TASK-PID to TIMESTAMP), the tracer prints a message at the end of each period for each CPU that is running an osnoise/CPU thread. The osnoise specific fields report: - The RUNTIME IN USE reports the amount of time in microseconds that the osnoise thread kept looping reading the time. - The NOISE IN US reports the sum of noise in microseconds observed by the osnoise tracer during the associated runtime. - The % OF CPU AVAILABLE reports the percentage of CPU available for the osnoise thread during the runtime window. - The MAX SINGLE NOISE IN US reports the maximum single noise observed during the runtime window. - The Interference counters display how many each of the respective interference happened during the runtime window. Note that the example above shows a high number of HW noise samples. The reason being is that this sample was taken on a virtual machine, and the host interference is detected as a hardware interference. Tracer options The tracer has a set of options inside the osnoise directory, they are: - osnoise/cpus: CPUs at which a osnoise thread will execute. - osnoise/period_us: the period of the osnoise thread. - osnoise/runtime_us: how long an osnoise thread will look for noise. - osnoise/stop_tracing_us: stop the system tracing if a single noise higher than the configured value happens. Writing 0 disables this option. - osnoise/stop_tracing_total_us: stop the system tracing if total noise higher than the configured value happens. Writing 0 disables this option. - tracing_threshold: the minimum delta between two time() reads to be considered as noise, in us. When set to 0, the default value will be used, which is currently 5 us. Additional Tracing In addition to the tracer, a set of tracepoints were added to facilitate the identification of the osnoise source. - osnoise:sample_threshold: printed anytime a noise is higher than the configurable tolerance_ns. - osnoise:nmi_noise: noise from NMI, including the duration. - osnoise:irq_noise: noise from an IRQ, including the duration. - osnoise:softirq_noise: noise from a SoftIRQ, including the duration. - osnoise:thread_noise: noise from a thread, including the duration. Note that all the values are *net values*. For example, if while osnoise is running, another thread preempts the osnoise thread, it will start a thread_noise duration at the start. Then, an IRQ takes place, preempting the thread_noise, starting a irq_noise. When the IRQ ends its execution, it will compute its duration, and this duration will be subtracted from the thread_noise, in such a way as to avoid the double accounting of the IRQ execution. This logic is valid for all sources of noise. Here is one example of the usage of these tracepoints:: osnoise/8-961 [008] d.h. 5789.857532: irq_noise: local_timer:236 start 5789.857529929 duration 1845 ns osnoise/8-961 [008] dNh. 5789.858408: irq_noise: local_timer:236 start 5789.858404871 duration 2848 ns migration/8-54 [008] d... 5789.858413: thread_noise: migration/8:54 start 5789.858409300 duration 3068 ns osnoise/8-961 [008] .... 5789.858413: sample_threshold: start 5789.858404555 duration 8723 ns interferences 2 In this example, a noise sample of 8 microseconds was reported in the last line, pointing to two interferences. Looking backward in the trace, the two previous entries were about the migration thread running after a timer IRQ execution. The first event is not part of the noise because it took place one millisecond before. It is worth noticing that the sum of the duration reported in the tracepoints is smaller than eight us reported in the sample_threshold. The reason roots in the overhead of the entry and exit code that happens before and after any interference execution. This justifies the dual approach: measuring thread and tracing. Link: https://lkml.kernel.org/r/e649467042d60e7b62714c9c6751a56299d15119.1624372313.git.bristot@redhat.com Cc: Phil Auld Cc: Sebastian Andrzej Siewior Cc: Kate Carcia Cc: Jonathan Corbet Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Alexandre Chartre Cc: Clark Willaims Cc: John Kacur Cc: Juri Lelli Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: x86@kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Daniel Bristot de Oliveira [ Made the following functions static: trace_irqentry_callback() trace_irqexit_callback() trace_intel_irqentry_callback() trace_intel_irqexit_callback() Added to include/trace.h: osnoise_arch_register() osnoise_arch_unregister() Fixed define logic for LATENCY_FS_NOTIFY Reported-by: kernel test robot ] Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace_irq.h | 13 +++++++++++++ include/linux/trace.h | 5 +++++ 2 files changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace_irq.h b/include/linux/ftrace_irq.h index 0abd9a1d2852..f6faa31289ba 100644 --- a/include/linux/ftrace_irq.h +++ b/include/linux/ftrace_irq.h @@ -7,12 +7,21 @@ extern bool trace_hwlat_callback_enabled; extern void trace_hwlat_callback(bool enter); #endif +#ifdef CONFIG_OSNOISE_TRACER +extern bool trace_osnoise_callback_enabled; +extern void trace_osnoise_callback(bool enter); +#endif + static inline void ftrace_nmi_enter(void) { #ifdef CONFIG_HWLAT_TRACER if (trace_hwlat_callback_enabled) trace_hwlat_callback(true); #endif +#ifdef CONFIG_OSNOISE_TRACER + if (trace_osnoise_callback_enabled) + trace_osnoise_callback(true); +#endif } static inline void ftrace_nmi_exit(void) @@ -21,6 +30,10 @@ static inline void ftrace_nmi_exit(void) if (trace_hwlat_callback_enabled) trace_hwlat_callback(false); #endif +#ifdef CONFIG_OSNOISE_TRACER + if (trace_osnoise_callback_enabled) + trace_osnoise_callback(false); +#endif } #endif /* _LINUX_FTRACE_IRQ_H */ diff --git a/include/linux/trace.h b/include/linux/trace.h index be1e130ed87c..4e3858640c47 100644 --- a/include/linux/trace.h +++ b/include/linux/trace.h @@ -41,6 +41,11 @@ int trace_array_init_printk(struct trace_array *tr); void trace_array_put(struct trace_array *tr); struct trace_array *trace_array_get_by_name(const char *name); int trace_array_destroy(struct trace_array *tr); + +/* For osnoise tracer */ +int osnoise_arch_register(void); +void osnoise_arch_unregister(void); + #endif /* CONFIG_TRACING */ #endif /* _LINUX_TRACE_H */ -- cgit v1.2.3 From 1ab6dc35e9148e3cb4a837fdd08f1ca56b55eda0 Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Mon, 19 Apr 2021 16:23:49 +0300 Subject: net/mlx5: DR, Add support for flow sampler offload Add SW steering support for sFlow / flow sampler action. Signed-off-by: Yevgeny Kliteynik Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 2d1ed78289ff..e32a0d61929b 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -11083,6 +11083,11 @@ struct mlx5_ifc_create_sampler_obj_in_bits { struct mlx5_ifc_sampler_obj_bits sampler_object; }; +struct mlx5_ifc_query_sampler_obj_out_bits { + struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr; + struct mlx5_ifc_sampler_obj_bits sampler_object; +}; + enum { MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_KEY_SIZE_128 = 0x0, MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_KEY_SIZE_256 = 0x1, -- cgit v1.2.3 From b3c0d72b092e52ae7369b52fb97f63eb2ea7f16a Mon Sep 17 00:00:00 2001 From: Chun-Kuang Hu Date: Mon, 15 Mar 2021 07:33:21 +0800 Subject: mailbox: mtk-cmdq: Remove cmdq_cb_status cmdq_cb_status is an error status. Use the standard error number instead of cmdq_cb_status to prevent status duplication. Signed-off-by: Chun-Kuang Hu Reviewed-by: Yongqiang Niu Signed-off-by: Jassi Brar --- include/linux/mailbox/mtk-cmdq-mailbox.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h index d5a983d65f05..2f7d9a37d611 100644 --- a/include/linux/mailbox/mtk-cmdq-mailbox.h +++ b/include/linux/mailbox/mtk-cmdq-mailbox.h @@ -65,13 +65,8 @@ enum cmdq_code { CMDQ_CODE_LOGIC = 0xa0, }; -enum cmdq_cb_status { - CMDQ_CB_NORMAL = 0, - CMDQ_CB_ERROR -}; - struct cmdq_cb_data { - enum cmdq_cb_status sta; + int sta; void *data; }; -- cgit v1.2.3 From 8ebc3b5aa4cfafd8b9d58e2595a12f0715594619 Mon Sep 17 00:00:00 2001 From: Chun-Kuang Hu Date: Mon, 15 Mar 2021 07:33:23 +0800 Subject: mailbox: mtk-cmdq: Add struct cmdq_pkt in struct cmdq_cb_data Current client use 'struct cmdq_pkt' as callback data, so change 'void *data' to 'struct cmdq_pkt *pkt'. Keep data until client use pkt instead of data. Signed-off-by: Chun-Kuang Hu Reviewed-by: Yongqiang Niu Signed-off-by: Jassi Brar --- include/linux/mailbox/mtk-cmdq-mailbox.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h index 2f7d9a37d611..44365aab043c 100644 --- a/include/linux/mailbox/mtk-cmdq-mailbox.h +++ b/include/linux/mailbox/mtk-cmdq-mailbox.h @@ -68,6 +68,7 @@ enum cmdq_code { struct cmdq_cb_data { int sta; void *data; + struct cmdq_pkt *pkt; }; typedef void (*cmdq_async_flush_cb)(struct cmdq_cb_data data); -- cgit v1.2.3 From bcda91bf86c1ff7647df85029d69f2aed80f210e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 7 Apr 2021 10:01:54 +0200 Subject: pwm: Add a device-managed function to add PWM chips MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This potentially simplifies low-level PWM drivers. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- include/linux/pwm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 5a73251d28e3..892ece4d4cfa 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -405,6 +405,9 @@ void *pwm_get_chip_data(struct pwm_device *pwm); int pwmchip_add(struct pwm_chip *chip); int pwmchip_remove(struct pwm_chip *chip); + +int devm_pwmchip_add(struct device *dev, struct pwm_chip *chip); + struct pwm_device *pwm_request_from_chip(struct pwm_chip *chip, unsigned int index, const char *label); -- cgit v1.2.3 From 77eccd0dfae353a64a2088d308bed3b373a4220f Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Tue, 1 Jun 2021 17:11:20 +0200 Subject: wait: use LIST_HEAD_INIT() to initialize wait_queue_head Replace the open-coded initialization with the right macro. Signed-off-by: Julian Wiedmann Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210601151120.329223-1-jwi@linux.ibm.com --- include/linux/wait.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index fe10e8570a52..99c5f05718cd 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -56,7 +56,7 @@ struct task_struct; #define __WAIT_QUEUE_HEAD_INITIALIZER(name) { \ .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ - .head = { &(name).head, &(name).head } } + .head = LIST_HEAD_INIT(name.head) } #define DECLARE_WAIT_QUEUE_HEAD(name) \ struct wait_queue_head name = __WAIT_QUEUE_HEAD_INITIALIZER(name) -- cgit v1.2.3 From 18765447c3b7867b3f8cccde52dc9d822852e71b Mon Sep 17 00:00:00 2001 From: Hailong Liu Date: Sun, 6 Jun 2021 19:54:51 +0800 Subject: sched/sysctl: Move extern sysctl declarations to sched.h Since commit '8a99b6833c88(sched: Move SCHED_DEBUG sysctl to debugfs)', SCHED_DEBUG sysctls are moved to debugfs, so these extern sysctls in include/linux/sched/sysctl.h are no longer needed for sysctl.c, even some are no longer needed. So move those extern sysctls that needed by kernel/sched/debug.c to kernel/sched/sched.h, and remove others that are no longer needed. Signed-off-by: Hailong Liu Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210606115451.26745-1-liuhailongg6@163.com --- include/linux/sched/sysctl.h | 18 ------------------ 1 file changed, 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index db2c0f34aaaf..304f431178fd 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -28,30 +28,12 @@ enum { sysctl_hung_task_timeout_secs = 0 }; extern unsigned int sysctl_sched_child_runs_first; -extern unsigned int sysctl_sched_latency; -extern unsigned int sysctl_sched_min_granularity; -extern unsigned int sysctl_sched_wakeup_granularity; - enum sched_tunable_scaling { SCHED_TUNABLESCALING_NONE, SCHED_TUNABLESCALING_LOG, SCHED_TUNABLESCALING_LINEAR, SCHED_TUNABLESCALING_END, }; -extern unsigned int sysctl_sched_tunable_scaling; - -extern unsigned int sysctl_numa_balancing_scan_delay; -extern unsigned int sysctl_numa_balancing_scan_period_min; -extern unsigned int sysctl_numa_balancing_scan_period_max; -extern unsigned int sysctl_numa_balancing_scan_size; - -#ifdef CONFIG_SCHED_DEBUG -extern __read_mostly unsigned int sysctl_sched_migration_cost; -extern __read_mostly unsigned int sysctl_sched_nr_migrate; - -extern int sysctl_resched_latency_warn_ms; -extern int sysctl_resched_latency_warn_once; -#endif /* * control realtime throttling: -- cgit v1.2.3 From 6549c46af8551b346bcc0b9043f93848319acd5c Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Sun, 27 Jun 2021 16:04:18 +0800 Subject: regulator: rt5033: Fix n_voltages settings for BUCK and LDO For linear regulators, the n_voltages should be (max - min) / step + 1. Buck voltage from 1v to 3V, per step 100mV, and vout mask is 0x1f. If value is from 20 to 31, the voltage will all be fixed to 3V. And LDO also, just vout range is different from 1.2v to 3v, step is the same. If value is from 18 to 31, the voltage will also be fixed to 3v. Signed-off-by: Axel Lin Reviewed-by: ChiYuan Huang Link: https://lore.kernel.org/r/20210627080418.1718127-1-axel.lin@ingics.com Signed-off-by: Mark Brown --- include/linux/mfd/rt5033-private.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/rt5033-private.h b/include/linux/mfd/rt5033-private.h index 2d1895c3efbf..40a0c2dfb80f 100644 --- a/include/linux/mfd/rt5033-private.h +++ b/include/linux/mfd/rt5033-private.h @@ -200,13 +200,13 @@ enum rt5033_reg { #define RT5033_REGULATOR_BUCK_VOLTAGE_MIN 1000000U #define RT5033_REGULATOR_BUCK_VOLTAGE_MAX 3000000U #define RT5033_REGULATOR_BUCK_VOLTAGE_STEP 100000U -#define RT5033_REGULATOR_BUCK_VOLTAGE_STEP_NUM 32 +#define RT5033_REGULATOR_BUCK_VOLTAGE_STEP_NUM 21 /* RT5033 regulator LDO output voltage uV */ #define RT5033_REGULATOR_LDO_VOLTAGE_MIN 1200000U #define RT5033_REGULATOR_LDO_VOLTAGE_MAX 3000000U #define RT5033_REGULATOR_LDO_VOLTAGE_STEP 100000U -#define RT5033_REGULATOR_LDO_VOLTAGE_STEP_NUM 32 +#define RT5033_REGULATOR_LDO_VOLTAGE_STEP_NUM 19 /* RT5033 regulator SAFE LDO output voltage uV */ #define RT5033_REGULATOR_SAFE_LDO_VOLTAGE 4900000U -- cgit v1.2.3 From f7d9f6370e006400655ff96cb148f56598492d91 Mon Sep 17 00:00:00 2001 From: Daniel Bristot de Oliveira Date: Mon, 28 Jun 2021 11:45:47 +0200 Subject: trace/osnoise: Fix 'no previous prototype' warnings kernel test robot reported some osnoise functions with "no previous prototype." Fix these warnings by making local functions static, and by adding: void osnoise_trace_irq_entry(int id); void osnoise_trace_irq_exit(int id, const char *desc); to include/linux/trace.h. Link: https://lkml.kernel.org/r/e40d3cb4be8bde921f4b40fa6a095cf85ab807bd.1624872608.git.bristot@redhat.com Fixes: bce29ac9ce0b ("trace: Add osnoise tracer") Reported-by: kernel test robot Signed-off-by: Daniel Bristot de Oliveira Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/trace.h b/include/linux/trace.h index 4e3858640c47..bf169612ffe1 100644 --- a/include/linux/trace.h +++ b/include/linux/trace.h @@ -45,6 +45,8 @@ int trace_array_destroy(struct trace_array *tr); /* For osnoise tracer */ int osnoise_arch_register(void); void osnoise_arch_unregister(void); +void osnoise_trace_irq_entry(int id); +void osnoise_trace_irq_exit(int id, const char *desc); #endif /* CONFIG_TRACING */ -- cgit v1.2.3 From 0d2cfbd41c4a5a0ca5598d1874b1081138cd64c6 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 27 Jun 2021 14:54:25 +0300 Subject: net: bridge: ignore switchdev events for LAG ports which didn't request replay There is a slight inconvenience in the switchdev replay helpers added recently, and this is when: ip link add br0 type bridge ip link add bond0 type bond ip link set bond0 master br0 bridge vlan add dev bond0 vid 100 ip link set swp0 master bond0 ip link set swp1 master bond0 Since the underlying driver (currently only DSA) asks for a replay of VLANs when swp0 and swp1 join the LAG because it is bridged, what will happen is that DSA will try to react twice on the VLAN event for swp0. This is not really a huge problem right now, because most drivers accept duplicates since the bridge itself does, but it will become a problem when we add support for replaying switchdev object deletions. Let's fix this by adding a blank void *ctx in the replay helpers, which will be passed on by the bridge in the switchdev notifications. If the context is NULL, everything is the same as before. But if the context is populated with a valid pointer, the underlying switchdev driver (currently DSA) can use the pointer to 'see through' the bridge port (which in the example above is bond0) and 'know' that the event is only for a particular physical port offloading that bridge port, and not for all of them. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 12e9a32dbca0..57df761b6f4a 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -71,7 +71,8 @@ bool br_multicast_has_router_adjacent(struct net_device *dev, int proto); bool br_multicast_enabled(const struct net_device *dev); bool br_multicast_router(const struct net_device *dev); int br_mdb_replay(struct net_device *br_dev, struct net_device *dev, - struct notifier_block *nb, struct netlink_ext_ack *extack); + const void *ctx, struct notifier_block *nb, + struct netlink_ext_ack *extack); #else static inline int br_multicast_list_adjacent(struct net_device *dev, struct list_head *br_ip_list) @@ -104,7 +105,7 @@ static inline bool br_multicast_router(const struct net_device *dev) return false; } static inline int br_mdb_replay(struct net_device *br_dev, - struct net_device *dev, + struct net_device *dev, const void *ctx, struct notifier_block *nb, struct netlink_ext_ack *extack) { @@ -120,7 +121,8 @@ int br_vlan_get_proto(const struct net_device *dev, u16 *p_proto); int br_vlan_get_info(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo); int br_vlan_replay(struct net_device *br_dev, struct net_device *dev, - struct notifier_block *nb, struct netlink_ext_ack *extack); + const void *ctx, struct notifier_block *nb, + struct netlink_ext_ack *extack); #else static inline bool br_vlan_enabled(const struct net_device *dev) { @@ -149,7 +151,7 @@ static inline int br_vlan_get_info(const struct net_device *dev, u16 vid, } static inline int br_vlan_replay(struct net_device *br_dev, - struct net_device *dev, + struct net_device *dev, const void *ctx, struct notifier_block *nb, struct netlink_ext_ack *extack) { @@ -166,7 +168,7 @@ bool br_port_flag_is_set(const struct net_device *dev, unsigned long flag); u8 br_port_get_stp_state(const struct net_device *dev); clock_t br_get_ageing_time(struct net_device *br_dev); int br_fdb_replay(struct net_device *br_dev, struct net_device *dev, - struct notifier_block *nb); + const void *ctx, struct notifier_block *nb); #else static inline struct net_device * br_fdb_find_port(const struct net_device *br_dev, @@ -197,7 +199,7 @@ static inline clock_t br_get_ageing_time(struct net_device *br_dev) } static inline int br_fdb_replay(struct net_device *br_dev, - struct net_device *dev, + struct net_device *dev, const void *ctx, struct notifier_block *nb) { return -EOPNOTSUPP; -- cgit v1.2.3 From bdf123b455ce596aec6e410ec36fe3687b6a2140 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 27 Jun 2021 14:54:26 +0300 Subject: net: bridge: constify variables in the replay helpers Some of the arguments and local variables for the newly added switchdev replay helpers can be const, so let's make them so. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 57df761b6f4a..6b54da2c65ba 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -104,8 +104,8 @@ static inline bool br_multicast_router(const struct net_device *dev) { return false; } -static inline int br_mdb_replay(struct net_device *br_dev, - struct net_device *dev, const void *ctx, +static inline int br_mdb_replay(const struct net_device *br_dev, + const struct net_device *dev, const void *ctx, struct notifier_block *nb, struct netlink_ext_ack *extack) { @@ -166,8 +166,8 @@ struct net_device *br_fdb_find_port(const struct net_device *br_dev, void br_fdb_clear_offload(const struct net_device *dev, u16 vid); bool br_port_flag_is_set(const struct net_device *dev, unsigned long flag); u8 br_port_get_stp_state(const struct net_device *dev); -clock_t br_get_ageing_time(struct net_device *br_dev); -int br_fdb_replay(struct net_device *br_dev, struct net_device *dev, +clock_t br_get_ageing_time(const struct net_device *br_dev); +int br_fdb_replay(const struct net_device *br_dev, const struct net_device *dev, const void *ctx, struct notifier_block *nb); #else static inline struct net_device * @@ -193,13 +193,13 @@ static inline u8 br_port_get_stp_state(const struct net_device *dev) return BR_STATE_DISABLED; } -static inline clock_t br_get_ageing_time(struct net_device *br_dev) +static inline clock_t br_get_ageing_time(const struct net_device *br_dev) { return 0; } -static inline int br_fdb_replay(struct net_device *br_dev, - struct net_device *dev, const void *ctx, +static inline int br_fdb_replay(const struct net_device *br_dev, + const struct net_device *dev, const void *ctx, struct notifier_block *nb) { return -EOPNOTSUPP; -- cgit v1.2.3 From 7e8c18586daf7c1653c4b43a8119bc9662ed8fa6 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 27 Jun 2021 14:54:27 +0300 Subject: net: bridge: allow the switchdev replay functions to be called for deletion When a switchdev port leaves a LAG that is a bridge port, the switchdev objects and port attributes offloaded to that port are not removed: ip link add br0 type bridge ip link add bond0 type bond mode 802.3ad ip link set swp0 master bond0 ip link set bond0 master br0 bridge vlan add dev bond0 vid 100 ip link set swp0 nomaster VLAN 100 will remain installed on swp0 despite it going into standalone mode, because as far as the bridge is concerned, nothing ever happened to its bridge port. Let's extend the bridge vlan, fdb and mdb replay functions to take a 'bool adding' argument, and make DSA and ocelot call the replay functions with 'adding' as false from the switchdev unsync path, for the switch port that leaves the bridge. Note that this patch in itself does not salvage anything, because in the current pull mode of operation, DSA still needs to call the replay helpers with adding=false. This will be done in another patch. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 6b54da2c65ba..b651c5e32a28 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -71,7 +71,7 @@ bool br_multicast_has_router_adjacent(struct net_device *dev, int proto); bool br_multicast_enabled(const struct net_device *dev); bool br_multicast_router(const struct net_device *dev); int br_mdb_replay(struct net_device *br_dev, struct net_device *dev, - const void *ctx, struct notifier_block *nb, + const void *ctx, bool adding, struct notifier_block *nb, struct netlink_ext_ack *extack); #else static inline int br_multicast_list_adjacent(struct net_device *dev, @@ -106,7 +106,7 @@ static inline bool br_multicast_router(const struct net_device *dev) } static inline int br_mdb_replay(const struct net_device *br_dev, const struct net_device *dev, const void *ctx, - struct notifier_block *nb, + bool adding, struct notifier_block *nb, struct netlink_ext_ack *extack) { return -EOPNOTSUPP; @@ -121,7 +121,7 @@ int br_vlan_get_proto(const struct net_device *dev, u16 *p_proto); int br_vlan_get_info(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo); int br_vlan_replay(struct net_device *br_dev, struct net_device *dev, - const void *ctx, struct notifier_block *nb, + const void *ctx, bool adding, struct notifier_block *nb, struct netlink_ext_ack *extack); #else static inline bool br_vlan_enabled(const struct net_device *dev) @@ -152,7 +152,7 @@ static inline int br_vlan_get_info(const struct net_device *dev, u16 vid, static inline int br_vlan_replay(struct net_device *br_dev, struct net_device *dev, const void *ctx, - struct notifier_block *nb, + bool adding, struct notifier_block *nb, struct netlink_ext_ack *extack) { return -EOPNOTSUPP; @@ -168,7 +168,7 @@ bool br_port_flag_is_set(const struct net_device *dev, unsigned long flag); u8 br_port_get_stp_state(const struct net_device *dev); clock_t br_get_ageing_time(const struct net_device *br_dev); int br_fdb_replay(const struct net_device *br_dev, const struct net_device *dev, - const void *ctx, struct notifier_block *nb); + const void *ctx, bool adding, struct notifier_block *nb); #else static inline struct net_device * br_fdb_find_port(const struct net_device *br_dev, @@ -200,7 +200,7 @@ static inline clock_t br_get_ageing_time(const struct net_device *br_dev) static inline int br_fdb_replay(const struct net_device *br_dev, const struct net_device *dev, const void *ctx, - struct notifier_block *nb) + bool adding, struct notifier_block *nb) { return -EOPNOTSUPP; } -- cgit v1.2.3 From a358f40600b3b39ae3906b6118625b99c0aa7a34 Mon Sep 17 00:00:00 2001 From: Tanner Love Date: Mon, 28 Jun 2021 09:50:06 -0400 Subject: once: implement DO_ONCE_LITE for non-fast-path "do once" functionality Certain uses of "do once" functionality reside outside of fast path, and so do not require jump label patching via static keys, making existing DO_ONCE undesirable in such cases. Replace uses of __section(".data.once") with DO_ONCE_LITE(_IF)? This patch changes the return values of xfs_printk_once, printk_once, and printk_deferred_once. Before, they returned whether the print was performed, but now, they always return true. This is okay because the return values of the following macros are entirely ignored throughout the kernel: - xfs_printk_once - xfs_warn_once - xfs_notice_once - xfs_info_once - printk_once - pr_emerg_once - pr_alert_once - pr_crit_once - pr_err_once - pr_warn_once - pr_notice_once - pr_info_once - pr_devel_once - pr_debug_once - printk_deferred_once - orc_warn Changes v3: - Expand commit message to explain why changing return values of xfs_printk_once, printk_once, printk_deferred_once is benign v2: - Fix i386 build warnings Signed-off-by: Tanner Love Acked-by: Eric Dumazet Acked-by: Mahesh Bandewar Acked-by: Steven Rostedt (VMware) Signed-off-by: David S. Miller --- include/linux/once_lite.h | 24 ++++++++++++++++++++++++ include/linux/printk.h | 23 +++-------------------- 2 files changed, 27 insertions(+), 20 deletions(-) create mode 100644 include/linux/once_lite.h (limited to 'include/linux') diff --git a/include/linux/once_lite.h b/include/linux/once_lite.h new file mode 100644 index 000000000000..861e606b820f --- /dev/null +++ b/include/linux/once_lite.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_ONCE_LITE_H +#define _LINUX_ONCE_LITE_H + +#include + +/* Call a function once. Similar to DO_ONCE(), but does not use jump label + * patching via static keys. + */ +#define DO_ONCE_LITE(func, ...) \ + DO_ONCE_LITE_IF(true, func, ##__VA_ARGS__) +#define DO_ONCE_LITE_IF(condition, func, ...) \ + ({ \ + static bool __section(".data.once") __already_done; \ + bool __ret_do_once = !!(condition); \ + \ + if (unlikely(__ret_do_once && !__already_done)) { \ + __already_done = true; \ + func(__VA_ARGS__); \ + } \ + unlikely(__ret_do_once); \ + }) + +#endif /* _LINUX_ONCE_LITE_H */ diff --git a/include/linux/printk.h b/include/linux/printk.h index fe7eb2351610..885379a1c9a1 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -8,6 +8,7 @@ #include #include #include +#include extern const char linux_banner[]; extern const char linux_proc_banner[]; @@ -436,27 +437,9 @@ extern int kptr_restrict; #ifdef CONFIG_PRINTK #define printk_once(fmt, ...) \ -({ \ - static bool __section(".data.once") __print_once; \ - bool __ret_print_once = !__print_once; \ - \ - if (!__print_once) { \ - __print_once = true; \ - printk(fmt, ##__VA_ARGS__); \ - } \ - unlikely(__ret_print_once); \ -}) + DO_ONCE_LITE(printk, fmt, ##__VA_ARGS__) #define printk_deferred_once(fmt, ...) \ -({ \ - static bool __section(".data.once") __print_once; \ - bool __ret_print_once = !__print_once; \ - \ - if (!__print_once) { \ - __print_once = true; \ - printk_deferred(fmt, ##__VA_ARGS__); \ - } \ - unlikely(__ret_print_once); \ -}) + DO_ONCE_LITE(printk_deferred, fmt, ##__VA_ARGS__) #else #define printk_once(fmt, ...) \ no_printk(fmt, ##__VA_ARGS__) -- cgit v1.2.3 From 9913d5745bd720c4266805c8d29952a3702e4eca Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Tue, 29 Jun 2021 09:40:10 -0400 Subject: tracepoint: Add tracepoint_probe_register_may_exist() for BPF tracing All internal use cases for tracepoint_probe_register() is set to not ever be called with the same function and data. If it is, it is considered a bug, as that means the accounting of handling tracepoints is corrupted. If the function and data for a tracepoint is already registered when tracepoint_probe_register() is called, it will call WARN_ON_ONCE() and return with EEXISTS. The BPF system call can end up calling tracepoint_probe_register() with the same data, which now means that this can trigger the warning because of a user space process. As WARN_ON_ONCE() should not be called because user space called a system call with bad data, there needs to be a way to register a tracepoint without triggering a warning. Enter tracepoint_probe_register_may_exist(), which can be called, but will not cause a WARN_ON() if the probe already exists. It will still error out with EEXIST, which will then be sent to the user space that performed the BPF system call. This keeps the previous testing for issues with other users of the tracepoint code, while letting BPF call it with duplicated data and not warn about it. Link: https://lore.kernel.org/lkml/20210626135845.4080-1-penguin-kernel@I-love.SAKURA.ne.jp/ Link: https://syzkaller.appspot.com/bug?id=41f4318cf01762389f4d1c1c459da4f542fe5153 Cc: stable@vger.kernel.org Fixes: c4f6699dfcb85 ("bpf: introduce BPF_RAW_TRACEPOINT") Reported-by: syzbot Reported-by: Tetsuo Handa Tested-by: syzbot+721aa903751db87aa244@syzkaller.appspotmail.com Signed-off-by: Steven Rostedt (VMware) --- include/linux/tracepoint.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 13f65420f188..ab58696d0ddd 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -41,7 +41,17 @@ extern int tracepoint_probe_register_prio(struct tracepoint *tp, void *probe, void *data, int prio); extern int +tracepoint_probe_register_prio_may_exist(struct tracepoint *tp, void *probe, void *data, + int prio); +extern int tracepoint_probe_unregister(struct tracepoint *tp, void *probe, void *data); +static inline int +tracepoint_probe_register_may_exist(struct tracepoint *tp, void *probe, + void *data) +{ + return tracepoint_probe_register_prio_may_exist(tp, probe, data, + TRACEPOINT_DEFAULT_PRIO); +} extern void for_each_kernel_tracepoint(void (*fct)(struct tracepoint *tp, void *priv), void *priv); -- cgit v1.2.3 From 82c850c12fc250bdba25e7e66f54adab2ffcfcd6 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 27 Jun 2021 17:40:12 -0700 Subject: : correct a function name in kernel-doc MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix kernel-doc function name warning: ../include/linux/dma-resv.h:227: warning: expecting prototype for dma_resv_exclusive(). Prototype was for dma_resv_excl_fence() instead Fixes: 6edbd6abb783d ("dma-buf: rename and cleanup dma_resv_get_excl v3") Signed-off-by: Randy Dunlap Cc: Sumit Semwal Cc: Christian König Cc: linux-media@vger.kernel.org Cc: dri-devel@lists.freedesktop.org Cc: linaro-mm-sig@lists.linaro.org Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210628004012.6792-1-rdunlap@infradead.org --- include/linux/dma-resv.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index 562b885cf9c3..e1ca2080a1ff 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -212,7 +212,7 @@ static inline void dma_resv_unlock(struct dma_resv *obj) } /** - * dma_resv_exclusive - return the object's exclusive fence + * dma_resv_excl_fence - return the object's exclusive fence * @obj: the reservation object * * Returns the exclusive fence (if any). Caller must either hold the objects -- cgit v1.2.3 From e97bc66377bca097e1f3349ca18ca17f202ff659 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 11 May 2021 23:41:10 -0400 Subject: NFS: nfs_find_open_context() may only select open files If a file has already been closed, then it should not be selected to support further I/O. Signed-off-by: Trond Myklebust [Trond: Fix an invalid pointer deref reported by Colin Ian King] --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index ffba254d2098..ce6474594872 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -84,6 +84,7 @@ struct nfs_open_context { #define NFS_CONTEXT_RESEND_WRITES (1) #define NFS_CONTEXT_BAD (2) #define NFS_CONTEXT_UNLOCK (3) +#define NFS_CONTEXT_FILE_OPEN (4) int error; struct list_head list; -- cgit v1.2.3 From 122e093c1734361dedb64f65c99b93e28e4624f4 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Mon, 28 Jun 2021 19:33:26 -0700 Subject: mm/page_alloc: fix memory map initialization for descending nodes On systems with memory nodes sorted in descending order, for instance Dell Precision WorkStation T5500, the struct pages for higher PFNs and respectively lower nodes, could be overwritten by the initialization of struct pages corresponding to the holes in the memory sections. For example for the below memory layout [ 0.245624] Early memory node ranges [ 0.248496] node 1: [mem 0x0000000000001000-0x0000000000090fff] [ 0.251376] node 1: [mem 0x0000000000100000-0x00000000dbdf8fff] [ 0.254256] node 1: [mem 0x0000000100000000-0x0000001423ffffff] [ 0.257144] node 0: [mem 0x0000001424000000-0x0000002023ffffff] the range 0x1424000000 - 0x1428000000 in the beginning of node 0 starts in the middle of a section and will be considered as a hole during the initialization of the last section in node 1. The wrong initialization of the memory map causes panic on boot when CONFIG_DEBUG_VM is enabled. Reorder loop order of the memory map initialization so that the outer loop will always iterate over populated memory regions in the ascending order and the inner loop will select the zone corresponding to the PFN range. This way initialization of the struct pages for the memory holes will be always done for the ranges that are actually not populated. [akpm@linux-foundation.org: coding style fixes] Link: https://lkml.kernel.org/r/YNXlMqBbL+tBG7yq@kernel.org Link: https://bugzilla.kernel.org/show_bug.cgi?id=213073 Link: https://lkml.kernel.org/r/20210624062305.10940-1-rppt@kernel.org Fixes: 0740a50b9baa ("mm/page_alloc.c: refactor initialization of struct page for holes in memory layout") Signed-off-by: Mike Rapoport Cc: Boris Petkov Cc: Robert Shteynfeld Cc: Baoquan He Cc: Vlastimil Babka Cc: David Hildenbrand Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 8ae31622deef..9afb8998e7e5 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2474,7 +2474,6 @@ extern void set_dma_reserve(unsigned long new_dma_reserve); extern void memmap_init_range(unsigned long, int, unsigned long, unsigned long, unsigned long, enum meminit_context, struct vmem_altmap *, int migratetype); -extern void memmap_init_zone(struct zone *zone); extern void setup_per_zone_wmarks(void); extern int __meminit init_per_zone_wmark_min(void); extern void mem_init(void); -- cgit v1.2.3 From 20ce0c2d5a303c41c0e02ceb596837868e290dcc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jonathan=20Neusch=C3=A4fer?= Date: Mon, 28 Jun 2021 19:33:32 -0700 Subject: kthread: switch to new kerneldoc syntax for named variable macro argument MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The syntax without dots is available since commit 43756e347f21 ("scripts/kernel-doc: Add support for named variable macro arguments"). The same HTML output is produced with and without this patch. Link: https://lkml.kernel.org/r/20210513161702.1721039-1-j.neuschaefer@gmx.net Signed-off-by: Jonathan Neuschäfer Cc: Jens Axboe Cc: Felix Kuehling Cc: Valentin Schneider Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kthread.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 2484ed97e72f..db3eafea168f 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -18,7 +18,7 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), * @threadfn: the function to run in the thread * @data: data pointer for @threadfn() * @namefmt: printf-style format string for the thread name - * @arg...: arguments for @namefmt. + * @arg: arguments for @namefmt. * * This macro will create a kthread on the current node, leaving it in * the stopped state. This is just a helper for kthread_create_on_node(); -- cgit v1.2.3 From 588c7fa022d7b2361500ead5660d9a1a2ecd9b7d Mon Sep 17 00:00:00 2001 From: Hyeonggon Yoo <42.hyeyoo@gmail.com> Date: Mon, 28 Jun 2021 19:34:39 -0700 Subject: mm, slub: change run-time assertion in kmalloc_index() to compile-time Currently when size is not supported by kmalloc_index, compiler will generate a run-time BUG() while compile-time error is also possible, and better. So change BUG to BUILD_BUG_ON_MSG to make compile-time check possible. Also remove code that allocates more than 32MB because current implementation supports only up to 32MB. [42.hyeyoo@gmail.com: fix support for clang 10] Link: https://lkml.kernel.org/r/20210518181247.GA10062@hyeyoo [vbabka@suse.cz: fix false-positive assert in kernel/bpf/local_storage.c] Link: https://lkml.kernel.org/r/bea97388-01df-8eac-091b-a3c89b4a4a09@suse.czLink: https://lkml.kernel.org/r/20210511173448.GA54466@hyeyoo [elver@google.com: kfence fix] Link: https://lkml.kernel.org/r/20210512195227.245000695c9014242e9a00e5@linux-foundation.org Signed-off-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Signed-off-by: Vlastimil Babka Reviewed-by: Vlastimil Babka Signed-off-by: Marco Elver Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Marco Elver Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 0c97d788762c..bc9ab3a5a017 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -346,8 +346,14 @@ static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags) * 1 = 65 .. 96 bytes * 2 = 129 .. 192 bytes * n = 2^(n-1)+1 .. 2^n + * + * Note: __kmalloc_index() is compile-time optimized, and not runtime optimized; + * typical usage is via kmalloc_index() and therefore evaluated at compile-time. + * Callers where !size_is_constant should only be test modules, where runtime + * overheads of __kmalloc_index() can be tolerated. Also see kmalloc_slab(). */ -static __always_inline unsigned int kmalloc_index(size_t size) +static __always_inline unsigned int __kmalloc_index(size_t size, + bool size_is_constant) { if (!size) return 0; @@ -382,12 +388,17 @@ static __always_inline unsigned int kmalloc_index(size_t size) if (size <= 8 * 1024 * 1024) return 23; if (size <= 16 * 1024 * 1024) return 24; if (size <= 32 * 1024 * 1024) return 25; - if (size <= 64 * 1024 * 1024) return 26; - BUG(); + + if ((IS_ENABLED(CONFIG_CC_IS_GCC) || CONFIG_CLANG_VERSION >= 110000) + && !IS_ENABLED(CONFIG_PROFILE_ALL_BRANCHES) && size_is_constant) + BUILD_BUG_ON_MSG(1, "unexpected size in kmalloc_index()"); + else + BUG(); /* Will never be reached. Needed because the compiler may complain */ return -1; } +#define kmalloc_index(s) __kmalloc_index(s, true) #endif /* !CONFIG_SLOB */ void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __malloc; -- cgit v1.2.3 From 792702911f581f7793962fbeb99d5c3a1b28f4c3 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Mon, 28 Jun 2021 19:34:52 -0700 Subject: slub: force on no_hash_pointers when slub_debug is enabled Obscuring the pointers that slub shows when debugging makes for some confusing slub debug messages: Padding overwritten. 0x0000000079f0674a-0x000000000d4dce17 Those addresses are hashed for kernel security reasons. If we're trying to be secure with slub_debug on the commandline we have some big problems given that we dump whole chunks of kernel memory to the kernel logs. Let's force on the no_hash_pointers commandline flag when slub_debug is on the commandline. This makes slub debug messages more meaningful and if by chance a kernel address is in some slub debug object dump we will have a better chance of figuring out what went wrong. Note that we don't use %px in the slub code because we want to reduce the number of places that %px is used in the kernel. This also nicely prints a big fat warning at kernel boot if slub_debug is on the commandline so that we know that this kernel shouldn't be used on production systems. [akpm@linux-foundation.org: fix build with CONFIG_SLUB_DEBUG=n] Link: https://lkml.kernel.org/r/20210601182202.3011020-5-swboyd@chromium.org Signed-off-by: Stephen Boyd Acked-by: Vlastimil Babka Acked-by: Petr Mladek Cc: Joe Perches Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Muchun Song Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 15d8bad3d2f2..bf950621febf 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -357,6 +357,8 @@ int sscanf(const char *, const char *, ...); extern __scanf(2, 0) int vsscanf(const char *, const char *, va_list); +extern int no_hash_pointers_enable(char *str); + extern int get_option(char **str, int *pint); extern char *get_options(const char *str, int nints, int *ints); extern unsigned long long memparse(const char *ptr, char **retptr); -- cgit v1.2.3 From 9f849c6f9572d8cef407f55928d3dc68fc42ad3e Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Mon, 28 Jun 2021 19:35:22 -0700 Subject: mm/page_reporting: allow driver to specify reporting order The page reporting order (threshold) is sticky to @pageblock_order by default. The page reporting can never be triggered because the freeing page can't come up with a free area like that huge. The situation becomes worse when the system memory becomes heavily fragmented. For example, the following configurations are used on ARM64 when 64KB base page size is enabled. In this specific case, the page reporting won't be triggered until the freeing page comes up with a 512MB free area. That's hard to be met, especially when the system memory becomes heavily fragmented. PAGE_SIZE: 64KB HPAGE_SIZE: 512MB pageblock_order: 13 (512MB) MAX_ORDER: 14 This allows the drivers to specify the page reporting order when the page reporting device is registered. It falls back to @pageblock_order if it's not specified by the driver. The existing users (hv_balloon and virtio_balloon) don't specify it and @pageblock_order is still taken as their page reporting order. So this shouldn't introduce any functional changes. Link: https://lkml.kernel.org/r/20210625014710.42954-4-gshan@redhat.com Signed-off-by: Gavin Shan Reviewed-by: Alexander Duyck Cc: Anshuman Khandual Cc: Catalin Marinas Cc: David Hildenbrand Cc: "Michael S. Tsirkin" Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_reporting.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/page_reporting.h b/include/linux/page_reporting.h index 3b99e0ec24f2..fe648dfa3a7c 100644 --- a/include/linux/page_reporting.h +++ b/include/linux/page_reporting.h @@ -18,6 +18,9 @@ struct page_reporting_dev_info { /* Current state of page reporting */ atomic_t state; + + /* Minimal order of page reporting */ + unsigned int order; }; /* Tear-down and bring-up for page reporting devices */ -- cgit v1.2.3 From f3b6a6df38aa514d97e8c6fcc748be1d4142bec9 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Mon, 28 Jun 2021 19:35:53 -0700 Subject: writeback, cgroup: keep list of inodes attached to bdi_writeback Currently there is no way to iterate over inodes attached to a specific cgwb structure. It limits the ability to efficiently reclaim the writeback structure itself and associated memory and block cgroup structures without scanning all inodes belonging to a sb, which can be prohibitively expensive. While dirty/in-active-writeback an inode belongs to one of the bdi_writeback's io lists: b_dirty, b_io, b_more_io and b_dirty_time. Once cleaned up, it's removed from all io lists. So the inode->i_io_list can be reused to maintain the list of inodes, attached to a bdi_writeback structure. This patch introduces a new wb->b_attached list, which contains all inodes which were dirty at least once and are attached to the given cgwb. Inodes attached to the root bdi_writeback structures are never placed on such list. The following patch will use this list to try to release cgwbs structures more efficiently. Link: https://lkml.kernel.org/r/20210608230225.2078447-6-guro@fb.com Signed-off-by: Roman Gushchin Suggested-by: Jan Kara Reviewed-by: Jan Kara Acked-by: Tejun Heo Acked-by: Dennis Zhou Cc: Alexander Viro Cc: Dave Chinner Cc: Jan Kara Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/backing-dev-defs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index fff9367a6348..e5dc238ebe4f 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -154,6 +154,7 @@ struct bdi_writeback { struct cgroup_subsys_state *blkcg_css; /* and blkcg */ struct list_head memcg_node; /* anchored at memcg->cgwb_list */ struct list_head blkcg_node; /* anchored at blkcg->cgwb_list */ + struct list_head b_attached; /* attached inodes, protected by list_lock */ union { struct work_struct release_work; -- cgit v1.2.3 From f5fbe6b7ad6ef1fbdf8074a6ca9fdab739bf86d4 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Mon, 28 Jun 2021 19:35:59 -0700 Subject: writeback, cgroup: support switching multiple inodes at once Currently only a single inode can be switched to another writeback structure at once. That means to switch an inode a separate inode_switch_wbs_context structure must be allocated, and a separate rcu callback and work must be scheduled. It's fine for the existing ad-hoc switching, which is not happening that often, but sub-optimal for massive switching required in order to release a writeback structure. To prepare for it, let's add a support for switching multiple inodes at once. Instead of containing a single inode pointer, inode_switch_wbs_context will contain a NULL-terminated array of inode pointers. inode_do_switch_wbs() will be called for each inode. To optimize the locking bdi->wb_switch_rwsem, old_wb's and new_wb's list_locks will be acquired and released only once altogether for all inodes. wb_wakeup() will be also be called only once. Instead of calling wb_put(old_wb) after each successful switch, wb_put_many() is introduced and used. Link: https://lkml.kernel.org/r/20210608230225.2078447-8-guro@fb.com Signed-off-by: Roman Gushchin Acked-by: Tejun Heo Reviewed-by: Jan Kara Acked-by: Dennis Zhou Cc: Alexander Viro Cc: Dave Chinner Cc: Jan Kara Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/backing-dev-defs.h | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index e5dc238ebe4f..63f52ad2ce7a 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -240,8 +240,9 @@ static inline void wb_get(struct bdi_writeback *wb) /** * wb_put - decrement a wb's refcount * @wb: bdi_writeback to put + * @nr: number of references to put */ -static inline void wb_put(struct bdi_writeback *wb) +static inline void wb_put_many(struct bdi_writeback *wb, unsigned long nr) { if (WARN_ON_ONCE(!wb->bdi)) { /* @@ -252,7 +253,16 @@ static inline void wb_put(struct bdi_writeback *wb) } if (wb != &wb->bdi->wb) - percpu_ref_put(&wb->refcnt); + percpu_ref_put_many(&wb->refcnt, nr); +} + +/** + * wb_put - decrement a wb's refcount + * @wb: bdi_writeback to put + */ +static inline void wb_put(struct bdi_writeback *wb) +{ + wb_put_many(wb, 1); } /** @@ -281,6 +291,10 @@ static inline void wb_put(struct bdi_writeback *wb) { } +static inline void wb_put_many(struct bdi_writeback *wb, unsigned long nr) +{ +} + static inline bool wb_dying(struct bdi_writeback *wb) { return false; -- cgit v1.2.3 From c22d70a162d3cc177282c4487be4d54876ca55c8 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Mon, 28 Jun 2021 19:36:03 -0700 Subject: writeback, cgroup: release dying cgwbs by switching attached inodes Asynchronously try to release dying cgwbs by switching attached inodes to the nearest living ancestor wb. It helps to get rid of per-cgroup writeback structures themselves and of pinned memory and block cgroups, which are significantly larger structures (mostly due to large per-cpu statistics data). This prevents memory waste and helps to avoid different scalability problems caused by large piles of dying cgroups. Reuse the existing mechanism of inode switching used for foreign inode detection. To speed things up batch up to 115 inode switching in a single operation (the maximum number is selected so that the resulting struct inode_switch_wbs_context can fit into 1024 bytes). Because every switching consists of two steps divided by an RCU grace period, it would be too slow without batching. Please note that the whole batch counts as a single operation (when increasing/decreasing isw_nr_in_flight). This allows to keep umounting working (flush the switching queue), however prevents cleanups from consuming the whole switching quota and effectively blocking the frn switching. A cgwb cleanup operation can fail due to different reasons (e.g. not enough memory, the cgwb has an in-flight/pending io, an attached inode in a wrong state, etc). In this case the next scheduled cleanup will make a new attempt. An attempt is made each time a new cgwb is offlined (in other words a memcg and/or a blkcg is deleted by a user). In the future an additional attempt scheduled by a timer can be implemented. [guro@fb.com: replace open-coded "115" with arithmetic] Link: https://lkml.kernel.org/r/YMEcSBcq/VXMiPPO@carbon.dhcp.thefacebook.com [guro@fb.com: add smp_mb() to inode_prepare_wbs_switch()] Link: https://lkml.kernel.org/r/YMFa+guFw7OFjf3X@carbon.dhcp.thefacebook.com [willy@infradead.org: fix documentation] Link: https://lkml.kernel.org/r/20210615200242.1716568-2-willy@infradead.org Link: https://lkml.kernel.org/r/20210608230225.2078447-9-guro@fb.com Signed-off-by: Roman Gushchin Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Tejun Heo Acked-by: Dennis Zhou Reviewed-by: Jan Kara Cc: Alexander Viro Cc: Dave Chinner Cc: Jan Kara Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/backing-dev-defs.h | 1 + include/linux/writeback.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 63f52ad2ce7a..1d7edad9914f 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -155,6 +155,7 @@ struct bdi_writeback { struct list_head memcg_node; /* anchored at memcg->cgwb_list */ struct list_head blkcg_node; /* anchored at blkcg->cgwb_list */ struct list_head b_attached; /* attached inodes, protected by list_lock */ + struct list_head offline_node; /* anchored at offline_cgwbs */ union { struct work_struct release_work; diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 8e5c5bb16e2d..95de51c10248 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -221,6 +221,7 @@ void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page, int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, unsigned long nr_pages, enum wb_reason reason, struct wb_completion *done); void cgroup_writeback_umount(void); +bool cleanup_offline_cgwb(struct bdi_writeback *wb); /** * inode_attach_wb - associate an inode with its wb -- cgit v1.2.3 From c1e3dbe9818e3caa4e467255a348df56912ca549 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 28 Jun 2021 19:36:09 -0700 Subject: fs: move ramfs_aops to libfs Move the ramfs aops to libfs and reuse them for kernfs and configfs. Thosw two did not wire up ->set_page_dirty before and now get __set_page_dirty_no_writeback, which is the right one for no-writeback address_space usage. Drop the now unused exports of the libfs helpers only used for ramfs-style pagecache usage. Link: https://lkml.kernel.org/r/20210614061512.3966143-3-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jan Kara Cc: Al Viro Cc: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index c3c88fdb9b2a..869909345420 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3422,13 +3422,10 @@ extern void noop_invalidatepage(struct page *page, unsigned int offset, unsigned int length); extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter); extern int simple_empty(struct dentry *); -extern int simple_readpage(struct file *file, struct page *page); extern int simple_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata); -extern int simple_write_end(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata); +extern const struct address_space_operations ram_aops; extern int always_delete_dentry(const struct dentry *); extern struct inode *alloc_anon_inode(struct super_block *); extern int simple_nosetlease(struct file *, long, struct file_lock **, void **); -- cgit v1.2.3 From 6e1cae881a0646f31fe2bda90297d820da1137eb Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 28 Jun 2021 19:36:15 -0700 Subject: mm/writeback: move __set_page_dirty() to core mm Patch series "Further set_page_dirty cleanups". Prompted by Christoph's recent patches, here are some more patches to improve the state of set_page_dirty(). They're all from the folio tree, so they've been tested to a certain extent. This patch (of 6): Nothing in __set_page_dirty() is specific to buffer_head, so move it to mm/page-writeback.c. That removes the only caller of account_page_dirtied() outside of page-writeback.c, so make it static. Link: https://lkml.kernel.org/r/20210615162342.1669332-1-willy@infradead.org Link: https://lkml.kernel.org/r/20210615162342.1669332-2-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Greg Kroah-Hartman Cc: Jan Kara Cc: Al Viro Cc: Dan Williams Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9afb8998e7e5..12589b811555 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1855,7 +1855,6 @@ int __set_page_dirty_nobuffers(struct page *page); int __set_page_dirty_no_writeback(struct page *page); int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page); -void account_page_dirtied(struct page *page, struct address_space *mapping); void account_page_cleaned(struct page *page, struct address_space *mapping, struct bdi_writeback *wb); int set_page_dirty(struct page *page); -- cgit v1.2.3 From fd7353f88bde80d557b6d74a5351979fc8b1b8db Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 28 Jun 2021 19:36:21 -0700 Subject: iomap: use __set_page_dirty_nobuffers The only difference between iomap_set_page_dirty() and __set_page_dirty_nobuffers() is that the latter includes a debugging check that a !Uptodate page has private data. Link: https://lkml.kernel.org/r/20210615162342.1669332-4-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Cc: Al Viro Cc: Dan Williams Cc: Greg Kroah-Hartman Cc: Jan Kara Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/iomap.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index c87d0cb0de6d..479c1da3e221 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -159,7 +159,6 @@ ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, const struct iomap_ops *ops); int iomap_readpage(struct page *page, const struct iomap_ops *ops); void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops); -int iomap_set_page_dirty(struct page *page); int iomap_is_partially_uptodate(struct page *page, unsigned long from, unsigned long count); int iomap_releasepage(struct page *page, gfp_t gfp_mask); -- cgit v1.2.3 From b82a96c9253333a8834b2df5f262a39cccf4f6c7 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 28 Jun 2021 19:36:27 -0700 Subject: fs: remove noop_set_page_dirty() Use __set_page_dirty_no_writeback() instead. This will set the dirty bit on the page, which will be used to avoid calling set_page_dirty() in the future. It will have no effect on actually writing the page back, as the pages are not on any LRU lists. [akpm@linux-foundation.org: export __set_page_dirty_no_writeback() to modules] Link: https://lkml.kernel.org/r/20210615162342.1669332-6-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Cc: Al Viro Cc: Christoph Hellwig Cc: Dan Williams Cc: Greg Kroah-Hartman Cc: Jan Kara Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 869909345420..fad6663cd1b0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3417,7 +3417,6 @@ extern int simple_rename(struct user_namespace *, struct inode *, extern void simple_recursive_removal(struct dentry *, void (*callback)(struct dentry *)); extern int noop_fsync(struct file *, loff_t, loff_t, int); -extern int noop_set_page_dirty(struct page *page); extern void noop_invalidatepage(struct page *page, unsigned int offset, unsigned int length); extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter); -- cgit v1.2.3 From 3a6b2162005f24c7caa10d7f10dba487629787f2 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 28 Jun 2021 19:36:30 -0700 Subject: mm: move page dirtying prototypes from mm.h These functions implement the address_space ->set_page_dirty operation and should live in pagemap.h, not mm.h so that the rest of the kernel doesn't get funny ideas about calling them directly. Link: https://lkml.kernel.org/r/20210615162342.1669332-7-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Cc: Al Viro Cc: Dan Williams Cc: Greg Kroah-Hartman Cc: Jan Kara Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 --- include/linux/pagemap.h | 4 ++++ 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 12589b811555..e39ed497578b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1850,9 +1850,6 @@ extern int try_to_release_page(struct page * page, gfp_t gfp_mask); extern void do_invalidatepage(struct page *page, unsigned int offset, unsigned int length); -void __set_page_dirty(struct page *, struct address_space *, int warn); -int __set_page_dirty_nobuffers(struct page *page); -int __set_page_dirty_no_writeback(struct page *page); int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page); void account_page_cleaned(struct page *page, struct address_space *mapping, diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 0f1b34dbf3a2..ed02aa522263 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -702,6 +702,10 @@ int wait_on_page_writeback_killable(struct page *page); extern void end_page_writeback(struct page *page); void wait_for_stable_page(struct page *page); +void __set_page_dirty(struct page *, struct address_space *, int warn); +int __set_page_dirty_nobuffers(struct page *page); +int __set_page_dirty_no_writeback(struct page *page); + void page_endio(struct page *page, bool is_write, int err); /** -- cgit v1.2.3 From a458b76a4171f893efa7657dc079924580a8746a Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Mon, 28 Jun 2021 19:36:40 -0700 Subject: mm: gup: pack has_pinned in MMF_HAS_PINNED has_pinned 32bit can be packed in the MMF_HAS_PINNED bit as a noop cleanup. Any atomic_inc/dec to the mm cacheline shared by all threads in pin-fast would reintroduce a loss of SMP scalability to pin-fast, so there's no future potential usefulness to keep an atomic in the mm for this. set_bit(MMF_HAS_PINNED) will be theoretically a bit slower than WRITE_ONCE (atomic_set is equivalent to WRITE_ONCE), but the set_bit (just like atomic_set after this commit) has to be still issued only once per "mm", so the difference between the two will be lost in the noise. will-it-scale "mmap2" shows no change in performance with enterprise config as expected. will-it-scale "pin_fast" retains the > 4000% SMP scalability performance improvement against upstream as expected. This is a noop as far as overall performance and SMP scalability are concerned. [peterx@redhat.com: pack has_pinned in MMF_HAS_PINNED] Link: https://lkml.kernel.org/r/YJqWESqyxa8OZA+2@t490s [akpm@linux-foundation.org: coding style fixes] [peterx@redhat.com: fix build for task_mmu.c, introduce mm_set_has_pinned_flag, fix comments] Link: https://lkml.kernel.org/r/20210507150553.208763-4-peterx@redhat.com Signed-off-by: Andrea Arcangeli Signed-off-by: Peter Xu Reviewed-by: John Hubbard Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: Kirill Shutemov Cc: Kirill Tkhai Cc: Matthew Wilcox Cc: Michal Hocko Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- include/linux/mm_types.h | 10 ---------- include/linux/sched/coredump.h | 8 ++++++++ 3 files changed, 9 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index e39ed497578b..79f32962d7ae 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1341,7 +1341,7 @@ static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma, if (!is_cow_mapping(vma->vm_flags)) return false; - if (!atomic_read(&vma->vm_mm->has_pinned)) + if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags)) return false; return page_maybe_dma_pinned(page); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 8f0fb62e8975..b66d0225414e 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -435,16 +435,6 @@ struct mm_struct { */ atomic_t mm_count; - /** - * @has_pinned: Whether this mm has pinned any pages. This can - * be either replaced in the future by @pinned_vm when it - * becomes stable, or grow into a counter on its own. We're - * aggresive on this bit now - even if the pinned pages were - * unpinned later on, we'll still keep this bit set for the - * lifecycle of this mm just for simplicity. - */ - atomic_t has_pinned; - #ifdef CONFIG_MMU atomic_long_t pgtables_bytes; /* PTE page table pages */ #endif diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index dfd82eab2902..4d9e3a656875 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -73,6 +73,14 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_OOM_VICTIM 25 /* mm is the oom victim */ #define MMF_OOM_REAP_QUEUED 26 /* mm was queued for oom_reaper */ #define MMF_MULTIPROCESS 27 /* mm is shared between processes */ +/* + * MMF_HAS_PINNED: Whether this mm has pinned any pages. This can be either + * replaced in the future by mm.pinned_vm when it becomes stable, or grow into + * a counter on its own. We're aggresive on this bit for now: even if the + * pinned pages were unpinned later on, we'll still keep this bit set for the + * lifecycle of this mm, just for simplicity. + */ +#define MMF_HAS_PINNED 28 /* FOLL_PIN has run, never cleared */ #define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ -- cgit v1.2.3 From 63d8620ecf93b5d8d0a254471184d08f8e8f538d Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Mon, 28 Jun 2021 19:36:46 -0700 Subject: mm/swapfile: use percpu_ref to serialize against concurrent swapoff Patch series "close various race windows for swap", v6. When I was investigating the swap code, I found some possible race windows. This series aims to fix all these races. But using current get/put_swap_device() to guard against concurrent swapoff for swap_readpage() looks terrible because swap_readpage() may take really long time. And to reduce the performance overhead on the hot-path as much as possible, it appears we can use the percpu_ref to close this race window(as suggested by Huang, Ying). The patch 1 adds percpu_ref support for swap and most of the remaining patches try to use this to close various race windows. More details can be found in the respective changelogs. This patch (of 4): Using current get/put_swap_device() to guard against concurrent swapoff for some swap ops, e.g. swap_readpage(), looks terrible because they might take really long time. This patch adds the percpu_ref support to serialize against concurrent swapoff(as suggested by Huang, Ying). Also we remove the SWP_VALID flag because it's used together with RCU solution. Link: https://lkml.kernel.org/r/20210426123316.806267-1-linmiaohe@huawei.com Link: https://lkml.kernel.org/r/20210426123316.806267-2-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Reviewed-by: "Huang, Ying" Cc: Alex Shi Cc: David Hildenbrand Cc: Dennis Zhou Cc: Hugh Dickins Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Matthew Wilcox Cc: Michal Hocko Cc: Minchan Kim Cc: Tim Chen Cc: Wei Yang Cc: Yang Shi Cc: Yu Zhao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 144727041e78..c9e7fea10b83 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -177,7 +177,6 @@ enum { SWP_PAGE_DISCARD = (1 << 10), /* freed swap page-cluster discards */ SWP_STABLE_WRITES = (1 << 11), /* no overwrite PG_writeback pages */ SWP_SYNCHRONOUS_IO = (1 << 12), /* synchronous IO is efficient */ - SWP_VALID = (1 << 13), /* swap is valid to be operated on? */ /* add others here before... */ SWP_SCANNING = (1 << 14), /* refcount in scan_swap_map */ }; @@ -240,6 +239,7 @@ struct swap_cluster_list { * The in-memory structure used to track swap areas. */ struct swap_info_struct { + struct percpu_ref users; /* indicate and keep swap device valid. */ unsigned long flags; /* SWP_USED etc: see above */ signed short prio; /* swap priority of this type */ struct plist_node list; /* entry in swap_active_head */ @@ -260,6 +260,7 @@ struct swap_info_struct { struct block_device *bdev; /* swap device or bdev of swap file */ struct file *swap_file; /* seldom referenced */ unsigned int old_block_size; /* seldom referenced */ + struct completion comp; /* seldom referenced */ #ifdef CONFIG_FRONTSWAP unsigned long *frontswap_map; /* frontswap in-use, one bit per page */ atomic_t frontswap_pages; /* frontswap pages in-use counter */ @@ -511,7 +512,7 @@ sector_t swap_page_sector(struct page *page); static inline void put_swap_device(struct swap_info_struct *si) { - rcu_read_unlock(); + percpu_ref_put(&si->users); } #else /* CONFIG_SWAP */ -- cgit v1.2.3 From 2799e77529c2a25492a4395db93996e3dacd762d Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Mon, 28 Jun 2021 19:36:50 -0700 Subject: swap: fix do_swap_page() race with swapoff When I was investigating the swap code, I found the below possible race window: CPU 1 CPU 2 ----- ----- do_swap_page if (data_race(si->flags & SWP_SYNCHRONOUS_IO) swap_readpage if (data_race(sis->flags & SWP_FS_OPS)) { swapoff .. p->swap_file = NULL; .. struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping;[oops!] Note that for the pages that are swapped in through swap cache, this isn't an issue. Because the page is locked, and the swap entry will be marked with SWAP_HAS_CACHE, so swapoff() can not proceed until the page has been unlocked. Fix this race by using get/put_swap_device() to guard against concurrent swapoff. Link: https://lkml.kernel.org/r/20210426123316.806267-3-linmiaohe@huawei.com Fixes: 0bcac06f27d7 ("mm,swap: skip swapcache for swapin of synchronous device") Signed-off-by: Miaohe Lin Reviewed-by: "Huang, Ying" Cc: Alex Shi Cc: David Hildenbrand Cc: Dennis Zhou Cc: Hugh Dickins Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Matthew Wilcox Cc: Michal Hocko Cc: Minchan Kim Cc: Tim Chen Cc: Wei Yang Cc: Yang Shi Cc: Yu Zhao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index c9e7fea10b83..46d51d058d05 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -527,6 +527,15 @@ static inline struct swap_info_struct *swp_swap_info(swp_entry_t entry) return NULL; } +static inline struct swap_info_struct *get_swap_device(swp_entry_t entry) +{ + return NULL; +} + +static inline void put_swap_device(struct swap_info_struct *si) +{ +} + #define swap_address_space(entry) (NULL) #define get_nr_swap_pages() 0L #define total_swap_pages 0L -- cgit v1.2.3 From f4c4a3f48480730214c4f02ffa480f6bf5b0718f Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Mon, 28 Jun 2021 19:37:12 -0700 Subject: mm: free idle swap cache page after COW With commit 09854ba94c6a ("mm: do_wp_page() simplification"), after COW, the idle swap cache page (neither the page nor the corresponding swap entry is mapped by any process) will be left in the LRU list, even if it's in the active list or the head of the inactive list. So, the page reclaimer may take quite some overhead to reclaim these actually unused pages. To help the page reclaiming, in this patch, after COW, the idle swap cache page will be tried to be freed. To avoid to introduce much overhead to the hot COW code path, a) there's almost zero overhead for non-swap case via checking PageSwapCache() firstly. b) the page lock is acquired via trylock only. To test the patch, we used pmbench memory accessing benchmark with working-set larger than available memory on a 2-socket Intel server with a NVMe SSD as swap device. Test results shows that the pmbench score increases up to 23.8% with the decreased size of swap cache and swapin throughput. Link: https://lkml.kernel.org/r/20210601053143.1380078-1-ying.huang@intel.com Signed-off-by: "Huang, Ying" Suggested-by: Johannes Weiner [use free_swap_cache()] Acked-by: Johannes Weiner Cc: Hugh Dickins Cc: Matthew Wilcox Cc: Peter Xu Cc: Mel Gorman Cc: Rik van Riel Cc: Andrea Arcangeli Cc: Michal Hocko Cc: Dave Hansen Cc: Tim Chen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 46d51d058d05..49b1dd2c100b 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -446,6 +446,7 @@ extern void __delete_from_swap_cache(struct page *page, extern void delete_from_swap_cache(struct page *); extern void clear_shadow_from_swap_cache(int type, unsigned long begin, unsigned long end); +extern void free_swap_cache(struct page *); extern void free_page_and_swap_cache(struct page *); extern void free_pages_and_swap_cache(struct page **, int); extern struct page *lookup_swap_cache(swp_entry_t entry, @@ -551,6 +552,10 @@ static inline void put_swap_device(struct swap_info_struct *si) #define free_pages_and_swap_cache(pages, nr) \ release_pages((pages), (nr)); +static inline void free_swap_cache(struct page *page) +{ +} + static inline void show_swap_cache_info(void) { } -- cgit v1.2.3 From 494c1dfe855ec1f70f89552fce5eadf4a1717552 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Mon, 28 Jun 2021 19:37:38 -0700 Subject: mm: memcg/slab: create a new set of kmalloc-cg- caches There are currently two problems in the way the objcg pointer array (memcg_data) in the page structure is being allocated and freed. On its allocation, it is possible that the allocated objcg pointer array comes from the same slab that requires memory accounting. If this happens, the slab will never become empty again as there is at least one object left (the obj_cgroup array) in the slab. When it is freed, the objcg pointer array object may be the last one in its slab and hence causes kfree() to be called again. With the right workload, the slab cache may be set up in a way that allows the recursive kfree() calling loop to nest deep enough to cause a kernel stack overflow and panic the system. One way to solve this problem is to split the kmalloc- caches (KMALLOC_NORMAL) into two separate sets - a new set of kmalloc- (KMALLOC_NORMAL) caches for unaccounted objects only and a new set of kmalloc-cg- (KMALLOC_CGROUP) caches for accounted objects only. All the other caches can still allow a mix of accounted and unaccounted objects. With this change, all the objcg pointer array objects will come from KMALLOC_NORMAL caches which won't have their objcg pointer arrays. So both the recursive kfree() problem and non-freeable slab problem are gone. Since both the KMALLOC_NORMAL and KMALLOC_CGROUP caches no longer have mixed accounted and unaccounted objects, this will slightly reduce the number of objcg pointer arrays that need to be allocated and save a bit of memory. On the other hand, creating a new set of kmalloc caches does have the effect of reducing cache utilization. So it is properly a wash. The new KMALLOC_CGROUP is added between KMALLOC_NORMAL and KMALLOC_RECLAIM so that the first for loop in create_kmalloc_caches() will include the newly added caches without change. [vbabka@suse.cz: don't create kmalloc-cg caches with cgroup.memory=nokmem] Link: https://lkml.kernel.org/r/20210512145107.6208-1-longman@redhat.com [akpm@linux-foundation.org: un-fat-finger v5 delta creation] [longman@redhat.com: disable cache merging for KMALLOC_NORMAL caches] Link: https://lkml.kernel.org/r/20210505200610.13943-4-longman@redhat.com Link: https://lkml.kernel.org/r/20210512145107.6208-1-longman@redhat.com Link: https://lkml.kernel.org/r/20210505200610.13943-3-longman@redhat.com Signed-off-by: Waiman Long Signed-off-by: Vlastimil Babka Suggested-by: Vlastimil Babka Reviewed-by: Shakeel Butt Acked-by: Roman Gushchin Cc: Christoph Lameter Cc: David Rientjes Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Michal Hocko Cc: Pekka Enberg Cc: Vladimir Davydov [longman@redhat.com: fix for CONFIG_ZONE_DMA=n] Suggested-by: Roman Gushchin Reviewed-by: Vlastimil Babka Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 42 +++++++++++++++++++++++++++++++++--------- 1 file changed, 33 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index bc9ab3a5a017..083f3ce550bc 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -305,9 +305,21 @@ static inline void __check_heap_object(const void *ptr, unsigned long n, /* * Whenever changing this, take care of that kmalloc_type() and * create_kmalloc_caches() still work as intended. + * + * KMALLOC_NORMAL can contain only unaccounted objects whereas KMALLOC_CGROUP + * is for accounted but unreclaimable and non-dma objects. All the other + * kmem caches can have both accounted and unaccounted objects. */ enum kmalloc_cache_type { KMALLOC_NORMAL = 0, +#ifndef CONFIG_ZONE_DMA + KMALLOC_DMA = KMALLOC_NORMAL, +#endif +#ifndef CONFIG_MEMCG_KMEM + KMALLOC_CGROUP = KMALLOC_NORMAL, +#else + KMALLOC_CGROUP, +#endif KMALLOC_RECLAIM, #ifdef CONFIG_ZONE_DMA KMALLOC_DMA, @@ -319,24 +331,36 @@ enum kmalloc_cache_type { extern struct kmem_cache * kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1]; +/* + * Define gfp bits that should not be set for KMALLOC_NORMAL. + */ +#define KMALLOC_NOT_NORMAL_BITS \ + (__GFP_RECLAIMABLE | \ + (IS_ENABLED(CONFIG_ZONE_DMA) ? __GFP_DMA : 0) | \ + (IS_ENABLED(CONFIG_MEMCG_KMEM) ? __GFP_ACCOUNT : 0)) + static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags) { -#ifdef CONFIG_ZONE_DMA /* * The most common case is KMALLOC_NORMAL, so test for it - * with a single branch for both flags. + * with a single branch for all the relevant flags. */ - if (likely((flags & (__GFP_DMA | __GFP_RECLAIMABLE)) == 0)) + if (likely((flags & KMALLOC_NOT_NORMAL_BITS) == 0)) return KMALLOC_NORMAL; /* - * At least one of the flags has to be set. If both are, __GFP_DMA - * is more important. + * At least one of the flags has to be set. Their priorities in + * decreasing order are: + * 1) __GFP_DMA + * 2) __GFP_RECLAIMABLE + * 3) __GFP_ACCOUNT */ - return flags & __GFP_DMA ? KMALLOC_DMA : KMALLOC_RECLAIM; -#else - return flags & __GFP_RECLAIMABLE ? KMALLOC_RECLAIM : KMALLOC_NORMAL; -#endif + if (IS_ENABLED(CONFIG_ZONE_DMA) && (flags & __GFP_DMA)) + return KMALLOC_DMA; + if (!IS_ENABLED(CONFIG_MEMCG_KMEM) || (flags & __GFP_RECLAIMABLE)) + return KMALLOC_RECLAIM; + else + return KMALLOC_CGROUP; } /* -- cgit v1.2.3 From a984226f457f849eb9c4ce727eeaa3b5080597d8 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Mon, 28 Jun 2021 19:37:53 -0700 Subject: mm: memcontrol: remove the pgdata parameter of mem_cgroup_page_lruvec All the callers of mem_cgroup_page_lruvec() just pass page_pgdat(page) as the 2nd parameter to it (except isolate_migratepages_block()). But for isolate_migratepages_block(), the page_pgdat(page) is also equal to the local variable of @pgdat. So mem_cgroup_page_lruvec() do not need the pgdat parameter. Just remove it to simplify the code. Link: https://lkml.kernel.org/r/20210417043538.9793-4-songmuchun@bytedance.com Signed-off-by: Muchun Song Acked-by: Johannes Weiner Reviewed-by: Shakeel Butt Acked-by: Roman Gushchin Acked-by: Michal Hocko Cc: Vladimir Davydov Cc: Xiongchun Duan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index c193be760709..f2a5aaba3577 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -743,13 +743,12 @@ out: /** * mem_cgroup_page_lruvec - return lruvec for isolating/putting an LRU page * @page: the page - * @pgdat: pgdat of the page * * This function relies on page->mem_cgroup being stable. */ -static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page, - struct pglist_data *pgdat) +static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page) { + pg_data_t *pgdat = page_pgdat(page); struct mem_cgroup *memcg = page_memcg(page); VM_WARN_ON_ONCE_PAGE(!memcg && !mem_cgroup_disabled(), page); @@ -1221,9 +1220,10 @@ static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, return &pgdat->__lruvec; } -static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page, - struct pglist_data *pgdat) +static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page) { + pg_data_t *pgdat = page_pgdat(page); + return &pgdat->__lruvec; } -- cgit v1.2.3 From f2e4d28dd9f6478dd54d47b91edc3fe62c019968 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Mon, 28 Jun 2021 19:37:56 -0700 Subject: mm: memcontrol: simplify lruvec_holds_page_lru_lock We already have a helper lruvec_memcg() to get the memcg from lruvec, we do not need to do it ourselves in the lruvec_holds_page_lru_lock(). So use lruvec_memcg() instead. And if mem_cgroup_disabled() returns false, the page_memcg(page) (the LRU pages) cannot be NULL. So remove the odd logic of "memcg = page_memcg(page) ? : root_mem_cgroup". And use lruvec_pgdat to simplify the code. We can have a single definition for this function that works for !CONFIG_MEMCG, CONFIG_MEMCG + mem_cgroup_disabled() and CONFIG_MEMCG. Link: https://lkml.kernel.org/r/20210417043538.9793-5-songmuchun@bytedance.com Signed-off-by: Muchun Song Acked-by: Johannes Weiner Reviewed-by: Shakeel Butt Acked-by: Roman Gushchin Acked-by: Michal Hocko Cc: Vladimir Davydov Cc: Xiongchun Duan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 31 +++++++------------------------ 1 file changed, 7 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index f2a5aaba3577..2fc728492c9b 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -755,22 +755,6 @@ static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page) return mem_cgroup_lruvec(memcg, pgdat); } -static inline bool lruvec_holds_page_lru_lock(struct page *page, - struct lruvec *lruvec) -{ - pg_data_t *pgdat = page_pgdat(page); - const struct mem_cgroup *memcg; - struct mem_cgroup_per_node *mz; - - if (mem_cgroup_disabled()) - return lruvec == &pgdat->__lruvec; - - mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); - memcg = page_memcg(page) ? : root_mem_cgroup; - - return lruvec->pgdat == pgdat && mz->memcg == memcg; -} - struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm); @@ -1227,14 +1211,6 @@ static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page) return &pgdat->__lruvec; } -static inline bool lruvec_holds_page_lru_lock(struct page *page, - struct lruvec *lruvec) -{ - pg_data_t *pgdat = page_pgdat(page); - - return lruvec == &pgdat->__lruvec; -} - static inline void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page) { } @@ -1516,6 +1492,13 @@ static inline void unlock_page_lruvec_irqrestore(struct lruvec *lruvec, spin_unlock_irqrestore(&lruvec->lru_lock, flags); } +static inline bool lruvec_holds_page_lru_lock(struct page *page, + struct lruvec *lruvec) +{ + return lruvec_pgdat(lruvec) == page_pgdat(page) && + lruvec_memcg(lruvec) == page_memcg(page); +} + /* Don't lock again iff page's lruvec locked */ static inline struct lruvec *relock_page_lruvec_irq(struct page *page, struct lruvec *locked_lruvec) -- cgit v1.2.3 From 7467c39128bda1d58af08aaeb0c7ba54d0ec87ae Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Mon, 28 Jun 2021 19:37:59 -0700 Subject: mm: memcontrol: rename lruvec_holds_page_lru_lock to page_matches_lruvec lruvec_holds_page_lru_lock() doesn't check anything about locking and is used to check whether the page belongs to the lruvec. So rename it to page_matches_lruvec(). Link: https://lkml.kernel.org/r/20210417043538.9793-6-songmuchun@bytedance.com Signed-off-by: Muchun Song Acked-by: Michal Hocko Acked-by: Johannes Weiner Reviewed-by: Shakeel Butt Cc: Roman Gushchin Cc: Vladimir Davydov Cc: Xiongchun Duan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 2fc728492c9b..0ce97eff79e2 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1492,8 +1492,8 @@ static inline void unlock_page_lruvec_irqrestore(struct lruvec *lruvec, spin_unlock_irqrestore(&lruvec->lru_lock, flags); } -static inline bool lruvec_holds_page_lru_lock(struct page *page, - struct lruvec *lruvec) +/* Test requires a stable page->memcg binding, see page_memcg() */ +static inline bool page_matches_lruvec(struct page *page, struct lruvec *lruvec) { return lruvec_pgdat(lruvec) == page_pgdat(page) && lruvec_memcg(lruvec) == page_memcg(page); @@ -1504,7 +1504,7 @@ static inline struct lruvec *relock_page_lruvec_irq(struct page *page, struct lruvec *locked_lruvec) { if (locked_lruvec) { - if (lruvec_holds_page_lru_lock(page, locked_lruvec)) + if (page_matches_lruvec(page, locked_lruvec)) return locked_lruvec; unlock_page_lruvec_irq(locked_lruvec); @@ -1518,7 +1518,7 @@ static inline struct lruvec *relock_page_lruvec_irqsave(struct page *page, struct lruvec *locked_lruvec, unsigned long *flags) { if (locked_lruvec) { - if (lruvec_holds_page_lru_lock(page, locked_lruvec)) + if (page_matches_lruvec(page, locked_lruvec)) return locked_lruvec; unlock_page_lruvec_irqrestore(locked_lruvec, *flags); -- cgit v1.2.3 From b51478a0b3c7040bfcadf6e2e04df5ddde59fd98 Mon Sep 17 00:00:00 2001 From: wenhuizhang Date: Mon, 28 Jun 2021 19:38:12 -0700 Subject: memcontrol: use flexible-array member Change deprecated zero-length-and-one-element-arrays into flexible array member.Zero-length and one-element arrays detected by Lukas's CodeChecker. Zero/one element arrays cause undefined behaviours if sizeof() used. Link: https://lkml.kernel.org/r/20210518200910.29912-1-wenhui@gwmail.gwu.edu Signed-off-by: wenhuizhang Reviewed-by: Muchun Song Acked-by: Michal Hocko Cc: Shakeel Butt Cc: Johannes Weiner Cc: Roman Gushchin Cc: Muchun Song Cc: Yang Shi Cc: Alex Shi Cc: Alexander Duyck Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 0ce97eff79e2..3cc18c2176e7 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -349,8 +349,7 @@ struct mem_cgroup { struct deferred_split deferred_split_queue; #endif - struct mem_cgroup_per_node *nodeinfo[0]; - /* WARNING: nodeinfo must be the last member here */ + struct mem_cgroup_per_node *nodeinfo[]; }; /* -- cgit v1.2.3 From c74d40e8b5e2ac5eee1ca45b12d3e174915f1d88 Mon Sep 17 00:00:00 2001 From: Dan Schatzberg Date: Mon, 28 Jun 2021 19:38:21 -0700 Subject: loop: charge i/o to mem and blk cg The current code only associates with the existing blkcg when aio is used to access the backing file. This patch covers all types of i/o to the backing file and also associates the memcg so if the backing file is on tmpfs, memory is charged appropriately. This patch also exports cgroup_get_e_css and int_active_memcg so it can be used by the loop module. Link: https://lkml.kernel.org/r/20210610173944.1203706-4-schatzberg.dan@gmail.com Signed-off-by: Dan Schatzberg Acked-by: Johannes Weiner Acked-by: Jens Axboe Cc: Chris Down Cc: Michal Hocko Cc: Ming Lei Cc: Shakeel Butt Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 3cc18c2176e7..1de3859233a6 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1230,6 +1230,12 @@ static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) return NULL; } +static inline +struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css) +{ + return NULL; +} + static inline void mem_cgroup_put(struct mem_cgroup *memcg) { } -- cgit v1.2.3 From 6a1803bb582c50909a7f6cc4153360eaf5ae8fc8 Mon Sep 17 00:00:00 2001 From: Huilong Deng Date: Mon, 28 Jun 2021 19:38:24 -0700 Subject: mm: memcontrol: remove trailing semicolon in macros Macros should not use a trailing semicolon. Link: https://lkml.kernel.org/r/20210614091530.22117-1-denghuilong@cdjrlc.com Signed-off-by: Huilong Deng Reviewed-by: Andrew Morton Reviewed-by: Shakeel Butt Cc: Roman Gushchin Cc: Michal Hocko Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 1de3859233a6..6d66037be646 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -192,7 +192,7 @@ enum memcg_kmem_state { struct memcg_padding { char x[0]; } ____cacheline_internodealigned_in_smp; -#define MEMCG_PADDING(name) struct memcg_padding name; +#define MEMCG_PADDING(name) struct memcg_padding name #else #define MEMCG_PADDING(name) #endif -- cgit v1.2.3 From 3b8db39fad98cbb1d36e079236a446fad710daea Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 28 Jun 2021 19:38:35 -0700 Subject: mm: ignore MAP_EXECUTABLE in ksys_mmap_pgoff() Let's also remove masking off MAP_EXECUTABLE from ksys_mmap_pgoff(): the last in-tree occurrence of MAP_EXECUTABLE is now in LEGACY_MAP_MASK, which accepts the flag e.g., for MAP_SHARED_VALIDATE; however, the flag is ignored throughout the kernel now. Add a comment to LEGACY_MAP_MASK stating that MAP_EXECUTABLE is ignored. Link: https://lkml.kernel.org/r/20210421093453.6904-4-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: "Eric W. Biederman" Reviewed-by: Kees Cook Cc: Alexander Shishkin Cc: Alexander Viro Cc: Arnaldo Carvalho de Melo Cc: Borislav Petkov Cc: Catalin Marinas Cc: Don Zickus Cc: Feng Tang Cc: Greg Ungerer Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kevin Brodsky Cc: Mark Rutland Cc: Michal Hocko Cc: Mike Rapoport Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mman.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mman.h b/include/linux/mman.h index 629cefc4ecba..ebb09a964272 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -31,6 +31,8 @@ /* * The historical set of flags that all mmap implementations implicitly * support when a ->mmap_validate() op is not provided in file_operations. + * + * MAP_EXECUTABLE is completely ignored throughout the kernel. */ #define LEGACY_MAP_MASK (MAP_SHARED \ | MAP_PRIVATE \ -- cgit v1.2.3 From ce6d42f2e4a2d98898419743b037a95661e3ac9d Mon Sep 17 00:00:00 2001 From: Liam Howlett Date: Mon, 28 Jun 2021 19:38:50 -0700 Subject: mm: add vma_lookup(), update find_vma_intersection() comments Patch series "mm: Add vma_lookup()", v2. Many places in the kernel use find_vma() to get a vma and then check the start address of the vma to ensure the next vma was not returned. Other places use the find_vma_intersection() call with add, addr + 1 as the range; looking for just the vma at a specific address. The third use of find_vma() is by developers who do not know that the function starts searching at the provided address upwards for the next vma. This results in a bug that is often overlooked for a long time. Adding the new vma_lookup() function will allow for cleaner code by removing the find_vma() calls which check limits, making find_vma_intersection() calls of a single address to be shorter, and potentially reduce the incorrect uses of find_vma(). This patch (of 22): Many places in the kernel use find_vma() to get a vma and then check the start address of the vma to ensure the next vma was not returned. Other places use the find_vma_intersection() call with add, addr + 1 as the range; looking for just the vma at a specific address. The third use of find_vma() is by developers who do not know that the function starts searching at the provided address upwards for the next vma. This results in a bug that is often overlooked for a long time. Adding the new vma_lookup() function will allow for cleaner code by removing the find_vma() calls which check limits, making find_vma_intersection() calls of a single address to be shorter, and potentially reduce the incorrect uses of find_vma(). Also change find_vma_intersection() comments and declaration to be of the correct length and add kernel documentation style comment. Link: https://lkml.kernel.org/r/20210521174745.2219620-1-Liam.Howlett@Oracle.com Link: https://lkml.kernel.org/r/20210521174745.2219620-2-Liam.Howlett@Oracle.com Signed-off-by: Liam R. Howlett Reviewed-by: Laurent Dufour Acked-by: David Hildenbrand Acked-by: Davidlohr Bueso Cc: David Miller Cc: Geert Uytterhoeven Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 36 ++++++++++++++++++++++++++++++++---- 1 file changed, 32 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 79f32962d7ae..1a98b5447a3b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2676,17 +2676,45 @@ extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long add extern struct vm_area_struct * find_vma_prev(struct mm_struct * mm, unsigned long addr, struct vm_area_struct **pprev); -/* Look up the first VMA which intersects the interval start_addr..end_addr-1, - NULL if none. Assume start_addr < end_addr. */ -static inline struct vm_area_struct * find_vma_intersection(struct mm_struct * mm, unsigned long start_addr, unsigned long end_addr) +/** + * find_vma_intersection() - Look up the first VMA which intersects the interval + * @mm: The process address space. + * @start_addr: The inclusive start user address. + * @end_addr: The exclusive end user address. + * + * Returns: The first VMA within the provided range, %NULL otherwise. Assumes + * start_addr < end_addr. + */ +static inline +struct vm_area_struct *find_vma_intersection(struct mm_struct *mm, + unsigned long start_addr, + unsigned long end_addr) { - struct vm_area_struct * vma = find_vma(mm,start_addr); + struct vm_area_struct *vma = find_vma(mm, start_addr); if (vma && end_addr <= vma->vm_start) vma = NULL; return vma; } +/** + * vma_lookup() - Find a VMA at a specific address + * @mm: The process address space. + * @addr: The user address. + * + * Return: The vm_area_struct at the given address, %NULL otherwise. + */ +static inline +struct vm_area_struct *vma_lookup(struct mm_struct *mm, unsigned long addr) +{ + struct vm_area_struct *vma = find_vma(mm, addr); + + if (vma && addr < vma->vm_start) + vma = NULL; + + return vma; +} + static inline unsigned long vm_start_gap(struct vm_area_struct *vma) { unsigned long vm_start = vma->vm_start; -- cgit v1.2.3 From a2afc59fb25027749bd41c44f47382522232019e Mon Sep 17 00:00:00 2001 From: "Uladzislau Rezki (Sony)" Date: Mon, 28 Jun 2021 19:40:11 -0700 Subject: mm/page_alloc: add an alloc_pages_bulk_array_node() helper Patch series "vmalloc() vs bulk allocator", v2. This patch (of 3): Add a "node" variant of the alloc_pages_bulk_array() function. The helper guarantees that a __alloc_pages_bulk() is invoked with a valid NUMA node ID. Link: https://lkml.kernel.org/r/20210516202056.2120-1-urezki@gmail.com Link: https://lkml.kernel.org/r/20210516202056.2120-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) Acked-by: Mel Gorman Cc: Mel Gorman Cc: Matthew Wilcox Cc: Nicholas Piggin Cc: Hillf Danton Cc: Michal Hocko Cc: Oleksiy Avramchenko Cc: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 11da8af06704..94f0b8b1cb55 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -536,6 +536,15 @@ alloc_pages_bulk_array(gfp_t gfp, unsigned long nr_pages, struct page **page_arr return __alloc_pages_bulk(gfp, numa_mem_id(), NULL, nr_pages, NULL, page_array); } +static inline unsigned long +alloc_pages_bulk_array_node(gfp_t gfp, int nid, unsigned long nr_pages, struct page **page_array) +{ + if (nid == NUMA_NO_NODE) + nid = numa_mem_id(); + + return __alloc_pages_bulk(gfp, nid, NULL, nr_pages, NULL, page_array); +} + /* * Allocate pages, preferring the node given as nid. The node must be valid and * online. For more general interface, see alloc_pages_node(). -- cgit v1.2.3 From 4469c0f17ec63dcc8c9ed512f4330b566c2c0d34 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Mon, 28 Jun 2021 19:40:30 -0700 Subject: printk: introduce dump_stack_lvl() dump_stack() is used for many different cases, which may require a log level consistent with other kernel messages surrounding the dump_stack() call. Without that, certain systems that are configured to ignore the default level messages will miss stack traces in critical error reports. This patch introduces dump_stack_lvl() that behaves similarly to dump_stack(), but accepts a custom log level. The old dump_stack() becomes equal to dump_stack_lvl(KERN_DEFAULT). A somewhat similar patch has been proposed in 2012: https://lore.kernel.org/lkml/1332493269.2359.9.camel@hebo/ , but wasn't merged. [elver@google.com: add missing dump_stack_lvl() stub if CONFIG_PRINTK=n] Link: https://lkml.kernel.org/r/YJ0KAM0hQev1AmWe@elver.google.com Link: https://lkml.kernel.org/r/20210506105405.3535023-1-glider@google.com Signed-off-by: Alexander Potapenko Reviewed-by: Marco Elver Cc: Petr Mladek Cc: Ingo Molnar Cc: he, bo Cc: Yanmin Zhang Cc: Prasad Sodagudi Cc: Dmitry Vyukov Cc: Sergey Senozhatsky Cc: Steven Rostedt Cc: Andrey Ryabinin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/printk.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index fe7eb2351610..f589b8b60806 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -206,6 +206,7 @@ void __init setup_log_buf(int early); __printf(1, 2) void dump_stack_set_arch_desc(const char *fmt, ...); void dump_stack_print_info(const char *log_lvl); void show_regs_print_info(const char *log_lvl); +extern asmlinkage void dump_stack_lvl(const char *log_lvl) __cold; extern asmlinkage void dump_stack(void) __cold; extern void printk_safe_flush(void); extern void printk_safe_flush_on_panic(void); @@ -269,6 +270,10 @@ static inline void show_regs_print_info(const char *log_lvl) { } +static inline void dump_stack_lvl(const char *log_lvl) +{ +} + static inline void dump_stack(void) { } -- cgit v1.2.3 From 3ff16d30f593d80a958104ee06a94562a12c5879 Mon Sep 17 00:00:00 2001 From: David Gow Date: Mon, 28 Jun 2021 19:40:36 -0700 Subject: kasan: test: improve failure message in KUNIT_EXPECT_KASAN_FAIL() The KUNIT_EXPECT_KASAN_FAIL() macro currently uses KUNIT_EXPECT_EQ() to compare fail_data.report_expected and fail_data.report_found. This always gave a somewhat useless error message on failure, but the addition of extra compile-time checking with READ_ONCE() has caused it to get much longer, and be truncated before anything useful is displayed. Instead, just check fail_data.report_found by hand (we've just set report_expected to 'true'), and print a better failure message with KUNIT_FAIL(). Because of this, report_expected is no longer used anywhere, and can be removed. Beforehand, a failure in: KUNIT_EXPECT_KASAN_FAIL(test, ((volatile char *)area)[3100]); would have looked like: [22:00:34] [FAILED] vmalloc_oob [22:00:34] # vmalloc_oob: EXPECTATION FAILED at lib/test_kasan.c:991 [22:00:34] Expected ({ do { extern void __compiletime_assert_705(void) __attribute__((__error__("Unsupported access size for {READ,WRITE}_ONCE()."))); if (!((sizeof(fail_data.report_expected) == sizeof(char) || sizeof(fail_data.repp [22:00:34] not ok 45 - vmalloc_oob With this change, it instead looks like: [22:04:04] [FAILED] vmalloc_oob [22:04:04] # vmalloc_oob: EXPECTATION FAILED at lib/test_kasan.c:993 [22:04:04] KASAN failure expected in "((volatile char *)area)[3100]", but none occurred [22:04:04] not ok 45 - vmalloc_oob Also update the example failure in the documentation to reflect this. Link: https://lkml.kernel.org/r/20210606005531.165954-1-davidgow@google.com Signed-off-by: David Gow Reviewed-by: Andrey Konovalov Reviewed-by: Marco Elver Acked-by: Brendan Higgins Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Daniel Axtens Cc: David Gow Cc: Jonathan Corbet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index b1678a61e6a7..18cd5ec2f469 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -17,7 +17,6 @@ struct task_struct; /* kasan_data struct is used in KUnit tests for KASAN expected failures */ struct kunit_kasan_expectation { - bool report_expected; bool report_found; }; -- cgit v1.2.3 From c0f8aa4fa815daacb6eca52cae04820d6aecb7c2 Mon Sep 17 00:00:00 2001 From: Daniel Axtens Date: Mon, 28 Jun 2021 19:40:46 -0700 Subject: mm: define default MAX_PTRS_PER_* in include/pgtable.h Commit c65e774fb3f6 ("x86/mm: Make PGDIR_SHIFT and PTRS_PER_P4D variable") made PTRS_PER_P4D variable on x86 and introduced MAX_PTRS_PER_P4D as a constant for cases which need a compile-time constant (e.g. fixed-size arrays). powerpc likewise has boot-time selectable MMU features which can cause other mm "constants" to vary. For KASAN, we have some static PTE/PMD/PUD/P4D arrays so we need compile-time maximums for all these constants. Extend the MAX_PTRS_PER_ idiom, and place default definitions in include/pgtable.h. These define MAX_PTRS_PER_x to be PTRS_PER_x unless an architecture has defined MAX_PTRS_PER_x in its arch headers. Clean up pgtable-nop4d.h and s390's MAX_PTRS_PER_P4D definitions while we're at it: both can just pick up the default now. Link: https://lkml.kernel.org/r/20210624034050.511391-4-dja@axtens.net Signed-off-by: Daniel Axtens Acked-by: Andrey Konovalov Reviewed-by: Christophe Leroy Reviewed-by: Marco Elver Cc: Aneesh Kumar K.V Cc: Balbir Singh Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Dmitry Vyukov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pgtable.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index a43047b1030d..c32600c9e1ad 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1592,4 +1592,26 @@ typedef unsigned int pgtbl_mod_mask; #define pte_leaf_size(x) PAGE_SIZE #endif +/* + * Some architectures have MMUs that are configurable or selectable at boot + * time. These lead to variable PTRS_PER_x. For statically allocated arrays it + * helps to have a static maximum value. + */ + +#ifndef MAX_PTRS_PER_PTE +#define MAX_PTRS_PER_PTE PTRS_PER_PTE +#endif + +#ifndef MAX_PTRS_PER_PMD +#define MAX_PTRS_PER_PMD PTRS_PER_PMD +#endif + +#ifndef MAX_PTRS_PER_PUD +#define MAX_PTRS_PER_PUD PTRS_PER_PUD +#endif + +#ifndef MAX_PTRS_PER_P4D +#define MAX_PTRS_PER_P4D PTRS_PER_P4D +#endif + #endif /* _LINUX_PGTABLE_H */ -- cgit v1.2.3 From cb32c9c5d45662770160e0055cb672fd6e0813e8 Mon Sep 17 00:00:00 2001 From: Daniel Axtens Date: Mon, 28 Jun 2021 19:40:49 -0700 Subject: kasan: use MAX_PTRS_PER_* for early shadow tables powerpc has a variable number of PTRS_PER_*, set at runtime based on the MMU that the kernel is booted under. This means the PTRS_PER_* are no longer constants, and therefore breaks the build. Switch to using MAX_PTRS_PER_*, which are constant. Link: https://lkml.kernel.org/r/20210624034050.511391-5-dja@axtens.net Signed-off-by: Daniel Axtens Suggested-by: Christophe Leroy Suggested-by: Balbir Singh Reviewed-by: Christophe Leroy Reviewed-by: Balbir Singh Reviewed-by: Marco Elver Reviewed-by: Andrey Konovalov Cc: Aneesh Kumar K.V Cc: Andrey Ryabinin Cc: Alexander Potapenko Cc: Dmitry Vyukov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 18cd5ec2f469..8d83bbffcfbb 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -40,9 +40,9 @@ struct kunit_kasan_expectation { #endif extern unsigned char kasan_early_shadow_page[PAGE_SIZE]; -extern pte_t kasan_early_shadow_pte[PTRS_PER_PTE + PTE_HWTABLE_PTRS]; -extern pmd_t kasan_early_shadow_pmd[PTRS_PER_PMD]; -extern pud_t kasan_early_shadow_pud[PTRS_PER_PUD]; +extern pte_t kasan_early_shadow_pte[MAX_PTRS_PER_PTE + PTE_HWTABLE_PTRS]; +extern pmd_t kasan_early_shadow_pmd[MAX_PTRS_PER_PMD]; +extern pud_t kasan_early_shadow_pud[MAX_PTRS_PER_PUD]; extern p4d_t kasan_early_shadow_p4d[MAX_PTRS_PER_P4D]; int kasan_populate_early_shadow(const void *shadow_start, -- cgit v1.2.3 From c5a54c706e04a4ba7c4e3428776ac9e44aec17ea Mon Sep 17 00:00:00 2001 From: Jungseung Lee Date: Mon, 28 Jun 2021 19:41:02 -0700 Subject: mm: report which part of mem is being freed on initmem case Add the details for figuring out which parts of the kernel image is being freed on initmem case. Before: Freeing unused kernel memory: 1024K After: Freeing unused kernel image (initmem) memory: 1024K Link: https://lkml.kernel.org/r/1622706274-4533-1-git-send-email-js07.lee@samsung.com Signed-off-by: Jungseung Lee Reviewed-by: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1a98b5447a3b..f08e9de92fc5 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2416,7 +2416,7 @@ static inline unsigned long free_initmem_default(int poison) extern char __init_begin[], __init_end[]; return free_reserved_area(&__init_begin, &__init_end, - poison, "unused kernel"); + poison, "unused kernel image (initmem)"); } static inline unsigned long get_num_physpages(void) -- cgit v1.2.3 From b19bd1c976afeefc2ebba3d4dae8a4c296dae67f Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Mon, 28 Jun 2021 19:41:04 -0700 Subject: mm/mmzone.h: simplify is_highmem_idx() There is a lot of historical ifdefery in is_highmem_idx() and its helper zone_movable_is_highmem() that was required because of two different paths for nodes and zones initialization that were selected at compile time. Until commit 3f08a302f533 ("mm: remove CONFIG_HAVE_MEMBLOCK_NODE_MAP option") the movable_zone variable was only available for configurations that had CONFIG_HAVE_MEMBLOCK_NODE_MAP enabled so the test in zone_movable_is_highmem() used that variable only for such configurations. For other configurations the test checked if the index of ZONE_MOVABLE was greater by 1 than the index of ZONE_HIGMEM and then movable zone was considered a highmem zone. Needless to say, ZONE_MOVABLE - 1 equals ZONE_HIGHMEM by definition when CONFIG_HIGHMEM=y. Commit 3f08a302f533 ("mm: remove CONFIG_HAVE_MEMBLOCK_NODE_MAP option") made movable_zone variable always available. Since this variable is set to ZONE_HIGHMEM if CONFIG_HIGHMEM is enabled and highmem zone is populated, it is enough to check whether zone_idx == ZONE_MOVABLE && movable_zone == ZONE_HIGMEM to test if zone index points to a highmem zone. Remove zone_movable_is_highmem() that is not used anywhere except is_highmem_idx() and use the test above in is_highmem_idx() instead. Link: https://lkml.kernel.org/r/20210426141927.1314326-3-rppt@kernel.org Signed-off-by: Mike Rapoport Reviewed-by: Anshuman Khandual Cc: Jonathan Corbet Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 13 +------------ 1 file changed, 1 insertion(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 0d53eba1c383..c2bfefd34b59 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -982,22 +982,11 @@ static inline void zone_set_nid(struct zone *zone, int nid) {} extern int movable_zone; -#ifdef CONFIG_HIGHMEM -static inline int zone_movable_is_highmem(void) -{ -#ifdef CONFIG_NEED_MULTIPLE_NODES - return movable_zone == ZONE_HIGHMEM; -#else - return (ZONE_MOVABLE - 1) == ZONE_HIGHMEM; -#endif -} -#endif - static inline int is_highmem_idx(enum zone_type idx) { #ifdef CONFIG_HIGHMEM return (idx == ZONE_HIGHMEM || - (idx == ZONE_MOVABLE && zone_movable_is_highmem())); + (idx == ZONE_MOVABLE && movable_zone == ZONE_HIGHMEM)); #else return 0; #endif -- cgit v1.2.3 From d2f07ec052ac1a720d6f1919e3dee7d73f04d495 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 28 Jun 2021 19:41:07 -0700 Subject: mm: make __dump_page static Patch series "Constify struct page arguments". While working on various solutions to the 32-bit struct page size regression, one of the problems I found was the networking stack expects to be able to pass const struct page pointers around, and the mm doesn't provide a lot of const-friendly functions to call. The root tangle of problems is that a lot of functions call VM_BUG_ON_PAGE(), which calls dump_page(), which calls a lot of functions which don't take a const struct page (but could be const). This patch (of 6): The only caller of __dump_page() now opencodes dump_page(), so remove it as an externally visible symbol. Link: https://lkml.kernel.org/r/20210416231531.2521383-1-willy@infradead.org Link: https://lkml.kernel.org/r/20210416231531.2521383-2-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Vlastimil Babka Reviewed-by: Anshuman Khandual Reviewed-by: William Kucharski Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmdebug.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h index 5d0767cb424a..1935d4c72d10 100644 --- a/include/linux/mmdebug.h +++ b/include/linux/mmdebug.h @@ -9,8 +9,7 @@ struct page; struct vm_area_struct; struct mm_struct; -extern void dump_page(struct page *page, const char *reason); -extern void __dump_page(struct page *page, const char *reason); +void dump_page(struct page *page, const char *reason); void dump_vma(const struct vm_area_struct *vma); void dump_mm(const struct mm_struct *mm); -- cgit v1.2.3 From 8bf6f451bded5db7840b3b2932ef48be5dce6b38 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 28 Jun 2021 19:41:16 -0700 Subject: mm/page_owner: constify dump_page_owner dump_page_owner() only uses struct page to find the page_ext, and lookup_page_ext() already takes a const argument. Link: https://lkml.kernel.org/r/20210416231531.2521383-4-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Vlastimil Babka Reviewed-by: Anshuman Khandual Reviewed-by: William Kucharski Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_owner.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page_owner.h b/include/linux/page_owner.h index 3468794f83d2..719bfe5108c5 100644 --- a/include/linux/page_owner.h +++ b/include/linux/page_owner.h @@ -14,7 +14,7 @@ extern void __set_page_owner(struct page *page, extern void __split_page_owner(struct page *page, unsigned int nr); extern void __copy_page_owner(struct page *oldpage, struct page *newpage); extern void __set_page_owner_migrate_reason(struct page *page, int reason); -extern void __dump_page_owner(struct page *page); +extern void __dump_page_owner(const struct page *page); extern void pagetypeinfo_showmixedcount_print(struct seq_file *m, pg_data_t *pgdat, struct zone *zone); @@ -46,7 +46,7 @@ static inline void set_page_owner_migrate_reason(struct page *page, int reason) if (static_branch_unlikely(&page_owner_inited)) __set_page_owner_migrate_reason(page, reason); } -static inline void dump_page_owner(struct page *page) +static inline void dump_page_owner(const struct page *page) { if (static_branch_unlikely(&page_owner_inited)) __dump_page_owner(page); @@ -69,7 +69,7 @@ static inline void copy_page_owner(struct page *oldpage, struct page *newpage) static inline void set_page_owner_migrate_reason(struct page *page, int reason) { } -static inline void dump_page_owner(struct page *page) +static inline void dump_page_owner(const struct page *page) { } #endif /* CONFIG_PAGE_OWNER */ -- cgit v1.2.3 From 0f2317e34e2c7b97efd4600122115410795ebeea Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 28 Jun 2021 19:41:19 -0700 Subject: mm: make compound_head const-preserving If you pass a const pointer to compound_head(), you get a const pointer back; if you pass a mutable pointer, you get a mutable pointer back. Also remove an unnecessary forward definition of struct page; we're about to dereference page->compound_head, so it must already have been defined. Link: https://lkml.kernel.org/r/20210416231531.2521383-5-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Vlastimil Babka Reviewed-by: Anshuman Khandual Reviewed-by: William Kucharski Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 04a34c08e0a6..d8e26243db25 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -177,17 +177,17 @@ enum pageflags { #ifndef __GENERATING_BOUNDS_H -struct page; /* forward declaration */ - -static inline struct page *compound_head(struct page *page) +static inline unsigned long _compound_head(const struct page *page) { unsigned long head = READ_ONCE(page->compound_head); if (unlikely(head & 1)) - return (struct page *) (head - 1); - return page; + return head - 1; + return (unsigned long)page; } +#define compound_head(page) ((typeof(page))_compound_head(page)) + static __always_inline int PageTail(struct page *page) { return READ_ONCE(page->compound_head) & 1; -- cgit v1.2.3 From ca891f41c4c7921a03dfd0fa1faf324393724480 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 28 Jun 2021 19:41:22 -0700 Subject: mm: constify get_pfnblock_flags_mask and get_pfnblock_migratetype The struct page is not modified by these routines, so it can be marked const. Link: https://lkml.kernel.org/r/20210416231531.2521383-6-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Vlastimil Babka Reviewed-by: Anshuman Khandual Reviewed-by: William Kucharski Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pageblock-flags.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h index fff52ad370c1..973fd731a520 100644 --- a/include/linux/pageblock-flags.h +++ b/include/linux/pageblock-flags.h @@ -54,7 +54,7 @@ extern unsigned int pageblock_order; /* Forward declaration */ struct page; -unsigned long get_pfnblock_flags_mask(struct page *page, +unsigned long get_pfnblock_flags_mask(const struct page *page, unsigned long pfn, unsigned long mask); -- cgit v1.2.3 From 5f7dadf3958f882b393d3c4c60da232dbac66424 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 28 Jun 2021 19:41:25 -0700 Subject: mm: constify page_count and page_ref_count Now that compound_head() accepts a const struct page pointer, these two functions can be marked as not modifying the page pointer they are passed. Link: https://lkml.kernel.org/r/20210416231531.2521383-7-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Vlastimil Babka Reviewed-by: Anshuman Khandual Reviewed-by: William Kucharski Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_ref.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h index f3318f34fc54..7ad46f45df39 100644 --- a/include/linux/page_ref.h +++ b/include/linux/page_ref.h @@ -62,12 +62,12 @@ static inline void __page_ref_unfreeze(struct page *page, int v) #endif -static inline int page_ref_count(struct page *page) +static inline int page_ref_count(const struct page *page) { return atomic_read(&page->_refcount); } -static inline int page_count(struct page *page) +static inline int page_count(const struct page *page) { return atomic_read(&compound_head(page)->_refcount); } -- cgit v1.2.3 From 1cfcee728391ece94a75e4b17fa87253d40c2185 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 28 Jun 2021 19:41:28 -0700 Subject: mm: optimise nth_page for contiguous memmap If the memmap is virtually contiguous (either because we're using a virtually mapped memmap or because we don't support a discontig memmap at all), then we can implement nth_page() by simple addition. Contrary to popular belief, the compiler is not able to optimise this itself for a vmemmap configuration. This reduces one example user (sg.c) by four instructions: struct page *page = nth_page(rsv_schp->pages[k], offset >> PAGE_SHIFT); before: 49 8b 45 70 mov 0x70(%r13),%rax 48 63 c9 movslq %ecx,%rcx 48 c1 eb 0c shr $0xc,%rbx 48 8b 04 c8 mov (%rax,%rcx,8),%rax 48 2b 05 00 00 00 00 sub 0x0(%rip),%rax R_X86_64_PC32 vmemmap_base-0x4 48 c1 f8 06 sar $0x6,%rax 48 01 d8 add %rbx,%rax 48 c1 e0 06 shl $0x6,%rax 48 03 05 00 00 00 00 add 0x0(%rip),%rax R_X86_64_PC32 vmemmap_base-0x4 after: 49 8b 45 70 mov 0x70(%r13),%rax 48 63 c9 movslq %ecx,%rcx 48 c1 eb 0c shr $0xc,%rbx 48 c1 e3 06 shl $0x6,%rbx 48 03 1c c8 add (%rax,%rcx,8),%rbx Link: https://lkml.kernel.org/r/20210413194625.1472345-1-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: David Hildenbrand Reviewed-by: Zi Yan Reviewed-by: Vlastimil Babka Cc: Tejun Heo Cc: FUJITA Tomonori Cc: Douglas Gilbert Cc: Chris Wilson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index f08e9de92fc5..9bd21e6fad6a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -234,7 +234,11 @@ int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *, int __add_to_page_cache_locked(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp, void **shadowp); +#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) +#else +#define nth_page(page,n) ((page) + (n)) +#endif /* to align the pointer to the (next) page boundary */ #define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE) -- cgit v1.2.3 From 28f836b6777b6f42dce068a40d83a891deaaca37 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 28 Jun 2021 19:41:38 -0700 Subject: mm/page_alloc: split per cpu page lists and zone stats The PCP (per-cpu page allocator in page_alloc.c) shares locking requirements with vmstat and the zone lock which is inconvenient and causes some issues. For example, the PCP list and vmstat share the same per-cpu space meaning that it's possible that vmstat updates dirty cache lines holding per-cpu lists across CPUs unless padding is used. Second, PREEMPT_RT does not want to disable IRQs for too long in the page allocator. This series splits the locking requirements and uses locks types more suitable for PREEMPT_RT, reduces the time when special locking is required for stats and reduces the time when IRQs need to be disabled on !PREEMPT_RT kernels. Why local_lock? PREEMPT_RT considers the following sequence to be unsafe as documented in Documentation/locking/locktypes.rst local_irq_disable(); spin_lock(&lock); The pcp allocator has this sequence for rmqueue_pcplist (local_irq_save) -> __rmqueue_pcplist -> rmqueue_bulk (spin_lock). While it's possible to separate this out, it generally means there are points where we enable IRQs and reenable them again immediately. To prevent a migration and the per-cpu pointer going stale, migrate_disable is also needed. That is a custom lock that is similar, but worse, than local_lock. Furthermore, on PREEMPT_RT, it's undesirable to leave IRQs disabled for too long. By converting to local_lock which disables migration on PREEMPT_RT, the locking requirements can be separated and start moving the protections for PCP, stats and the zone lock to PREEMPT_RT-safe equivalent locking. As a bonus, local_lock also means that PROVE_LOCKING does something useful. After that, it's obvious that zone_statistics incurs too much overhead and leaves IRQs disabled for longer than necessary on !PREEMPT_RT kernels. zone_statistics uses perfectly accurate counters requiring IRQs be disabled for parallel RMW sequences when inaccurate ones like vm_events would do. The series makes the NUMA statistics (NUMA_HIT and friends) inaccurate counters that then require no special protection on !PREEMPT_RT. The bulk page allocator can then do stat updates in bulk with IRQs enabled which should improve the efficiency. Technically, this could have been done without the local_lock and vmstat conversion work and the order simply reflects the timing of when different series were implemented. Finally, there are places where we conflate IRQs being disabled for the PCP with the IRQ-safe zone spinlock. The remainder of the series reduces the scope of what is protected by disabled IRQs on !PREEMPT_RT kernels. By the end of the series, page_alloc.c does not call local_irq_save so the locking scope is a bit clearer. The one exception is that modifying NR_FREE_PAGES still happens in places where it's known the IRQs are disabled as it's harmless for PREEMPT_RT and would be expensive to split the locking there. No performance data is included because despite the overhead of the stats, it's within the noise for most workloads on !PREEMPT_RT. However, Jesper Dangaard Brouer ran a page allocation microbenchmark on a E5-1650 v4 @ 3.60GHz CPU on the first version of this series. Focusing on the array variant of the bulk page allocator reveals the following. (CPU: Intel(R) Xeon(R) CPU E5-1650 v4 @ 3.60GHz) ARRAY variant: time_bulk_page_alloc_free_array: step=bulk size Baseline Patched 1 56.383 54.225 (+3.83%) 2 40.047 35.492 (+11.38%) 3 37.339 32.643 (+12.58%) 4 35.578 30.992 (+12.89%) 8 33.592 29.606 (+11.87%) 16 32.362 28.532 (+11.85%) 32 31.476 27.728 (+11.91%) 64 30.633 27.252 (+11.04%) 128 30.596 27.090 (+11.46%) While this is a positive outcome, the series is more likely to be interesting to the RT people in terms of getting parts of the PREEMPT_RT tree into mainline. This patch (of 9): The per-cpu page allocator lists and the per-cpu vmstat deltas are stored in the same struct per_cpu_pages even though vmstats have no direct impact on the per-cpu page lists. This is inconsistent because the vmstats for a node are stored on a dedicated structure. The bigger issue is that the per_cpu_pages structure is not cache-aligned and stat updates either cache conflict with adjacent per-cpu lists incurring a runtime cost or padding is required incurring a memory cost. This patch splits the per-cpu pagelists and the vmstat deltas into separate structures. It's mostly a mechanical conversion but some variable renaming is done to clearly distinguish the per-cpu pages structure (pcp) from the vmstats (pzstats). Superficially, this appears to increase the size of the per_cpu_pages structure but the movement of expire fills a structure hole so there is no impact overall. [mgorman@techsingularity.net: make it W=1 cleaner] Link: https://lkml.kernel.org/r/20210514144622.GA3735@techsingularity.net [mgorman@techsingularity.net: make it W=1 even cleaner] Link: https://lkml.kernel.org/r/20210516140705.GB3735@techsingularity.net [lkp@intel.com: check struct per_cpu_zonestat has a non-zero size] [vbabka@suse.cz: Init zone->per_cpu_zonestats properly] Link: https://lkml.kernel.org/r/20210512095458.30632-1-mgorman@techsingularity.net Link: https://lkml.kernel.org/r/20210512095458.30632-2-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Acked-by: Peter Zijlstra (Intel) Cc: Chuck Lever Cc: Jesper Dangaard Brouer Cc: Thomas Gleixner Cc: Sebastian Andrzej Siewior Cc: Ingo Molnar Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 18 ++++++++++-------- include/linux/vmstat.h | 8 ++++---- 2 files changed, 14 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index c2bfefd34b59..a50b123ab7ae 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -341,20 +341,21 @@ struct per_cpu_pages { int count; /* number of pages in the list */ int high; /* high watermark, emptying needed */ int batch; /* chunk size for buddy add/remove */ +#ifdef CONFIG_NUMA + int expire; /* When 0, remote pagesets are drained */ +#endif /* Lists of pages, one per migrate type stored on the pcp-lists */ struct list_head lists[MIGRATE_PCPTYPES]; }; -struct per_cpu_pageset { - struct per_cpu_pages pcp; -#ifdef CONFIG_NUMA - s8 expire; - u16 vm_numa_stat_diff[NR_VM_NUMA_STAT_ITEMS]; -#endif +struct per_cpu_zonestat { #ifdef CONFIG_SMP - s8 stat_threshold; s8 vm_stat_diff[NR_VM_ZONE_STAT_ITEMS]; + s8 stat_threshold; +#endif +#ifdef CONFIG_NUMA + u16 vm_numa_stat_diff[NR_VM_NUMA_STAT_ITEMS]; #endif }; @@ -484,7 +485,8 @@ struct zone { int node; #endif struct pglist_data *zone_pgdat; - struct per_cpu_pageset __percpu *pageset; + struct per_cpu_pages __percpu *per_cpu_pageset; + struct per_cpu_zonestat __percpu *per_cpu_zonestats; /* * the high and batch values are copied to individual pagesets for * faster access diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 3299cd69e4ca..0c5f36504613 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -163,7 +163,7 @@ static inline unsigned long zone_numa_state_snapshot(struct zone *zone, int cpu; for_each_online_cpu(cpu) - x += per_cpu_ptr(zone->pageset, cpu)->vm_numa_stat_diff[item]; + x += per_cpu_ptr(zone->per_cpu_zonestats, cpu)->vm_numa_stat_diff[item]; return x; } @@ -236,7 +236,7 @@ static inline unsigned long zone_page_state_snapshot(struct zone *zone, #ifdef CONFIG_SMP int cpu; for_each_online_cpu(cpu) - x += per_cpu_ptr(zone->pageset, cpu)->vm_stat_diff[item]; + x += per_cpu_ptr(zone->per_cpu_zonestats, cpu)->vm_stat_diff[item]; if (x < 0) x = 0; @@ -291,7 +291,7 @@ struct ctl_table; int vmstat_refresh(struct ctl_table *, int write, void *buffer, size_t *lenp, loff_t *ppos); -void drain_zonestat(struct zone *zone, struct per_cpu_pageset *); +void drain_zonestat(struct zone *zone, struct per_cpu_zonestat *); int calculate_pressure_threshold(struct zone *zone); int calculate_normal_threshold(struct zone *zone); @@ -399,7 +399,7 @@ static inline void cpu_vm_stats_fold(int cpu) { } static inline void quiet_vmstat(void) { } static inline void drain_zonestat(struct zone *zone, - struct per_cpu_pageset *pset) { } + struct per_cpu_zonestat *pzstats) { } #endif /* CONFIG_SMP */ static inline void __mod_zone_freepage_state(struct zone *zone, int nr_pages, -- cgit v1.2.3 From dbbee9d5cd83f9d0a29639e260516907ceb2ac3d Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 28 Jun 2021 19:41:41 -0700 Subject: mm/page_alloc: convert per-cpu list protection to local_lock There is a lack of clarity of what exactly local_irq_save/local_irq_restore protects in page_alloc.c . It conflates the protection of per-cpu page allocation structures with per-cpu vmstat deltas. This patch protects the PCP structure using local_lock which for most configurations is identical to IRQ enabling/disabling. The scope of the lock is still wider than it should be but this is decreased later. It is possible for the local_lock to be embedded safely within struct per_cpu_pages but it adds complexity to free_unref_page_list. [akpm@linux-foundation.org: coding style fixes] [mgorman@techsingularity.net: work around a pahole limitation with zero-sized struct pagesets] Link: https://lkml.kernel.org/r/20210526080741.GW30378@techsingularity.net [lkp@intel.com: Make pagesets static] Link: https://lkml.kernel.org/r/20210512095458.30632-3-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Acked-by: Peter Zijlstra (Intel) Cc: Chuck Lever Cc: Ingo Molnar Cc: Jesper Dangaard Brouer Cc: Michal Hocko Cc: Sebastian Andrzej Siewior Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index a50b123ab7ae..0d6bb737e5a2 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -20,6 +20,7 @@ #include #include #include +#include #include /* Free memory management - zoned buddy allocator. */ @@ -337,6 +338,7 @@ enum zone_watermarks { #define high_wmark_pages(z) (z->_watermark[WMARK_HIGH] + z->watermark_boost) #define wmark_pages(z, i) (z->_watermark[i] + z->watermark_boost) +/* Fields and list protected by pagesets local_lock in page_alloc.c */ struct per_cpu_pages { int count; /* number of pages in the list */ int high; /* high watermark, emptying needed */ -- cgit v1.2.3 From f19298b9516c1a031b34b4147773457e3efe743b Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 28 Jun 2021 19:41:44 -0700 Subject: mm/vmstat: convert NUMA statistics to basic NUMA counters NUMA statistics are maintained on the zone level for hits, misses, foreign etc but nothing relies on them being perfectly accurate for functional correctness. The counters are used by userspace to get a general overview of a workloads NUMA behaviour but the page allocator incurs a high cost to maintain perfect accuracy similar to what is required for a vmstat like NR_FREE_PAGES. There even is a sysctl vm.numa_stat to allow userspace to turn off the collection of NUMA statistics like NUMA_HIT. This patch converts NUMA_HIT and friends to be NUMA events with similar accuracy to VM events. There is a possibility that slight errors will be introduced but the overall trend as seen by userspace will be similar. The counters are no longer updated from vmstat_refresh context as it is unnecessary overhead for counters that may never be read by userspace. Note that counters could be maintained at the node level to save space but it would have a user-visible impact due to /proc/zoneinfo. [lkp@intel.com: Fix misplaced closing brace for !CONFIG_NUMA] Link: https://lkml.kernel.org/r/20210512095458.30632-4-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Acked-by: Peter Zijlstra (Intel) Cc: Chuck Lever Cc: Ingo Molnar Cc: Jesper Dangaard Brouer Cc: Michal Hocko Cc: Sebastian Andrzej Siewior Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 13 +++++++++---- include/linux/vmstat.h | 43 ++++++++++++++++++++----------------------- 2 files changed, 29 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 0d6bb737e5a2..f86018d5e362 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -135,10 +135,10 @@ enum numa_stat_item { NUMA_INTERLEAVE_HIT, /* interleaver preferred this zone */ NUMA_LOCAL, /* allocation from local node */ NUMA_OTHER, /* allocation from other node */ - NR_VM_NUMA_STAT_ITEMS + NR_VM_NUMA_EVENT_ITEMS }; #else -#define NR_VM_NUMA_STAT_ITEMS 0 +#define NR_VM_NUMA_EVENT_ITEMS 0 #endif enum zone_stat_item { @@ -357,7 +357,12 @@ struct per_cpu_zonestat { s8 stat_threshold; #endif #ifdef CONFIG_NUMA - u16 vm_numa_stat_diff[NR_VM_NUMA_STAT_ITEMS]; + /* + * Low priority inaccurate counters that are only folded + * on demand. Use a large type to avoid the overhead of + * folding during refresh_cpu_vm_stats. + */ + unsigned long vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; #endif }; @@ -623,7 +628,7 @@ struct zone { ZONE_PADDING(_pad3_) /* Zone statistics */ atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; - atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS]; + atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; } ____cacheline_internodealigned_in_smp; enum pgdat_flags { diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 0c5f36504613..59748bbbba4c 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -138,34 +138,27 @@ static inline void vm_events_fold_cpu(int cpu) * Zone and node-based page accounting with per cpu differentials. */ extern atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS]; -extern atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS]; extern atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS]; +extern atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; #ifdef CONFIG_NUMA -static inline void zone_numa_state_add(long x, struct zone *zone, - enum numa_stat_item item) +static inline void zone_numa_event_add(long x, struct zone *zone, + enum numa_stat_item item) { - atomic_long_add(x, &zone->vm_numa_stat[item]); - atomic_long_add(x, &vm_numa_stat[item]); + atomic_long_add(x, &zone->vm_numa_event[item]); + atomic_long_add(x, &vm_numa_event[item]); } -static inline unsigned long global_numa_state(enum numa_stat_item item) +static inline unsigned long zone_numa_event_state(struct zone *zone, + enum numa_stat_item item) { - long x = atomic_long_read(&vm_numa_stat[item]); - - return x; + return atomic_long_read(&zone->vm_numa_event[item]); } -static inline unsigned long zone_numa_state_snapshot(struct zone *zone, - enum numa_stat_item item) +static inline unsigned long +global_numa_event_state(enum numa_stat_item item) { - long x = atomic_long_read(&zone->vm_numa_stat[item]); - int cpu; - - for_each_online_cpu(cpu) - x += per_cpu_ptr(zone->per_cpu_zonestats, cpu)->vm_numa_stat_diff[item]; - - return x; + return atomic_long_read(&vm_numa_event[item]); } #endif /* CONFIG_NUMA */ @@ -245,18 +238,22 @@ static inline unsigned long zone_page_state_snapshot(struct zone *zone, } #ifdef CONFIG_NUMA -extern void __inc_numa_state(struct zone *zone, enum numa_stat_item item); +extern void __count_numa_event(struct zone *zone, enum numa_stat_item item); extern unsigned long sum_zone_node_page_state(int node, enum zone_stat_item item); -extern unsigned long sum_zone_numa_state(int node, enum numa_stat_item item); +extern unsigned long sum_zone_numa_event_state(int node, enum numa_stat_item item); extern unsigned long node_page_state(struct pglist_data *pgdat, enum node_stat_item item); extern unsigned long node_page_state_pages(struct pglist_data *pgdat, enum node_stat_item item); +extern void fold_vm_numa_events(void); #else #define sum_zone_node_page_state(node, item) global_zone_page_state(item) #define node_page_state(node, item) global_node_page_state(item) #define node_page_state_pages(node, item) global_node_page_state_pages(item) +static inline void fold_vm_numa_events(void) +{ +} #endif /* CONFIG_NUMA */ #ifdef CONFIG_SMP @@ -428,7 +425,7 @@ static inline const char *numa_stat_name(enum numa_stat_item item) static inline const char *node_stat_name(enum node_stat_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + - NR_VM_NUMA_STAT_ITEMS + + NR_VM_NUMA_EVENT_ITEMS + item]; } @@ -440,7 +437,7 @@ static inline const char *lru_list_name(enum lru_list lru) static inline const char *writeback_stat_name(enum writeback_stat_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + - NR_VM_NUMA_STAT_ITEMS + + NR_VM_NUMA_EVENT_ITEMS + NR_VM_NODE_STAT_ITEMS + item]; } @@ -449,7 +446,7 @@ static inline const char *writeback_stat_name(enum writeback_stat_item item) static inline const char *vm_event_name(enum vm_event_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + - NR_VM_NUMA_STAT_ITEMS + + NR_VM_NUMA_EVENT_ITEMS + NR_VM_NODE_STAT_ITEMS + NR_VM_WRITEBACK_STAT_ITEMS + item]; -- cgit v1.2.3 From 3ac44a346a50988131db124a7e4bb99d3ec71706 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 28 Jun 2021 19:41:47 -0700 Subject: mm/vmstat: inline NUMA event counter updates __count_numa_event is small enough to be treated similarly to __count_vm_event so inline it. Link: https://lkml.kernel.org/r/20210512095458.30632-5-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Acked-by: Peter Zijlstra (Intel) Cc: Chuck Lever Cc: Ingo Molnar Cc: Jesper Dangaard Brouer Cc: Michal Hocko Cc: Sebastian Andrzej Siewior Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmstat.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 59748bbbba4c..fe32a2210e73 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -238,7 +238,15 @@ static inline unsigned long zone_page_state_snapshot(struct zone *zone, } #ifdef CONFIG_NUMA -extern void __count_numa_event(struct zone *zone, enum numa_stat_item item); +/* See __count_vm_event comment on why raw_cpu_inc is used. */ +static inline void +__count_numa_event(struct zone *zone, enum numa_stat_item item) +{ + struct per_cpu_zonestat __percpu *pzstats = zone->per_cpu_zonestats; + + raw_cpu_inc(pzstats->vm_numa_event[item]); +} + extern unsigned long sum_zone_node_page_state(int node, enum zone_stat_item item); extern unsigned long sum_zone_numa_event_state(int node, enum numa_stat_item item); -- cgit v1.2.3 From 3e23060b2d0b7eebf37b3b6043ea68da0ebc0646 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 28 Jun 2021 19:41:50 -0700 Subject: mm/page_alloc: batch the accounting updates in the bulk allocator Now that the zone_statistics are simple counters that do not require special protection, the bulk allocator accounting updates can be batch updated without adding too much complexity with protected RMW updates or using xchg. Link: https://lkml.kernel.org/r/20210512095458.30632-6-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Acked-by: Peter Zijlstra (Intel) Cc: Chuck Lever Cc: Ingo Molnar Cc: Jesper Dangaard Brouer Cc: Michal Hocko Cc: Sebastian Andrzej Siewior Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmstat.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index fe32a2210e73..d6a6cf53b127 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -247,6 +247,14 @@ __count_numa_event(struct zone *zone, enum numa_stat_item item) raw_cpu_inc(pzstats->vm_numa_event[item]); } +static inline void +__count_numa_events(struct zone *zone, enum numa_stat_item item, long delta) +{ + struct per_cpu_zonestat __percpu *pzstats = zone->per_cpu_zonestats; + + raw_cpu_add(pzstats->vm_numa_event[item], delta); +} + extern unsigned long sum_zone_node_page_state(int node, enum zone_stat_item item); extern unsigned long sum_zone_numa_event_state(int node, enum numa_stat_item item); -- cgit v1.2.3 From bbbecb35a41cb5c63ef78e14cc8b95fa9130bc1a Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 28 Jun 2021 19:42:09 -0700 Subject: mm/page_alloc: delete vm.percpu_pagelist_fraction Patch series "Calculate pcp->high based on zone sizes and active CPUs", v2. The per-cpu page allocator (PCP) is meant to reduce contention on the zone lock but the sizing of batch and high is archaic and neither takes the zone size into account or the number of CPUs local to a zone. With larger zones and more CPUs per node, the contention is getting worse. Furthermore, the fact that vm.percpu_pagelist_fraction adjusts both batch and high values means that the sysctl can reduce zone lock contention but also increase allocation latencies. This series disassociates pcp->high from pcp->batch and then scales pcp->high based on the size of the local zone with limited impact to reclaim and accounting for active CPUs but leaves pcp->batch static. It also adapts the number of pages that can be on the pcp list based on recent freeing patterns. The motivation is partially to adjust to larger memory sizes but is also driven by the fact that large batches of page freeing via release_pages() often shows zone contention as a major part of the problem. Another is a bug report based on an older kernel where a multi-terabyte process can takes several minutes to exit. A workaround was to use vm.percpu_pagelist_fraction to increase the pcp->high value but testing indicated that a production workload could not use the same values because of an increase in allocation latencies. Unfortunately, I cannot reproduce this test case myself as the multi-terabyte machines are in active use but it should alleviate the problem. The series aims to address both and partially acts as a pre-requisite. pcp only works with order-0 which is useless for SLUB (when using high orders) and THP (unconditionally). To store high-order pages on PCP, the pcp->high values need to be increased first. This patch (of 6): The vm.percpu_pagelist_fraction is used to increase the batch and high limits for the per-cpu page allocator (PCP). The intent behind the sysctl is to reduce zone lock acquisition when allocating/freeing pages but it has a problem. While it can decrease contention, it can also increase latency on the allocation side due to unreasonably large batch sizes. This leads to games where an administrator adjusts percpu_pagelist_fraction on the fly to work around contention and allocation latency problems. This series aims to alleviate the problems with zone lock contention while avoiding the allocation-side latency problems. For the purposes of review, it's easier to remove this sysctl now and reintroduce a similar sysctl later in the series that deals only with pcp->high. Link: https://lkml.kernel.org/r/20210525080119.5455-1-mgorman@techsingularity.net Link: https://lkml.kernel.org/r/20210525080119.5455-2-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Dave Hansen Acked-by: Vlastimil Babka Cc: Hillf Danton Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index f86018d5e362..7937a1d1d166 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1027,15 +1027,12 @@ int watermark_scale_factor_sysctl_handler(struct ctl_table *, int, void *, extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES]; int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); -int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int, - void *, size_t *, loff_t *); int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int numa_zonelist_order_handler(struct ctl_table *, int, void *, size_t *, loff_t *); -extern int percpu_pagelist_fraction; extern char numa_zonelist_order[]; #define NUMA_ZONELIST_ORDER_LEN 16 -- cgit v1.2.3 From 04f8cfeaed0849e702278378bce3867577ca45fb Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 28 Jun 2021 19:42:15 -0700 Subject: mm/page_alloc: adjust pcp->high after CPU hotplug events The PCP high watermark is based on the number of online CPUs so the watermarks must be adjusted during CPU hotplug. At the time of hot-remove, the number of online CPUs is already adjusted but during hot-add, a delta needs to be applied to update PCP to the correct value. After this patch is applied, the high watermarks are adjusted correctly. # grep high: /proc/zoneinfo | tail -1 high: 649 # echo 0 > /sys/devices/system/cpu/cpu4/online # grep high: /proc/zoneinfo | tail -1 high: 664 # echo 1 > /sys/devices/system/cpu/cpu4/online # grep high: /proc/zoneinfo | tail -1 high: 649 Link: https://lkml.kernel.org/r/20210525080119.5455-4-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Dave Hansen Cc: Hillf Danton Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpuhotplug.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 4a62b3980642..47e13582d9fc 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -54,7 +54,7 @@ enum cpuhp_state { CPUHP_MM_MEMCQ_DEAD, CPUHP_PERCPU_CNT_DEAD, CPUHP_RADIX_DEAD, - CPUHP_PAGE_ALLOC_DEAD, + CPUHP_PAGE_ALLOC, CPUHP_NET_DEV_DEAD, CPUHP_PCI_XGENE_DEAD, CPUHP_IOMMU_IOVA_DEAD, -- cgit v1.2.3 From 3b12e7e97938424de2bb1b95ba0bd6a49bad39f9 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 28 Jun 2021 19:42:18 -0700 Subject: mm/page_alloc: scale the number of pages that are batch freed When a task is freeing a large number of order-0 pages, it may acquire the zone->lock multiple times freeing pages in batches. This may unnecessarily contend on the zone lock when freeing very large number of pages. This patch adapts the size of the batch based on the recent pattern to scale the batch size for subsequent frees. As the machines I used were not large enough to test this are not large enough to illustrate a problem, a debugging patch shows patterns like the following (slightly editted for clarity) Baseline vanilla kernel time-unmap-14426 [...] free_pcppages_bulk: free 63 count 378 high 378 time-unmap-14426 [...] free_pcppages_bulk: free 63 count 378 high 378 time-unmap-14426 [...] free_pcppages_bulk: free 63 count 378 high 378 time-unmap-14426 [...] free_pcppages_bulk: free 63 count 378 high 378 time-unmap-14426 [...] free_pcppages_bulk: free 63 count 378 high 378 With patches time-unmap-7724 [...] free_pcppages_bulk: free 126 count 814 high 814 time-unmap-7724 [...] free_pcppages_bulk: free 252 count 814 high 814 time-unmap-7724 [...] free_pcppages_bulk: free 504 count 814 high 814 time-unmap-7724 [...] free_pcppages_bulk: free 751 count 814 high 814 time-unmap-7724 [...] free_pcppages_bulk: free 751 count 814 high 814 Link: https://lkml.kernel.org/r/20210525080119.5455-5-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Dave Hansen Acked-by: Vlastimil Babka Cc: Hillf Danton Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 7937a1d1d166..0a86b2890a16 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -343,8 +343,9 @@ struct per_cpu_pages { int count; /* number of pages in the list */ int high; /* high watermark, emptying needed */ int batch; /* chunk size for buddy add/remove */ + short free_factor; /* batch scaling factor during free */ #ifdef CONFIG_NUMA - int expire; /* When 0, remote pagesets are drained */ + short expire; /* When 0, remote pagesets are drained */ #endif /* Lists of pages, one per migrate type stored on the pcp-lists */ -- cgit v1.2.3 From c49c2c47dab6b8d45022b3fabf0642a0e62e3109 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 28 Jun 2021 19:42:21 -0700 Subject: mm/page_alloc: limit the number of pages on PCP lists when reclaim is active When kswapd is active then direct reclaim is potentially active. In either case, it is possible that a zone would be balanced if pages were not trapped on PCP lists. Instead of draining remote pages, simply limit the size of the PCP lists while kswapd is active. Link: https://lkml.kernel.org/r/20210525080119.5455-6-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Dave Hansen Cc: Hillf Danton Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 0a86b2890a16..b2f40d64bc4b 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -647,6 +647,7 @@ enum zone_flags { ZONE_BOOSTED_WATERMARK, /* zone recently boosted watermarks. * Cleared when kswapd is woken. */ + ZONE_RECLAIM_ACTIVE, /* kswapd may be scanning the zone. */ }; static inline unsigned long zone_managed_pages(struct zone *zone) -- cgit v1.2.3 From 74f44822097c665041010994502b5971d6cd9f04 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 28 Jun 2021 19:42:24 -0700 Subject: mm/page_alloc: introduce vm.percpu_pagelist_high_fraction This introduces a new sysctl vm.percpu_pagelist_high_fraction. It is similar to the old vm.percpu_pagelist_fraction. The old sysctl increased both pcp->batch and pcp->high with the higher pcp->high potentially reducing zone->lock contention. However, the higher pcp->batch value also potentially increased allocation latency while the PCP was refilled. This sysctl only adjusts pcp->high so that zone->lock contention is potentially reduced but allocation latency during a PCP refill remains the same. # grep -E "high:|batch" /proc/zoneinfo | tail -2 high: 649 batch: 63 # sysctl vm.percpu_pagelist_high_fraction=8 # grep -E "high:|batch" /proc/zoneinfo | tail -2 high: 35071 batch: 63 # sysctl vm.percpu_pagelist_high_fraction=64 high: 4383 batch: 63 # sysctl vm.percpu_pagelist_high_fraction=0 high: 649 batch: 63 [mgorman@techsingularity.net: fix documentation] Link: https://lkml.kernel.org/r/20210528151010.GQ30378@techsingularity.net Link: https://lkml.kernel.org/r/20210525080119.5455-7-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Dave Hansen Acked-by: Vlastimil Babka Cc: Hillf Danton Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index b2f40d64bc4b..7d206ca850c7 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1029,12 +1029,15 @@ int watermark_scale_factor_sysctl_handler(struct ctl_table *, int, void *, extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES]; int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); +int percpu_pagelist_high_fraction_sysctl_handler(struct ctl_table *, int, + void *, size_t *, loff_t *); int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int numa_zonelist_order_handler(struct ctl_table *, int, void *, size_t *, loff_t *); +extern int percpu_pagelist_high_fraction; extern char numa_zonelist_order[]; #define NUMA_ZONELIST_ORDER_LEN 16 -- cgit v1.2.3 From 777c00f5ede4fcb9ae49a2a957bec26d4d8f4c29 Mon Sep 17 00:00:00 2001 From: Dong Aisheng Date: Mon, 28 Jun 2021 19:42:27 -0700 Subject: mm: drop SECTION_SHIFT in code comments Actually SECTIONS_SHIFT is used in the kernel code, so the code comments is strictly incorrect. And since commit bbeae5b05ef6 ("mm: move page flags layout to separate header"), SECTIONS_SHIFT definition has been moved to include/linux/page-flags-layout.h, since code itself looks quite straighforward, instead of moving the code comment into the new place as well, we just simply remove it. This also fixed a checkpatch complain derived from the original code: WARNING: please, no space before tabs + * SECTIONS_SHIFT ^I^I#bits space required to store a section #$ Link: https://lkml.kernel.org/r/20210531091908.1738465-2-aisheng.dong@nxp.com Signed-off-by: Dong Aisheng Suggested-by: Yu Zhao Reviewed-by: Yu Zhao Cc: Andrey Konovalov Cc: Catalin Marinas Cc: Kees Cook Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 7d206ca850c7..3e62e8ef68b5 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1200,8 +1200,6 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, #ifdef CONFIG_SPARSEMEM /* - * SECTION_SHIFT #bits space required to store a section # - * * PA_SECTION_SHIFT physical address to/from section number * PFN_SECTION_SHIFT pfn to/from section number */ -- cgit v1.2.3 From bb1c50d3967f69f413b333713c2718d48d1ab7ea Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Mon, 28 Jun 2021 19:42:52 -0700 Subject: mm: remove CONFIG_DISCONTIGMEM There are no architectures that support DISCONTIGMEM left. Remove the configuration option and the dead code it was guarding in the generic memory management code. Link: https://lkml.kernel.org/r/20210608091316.3622-6-rppt@kernel.org Signed-off-by: Mike Rapoport Acked-by: Arnd Bergmann Acked-by: David Hildenbrand Cc: Geert Uytterhoeven Cc: Ivan Kokshaysky Cc: Jonathan Corbet Cc: Matt Turner Cc: Richard Henderson Cc: Vineet Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 3e62e8ef68b5..6f9829562af2 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -749,10 +749,12 @@ struct zonelist { struct zoneref _zonerefs[MAX_ZONES_PER_ZONELIST + 1]; }; -#ifndef CONFIG_DISCONTIGMEM -/* The array of struct pages - for discontigmem use pgdat->lmem_map */ +/* + * The array of struct pages for flatmem. + * It must be declared for SPARSEMEM as well because there are configurations + * that rely on that. + */ extern struct page *mem_map; -#endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split { -- cgit v1.2.3 From d3c251ab95b69f3dc189c4657baeac1b4c050789 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Mon, 28 Jun 2021 19:42:55 -0700 Subject: arch, mm: remove stale mentions of DISCONIGMEM There are several places that mention DISCONIGMEM in comments or have stale code guarded by CONFIG_DISCONTIGMEM. Remove the dead code and update the comments. Link: https://lkml.kernel.org/r/20210608091316.3622-7-rppt@kernel.org Signed-off-by: Mike Rapoport Acked-by: Arnd Bergmann Reviewed-by: David Hildenbrand Cc: Geert Uytterhoeven Cc: Ivan Kokshaysky Cc: Jonathan Corbet Cc: Matt Turner Cc: Richard Henderson Cc: Vineet Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 94f0b8b1cb55..0bec15b0691f 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -494,8 +494,8 @@ static inline int gfp_zonelist(gfp_t flags) * There are two zonelists per node, one for all zones with memory and * one containing just zones from the node the zonelist belongs to. * - * For the normal case of non-DISCONTIGMEM systems the NODE_DATA() gets - * optimized to &contig_page_data at compile-time. + * For the case of non-NUMA systems the NODE_DATA() gets optimized to + * &contig_page_data at compile-time. */ static inline struct zonelist *node_zonelist(int nid, gfp_t flags) { -- cgit v1.2.3 From a9ee6cf5c60ed1070e786e53665f9b2f23f2bd11 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Mon, 28 Jun 2021 19:43:01 -0700 Subject: mm: replace CONFIG_NEED_MULTIPLE_NODES with CONFIG_NUMA After removal of DISCINTIGMEM the NEED_MULTIPLE_NODES and NUMA configuration options are equivalent. Drop CONFIG_NEED_MULTIPLE_NODES and use CONFIG_NUMA instead. Done with $ sed -i 's/CONFIG_NEED_MULTIPLE_NODES/CONFIG_NUMA/' \ $(git grep -wl CONFIG_NEED_MULTIPLE_NODES) $ sed -i 's/NEED_MULTIPLE_NODES/NUMA/' \ $(git grep -wl NEED_MULTIPLE_NODES) with manual tweaks afterwards. [rppt@linux.ibm.com: fix arm boot crash] Link: https://lkml.kernel.org/r/YMj9vHhHOiCVN4BF@linux.ibm.com Link: https://lkml.kernel.org/r/20210608091316.3622-9-rppt@kernel.org Signed-off-by: Mike Rapoport Acked-by: Arnd Bergmann Acked-by: David Hildenbrand Cc: Geert Uytterhoeven Cc: Ivan Kokshaysky Cc: Jonathan Corbet Cc: Matt Turner Cc: Richard Henderson Cc: Vineet Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 6 +++--- include/linux/mm.h | 4 ++-- include/linux/mmzone.h | 6 +++--- 3 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 5984fff3f175..552309342c38 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -50,7 +50,7 @@ struct memblock_region { phys_addr_t base; phys_addr_t size; enum memblock_flags flags; -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA int nid; #endif }; @@ -347,7 +347,7 @@ int __init deferred_page_init_max_threads(const struct cpumask *node_cpumask); int memblock_set_node(phys_addr_t base, phys_addr_t size, struct memblock_type *type, int nid); -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA static inline void memblock_set_region_node(struct memblock_region *r, int nid) { r->nid = nid; @@ -366,7 +366,7 @@ static inline int memblock_get_region_node(const struct memblock_region *r) { return 0; } -#endif /* CONFIG_NEED_MULTIPLE_NODES */ +#endif /* CONFIG_NUMA */ /* Flags for memblock allocation APIs */ #define MEMBLOCK_ALLOC_ANYWHERE (~(phys_addr_t)0) diff --git a/include/linux/mm.h b/include/linux/mm.h index 9bd21e6fad6a..07922ee1477e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -46,7 +46,7 @@ extern int sysctl_page_lock_unfairness; void init_mm_internals(void); -#ifndef CONFIG_NEED_MULTIPLE_NODES /* Don't use mapnrs, do it properly */ +#ifndef CONFIG_NUMA /* Don't use mapnrs, do it properly */ extern unsigned long max_mapnr; static inline void set_max_mapnr(unsigned long limit) @@ -2460,7 +2460,7 @@ extern void get_pfn_range_for_nid(unsigned int nid, unsigned long *start_pfn, unsigned long *end_pfn); extern unsigned long find_min_pfn_with_active_regions(void); -#ifndef CONFIG_NEED_MULTIPLE_NODES +#ifndef CONFIG_NUMA static inline int early_pfn_to_nid(unsigned long pfn) { return 0; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 6f9829562af2..4bd420ed3961 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1043,17 +1043,17 @@ extern int percpu_pagelist_high_fraction; extern char numa_zonelist_order[]; #define NUMA_ZONELIST_ORDER_LEN 16 -#ifndef CONFIG_NEED_MULTIPLE_NODES +#ifndef CONFIG_NUMA extern struct pglist_data contig_page_data; #define NODE_DATA(nid) (&contig_page_data) #define NODE_MEM_MAP(nid) mem_map -#else /* CONFIG_NEED_MULTIPLE_NODES */ +#else /* CONFIG_NUMA */ #include -#endif /* !CONFIG_NEED_MULTIPLE_NODES */ +#endif /* !CONFIG_NUMA */ extern struct pglist_data *first_online_pgdat(void); extern struct pglist_data *next_online_pgdat(struct pglist_data *pgdat); -- cgit v1.2.3 From 43b02ba93b25b1caff7a3457fc5d005485e78da5 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Mon, 28 Jun 2021 19:43:05 -0700 Subject: mm: replace CONFIG_FLAT_NODE_MEM_MAP with CONFIG_FLATMEM After removal of the DISCONTIGMEM memory model the FLAT_NODE_MEM_MAP configuration option is equivalent to FLATMEM. Drop CONFIG_FLAT_NODE_MEM_MAP and use CONFIG_FLATMEM instead. Link: https://lkml.kernel.org/r/20210608091316.3622-10-rppt@kernel.org Signed-off-by: Mike Rapoport Acked-by: Arnd Bergmann Acked-by: David Hildenbrand Cc: Geert Uytterhoeven Cc: Ivan Kokshaysky Cc: Jonathan Corbet Cc: Matt Turner Cc: Richard Henderson Cc: Vineet Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 4bd420ed3961..578588d4afc9 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -788,7 +788,7 @@ typedef struct pglist_data { struct zonelist node_zonelists[MAX_ZONELISTS]; int nr_zones; /* number of populated zones in this node */ -#ifdef CONFIG_FLAT_NODE_MEM_MAP /* means !SPARSEMEM */ +#ifdef CONFIG_FLATMEM /* means !SPARSEMEM */ struct page *node_mem_map; #ifdef CONFIG_PAGE_EXTENSION struct page_ext *node_page_ext; @@ -878,7 +878,7 @@ typedef struct pglist_data { #define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages) #define node_spanned_pages(nid) (NODE_DATA(nid)->node_spanned_pages) -#ifdef CONFIG_FLAT_NODE_MEM_MAP +#ifdef CONFIG_FLATMEM #define pgdat_page_nr(pgdat, pagenr) ((pgdat)->node_mem_map + (pagenr)) #else #define pgdat_page_nr(pgdat, pagenr) pfn_to_page((pgdat)->node_start_pfn + (pagenr)) -- cgit v1.2.3 From 44042b4498728f4376e84bae1ac8016d146d850b Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 28 Jun 2021 19:43:08 -0700 Subject: mm/page_alloc: allow high-order pages to be stored on the per-cpu lists The per-cpu page allocator (PCP) only stores order-0 pages. This means that all THP and "cheap" high-order allocations including SLUB contends on the zone->lock. This patch extends the PCP allocator to store THP and "cheap" high-order pages. Note that struct per_cpu_pages increases in size to 256 bytes (4 cache lines) on x86-64. Note that this is not necessarily a universal performance win because of how it is implemented. High-order pages can cause pcp->high to be exceeded prematurely for lower-orders so for example, a large number of THP pages being freed could release order-0 pages from the PCP lists. Hence, much depends on the allocation/free pattern as observed by a single CPU to determine if caching helps or hurts a particular workload. That said, basic performance testing passed. The following is a netperf UDP_STREAM test which hits the relevant patches as some of the network allocations are high-order. netperf-udp 5.13.0-rc2 5.13.0-rc2 mm-pcpburst-v3r4 mm-pcphighorder-v1r7 Hmean send-64 261.46 ( 0.00%) 266.30 * 1.85%* Hmean send-128 516.35 ( 0.00%) 536.78 * 3.96%* Hmean send-256 1014.13 ( 0.00%) 1034.63 * 2.02%* Hmean send-1024 3907.65 ( 0.00%) 4046.11 * 3.54%* Hmean send-2048 7492.93 ( 0.00%) 7754.85 * 3.50%* Hmean send-3312 11410.04 ( 0.00%) 11772.32 * 3.18%* Hmean send-4096 13521.95 ( 0.00%) 13912.34 * 2.89%* Hmean send-8192 21660.50 ( 0.00%) 22730.72 * 4.94%* Hmean send-16384 31902.32 ( 0.00%) 32637.50 * 2.30%* Functionally, a patch like this is necessary to make bulk allocation of high-order pages work with similar performance to order-0 bulk allocations. The bulk allocator is not updated in this series as it would have to be determined by bulk allocation users how they want to track the order of pages allocated with the bulk allocator. Link: https://lkml.kernel.org/r/20210611135753.GC30378@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Zi Yan Cc: Dave Hansen Cc: Michal Hocko Cc: Jesper Dangaard Brouer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 578588d4afc9..265a32e1ff74 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -333,6 +333,24 @@ enum zone_watermarks { NR_WMARK }; +/* + * One per migratetype for each PAGE_ALLOC_COSTLY_ORDER plus one additional + * for pageblock size for THP if configured. + */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define NR_PCP_THP 1 +#else +#define NR_PCP_THP 0 +#endif +#define NR_PCP_LISTS (MIGRATE_PCPTYPES * (PAGE_ALLOC_COSTLY_ORDER + 1 + NR_PCP_THP)) + +/* + * Shift to encode migratetype and order in the same integer, with order + * in the least significant bits. + */ +#define NR_PCP_ORDER_WIDTH 8 +#define NR_PCP_ORDER_MASK ((1<_watermark[WMARK_MIN] + z->watermark_boost) #define low_wmark_pages(z) (z->_watermark[WMARK_LOW] + z->watermark_boost) #define high_wmark_pages(z) (z->_watermark[WMARK_HIGH] + z->watermark_boost) @@ -349,7 +367,7 @@ struct per_cpu_pages { #endif /* Lists of pages, one per migrate type stored on the pcp-lists */ - struct list_head lists[MIGRATE_PCPTYPES]; + struct list_head lists[NR_PCP_LISTS]; }; struct per_cpu_zonestat { -- cgit v1.2.3 From a3f5d80ea401ac857f2910e28b15f35b2cf902f4 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Mon, 28 Jun 2021 19:43:14 -0700 Subject: mm,hwpoison: send SIGBUS with error virutal address Now an action required MCE in already hwpoisoned address surely sends a SIGBUS to current process, but the SIGBUS doesn't convey error virtual address. That's not optimal for hwpoison-aware applications. To fix the issue, make memory_failure() call kill_accessing_process(), that does pagetable walk to find the error virtual address. It could find multiple virtual addresses for the same error page, and it seems hard to tell which virtual address is correct one. But that's rare and sending incorrect virtual address could be better than no address. So let's report the first found virtual address for now. [naoya.horiguchi@nec.com: fix walk_page_range() return] Link: https://lkml.kernel.org/r/20210603051055.GA244241@hori.linux.bs1.fc.nec.co.jp Link: https://lkml.kernel.org/r/20210521030156.2612074-4-nao.horiguchi@gmail.com Signed-off-by: Naoya Horiguchi Cc: Tony Luck Cc: Aili Yao Cc: Oscar Salvador Cc: David Hildenbrand Cc: Borislav Petkov Cc: Andy Lutomirski Cc: Jue Wang Cc: Borislav Petkov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swapops.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 6430a94c6981..5907205c712c 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -330,6 +330,11 @@ static inline int is_hwpoison_entry(swp_entry_t entry) return swp_type(entry) == SWP_HWPOISON; } +static inline unsigned long hwpoison_entry_to_pfn(swp_entry_t entry) +{ + return swp_offset(entry); +} + static inline void num_poisoned_pages_inc(void) { atomic_long_inc(&num_poisoned_pages); -- cgit v1.2.3 From e3ae2365efc14269170a6326477e669332271ab3 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Sun, 27 Jun 2021 18:48:21 -0400 Subject: net: sock: introduce sk_error_report This patch introduces a function wrapper to call the sk_error_report callback. That will prepare to add additional handling whenever sk_error_report is called, for example to trace socket errors. Signed-off-by: Alexander Aring Signed-off-by: David S. Miller --- include/linux/skmsg.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index fcaa9a7996c8..31866031e370 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -347,7 +347,7 @@ static inline void sk_psock_report_error(struct sk_psock *psock, int err) struct sock *sk = psock->sk; sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } struct sk_psock *sk_psock_init(struct sock *sk, int node); -- cgit v1.2.3 From 5a9b876e9d76810536bac70c78d961198612919c Mon Sep 17 00:00:00 2001 From: Ling Pei Lee Date: Tue, 29 Jun 2021 11:08:57 +0800 Subject: net: stmmac: option to enable PHY WOL with PMT enabled The current stmmac driver WOL implementation will enable MAC WOL if MAC HW PMT feature is on. Else, the driver will check for PHY WOL support. There is another case where MAC HW PMT is enabled but the platform still goes for the PHY WOL option. E.g, Intel platform are designed for PHY WOL but not MAC WOL although HW MAC PMT features are enabled. Introduce use_phy_wol platform data to select PHY WOL instead of depending on HW PMT features. Set use_phy_wol will disable the plat->pmt which currently used to determine the system to wake up by MAC WOL or PHY WOL. Signed-off-by: Ling Pei Lee Signed-off-by: David S. Miller --- include/linux/stmmac.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 3867980d1447..d5ae621d66ba 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -265,5 +265,6 @@ struct plat_stmmacenet_data { int msi_sfty_ue_vec; int msi_rx_base_vec; int msi_tx_base_vec; + bool use_phy_wol; }; #endif -- cgit v1.2.3 From 3e0f897fd92662f0ff21ca1759d724a9ad574858 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 23 Jun 2021 09:54:42 +0530 Subject: cpufreq: Remove the ->stop_cpu() driver callback Now that all users of ->stop_cpu() have been migrated to using other callbacks, drop it from the core. Signed-off-by: Viresh Kumar [ rjw: Minor edits in the subject and changelog ] Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 353969c7acd3..2e2267a36502 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -371,7 +371,6 @@ struct cpufreq_driver { int (*online)(struct cpufreq_policy *policy); int (*offline)(struct cpufreq_policy *policy); int (*exit)(struct cpufreq_policy *policy); - void (*stop_cpu)(struct cpufreq_policy *policy); int (*suspend)(struct cpufreq_policy *policy); int (*resume)(struct cpufreq_policy *policy); -- cgit v1.2.3 From c333b936c1530e76eba4e81091874d1217046131 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 7 Jun 2021 15:24:57 +0300 Subject: pwm: core: Remove unused devm_pwm_put() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are no users and seems no will come of the devm_pwm_put(). Remove the function. While at it, slightly update documentation. Signed-off-by: Andy Shevchenko Reviewed-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- include/linux/pwm.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 892ece4d4cfa..a0b7e43049d5 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -426,7 +426,6 @@ struct pwm_device *devm_of_pwm_get(struct device *dev, struct device_node *np, struct pwm_device *devm_fwnode_pwm_get(struct device *dev, struct fwnode_handle *fwnode, const char *con_id); -void devm_pwm_put(struct device *dev, struct pwm_device *pwm); #else static inline struct pwm_device *pwm_request(int pwm_id, const char *label) { @@ -533,10 +532,6 @@ devm_fwnode_pwm_get(struct device *dev, struct fwnode_handle *fwnode, { return ERR_PTR(-ENODEV); } - -static inline void devm_pwm_put(struct device *dev, struct pwm_device *pwm) -{ -} #endif static inline void pwm_apply_args(struct pwm_device *pwm) -- cgit v1.2.3 From b3beca76181681fce9cf72f37d19c3030e3353c0 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 29 Jun 2021 11:57:08 +0530 Subject: cpufreq: Remove ->resolve_freq() Commit e3c062360870 ("cpufreq: add cpufreq_driver_resolve_freq()") introduced this callback, back in 2016, for drivers that provide the ->target() callback. The kernel hasn't seen a single user of it in the past 5 years and it is not likely to be used any time soon. Remove it for now. Signed-off-by: Viresh Kumar [ rjw: Changelog edits ] Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 2e2267a36502..9fd719475fcd 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -330,15 +330,6 @@ struct cpufreq_driver { unsigned long target_perf, unsigned long capacity); - /* - * Caches and returns the lowest driver-supported frequency greater than - * or equal to the target frequency, subject to any driver limitations. - * Does not set the frequency. Only to be implemented for drivers with - * target(). - */ - unsigned int (*resolve_freq)(struct cpufreq_policy *policy, - unsigned int target_freq); - /* * Only for drivers with target_index() and CPUFREQ_ASYNC_NOTIFICATION * unset. -- cgit v1.2.3 From bbd7a6cc382f4317b08ba71151b23abf76fc4c34 Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Mon, 28 Jun 2021 00:39:57 +0200 Subject: clk: divider: Add re-usable determine_rate implementations These are useful when running on 32-bit systems to increase the upper supported frequency limit. clk_ops.round_rate returns a signed long which limits the maximum rate on 32-bit systems to 2^31 (or approx. 2.14GHz). clk_ops.determine_rate internally uses an unsigned long so the maximum rate on 32-bit systems is 2^32 or approx. 4.29GHz. To avoid code-duplication switch over divider_{ro_,}round_rate_parent to use the new divider_{ro_,}determine_rate functions. Reviewed-by: Jerome Brunet Signed-off-by: Martin Blumenstingl Link: https://lore.kernel.org/r/20210627223959.188139-2-martin.blumenstingl@googlemail.com Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 162a2e5546a3..d83b829305c0 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -629,6 +629,12 @@ long divider_ro_round_rate_parent(struct clk_hw *hw, struct clk_hw *parent, unsigned long rate, unsigned long *prate, const struct clk_div_table *table, u8 width, unsigned long flags, unsigned int val); +int divider_determine_rate(struct clk_hw *hw, struct clk_rate_request *req, + const struct clk_div_table *table, u8 width, + unsigned long flags); +int divider_ro_determine_rate(struct clk_hw *hw, struct clk_rate_request *req, + const struct clk_div_table *table, u8 width, + unsigned long flags, unsigned int val); int divider_get_val(unsigned long rate, unsigned long parent_rate, const struct clk_div_table *table, u8 width, unsigned long flags); -- cgit v1.2.3 From 5ec780a6eddacbbbc1c5d5838753c3ca43f93526 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Jun 2021 10:10:12 +0200 Subject: block: mark blk_mq_init_queue_data static All driver uses are gone now. Signed-off-by: Christoph Hellwig Reviewed-by: Bart Van Assche Link: https://lore.kernel.org/r/20210624081012.256464-1-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index fd2de2b422ed..1d18447ebebc 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -439,8 +439,6 @@ enum { struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata); struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *); -struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set, - void *queuedata); int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, struct request_queue *q); void blk_mq_unregister_dev(struct device *, struct request_queue *); -- cgit v1.2.3 From da6269da4cfe29f484e8fd27c1496b81b47e2499 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Jun 2021 14:39:34 +0200 Subject: block: remove REQ_OP_SCSI_{IN,OUT} With the legacy IDE driver gone drivers now use either REQ_OP_DRV_* or REQ_OP_SCSI_*, so unify the two concepts of passthrough requests into a single one. Reviewed-by: Chaitanya Kulkarni Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 3 --- include/linux/blkdev.h | 33 +++------------------------------ 2 files changed, 3 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index fd3860d18d7e..db61f7df1823 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -350,9 +350,6 @@ enum req_opf { /* reset all the zone present on the device */ REQ_OP_ZONE_RESET_ALL = 17, - /* SCSI passthrough using struct scsi_request */ - REQ_OP_SCSI_IN = 32, - REQ_OP_SCSI_OUT = 33, /* Driver private requests */ REQ_OP_DRV_IN = 34, REQ_OP_DRV_OUT = 35, diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d66d0da72529..d199e51524eb 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -240,42 +240,15 @@ struct request { void *end_io_data; }; -static inline bool blk_op_is_scsi(unsigned int op) -{ - return op == REQ_OP_SCSI_IN || op == REQ_OP_SCSI_OUT; -} - -static inline bool blk_op_is_private(unsigned int op) +static inline bool blk_op_is_passthrough(unsigned int op) { + op &= REQ_OP_MASK; return op == REQ_OP_DRV_IN || op == REQ_OP_DRV_OUT; } -static inline bool blk_rq_is_scsi(struct request *rq) -{ - return blk_op_is_scsi(req_op(rq)); -} - -static inline bool blk_rq_is_private(struct request *rq) -{ - return blk_op_is_private(req_op(rq)); -} - static inline bool blk_rq_is_passthrough(struct request *rq) { - return blk_rq_is_scsi(rq) || blk_rq_is_private(rq); -} - -static inline bool bio_is_passthrough(struct bio *bio) -{ - unsigned op = bio_op(bio); - - return blk_op_is_scsi(op) || blk_op_is_private(op); -} - -static inline bool blk_op_is_passthrough(unsigned int op) -{ - return (blk_op_is_scsi(op & REQ_OP_MASK) || - blk_op_is_private(op & REQ_OP_MASK)); + return blk_op_is_passthrough(req_op(rq)); } static inline unsigned short req_get_ioprio(struct request *req) -- cgit v1.2.3 From fb9b16e15cd70e21d8af7f03d700deb9509c2ce8 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 10 Jun 2021 14:44:36 -0700 Subject: block: return errors from blk_execute_rq() The synchronous blk_execute_rq() had not provided a way for its callers to know if its request was successful or not. Return the blk_status_t result of the request. Reviewed-by: Christoph Hellwig Reviewed-by: Ming Lei Signed-off-by: Keith Busch Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20210610214437.641245-4-kbusch@kernel.org Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d199e51524eb..c454fb446fd0 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -909,10 +909,12 @@ extern int blk_rq_map_kern(struct request_queue *, struct request *, void *, uns extern int blk_rq_map_user_iov(struct request_queue *, struct request *, struct rq_map_data *, const struct iov_iter *, gfp_t); -extern void blk_execute_rq(struct gendisk *, struct request *, int); extern void blk_execute_rq_nowait(struct gendisk *, struct request *, int, rq_end_io_fn *); +blk_status_t blk_execute_rq(struct gendisk *bd_disk, struct request *rq, + int at_head); + /* Helper to convert REQ_OP_XXX to its string format XXX */ extern const char *blk_op_str(unsigned int op); -- cgit v1.2.3 From 1eb5dde674f57b1a1918dab33f09e35cdd64eb07 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 23 Jun 2020 15:49:40 +0530 Subject: cpufreq: CPPC: Add support for frequency invariance The Frequency Invariance Engine (FIE) is providing a frequency scaling correction factor that helps achieve more accurate load-tracking. Normally, this scaling factor can be obtained directly with the help of the cpufreq drivers as they know the exact frequency the hardware is running at. But that isn't the case for CPPC cpufreq driver. Another way of obtaining that is using the arch specific counter support, which is already present in kernel, but that hardware is optional for platforms. This patch updates the CPPC driver to register itself with the topology core to provide its own implementation (cppc_scale_freq_tick()) of topology_scale_freq_tick() which gets called by the scheduler on every tick. Note that the arch specific counters have higher priority than CPPC counters, if available, though the CPPC driver doesn't need to have any special handling for that. On an invocation of cppc_scale_freq_tick(), we schedule an irq work (since we reach here from hard-irq context), which then schedules a normal work item and cppc_scale_freq_workfn() updates the per_cpu arch_freq_scale variable based on the counter updates since the last tick. To allow platforms to disable this CPPC counter-based frequency invariance support, this is all done under CONFIG_ACPI_CPPC_CPUFREQ_FIE, which is enabled by default. This also exports sched_setattr_nocheck() as the CPPC driver can be built as a module. Cc: linux-acpi@vger.kernel.org Tested-by: Vincent Guittot Reviewed-by: Ionela Voinescu Tested-by: Qian Cai Signed-off-by: Viresh Kumar --- include/linux/arch_topology.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index 11e555cfaecb..f180240dc95f 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -37,6 +37,7 @@ bool topology_scale_freq_invariant(void); enum scale_freq_source { SCALE_FREQ_SOURCE_CPUFREQ = 0, SCALE_FREQ_SOURCE_ARCH, + SCALE_FREQ_SOURCE_CPPC, }; struct scale_freq_data { -- cgit v1.2.3 From 426e5c429d16e4cd5ded46e21ff8e939bf8abd0f Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Wed, 30 Jun 2021 18:47:00 -0700 Subject: mm: memory_hotplug: factor out bootmem core functions to bootmem_info.c Patch series "Free some vmemmap pages of HugeTLB page", v23. This patch series will free some vmemmap pages(struct page structures) associated with each HugeTLB page when preallocated to save memory. In order to reduce the difficulty of the first version of code review. In this version, we disable PMD/huge page mapping of vmemmap if this feature was enabled. This acutely eliminates a bunch of the complex code doing page table manipulation. When this patch series is solid, we cam add the code of vmemmap page table manipulation in the future. The struct page structures (page structs) are used to describe a physical page frame. By default, there is an one-to-one mapping from a page frame to it's corresponding page struct. The HugeTLB pages consist of multiple base page size pages and is supported by many architectures. See hugetlbpage.rst in the Documentation directory for more details. On the x86 architecture, HugeTLB pages of size 2MB and 1GB are currently supported. Since the base page size on x86 is 4KB, a 2MB HugeTLB page consists of 512 base pages and a 1GB HugeTLB page consists of 4096 base pages. For each base page, there is a corresponding page struct. Within the HugeTLB subsystem, only the first 4 page structs are used to contain unique information about a HugeTLB page. HUGETLB_CGROUP_MIN_ORDER provides this upper limit. The only 'useful' information in the remaining page structs is the compound_head field, and this field is the same for all tail pages. By removing redundant page structs for HugeTLB pages, memory can returned to the buddy allocator for other uses. When the system boot up, every 2M HugeTLB has 512 struct page structs which size is 8 pages(sizeof(struct page) * 512 / PAGE_SIZE). HugeTLB struct pages(8 pages) page frame(8 pages) +-----------+ ---virt_to_page---> +-----------+ mapping to +-----------+ | | | 0 | -------------> | 0 | | | +-----------+ +-----------+ | | | 1 | -------------> | 1 | | | +-----------+ +-----------+ | | | 2 | -------------> | 2 | | | +-----------+ +-----------+ | | | 3 | -------------> | 3 | | | +-----------+ +-----------+ | | | 4 | -------------> | 4 | | 2MB | +-----------+ +-----------+ | | | 5 | -------------> | 5 | | | +-----------+ +-----------+ | | | 6 | -------------> | 6 | | | +-----------+ +-----------+ | | | 7 | -------------> | 7 | | | +-----------+ +-----------+ | | | | | | +-----------+ The value of page->compound_head is the same for all tail pages. The first page of page structs (page 0) associated with the HugeTLB page contains the 4 page structs necessary to describe the HugeTLB. The only use of the remaining pages of page structs (page 1 to page 7) is to point to page->compound_head. Therefore, we can remap pages 2 to 7 to page 1. Only 2 pages of page structs will be used for each HugeTLB page. This will allow us to free the remaining 6 pages to the buddy allocator. Here is how things look after remapping. HugeTLB struct pages(8 pages) page frame(8 pages) +-----------+ ---virt_to_page---> +-----------+ mapping to +-----------+ | | | 0 | -------------> | 0 | | | +-----------+ +-----------+ | | | 1 | -------------> | 1 | | | +-----------+ +-----------+ | | | 2 | ----------------^ ^ ^ ^ ^ ^ | | +-----------+ | | | | | | | | 3 | ------------------+ | | | | | | +-----------+ | | | | | | | 4 | --------------------+ | | | | 2MB | +-----------+ | | | | | | 5 | ----------------------+ | | | | +-----------+ | | | | | 6 | ------------------------+ | | | +-----------+ | | | | 7 | --------------------------+ | | +-----------+ | | | | | | +-----------+ When a HugeTLB is freed to the buddy system, we should allocate 6 pages for vmemmap pages and restore the previous mapping relationship. Apart from 2MB HugeTLB page, we also have 1GB HugeTLB page. It is similar to the 2MB HugeTLB page. We also can use this approach to free the vmemmap pages. In this case, for the 1GB HugeTLB page, we can save 4094 pages. This is a very substantial gain. On our server, run some SPDK/QEMU applications which will use 1024GB HugeTLB page. With this feature enabled, we can save ~16GB (1G hugepage)/~12GB (2MB hugepage) memory. Because there are vmemmap page tables reconstruction on the freeing/allocating path, it increases some overhead. Here are some overhead analysis. 1) Allocating 10240 2MB HugeTLB pages. a) With this patch series applied: # time echo 10240 > /proc/sys/vm/nr_hugepages real 0m0.166s user 0m0.000s sys 0m0.166s # bpftrace -e 'kprobe:alloc_fresh_huge_page { @start[tid] = nsecs; } kretprobe:alloc_fresh_huge_page /@start[tid]/ { @latency = hist(nsecs - @start[tid]); delete(@start[tid]); }' Attaching 2 probes... @latency: [8K, 16K) 5476 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@| [16K, 32K) 4760 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ | [32K, 64K) 4 | | b) Without this patch series: # time echo 10240 > /proc/sys/vm/nr_hugepages real 0m0.067s user 0m0.000s sys 0m0.067s # bpftrace -e 'kprobe:alloc_fresh_huge_page { @start[tid] = nsecs; } kretprobe:alloc_fresh_huge_page /@start[tid]/ { @latency = hist(nsecs - @start[tid]); delete(@start[tid]); }' Attaching 2 probes... @latency: [4K, 8K) 10147 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@| [8K, 16K) 93 | | Summarize: this feature is about ~2x slower than before. 2) Freeing 10240 2MB HugeTLB pages. a) With this patch series applied: # time echo 0 > /proc/sys/vm/nr_hugepages real 0m0.213s user 0m0.000s sys 0m0.213s # bpftrace -e 'kprobe:free_pool_huge_page { @start[tid] = nsecs; } kretprobe:free_pool_huge_page /@start[tid]/ { @latency = hist(nsecs - @start[tid]); delete(@start[tid]); }' Attaching 2 probes... @latency: [8K, 16K) 6 | | [16K, 32K) 10227 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@| [32K, 64K) 7 | | b) Without this patch series: # time echo 0 > /proc/sys/vm/nr_hugepages real 0m0.081s user 0m0.000s sys 0m0.081s # bpftrace -e 'kprobe:free_pool_huge_page { @start[tid] = nsecs; } kretprobe:free_pool_huge_page /@start[tid]/ { @latency = hist(nsecs - @start[tid]); delete(@start[tid]); }' Attaching 2 probes... @latency: [4K, 8K) 6805 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@| [8K, 16K) 3427 |@@@@@@@@@@@@@@@@@@@@@@@@@@ | [16K, 32K) 8 | | Summary: The overhead of __free_hugepage is about ~2-3x slower than before. Although the overhead has increased, the overhead is not significant. Like Mike said, "However, remember that the majority of use cases create HugeTLB pages at or shortly after boot time and add them to the pool. So, additional overhead is at pool creation time. There is no change to 'normal run time' operations of getting a page from or returning a page to the pool (think page fault/unmap)". Despite the overhead and in addition to the memory gains from this series. The following data is obtained by Joao Martins. Very thanks to his effort. There's an additional benefit which is page (un)pinners will see an improvement and Joao presumes because there are fewer memmap pages and thus the tail/head pages are staying in cache more often. Out of the box Joao saw (when comparing linux-next against linux-next + this series) with gup_test and pinning a 16G HugeTLB file (with 1G pages): get_user_pages(): ~32k -> ~9k unpin_user_pages(): ~75k -> ~70k Usually any tight loop fetching compound_head(), or reading tail pages data (e.g. compound_head) benefit a lot. There's some unpinning inefficiencies Joao was fixing[2], but with that in added it shows even more: unpin_user_pages(): ~27k -> ~3.8k [1] https://lore.kernel.org/linux-mm/20210409205254.242291-1-mike.kravetz@oracle.com/ [2] https://lore.kernel.org/linux-mm/20210204202500.26474-1-joao.m.martins@oracle.com/ This patch (of 9): Move bootmem info registration common API to individual bootmem_info.c. And we will use {get,put}_page_bootmem() to initialize the page for the vmemmap pages or free the vmemmap pages to buddy in the later patch. So move them out of CONFIG_MEMORY_HOTPLUG_SPARSE. This is just code movement without any functional change. Link: https://lkml.kernel.org/r/20210510030027.56044-1-songmuchun@bytedance.com Link: https://lkml.kernel.org/r/20210510030027.56044-2-songmuchun@bytedance.com Signed-off-by: Muchun Song Acked-by: Mike Kravetz Reviewed-by: Oscar Salvador Reviewed-by: David Hildenbrand Reviewed-by: Miaohe Lin Tested-by: Chen Huang Tested-by: Bodeddula Balasubramaniam Cc: Jonathan Corbet Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: x86@kernel.org Cc: "H. Peter Anvin" Cc: Dave Hansen Cc: Andy Lutomirski Cc: Peter Zijlstra Cc: Alexander Viro Cc: Paul E. McKenney Cc: Pawan Gupta Cc: Randy Dunlap Cc: Oliver Neukum Cc: Anshuman Khandual Cc: Joerg Roedel Cc: Mina Almasry Cc: David Rientjes Cc: Matthew Wilcox Cc: Michal Hocko Cc: Barry Song Cc: HORIGUCHI NAOYA Cc: Joao Martins Cc: Xiongchun Duan Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem_info.h | 40 ++++++++++++++++++++++++++++++++++++++++ include/linux/memory_hotplug.h | 27 --------------------------- 2 files changed, 40 insertions(+), 27 deletions(-) create mode 100644 include/linux/bootmem_info.h (limited to 'include/linux') diff --git a/include/linux/bootmem_info.h b/include/linux/bootmem_info.h new file mode 100644 index 000000000000..4ed6dee1adc9 --- /dev/null +++ b/include/linux/bootmem_info.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_BOOTMEM_INFO_H +#define __LINUX_BOOTMEM_INFO_H + +#include + +/* + * Types for free bootmem stored in page->lru.next. These have to be in + * some random range in unsigned long space for debugging purposes. + */ +enum { + MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 12, + SECTION_INFO = MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE, + MIX_SECTION_INFO, + NODE_INFO, + MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE = NODE_INFO, +}; + +#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE +void __init register_page_bootmem_info_node(struct pglist_data *pgdat); + +void get_page_bootmem(unsigned long info, struct page *page, + unsigned long type); +void put_page_bootmem(struct page *page); +#else +static inline void register_page_bootmem_info_node(struct pglist_data *pgdat) +{ +} + +static inline void put_page_bootmem(struct page *page) +{ +} + +static inline void get_page_bootmem(unsigned long info, struct page *page, + unsigned long type) +{ +} +#endif + +#endif /* __LINUX_BOOTMEM_INFO_H */ diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 28f32fd00fe9..a7fd2c3ccb77 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -18,18 +18,6 @@ struct vmem_altmap; #ifdef CONFIG_MEMORY_HOTPLUG struct page *pfn_to_online_page(unsigned long pfn); -/* - * Types for free bootmem stored in page->lru.next. These have to be in - * some random range in unsigned long space for debugging purposes. - */ -enum { - MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 12, - SECTION_INFO = MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE, - MIX_SECTION_INFO, - NODE_INFO, - MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE = NODE_INFO, -}; - /* Types for control the zone type of onlined and offlined memory */ enum { /* Offline the memory. */ @@ -222,17 +210,6 @@ static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) #endif /* CONFIG_NUMA */ #endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */ -#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE -extern void __init register_page_bootmem_info_node(struct pglist_data *pgdat); -#else -static inline void register_page_bootmem_info_node(struct pglist_data *pgdat) -{ -} -#endif -extern void put_page_bootmem(struct page *page); -extern void get_page_bootmem(unsigned long ingo, struct page *page, - unsigned long type); - void get_online_mems(void); void put_online_mems(void); @@ -260,10 +237,6 @@ static inline void zone_span_writelock(struct zone *zone) {} static inline void zone_span_writeunlock(struct zone *zone) {} static inline void zone_seqlock_init(struct zone *zone) {} -static inline void register_page_bootmem_info_node(struct pglist_data *pgdat) -{ -} - static inline int try_online_node(int nid) { return 0; -- cgit v1.2.3 From cd39d4e9e71c5437b67c819c3d53032145bf2879 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Wed, 30 Jun 2021 18:47:09 -0700 Subject: mm: hugetlb: gather discrete indexes of tail page For HugeTLB page, there are more metadata to save in the struct page. But the head struct page cannot meet our needs, so we have to abuse other tail struct page to store the metadata. In order to avoid conflicts caused by subsequent use of more tail struct pages, we can gather these discrete indexes of tail struct page. In this case, it will be easier to add a new tail page index later. Link: https://lkml.kernel.org/r/20210510030027.56044-4-songmuchun@bytedance.com Signed-off-by: Muchun Song Reviewed-by: Oscar Salvador Reviewed-by: Miaohe Lin Tested-by: Chen Huang Tested-by: Bodeddula Balasubramaniam Acked-by: Michal Hocko Reviewed-by: Mike Kravetz Cc: Alexander Viro Cc: Andy Lutomirski Cc: Anshuman Khandual Cc: Balbir Singh Cc: Barry Song Cc: Borislav Petkov Cc: Dave Hansen Cc: David Hildenbrand Cc: David Rientjes Cc: HORIGUCHI NAOYA Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Joao Martins Cc: Joerg Roedel Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Mina Almasry Cc: Oliver Neukum Cc: Paul E. McKenney Cc: Pawan Gupta Cc: Peter Zijlstra Cc: Randy Dunlap Cc: Thomas Gleixner Cc: Xiongchun Duan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 21 +++++++++++++++++++-- include/linux/hugetlb_cgroup.h | 19 +++++++++++-------- 2 files changed, 30 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 3c0117656745..0c8c96481259 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -29,6 +29,23 @@ typedef struct { unsigned long pd; } hugepd_t; #include #include +/* + * For HugeTLB page, there are more metadata to save in the struct page. But + * the head struct page cannot meet our needs, so we have to abuse other tail + * struct page to store the metadata. In order to avoid conflicts caused by + * subsequent use of more tail struct pages, we gather these discrete indexes + * of tail struct page here. + */ +enum { + SUBPAGE_INDEX_SUBPOOL = 1, /* reuse page->private */ +#ifdef CONFIG_CGROUP_HUGETLB + SUBPAGE_INDEX_CGROUP, /* reuse page->private */ + SUBPAGE_INDEX_CGROUP_RSVD, /* reuse page->private */ + __MAX_CGROUP_SUBPAGE_INDEX = SUBPAGE_INDEX_CGROUP_RSVD, +#endif + __NR_USED_SUBPAGE, +}; + struct hugepage_subpool { spinlock_t lock; long count; @@ -635,13 +652,13 @@ extern unsigned int default_hstate_idx; */ static inline struct hugepage_subpool *hugetlb_page_subpool(struct page *hpage) { - return (struct hugepage_subpool *)(hpage+1)->private; + return (void *)page_private(hpage + SUBPAGE_INDEX_SUBPOOL); } static inline void hugetlb_set_page_subpool(struct page *hpage, struct hugepage_subpool *subpool) { - set_page_private(hpage+1, (unsigned long)subpool); + set_page_private(hpage + SUBPAGE_INDEX_SUBPOOL, (unsigned long)subpool); } static inline struct hstate *hstate_file(struct file *f) diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h index 0bff345c4bc6..0b8d1fdda3a1 100644 --- a/include/linux/hugetlb_cgroup.h +++ b/include/linux/hugetlb_cgroup.h @@ -21,15 +21,16 @@ struct hugetlb_cgroup; struct resv_map; struct file_region; +#ifdef CONFIG_CGROUP_HUGETLB /* * Minimum page order trackable by hugetlb cgroup. * At least 4 pages are necessary for all the tracking information. - * The second tail page (hpage[2]) is the fault usage cgroup. - * The third tail page (hpage[3]) is the reservation usage cgroup. + * The second tail page (hpage[SUBPAGE_INDEX_CGROUP]) is the fault + * usage cgroup. The third tail page (hpage[SUBPAGE_INDEX_CGROUP_RSVD]) + * is the reservation usage cgroup. */ -#define HUGETLB_CGROUP_MIN_ORDER 2 +#define HUGETLB_CGROUP_MIN_ORDER order_base_2(__MAX_CGROUP_SUBPAGE_INDEX + 1) -#ifdef CONFIG_CGROUP_HUGETLB enum hugetlb_memory_event { HUGETLB_MAX, HUGETLB_NR_MEMORY_EVENTS, @@ -66,9 +67,9 @@ __hugetlb_cgroup_from_page(struct page *page, bool rsvd) if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER) return NULL; if (rsvd) - return (struct hugetlb_cgroup *)page[3].private; + return (void *)page_private(page + SUBPAGE_INDEX_CGROUP_RSVD); else - return (struct hugetlb_cgroup *)page[2].private; + return (void *)page_private(page + SUBPAGE_INDEX_CGROUP); } static inline struct hugetlb_cgroup *hugetlb_cgroup_from_page(struct page *page) @@ -90,9 +91,11 @@ static inline int __set_hugetlb_cgroup(struct page *page, if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER) return -1; if (rsvd) - page[3].private = (unsigned long)h_cg; + set_page_private(page + SUBPAGE_INDEX_CGROUP_RSVD, + (unsigned long)h_cg); else - page[2].private = (unsigned long)h_cg; + set_page_private(page + SUBPAGE_INDEX_CGROUP, + (unsigned long)h_cg); return 0; } -- cgit v1.2.3 From f41f2ed43ca5258d70d53290d1951a21621f95c8 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Wed, 30 Jun 2021 18:47:13 -0700 Subject: mm: hugetlb: free the vmemmap pages associated with each HugeTLB page Every HugeTLB has more than one struct page structure. We __know__ that we only use the first 4 (__NR_USED_SUBPAGE) struct page structures to store metadata associated with each HugeTLB. There are a lot of struct page structures associated with each HugeTLB page. For tail pages, the value of compound_head is the same. So we can reuse first page of tail page structures. We map the virtual addresses of the remaining pages of tail page structures to the first tail page struct, and then free these page frames. Therefore, we need to reserve two pages as vmemmap areas. When we allocate a HugeTLB page from the buddy, we can free some vmemmap pages associated with each HugeTLB page. It is more appropriate to do it in the prep_new_huge_page(). The free_vmemmap_pages_per_hpage(), which indicates how many vmemmap pages associated with a HugeTLB page can be freed, returns zero for now, which means the feature is disabled. We will enable it once all the infrastructure is there. [willy@infradead.org: fix documentation warning] Link: https://lkml.kernel.org/r/20210615200242.1716568-5-willy@infradead.org Link: https://lkml.kernel.org/r/20210510030027.56044-5-songmuchun@bytedance.com Signed-off-by: Muchun Song Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Oscar Salvador Tested-by: Chen Huang Tested-by: Bodeddula Balasubramaniam Acked-by: Michal Hocko Reviewed-by: Mike Kravetz Cc: Alexander Viro Cc: Andy Lutomirski Cc: Anshuman Khandual Cc: Balbir Singh Cc: Barry Song Cc: Borislav Petkov Cc: Dave Hansen Cc: David Hildenbrand Cc: David Rientjes Cc: HORIGUCHI NAOYA Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Joao Martins Cc: Joerg Roedel Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Mina Almasry Cc: Oliver Neukum Cc: Paul E. McKenney Cc: Pawan Gupta Cc: Peter Zijlstra Cc: Randy Dunlap Cc: Thomas Gleixner Cc: Xiongchun Duan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem_info.h | 28 +++++++++++++++++++++++++++- include/linux/mm.h | 3 +++ 2 files changed, 30 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bootmem_info.h b/include/linux/bootmem_info.h index 4ed6dee1adc9..2bc8b1f69c93 100644 --- a/include/linux/bootmem_info.h +++ b/include/linux/bootmem_info.h @@ -2,7 +2,7 @@ #ifndef __LINUX_BOOTMEM_INFO_H #define __LINUX_BOOTMEM_INFO_H -#include +#include /* * Types for free bootmem stored in page->lru.next. These have to be in @@ -22,6 +22,27 @@ void __init register_page_bootmem_info_node(struct pglist_data *pgdat); void get_page_bootmem(unsigned long info, struct page *page, unsigned long type); void put_page_bootmem(struct page *page); + +/* + * Any memory allocated via the memblock allocator and not via the + * buddy will be marked reserved already in the memmap. For those + * pages, we can call this function to free it to buddy allocator. + */ +static inline void free_bootmem_page(struct page *page) +{ + unsigned long magic = (unsigned long)page->freelist; + + /* + * The reserve_bootmem_region sets the reserved flag on bootmem + * pages. + */ + VM_BUG_ON_PAGE(page_ref_count(page) != 2, page); + + if (magic == SECTION_INFO || magic == MIX_SECTION_INFO) + put_page_bootmem(page); + else + VM_BUG_ON_PAGE(1, page); +} #else static inline void register_page_bootmem_info_node(struct pglist_data *pgdat) { @@ -35,6 +56,11 @@ static inline void get_page_bootmem(unsigned long info, struct page *page, unsigned long type) { } + +static inline void free_bootmem_page(struct page *page) +{ + free_reserved_page(page); +} #endif #endif /* __LINUX_BOOTMEM_INFO_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 07922ee1477e..3437aa7c6c91 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3076,6 +3076,9 @@ static inline void print_vma_addr(char *prefix, unsigned long rip) } #endif +void vmemmap_remap_free(unsigned long start, unsigned long end, + unsigned long reuse); + void *sparse_buffer_alloc(unsigned long size); struct page * __populate_section_memmap(unsigned long pfn, unsigned long nr_pages, int nid, struct vmem_altmap *altmap); -- cgit v1.2.3 From ad2fa3717b74994a22519dbe045757135db00dbb Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Wed, 30 Jun 2021 18:47:21 -0700 Subject: mm: hugetlb: alloc the vmemmap pages associated with each HugeTLB page When we free a HugeTLB page to the buddy allocator, we need to allocate the vmemmap pages associated with it. However, we may not be able to allocate the vmemmap pages when the system is under memory pressure. In this case, we just refuse to free the HugeTLB page. This changes behavior in some corner cases as listed below: 1) Failing to free a huge page triggered by the user (decrease nr_pages). User needs to try again later. 2) Failing to free a surplus huge page when freed by the application. Try again later when freeing a huge page next time. 3) Failing to dissolve a free huge page on ZONE_MOVABLE via offline_pages(). This can happen when we have plenty of ZONE_MOVABLE memory, but not enough kernel memory to allocate vmemmmap pages. We may even be able to migrate huge page contents, but will not be able to dissolve the source huge page. This will prevent an offline operation and is unfortunate as memory offlining is expected to succeed on movable zones. Users that depend on memory hotplug to succeed for movable zones should carefully consider whether the memory savings gained from this feature are worth the risk of possibly not being able to offline memory in certain situations. 4) Failing to dissolve a huge page on CMA/ZONE_MOVABLE via alloc_contig_range() - once we have that handling in place. Mainly affects CMA and virtio-mem. Similar to 3). virito-mem will handle migration errors gracefully. CMA might be able to fallback on other free areas within the CMA region. Vmemmap pages are allocated from the page freeing context. In order for those allocations to be not disruptive (e.g. trigger oom killer) __GFP_NORETRY is used. hugetlb_lock is dropped for the allocation because a non sleeping allocation would be too fragile and it could fail too easily under memory pressure. GFP_ATOMIC or other modes to access memory reserves is not used because we want to prevent consuming reserves under heavy hugetlb freeing. [mike.kravetz@oracle.com: fix dissolve_free_huge_page use of tail/head page] Link: https://lkml.kernel.org/r/20210527231225.226987-1-mike.kravetz@oracle.com [willy@infradead.org: fix alloc_vmemmap_page_list documentation warning] Link: https://lkml.kernel.org/r/20210615200242.1716568-6-willy@infradead.org Link: https://lkml.kernel.org/r/20210510030027.56044-7-songmuchun@bytedance.com Signed-off-by: Muchun Song Signed-off-by: Mike Kravetz Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Mike Kravetz Reviewed-by: Oscar Salvador Cc: Alexander Viro Cc: Andy Lutomirski Cc: Anshuman Khandual Cc: Balbir Singh Cc: Barry Song Cc: Bodeddula Balasubramaniam Cc: Borislav Petkov Cc: Chen Huang Cc: Dave Hansen Cc: David Hildenbrand Cc: David Rientjes Cc: HORIGUCHI NAOYA Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Joao Martins Cc: Joerg Roedel Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Michal Hocko Cc: Mina Almasry Cc: Oliver Neukum Cc: Paul E. McKenney Cc: Pawan Gupta Cc: Peter Zijlstra Cc: Randy Dunlap Cc: Thomas Gleixner Cc: Xiongchun Duan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 3 +++ include/linux/mm.h | 2 ++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 0c8c96481259..3578d9d708fe 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -532,12 +532,14 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, * modifications require hugetlb_lock. * HPG_freed - Set when page is on the free lists. * Synchronization: hugetlb_lock held for examination and modification. + * HPG_vmemmap_optimized - Set when the vmemmap pages of the page are freed. */ enum hugetlb_page_flags { HPG_restore_reserve = 0, HPG_migratable, HPG_temporary, HPG_freed, + HPG_vmemmap_optimized, __NR_HPAGEFLAGS, }; @@ -583,6 +585,7 @@ HPAGEFLAG(RestoreReserve, restore_reserve) HPAGEFLAG(Migratable, migratable) HPAGEFLAG(Temporary, temporary) HPAGEFLAG(Freed, freed) +HPAGEFLAG(VmemmapOptimized, vmemmap_optimized) #ifdef CONFIG_HUGETLB_PAGE diff --git a/include/linux/mm.h b/include/linux/mm.h index 3437aa7c6c91..706bee98d965 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3078,6 +3078,8 @@ static inline void print_vma_addr(char *prefix, unsigned long rip) void vmemmap_remap_free(unsigned long start, unsigned long end, unsigned long reuse); +int vmemmap_remap_alloc(unsigned long start, unsigned long end, + unsigned long reuse, gfp_t gfp_mask); void *sparse_buffer_alloc(unsigned long size); struct page * __populate_section_memmap(unsigned long pfn, -- cgit v1.2.3 From e9fdff87e893ec5b7c32836675db80cf691b2a8b Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Wed, 30 Jun 2021 18:47:25 -0700 Subject: mm: hugetlb: add a kernel parameter hugetlb_free_vmemmap Add a kernel parameter hugetlb_free_vmemmap to enable the feature of freeing unused vmemmap pages associated with each hugetlb page on boot. We disable PMD mapping of vmemmap pages for x86-64 arch when this feature is enabled. Because vmemmap_remap_free() depends on vmemmap being base page mapped. Link: https://lkml.kernel.org/r/20210510030027.56044-8-songmuchun@bytedance.com Signed-off-by: Muchun Song Reviewed-by: Oscar Salvador Reviewed-by: Barry Song Reviewed-by: Miaohe Lin Tested-by: Chen Huang Tested-by: Bodeddula Balasubramaniam Reviewed-by: Mike Kravetz Cc: Alexander Viro Cc: Andy Lutomirski Cc: Anshuman Khandual Cc: Balbir Singh Cc: Borislav Petkov Cc: Dave Hansen Cc: David Hildenbrand Cc: David Rientjes Cc: HORIGUCHI NAOYA Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Joao Martins Cc: Joerg Roedel Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Michal Hocko Cc: Mina Almasry Cc: Oliver Neukum Cc: Paul E. McKenney Cc: Pawan Gupta Cc: Peter Zijlstra Cc: Randy Dunlap Cc: Thomas Gleixner Cc: Xiongchun Duan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 3578d9d708fe..9ad99848f9f0 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -892,6 +892,20 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, } #endif +#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP +extern bool hugetlb_free_vmemmap_enabled; + +static inline bool is_hugetlb_free_vmemmap_enabled(void) +{ + return hugetlb_free_vmemmap_enabled; +} +#else +static inline bool is_hugetlb_free_vmemmap_enabled(void) +{ + return false; +} +#endif + #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; @@ -1046,6 +1060,11 @@ static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr pte_t *ptep, pte_t pte, unsigned long sz) { } + +static inline bool is_hugetlb_free_vmemmap_enabled(void) +{ + return false; +} #endif /* CONFIG_HUGETLB_PAGE */ static inline spinlock_t *huge_pte_lock(struct hstate *h, -- cgit v1.2.3 From 774905878fc9b0b9a5ee4a889b97f773a077aeee Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Wed, 30 Jun 2021 18:47:33 -0700 Subject: mm: hugetlb: introduce nr_free_vmemmap_pages in the struct hstate All the infrastructure is ready, so we introduce nr_free_vmemmap_pages field in the hstate to indicate how many vmemmap pages associated with a HugeTLB page that can be freed to buddy allocator. And initialize it in the hugetlb_vmemmap_init(). This patch is actual enablement of the feature. There are only (RESERVE_VMEMMAP_SIZE / sizeof(struct page)) struct page structs that can be used when CONFIG_HUGETLB_PAGE_FREE_VMEMMAP, so add a BUILD_BUG_ON to catch invalid usage of the tail struct page. Link: https://lkml.kernel.org/r/20210510030027.56044-10-songmuchun@bytedance.com Signed-off-by: Muchun Song Acked-by: Mike Kravetz Reviewed-by: Oscar Salvador Reviewed-by: Miaohe Lin Tested-by: Chen Huang Tested-by: Bodeddula Balasubramaniam Cc: Alexander Viro Cc: Andy Lutomirski Cc: Anshuman Khandual Cc: Balbir Singh Cc: Barry Song Cc: Borislav Petkov Cc: Dave Hansen Cc: David Hildenbrand Cc: David Rientjes Cc: HORIGUCHI NAOYA Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Joao Martins Cc: Joerg Roedel Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Michal Hocko Cc: Mina Almasry Cc: Oliver Neukum Cc: Paul E. McKenney Cc: Pawan Gupta Cc: Peter Zijlstra Cc: Randy Dunlap Cc: Thomas Gleixner Cc: Xiongchun Duan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 9ad99848f9f0..8c1920844236 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -608,6 +608,9 @@ struct hstate { unsigned int nr_huge_pages_node[MAX_NUMNODES]; unsigned int free_huge_pages_node[MAX_NUMNODES]; unsigned int surplus_huge_pages_node[MAX_NUMNODES]; +#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP + unsigned int nr_free_vmemmap_pages; +#endif #ifdef CONFIG_CGROUP_HUGETLB /* cgroup control files */ struct cftype cgroup_files_dfl[7]; -- cgit v1.2.3 From b2bd53f18bb7f7cfc91b3bb527d7809376700a8e Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Wed, 30 Jun 2021 18:47:43 -0700 Subject: mm/huge_memory.c: remove dedicated macro HPAGE_CACHE_INDEX_MASK Patch series "Cleanup and fixup for huge_memory:, v3. This series contains cleanups to remove dedicated macro and remove unnecessary tlb_remove_page_size() for huge zero pmd. Also this adds missing read-only THP checking for transparent_hugepage_enabled() and avoids discarding hugepage if other processes are mapping it. More details can be found in the respective changelogs. Thi patch (of 5): Rewrite the pgoff checking logic to remove macro HPAGE_CACHE_INDEX_MASK which is only used here to simplify the code. Link: https://lkml.kernel.org/r/20210511134857.1581273-1-linmiaohe@huawei.com Link: https://lkml.kernel.org/r/20210511134857.1581273-2-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Reviewed-by: Yang Shi Reviewed-by: Anshuman Khandual Reviewed-by: David Hildenbrand Cc: Zi Yan Cc: William Kucharski Cc: Matthew Wilcox Cc: "Aneesh Kumar K . V" Cc: Ralph Campbell Cc: Song Liu Cc: Kirill A. Shutemov Cc: Rik van Riel Cc: Johannes Weiner Cc: Minchan Kim Cc: Hugh Dickins Cc: Alexey Dobriyan Cc: Mike Kravetz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 2a8ebe6c222e..8a5f49abcfa2 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -152,15 +152,13 @@ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) bool transparent_hugepage_enabled(struct vm_area_struct *vma); -#define HPAGE_CACHE_INDEX_MASK (HPAGE_PMD_NR - 1) - static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, unsigned long haddr) { /* Don't have to check pgoff for anonymous vma */ if (!vma_is_anonymous(vma)) { - if (((vma->vm_start >> PAGE_SHIFT) & HPAGE_CACHE_INDEX_MASK) != - (vma->vm_pgoff & HPAGE_CACHE_INDEX_MASK)) + if (!IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff, + HPAGE_PMD_NR)) return false; } -- cgit v1.2.3 From e6be37b2e7bddfe0c76585ee7c7eee5acc8efeab Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Wed, 30 Jun 2021 18:47:50 -0700 Subject: mm/huge_memory.c: add missing read-only THP checking in transparent_hugepage_enabled() Since commit 99cb0dbd47a1 ("mm,thp: add read-only THP support for (non-shmem) FS"), read-only THP file mapping is supported. But it forgot to add checking for it in transparent_hugepage_enabled(). To fix it, we add checking for read-only THP file mapping and also introduce helper transhuge_vma_enabled() to check whether thp is enabled for specified vma to reduce duplicated code. We rename transparent_hugepage_enabled to transparent_hugepage_active to make the code easier to follow as suggested by David Hildenbrand. [linmiaohe@huawei.com: define transhuge_vma_enabled next to transhuge_vma_suitable] Link: https://lkml.kernel.org/r/20210514093007.4117906-1-linmiaohe@huawei.com Link: https://lkml.kernel.org/r/20210511134857.1581273-4-linmiaohe@huawei.com Fixes: 99cb0dbd47a1 ("mm,thp: add read-only THP support for (non-shmem) FS") Signed-off-by: Miaohe Lin Reviewed-by: Yang Shi Cc: Alexey Dobriyan Cc: "Aneesh Kumar K . V" Cc: Anshuman Khandual Cc: David Hildenbrand Cc: Hugh Dickins Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Matthew Wilcox Cc: Minchan Kim Cc: Ralph Campbell Cc: Rik van Riel Cc: Song Liu Cc: William Kucharski Cc: Zi Yan Cc: Mike Kravetz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 57 ++++++++++++++++++++++++++++++------------------- 1 file changed, 35 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 8a5f49abcfa2..b4e1ebaae825 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -115,9 +115,34 @@ extern struct kobj_attribute shmem_enabled_attr; extern unsigned long transparent_hugepage_flags; +static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, + unsigned long haddr) +{ + /* Don't have to check pgoff for anonymous vma */ + if (!vma_is_anonymous(vma)) { + if (!IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff, + HPAGE_PMD_NR)) + return false; + } + + if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end) + return false; + return true; +} + +static inline bool transhuge_vma_enabled(struct vm_area_struct *vma, + unsigned long vm_flags) +{ + /* Explicitly disabled through madvise. */ + if ((vm_flags & VM_NOHUGEPAGE) || + test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) + return false; + return true; +} + /* * to be used on vmas which are known to support THP. - * Use transparent_hugepage_enabled otherwise + * Use transparent_hugepage_active otherwise */ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) { @@ -128,15 +153,12 @@ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_NEVER_DAX)) return false; - if (vma->vm_flags & VM_NOHUGEPAGE) + if (!transhuge_vma_enabled(vma, vma->vm_flags)) return false; if (vma_is_temporary_stack(vma)) return false; - if (test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) - return false; - if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_FLAG)) return true; @@ -150,22 +172,7 @@ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) return false; } -bool transparent_hugepage_enabled(struct vm_area_struct *vma); - -static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, - unsigned long haddr) -{ - /* Don't have to check pgoff for anonymous vma */ - if (!vma_is_anonymous(vma)) { - if (!IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff, - HPAGE_PMD_NR)) - return false; - } - - if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end) - return false; - return true; -} +bool transparent_hugepage_active(struct vm_area_struct *vma); #define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ @@ -352,7 +359,7 @@ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) return false; } -static inline bool transparent_hugepage_enabled(struct vm_area_struct *vma) +static inline bool transparent_hugepage_active(struct vm_area_struct *vma) { return false; } @@ -363,6 +370,12 @@ static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, return false; } +static inline bool transhuge_vma_enabled(struct vm_area_struct *vma, + unsigned long vm_flags) +{ + return false; +} + static inline void prep_transhuge_page(struct page *page) {} static inline bool is_transparent_hugepage(struct page *page) -- cgit v1.2.3 From 79c1c594f49a88fba9744cb5c85978c6b1b365ec Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Wed, 30 Jun 2021 18:48:00 -0700 Subject: mm/hugetlb: change parameters of arch_make_huge_pte() Patch series "Subject: [PATCH v2 0/5] Implement huge VMAP and VMALLOC on powerpc 8xx", v2. This series implements huge VMAP and VMALLOC on powerpc 8xx. Powerpc 8xx has 4 page sizes: - 4k - 16k - 512k - 8M At the time being, vmalloc and vmap only support huge pages which are leaf at PMD level. Here the PMD level is 4M, it doesn't correspond to any supported page size. For now, implement use of 16k and 512k pages which is done at PTE level. Support of 8M pages will be implemented later, it requires use of hugepd tables. To allow this, the architecture provides two functions: - arch_vmap_pte_range_map_size() which tells vmap_pte_range() what page size to use. A stub returning PAGE_SIZE is provided when the architecture doesn't provide this function. - arch_vmap_pte_supported_shift() which tells __vmalloc_node_range() what page shift to use for a given area size. A stub returning PAGE_SHIFT is provided when the architecture doesn't provide this function. This patch (of 5): At the time being, arch_make_huge_pte() has the following prototype: pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, struct page *page, int writable); vma is used to get the pages shift or size. vma is also used on Sparc to get vm_flags. page is not used. writable is not used. In order to use this function without a vma, replace vma by shift and flags. Also remove the used parameters. Link: https://lkml.kernel.org/r/cover.1620795204.git.christophe.leroy@csgroup.eu Link: https://lkml.kernel.org/r/f4633ac6a7da2f22f31a04a89e0a7026bb78b15b.1620795204.git.christophe.leroy@csgroup.eu Signed-off-by: Christophe Leroy Acked-by: Mike Kravetz Cc: Nicholas Piggin Cc: Mike Kravetz Cc: Mike Rapoport Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Uladzislau Rezki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 8c1920844236..cfde3bec2261 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -741,8 +741,8 @@ static inline void arch_clear_hugepage_flags(struct page *page) { } #endif #ifndef arch_make_huge_pte -static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, - struct page *page, int writable) +static inline pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, + vm_flags_t flags) { return entry; } -- cgit v1.2.3 From c742199a014de23ee92055c2473d91fe5561ffdf Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Wed, 30 Jun 2021 18:48:03 -0700 Subject: mm/pgtable: add stubs for {pmd/pub}_{set/clear}_huge For architectures with no PMD and/or no PUD, add stubs similar to what we have for architectures without P4D. [christophe.leroy@csgroup.eu: arm64: define only {pud/pmd}_{set/clear}_huge when useful] Link: https://lkml.kernel.org/r/73ec95f40cafbbb69bdfb43a7f53876fd845b0ce.1620990479.git.christophe.leroy@csgroup.eu [christophe.leroy@csgroup.eu: x86: define only {pud/pmd}_{set/clear}_huge when useful] Link: https://lkml.kernel.org/r/7fbf1b6bc3e15c07c24fa45278d57064f14c896b.1620930415.git.christophe.leroy@csgroup.eu Link: https://lkml.kernel.org/r/5ac5976419350e8e048d463a64cae449eb3ba4b0.1620795204.git.christophe.leroy@csgroup.eu Signed-off-by: Christophe Leroy Cc: Benjamin Herrenschmidt Cc: Michael Ellerman Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nicholas Piggin Cc: Paul Mackerras Cc: Uladzislau Rezki Cc: Naresh Kamboju Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pgtable.h | 26 +++++++++++++++++++++++++- 1 file changed, 25 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index c32600c9e1ad..2b0d02291178 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1379,10 +1379,34 @@ static inline int p4d_clear_huge(p4d_t *p4d) } #endif /* !__PAGETABLE_P4D_FOLDED */ +#ifndef __PAGETABLE_PUD_FOLDED int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot); -int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot); int pud_clear_huge(pud_t *pud); +#else +static inline int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) +{ + return 0; +} +static inline int pud_clear_huge(pud_t *pud) +{ + return 0; +} +#endif /* !__PAGETABLE_PUD_FOLDED */ + +#ifndef __PAGETABLE_PMD_FOLDED +int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot); int pmd_clear_huge(pmd_t *pmd); +#else +static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) +{ + return 0; +} +static inline int pmd_clear_huge(pmd_t *pmd) +{ + return 0; +} +#endif /* !__PAGETABLE_PMD_FOLDED */ + int p4d_free_pud_page(p4d_t *p4d, unsigned long addr); int pud_free_pmd_page(pud_t *pud, unsigned long addr); int pmd_free_pte_page(pmd_t *pmd, unsigned long addr); -- cgit v1.2.3 From f7ee1f13d606c1b1be3bdaf1609f3991bc06da87 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Wed, 30 Jun 2021 18:48:06 -0700 Subject: mm/vmalloc: enable mapping of huge pages at pte level in vmap On some architectures like powerpc, there are huge pages that are mapped at pte level. Enable it in vmap. For that, architectures can provide arch_vmap_pte_range_map_size() that returns the size of pages to map at pte level. Link: https://lkml.kernel.org/r/fb3ccc73377832ac6708181ec419128a2f98ce36.1620795204.git.christophe.leroy@csgroup.eu Signed-off-by: Christophe Leroy Cc: Benjamin Herrenschmidt Cc: Michael Ellerman Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nicholas Piggin Cc: Paul Mackerras Cc: Uladzislau Rezki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index bfaaf0b6fa76..54ec0736a656 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -104,6 +104,14 @@ static inline bool arch_vmap_pmd_supported(pgprot_t prot) } #endif +#ifndef arch_vmap_pte_range_map_size +static inline unsigned long arch_vmap_pte_range_map_size(unsigned long addr, unsigned long end, + u64 pfn, unsigned int max_page_shift) +{ + return PAGE_SIZE; +} +#endif + /* * Highlevel APIs for driver use */ -- cgit v1.2.3 From 3382bbee0464bf31e63853c6ec2a83ead77a01cc Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Wed, 30 Jun 2021 18:48:09 -0700 Subject: mm/vmalloc: enable mapping of huge pages at pte level in vmalloc On some architectures like powerpc, there are huge pages that are mapped at pte level. Enable it in vmalloc. For that, architectures can provide arch_vmap_pte_supported_shift() that returns the shift for pages to map at pte level. Link: https://lkml.kernel.org/r/2c717e3b1fba1894d890feb7669f83025bfa314d.1620795204.git.christophe.leroy@csgroup.eu Signed-off-by: Christophe Leroy Cc: Benjamin Herrenschmidt Cc: Michael Ellerman Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nicholas Piggin Cc: Paul Mackerras Cc: Uladzislau Rezki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 54ec0736a656..1dabd6f22486 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -112,6 +112,13 @@ static inline unsigned long arch_vmap_pte_range_map_size(unsigned long addr, uns } #endif +#ifndef arch_vmap_pte_supported_shift +static inline int arch_vmap_pte_supported_shift(unsigned long size) +{ + return PAGE_SHIFT; +} +#endif + /* * Highlevel APIs for driver use */ -- cgit v1.2.3 From 8cc5fcbb5be814c115085549b700e473685b11e9 Mon Sep 17 00:00:00 2001 From: Mina Almasry Date: Wed, 30 Jun 2021 18:48:19 -0700 Subject: mm, hugetlb: fix racy resv_huge_pages underflow on UFFDIO_COPY On UFFDIO_COPY, if we fail to copy the page contents while holding the hugetlb_fault_mutex, we will drop the mutex and return to the caller after allocating a page that consumed a reservation. In this case there may be a fault that double consumes the reservation. To handle this, we free the allocated page, fix the reservations, and allocate a temporary hugetlb page and return that to the caller. When the caller does the copy outside of the lock, we again check the cache, and allocate a page consuming the reservation, and copy over the contents. Test: Hacked the code locally such that resv_huge_pages underflows produce a warning and the copy_huge_page_from_user() always fails, then: ./tools/testing/selftests/vm/userfaultfd hugetlb_shared 10 2 /tmp/kokonut_test/huge/userfaultfd_test && echo test success ./tools/testing/selftests/vm/userfaultfd hugetlb 10 2 /tmp/kokonut_test/huge/userfaultfd_test && echo test success Both tests succeed and produce no warnings. After the test runs number of free/resv hugepages is correct. [yuehaibing@huawei.com: remove set but not used variable 'vm_alloc_shared'] Link: https://lkml.kernel.org/r/20210601141610.28332-1-yuehaibing@huawei.com [almasrymina@google.com: fix allocation error check and copy func name] Link: https://lkml.kernel.org/r/20210605010626.1459873-1-almasrymina@google.com Link: https://lkml.kernel.org/r/20210528005029.88088-1-almasrymina@google.com Signed-off-by: Mina Almasry Signed-off-by: YueHaibing Cc: Axel Rasmussen Cc: Peter Xu Cc: Mike Kravetz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 4bb4e519e3f5..7b7b73977278 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -51,6 +51,7 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page); extern int migrate_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page, int extra_count); +extern void copy_huge_page(struct page *dst, struct page *src); #else static inline void putback_movable_pages(struct list_head *l) {} @@ -77,6 +78,9 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping, return -ENOSYS; } +static inline void copy_huge_page(struct page *dst, struct page *src) +{ +} #endif /* CONFIG_MIGRATION */ #ifdef CONFIG_COMPACTION -- cgit v1.2.3 From 3bc2b6a725963bb1b441356873da890e397c1a3f Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Wed, 30 Jun 2021 18:48:22 -0700 Subject: mm: sparsemem: split the huge PMD mapping of vmemmap pages Patch series "Split huge PMD mapping of vmemmap pages", v4. In order to reduce the difficulty of code review in series[1]. We disable huge PMD mapping of vmemmap pages when that feature is enabled. In this series, we do not disable huge PMD mapping of vmemmap pages anymore. We will split huge PMD mapping when needed. When HugeTLB pages are freed from the pool we do not attempt coalasce and move back to a PMD mapping because it is much more complex. [1] https://lore.kernel.org/linux-doc/20210510030027.56044-1-songmuchun@bytedance.com/ This patch (of 3): In [1], PMD mappings of vmemmap pages were disabled if the the feature hugetlb_free_vmemmap was enabled. This was done to simplify the initial implementation of vmmemap freeing for hugetlb pages. Now, remove this simplification by allowing PMD mapping and switching to PTE mappings as needed for allocated hugetlb pages. When a hugetlb page is allocated, the vmemmap page tables are walked to free vmemmap pages. During this walk, split huge PMD mappings to PTE mappings as required. In the unlikely case PTE pages can not be allocated, return error(ENOMEM) and do not optimize vmemmap of the hugetlb page. When HugeTLB pages are freed from the pool, we do not attempt to coalesce and move back to a PMD mapping because it is much more complex. [1] https://lkml.kernel.org/r/20210510030027.56044-8-songmuchun@bytedance.com Link: https://lkml.kernel.org/r/20210616094915.34432-1-songmuchun@bytedance.com Link: https://lkml.kernel.org/r/20210616094915.34432-2-songmuchun@bytedance.com Signed-off-by: Muchun Song Reviewed-by: Mike Kravetz Cc: Oscar Salvador Cc: Michal Hocko Cc: David Hildenbrand Cc: Chen Huang Cc: Jonathan Corbet Cc: Xiongchun Duan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 706bee98d965..aa875dacd9c3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3076,8 +3076,8 @@ static inline void print_vma_addr(char *prefix, unsigned long rip) } #endif -void vmemmap_remap_free(unsigned long start, unsigned long end, - unsigned long reuse); +int vmemmap_remap_free(unsigned long start, unsigned long end, + unsigned long reuse); int vmemmap_remap_alloc(unsigned long start, unsigned long end, unsigned long reuse, gfp_t gfp_mask); -- cgit v1.2.3 From 2d7a21715f25122779e2bed17db8c57aa01e922f Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Wed, 30 Jun 2021 18:48:25 -0700 Subject: mm: sparsemem: use huge PMD mapping for vmemmap pages The preparation of splitting huge PMD mapping of vmemmap pages is ready, so switch the mapping from PTE to PMD. Link: https://lkml.kernel.org/r/20210616094915.34432-3-songmuchun@bytedance.com Signed-off-by: Muchun Song Reviewed-by: Mike Kravetz Cc: Chen Huang Cc: David Hildenbrand Cc: Jonathan Corbet Cc: Michal Hocko Cc: Oscar Salvador Cc: Xiongchun Duan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 25 ++++++------------------- 1 file changed, 6 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index cfde3bec2261..f11ba701e199 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -895,20 +895,6 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, } #endif -#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP -extern bool hugetlb_free_vmemmap_enabled; - -static inline bool is_hugetlb_free_vmemmap_enabled(void) -{ - return hugetlb_free_vmemmap_enabled; -} -#else -static inline bool is_hugetlb_free_vmemmap_enabled(void) -{ - return false; -} -#endif - #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; @@ -1063,13 +1049,14 @@ static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr pte_t *ptep, pte_t pte, unsigned long sz) { } - -static inline bool is_hugetlb_free_vmemmap_enabled(void) -{ - return false; -} #endif /* CONFIG_HUGETLB_PAGE */ +#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP +extern bool hugetlb_free_vmemmap_enabled; +#else +#define hugetlb_free_vmemmap_enabled false +#endif + static inline spinlock_t *huge_pte_lock(struct hstate *h, struct mm_struct *mm, pte_t *pte) { -- cgit v1.2.3 From 8f34f1eac3820fc2722e5159acceb22545b30b0d Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 30 Jun 2021 18:49:02 -0700 Subject: mm/userfaultfd: fix uffd-wp special cases for fork() We tried to do something similar in b569a1760782 ("userfaultfd: wp: drop _PAGE_UFFD_WP properly when fork") previously, but it's not doing it all right.. A few fixes around the code path: 1. We were referencing VM_UFFD_WP vm_flags on the _old_ vma rather than the new vma. That's overlooked in b569a1760782, so it won't work as expected. Thanks to the recent rework on fork code (7a4830c380f3a8b3), we can easily get the new vma now, so switch the checks to that. 2. Dropping the uffd-wp bit in copy_huge_pmd() could be wrong if the huge pmd is a migration huge pmd. When it happens, instead of using pmd_uffd_wp(), we should use pmd_swp_uffd_wp(). The fix is simply to handle them separately. 3. Forget to carry over uffd-wp bit for a write migration huge pmd entry. This also happens in copy_huge_pmd(), where we converted a write huge migration entry into a read one. 4. In copy_nonpresent_pte(), drop uffd-wp if necessary for swap ptes. 5. In copy_present_page() when COW is enforced when fork(), we also need to pass over the uffd-wp bit if VM_UFFD_WP is armed on the new vma, and when the pte to be copied has uffd-wp bit set. Remove the comment in copy_present_pte() about this. It won't help a huge lot to only comment there, but comment everywhere would be an overkill. Let's assume the commit messages would help. [peterx@redhat.com: fix a few thp pmd missing uffd-wp bit] Link: https://lkml.kernel.org/r/20210428225030.9708-4-peterx@redhat.com Link: https://lkml.kernel.org/r/20210428225030.9708-3-peterx@redhat.com Fixes: b569a1760782f ("userfaultfd: wp: drop _PAGE_UFFD_WP properly when fork") Signed-off-by: Peter Xu Cc: Jerome Glisse Cc: Mike Rapoport Cc: Alexander Viro Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: Brian Geffon Cc: "Dr . David Alan Gilbert" Cc: Hugh Dickins Cc: Joe Perches Cc: Kirill A. Shutemov Cc: Lokesh Gidra Cc: Mike Kravetz Cc: Mina Almasry Cc: Oliver Upton Cc: Shaohua Li Cc: Shuah Khan Cc: Stephen Rothwell Cc: Wang Qing Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 2 +- include/linux/swapops.h | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index b4e1ebaae825..939f21b69ead 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -10,7 +10,7 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf); int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, - struct vm_area_struct *vma); + struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma); void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd); int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, pud_t *dst_pud, pud_t *src_pud, unsigned long addr, diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 5907205c712c..708fbeb21dd3 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -265,6 +265,8 @@ static inline swp_entry_t pmd_to_swp_entry(pmd_t pmd) if (pmd_swp_soft_dirty(pmd)) pmd = pmd_swp_clear_soft_dirty(pmd); + if (pmd_swp_uffd_wp(pmd)) + pmd = pmd_swp_clear_uffd_wp(pmd); arch_entry = __pmd_to_swp_entry(pmd); return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry)); } -- cgit v1.2.3 From 3460f6e5c1ed94c2ab7c1ccc032a5bebd88deaa7 Mon Sep 17 00:00:00 2001 From: Axel Rasmussen Date: Wed, 30 Jun 2021 18:49:17 -0700 Subject: userfaultfd/shmem: combine shmem_{mcopy_atomic,mfill_zeropage}_pte Patch series "userfaultfd: add minor fault handling for shmem", v6. Overview ======== See the series which added minor faults for hugetlbfs [3] for a detailed overview of minor fault handling in general. This series adds the same support for shmem-backed areas. This series is structured as follows: - Commits 1 and 2 are cleanups. - Commits 3 and 4 implement the new feature (minor fault handling for shmem). - Commit 5 advertises that the feature is now available since at this point it's fully implemented. - Commit 6 is a final cleanup, modifying an existing code path to re-use a new helper we've introduced. - Commits 7, 8, 9, 10 update the userfaultfd selftest to exercise the feature. Use Case ======== In some cases it is useful to have VM memory backed by tmpfs instead of hugetlbfs. So, this feature will be used to support the same VM live migration use case described in my original series. Additionally, Android folks (Lokesh Gidra ) hope to optimize the Android Runtime garbage collector using this feature: "The plan is to use userfaultfd for concurrently compacting the heap. With this feature, the heap can be shared-mapped at another location where the GC-thread(s) could continue the compaction operation without the need to invoke userfault ioctl(UFFDIO_COPY) each time. OTOH, if and when Java threads get faults on the heap, UFFDIO_CONTINUE can be used to resume execution. Furthermore, this feature enables updating references in the 'non-moving' portion of the heap efficiently. Without this feature, uneccessary page copying (ioctl(UFFDIO_COPY)) would be required." [1] https://lore.kernel.org/patchwork/cover/1388144/ [2] https://lore.kernel.org/patchwork/patch/1408161/ [3] https://lore.kernel.org/linux-fsdevel/20210301222728.176417-1-axelrasmussen@google.com/T/#t This patch (of 9): Previously, we did a dance where we had one calling path in userfaultfd.c (mfill_atomic_pte), but then we split it into two in shmem_fs.h (shmem_{mcopy_atomic,mfill_zeropage}_pte), and then rejoined into a single shared function in shmem.c (shmem_mfill_atomic_pte). This is all a bit overly complex. Just call the single combined shmem function directly, allowing us to clean up various branches, boilerplate, etc. While we're touching this function, two other small cleanup changes: - offset is equivalent to pgoff, so we can get rid of offset entirely. - Split two VM_BUG_ON cases into two statements. This means the line number reported when the BUG is hit specifies exactly which condition was true. Link: https://lkml.kernel.org/r/20210503180737.2487560-1-axelrasmussen@google.com Link: https://lkml.kernel.org/r/20210503180737.2487560-3-axelrasmussen@google.com Signed-off-by: Axel Rasmussen Reviewed-by: Peter Xu Acked-by: Hugh Dickins Cc: Alexander Viro Cc: Andrea Arcangeli Cc: Brian Geffon Cc: "Dr . David Alan Gilbert" Cc: Jerome Glisse Cc: Joe Perches Cc: Kirill A. Shutemov Cc: Lokesh Gidra Cc: Mike Kravetz Cc: Mike Rapoport Cc: Mina Almasry Cc: Oliver Upton Cc: Shaohua Li Cc: Shuah Khan Cc: Stephen Rothwell Cc: Wang Qing Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shmem_fs.h | 19 ++++++++----------- 1 file changed, 8 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index d82b6f396588..a69ea4d97fdd 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -122,21 +122,18 @@ static inline bool shmem_file(struct file *file) extern bool shmem_charge(struct inode *inode, long pages); extern void shmem_uncharge(struct inode *inode, long pages); +#ifdef CONFIG_USERFAULTFD #ifdef CONFIG_SHMEM -extern int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, +extern int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, + bool zeropage, struct page **pagep); -extern int shmem_mfill_zeropage_pte(struct mm_struct *dst_mm, - pmd_t *dst_pmd, - struct vm_area_struct *dst_vma, - unsigned long dst_addr); -#else -#define shmem_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, dst_addr, \ - src_addr, pagep) ({ BUG(); 0; }) -#define shmem_mfill_zeropage_pte(dst_mm, dst_pmd, dst_vma, \ - dst_addr) ({ BUG(); 0; }) -#endif +#else /* !CONFIG_SHMEM */ +#define shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, \ + src_addr, zeropage, pagep) ({ BUG(); 0; }) +#endif /* CONFIG_SHMEM */ +#endif /* CONFIG_USERFAULTFD */ #endif -- cgit v1.2.3 From 7d64ae3ab648a967b7ba5cc3e89281d76742c34e Mon Sep 17 00:00:00 2001 From: Axel Rasmussen Date: Wed, 30 Jun 2021 18:49:31 -0700 Subject: userfaultfd/shmem: modify shmem_mfill_atomic_pte to use install_pte() In a previous commit, we added the mfill_atomic_install_pte() helper. This helper does the job of setting up PTEs for an existing page, to map it into a given VMA. It deals with both the anon and shmem cases, as well as the shared and private cases. In other words, shmem_mfill_atomic_pte() duplicates a case it already handles. So, expose it, and let shmem_mfill_atomic_pte() use it directly, to reduce code duplication. This requires that we refactor shmem_mfill_atomic_pte() a bit: Instead of doing accounting (shmem_recalc_inode() et al) part-way through the PTE setup, do it afterward. This frees up mfill_atomic_install_pte() from having to care about this accounting, and means we don't need to e.g. shmem_uncharge() in the error path. A side effect is this switches shmem_mfill_atomic_pte() to use lru_cache_add_inactive_or_unevictable() instead of just lru_cache_add(). This wrapper does some extra accounting in an exceptional case, if appropriate, so it's actually the more correct thing to use. Link: https://lkml.kernel.org/r/20210503180737.2487560-7-axelrasmussen@google.com Signed-off-by: Axel Rasmussen Reviewed-by: Peter Xu Acked-by: Hugh Dickins Cc: Alexander Viro Cc: Andrea Arcangeli Cc: Brian Geffon Cc: "Dr . David Alan Gilbert" Cc: Jerome Glisse Cc: Joe Perches Cc: Kirill A. Shutemov Cc: Lokesh Gidra Cc: Mike Kravetz Cc: Mike Rapoport Cc: Mina Almasry Cc: Oliver Upton Cc: Shaohua Li Cc: Shuah Khan Cc: Stephen Rothwell Cc: Wang Qing Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/userfaultfd_k.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 794d1538b8ba..331d2ccf0bcc 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -53,6 +53,11 @@ enum mcopy_atomic_mode { MCOPY_ATOMIC_CONTINUE, }; +extern int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, struct page *page, + bool newly_allocated, bool wp_copy); + extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long src_start, unsigned long len, bool *mmap_changing, __u64 mode); -- cgit v1.2.3 From 3c36b419b111e28a657e6534aae07964a98a5ca9 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Wed, 30 Jun 2021 18:50:03 -0700 Subject: fs/proc/kcore: drop KCORE_REMAP and KCORE_OTHER Patch series "fs/proc/kcore: don't read offline sections, logically offline pages and hwpoisoned pages", v3. Looking for places where the kernel might unconditionally read PageOffline() pages, I stumbled over /proc/kcore; turns out /proc/kcore needs some more love to not touch some other pages we really don't want to read -- i.e., hwpoisoned ones. Examples for PageOffline() pages are pages inflated in a balloon, memory unplugged via virtio-mem, and partially-present sections in memory added by the Hyper-V balloon. When reading pages inflated in a balloon, we essentially produce unnecessary load in the hypervisor; holes in partially present sections in case of Hyper-V are not accessible and already were a problem for /proc/vmcore, fixed in makedumpfile by detecting PageOffline() pages. In the future, virtio-mem might disallow reading unplugged memory -- marked as PageOffline() -- in some environments, resulting in undefined behavior when accessed; therefore, I'm trying to identify and rework all these (corner) cases. With this series, there is really only access via /dev/mem, /proc/vmcore and kdb left after I ripped out /dev/kmem. kdb is an advanced corner-case use case -- we won't care for now if someone explicitly tries to do nasty things by reading from/writing to physical addresses we better not touch. /dev/mem is a use case we won't support for virtio-mem, at least for now, so we'll simply disallow mapping any virtio-mem memory via /dev/mem next. /proc/vmcore is really only a problem when dumping the old kernel via something that's not makedumpfile (read: basically never), however, we'll try sanitizing that as well in the second kernel in the future. Tested via kcore_dump: https://github.com/schlafwandler/kcore_dump This patch (of 6): Commit db779ef67ffe ("proc/kcore: Remove unused kclist_add_remap()") removed the last user of KCORE_REMAP. Commit 595dd46ebfc1 ("vfs/proc/kcore, x86/mm/kcore: Fix SMAP fault when dumping vsyscall user page") removed the last user of KCORE_OTHER. Let's drop both types. While at it, also drop vaddr in "struct kcore_list", used by KCORE_REMAP only. Link: https://lkml.kernel.org/r/20210526093041.8800-1-david@redhat.com Link: https://lkml.kernel.org/r/20210526093041.8800-2-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Mike Rapoport Cc: "Michael S. Tsirkin" Cc: Jason Wang Cc: Alexey Dobriyan Cc: "Matthew Wilcox (Oracle)" Cc: Oscar Salvador Cc: Michal Hocko Cc: Roman Gushchin Cc: Alex Shi Cc: Steven Price Cc: Mike Kravetz Cc: Aili Yao Cc: Jiri Bohac Cc: "K. Y. Srinivasan" Cc: Haiyang Zhang Cc: Stephen Hemminger Cc: Wei Liu Cc: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kcore.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kcore.h b/include/linux/kcore.h index da676cdbd727..86c0f1d18998 100644 --- a/include/linux/kcore.h +++ b/include/linux/kcore.h @@ -11,14 +11,11 @@ enum kcore_type { KCORE_RAM, KCORE_VMEMMAP, KCORE_USER, - KCORE_OTHER, - KCORE_REMAP, }; struct kcore_list { struct list_head list; unsigned long addr; - unsigned long vaddr; size_t size; int type; }; -- cgit v1.2.3 From 0daa322b8ff94d8ee4081c2c6868a1aaf1309642 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Wed, 30 Jun 2021 18:50:10 -0700 Subject: fs/proc/kcore: don't read offline sections, logically offline pages and hwpoisoned pages Let's avoid reading: 1) Offline memory sections: the content of offline memory sections is stale as the memory is effectively unused by the kernel. On s390x with standby memory, offline memory sections (belonging to offline storage increments) are not accessible. With virtio-mem and the hyper-v balloon, we can have unavailable memory chunks that should not be accessed inside offline memory sections. Last but not least, offline memory sections might contain hwpoisoned pages which we can no longer identify because the memmap is stale. 2) PG_offline pages: logically offline pages that are documented as "The content of these pages is effectively stale. Such pages should not be touched (read/write/dump/save) except by their owner.". Examples include pages inflated in a balloon or unavailble memory ranges inside hotplugged memory sections with virtio-mem or the hyper-v balloon. 3) PG_hwpoison pages: Reading pages marked as hwpoisoned can be fatal. As documented: "Accessing is not safe since it may cause another machine check. Don't touch!" Introduce is_page_hwpoison(), adding a comment that it is inherently racy but best we can really do. Reading /proc/kcore now performs similar checks as when reading /proc/vmcore for kdump via makedumpfile: problematic pages are exclude. It's also similar to hibernation code, however, we don't skip hwpoisoned pages when processing pages in kernel/power/snapshot.c:saveable_page() yet. Note 1: we can race against memory offlining code, especially memory going offline and getting unplugged: however, we will properly tear down the identity mapping and handle faults gracefully when accessing this memory from kcore code. Note 2: we can race against drivers setting PageOffline() and turning memory inaccessible in the hypervisor. We'll handle this in a follow-up patch. Link: https://lkml.kernel.org/r/20210526093041.8800-4-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Mike Rapoport Reviewed-by: Oscar Salvador Cc: Aili Yao Cc: Alexey Dobriyan Cc: Alex Shi Cc: Haiyang Zhang Cc: Jason Wang Cc: Jiri Bohac Cc: "K. Y. Srinivasan" Cc: "Matthew Wilcox (Oracle)" Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Mike Kravetz Cc: Naoya Horiguchi Cc: Roman Gushchin Cc: Stephen Hemminger Cc: Steven Price Cc: Wei Liu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index d8e26243db25..613295588848 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -694,6 +694,18 @@ PAGEFLAG_FALSE(DoubleMap) TESTSCFLAG_FALSE(DoubleMap) #endif +/* + * Check if a page is currently marked HWPoisoned. Note that this check is + * best effort only and inherently racy: there is no way to synchronize with + * failing hardware. + */ +static inline bool is_page_hwpoison(struct page *page) +{ + if (PageHWPoison(page)) + return true; + return PageHuge(page) && PageHWPoison(compound_head(page)); +} + /* * For pages that are never mapped to userspace (and aren't PageSlab), * page_type may be used. Because it is initialised to -1, we invert the -- cgit v1.2.3 From 82840451936f0301781ece80322230fd8edfc648 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Wed, 30 Jun 2021 18:50:14 -0700 Subject: mm: introduce page_offline_(begin|end|freeze|thaw) to synchronize setting PageOffline() A driver might set a page logically offline -- PageOffline() -- and turn the page inaccessible in the hypervisor; after that, access to page content can be fatal. One example is virtio-mem; while unplugged memory -- marked as PageOffline() can currently be read in the hypervisor, this will no longer be the case in the future; for example, when having a virtio-mem device backed by huge pages in the hypervisor. Some special PFN walkers -- i.e., /proc/kcore -- read content of random pages after checking PageOffline(); however, these PFN walkers can race with drivers that set PageOffline(). Let's introduce page_offline_(begin|end|freeze|thaw) for synchronizing. page_offline_freeze()/page_offline_thaw() allows for a subsystem to synchronize with such drivers, achieving that a page cannot be set PageOffline() while frozen. page_offline_begin()/page_offline_end() is used by drivers that care about such races when setting a page PageOffline(). For simplicity, use a rwsem for now; neither drivers nor users are performance sensitive. Link: https://lkml.kernel.org/r/20210526093041.8800-5-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Michal Hocko Reviewed-by: Mike Rapoport Reviewed-by: Oscar Salvador Cc: Aili Yao Cc: Alexey Dobriyan Cc: Alex Shi Cc: Haiyang Zhang Cc: Jason Wang Cc: Jiri Bohac Cc: "K. Y. Srinivasan" Cc: "Matthew Wilcox (Oracle)" Cc: "Michael S. Tsirkin" Cc: Mike Kravetz Cc: Naoya Horiguchi Cc: Roman Gushchin Cc: Stephen Hemminger Cc: Steven Price Cc: Wei Liu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 613295588848..3e7e616067fc 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -769,9 +769,19 @@ PAGE_TYPE_OPS(Buddy, buddy) * relies on this feature is aware that re-onlining the memory block will * require to re-set the pages PageOffline() and not giving them to the * buddy via online_page_callback_t. + * + * There are drivers that mark a page PageOffline() and expect there won't be + * any further access to page content. PFN walkers that read content of random + * pages should check PageOffline() and synchronize with such drivers using + * page_offline_freeze()/page_offline_thaw(). */ PAGE_TYPE_OPS(Offline, offline) +extern void page_offline_freeze(void); +extern void page_offline_thaw(void); +extern void page_offline_begin(void); +extern void page_offline_end(void); + /* * Marks pages in use as page tables. */ -- cgit v1.2.3 From 2a03085ce88792bac2e25319fc2874a885e7e102 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Wed, 30 Jun 2021 18:50:45 -0700 Subject: mm/zbud: don't export any zbud API The zbud doesn't need to export any API and it is meant to be used via zpool API since the commit 12d79d64bfd3 ("mm/zpool: update zswap to use zpool"). So we can remove the unneeded zbud.h and move down zpool API to avoid any forward declaration. [linmiaohe@huawei.com: fix unused function warnings when CONFIG_ZPOOL is disabled] Link: https://lkml.kernel.org/r/20210619025508.1239386-1-linmiaohe@huawei.com Link: https://lkml.kernel.org/r/20210608114515.206992-3-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Cc: Dan Streetman Cc: Seth Jennings Cc: Nathan Chancellor Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/zbud.h | 23 ----------------------- 1 file changed, 23 deletions(-) delete mode 100644 include/linux/zbud.h (limited to 'include/linux') diff --git a/include/linux/zbud.h b/include/linux/zbud.h deleted file mode 100644 index b1eaf6e31735..000000000000 --- a/include/linux/zbud.h +++ /dev/null @@ -1,23 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ZBUD_H_ -#define _ZBUD_H_ - -#include - -struct zbud_pool; - -struct zbud_ops { - int (*evict)(struct zbud_pool *pool, unsigned long handle); -}; - -struct zbud_pool *zbud_create_pool(gfp_t gfp, const struct zbud_ops *ops); -void zbud_destroy_pool(struct zbud_pool *pool); -int zbud_alloc(struct zbud_pool *pool, size_t size, gfp_t gfp, - unsigned long *handle); -void zbud_free(struct zbud_pool *pool, unsigned long handle); -int zbud_reclaim_page(struct zbud_pool *pool, unsigned int retries); -void *zbud_map(struct zbud_pool *pool, unsigned long handle); -void zbud_unmap(struct zbud_pool *pool, unsigned long handle); -u64 zbud_get_pool_size(struct zbud_pool *pool); - -#endif /* _ZBUD_H_ */ -- cgit v1.2.3 From b26e517a058bd40c790a1d9868c896842f2e4155 Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Wed, 30 Jun 2021 18:50:56 -0700 Subject: mm/mempolicy: cleanup nodemask intersection check for oom Patch series "mm/mempolicy: some fix and semantics cleanup", v4. Current memory policy code has some confusing and ambiguous part about MPOL_LOCAL policy, as it is handled as a faked MPOL_PREFERRED one, and there are many places having to distinguish them. Also the nodemask intersection check needs cleanup to be more explicit for OOM use, and handle MPOL_INTERLEAVE correctly. This patchset cleans up these and unifies the parameter sanity check for mbind() and set_mempolicy(). This patch (of 3): mempolicy_nodemask_intersects seem to be a general purpose mempolicy function. In fact it is partially tailored for the OOM purpose instead. The oom proper is the only existing user so rename the function to make that purpose explicit. While at it drop the MPOL_INTERLEAVE as those allocations never has a nodemask defined (see alloc_page_interleave) so this is a dead code and a confusing one because MPOL_INTERLEAVE is a hint rather than a hard requirement so it shouldn't be considered during the OOM. The final code can be reduced to a check for MPOL_BIND which is the only memory policy that is a hard requirement and thus relevant to a constrained OOM logic. [mhocko@suse.com: changelog edits] Link: https://lkml.kernel.org/r/1622560492-1294-1-git-send-email-feng.tang@intel.com Link: https://lkml.kernel.org/r/1622560492-1294-2-git-send-email-feng.tang@intel.com Link: https://lkml.kernel.org/r/1622469956-82897-1-git-send-email-feng.tang@intel.com Link: https://lkml.kernel.org/r/1622469956-82897-2-git-send-email-feng.tang@intel.com Signed-off-by: Feng Tang Suggested-by: Michal Hocko Acked-by: Michal Hocko Cc: Andi Kleen Cc: Andrea Arcangeli Cc: Ben Widawsky Cc: Dan Williams Cc: Dave Hansen Cc: David Rientjes Cc: Huang Ying Cc: Mel Gorman Cc: Mike Kravetz Cc: Randy Dunlap Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 5f1c74df264d..8773c55c7744 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -150,7 +150,7 @@ extern int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask); extern bool init_nodemask_of_mempolicy(nodemask_t *mask); -extern bool mempolicy_nodemask_intersects(struct task_struct *tsk, +extern bool mempolicy_in_oom_domain(struct task_struct *tsk, const nodemask_t *mask); extern nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy); -- cgit v1.2.3 From 269fbe72cded0afce0090103e90d2ae8ef8ac5b5 Mon Sep 17 00:00:00 2001 From: Ben Widawsky Date: Wed, 30 Jun 2021 18:51:10 -0700 Subject: mm/mempolicy: use unified 'nodes' for bind/interleave/prefer policies Current structure 'mempolicy' uses a union to store the node info for bind/interleave/perfer policies. union { short preferred_node; /* preferred */ nodemask_t nodes; /* interleave/bind */ /* undefined for default */ } v; Since preferred node can also be represented by a nodemask_t with only ont bit set, unify these policies with using one nodemask_t 'nodes', which can remove a union, simplify the code and make it easier to support future's new policy's node info. Link: https://lore.kernel.org/r/20200630212517.308045-7-ben.widawsky@intel.com Link: https://lkml.kernel.org/r/1623399825-75651-1-git-send-email-feng.tang@intel.com Co-developed-by: Feng Tang Signed-off-by: Ben Widawsky Signed-off-by: Feng Tang Cc: Michal Hocko Cc: David Rientjes Cc: Dave Hansen Cc: Andrea Arcangeli Cc: Mel Gorman Cc: Mike Kravetz Cc: Vlastimil Babka Cc: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 8773c55c7744..0aaf91b496e2 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -46,11 +46,8 @@ struct mempolicy { atomic_t refcnt; unsigned short mode; /* See MPOL_* above */ unsigned short flags; /* See set_mempolicy() MPOL_F_* above */ - union { - short preferred_node; /* preferred */ - nodemask_t nodes; /* interleave/bind */ - /* undefined for default */ - } v; + nodemask_t nodes; /* interleave/bind/perfer */ + union { nodemask_t cpuset_mems_allowed; /* relative to these nodes */ nodemask_t user_nodemask; /* nodemask passed by user */ -- cgit v1.2.3 From 51c656aef629bae94f2b07fcee7eabe280b905ea Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 30 Jun 2021 18:51:13 -0700 Subject: include/linux/mmzone.h: add documentation for pfn_valid() Patch series "arm64: drop pfn_valid_within() and simplify pfn_valid()", v4. These patches aim to remove CONFIG_HOLES_IN_ZONE and essentially hardwire pfn_valid_within() to 1. The idea is to mark NOMAP pages as reserved in the memory map and restore the intended semantics of pfn_valid() to designate availability of struct page for a pfn. With this the core mm will be able to cope with the fact that it cannot use NOMAP pages and the holes created by NOMAP ranges within MAX_ORDER blocks will be treated correctly even without the need for pfn_valid_within. This patch (of 4): Add comment describing the semantics of pfn_valid() that clarifies that pfn_valid() only checks for availability of a memory map entry (i.e. struct page) for a PFN rather than availability of usable memory backing that PFN. The most "generic" version of pfn_valid() used by the configurations with SPARSEMEM enabled resides in include/linux/mmzone.h so this is the most suitable place for documentation about semantics of pfn_valid(). Link: https://lkml.kernel.org/r/20210511100550.28178-1-rppt@kernel.org Link: https://lkml.kernel.org/r/20210511100550.28178-2-rppt@kernel.org Signed-off-by: Mike Rapoport Suggested-by: Anshuman Khandual Reviewed-by: Anshuman Khandual Acked-by: Ard Biesheuvel Reviewed-by: Kefeng Wang Cc: Catalin Marinas Cc: David Hildenbrand Cc: Marc Zyngier Cc: Mark Rutland Cc: Mike Rapoport Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 265a32e1ff74..7da43337ad23 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1445,6 +1445,17 @@ static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) #endif #ifndef CONFIG_HAVE_ARCH_PFN_VALID +/** + * pfn_valid - check if there is a valid memory map entry for a PFN + * @pfn: the page frame number to check + * + * Check if there is a valid memory map entry aka struct page for the @pfn. + * Note, that availability of the memory map entry does not imply that + * there is actual usable memory at that @pfn. The struct page may + * represent a hole or an unusable page frame. + * + * Return: 1 for PFNs that have memory map entries and 0 otherwise + */ static inline int pfn_valid(unsigned long pfn) { struct mem_section *ms; -- cgit v1.2.3 From 9092d4f7a1f846bcc72e9aace4ed64ed3fc4aa32 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 30 Jun 2021 18:51:16 -0700 Subject: memblock: update initialization of reserved pages The struct pages representing a reserved memory region are initialized using reserve_bootmem_range() function. This function is called for each reserved region just before the memory is freed from memblock to the buddy page allocator. The struct pages for MEMBLOCK_NOMAP regions are kept with the default values set by the memory map initialization which makes it necessary to have a special treatment for such pages in pfn_valid() and pfn_valid_within(). Split out initialization of the reserved pages to a function with a meaningful name and treat the MEMBLOCK_NOMAP regions the same way as the reserved regions and mark struct pages for the NOMAP regions as PageReserved. Link: https://lkml.kernel.org/r/20210511100550.28178-3-rppt@kernel.org Signed-off-by: Mike Rapoport Reviewed-by: David Hildenbrand Reviewed-by: Anshuman Khandual Acked-by: Ard Biesheuvel Reviewed-by: Kefeng Wang Cc: Catalin Marinas Cc: Marc Zyngier Cc: Mark Rutland Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 552309342c38..cbf46f56d105 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -30,7 +30,9 @@ extern unsigned long long max_possible_pfn; * @MEMBLOCK_NONE: no special request * @MEMBLOCK_HOTPLUG: hotpluggable region * @MEMBLOCK_MIRROR: mirrored region - * @MEMBLOCK_NOMAP: don't add to kernel direct mapping + * @MEMBLOCK_NOMAP: don't add to kernel direct mapping and treat as + * reserved in the memory map; refer to memblock_mark_nomap() description + * for further details */ enum memblock_flags { MEMBLOCK_NONE = 0x0, /* No special request */ -- cgit v1.2.3 From 16c9afc776608324ca71c0bc354987bab532f51d Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Wed, 30 Jun 2021 18:51:26 -0700 Subject: arm64/mm: drop HAVE_ARCH_PFN_VALID CONFIG_SPARSEMEM_VMEMMAP is now the only available memory model on arm64 platforms and free_unused_memmap() would just return without creating any holes in the memmap mapping. There is no need for any special handling in pfn_valid() and HAVE_ARCH_PFN_VALID can just be dropped. This also moves the pfn upper bits sanity check into generic pfn_valid(). Link: https://lkml.kernel.org/r/1621947349-25421-1-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Acked-by: David Hildenbrand Acked-by: Mike Rapoport Cc: Catalin Marinas Cc: Will Deacon Cc: David Hildenbrand Cc: Mike Rapoport Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 7da43337ad23..7bc7e41b6c31 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1460,6 +1460,15 @@ static inline int pfn_valid(unsigned long pfn) { struct mem_section *ms; + /* + * Ensure the upper PAGE_SHIFT bits are clear in the + * pfn. Else it might lead to false positives when + * some of the upper bits are set, but the lower bits + * match a valid pfn. + */ + if (PHYS_PFN(PFN_PHYS(pfn)) != pfn) + return 0; + if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; ms = __nr_to_section(pfn_to_section_nr(pfn)); -- cgit v1.2.3 From 6acfb5ba150cf75005ce85e0e25d79ef2fec287c Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Wed, 30 Jun 2021 18:51:29 -0700 Subject: mm: migrate: fix missing update page_private to hugetlb_page_subpool Since commit d6995da31122 ("hugetlb: use page.private for hugetlb specific page flags") converts page.private for hugetlb specific page flags. We should use hugetlb_page_subpool() to get the subpool pointer instead of page_private(). This 'could' prevent the migration of hugetlb pages. page_private(hpage) is now used for hugetlb page specific flags. At migration time, the only flag which could be set is HPageVmemmapOptimized. This flag will only be set if the new vmemmap reduction feature is enabled. In addition, !page_mapping() implies an anonymous mapping. So, this will prevent migration of hugetb pages in anonymous mappings if the vmemmap reduction feature is enabled. In addition, that if statement checked for the rare race condition of a page being migrated while in the process of being freed. Since that check is now wrong, we could leak hugetlb subpool usage counts. The commit forgot to update it in the page migration routine. So fix it. [songmuchun@bytedance.com: fix compiler error when !CONFIG_HUGETLB_PAGE reported by Randy] Link: https://lkml.kernel.org/r/20210521022747.35736-1-songmuchun@bytedance.com Link: https://lkml.kernel.org/r/20210520025949.1866-1-songmuchun@bytedance.com Fixes: d6995da31122 ("hugetlb: use page.private for hugetlb specific page flags") Signed-off-by: Muchun Song Reported-by: Anshuman Khandual Reviewed-by: Mike Kravetz Acked-by: Michal Hocko Tested-by: Anshuman Khandual [arm64] Cc: Oscar Salvador Cc: David Hildenbrand Cc: Matthew Wilcox Cc: Xiongchun Duan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index f11ba701e199..a58e11f2db15 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -898,6 +898,11 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; +static inline struct hugepage_subpool *hugetlb_page_subpool(struct page *hpage) +{ + return NULL; +} + static inline int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list) { -- cgit v1.2.3 From 5db4f15c4fd7ae74dd40c6f84bf56dfcf13d10cf Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Wed, 30 Jun 2021 18:51:35 -0700 Subject: mm: memory: add orig_pmd to struct vm_fault Pach series "mm: thp: use generic THP migration for NUMA hinting fault", v3. When the THP NUMA fault support was added THP migration was not supported yet. So the ad hoc THP migration was implemented in NUMA fault handling. Since v4.14 THP migration has been supported so it doesn't make too much sense to still keep another THP migration implementation rather than using the generic migration code. It is definitely a maintenance burden to keep two THP migration implementation for different code paths and it is more error prone. Using the generic THP migration implementation allows us remove the duplicate code and some hacks needed by the old ad hoc implementation. A quick grep shows x86_64, PowerPC (book3s), ARM64 ans S390 support both THP and NUMA balancing. The most of them support THP migration except for S390. Zi Yan tried to add THP migration support for S390 before but it was not accepted due to the design of S390 PMD. For the discussion, please see: https://lkml.org/lkml/2018/4/27/953. Per the discussion with Gerald Schaefer in v1 it is acceptible to skip huge PMD for S390 for now. I saw there were some hacks about gup from git history, but I didn't figure out if they have been removed or not since I just found FOLL_NUMA code in the current gup implementation and they seems useful. Patch #1 ~ #2 are preparation patches. Patch #3 is the real meat. Patch #4 ~ #6 keep consistent counters and behaviors with before. Patch #7 skips change huge PMD to prot_none if thp migration is not supported. Test ---- Did some tests to measure the latency of do_huge_pmd_numa_page. The test VM has 80 vcpus and 64G memory. The test would create 2 processes to consume 128G memory together which would incur memory pressure to cause THP splits. And it also creates 80 processes to hog cpu, and the memory consumer processes are bound to different nodes periodically in order to increase NUMA faults. The below test script is used: echo 3 > /proc/sys/vm/drop_caches # Run stress-ng for 24 hours ./stress-ng/stress-ng --vm 2 --vm-bytes 64G --timeout 24h & PID=$! ./stress-ng/stress-ng --cpu $NR_CPUS --timeout 24h & # Wait for vm stressors forked sleep 5 PID_1=`pgrep -P $PID | awk 'NR == 1'` PID_2=`pgrep -P $PID | awk 'NR == 2'` JOB1=`pgrep -P $PID_1` JOB2=`pgrep -P $PID_2` # Bind load jobs to different nodes periodically to force generate # cross node memory access while [ -d "/proc/$PID" ] do taskset -apc 8 $JOB1 taskset -apc 8 $JOB2 sleep 300 taskset -apc 58 $JOB1 taskset -apc 58 $JOB2 sleep 300 done With the above test the histogram of latency of do_huge_pmd_numa_page is as shown below. Since the number of do_huge_pmd_numa_page varies drastically for each run (should be due to scheduler), so I converted the raw number to percentage. patched base @us[stress-ng]: [0] 3.57% 0.16% [1] 55.68% 18.36% [2, 4) 10.46% 40.44% [4, 8) 7.26% 17.82% [8, 16) 21.12% 13.41% [16, 32) 1.06% 4.27% [32, 64) 0.56% 4.07% [64, 128) 0.16% 0.35% [128, 256) < 0.1% < 0.1% [256, 512) < 0.1% < 0.1% [512, 1K) < 0.1% < 0.1% [1K, 2K) < 0.1% < 0.1% [2K, 4K) < 0.1% < 0.1% [4K, 8K) < 0.1% < 0.1% [8K, 16K) < 0.1% < 0.1% [16K, 32K) < 0.1% < 0.1% [32K, 64K) < 0.1% < 0.1% Per the result, patched kernel is even slightly better than the base kernel. I think this is because the lock contention against THP split is less than base kernel due to the refactor. To exclude the affect from THP split, I also did test w/o memory pressure. No obvious regression is spotted. The below is the test result *w/o* memory pressure. patched base @us[stress-ng]: [0] 7.97% 18.4% [1] 69.63% 58.24% [2, 4) 4.18% 2.63% [4, 8) 0.22% 0.17% [8, 16) 1.03% 0.92% [16, 32) 0.14% < 0.1% [32, 64) < 0.1% < 0.1% [64, 128) < 0.1% < 0.1% [128, 256) < 0.1% < 0.1% [256, 512) 0.45% 1.19% [512, 1K) 15.45% 17.27% [1K, 2K) < 0.1% < 0.1% [2K, 4K) < 0.1% < 0.1% [4K, 8K) < 0.1% < 0.1% [8K, 16K) 0.86% 0.88% [16K, 32K) < 0.1% 0.15% [32K, 64K) < 0.1% < 0.1% [64K, 128K) < 0.1% < 0.1% [128K, 256K) < 0.1% < 0.1% The series also survived a series of tests that exercise NUMA balancing migrations by Mel. This patch (of 7): Add orig_pmd to struct vm_fault so the "orig_pmd" parameter used by huge page fault could be removed, just like its PTE counterpart does. Link: https://lkml.kernel.org/r/20210518200801.7413-1-shy828301@gmail.com Link: https://lkml.kernel.org/r/20210518200801.7413-2-shy828301@gmail.com Signed-off-by: Yang Shi Acked-by: Mel Gorman Cc: Kirill A. Shutemov Cc: Zi Yan Cc: Huang Ying Cc: Michal Hocko Cc: Hugh Dickins Cc: Gerald Schaefer Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Christian Borntraeger Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 9 ++++----- include/linux/mm.h | 7 ++++++- 2 files changed, 10 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 939f21b69ead..f123e15d966e 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -11,7 +11,7 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf); int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma); -void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd); +void huge_pmd_set_accessed(struct vm_fault *vmf); int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, pud_t *dst_pud, pud_t *src_pud, unsigned long addr, struct vm_area_struct *vma); @@ -24,7 +24,7 @@ static inline void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud) } #endif -vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd); +vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf); struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, unsigned int flags); @@ -288,7 +288,7 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud, int flags, struct dev_pagemap **pgmap); -vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd); +vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf); extern struct page *huge_zero_page; extern unsigned long huge_zero_pfn; @@ -441,8 +441,7 @@ static inline spinlock_t *pud_trans_huge_lock(pud_t *pud, return NULL; } -static inline vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, - pmd_t orig_pmd) +static inline vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) { return 0; } diff --git a/include/linux/mm.h b/include/linux/mm.h index aa875dacd9c3..3cbd2d6d248e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -550,7 +550,12 @@ struct vm_fault { pud_t *pud; /* Pointer to pud entry matching * the 'address' */ - pte_t orig_pte; /* Value of PTE at the time of fault */ + union { + pte_t orig_pte; /* Value of PTE at the time of fault */ + pmd_t orig_pmd; /* Value of PMD at the time of fault, + * used by PMD fault only. + */ + }; struct page *cow_page; /* Page handler may use for COW fault */ struct page *page; /* ->fault handlers should return a -- cgit v1.2.3 From c5b5a3dd2c1fa61049b7789ce596faff4d659a61 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Wed, 30 Jun 2021 18:51:42 -0700 Subject: mm: thp: refactor NUMA fault handling When the THP NUMA fault support was added THP migration was not supported yet. So the ad hoc THP migration was implemented in NUMA fault handling. Since v4.14 THP migration has been supported so it doesn't make too much sense to still keep another THP migration implementation rather than using the generic migration code. This patch reworks the NUMA fault handling to use generic migration implementation to migrate misplaced page. There is no functional change. After the refactor the flow of NUMA fault handling looks just like its PTE counterpart: Acquire ptl Prepare for migration (elevate page refcount) Release ptl Isolate page from lru and elevate page refcount Migrate the misplaced THP If migration fails just restore the old normal PMD. In the old code anon_vma lock was needed to serialize THP migration against THP split, but since then the THP code has been reworked a lot, it seems anon_vma lock is not required anymore to avoid the race. The page refcount elevation when holding ptl should prevent from THP split. Use migrate_misplaced_page() for both base page and THP NUMA hinting fault and remove all the dead and duplicate code. [dan.carpenter@oracle.com: fix a double unlock bug] Link: https://lkml.kernel.org/r/YLX8uYN01JmfLnlK@mwanda Link: https://lkml.kernel.org/r/20210518200801.7413-4-shy828301@gmail.com Signed-off-by: Yang Shi Signed-off-by: Dan Carpenter Acked-by: Mel Gorman Cc: Christian Borntraeger Cc: Gerald Schaefer Cc: Heiko Carstens Cc: Huang Ying Cc: Hugh Dickins Cc: Kirill A. Shutemov Cc: Michal Hocko Cc: Vasily Gorbik Cc: Zi Yan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 23 ----------------------- 1 file changed, 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 7b7b73977278..9b7b7cd3bae9 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -99,14 +99,9 @@ static inline void __ClearPageMovable(struct page *page) #endif #ifdef CONFIG_NUMA_BALANCING -extern bool pmd_trans_migrating(pmd_t pmd); extern int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, int node); #else -static inline bool pmd_trans_migrating(pmd_t pmd) -{ - return false; -} static inline int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, int node) { @@ -114,24 +109,6 @@ static inline int migrate_misplaced_page(struct page *page, } #endif /* CONFIG_NUMA_BALANCING */ -#if defined(CONFIG_NUMA_BALANCING) && defined(CONFIG_TRANSPARENT_HUGEPAGE) -extern int migrate_misplaced_transhuge_page(struct mm_struct *mm, - struct vm_area_struct *vma, - pmd_t *pmd, pmd_t entry, - unsigned long address, - struct page *page, int node); -#else -static inline int migrate_misplaced_transhuge_page(struct mm_struct *mm, - struct vm_area_struct *vma, - pmd_t *pmd, pmd_t entry, - unsigned long address, - struct page *page, int node) -{ - return -EAGAIN; -} -#endif /* CONFIG_NUMA_BALANCING && CONFIG_TRANSPARENT_HUGEPAGE*/ - - #ifdef CONFIG_MIGRATION /* -- cgit v1.2.3 From 1fb08ac63beedf58e2ae9f229ea1f9474949a185 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Wed, 30 Jun 2021 18:52:01 -0700 Subject: mm: rmap: make try_to_unmap() void function Currently try_to_unmap() return bool value by checking page_mapcount(), however this may return false positive since page_mapcount() doesn't check all subpages of compound page. The total_mapcount() could be used instead, but its cost is higher since it traverses all subpages. Actually the most callers of try_to_unmap() don't care about the return value at all. So just need check if page is still mapped by page_mapped() when necessary. And page_mapped() does bail out early when it finds mapped subpage. Link: https://lkml.kernel.org/r/bb27e3fe-6036-b637-5086-272befbfe3da@google.com Suggested-by: Hugh Dickins Signed-off-by: Yang Shi Acked-by: Minchan Kim Reviewed-by: Shakeel Butt Acked-by: Kirill A. Shutemov Signed-off-by: Hugh Dickins Acked-by: Naoya Horiguchi Cc: Alistair Popple Cc: Jan Kara Cc: Jue Wang Cc: "Matthew Wilcox (Oracle)" Cc: Miaohe Lin Cc: Oscar Salvador Cc: Peter Xu Cc: Ralph Campbell Cc: Wang Yugui Cc: Zi Yan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 8d04e7deedc6..ed31a559e857 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -195,7 +195,7 @@ static inline void page_dup_rmap(struct page *page, bool compound) int page_referenced(struct page *, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags); -bool try_to_unmap(struct page *, enum ttu_flags flags); +void try_to_unmap(struct page *, enum ttu_flags flags); /* Avoid racy checks */ #define PVMW_SYNC (1 << 0) -- cgit v1.2.3 From c4ffefd16daba0f29fa7d9534de20949b673eca0 Mon Sep 17 00:00:00 2001 From: Hyeonggon Yoo <42.hyeyoo@gmail.com> Date: Wed, 30 Jun 2021 18:53:10 -0700 Subject: mm: fix typos and grammar error in comments We moves tha -> We move that in mm/swap.c statments -> statements in include/linux/mm.h Link: https://lkml.kernel.org/r/20210509063444.GA24745@hyeyoo Signed-off-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 3cbd2d6d248e..714ad9b26ed2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -155,7 +155,7 @@ extern int mmap_rnd_compat_bits __read_mostly; /* This function must be updated when the size of struct page grows above 80 * or reduces below 56. The idea that compiler optimizes out switch() * statement, and only leaves move/store instructions. Also the compiler can - * combine write statments if they are both assignments and can be reordered, + * combine write statements if they are both assignments and can be reordered, * this can result in several of the writes here being dropped. */ #define mm_zero_struct_page(pp) __mm_zero_struct_page(pp) -- cgit v1.2.3 From fac7757e1fb05b75c8e22d4f8fe2f6c9c4d7edca Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Wed, 30 Jun 2021 18:53:13 -0700 Subject: mm: define default value for FIRST_USER_ADDRESS Currently most platforms define FIRST_USER_ADDRESS as 0UL duplication the same code all over. Instead just define a generic default value (i.e 0UL) for FIRST_USER_ADDRESS and let the platforms override when required. This makes it much cleaner with reduced code. The default FIRST_USER_ADDRESS here would be skipped in when the given platform overrides its value via . Link: https://lkml.kernel.org/r/1620615725-24623-1-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Acked-by: Geert Uytterhoeven [m68k] Acked-by: Guo Ren [csky] Acked-by: Stafford Horne [openrisc] Acked-by: Catalin Marinas [arm64] Acked-by: Mike Rapoport Acked-by: Palmer Dabbelt [RISC-V] Cc: Richard Henderson Cc: Vineet Gupta Cc: Catalin Marinas Cc: Will Deacon Cc: Guo Ren Cc: Brian Cain Cc: Geert Uytterhoeven Cc: Michal Simek Cc: Thomas Bogendoerfer Cc: Ley Foon Tan Cc: Jonas Bonn Cc: Stefan Kristiansson Cc: Stafford Horne Cc: "James E.J. Bottomley" Cc: Michael Ellerman Cc: Christophe Leroy Cc: Paul Walmsley Cc: Heiko Carstens Cc: Yoshinori Sato Cc: "David S. Miller" Cc: Jeff Dike Cc: Thomas Gleixner Cc: Chris Zankel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pgtable.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 2b0d02291178..69700e3e615f 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -28,6 +28,15 @@ #define USER_PGTABLES_CEILING 0UL #endif +/* + * This defines the first usable user address. Platforms + * can override its value with custom FIRST_USER_ADDRESS + * defined in their respective . + */ +#ifndef FIRST_USER_ADDRESS +#define FIRST_USER_ADDRESS 0UL +#endif + /* * A page table page can be thought of an array like this: pXd_t[PTRS_PER_PxD] * -- cgit v1.2.3 From 041711ce7cdf023f53d76f64d82b75210248e18d Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Wed, 30 Jun 2021 18:53:17 -0700 Subject: mm: fix spelling mistakes Fix some spelling mistakes in comments: each having differents usage ==> each has a different usage statments ==> statements adresses ==> addresses aggresive ==> aggressive datas ==> data posion ==> poison higer ==> higher precisly ==> precisely wont ==> won't We moves tha ==> We move the endianess ==> endianness Link: https://lkml.kernel.org/r/20210519065853.7723-2-thunder.leizhen@huawei.com Signed-off-by: Zhen Lei Reviewed-by: Souptick Joarder Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memremap.h | 2 +- include/linux/mm_types.h | 2 +- include/linux/mmzone.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 45a79da89c5f..c0e9d35889e8 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -26,7 +26,7 @@ struct vmem_altmap { }; /* - * Specialize ZONE_DEVICE memory into multiple types each having differents + * Specialize ZONE_DEVICE memory into multiple types each has a different * usage. * * MEMORY_DEVICE_PRIVATE: diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index b66d0225414e..748617780924 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -397,7 +397,7 @@ struct mm_struct { unsigned long mmap_base; /* base of mmap area */ unsigned long mmap_legacy_base; /* base of mmap area in bottom-up allocations */ #ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES - /* Base adresses for compatible mmap() */ + /* Base addresses for compatible mmap() */ unsigned long mmap_compat_base; unsigned long mmap_compat_legacy_base; #endif diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 7bc7e41b6c31..0ed2c23ed3fb 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -114,7 +114,7 @@ static inline bool free_area_empty(struct free_area *area, int migratetype) struct pglist_data; /* - * Add a wild amount of padding here to ensure datas fall into separate + * Add a wild amount of padding here to ensure data fall into separate * cachelines. There are very few zone structures in the machine, so space * consumption is not a concern here. */ -- cgit v1.2.3 From 2bb6a033fb4078f1c528ee575f551064ed738d6f Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 30 Jun 2021 18:53:47 -0700 Subject: mm/swap: make swap_address_space an inline function make W=1 generates the following warning in page_mapping() for allnoconfig mm/util.c:700:15: warning: variable `entry' set but not used [-Wunused-but-set-variable] swp_entry_t entry; ^~~~~ swap_address is a #define on !CONFIG_SWAP configurations. Make the helper an inline function to suppress the warning, add type checking and to apply any side-effects in the parameter list. Link: https://lkml.kernel.org/r/20210520084809.8576-12-mgorman@techsingularity.net Signed-off-by: Mel Gorman Reviewed-by: Yang Shi Acked-by: Vlastimil Babka Cc: Dan Streetman Cc: David Hildenbrand Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 49b1dd2c100b..ac9bd84c905e 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -537,7 +537,11 @@ static inline void put_swap_device(struct swap_info_struct *si) { } -#define swap_address_space(entry) (NULL) +static inline struct address_space *swap_address_space(swp_entry_t entry) +{ + return NULL; +} + #define get_nr_swap_pages() 0L #define total_swap_pages 0L #define total_swapcache_pages() 0UL -- cgit v1.2.3 From 351de44fde5afc3b0b23294ebf404e78065c2745 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 30 Jun 2021 18:53:56 -0700 Subject: mm/swap: make NODE_DATA an inline function on CONFIG_FLATMEM make W=1 generates the following warning in mm/workingset.c for allnoconfig mm/workingset.c: In function `unpack_shadow': mm/workingset.c:201:15: warning: variable `nid' set but not used [-Wunused-but-set-variable] int memcgid, nid; ^~~ On FLATMEM, NODE_DATA returns a global pglist_data without dereferencing nid. Make the helper an inline function to suppress the warning, add type checking and to apply any side-effects in the parameter list. Link: https://lkml.kernel.org/r/20210520084809.8576-15-mgorman@techsingularity.net Signed-off-by: Mel Gorman Reviewed-by: Yang Shi Acked-by: Vlastimil Babka Cc: Dan Streetman Cc: David Hildenbrand Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 0ed2c23ed3fb..fcb535560028 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1064,7 +1064,10 @@ extern char numa_zonelist_order[]; #ifndef CONFIG_NUMA extern struct pglist_data contig_page_data; -#define NODE_DATA(nid) (&contig_page_data) +static inline struct pglist_data *NODE_DATA(int nid) +{ + return &contig_page_data; +} #define NODE_MEM_MAP(nid) mem_map #else /* CONFIG_NUMA */ -- cgit v1.2.3 From 1c2f7d14d84f767a797558609eb034511e02f41e Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Wed, 30 Jun 2021 18:53:59 -0700 Subject: mm/thp: define default pmd_pgtable() Currently most platforms define pmd_pgtable() as pmd_page() duplicating the same code all over. Instead just define a default value i.e pmd_page() for pmd_pgtable() and let platforms override when required via . All the existing platform that override pmd_pgtable() have been moved into their respective header in order to precede before the new generic definition. This makes it much cleaner with reduced code. Link: https://lkml.kernel.org/r/1623646133-20306-1-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Acked-by: Geert Uytterhoeven Acked-by: Mike Rapoport Cc: Nick Hu Cc: Richard Henderson Cc: Vineet Gupta Cc: Catalin Marinas Cc: Will Deacon Cc: Guo Ren Cc: Brian Cain Cc: Geert Uytterhoeven Cc: Michal Simek Cc: Thomas Bogendoerfer Cc: Ley Foon Tan Cc: Jonas Bonn Cc: Stefan Kristiansson Cc: Stafford Horne Cc: "James E.J. Bottomley" Cc: Michael Ellerman Cc: Christophe Leroy Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Heiko Carstens Cc: Yoshinori Sato Cc: "David S. Miller" Cc: Jeff Dike Cc: Thomas Gleixner Cc: Chris Zankel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pgtable.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 69700e3e615f..e82660f7b9e4 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -37,6 +37,15 @@ #define FIRST_USER_ADDRESS 0UL #endif +/* + * This defines the generic helper for accessing PMD page + * table page. Although platforms can still override this + * via their respective . + */ +#ifndef pmd_pgtable +#define pmd_pgtable(pmd) pmd_page(pmd) +#endif + /* * A page table page can be thought of an array like this: pXd_t[PTRS_PER_PxD] * -- cgit v1.2.3 From af5cdaf82238fb3637a0d0fff4670e5be71c611c Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Wed, 30 Jun 2021 18:54:06 -0700 Subject: mm: remove special swap entry functions Patch series "Add support for SVM atomics in Nouveau", v11. Introduction ============ Some devices have features such as atomic PTE bits that can be used to implement atomic access to system memory. To support atomic operations to a shared virtual memory page such a device needs access to that page which is exclusive of the CPU. This series introduces a mechanism to temporarily unmap pages granting exclusive access to a device. These changes are required to support OpenCL atomic operations in Nouveau to shared virtual memory (SVM) regions allocated with the CL_MEM_SVM_ATOMICS clSVMAlloc flag. A more complete description of the OpenCL SVM feature is available at https://www.khronos.org/registry/OpenCL/specs/3.0-unified/html/ OpenCL_API.html#_shared_virtual_memory . Implementation ============== Exclusive device access is implemented by adding a new swap entry type (SWAP_DEVICE_EXCLUSIVE) which is similar to a migration entry. The main difference is that on fault the original entry is immediately restored by the fault handler instead of waiting. Restoring the entry triggers calls to MMU notifers which allows a device driver to revoke the atomic access permission from the GPU prior to the CPU finalising the entry. Patches ======= Patches 1 & 2 refactor existing migration and device private entry functions. Patches 3 & 4 rework try_to_unmap_one() by splitting out unrelated functionality into separate functions - try_to_migrate_one() and try_to_munlock_one(). Patch 5 renames some existing code but does not introduce functionality. Patch 6 is a small clean-up to swap entry handling in copy_pte_range(). Patch 7 contains the bulk of the implementation for device exclusive memory. Patch 8 contains some additions to the HMM selftests to ensure everything works as expected. Patch 9 is a cleanup for the Nouveau SVM implementation. Patch 10 contains the implementation of atomic access for the Nouveau driver. Testing ======= This has been tested with upstream Mesa 21.1.0 and a simple OpenCL program which checks that GPU atomic accesses to system memory are atomic. Without this series the test fails as there is no way of write-protecting the page mapping which results in the device clobbering CPU writes. For reference the test is available at https://ozlabs.org/~apopple/opencl_svm_atomics/ Further testing has been performed by adding support for testing exclusive access to the hmm-tests kselftests. This patch (of 10): Remove multiple similar inline functions for dealing with different types of special swap entries. Both migration and device private swap entries use the swap offset to store a pfn. Instead of multiple inline functions to obtain a struct page for each swap entry type use a common function pfn_swap_entry_to_page(). Also open-code the various entry_to_pfn() functions as this results is shorter code that is easier to understand. Link: https://lkml.kernel.org/r/20210616105937.23201-1-apopple@nvidia.com Link: https://lkml.kernel.org/r/20210616105937.23201-2-apopple@nvidia.com Signed-off-by: Alistair Popple Reviewed-by: Ralph Campbell Reviewed-by: Christoph Hellwig Cc: "Matthew Wilcox (Oracle)" Cc: Hugh Dickins Cc: Peter Xu Cc: Shakeel Butt Cc: Ben Skeggs Cc: Jason Gunthorpe Cc: John Hubbard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 4 +-- include/linux/swapops.h | 69 +++++++++++++++++-------------------------------- 2 files changed, 25 insertions(+), 48 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index ac9bd84c905e..df7cbb6b3d3e 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -564,8 +564,8 @@ static inline void show_swap_cache_info(void) { } -#define free_swap_and_cache(e) ({(is_migration_entry(e) || is_device_private_entry(e));}) -#define swapcache_prepare(e) ({(is_migration_entry(e) || is_device_private_entry(e));}) +/* used to sanity check ptes in zap_pte_range when CONFIG_SWAP=0 */ +#define free_swap_and_cache(e) is_pfn_swap_entry(e) static inline int add_swap_count_continuation(swp_entry_t swp, gfp_t gfp_mask) { diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 708fbeb21dd3..c24c79812bc1 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -128,16 +128,6 @@ static inline bool is_write_device_private_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_DEVICE_WRITE); } - -static inline unsigned long device_private_entry_to_pfn(swp_entry_t entry) -{ - return swp_offset(entry); -} - -static inline struct page *device_private_entry_to_page(swp_entry_t entry) -{ - return pfn_to_page(swp_offset(entry)); -} #else /* CONFIG_DEVICE_PRIVATE */ static inline swp_entry_t make_device_private_entry(struct page *page, bool write) { @@ -157,16 +147,6 @@ static inline bool is_write_device_private_entry(swp_entry_t entry) { return false; } - -static inline unsigned long device_private_entry_to_pfn(swp_entry_t entry) -{ - return 0; -} - -static inline struct page *device_private_entry_to_page(swp_entry_t entry) -{ - return NULL; -} #endif /* CONFIG_DEVICE_PRIVATE */ #ifdef CONFIG_MIGRATION @@ -189,22 +169,6 @@ static inline int is_write_migration_entry(swp_entry_t entry) return unlikely(swp_type(entry) == SWP_MIGRATION_WRITE); } -static inline unsigned long migration_entry_to_pfn(swp_entry_t entry) -{ - return swp_offset(entry); -} - -static inline struct page *migration_entry_to_page(swp_entry_t entry) -{ - struct page *p = pfn_to_page(swp_offset(entry)); - /* - * Any use of migration entries may only occur while the - * corresponding page is locked - */ - BUG_ON(!PageLocked(compound_head(p))); - return p; -} - static inline void make_migration_entry_read(swp_entry_t *entry) { *entry = swp_entry(SWP_MIGRATION_READ, swp_offset(*entry)); @@ -224,16 +188,6 @@ static inline int is_migration_entry(swp_entry_t swp) return 0; } -static inline unsigned long migration_entry_to_pfn(swp_entry_t entry) -{ - return 0; -} - -static inline struct page *migration_entry_to_page(swp_entry_t entry) -{ - return NULL; -} - static inline void make_migration_entry_read(swp_entry_t *entryp) { } static inline void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, spinlock_t *ptl) { } @@ -248,6 +202,29 @@ static inline int is_write_migration_entry(swp_entry_t entry) #endif +static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry) +{ + struct page *p = pfn_to_page(swp_offset(entry)); + + /* + * Any use of migration entries may only occur while the + * corresponding page is locked + */ + BUG_ON(is_migration_entry(entry) && !PageLocked(p)); + + return p; +} + +/* + * A pfn swap entry is a special type of swap entry that always has a pfn stored + * in the swap offset. They are used to represent unaddressable device memory + * and to restrict access to a page undergoing migration. + */ +static inline bool is_pfn_swap_entry(swp_entry_t entry) +{ + return is_migration_entry(entry) || is_device_private_entry(entry); +} + struct page_vma_mapped_walk; #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION -- cgit v1.2.3 From 4dd845b5a3e57ad07f26ef808707b064696fe34b Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Wed, 30 Jun 2021 18:54:09 -0700 Subject: mm/swapops: rework swap entry manipulation code Both migration and device private pages use special swap entries that are manipluated by a range of inline functions. The arguments to these are somewhat inconsistent so rework them to remove flag type arguments and to make the arguments similar for both read and write entry creation. Link: https://lkml.kernel.org/r/20210616105937.23201-3-apopple@nvidia.com Signed-off-by: Alistair Popple Reviewed-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Reviewed-by: Ralph Campbell Cc: Ben Skeggs Cc: Hugh Dickins Cc: John Hubbard Cc: "Matthew Wilcox (Oracle)" Cc: Peter Xu Cc: Shakeel Butt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swapops.h | 56 ++++++++++++++++++++++++++----------------------- 1 file changed, 30 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swapops.h b/include/linux/swapops.h index c24c79812bc1..04d76357aa0c 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -107,35 +107,35 @@ static inline void *swp_to_radix_entry(swp_entry_t entry) } #if IS_ENABLED(CONFIG_DEVICE_PRIVATE) -static inline swp_entry_t make_device_private_entry(struct page *page, bool write) +static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset) { - return swp_entry(write ? SWP_DEVICE_WRITE : SWP_DEVICE_READ, - page_to_pfn(page)); + return swp_entry(SWP_DEVICE_READ, offset); } -static inline bool is_device_private_entry(swp_entry_t entry) +static inline swp_entry_t make_writable_device_private_entry(pgoff_t offset) { - int type = swp_type(entry); - return type == SWP_DEVICE_READ || type == SWP_DEVICE_WRITE; + return swp_entry(SWP_DEVICE_WRITE, offset); } -static inline void make_device_private_entry_read(swp_entry_t *entry) +static inline bool is_device_private_entry(swp_entry_t entry) { - *entry = swp_entry(SWP_DEVICE_READ, swp_offset(*entry)); + int type = swp_type(entry); + return type == SWP_DEVICE_READ || type == SWP_DEVICE_WRITE; } -static inline bool is_write_device_private_entry(swp_entry_t entry) +static inline bool is_writable_device_private_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_DEVICE_WRITE); } #else /* CONFIG_DEVICE_PRIVATE */ -static inline swp_entry_t make_device_private_entry(struct page *page, bool write) +static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset) { return swp_entry(0, 0); } -static inline void make_device_private_entry_read(swp_entry_t *entry) +static inline swp_entry_t make_writable_device_private_entry(pgoff_t offset) { + return swp_entry(0, 0); } static inline bool is_device_private_entry(swp_entry_t entry) @@ -143,35 +143,32 @@ static inline bool is_device_private_entry(swp_entry_t entry) return false; } -static inline bool is_write_device_private_entry(swp_entry_t entry) +static inline bool is_writable_device_private_entry(swp_entry_t entry) { return false; } #endif /* CONFIG_DEVICE_PRIVATE */ #ifdef CONFIG_MIGRATION -static inline swp_entry_t make_migration_entry(struct page *page, int write) -{ - BUG_ON(!PageLocked(compound_head(page))); - - return swp_entry(write ? SWP_MIGRATION_WRITE : SWP_MIGRATION_READ, - page_to_pfn(page)); -} - static inline int is_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_READ || swp_type(entry) == SWP_MIGRATION_WRITE); } -static inline int is_write_migration_entry(swp_entry_t entry) +static inline int is_writable_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_WRITE); } -static inline void make_migration_entry_read(swp_entry_t *entry) +static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) { - *entry = swp_entry(SWP_MIGRATION_READ, swp_offset(*entry)); + return swp_entry(SWP_MIGRATION_READ, offset); +} + +static inline swp_entry_t make_writable_migration_entry(pgoff_t offset) +{ + return swp_entry(SWP_MIGRATION_WRITE, offset); } extern void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, @@ -181,21 +178,28 @@ extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, extern void migration_entry_wait_huge(struct vm_area_struct *vma, struct mm_struct *mm, pte_t *pte); #else +static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) +{ + return swp_entry(0, 0); +} + +static inline swp_entry_t make_writable_migration_entry(pgoff_t offset) +{ + return swp_entry(0, 0); +} -#define make_migration_entry(page, write) swp_entry(0, 0) static inline int is_migration_entry(swp_entry_t swp) { return 0; } -static inline void make_migration_entry_read(swp_entry_t *entryp) { } static inline void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, spinlock_t *ptl) { } static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { } static inline void migration_entry_wait_huge(struct vm_area_struct *vma, struct mm_struct *mm, pte_t *pte) { } -static inline int is_write_migration_entry(swp_entry_t entry) +static inline int is_writable_migration_entry(swp_entry_t entry) { return 0; } -- cgit v1.2.3 From cd62734ca60dbb2ab5bb19c8d837dd9990955310 Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Wed, 30 Jun 2021 18:54:12 -0700 Subject: mm/rmap: split try_to_munlock from try_to_unmap The behaviour of try_to_unmap_one() is difficult to follow because it performs different operations based on a fairly large set of flags used in different combinations. TTU_MUNLOCK is one such flag. However it is exclusively used by try_to_munlock() which specifies no other flags. Therefore rather than overload try_to_unmap_one() with unrelated behaviour split this out into it's own function and remove the flag. Link: https://lkml.kernel.org/r/20210616105937.23201-4-apopple@nvidia.com Signed-off-by: Alistair Popple Reviewed-by: Ralph Campbell Reviewed-by: Christoph Hellwig Cc: Ben Skeggs Cc: Hugh Dickins Cc: Jason Gunthorpe Cc: John Hubbard Cc: "Matthew Wilcox (Oracle)" Cc: Peter Xu Cc: Shakeel Butt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rmap.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index ed31a559e857..69190efbd842 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -87,7 +87,6 @@ struct anon_vma_chain { enum ttu_flags { TTU_MIGRATION = 0x1, /* migration mode */ - TTU_MUNLOCK = 0x2, /* munlock mode */ TTU_SPLIT_HUGE_PMD = 0x4, /* split huge PMD if any */ TTU_IGNORE_MLOCK = 0x8, /* ignore mlock */ @@ -240,7 +239,7 @@ int page_mkclean(struct page *); * called in munlock()/munmap() path to check for other vmas holding * the page mlocked. */ -void try_to_munlock(struct page *); +void page_mlock(struct page *page); void remove_migration_ptes(struct page *old, struct page *new, bool locked); -- cgit v1.2.3 From a98a2f0c8ce1b2138cb8e3ae410444dedcc14809 Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Wed, 30 Jun 2021 18:54:16 -0700 Subject: mm/rmap: split migration into its own function Migration is currently implemented as a mode of operation for try_to_unmap_one() generally specified by passing the TTU_MIGRATION flag or in the case of splitting a huge anonymous page TTU_SPLIT_FREEZE. However it does not have much in common with the rest of the unmap functionality of try_to_unmap_one() and thus splitting it into a separate function reduces the complexity of try_to_unmap_one() making it more readable. Several simplifications can also be made in try_to_migrate_one() based on the following observations: - All users of TTU_MIGRATION also set TTU_IGNORE_MLOCK. - No users of TTU_MIGRATION ever set TTU_IGNORE_HWPOISON. - No users of TTU_MIGRATION ever set TTU_BATCH_FLUSH. TTU_SPLIT_FREEZE is a special case of migration used when splitting an anonymous page. This is most easily dealt with by calling the correct function from unmap_page() in mm/huge_memory.c - either try_to_migrate() for PageAnon or try_to_unmap(). Link: https://lkml.kernel.org/r/20210616105937.23201-5-apopple@nvidia.com Signed-off-by: Alistair Popple Reviewed-by: Christoph Hellwig Reviewed-by: Ralph Campbell Cc: Ben Skeggs Cc: Hugh Dickins Cc: Jason Gunthorpe Cc: John Hubbard Cc: "Matthew Wilcox (Oracle)" Cc: Peter Xu Cc: Shakeel Butt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rmap.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 69190efbd842..b0ea9d98302f 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -86,8 +86,6 @@ struct anon_vma_chain { }; enum ttu_flags { - TTU_MIGRATION = 0x1, /* migration mode */ - TTU_SPLIT_HUGE_PMD = 0x4, /* split huge PMD if any */ TTU_IGNORE_MLOCK = 0x8, /* ignore mlock */ TTU_SYNC = 0x10, /* avoid racy checks with PVMW_SYNC */ @@ -97,7 +95,6 @@ enum ttu_flags { * do a final flush if necessary */ TTU_RMAP_LOCKED = 0x80, /* do not grab rmap lock: * caller holds it */ - TTU_SPLIT_FREEZE = 0x100, /* freeze pte under splitting thp */ }; #ifdef CONFIG_MMU @@ -194,6 +191,7 @@ static inline void page_dup_rmap(struct page *page, bool compound) int page_referenced(struct page *, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags); +void try_to_migrate(struct page *page, enum ttu_flags flags); void try_to_unmap(struct page *, enum ttu_flags flags); /* Avoid racy checks */ -- cgit v1.2.3 From 6b49bf6ddbb0d7992c816846acfa5fd1cf751c36 Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Wed, 30 Jun 2021 18:54:19 -0700 Subject: mm: rename migrate_pgmap_owner MMU notifier ranges have a migrate_pgmap_owner field which is used by drivers to store a pointer. This is subsequently used by the driver callback to filter MMU_NOTIFY_MIGRATE events. Other notifier event types can also benefit from this filtering, so rename the 'migrate_pgmap_owner' field to 'owner' and create a new notifier initialisation function to initialise this field. Link: https://lkml.kernel.org/r/20210616105937.23201-6-apopple@nvidia.com Signed-off-by: Alistair Popple Suggested-by: Peter Xu Reviewed-by: Peter Xu Cc: Ben Skeggs Cc: Christoph Hellwig Cc: Hugh Dickins Cc: Jason Gunthorpe Cc: John Hubbard Cc: "Matthew Wilcox (Oracle)" Cc: Ralph Campbell Cc: Shakeel Butt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmu_notifier.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 1a6a9eb6d3fa..8e428eb813b8 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -41,7 +41,7 @@ struct mmu_interval_notifier; * * @MMU_NOTIFY_MIGRATE: used during migrate_vma_collect() invalidate to signal * a device driver to possibly ignore the invalidation if the - * migrate_pgmap_owner field matches the driver's device private pgmap owner. + * owner field matches the driver's device private pgmap owner. */ enum mmu_notifier_event { MMU_NOTIFY_UNMAP = 0, @@ -269,7 +269,7 @@ struct mmu_notifier_range { unsigned long end; unsigned flags; enum mmu_notifier_event event; - void *migrate_pgmap_owner; + void *owner; }; static inline int mm_has_notifiers(struct mm_struct *mm) @@ -521,14 +521,14 @@ static inline void mmu_notifier_range_init(struct mmu_notifier_range *range, range->flags = flags; } -static inline void mmu_notifier_range_init_migrate( - struct mmu_notifier_range *range, unsigned int flags, +static inline void mmu_notifier_range_init_owner( + struct mmu_notifier_range *range, + enum mmu_notifier_event event, unsigned int flags, struct vm_area_struct *vma, struct mm_struct *mm, - unsigned long start, unsigned long end, void *pgmap) + unsigned long start, unsigned long end, void *owner) { - mmu_notifier_range_init(range, MMU_NOTIFY_MIGRATE, flags, vma, mm, - start, end); - range->migrate_pgmap_owner = pgmap; + mmu_notifier_range_init(range, event, flags, vma, mm, start, end); + range->owner = owner; } #define ptep_clear_flush_young_notify(__vma, __address, __ptep) \ @@ -655,8 +655,8 @@ static inline void _mmu_notifier_range_init(struct mmu_notifier_range *range, #define mmu_notifier_range_init(range,event,flags,vma,mm,start,end) \ _mmu_notifier_range_init(range, start, end) -#define mmu_notifier_range_init_migrate(range, flags, vma, mm, start, end, \ - pgmap) \ +#define mmu_notifier_range_init_owner(range, event, flags, vma, mm, start, \ + end, owner) \ _mmu_notifier_range_init(range, start, end) static inline bool -- cgit v1.2.3 From b756a3b5e7ead8f6f4b03cea8ac22478ce04c8a8 Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Wed, 30 Jun 2021 18:54:25 -0700 Subject: mm: device exclusive memory access Some devices require exclusive write access to shared virtual memory (SVM) ranges to perform atomic operations on that memory. This requires CPU page tables to be updated to deny access whilst atomic operations are occurring. In order to do this introduce a new swap entry type (SWP_DEVICE_EXCLUSIVE). When a SVM range needs to be marked for exclusive access by a device all page table mappings for the particular range are replaced with device exclusive swap entries. This causes any CPU access to the page to result in a fault. Faults are resovled by replacing the faulting entry with the original mapping. This results in MMU notifiers being called which a driver uses to update access permissions such as revoking atomic access. After notifiers have been called the device will no longer have exclusive access to the region. Walking of the page tables to find the target pages is handled by get_user_pages() rather than a direct page table walk. A direct page table walk similar to what migrate_vma_collect()/unmap() does could also have been utilised. However this resulted in more code similar in functionality to what get_user_pages() provides as page faulting is required to make the PTEs present and to break COW. [dan.carpenter@oracle.com: fix signedness bug in make_device_exclusive_range()] Link: https://lkml.kernel.org/r/YNIz5NVnZ5GiZ3u1@mwanda Link: https://lkml.kernel.org/r/20210616105937.23201-8-apopple@nvidia.com Signed-off-by: Alistair Popple Signed-off-by: Dan Carpenter Reviewed-by: Christoph Hellwig Cc: Ben Skeggs Cc: Hugh Dickins Cc: Jason Gunthorpe Cc: John Hubbard Cc: "Matthew Wilcox (Oracle)" Cc: Peter Xu Cc: Ralph Campbell Cc: Shakeel Butt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmu_notifier.h | 6 ++++++ include/linux/rmap.h | 4 ++++ include/linux/swap.h | 9 +++++++-- include/linux/swapops.h | 44 +++++++++++++++++++++++++++++++++++++++++++- 4 files changed, 60 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 8e428eb813b8..6692da8d121d 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -42,6 +42,11 @@ struct mmu_interval_notifier; * @MMU_NOTIFY_MIGRATE: used during migrate_vma_collect() invalidate to signal * a device driver to possibly ignore the invalidation if the * owner field matches the driver's device private pgmap owner. + * + * @MMU_NOTIFY_EXCLUSIVE: to signal a device driver that the device will no + * longer have exclusive access to the page. When sent during creation of an + * exclusive range the owner will be initialised to the value provided by the + * caller of make_device_exclusive_range(), otherwise the owner will be NULL. */ enum mmu_notifier_event { MMU_NOTIFY_UNMAP = 0, @@ -51,6 +56,7 @@ enum mmu_notifier_event { MMU_NOTIFY_SOFT_DIRTY, MMU_NOTIFY_RELEASE, MMU_NOTIFY_MIGRATE, + MMU_NOTIFY_EXCLUSIVE, }; #define MMU_NOTIFIER_RANGE_BLOCKABLE (1 << 0) diff --git a/include/linux/rmap.h b/include/linux/rmap.h index b0ea9d98302f..83fb86133fe1 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -194,6 +194,10 @@ int page_referenced(struct page *, int is_locked, void try_to_migrate(struct page *page, enum ttu_flags flags); void try_to_unmap(struct page *, enum ttu_flags flags); +int make_device_exclusive_range(struct mm_struct *mm, unsigned long start, + unsigned long end, struct page **pages, + void *arg); + /* Avoid racy checks */ #define PVMW_SYNC (1 << 0) /* Look for migarion entries rather than present PTEs */ diff --git a/include/linux/swap.h b/include/linux/swap.h index df7cbb6b3d3e..6f5a43251593 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -62,12 +62,17 @@ static inline int current_is_kswapd(void) * migrate part of a process memory to device memory. * * When a page is migrated from CPU to device, we set the CPU page table entry - * to a special SWP_DEVICE_* entry. + * to a special SWP_DEVICE_{READ|WRITE} entry. + * + * When a page is mapped by the device for exclusive access we set the CPU page + * table entries to special SWP_DEVICE_EXCLUSIVE_* entries. */ #ifdef CONFIG_DEVICE_PRIVATE -#define SWP_DEVICE_NUM 2 +#define SWP_DEVICE_NUM 4 #define SWP_DEVICE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM) #define SWP_DEVICE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+1) +#define SWP_DEVICE_EXCLUSIVE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+2) +#define SWP_DEVICE_EXCLUSIVE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+3) #else #define SWP_DEVICE_NUM 0 #endif diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 04d76357aa0c..d356ab4047f7 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -127,6 +127,27 @@ static inline bool is_writable_device_private_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_DEVICE_WRITE); } + +static inline swp_entry_t make_readable_device_exclusive_entry(pgoff_t offset) +{ + return swp_entry(SWP_DEVICE_EXCLUSIVE_READ, offset); +} + +static inline swp_entry_t make_writable_device_exclusive_entry(pgoff_t offset) +{ + return swp_entry(SWP_DEVICE_EXCLUSIVE_WRITE, offset); +} + +static inline bool is_device_exclusive_entry(swp_entry_t entry) +{ + return swp_type(entry) == SWP_DEVICE_EXCLUSIVE_READ || + swp_type(entry) == SWP_DEVICE_EXCLUSIVE_WRITE; +} + +static inline bool is_writable_device_exclusive_entry(swp_entry_t entry) +{ + return unlikely(swp_type(entry) == SWP_DEVICE_EXCLUSIVE_WRITE); +} #else /* CONFIG_DEVICE_PRIVATE */ static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset) { @@ -147,6 +168,26 @@ static inline bool is_writable_device_private_entry(swp_entry_t entry) { return false; } + +static inline swp_entry_t make_readable_device_exclusive_entry(pgoff_t offset) +{ + return swp_entry(0, 0); +} + +static inline swp_entry_t make_writable_device_exclusive_entry(pgoff_t offset) +{ + return swp_entry(0, 0); +} + +static inline bool is_device_exclusive_entry(swp_entry_t entry) +{ + return false; +} + +static inline bool is_writable_device_exclusive_entry(swp_entry_t entry) +{ + return false; +} #endif /* CONFIG_DEVICE_PRIVATE */ #ifdef CONFIG_MIGRATION @@ -226,7 +267,8 @@ static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry) */ static inline bool is_pfn_swap_entry(swp_entry_t entry) { - return is_migration_entry(entry) || is_device_private_entry(entry); + return is_migration_entry(entry) || is_device_private_entry(entry) || + is_device_exclusive_entry(entry); } struct page_vma_mapped_walk; -- cgit v1.2.3 From 070c46505a265d54eba7f713760fa6ed984f2921 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 30 Jun 2021 18:54:56 -0700 Subject: drm: include only needed headers in ascii85.h The ascii85.h is user of exactly two headers, i.e. math.h and types.h. There is no need to carry on entire kernel.h. Link: https://lkml.kernel.org/r/20210611185915.44181-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Reviewed-by: Jani Nikula Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ascii85.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ascii85.h b/include/linux/ascii85.h index 4cc40201273e..83ad775ad0aa 100644 --- a/include/linux/ascii85.h +++ b/include/linux/ascii85.h @@ -8,7 +8,8 @@ #ifndef _ASCII85_H_ #define _ASCII85_H_ -#include +#include +#include #define ASCII85_BUFSZ 6 -- cgit v1.2.3 From f39650de687e35766572ac89dbcd16a5911e2f0a Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 30 Jun 2021 18:54:59 -0700 Subject: kernel.h: split out panic and oops helpers kernel.h is being used as a dump for all kinds of stuff for a long time. Here is the attempt to start cleaning it up by splitting out panic and oops helpers. There are several purposes of doing this: - dropping dependency in bug.h - dropping a loop by moving out panic_notifier.h - unload kernel.h from something which has its own domain At the same time convert users tree-wide to use new headers, although for the time being include new header back to kernel.h to avoid twisted indirected includes for existing users. [akpm@linux-foundation.org: thread_info.h needs limits.h] [andriy.shevchenko@linux.intel.com: ia64 fix] Link: https://lkml.kernel.org/r/20210520130557.55277-1-andriy.shevchenko@linux.intel.com Link: https://lkml.kernel.org/r/20210511074137.33666-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Reviewed-by: Bjorn Andersson Co-developed-by: Andrew Morton Acked-by: Mike Rapoport Acked-by: Corey Minyard Acked-by: Christian Brauner Acked-by: Arnd Bergmann Acked-by: Kees Cook Acked-by: Wei Liu Acked-by: Rasmus Villemoes Signed-off-by: Andrew Morton Acked-by: Sebastian Reichel Acked-by: Luis Chamberlain Acked-by: Stephen Boyd Acked-by: Thomas Bogendoerfer Acked-by: Helge Deller # parisc Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 84 +----------------------------------- include/linux/panic.h | 98 ++++++++++++++++++++++++++++++++++++++++++ include/linux/panic_notifier.h | 12 ++++++ include/linux/thread_info.h | 1 + 4 files changed, 112 insertions(+), 83 deletions(-) create mode 100644 include/linux/panic.h create mode 100644 include/linux/panic_notifier.h (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index bf950621febf..baea2eb763d0 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -72,7 +73,6 @@ #define lower_32_bits(n) ((u32)((n) & 0xffffffff)) struct completion; -struct pt_regs; struct user; #ifdef CONFIG_PREEMPT_VOLUNTARY @@ -177,14 +177,6 @@ void __might_fault(const char *file, int line); static inline void might_fault(void) { } #endif -extern struct atomic_notifier_head panic_notifier_list; -extern long (*panic_blink)(int state); -__printf(1, 2) -void panic(const char *fmt, ...) __noreturn __cold; -void nmi_panic(struct pt_regs *regs, const char *msg); -extern void oops_enter(void); -extern void oops_exit(void); -extern bool oops_may_print(void); void do_exit(long error_code) __noreturn; void complete_and_exit(struct completion *, long) __noreturn; @@ -372,52 +364,8 @@ extern int __kernel_text_address(unsigned long addr); extern int kernel_text_address(unsigned long addr); extern int func_ptr_is_kernel_text(void *ptr); -#ifdef CONFIG_SMP -extern unsigned int sysctl_oops_all_cpu_backtrace; -#else -#define sysctl_oops_all_cpu_backtrace 0 -#endif /* CONFIG_SMP */ - extern void bust_spinlocks(int yes); -extern int panic_timeout; -extern unsigned long panic_print; -extern int panic_on_oops; -extern int panic_on_unrecovered_nmi; -extern int panic_on_io_nmi; -extern int panic_on_warn; -extern unsigned long panic_on_taint; -extern bool panic_on_taint_nousertaint; -extern int sysctl_panic_on_rcu_stall; -extern int sysctl_max_rcu_stall_to_panic; -extern int sysctl_panic_on_stackoverflow; - -extern bool crash_kexec_post_notifiers; -/* - * panic_cpu is used for synchronizing panic() and crash_kexec() execution. It - * holds a CPU number which is executing panic() currently. A value of - * PANIC_CPU_INVALID means no CPU has entered panic() or crash_kexec(). - */ -extern atomic_t panic_cpu; -#define PANIC_CPU_INVALID -1 - -/* - * Only to be used by arch init code. If the user over-wrote the default - * CONFIG_PANIC_TIMEOUT, honor it. - */ -static inline void set_arch_panic_timeout(int timeout, int arch_default_timeout) -{ - if (panic_timeout == arch_default_timeout) - panic_timeout = timeout; -} -extern const char *print_tainted(void); -enum lockdep_ok { - LOCKDEP_STILL_OK, - LOCKDEP_NOW_UNRELIABLE -}; -extern void add_taint(unsigned flag, enum lockdep_ok); -extern int test_taint(unsigned flag); -extern unsigned long get_taint(void); extern int root_mountflags; extern bool early_boot_irqs_disabled; @@ -436,36 +384,6 @@ extern enum system_states { SYSTEM_SUSPEND, } system_state; -/* This cannot be an enum because some may be used in assembly source. */ -#define TAINT_PROPRIETARY_MODULE 0 -#define TAINT_FORCED_MODULE 1 -#define TAINT_CPU_OUT_OF_SPEC 2 -#define TAINT_FORCED_RMMOD 3 -#define TAINT_MACHINE_CHECK 4 -#define TAINT_BAD_PAGE 5 -#define TAINT_USER 6 -#define TAINT_DIE 7 -#define TAINT_OVERRIDDEN_ACPI_TABLE 8 -#define TAINT_WARN 9 -#define TAINT_CRAP 10 -#define TAINT_FIRMWARE_WORKAROUND 11 -#define TAINT_OOT_MODULE 12 -#define TAINT_UNSIGNED_MODULE 13 -#define TAINT_SOFTLOCKUP 14 -#define TAINT_LIVEPATCH 15 -#define TAINT_AUX 16 -#define TAINT_RANDSTRUCT 17 -#define TAINT_FLAGS_COUNT 18 -#define TAINT_FLAGS_MAX ((1UL << TAINT_FLAGS_COUNT) - 1) - -struct taint_flag { - char c_true; /* character printed when tainted */ - char c_false; /* character printed when not tainted */ - bool module; /* also show as a per-module taint flag */ -}; - -extern const struct taint_flag taint_flags[TAINT_FLAGS_COUNT]; - extern const char hex_asc[]; #define hex_asc_lo(x) hex_asc[((x) & 0x0f)] #define hex_asc_hi(x) hex_asc[((x) & 0xf0) >> 4] diff --git a/include/linux/panic.h b/include/linux/panic.h new file mode 100644 index 000000000000..f5844908a089 --- /dev/null +++ b/include/linux/panic.h @@ -0,0 +1,98 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_PANIC_H +#define _LINUX_PANIC_H + +#include +#include + +struct pt_regs; + +extern long (*panic_blink)(int state); +__printf(1, 2) +void panic(const char *fmt, ...) __noreturn __cold; +void nmi_panic(struct pt_regs *regs, const char *msg); +extern void oops_enter(void); +extern void oops_exit(void); +extern bool oops_may_print(void); + +#ifdef CONFIG_SMP +extern unsigned int sysctl_oops_all_cpu_backtrace; +#else +#define sysctl_oops_all_cpu_backtrace 0 +#endif /* CONFIG_SMP */ + +extern int panic_timeout; +extern unsigned long panic_print; +extern int panic_on_oops; +extern int panic_on_unrecovered_nmi; +extern int panic_on_io_nmi; +extern int panic_on_warn; + +extern unsigned long panic_on_taint; +extern bool panic_on_taint_nousertaint; + +extern int sysctl_panic_on_rcu_stall; +extern int sysctl_max_rcu_stall_to_panic; +extern int sysctl_panic_on_stackoverflow; + +extern bool crash_kexec_post_notifiers; + +/* + * panic_cpu is used for synchronizing panic() and crash_kexec() execution. It + * holds a CPU number which is executing panic() currently. A value of + * PANIC_CPU_INVALID means no CPU has entered panic() or crash_kexec(). + */ +extern atomic_t panic_cpu; +#define PANIC_CPU_INVALID -1 + +/* + * Only to be used by arch init code. If the user over-wrote the default + * CONFIG_PANIC_TIMEOUT, honor it. + */ +static inline void set_arch_panic_timeout(int timeout, int arch_default_timeout) +{ + if (panic_timeout == arch_default_timeout) + panic_timeout = timeout; +} + +/* This cannot be an enum because some may be used in assembly source. */ +#define TAINT_PROPRIETARY_MODULE 0 +#define TAINT_FORCED_MODULE 1 +#define TAINT_CPU_OUT_OF_SPEC 2 +#define TAINT_FORCED_RMMOD 3 +#define TAINT_MACHINE_CHECK 4 +#define TAINT_BAD_PAGE 5 +#define TAINT_USER 6 +#define TAINT_DIE 7 +#define TAINT_OVERRIDDEN_ACPI_TABLE 8 +#define TAINT_WARN 9 +#define TAINT_CRAP 10 +#define TAINT_FIRMWARE_WORKAROUND 11 +#define TAINT_OOT_MODULE 12 +#define TAINT_UNSIGNED_MODULE 13 +#define TAINT_SOFTLOCKUP 14 +#define TAINT_LIVEPATCH 15 +#define TAINT_AUX 16 +#define TAINT_RANDSTRUCT 17 +#define TAINT_FLAGS_COUNT 18 +#define TAINT_FLAGS_MAX ((1UL << TAINT_FLAGS_COUNT) - 1) + +struct taint_flag { + char c_true; /* character printed when tainted */ + char c_false; /* character printed when not tainted */ + bool module; /* also show as a per-module taint flag */ +}; + +extern const struct taint_flag taint_flags[TAINT_FLAGS_COUNT]; + +enum lockdep_ok { + LOCKDEP_STILL_OK, + LOCKDEP_NOW_UNRELIABLE, +}; + +extern const char *print_tainted(void); +extern void add_taint(unsigned flag, enum lockdep_ok); +extern int test_taint(unsigned flag); +extern unsigned long get_taint(void); + +#endif /* _LINUX_PANIC_H */ diff --git a/include/linux/panic_notifier.h b/include/linux/panic_notifier.h new file mode 100644 index 000000000000..41e32483d7a7 --- /dev/null +++ b/include/linux/panic_notifier.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_PANIC_NOTIFIERS_H +#define _LINUX_PANIC_NOTIFIERS_H + +#include +#include + +extern struct atomic_notifier_head panic_notifier_list; + +extern bool crash_kexec_post_notifiers; + +#endif /* _LINUX_PANIC_NOTIFIERS_H */ diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index 157762db9d4b..0999f6317978 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -9,6 +9,7 @@ #define _LINUX_THREAD_INFO_H #include +#include #include #include #include -- cgit v1.2.3 From 994b69703e86ed0ab2228fc606761a3b08d48af3 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 30 Jun 2021 18:55:05 -0700 Subject: lib/string_helpers: switch to use BIT() macro Patch series "lib/string_helpers: get rid of ugly *_escape_mem_ascii()", v3. Get rid of ugly *_escape_mem_ascii() API since it's not flexible and has the only single user. Provide better approach based on usage of the string_escape_mem() with appropriate flags. Test cases has been expanded accordingly to cover new functionality. This patch (of 15): Switch to use BIT() macro for flag definitions. No changes implied. Link: https://lkml.kernel.org/r/20210504180819.73127-1-andriy.shevchenko@linux.intel.com Link: https://lkml.kernel.org/r/20210504180819.73127-2-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Cc: "J. Bruce Fields" Cc: Chuck Lever Cc: Alexander Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/string_helpers.h | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h index fa06dcdc481e..bf01e24edd89 100644 --- a/include/linux/string_helpers.h +++ b/include/linux/string_helpers.h @@ -2,6 +2,7 @@ #ifndef _LINUX_STRING_HELPERS_H_ #define _LINUX_STRING_HELPERS_H_ +#include #include #include @@ -18,10 +19,10 @@ enum string_size_units { void string_get_size(u64 size, u64 blk_size, enum string_size_units units, char *buf, int len); -#define UNESCAPE_SPACE 0x01 -#define UNESCAPE_OCTAL 0x02 -#define UNESCAPE_HEX 0x04 -#define UNESCAPE_SPECIAL 0x08 +#define UNESCAPE_SPACE BIT(0) +#define UNESCAPE_OCTAL BIT(1) +#define UNESCAPE_HEX BIT(2) +#define UNESCAPE_SPECIAL BIT(3) #define UNESCAPE_ANY \ (UNESCAPE_SPACE | UNESCAPE_OCTAL | UNESCAPE_HEX | UNESCAPE_SPECIAL) @@ -42,15 +43,15 @@ static inline int string_unescape_any_inplace(char *buf) return string_unescape_any(buf, buf, 0); } -#define ESCAPE_SPACE 0x01 -#define ESCAPE_SPECIAL 0x02 -#define ESCAPE_NULL 0x04 -#define ESCAPE_OCTAL 0x08 +#define ESCAPE_SPACE BIT(0) +#define ESCAPE_SPECIAL BIT(1) +#define ESCAPE_NULL BIT(2) +#define ESCAPE_OCTAL BIT(3) #define ESCAPE_ANY \ (ESCAPE_SPACE | ESCAPE_OCTAL | ESCAPE_SPECIAL | ESCAPE_NULL) -#define ESCAPE_NP 0x10 +#define ESCAPE_NP BIT(4) #define ESCAPE_ANY_NP (ESCAPE_ANY | ESCAPE_NP) -#define ESCAPE_HEX 0x20 +#define ESCAPE_HEX BIT(5) int string_escape_mem(const char *src, size_t isz, char *dst, size_t osz, unsigned int flags, const char *only); -- cgit v1.2.3 From a0809783355cfe1cc1b2fa7f881c3a79df0b2a27 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 30 Jun 2021 18:55:14 -0700 Subject: lib/string_helpers: introduce ESCAPE_NA for escaping non-ASCII Some users may want to have an ASCII based filter, provided by isascii() function. Here is the addition of a such. Link: https://lkml.kernel.org/r/20210504180819.73127-5-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Cc: Alexander Viro Cc: Chuck Lever Cc: "J. Bruce Fields" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/string_helpers.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h index bf01e24edd89..d6cf6fe10f74 100644 --- a/include/linux/string_helpers.h +++ b/include/linux/string_helpers.h @@ -52,6 +52,7 @@ static inline int string_unescape_any_inplace(char *buf) #define ESCAPE_NP BIT(4) #define ESCAPE_ANY_NP (ESCAPE_ANY | ESCAPE_NP) #define ESCAPE_HEX BIT(5) +#define ESCAPE_NA BIT(6) int string_escape_mem(const char *src, size_t isz, char *dst, size_t osz, unsigned int flags, const char *only); -- cgit v1.2.3 From 0362c27fb373ea04eace9e7a70e61036ab81f09f Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 30 Jun 2021 18:55:17 -0700 Subject: lib/string_helpers: introduce ESCAPE_NAP to escape non-ASCII and non-printable Some users may want to have an ASCII based filter for printable only characters, provided by conjunction of isascii() and isprint() functions. Here is the addition of a such. Link: https://lkml.kernel.org/r/20210504180819.73127-6-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Cc: Alexander Viro Cc: Chuck Lever Cc: "J. Bruce Fields" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/string_helpers.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h index d6cf6fe10f74..811c6a627620 100644 --- a/include/linux/string_helpers.h +++ b/include/linux/string_helpers.h @@ -53,6 +53,7 @@ static inline int string_unescape_any_inplace(char *buf) #define ESCAPE_ANY_NP (ESCAPE_ANY | ESCAPE_NP) #define ESCAPE_HEX BIT(5) #define ESCAPE_NA BIT(6) +#define ESCAPE_NAP BIT(7) int string_escape_mem(const char *src, size_t isz, char *dst, size_t osz, unsigned int flags, const char *only); -- cgit v1.2.3 From aec0d0966f20d131cc4ff6927b02d448a478a6d4 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 30 Jun 2021 18:55:20 -0700 Subject: lib/string_helpers: allow to append additional characters to be escaped Introduce a new flag to append additional characters, passed in 'only' parameter, to be escaped if they fall in the corresponding class. Link: https://lkml.kernel.org/r/20210504180819.73127-7-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Cc: Alexander Viro Cc: Chuck Lever Cc: "J. Bruce Fields" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/string_helpers.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h index 811c6a627620..f8728ed4d563 100644 --- a/include/linux/string_helpers.h +++ b/include/linux/string_helpers.h @@ -54,6 +54,7 @@ static inline int string_unescape_any_inplace(char *buf) #define ESCAPE_HEX BIT(5) #define ESCAPE_NA BIT(6) #define ESCAPE_NAP BIT(7) +#define ESCAPE_APPEND BIT(8) int string_escape_mem(const char *src, size_t isz, char *dst, size_t osz, unsigned int flags, const char *only); -- cgit v1.2.3 From 259fa5d7d825122c30ad4122c6a1cc937eb74c2d Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 30 Jun 2021 18:55:29 -0700 Subject: lib/test-string_helpers: add test cases for new features We have got new flags and hence new features of string_escape_mem(). Add test cases for that. Link: https://lkml.kernel.org/r/20210504180819.73127-10-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Cc: Alexander Viro Cc: Chuck Lever Cc: "J. Bruce Fields" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/string_helpers.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h index f8728ed4d563..9b0eca2badf2 100644 --- a/include/linux/string_helpers.h +++ b/include/linux/string_helpers.h @@ -26,6 +26,8 @@ void string_get_size(u64 size, u64 blk_size, enum string_size_units units, #define UNESCAPE_ANY \ (UNESCAPE_SPACE | UNESCAPE_OCTAL | UNESCAPE_HEX | UNESCAPE_SPECIAL) +#define UNESCAPE_ALL_MASK GENMASK(3, 0) + int string_unescape(char *src, char *dst, size_t size, unsigned int flags); static inline int string_unescape_inplace(char *buf, unsigned int flags) @@ -56,6 +58,8 @@ static inline int string_unescape_any_inplace(char *buf) #define ESCAPE_NAP BIT(7) #define ESCAPE_APPEND BIT(8) +#define ESCAPE_ALL_MASK GENMASK(8, 0) + int string_escape_mem(const char *src, size_t isz, char *dst, size_t osz, unsigned int flags, const char *only); -- cgit v1.2.3 From 1d31aa172a4e6728918a06ee7f1d6bcb7507172c Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 30 Jun 2021 18:55:34 -0700 Subject: seq_file: introduce seq_escape_mem() Introduce seq_escape_mem() to allow users to pass additional parameters to string_escape_mem(). Link: https://lkml.kernel.org/r/20210504180819.73127-12-andriy.shevchenko@linux.intel.com Suggested-by: Al Viro Signed-off-by: Andy Shevchenko Cc: Chuck Lever Cc: "J. Bruce Fields" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/seq_file.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 723b1fa1177e..6de442182784 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -126,6 +126,8 @@ void seq_put_decimal_ll(struct seq_file *m, const char *delimiter, long long num void seq_put_hex_ll(struct seq_file *m, const char *delimiter, unsigned long long v, unsigned int width); +void seq_escape_mem(struct seq_file *m, const char *src, size_t len, + unsigned int flags, const char *esc); void seq_escape(struct seq_file *m, const char *s, const char *esc); void seq_escape_mem_ascii(struct seq_file *m, const char *src, size_t isz); -- cgit v1.2.3 From e7ed4a3b922b04d2042cd2e19d1096fa457b6c11 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 30 Jun 2021 18:55:37 -0700 Subject: seq_file: add seq_escape_str() as replica of string_escape_str() In some cases we want to escape characters from NULL-terminated strings. Add seq_escape_str() as replica of string_escape_str() for that. Link: https://lkml.kernel.org/r/20210504180819.73127-13-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Cc: Alexander Viro Cc: Chuck Lever Cc: "J. Bruce Fields" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/seq_file.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 6de442182784..63f021cb1b12 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -128,6 +128,13 @@ void seq_put_hex_ll(struct seq_file *m, const char *delimiter, void seq_escape_mem(struct seq_file *m, const char *src, size_t len, unsigned int flags, const char *esc); + +static inline void seq_escape_str(struct seq_file *m, const char *src, + unsigned int flags, const char *esc) +{ + seq_escape_mem(m, src, strlen(src), flags, esc); +} + void seq_escape(struct seq_file *m, const char *s, const char *esc); void seq_escape_mem_ascii(struct seq_file *m, const char *src, size_t isz); -- cgit v1.2.3 From cc72181a65990193f54284417efa01d4580014e6 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 30 Jun 2021 18:55:46 -0700 Subject: seq_file: drop unused *_escape_mem_ascii() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are no more users of the seq_escape_mem_ascii() followed by string_escape_mem_ascii(). Remove them for good. Link: https://lkml.kernel.org/r/20210504180819.73127-16-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Cc: Alexander Viro Cc: Chuck Lever Cc: "J. Bruce Fields" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/seq_file.h | 1 - include/linux/string_helpers.h | 3 --- 2 files changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 63f021cb1b12..dd99569595fd 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -136,7 +136,6 @@ static inline void seq_escape_str(struct seq_file *m, const char *src, } void seq_escape(struct seq_file *m, const char *s, const char *esc); -void seq_escape_mem_ascii(struct seq_file *m, const char *src, size_t isz); void seq_hex_dump(struct seq_file *m, const char *prefix_str, int prefix_type, int rowsize, int groupsize, const void *buf, size_t len, diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h index 9b0eca2badf2..68189c4a2eb1 100644 --- a/include/linux/string_helpers.h +++ b/include/linux/string_helpers.h @@ -63,9 +63,6 @@ static inline int string_unescape_any_inplace(char *buf) int string_escape_mem(const char *src, size_t isz, char *dst, size_t osz, unsigned int flags, const char *only); -int string_escape_mem_ascii(const char *src, size_t isz, char *dst, - size_t osz); - static inline int string_escape_mem_any_np(const char *src, size_t isz, char *dst, size_t osz, const char *only) { -- cgit v1.2.3 From 478485f6c0e5936b62c0c9393a865bfb00f037a5 Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Wed, 30 Jun 2021 18:55:58 -0700 Subject: lib/mpi: fix spelling mistakes Fix some spelling mistakes in comments: flaged ==> flagged bufer ==> buffer multipler ==> multiplier MULTIPLER ==> MULTIPLIER leaset ==> least chnage ==> change Link: https://lkml.kernel.org/r/20210604074401.12198-1-thunder.leizhen@huawei.com Signed-off-by: Zhen Lei Cc: Herbert Xu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mpi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mpi.h b/include/linux/mpi.h index 3e5358f4de2f..eb0d1c1db208 100644 --- a/include/linux/mpi.h +++ b/include/linux/mpi.h @@ -200,7 +200,7 @@ struct mpi_ec_ctx { unsigned int nbits; /* Number of bits. */ /* Domain parameters. Note that they may not all be set and if set - * the MPIs may be flaged as constant. + * the MPIs may be flagged as constant. */ MPI p; /* Prime specifying the field GF(p). */ MPI a; /* First coefficient of the Weierstrass equation. */ @@ -267,7 +267,7 @@ int mpi_ec_curve_point(MPI_POINT point, struct mpi_ec_ctx *ctx); /** * mpi_get_size() - returns max size required to store the number * - * @a: A multi precision integer for which we want to allocate a bufer + * @a: A multi precision integer for which we want to allocate a buffer * * Return: size required to store the number */ -- cgit v1.2.3 From 4c52729377eab025b238caeed48994a39c3b73f2 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 30 Jun 2021 18:56:10 -0700 Subject: kernel.h: split out kstrtox() and simple_strtox() to a separate header kernel.h is being used as a dump for all kinds of stuff for a long time. Here is the attempt to start cleaning it up by splitting out kstrtox() and simple_strtox() helpers. At the same time convert users in header and lib folders to use new header. Though for time being include new header back to kernel.h to avoid twisted indirected includes for existing users. [andy.shevchenko@gmail.com: fix documentation references] Link: https://lkml.kernel.org/r/20210615220003.377901-1-andy.shevchenko@gmail.com Link: https://lkml.kernel.org/r/20210611185815.44103-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Acked-by: Jonathan Cameron Cc: Francis Laniel Cc: Randy Dunlap Cc: Kars Mulder Cc: Trond Myklebust Cc: Anna Schumaker Cc: "J. Bruce Fields" Cc: Chuck Lever Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 143 +-------------------------------------- include/linux/kstrtox.h | 155 +++++++++++++++++++++++++++++++++++++++++++ include/linux/string.h | 7 -- include/linux/sunrpc/cache.h | 1 + 4 files changed, 157 insertions(+), 149 deletions(-) create mode 100644 include/linux/kstrtox.h (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index baea2eb763d0..7bb0a5cb7d57 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -180,148 +181,6 @@ static inline void might_fault(void) { } void do_exit(long error_code) __noreturn; void complete_and_exit(struct completion *, long) __noreturn; -/* Internal, do not use. */ -int __must_check _kstrtoul(const char *s, unsigned int base, unsigned long *res); -int __must_check _kstrtol(const char *s, unsigned int base, long *res); - -int __must_check kstrtoull(const char *s, unsigned int base, unsigned long long *res); -int __must_check kstrtoll(const char *s, unsigned int base, long long *res); - -/** - * kstrtoul - convert a string to an unsigned long - * @s: The start of the string. The string must be null-terminated, and may also - * include a single newline before its terminating null. The first character - * may also be a plus sign, but not a minus sign. - * @base: The number base to use. The maximum supported base is 16. If base is - * given as 0, then the base of the string is automatically detected with the - * conventional semantics - If it begins with 0x the number will be parsed as a - * hexadecimal (case insensitive), if it otherwise begins with 0, it will be - * parsed as an octal number. Otherwise it will be parsed as a decimal. - * @res: Where to write the result of the conversion on success. - * - * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. - * Preferred over simple_strtoul(). Return code must be checked. -*/ -static inline int __must_check kstrtoul(const char *s, unsigned int base, unsigned long *res) -{ - /* - * We want to shortcut function call, but - * __builtin_types_compatible_p(unsigned long, unsigned long long) = 0. - */ - if (sizeof(unsigned long) == sizeof(unsigned long long) && - __alignof__(unsigned long) == __alignof__(unsigned long long)) - return kstrtoull(s, base, (unsigned long long *)res); - else - return _kstrtoul(s, base, res); -} - -/** - * kstrtol - convert a string to a long - * @s: The start of the string. The string must be null-terminated, and may also - * include a single newline before its terminating null. The first character - * may also be a plus sign or a minus sign. - * @base: The number base to use. The maximum supported base is 16. If base is - * given as 0, then the base of the string is automatically detected with the - * conventional semantics - If it begins with 0x the number will be parsed as a - * hexadecimal (case insensitive), if it otherwise begins with 0, it will be - * parsed as an octal number. Otherwise it will be parsed as a decimal. - * @res: Where to write the result of the conversion on success. - * - * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. - * Preferred over simple_strtol(). Return code must be checked. - */ -static inline int __must_check kstrtol(const char *s, unsigned int base, long *res) -{ - /* - * We want to shortcut function call, but - * __builtin_types_compatible_p(long, long long) = 0. - */ - if (sizeof(long) == sizeof(long long) && - __alignof__(long) == __alignof__(long long)) - return kstrtoll(s, base, (long long *)res); - else - return _kstrtol(s, base, res); -} - -int __must_check kstrtouint(const char *s, unsigned int base, unsigned int *res); -int __must_check kstrtoint(const char *s, unsigned int base, int *res); - -static inline int __must_check kstrtou64(const char *s, unsigned int base, u64 *res) -{ - return kstrtoull(s, base, res); -} - -static inline int __must_check kstrtos64(const char *s, unsigned int base, s64 *res) -{ - return kstrtoll(s, base, res); -} - -static inline int __must_check kstrtou32(const char *s, unsigned int base, u32 *res) -{ - return kstrtouint(s, base, res); -} - -static inline int __must_check kstrtos32(const char *s, unsigned int base, s32 *res) -{ - return kstrtoint(s, base, res); -} - -int __must_check kstrtou16(const char *s, unsigned int base, u16 *res); -int __must_check kstrtos16(const char *s, unsigned int base, s16 *res); -int __must_check kstrtou8(const char *s, unsigned int base, u8 *res); -int __must_check kstrtos8(const char *s, unsigned int base, s8 *res); -int __must_check kstrtobool(const char *s, bool *res); - -int __must_check kstrtoull_from_user(const char __user *s, size_t count, unsigned int base, unsigned long long *res); -int __must_check kstrtoll_from_user(const char __user *s, size_t count, unsigned int base, long long *res); -int __must_check kstrtoul_from_user(const char __user *s, size_t count, unsigned int base, unsigned long *res); -int __must_check kstrtol_from_user(const char __user *s, size_t count, unsigned int base, long *res); -int __must_check kstrtouint_from_user(const char __user *s, size_t count, unsigned int base, unsigned int *res); -int __must_check kstrtoint_from_user(const char __user *s, size_t count, unsigned int base, int *res); -int __must_check kstrtou16_from_user(const char __user *s, size_t count, unsigned int base, u16 *res); -int __must_check kstrtos16_from_user(const char __user *s, size_t count, unsigned int base, s16 *res); -int __must_check kstrtou8_from_user(const char __user *s, size_t count, unsigned int base, u8 *res); -int __must_check kstrtos8_from_user(const char __user *s, size_t count, unsigned int base, s8 *res); -int __must_check kstrtobool_from_user(const char __user *s, size_t count, bool *res); - -static inline int __must_check kstrtou64_from_user(const char __user *s, size_t count, unsigned int base, u64 *res) -{ - return kstrtoull_from_user(s, count, base, res); -} - -static inline int __must_check kstrtos64_from_user(const char __user *s, size_t count, unsigned int base, s64 *res) -{ - return kstrtoll_from_user(s, count, base, res); -} - -static inline int __must_check kstrtou32_from_user(const char __user *s, size_t count, unsigned int base, u32 *res) -{ - return kstrtouint_from_user(s, count, base, res); -} - -static inline int __must_check kstrtos32_from_user(const char __user *s, size_t count, unsigned int base, s32 *res) -{ - return kstrtoint_from_user(s, count, base, res); -} - -/* - * Use kstrto instead. - * - * NOTE: simple_strto does not check for the range overflow and, - * depending on the input, may give interesting results. - * - * Use these functions if and only if you cannot use kstrto, because - * the conversion ends on the first non-digit character, which may be far - * beyond the supported range. It might be useful to parse the strings like - * 10x50 or 12:21 without altering original string or temporary buffer in use. - * Keep in mind above caveat. - */ - -extern unsigned long simple_strtoul(const char *,char **,unsigned int); -extern long simple_strtol(const char *,char **,unsigned int); -extern unsigned long long simple_strtoull(const char *,char **,unsigned int); -extern long long simple_strtoll(const char *,char **,unsigned int); - extern int num_to_str(char *buf, int size, unsigned long long num, unsigned int width); diff --git a/include/linux/kstrtox.h b/include/linux/kstrtox.h new file mode 100644 index 000000000000..529974e22ea7 --- /dev/null +++ b/include/linux/kstrtox.h @@ -0,0 +1,155 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_KSTRTOX_H +#define _LINUX_KSTRTOX_H + +#include +#include + +/* Internal, do not use. */ +int __must_check _kstrtoul(const char *s, unsigned int base, unsigned long *res); +int __must_check _kstrtol(const char *s, unsigned int base, long *res); + +int __must_check kstrtoull(const char *s, unsigned int base, unsigned long long *res); +int __must_check kstrtoll(const char *s, unsigned int base, long long *res); + +/** + * kstrtoul - convert a string to an unsigned long + * @s: The start of the string. The string must be null-terminated, and may also + * include a single newline before its terminating null. The first character + * may also be a plus sign, but not a minus sign. + * @base: The number base to use. The maximum supported base is 16. If base is + * given as 0, then the base of the string is automatically detected with the + * conventional semantics - If it begins with 0x the number will be parsed as a + * hexadecimal (case insensitive), if it otherwise begins with 0, it will be + * parsed as an octal number. Otherwise it will be parsed as a decimal. + * @res: Where to write the result of the conversion on success. + * + * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. + * Preferred over simple_strtoul(). Return code must be checked. +*/ +static inline int __must_check kstrtoul(const char *s, unsigned int base, unsigned long *res) +{ + /* + * We want to shortcut function call, but + * __builtin_types_compatible_p(unsigned long, unsigned long long) = 0. + */ + if (sizeof(unsigned long) == sizeof(unsigned long long) && + __alignof__(unsigned long) == __alignof__(unsigned long long)) + return kstrtoull(s, base, (unsigned long long *)res); + else + return _kstrtoul(s, base, res); +} + +/** + * kstrtol - convert a string to a long + * @s: The start of the string. The string must be null-terminated, and may also + * include a single newline before its terminating null. The first character + * may also be a plus sign or a minus sign. + * @base: The number base to use. The maximum supported base is 16. If base is + * given as 0, then the base of the string is automatically detected with the + * conventional semantics - If it begins with 0x the number will be parsed as a + * hexadecimal (case insensitive), if it otherwise begins with 0, it will be + * parsed as an octal number. Otherwise it will be parsed as a decimal. + * @res: Where to write the result of the conversion on success. + * + * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. + * Preferred over simple_strtol(). Return code must be checked. + */ +static inline int __must_check kstrtol(const char *s, unsigned int base, long *res) +{ + /* + * We want to shortcut function call, but + * __builtin_types_compatible_p(long, long long) = 0. + */ + if (sizeof(long) == sizeof(long long) && + __alignof__(long) == __alignof__(long long)) + return kstrtoll(s, base, (long long *)res); + else + return _kstrtol(s, base, res); +} + +int __must_check kstrtouint(const char *s, unsigned int base, unsigned int *res); +int __must_check kstrtoint(const char *s, unsigned int base, int *res); + +static inline int __must_check kstrtou64(const char *s, unsigned int base, u64 *res) +{ + return kstrtoull(s, base, res); +} + +static inline int __must_check kstrtos64(const char *s, unsigned int base, s64 *res) +{ + return kstrtoll(s, base, res); +} + +static inline int __must_check kstrtou32(const char *s, unsigned int base, u32 *res) +{ + return kstrtouint(s, base, res); +} + +static inline int __must_check kstrtos32(const char *s, unsigned int base, s32 *res) +{ + return kstrtoint(s, base, res); +} + +int __must_check kstrtou16(const char *s, unsigned int base, u16 *res); +int __must_check kstrtos16(const char *s, unsigned int base, s16 *res); +int __must_check kstrtou8(const char *s, unsigned int base, u8 *res); +int __must_check kstrtos8(const char *s, unsigned int base, s8 *res); +int __must_check kstrtobool(const char *s, bool *res); + +int __must_check kstrtoull_from_user(const char __user *s, size_t count, unsigned int base, unsigned long long *res); +int __must_check kstrtoll_from_user(const char __user *s, size_t count, unsigned int base, long long *res); +int __must_check kstrtoul_from_user(const char __user *s, size_t count, unsigned int base, unsigned long *res); +int __must_check kstrtol_from_user(const char __user *s, size_t count, unsigned int base, long *res); +int __must_check kstrtouint_from_user(const char __user *s, size_t count, unsigned int base, unsigned int *res); +int __must_check kstrtoint_from_user(const char __user *s, size_t count, unsigned int base, int *res); +int __must_check kstrtou16_from_user(const char __user *s, size_t count, unsigned int base, u16 *res); +int __must_check kstrtos16_from_user(const char __user *s, size_t count, unsigned int base, s16 *res); +int __must_check kstrtou8_from_user(const char __user *s, size_t count, unsigned int base, u8 *res); +int __must_check kstrtos8_from_user(const char __user *s, size_t count, unsigned int base, s8 *res); +int __must_check kstrtobool_from_user(const char __user *s, size_t count, bool *res); + +static inline int __must_check kstrtou64_from_user(const char __user *s, size_t count, unsigned int base, u64 *res) +{ + return kstrtoull_from_user(s, count, base, res); +} + +static inline int __must_check kstrtos64_from_user(const char __user *s, size_t count, unsigned int base, s64 *res) +{ + return kstrtoll_from_user(s, count, base, res); +} + +static inline int __must_check kstrtou32_from_user(const char __user *s, size_t count, unsigned int base, u32 *res) +{ + return kstrtouint_from_user(s, count, base, res); +} + +static inline int __must_check kstrtos32_from_user(const char __user *s, size_t count, unsigned int base, s32 *res) +{ + return kstrtoint_from_user(s, count, base, res); +} + +/* + * Use kstrto instead. + * + * NOTE: simple_strto does not check for the range overflow and, + * depending on the input, may give interesting results. + * + * Use these functions if and only if you cannot use kstrto, because + * the conversion ends on the first non-digit character, which may be far + * beyond the supported range. It might be useful to parse the strings like + * 10x50 or 12:21 without altering original string or temporary buffer in use. + * Keep in mind above caveat. + */ + +extern unsigned long simple_strtoul(const char *,char **,unsigned int); +extern long simple_strtol(const char *,char **,unsigned int); +extern unsigned long long simple_strtoull(const char *,char **,unsigned int); +extern long long simple_strtoll(const char *,char **,unsigned int); + +static inline int strtobool(const char *s, bool *res) +{ + return kstrtobool(s, res); +} + +#endif /* _LINUX_KSTRTOX_H */ diff --git a/include/linux/string.h b/include/linux/string.h index 9521d8cab18e..b48d2d28e0b1 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -2,7 +2,6 @@ #ifndef _LINUX_STRING_H_ #define _LINUX_STRING_H_ - #include /* for inline */ #include /* for size_t */ #include /* for NULL */ @@ -184,12 +183,6 @@ extern char **argv_split(gfp_t gfp, const char *str, int *argcp); extern void argv_free(char **argv); extern bool sysfs_streq(const char *s1, const char *s2); -extern int kstrtobool(const char *s, bool *res); -static inline int strtobool(const char *s, bool *res) -{ - return kstrtobool(s, res); -} - int match_string(const char * const *array, size_t n, const char *string); int __sysfs_match_string(const char * const *array, size_t n, const char *s); diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index d0965e2997b0..b134b2b3371c 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -14,6 +14,7 @@ #include #include #include +#include #include /* -- cgit v1.2.3 From 66ce75144d4b33e376f187df3dec495fe47d2ad0 Mon Sep 17 00:00:00 2001 From: Barry Song Date: Wed, 30 Jun 2021 18:56:31 -0700 Subject: kprobes: remove duplicated strong free_insn_page in x86 and s390 free_insn_page() in x86 and s390 is same with the common weak function in kernel/kprobes.c. Plus, the comment "Recover page to RW mode before releasing it" in x86 seems insensible to be there since resetting mapping is done by common code in vfree() of module_memfree(). So drop these two duplicated strong functions and related comment, then mark the common one in kernel/kprobes.c strong. Link: https://lkml.kernel.org/r/20210608065736.32656-1-song.bao.hua@hisilicon.com Signed-off-by: Barry Song Acked-by: Masami Hiramatsu Acked-by: Heiko Carstens Reviewed-by: Christoph Hellwig Cc: "H. Peter Anvin" Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Vasily Gorbik Cc: Christian Borntraeger Cc: "Naveen N. Rao" Cc: Anil S Keshavamurthy Cc: David S. Miller Cc: Qi Liu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kprobes.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 1883a4a9f16a..c98a35a75f40 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -407,7 +407,6 @@ int enable_kprobe(struct kprobe *kp); void dump_kprobe(struct kprobe *kp); void *alloc_insn_page(void); -void free_insn_page(void *page); int kprobe_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym); -- cgit v1.2.3 From 97c885d585c53d3f1ad4545b0ee10f0bdfaa1a4d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 30 Jun 2021 18:56:43 -0700 Subject: x86: signal: don't do sas_ss_reset() until we are certain that sigframe won't be abandoned Currently we handle SS_AUTODISARM as soon as we have stored the altstack settings into sigframe - that's the point when we have set the things up for eventual sigreturn to restore the old settings. And if we manage to set the sigframe up (we are not done with that yet), everything's fine. However, in case of failure we end up with sigframe-to-be abandoned and SIGSEGV force-delivered. And in that case we end up with inconsistent rules - late failures have altstack reset, early ones do not. It's trivial to get consistent behaviour - just handle SS_AUTODISARM once we have set the sigframe up and are committed to entering the handler, i.e. in signal_delivered(). Link: https://lore.kernel.org/lkml/20200404170604.GN23230@ZenIV.linux.org.uk/ Link: https://github.com/ClangBuiltLinux/linux/issues/876 Link: https://lkml.kernel.org/r/20210422230846.1756380-1-ndesaulniers@google.com Signed-off-by: Al Viro Signed-off-by: Nick Desaulniers Acked-by: Oleg Nesterov Tested-by: Nathan Chancellor Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compat.h | 2 -- include/linux/signal.h | 2 -- 2 files changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 8855b1b702b2..c270124e4402 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -532,8 +532,6 @@ int __compat_save_altstack(compat_stack_t __user *, unsigned long); &__uss->ss_sp, label); \ unsafe_put_user(t->sas_ss_flags, &__uss->ss_flags, label); \ unsafe_put_user(t->sas_ss_size, &__uss->ss_size, label); \ - if (t->sas_ss_flags & SS_AUTODISARM) \ - sas_ss_reset(t); \ } while (0); /* diff --git a/include/linux/signal.h b/include/linux/signal.h index 5160fd45e5ca..3454c7ff0778 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -462,8 +462,6 @@ int __save_altstack(stack_t __user *, unsigned long); unsafe_put_user((void __user *)t->sas_ss_sp, &__uss->ss_sp, label); \ unsafe_put_user(t->sas_ss_flags, &__uss->ss_flags, label); \ unsafe_put_user(t->sas_ss_size, &__uss->ss_size, label); \ - if (t->sas_ss_flags & SS_AUTODISARM) \ - sas_ss_reset(t); \ } while (0); #ifdef CONFIG_PROC_FS -- cgit v1.2.3 From 540540d06e9d9b3769b46d88def90f7e7c002322 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Wed, 30 Jun 2021 18:56:49 -0700 Subject: kcov: add __no_sanitize_coverage to fix noinstr for all architectures Until now no compiler supported an attribute to disable coverage instrumentation as used by KCOV. To work around this limitation on x86, noinstr functions have their coverage instrumentation turned into nops by objtool. However, this solution doesn't scale automatically to other architectures, such as arm64, which are migrating to use the generic entry code. Clang [1] and GCC [2] have added support for the attribute recently. [1] https://github.com/llvm/llvm-project/commit/280333021e9550d80f5c1152a34e33e81df1e178 [2] https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=cec4d4a6782c9bd8d071839c50a239c49caca689 The changes will appear in Clang 13 and GCC 12. Add __no_sanitize_coverage for both compilers, and add it to noinstr. Note: In the Clang case, __has_feature(coverage_sanitizer) is only true if the feature is enabled, and therefore we do not require an additional defined(CONFIG_KCOV) (like in the GCC case where __has_attribute(..) is always true) to avoid adding redundant attributes to functions if KCOV is off. That being said, compilers that support the attribute will not generate errors/warnings if the attribute is redundantly used; however, where possible let's avoid it as it reduces preprocessed code size and associated compile-time overheads. [elver@google.com: Implement __has_feature(coverage_sanitizer) in Clang] Link: https://lkml.kernel.org/r/20210527162655.3246381-1-elver@google.com [elver@google.com: add comment explaining __has_feature() in Clang] Link: https://lkml.kernel.org/r/20210527194448.3470080-1-elver@google.com Link: https://lkml.kernel.org/r/20210525175819.699786-1-elver@google.com Signed-off-by: Marco Elver Acked-by: Peter Zijlstra (Intel) Reviewed-by: Miguel Ojeda Reviewed-by: Nathan Chancellor Cc: Nick Desaulniers Cc: Kees Cook Cc: Will Deacon Cc: Ard Biesheuvel Cc: Luc Van Oostenryck Cc: Arvind Sankar Cc: Masahiro Yamada Cc: Sami Tolvanen Cc: Arnd Bergmann Cc: Dmitry Vyukov Cc: Mark Rutland Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compiler-clang.h | 17 +++++++++++++++++ include/linux/compiler-gcc.h | 6 ++++++ include/linux/compiler_types.h | 2 +- 3 files changed, 24 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index adbe76b203e2..49b0ac8b6fd3 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -13,6 +13,12 @@ /* all clang versions usable with the kernel support KASAN ABI version 5 */ #define KASAN_ABI_VERSION 5 +/* + * Note: Checking __has_feature(*_sanitizer) is only true if the feature is + * enabled. Therefore it is not required to additionally check defined(CONFIG_*) + * to avoid adding redundant attributes in other configurations. + */ + #if __has_feature(address_sanitizer) || __has_feature(hwaddress_sanitizer) /* Emulate GCC's __SANITIZE_ADDRESS__ flag */ #define __SANITIZE_ADDRESS__ @@ -45,6 +51,17 @@ #define __no_sanitize_undefined #endif +/* + * Support for __has_feature(coverage_sanitizer) was added in Clang 13 together + * with no_sanitize("coverage"). Prior versions of Clang support coverage + * instrumentation, but cannot be queried for support by the preprocessor. + */ +#if __has_feature(coverage_sanitizer) +#define __no_sanitize_coverage __attribute__((no_sanitize("coverage"))) +#else +#define __no_sanitize_coverage +#endif + /* * Not all versions of clang implement the type-generic versions * of the builtin overflow checkers. Fortunately, clang implements diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 5d97ef738a57..cb9217fc60af 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -122,6 +122,12 @@ #define __no_sanitize_undefined #endif +#if defined(CONFIG_KCOV) && __has_attribute(__no_sanitize_coverage__) +#define __no_sanitize_coverage __attribute__((no_sanitize_coverage)) +#else +#define __no_sanitize_coverage +#endif + #if GCC_VERSION >= 50100 #define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 #endif diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index d29bda7f6ebd..cc2bee7f0977 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -210,7 +210,7 @@ struct ftrace_likely_data { /* Section for code which can't be instrumented at all */ #define noinstr \ noinline notrace __attribute((__section__(".noinstr.text"))) \ - __no_kcsan __no_sanitize_address + __no_kcsan __no_sanitize_address __no_sanitize_coverage #endif /* __KERNEL__ */ -- cgit v1.2.3 From 5d43f951b1ac797450bb4d230fdc960b739bea04 Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Wed, 30 Jun 2021 16:11:52 +0800 Subject: ptp: add ptp virtual clock driver framework This patch is to add ptp virtual clock driver framework utilizing timecounter/cyclecounter. The patch just exports two essential APIs for PTP driver. - ptp_vclock_register() - ptp_vclock_unregister() Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- include/linux/ptp_clock_kernel.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index aba237c0b3a2..b6fb771ee524 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -11,7 +11,9 @@ #include #include #include +#include +#define PTP_CLOCK_NAME_LEN 32 /** * struct ptp_clock_request - request PTP clock event * @@ -134,7 +136,7 @@ struct ptp_system_timestamp { struct ptp_clock_info { struct module *owner; - char name[16]; + char name[PTP_CLOCK_NAME_LEN]; s32 max_adj; int n_alarm; int n_ext_ts; -- cgit v1.2.3 From acb288e8047b7569fbc9af6fa6e9405315345103 Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Wed, 30 Jun 2021 16:11:55 +0800 Subject: ptp: add kernel API ptp_get_vclocks_index() Add kernel API ptp_get_vclocks_index() to get all ptp vclocks index on pclock. This is preparation for supporting ptp vclocks info query through ethtool. Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- include/linux/ptp_clock_kernel.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index b6fb771ee524..300a984fec87 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -306,6 +306,18 @@ int ptp_schedule_worker(struct ptp_clock *ptp, unsigned long delay); */ void ptp_cancel_worker_sync(struct ptp_clock *ptp); +/** + * ptp_get_vclocks_index() - get all vclocks index on pclock, and + * caller is responsible to free memory + * of vclock_index + * + * @pclock_index: phc index of ptp pclock. + * @vclock_index: pointer to pointer of vclock index. + * + * return number of vclocks. + */ +int ptp_get_vclocks_index(int pclock_index, int **vclock_index); + #else static inline struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, struct device *parent) @@ -325,6 +337,8 @@ static inline int ptp_schedule_worker(struct ptp_clock *ptp, { return -EOPNOTSUPP; } static inline void ptp_cancel_worker_sync(struct ptp_clock *ptp) { } +static inline int ptp_get_vclocks_index(int pclock_index, int **vclock_index) +{ return 0; } #endif -- cgit v1.2.3 From c156174a67070042d51d2c866146d3c934d5468c Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Wed, 30 Jun 2021 16:11:56 +0800 Subject: ethtool: add a new command for getting PHC virtual clocks Add an interface for getting PHC (PTP Hardware Clock) virtual clocks, which are based on PHC physical clock providing hardware timestamp to network packets. Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- include/linux/ethtool.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 29dbb603bc91..232daaec56e4 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -757,6 +757,16 @@ void ethtool_params_from_link_mode(struct ethtool_link_ksettings *link_ksettings, enum ethtool_link_mode_bit_indices link_mode); +/** + * ethtool_get_phc_vclocks - Derive phc vclocks information, and caller + * is responsible to free memory of vclock_index + * @dev: pointer to net_device structure + * @vclock_index: pointer to pointer of vclock index + * + * Return number of phc vclocks + */ +int ethtool_get_phc_vclocks(struct net_device *dev, int **vclock_index); + /** * ethtool_sprintf - Write formatted string to ethtool string data * @data: Pointer to start of string to update -- cgit v1.2.3 From 895487a3a10fb3a177e20dcde875515d46ccd4df Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Wed, 30 Jun 2021 16:11:57 +0800 Subject: ptp: add kernel API ptp_convert_timestamp() Add kernel API ptp_convert_timestamp() to convert raw hardware timestamp to a specified ptp vclock time. Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- include/linux/ptp_clock_kernel.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 300a984fec87..71fac9237725 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -12,6 +12,7 @@ #include #include #include +#include #define PTP_CLOCK_NAME_LEN 32 /** @@ -318,6 +319,15 @@ void ptp_cancel_worker_sync(struct ptp_clock *ptp); */ int ptp_get_vclocks_index(int pclock_index, int **vclock_index); +/** + * ptp_convert_timestamp() - convert timestamp to a ptp vclock time + * + * @hwtstamps: skb_shared_hwtstamps structure pointer + * @vclock_index: phc index of ptp vclock. + */ +void ptp_convert_timestamp(struct skb_shared_hwtstamps *hwtstamps, + int vclock_index); + #else static inline struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, struct device *parent) @@ -339,6 +349,9 @@ static inline void ptp_cancel_worker_sync(struct ptp_clock *ptp) { } static inline int ptp_get_vclocks_index(int pclock_index, int **vclock_index) { return 0; } +static inline void ptp_convert_timestamp(struct skb_shared_hwtstamps *hwtstamps, + int vclock_index) +{ } #endif -- cgit v1.2.3 From bd7a94c0fa41dfbea8564556c7a28b05e353c5da Mon Sep 17 00:00:00 2001 From: Aubrey Li Date: Fri, 2 Jul 2021 15:03:49 +0800 Subject: ACPI: Correct \_SB._OSC bit definition for PRM According to Platform Runtime Mechanism Specification v1.0 [1], Page 42, \_SB._OSC bit 21 is used to indicate OS support for PRM. Update the definition of the PRM support bit in the code to match the specification. Link: https://uefi.org/sites/default/files/resources/Platform%20Runtime%20Mechanism%20-%20with%20legal%20notice.pdf # [1] Fixes: 60faa8f1ac6e ("ACPI: Add \_SB._OSC bit for PRM") Signed-off-by: Aubrey Li [ rjw: Changelog edits ] Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index a618ba698a5c..81786864566c 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -551,8 +551,8 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); #define OSC_SB_OSLPI_SUPPORT 0x00000100 #define OSC_SB_CPC_DIVERSE_HIGH_SUPPORT 0x00001000 #define OSC_SB_GENERIC_INITIATOR_SUPPORT 0x00002000 -#define OSC_SB_PRM_SUPPORT 0x00020000 #define OSC_SB_NATIVE_USB4_SUPPORT 0x00040000 +#define OSC_SB_PRM_SUPPORT 0x00200000 extern bool osc_sb_apei_support_acked; extern bool osc_pc_lpi_support_confirmed; -- cgit v1.2.3 From e13cd45d352dedac53529fb49e7d7e293f74fb90 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Mon, 31 May 2021 19:04:04 +0300 Subject: vdpa/mlx5: Support creating resources with uid == 0 Currently all resources must be created with uid != 0 which is essential when userspace processes are allocating virtquueue resources. Since this is a kernel implementation, it is perfectly legal to open resources with uid == 0. In case firmware supports, avoid allocating user context. Signed-off-by: Eli Cohen Link: https://lore.kernel.org/r/20210531160404.31368-1-elic@nvidia.com Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- include/linux/mlx5/mlx5_ifc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index b4546e29e561..b0009aa3647f 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1512,7 +1512,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 uar_4k[0x1]; u8 reserved_at_241[0x9]; u8 uar_sz[0x6]; - u8 reserved_at_250[0x8]; + u8 reserved_at_248[0x2]; + u8 umem_uid_0[0x1]; + u8 reserved_at_250[0x5]; u8 log_pg_sz[0x8]; u8 bf[0x1]; -- cgit v1.2.3 From a029a4eab39e4bf542907a3263773fce3d48c983 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Fri, 25 Jun 2021 15:17:01 +0200 Subject: s390/cpumf: Allow concurrent access for CPU Measurement Counter Facility Commit cf6acb8bdb1d ("s390/cpumf: Add support for complete counter set extraction") allows access to the CPU Measurement Counter Facility via character device /dev/hwctr. The access was exclusive via this device or via perf_event_open() system call. Only one path at a time was permitted. The CPU Measurement Counter Facility device driver blocked access to other processes. This patch removes this restriction and allows concurrent access to the CPU Measurement Counter Facility from multiple processes at the same time via perf_event_open() SVC and via /dev/hwctr device. The access via /dev/hwctr device is still exclusive, only one process is allowed to access this device. This patch - moves the /dev/hwctr device access from file perf_cpum_cf_diag.c. to file perf_cpum_cf.c. - use only one trace buffer .../s390dbf/cpum_cf. - remove cfset_csd structure and includes its members it into the structure cpu_cf_events. This results in one data structure and simplifies the access. - rework function familiy ctr_set_enable, ctr_set_disable, ctr_set_start and ctr_set_stop which operate on a counter set number. Now they operate on a counter set bit mask. - move CF_DIAG event functionality to file perf_cpum_cf.c. It now contains the complete functionality of the CPU Measurement Counter Facility: - Performance measurement support for counters using perf stat. - Support for complete counter set extraction with device /dev/hwctr. - Support for counter set extraction event CF_DIAG attached to samples using perf record. - removes file perf_cpum_cf_diag.c Signed-off-by: Thomas Richter Reviewed-by: Sumanth Korikkar Signed-off-by: Vasily Gorbik --- include/linux/cpuhotplug.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 47e13582d9fc..f39b34b13871 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -171,7 +171,6 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_CSTATE_ONLINE, CPUHP_AP_PERF_X86_IDXD_ONLINE, CPUHP_AP_PERF_S390_CF_ONLINE, - CPUHP_AP_PERF_S390_CFD_ONLINE, CPUHP_AP_PERF_S390_SF_ONLINE, CPUHP_AP_PERF_ARM_CCI_ONLINE, CPUHP_AP_PERF_ARM_CCN_ONLINE, -- cgit v1.2.3 From b2aae654a4794ef898ad33a179f341eb610f6b85 Mon Sep 17 00:00:00 2001 From: Xiaoliang Yang Date: Mon, 5 Jul 2021 18:26:54 +0800 Subject: net: stmmac: add mutex lock to protect est parameters Add a mutex lock to protect est structure parameters so that the EST parameters can be updated by other threads. Signed-off-by: Xiaoliang Yang Signed-off-by: David S. Miller --- include/linux/stmmac.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index d5ae621d66ba..09157b8a5810 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -115,6 +115,7 @@ struct stmmac_axi { #define EST_GCL 1024 struct stmmac_est { + struct mutex lock; int enable; u32 btr_offset[2]; u32 btr[2]; -- cgit v1.2.3 From e9e3720002f61cd637a49ecafae77cac230eefae Mon Sep 17 00:00:00 2001 From: Xiaoliang Yang Date: Mon, 5 Jul 2021 18:26:55 +0800 Subject: net: stmmac: ptp: update tas basetime after ptp adjust After adjusting the ptp time, the Qbv base time may be the past time of the new current time. dwmac5 hardware limited the base time cannot be set as past time. This patch add a btr_reserve to store the base time get from qopt, then calculate the base time and reset the Qbv configuration after ptp time adjust. Signed-off-by: Xiaoliang Yang Signed-off-by: David S. Miller --- include/linux/stmmac.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 09157b8a5810..a6f03b36fc4f 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -117,6 +117,7 @@ struct stmmac_axi { struct stmmac_est { struct mutex lock; int enable; + u32 btr_reserve[2]; u32 btr_offset[2]; u32 btr[2]; u32 ctr[2]; -- cgit v1.2.3 From 347269c113f10fbe893f11dd3ae5f44aa15d3111 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Krzysztof=20Wilczy=C5=84ski?= Date: Sat, 3 Jul 2021 15:13:02 +0000 Subject: PCI: Fix kernel-doc formatting MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix kernel-doc formatting throughout drivers/pci and related include files. No change to functionality intended. Check for warnings: $ find include drivers/pci -type f -path "*pci*.[ch]" | xargs scripts/kernel-doc -none [bhelgaas: squashed to one commit] Link: https://lore.kernel.org/r/20210509030237.368540-1-kw@linux.com Link: https://lore.kernel.org/r/20210703151306.1922450-1-kw@linux.com Link: https://lore.kernel.org/r/20210703151306.1922450-2-kw@linux.com Link: https://lore.kernel.org/r/20210703151306.1922450-3-kw@linux.com Link: https://lore.kernel.org/r/20210703151306.1922450-4-kw@linux.com Link: https://lore.kernel.org/r/20210703151306.1922450-5-kw@linux.com Signed-off-by: Krzysztof Wilczyński Signed-off-by: Bjorn Helgaas --- include/linux/pci-ep-cfs.h | 2 +- include/linux/pci-epc.h | 5 ++++- include/linux/pci-epf.h | 5 ++++- include/linux/pci_hotplug.h | 2 ++ 4 files changed, 11 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-ep-cfs.h b/include/linux/pci-ep-cfs.h index 662881335c7e..3e2140d7e31d 100644 --- a/include/linux/pci-ep-cfs.h +++ b/include/linux/pci-ep-cfs.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0+ */ -/** +/* * PCI Endpoint ConfigFS header file * * Copyright (C) 2017 Texas Instruments diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index b82c9b100e97..50a649d33e68 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/** +/* * PCI Endpoint *Controller* (EPC) header file * * Copyright (C) 2017 Texas Instruments @@ -58,6 +58,7 @@ pci_epc_interface_string(enum pci_epc_interface_type type) * @map_msi_irq: ops to map physical address to MSI address and return MSI data * @start: ops to start the PCI link * @stop: ops to stop the PCI link + * @get_features: ops to get the features supported by the EPC * @owner: the module owner containing the ops */ struct pci_epc_ops { @@ -150,6 +151,8 @@ struct pci_epc { /** * struct pci_epc_features - features supported by a EPC device per function * @linkup_notifier: indicate if the EPC device can notify EPF driver on link up + * @core_init_notifier: indicate cores that can notify about their availability + * for initialization * @msi_capable: indicate if the endpoint function has MSI capability * @msix_capable: indicate if the endpoint function has MSI-X capability * @reserved_bar: bitmap to indicate reserved BAR unavailable to function driver diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h index 6833e2160ef1..2debc27ba95e 100644 --- a/include/linux/pci-epf.h +++ b/include/linux/pci-epf.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/** +/* * PCI Endpoint *Function* (EPF) header file * * Copyright (C) 2017 Texas Instruments @@ -102,6 +102,8 @@ struct pci_epf_driver { * @phys_addr: physical address that should be mapped to the BAR * @addr: virtual address corresponding to the @phys_addr * @size: the size of the address space present in BAR + * @barno: BAR number + * @flags: flags that are set for the BAR */ struct pci_epf_bar { dma_addr_t phys_addr; @@ -118,6 +120,7 @@ struct pci_epf_bar { * @header: represents standard configuration header * @bar: represents the BAR of EPF device * @msi_interrupts: number of MSI interrupts required by this function + * @msix_interrupts: number of MSI-X interrupts required by this function * @func_no: unique function number within this endpoint device * @epc: the EPC device to which this EPF device is bound * @driver: the EPF driver to which this EPF device is bound diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index b482e42d7153..2dac431d94ac 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -50,6 +50,8 @@ struct hotplug_slot_ops { /** * struct hotplug_slot - used to register a physical slot with the hotplug pci core * @ops: pointer to the &struct hotplug_slot_ops to be used for this slot + * @slot_list: internal list used to track hotplug PCI slots + * @pci_slot: represents a physical slot * @owner: The module owner of this structure * @mod_name: The module name (KBUILD_MODNAME) of this structure */ -- cgit v1.2.3 From ae21f835a5bda0ef1d00940373445693a764d89e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 1 Jul 2021 16:48:23 -0500 Subject: PCI/P2PDMA: Finish RCU conversion of pdev->p2pdma MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit While looking at pci_alloc_p2pmem() I found RCU protection was not properly applied there, as pdev->p2pdma was potentially read multiple times. Fix pci_alloc_p2pmem(), add __rcu qualifier to p2pdma field of struct pci_dev, and fix all other accesses to this field with proper RCU verbs. Link: https://lore.kernel.org/r/20210701095621.3129283-1-eric.dumazet@gmail.com Fixes: 1570175abd16 ("PCI/P2PDMA: track pgmap references per resource, not globally") Signed-off-by: Eric Dumazet Signed-off-by: Bjorn Helgaas Reviewed-by: Christoph Hellwig Reviewed-by: Logan Gunthorpe Cc: Dan Williams Cc: Ira Weiny Cc: Greg Kroah-Hartman Cc: "Jérôme Glisse" Cc: "Rafael J. Wysocki" --- include/linux/pci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index c20211e59a57..58a39c7239f3 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -497,7 +497,7 @@ struct pci_dev { u16 pasid_features; #endif #ifdef CONFIG_PCI_P2PDMA - struct pci_p2pdma *p2pdma; + struct pci_p2pdma __rcu *p2pdma; #endif u16 acs_cap; /* ACS Capability offset */ phys_addr_t rom; /* Physical address if not from BAR */ -- cgit v1.2.3 From 99cdf57b33e68df7afc876739c93a11f0b1ba807 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 3 Jun 2021 16:50:40 -0400 Subject: lockd: Remove stale comments Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/lockd/xdr.h | 6 ------ include/linux/lockd/xdr4.h | 7 +------ 2 files changed, 1 insertion(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h index 7ab9f264313f..a98309c0121c 100644 --- a/include/linux/lockd/xdr.h +++ b/include/linux/lockd/xdr.h @@ -109,11 +109,5 @@ int nlmsvc_decode_shareargs(struct svc_rqst *, __be32 *); int nlmsvc_encode_shareres(struct svc_rqst *, __be32 *); int nlmsvc_decode_notify(struct svc_rqst *, __be32 *); int nlmsvc_decode_reboot(struct svc_rqst *, __be32 *); -/* -int nlmclt_encode_testargs(struct rpc_rqst *, u32 *, struct nlm_args *); -int nlmclt_encode_lockargs(struct rpc_rqst *, u32 *, struct nlm_args *); -int nlmclt_encode_cancargs(struct rpc_rqst *, u32 *, struct nlm_args *); -int nlmclt_encode_unlockargs(struct rpc_rqst *, u32 *, struct nlm_args *); - */ #endif /* LOCKD_XDR_H */ diff --git a/include/linux/lockd/xdr4.h b/include/linux/lockd/xdr4.h index e709fe5924f2..5ae766f26e04 100644 --- a/include/linux/lockd/xdr4.h +++ b/include/linux/lockd/xdr4.h @@ -37,12 +37,7 @@ int nlm4svc_decode_shareargs(struct svc_rqst *, __be32 *); int nlm4svc_encode_shareres(struct svc_rqst *, __be32 *); int nlm4svc_decode_notify(struct svc_rqst *, __be32 *); int nlm4svc_decode_reboot(struct svc_rqst *, __be32 *); -/* -int nlmclt_encode_testargs(struct rpc_rqst *, u32 *, struct nlm_args *); -int nlmclt_encode_lockargs(struct rpc_rqst *, u32 *, struct nlm_args *); -int nlmclt_encode_cancargs(struct rpc_rqst *, u32 *, struct nlm_args *); -int nlmclt_encode_unlockargs(struct rpc_rqst *, u32 *, struct nlm_args *); - */ + extern const struct rpc_version nlm_version4; #endif /* LOCKD_XDR4_H */ -- cgit v1.2.3 From fe21cb91ae7bca1ae7805454be80b6d03bec85f7 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 2 Jul 2021 16:48:21 +0530 Subject: net: core: Split out code to run generic XDP prog MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This helper can later be utilized in code that runs cpumap and devmap programs in generic redirect mode and adjust skb based on changes made to xdp_buff. When returning XDP_REDIRECT/XDP_TX, it invokes __skb_push, so whenever a generic redirect path invokes devmap/cpumap prog if set, it must __skb_pull again as we expect mac header to be pulled. It also drops the skb_reset_mac_len call after do_xdp_generic, as the mac_header and network_header are advanced by the same offset, so the difference (mac_len) remains constant. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Reviewed-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/bpf/20210702111825.491065-2-memxor@gmail.com --- include/linux/netdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index eaf5bb008aa9..42f6f866d5f3 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3984,6 +3984,8 @@ static inline void dev_consume_skb_any(struct sk_buff *skb) __dev_kfree_skb_any(skb, SKB_REASON_CONSUMED); } +u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, + struct bpf_prog *xdp_prog); void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog); int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb); int netif_rx(struct sk_buff *skb); -- cgit v1.2.3 From cb0f80039fb7ec9981a74d22019daaa85ff51a3d Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 2 Jul 2021 16:48:22 +0530 Subject: bitops: Add non-atomic bitops for pointers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit cpumap needs to set, clear, and test the lowest bit in skb pointer in various places. To make these checks less noisy, add pointer friendly bitop macros that also do some typechecking to sanitize the argument. These wrap the non-atomic bitops __set_bit, __clear_bit, and test_bit but for pointer arguments. Pointer's address has to be passed in and it is treated as an unsigned long *, since width and representation of pointer and unsigned long match on targets Linux supports. They are prefixed with double underscore to indicate lack of atomicity. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Reviewed-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/bpf/20210702111825.491065-3-memxor@gmail.com --- include/linux/bitops.h | 50 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/typecheck.h | 9 +++++++++ 2 files changed, 59 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 26bf15e6cd35..5e62e2383b7f 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -4,6 +4,7 @@ #include #include +#include #include @@ -253,6 +254,55 @@ static __always_inline void __assign_bit(long nr, volatile unsigned long *addr, __clear_bit(nr, addr); } +/** + * __ptr_set_bit - Set bit in a pointer's value + * @nr: the bit to set + * @addr: the address of the pointer variable + * + * Example: + * void *p = foo(); + * __ptr_set_bit(bit, &p); + */ +#define __ptr_set_bit(nr, addr) \ + ({ \ + typecheck_pointer(*(addr)); \ + __set_bit(nr, (unsigned long *)(addr)); \ + }) + +/** + * __ptr_clear_bit - Clear bit in a pointer's value + * @nr: the bit to clear + * @addr: the address of the pointer variable + * + * Example: + * void *p = foo(); + * __ptr_clear_bit(bit, &p); + */ +#define __ptr_clear_bit(nr, addr) \ + ({ \ + typecheck_pointer(*(addr)); \ + __clear_bit(nr, (unsigned long *)(addr)); \ + }) + +/** + * __ptr_test_bit - Test bit in a pointer's value + * @nr: the bit to test + * @addr: the address of the pointer variable + * + * Example: + * void *p = foo(); + * if (__ptr_test_bit(bit, &p)) { + * ... + * } else { + * ... + * } + */ +#define __ptr_test_bit(nr, addr) \ + ({ \ + typecheck_pointer(*(addr)); \ + test_bit(nr, (unsigned long *)(addr)); \ + }) + #ifdef __KERNEL__ #ifndef set_mask_bits diff --git a/include/linux/typecheck.h b/include/linux/typecheck.h index 20d310331eb5..46b15e2aaefb 100644 --- a/include/linux/typecheck.h +++ b/include/linux/typecheck.h @@ -22,4 +22,13 @@ (void)__tmp; \ }) +/* + * Check at compile time that something is a pointer type. + */ +#define typecheck_pointer(x) \ +({ typeof(x) __dummy; \ + (void)sizeof(*__dummy); \ + 1; \ +}) + #endif /* TYPECHECK_H_INCLUDED */ -- cgit v1.2.3 From 11941f8a85362f612df61f4aaab0e41b64d2111d Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 2 Jul 2021 16:48:23 +0530 Subject: bpf: cpumap: Implement generic cpumap MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This change implements CPUMAP redirect support for generic XDP programs. The idea is to reuse the cpu map entry's queue that is used to push native xdp frames for redirecting skb to a different CPU. This will match native XDP behavior (in that RPS is invoked again for packet reinjected into networking stack). To be able to determine whether the incoming skb is from the driver or cpumap, we reuse skb->redirected bit that skips generic XDP processing when it is set. To always make use of this, CONFIG_NET_REDIRECT guard on it has been lifted and it is always available. >From the redirect side, we add the skb to ptr_ring with its lowest bit set to 1. This should be safe as skb is not 1-byte aligned. This allows kthread to discern between xdp_frames and sk_buff. On consumption of the ptr_ring item, the lowest bit is unset. In the end, the skb is simply added to the list that kthread is anyway going to maintain for xdp_frames converted to skb, and then received again by using netif_receive_skb_list. Bulking optimization for generic cpumap is left as an exercise for a future patch for now. Since cpumap entry progs are now supported, also remove check in generic_xdp_install for the cpumap. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Reviewed-by: Toke Høiland-Jørgensen Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/bpf/20210702111825.491065-4-memxor@gmail.com --- include/linux/bpf.h | 9 ++++++++- include/linux/skbuff.h | 10 ++-------- 2 files changed, 10 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f309fc1509f2..095aaa104c56 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1513,7 +1513,8 @@ bool dev_map_can_have_prog(struct bpf_map *map); void __cpu_map_flush(void); int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, struct net_device *dev_rx); -bool cpu_map_prog_allowed(struct bpf_map *map); +int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu, + struct sk_buff *skb); /* Return map's numa specified by userspace */ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr) @@ -1710,6 +1711,12 @@ static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, return 0; } +static inline int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu, + struct sk_buff *skb) +{ + return -EOPNOTSUPP; +} + static inline bool cpu_map_prog_allowed(struct bpf_map *map) { return false; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b2db9cd9a73f..f19190820e63 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -863,8 +863,8 @@ struct sk_buff { __u8 tc_skip_classify:1; __u8 tc_at_ingress:1; #endif -#ifdef CONFIG_NET_REDIRECT __u8 redirected:1; +#ifdef CONFIG_NET_REDIRECT __u8 from_ingress:1; #endif #ifdef CONFIG_TLS_DEVICE @@ -4664,17 +4664,13 @@ static inline __wsum lco_csum(struct sk_buff *skb) static inline bool skb_is_redirected(const struct sk_buff *skb) { -#ifdef CONFIG_NET_REDIRECT return skb->redirected; -#else - return false; -#endif } static inline void skb_set_redirected(struct sk_buff *skb, bool from_ingress) { -#ifdef CONFIG_NET_REDIRECT skb->redirected = 1; +#ifdef CONFIG_NET_REDIRECT skb->from_ingress = from_ingress; if (skb->from_ingress) skb->tstamp = 0; @@ -4683,9 +4679,7 @@ static inline void skb_set_redirected(struct sk_buff *skb, bool from_ingress) static inline void skb_reset_redirect(struct sk_buff *skb) { -#ifdef CONFIG_NET_REDIRECT skb->redirected = 0; -#endif } static inline bool skb_csum_is_sctp(struct sk_buff *skb) -- cgit v1.2.3 From 2ea5eabaf04a1829383aefe98ac38a2e5ae2d698 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 2 Jul 2021 16:48:24 +0530 Subject: bpf: devmap: Implement devmap prog execution for generic XDP MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This lifts the restriction on running devmap BPF progs in generic redirect mode. To match native XDP behavior, it is invoked right before generic_xdp_tx is called, and only supports XDP_PASS/XDP_ABORTED/ XDP_DROP actions. We also return 0 even if devmap program drops the packet, as semantically redirect has already succeeded and the devmap prog is the last point before TX of the packet to device where it can deliver a verdict on the packet. This also means it must take care of freeing the skb, as xdp_do_generic_redirect callers only do that in case an error is returned. Since devmap entry prog is supported, remove the check in generic_xdp_install entirely. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Reviewed-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/bpf/20210702111825.491065-5-memxor@gmail.com --- include/linux/bpf.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 095aaa104c56..4afbff308ca3 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1508,7 +1508,6 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, struct bpf_prog *xdp_prog, struct bpf_map *map, bool exclude_ingress); -bool dev_map_can_have_prog(struct bpf_map *map); void __cpu_map_flush(void); int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, -- cgit v1.2.3 From 530a5678bc0083e84f99f38f77ced8fbb3d18434 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Wed, 2 Jun 2021 10:15:33 +0800 Subject: vdpa: support packed virtqueue for set/get_vq_state() This patch extends the vdpa_vq_state to support packed virtqueue state which is basically the device/driver ring wrap counters and the avail and used index. This will be used for the virito-vdpa support for the packed virtqueue and the future vhost/vhost-vdpa support for the packed virtqueue. Signed-off-by: Jason Wang Link: https://lore.kernel.org/r/20210602021536.39525-2-jasowang@redhat.com Signed-off-by: Michael S. Tsirkin Reviewed-by: Eli Cohen --- include/linux/vdpa.h | 25 +++++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index f311d227aa1b..3357ac98878d 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -28,13 +28,34 @@ struct vdpa_notification_area { }; /** - * struct vdpa_vq_state - vDPA vq_state definition + * struct vdpa_vq_state_split - vDPA split virtqueue state * @avail_index: available index */ -struct vdpa_vq_state { +struct vdpa_vq_state_split { u16 avail_index; }; +/** + * struct vdpa_vq_state_packed - vDPA packed virtqueue state + * @last_avail_counter: last driver ring wrap counter observed by device + * @last_avail_idx: device available index + * @last_used_counter: device ring wrap counter + * @last_used_idx: used index + */ +struct vdpa_vq_state_packed { + u16 last_avail_counter:1; + u16 last_avail_idx:15; + u16 last_used_counter:1; + u16 last_used_idx:15; +}; + +struct vdpa_vq_state { + union { + struct vdpa_vq_state_split split; + struct vdpa_vq_state_packed packed; + }; +}; + struct vdpa_mgmt_dev; /** -- cgit v1.2.3 From 0140b3d07617e71a8d9509776434ced107572fc8 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Wed, 2 Jun 2021 10:15:34 +0800 Subject: virtio-pci library: introduce vp_modern_get_driver_features() This patch introduce a helper to get driver/guest features from the device. Signed-off-by: Jason Wang Link: https://lore.kernel.org/r/20210602021536.39525-3-jasowang@redhat.com Signed-off-by: Michael S. Tsirkin Reviewed-by: Eli Cohen --- include/linux/virtio_pci_modern.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h index 6a95b58fd0f4..eb2bd9b4077d 100644 --- a/include/linux/virtio_pci_modern.h +++ b/include/linux/virtio_pci_modern.h @@ -79,6 +79,7 @@ static inline void vp_iowrite64_twopart(u64 val, } u64 vp_modern_get_features(struct virtio_pci_modern_device *mdev); +u64 vp_modern_get_driver_features(struct virtio_pci_modern_device *mdev); void vp_modern_set_features(struct virtio_pci_modern_device *mdev, u64 features); u32 vp_modern_generation(struct virtio_pci_modern_device *mdev); -- cgit v1.2.3 From 0705e8d1e2207ceeb83dc6e1751b6b82718b353a Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 2 Jul 2021 18:05:03 -0400 Subject: ext4: inline jbd2_journal_[un]register_shrinker() The function jbd2_journal_unregister_shrinker() was getting called twice when the file system was getting unmounted. On Power and ARM platforms this was causing kernel crash when unmounting the file system, when a percpu_counter was destroyed twice. Fix this by removing jbd2_journal_[un]register_shrinker() functions, and inlining the shrinker setup and teardown into journal_init_common() and jbd2_journal_destroy(). This means that ext4 and ocfs2 now no longer need to know about registering and unregistering jbd2's shrinker. Also, while we're at it, rename the percpu counter from j_jh_shrink_count to j_checkpoint_jh_count, since this makes it clearer what this counter is intended to track. Link: https://lore.kernel.org/r/20210705145025.3363130-1-tytso@mit.edu Fixes: 4ba3fcdde7e3 ("jbd2,ext4: add a shrinker to release checkpointed buffers") Reported-by: Jon Hunter Reported-by: Sachin Sant Tested-by: Sachin Sant Tested-by: Jon Hunter Reviewed-by: Jan Kara Signed-off-by: Theodore Ts'o --- include/linux/jbd2.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 6cc035321562..fd933c45281a 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -918,11 +918,11 @@ struct journal_s struct shrinker j_shrinker; /** - * @j_jh_shrink_count: + * @j_checkpoint_jh_count: * * Number of journal buffers on the checkpoint list. [j_list_lock] */ - struct percpu_counter j_jh_shrink_count; + struct percpu_counter j_checkpoint_jh_count; /** * @j_shrink_transaction: @@ -1556,8 +1556,6 @@ extern int jbd2_journal_set_features (journal_t *, unsigned long, unsigned long, unsigned long); extern void jbd2_journal_clear_features (journal_t *, unsigned long, unsigned long, unsigned long); -extern int jbd2_journal_register_shrinker(journal_t *journal); -extern void jbd2_journal_unregister_shrinker(journal_t *journal); extern int jbd2_journal_load (journal_t *journal); extern int jbd2_journal_destroy (journal_t *); extern int jbd2_journal_recover (journal_t *journal); -- cgit v1.2.3 From c5a382ebdbdaac27ec109993e29f9045d70297f2 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Tue, 8 Jun 2021 15:59:12 -0400 Subject: sunrpc: Create per-rpc_clnt sysfs kobjects These will eventually have files placed under them for sysfs operations. Signed-off-by: Anna Schumaker Signed-off-by: Olga Kornievskaia Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 02e7a5863d28..8b5d5c97553e 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -29,6 +29,7 @@ #include struct rpc_inode; +struct rpc_sysfs_client; /* * The high-level client handle @@ -71,6 +72,7 @@ struct rpc_clnt { #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) struct dentry *cl_debugfs; /* debugfs directory */ #endif + struct rpc_sysfs_client *cl_sysfs; /* sysfs directory */ /* cl_work is only needed after cl_xpi is no longer used, * and that are of similar size */ -- cgit v1.2.3 From 572caba402e10b35a080d1b43c0193da364f3a17 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Tue, 8 Jun 2021 15:59:13 -0400 Subject: sunrpc: add xprt id This adds a unique identifier for a sunrpc transport in sysfs, which is similarly managed to the unique IDs of clients. Signed-off-by: Dan Aloni Signed-off-by: Olga Kornievskaia Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 61b622e334ee..1fbc470ce205 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -185,6 +185,7 @@ enum xprt_transports { struct rpc_xprt { struct kref kref; /* Reference count */ const struct rpc_xprt_ops *ops; /* transport methods */ + unsigned int id; /* transport id */ const struct rpc_timeout *timeout; /* timeout parms */ struct sockaddr_storage addr; /* server address */ @@ -370,6 +371,7 @@ struct rpc_xprt * xprt_alloc(struct net *net, size_t size, void xprt_free(struct rpc_xprt *); void xprt_add_backlog(struct rpc_xprt *xprt, struct rpc_task *task); bool xprt_wake_up_backlog(struct rpc_xprt *xprt, struct rpc_rqst *req); +void xprt_cleanup_ids(void); static inline int xprt_enable_swap(struct rpc_xprt *xprt) -- cgit v1.2.3 From 5b9268727f299f87432e8b035e9e8bec8ba13e8d Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Tue, 8 Jun 2021 15:59:14 -0400 Subject: sunrpc: add IDs to multipath This is used to uniquely identify sunrpc multipath objects in /sys. Signed-off-by: Dan Aloni Signed-off-by: Olga Kornievskaia Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprtmultipath.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprtmultipath.h b/include/linux/sunrpc/xprtmultipath.h index c6cce3fbf29d..ef95a6f18ccf 100644 --- a/include/linux/sunrpc/xprtmultipath.h +++ b/include/linux/sunrpc/xprtmultipath.h @@ -14,6 +14,7 @@ struct rpc_xprt_switch { spinlock_t xps_lock; struct kref xps_kref; + unsigned int xps_id; unsigned int xps_nxprts; unsigned int xps_nactive; atomic_long_t xps_queuelen; @@ -71,4 +72,7 @@ extern struct rpc_xprt *xprt_iter_get_next(struct rpc_xprt_iter *xpi); extern bool rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps, const struct sockaddr *sap); + +extern void xprt_multipath_cleanup_ids(void); + #endif -- cgit v1.2.3 From d3abc73987fd2a5992a9bdae9f44fa43d1b4db70 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Tue, 8 Jun 2021 15:59:15 -0400 Subject: sunrpc: keep track of the xprt_class in rpc_xprt structure We need to keep track of the type for a given transport. Signed-off-by: Olga Kornievskaia Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 1fbc470ce205..7efc6c0a5455 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -53,6 +53,7 @@ enum rpc_display_format_t { struct rpc_task; struct rpc_xprt; +struct xprt_class; struct seq_file; struct svc_serv; struct net; @@ -289,6 +290,7 @@ struct rpc_xprt { atomic_t inject_disconnect; #endif struct rcu_head rcu; + const struct xprt_class *xprt_class; }; #if defined(CONFIG_SUNRPC_BACKCHANNEL) -- cgit v1.2.3 From baea99445dd4675a834e8a5987d2f368adb62e6c Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Tue, 8 Jun 2021 15:59:16 -0400 Subject: sunrpc: add xprt_switch direcotry to sunrpc's sysfs Add xprt_switch directory to the sysfs and create individual xprt_swith subdirectories for multipath transport group. Signed-off-by: Olga Kornievskaia Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprtmultipath.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprtmultipath.h b/include/linux/sunrpc/xprtmultipath.h index ef95a6f18ccf..b19addc8b715 100644 --- a/include/linux/sunrpc/xprtmultipath.h +++ b/include/linux/sunrpc/xprtmultipath.h @@ -10,6 +10,7 @@ #define _NET_SUNRPC_XPRTMULTIPATH_H struct rpc_xprt_iter_ops; +struct rpc_sysfs_xprt_switch; struct rpc_xprt_switch { spinlock_t xps_lock; struct kref xps_kref; @@ -24,6 +25,7 @@ struct rpc_xprt_switch { const struct rpc_xprt_iter_ops *xps_iter_ops; + struct rpc_sysfs_xprt_switch *xps_sysfs; struct rcu_head xps_rcu; }; -- cgit v1.2.3 From d408ebe04ac58eb370e2d264e88edbab746adda6 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Tue, 8 Jun 2021 15:59:18 -0400 Subject: sunrpc: add add sysfs directory per xprt under each xprt_switch Add individual transport directories under each transport switch group. For instance, for each nconnect=X connections there will be a transport directory. Naming conventions also identifies transport type -- xprt-- where type is udp, tcp, rdma, local, bc. Signed-off-by: Olga Kornievskaia Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 7efc6c0a5455..8360db664e5f 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -183,6 +183,7 @@ enum xprt_transports { XPRT_TRANSPORT_LOCAL = 257, }; +struct rpc_sysfs_xprt; struct rpc_xprt { struct kref kref; /* Reference count */ const struct rpc_xprt_ops *ops; /* transport methods */ @@ -291,6 +292,7 @@ struct rpc_xprt { #endif struct rcu_head rcu; const struct xprt_class *xprt_class; + struct rpc_sysfs_xprt *xprt_sysfs; }; #if defined(CONFIG_SUNRPC_BACKCHANNEL) -- cgit v1.2.3 From e091853ebdb486fd8bde86b87178fdf3850914fc Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Wed, 23 Jun 2021 23:28:46 -0400 Subject: SUNRPC mark the first transport When an RPC client gets created it's first transport is special and should be marked a main transport. Signed-off-by: Olga Kornievskaia Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 13a4eaf385cf..692e5946c029 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -293,6 +293,7 @@ struct rpc_xprt { struct rcu_head rcu; const struct xprt_class *xprt_class; struct rpc_sysfs_xprt *xprt_sysfs; + bool main; /*mark if this is the 1st transport */ }; #if defined(CONFIG_SUNRPC_BACKCHANNEL) -- cgit v1.2.3 From a8482488a7d6d320f63a9ee1912dbb5ae5b80a61 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Wed, 23 Jun 2021 23:28:48 -0400 Subject: SUNRPC query transport's source port Provide ability to query transport's source port. Signed-off-by: Olga Kornievskaia Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprtsock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h index 3c1423ee74b4..8c2a712cb242 100644 --- a/include/linux/sunrpc/xprtsock.h +++ b/include/linux/sunrpc/xprtsock.h @@ -10,6 +10,7 @@ int init_socket_xprt(void); void cleanup_socket_xprt(void); +unsigned short get_srcport(struct rpc_xprt *); #define RPC_MIN_RESVPORT (1U) #define RPC_MAX_RESVPORT (65535U) -- cgit v1.2.3 From 587bc7255d26ca80b58026881db5fb3bf770cc43 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Tue, 8 Jun 2021 15:59:19 -0400 Subject: sunrpc: add dst_attr attributes to the sysfs xprt directory Allow to query and set the destination's address of a transport. Setting of the destination address is allowed only for TCP or RDMA based connections. Signed-off-by: Olga Kornievskaia Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 8360db664e5f..13a4eaf385cf 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -414,6 +414,7 @@ void xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie); bool xprt_lock_connect(struct rpc_xprt *, struct rpc_task *, void *); void xprt_unlock_connect(struct rpc_xprt *, void *); +void xprt_release_write(struct rpc_xprt *, struct rpc_task *); /* * Reserved bit positions in xprt->state -- cgit v1.2.3 From 5b7eb78486cd9ac58bfbd6d84ea0fe2d9fead03b Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Wed, 23 Jun 2021 23:28:50 -0400 Subject: SUNRPC: take a xprt offline using sysfs Using sysfs's xprt_state attribute, mark a particular transport offline. It will not be picked during the round-robin selection. It's not allowed to take the main (1st created transport associated with the rpc_client) offline. Also bring a transport back online via sysfs by writing "online" and that would allow for this transport to be picked during the round- robin selection. Signed-off-by: Olga Kornievskaia Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 692e5946c029..b8ed7fa1b4ca 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -427,6 +427,7 @@ void xprt_release_write(struct rpc_xprt *, struct rpc_task *); #define XPRT_BOUND (4) #define XPRT_BINDING (5) #define XPRT_CLOSING (6) +#define XPRT_OFFLINE (7) #define XPRT_CONGESTED (9) #define XPRT_CWND_WAIT (10) #define XPRT_WRITE_SPACE (11) -- cgit v1.2.3 From 85e39feead948bdf8322c961d7a9bebc20d629f3 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Wed, 23 Jun 2021 23:28:51 -0400 Subject: NFSv4.1 identify and mark RPC tasks that can move between transports In preparation for when we can re-try a task on a different transport, identify and mark such RPC tasks as moveable. Only 4.1+ operarations can be re-tried on a different transport. Signed-off-by: Olga Kornievskaia Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index df696efdd675..a237b8dbf608 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -121,6 +121,7 @@ struct rpc_task_setup { */ #define RPC_TASK_ASYNC 0x0001 /* is an async task */ #define RPC_TASK_SWAPPER 0x0002 /* is swapping in/out */ +#define RPC_TASK_MOVEABLE 0x0004 /* nfs4.1+ rpc tasks */ #define RPC_TASK_NULLCREDS 0x0010 /* Use AUTH_NULL credential */ #define RPC_CALL_MAJORSEEN 0x0020 /* major timeout seen */ #define RPC_TASK_ROOTCREDS 0x0040 /* force root creds */ @@ -139,6 +140,7 @@ struct rpc_task_setup { #define RPC_IS_SOFT(t) ((t)->tk_flags & (RPC_TASK_SOFT|RPC_TASK_TIMEOUT)) #define RPC_IS_SOFTCONN(t) ((t)->tk_flags & RPC_TASK_SOFTCONN) #define RPC_WAS_SENT(t) ((t)->tk_flags & RPC_TASK_SENT) +#define RPC_IS_MOVEABLE(t) ((t)->tk_flags & RPC_TASK_MOVEABLE) #define RPC_TASK_RUNNING 0 #define RPC_TASK_QUEUED 1 -- cgit v1.2.3 From 6f081693e7b2ba63422b735684b05a850a6351ba Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Wed, 23 Jun 2021 23:28:53 -0400 Subject: sunrpc: remove an offlined xprt using sysfs Once a transport has been put offline, this transport can be also removed from the list of transports. Any tasks that have been stuck on this transport would find the next available active transport and be re-tried. This transport would be removed from the xprt_switch list and freed. Signed-off-by: Olga Kornievskaia Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index b8ed7fa1b4ca..c8c39f22d3b1 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -428,6 +428,7 @@ void xprt_release_write(struct rpc_xprt *, struct rpc_task *); #define XPRT_BINDING (5) #define XPRT_CLOSING (6) #define XPRT_OFFLINE (7) +#define XPRT_REMOVE (8) #define XPRT_CONGESTED (9) #define XPRT_CWND_WAIT (10) #define XPRT_WRITE_SPACE (11) -- cgit v1.2.3 From b4e89bcba2b3a966e043107cb52c682bb860cee7 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 2 Jul 2021 17:24:22 -0400 Subject: NFSv4/pnfs: Clean up layout get on open Cache the layout in the arguments so we don't have to keep looking it up from the inode. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 717ecc87c9e7..e9698b6278a5 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -277,6 +277,7 @@ struct nfs4_layoutget { struct nfs4_layoutget_args args; struct nfs4_layoutget_res res; const struct cred *cred; + struct pnfs_layout_hdr *lo; gfp_t gfp_flags; }; -- cgit v1.2.3 From c23c80822fbdf69c1aacbca50b8339972697f850 Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Wed, 7 Jul 2021 18:07:34 -0700 Subject: lib: fix spelling mistakes in header files Fix some spelling mistakes in comments found by "codespell": Hoever ==> However poiter ==> pointer representaion ==> representation uppon ==> upon independend ==> independent aquired ==> acquired mis-match ==> mismatch scrach ==> scratch struture ==> structure Analagous ==> Analogous interation ==> iteration And some were discovered manually by Joe Perches and Christoph Lameter: stroed ==> stored arch independent ==> an architecture independent A example structure for ==> Example structure for Link: https://lkml.kernel.org/r/20210609150027.14805-2-thunder.leizhen@huawei.com Signed-off-by: Zhen Lei Cc: Christoph Lameter Cc: Masami Hiramatsu Cc: Dennis Zhou Cc: Tejun Heo Cc: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootconfig.h | 4 ++-- include/linux/cpumask.h | 2 +- include/linux/debugobjects.h | 2 +- include/linux/lru_cache.h | 8 ++++---- include/linux/nodemask.h | 6 +++--- include/linux/percpu-refcount.h | 2 +- include/linux/scatterlist.h | 2 +- 7 files changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h index 6bdd94cff4e2..abe089c27529 100644 --- a/include/linux/bootconfig.h +++ b/include/linux/bootconfig.h @@ -214,10 +214,10 @@ static inline struct xbc_node * __init xbc_node_get_subkey(struct xbc_node *node * @value: Iterated value of array entry. * * Iterate array entries of given @key under @node. Each array entry node - * is stroed to @anode and @value. If the @node doesn't have @key node, + * is stored to @anode and @value. If the @node doesn't have @key node, * it does nothing. * Note that even if the found key node has only one value (not array) - * this executes block once. Hoever, if the found key node has no value + * this executes block once. However, if the found key node has no value * (key-only node), this does nothing. So don't use this for testing the * key-value pair existence. */ diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index bfc4690de4f4..f3689a52bfd0 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -259,7 +259,7 @@ extern int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool /** * for_each_cpu_wrap - iterate over every cpu in a mask, starting at a specified location * @cpu: the (optionally unsigned) integer iterator - * @mask: the cpumask poiter + * @mask: the cpumask pointer * @start: the start location * * The implementation does not assume any bit in @mask is set (including @start). diff --git a/include/linux/debugobjects.h b/include/linux/debugobjects.h index 8d2dde23e9fb..32444686b6ff 100644 --- a/include/linux/debugobjects.h +++ b/include/linux/debugobjects.h @@ -18,7 +18,7 @@ enum debug_obj_state { struct debug_obj_descr; /** - * struct debug_obj - representaion of an tracked object + * struct debug_obj - representation of an tracked object * @node: hlist node to link the object into the tracker list * @state: tracked object state * @astate: current active state diff --git a/include/linux/lru_cache.h b/include/linux/lru_cache.h index 429d67d815ce..07add7882a5d 100644 --- a/include/linux/lru_cache.h +++ b/include/linux/lru_cache.h @@ -32,7 +32,7 @@ This header file (and its .c file; kernel-doc of functions see there) Because of this later property, it is called "lru_cache". As it actually Tracks Objects in an Active SeT, we could also call it toast (incidentally that is what may happen to the data on the - backend storage uppon next resync, if we don't get it right). + backend storage upon next resync, if we don't get it right). What for? @@ -152,7 +152,7 @@ struct lc_element { * for paranoia, and for "lc_element_to_index" */ unsigned lc_index; /* if we want to track a larger set of objects, - * it needs to become arch independend u64 */ + * it needs to become an architecture independent u64 */ unsigned lc_number; /* special label when on free list */ #define LC_FREE (~0U) @@ -263,7 +263,7 @@ extern void lc_seq_dump_details(struct seq_file *seq, struct lru_cache *lc, char * * Allows (expects) the set to be "dirty". Note that the reference counts and * order on the active and lru lists may still change. Used to serialize - * changing transactions. Returns true if we aquired the lock. + * changing transactions. Returns true if we acquired the lock. */ static inline int lc_try_lock_for_transaction(struct lru_cache *lc) { @@ -275,7 +275,7 @@ static inline int lc_try_lock_for_transaction(struct lru_cache *lc) * @lc: the lru cache to operate on * * Note that the reference counts and order on the active and lru lists may - * still change. Only works on a "clean" set. Returns true if we aquired the + * still change. Only works on a "clean" set. Returns true if we acquired the * lock, which means there are no pending changes, and any further attempt to * change the set will not succeed until the next lc_unlock(). */ diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index ac398e143c9a..567c3ddba2c4 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -119,7 +119,7 @@ static inline const unsigned long *__nodemask_pr_bits(const nodemask_t *m) * The inline keyword gives the compiler room to decide to inline, or * not inline a function as it sees best. However, as these functions * are called in both __init and non-__init functions, if they are not - * inlined we will end up with a section mis-match error (of the type of + * inlined we will end up with a section mismatch error (of the type of * freeable items not being freed). So we must use __always_inline here * to fix the problem. If other functions in the future also end up in * this situation they will also need to be annotated as __always_inline @@ -515,7 +515,7 @@ static inline int node_random(const nodemask_t *mask) #define for_each_online_node(node) for_each_node_state(node, N_ONLINE) /* - * For nodemask scrach area. + * For nodemask scratch area. * NODEMASK_ALLOC(type, name) allocates an object with a specified type and * name. */ @@ -528,7 +528,7 @@ static inline int node_random(const nodemask_t *mask) #define NODEMASK_FREE(m) do {} while (0) #endif -/* A example struture for using NODEMASK_ALLOC, used in mempolicy. */ +/* Example structure for using NODEMASK_ALLOC, used in mempolicy. */ struct nodemask_scratch { nodemask_t mask1; nodemask_t mask2; diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index 16c35a728b4c..ae16a9856305 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -213,7 +213,7 @@ static inline void percpu_ref_get_many(struct percpu_ref *ref, unsigned long nr) * percpu_ref_get - increment a percpu refcount * @ref: percpu_ref to get * - * Analagous to atomic_long_inc(). + * Analogous to atomic_long_inc(). * * This function is safe to call as long as @ref is between init and exit. */ diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 6f70572b2938..ecf87484814f 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -474,7 +474,7 @@ sg_page_iter_dma_address(struct sg_dma_page_iter *dma_iter) * Iterates over sg entries mapping page-by-page. On each successful * iteration, @miter->page points to the mapped page and * @miter->length bytes of data can be accessed at @miter->addr. As - * long as an interation is enclosed between start and stop, the user + * long as an iteration is enclosed between start and stop, the user * is free to choose control structure and when to stop. * * @miter->consumed is set to @miter->length on each iteration. It -- cgit v1.2.3 From 6d47c23b16aa78ff93a3050ccf4b1bd1c064b8b3 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 7 Jul 2021 18:07:59 -0700 Subject: set_memory: allow querying whether set_direct_map_*() is actually enabled On arm64, set_direct_map_*() functions may return 0 without actually changing the linear map. This behaviour can be controlled using kernel parameters, so we need a way to determine at runtime whether calls to set_direct_map_invalid_noflush() and set_direct_map_default_noflush() have any effect. Extend set_memory API with can_set_direct_map() function that allows checking if calling set_direct_map_*() will actually change the page table, replace several occurrences of open coded checks in arm64 with the new function and provide a generic stub for architectures that always modify page tables upon calls to set_direct_map APIs. [arnd@arndb.de: arm64: kfence: fix header inclusion ] Link: https://lkml.kernel.org/r/20210518072034.31572-4-rppt@kernel.org Signed-off-by: Mike Rapoport Reviewed-by: Catalin Marinas Reviewed-by: David Hildenbrand Acked-by: James Bottomley Cc: Alexander Viro Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Christopher Lameter Cc: Dan Williams Cc: Dave Hansen Cc: Elena Reshetova Cc: Hagen Paul Pfeifer Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: James Bottomley Cc: "Kirill A. Shutemov" Cc: Mark Rutland Cc: Matthew Wilcox Cc: Michael Kerrisk Cc: Palmer Dabbelt Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Rick Edgecombe Cc: Roman Gushchin Cc: Shakeel Butt Cc: Shuah Khan Cc: Thomas Gleixner Cc: Tycho Andersen Cc: Will Deacon Cc: kernel test robot Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/set_memory.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h index fe1aa4e54680..f36be5166c19 100644 --- a/include/linux/set_memory.h +++ b/include/linux/set_memory.h @@ -28,7 +28,19 @@ static inline bool kernel_page_present(struct page *page) { return true; } +#else /* CONFIG_ARCH_HAS_SET_DIRECT_MAP */ +/* + * Some architectures, e.g. ARM64 can disable direct map modifications at + * boot time. Let them overrive this query. + */ +#ifndef can_set_direct_map +static inline bool can_set_direct_map(void) +{ + return true; +} +#define can_set_direct_map can_set_direct_map #endif +#endif /* CONFIG_ARCH_HAS_SET_DIRECT_MAP */ #ifndef set_mce_nospec static inline int set_mce_nospec(unsigned long pfn, bool unmap) -- cgit v1.2.3 From 1507f51255c9ff07d75909a84e7c0d7f3c4b2f49 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 7 Jul 2021 18:08:03 -0700 Subject: mm: introduce memfd_secret system call to create "secret" memory areas Introduce "memfd_secret" system call with the ability to create memory areas visible only in the context of the owning process and not mapped not only to other processes but in the kernel page tables as well. The secretmem feature is off by default and the user must explicitly enable it at the boot time. Once secretmem is enabled, the user will be able to create a file descriptor using the memfd_secret() system call. The memory areas created by mmap() calls from this file descriptor will be unmapped from the kernel direct map and they will be only mapped in the page table of the processes that have access to the file descriptor. Secretmem is designed to provide the following protections: * Enhanced protection (in conjunction with all the other in-kernel attack prevention systems) against ROP attacks. Seceretmem makes "simple" ROP insufficient to perform exfiltration, which increases the required complexity of the attack. Along with other protections like the kernel stack size limit and address space layout randomization which make finding gadgets is really hard, absence of any in-kernel primitive for accessing secret memory means the one gadget ROP attack can't work. Since the only way to access secret memory is to reconstruct the missing mapping entry, the attacker has to recover the physical page and insert a PTE pointing to it in the kernel and then retrieve the contents. That takes at least three gadgets which is a level of difficulty beyond most standard attacks. * Prevent cross-process secret userspace memory exposures. Once the secret memory is allocated, the user can't accidentally pass it into the kernel to be transmitted somewhere. The secreremem pages cannot be accessed via the direct map and they are disallowed in GUP. * Harden against exploited kernel flaws. In order to access secretmem, a kernel-side attack would need to either walk the page tables and create new ones, or spawn a new privileged uiserspace process to perform secrets exfiltration using ptrace. The file descriptor based memory has several advantages over the "traditional" mm interfaces, such as mlock(), mprotect(), madvise(). File descriptor approach allows explicit and controlled sharing of the memory areas, it allows to seal the operations. Besides, file descriptor based memory paves the way for VMMs to remove the secret memory range from the userspace hipervisor process, for instance QEMU. Andy Lutomirski says: "Getting fd-backed memory into a guest will take some possibly major work in the kernel, but getting vma-backed memory into a guest without mapping it in the host user address space seems much, much worse." memfd_secret() is made a dedicated system call rather than an extension to memfd_create() because it's purpose is to allow the user to create more secure memory mappings rather than to simply allow file based access to the memory. Nowadays a new system call cost is negligible while it is way simpler for userspace to deal with a clear-cut system calls than with a multiplexer or an overloaded syscall. Moreover, the initial implementation of memfd_secret() is completely distinct from memfd_create() so there is no much sense in overloading memfd_create() to begin with. If there will be a need for code sharing between these implementation it can be easily achieved without a need to adjust user visible APIs. The secret memory remains accessible in the process context using uaccess primitives, but it is not exposed to the kernel otherwise; secret memory areas are removed from the direct map and functions in the follow_page()/get_user_page() family will refuse to return a page that belongs to the secret memory area. Once there will be a use case that will require exposing secretmem to the kernel it will be an opt-in request in the system call flags so that user would have to decide what data can be exposed to the kernel. Removing of the pages from the direct map may cause its fragmentation on architectures that use large pages to map the physical memory which affects the system performance. However, the original Kconfig text for CONFIG_DIRECT_GBPAGES said that gigabyte pages in the direct map "... can improve the kernel's performance a tiny bit ..." (commit 00d1c5e05736 ("x86: add gbpages switches")) and the recent report [1] showed that "... although 1G mappings are a good default choice, there is no compelling evidence that it must be the only choice". Hence, it is sufficient to have secretmem disabled by default with the ability of a system administrator to enable it at boot time. Pages in the secretmem regions are unevictable and unmovable to avoid accidental exposure of the sensitive data via swap or during page migration. Since the secretmem mappings are locked in memory they cannot exceed RLIMIT_MEMLOCK. Since these mappings are already locked independently from mlock(), an attempt to mlock()/munlock() secretmem range would fail and mlockall()/munlockall() will ignore secretmem mappings. However, unlike mlock()ed memory, secretmem currently behaves more like long-term GUP: secretmem mappings are unmovable mappings directly consumed by user space. With default limits, there is no excessive use of secretmem and it poses no real problem in combination with ZONE_MOVABLE/CMA, but in the future this should be addressed to allow balanced use of large amounts of secretmem along with ZONE_MOVABLE/CMA. A page that was a part of the secret memory area is cleared when it is freed to ensure the data is not exposed to the next user of that page. The following example demonstrates creation of a secret mapping (error handling is omitted): fd = memfd_secret(0); ftruncate(fd, MAP_SIZE); ptr = mmap(NULL, MAP_SIZE, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); [1] https://lore.kernel.org/linux-mm/213b4567-46ce-f116-9cdf-bbd0c884eb3c@linux.intel.com/ [akpm@linux-foundation.org: suppress Kconfig whine] Link: https://lkml.kernel.org/r/20210518072034.31572-5-rppt@kernel.org Signed-off-by: Mike Rapoport Acked-by: Hagen Paul Pfeifer Acked-by: James Bottomley Cc: Alexander Viro Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christopher Lameter Cc: Dan Williams Cc: Dave Hansen Cc: Elena Reshetova Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: James Bottomley Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox Cc: Mark Rutland Cc: Michael Kerrisk Cc: Palmer Dabbelt Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Rick Edgecombe Cc: Roman Gushchin Cc: Shakeel Butt Cc: Shuah Khan Cc: Thomas Gleixner Cc: Tycho Andersen Cc: Will Deacon Cc: David Hildenbrand Cc: kernel test robot Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/secretmem.h | 48 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) create mode 100644 include/linux/secretmem.h (limited to 'include/linux') diff --git a/include/linux/secretmem.h b/include/linux/secretmem.h new file mode 100644 index 000000000000..e617b4afcc62 --- /dev/null +++ b/include/linux/secretmem.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _LINUX_SECRETMEM_H +#define _LINUX_SECRETMEM_H + +#ifdef CONFIG_SECRETMEM + +extern const struct address_space_operations secretmem_aops; + +static inline bool page_is_secretmem(struct page *page) +{ + struct address_space *mapping; + + /* + * Using page_mapping() is quite slow because of the actual call + * instruction and repeated compound_head(page) inside the + * page_mapping() function. + * We know that secretmem pages are not compound and LRU so we can + * save a couple of cycles here. + */ + if (PageCompound(page) || !PageLRU(page)) + return false; + + mapping = (struct address_space *) + ((unsigned long)page->mapping & ~PAGE_MAPPING_FLAGS); + + if (mapping != page->mapping) + return false; + + return mapping->a_ops == &secretmem_aops; +} + +bool vma_is_secretmem(struct vm_area_struct *vma); + +#else + +static inline bool vma_is_secretmem(struct vm_area_struct *vma) +{ + return false; +} + +static inline bool page_is_secretmem(struct page *page) +{ + return false; +} + +#endif /* CONFIG_SECRETMEM */ + +#endif /* _LINUX_SECRETMEM_H */ -- cgit v1.2.3 From 9a436f8ff6316c3c1a21a758e14ded930bd615d9 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 7 Jul 2021 18:08:07 -0700 Subject: PM: hibernate: disable when there are active secretmem users It is unsafe to allow saving of secretmem areas to the hibernation snapshot as they would be visible after the resume and this essentially will defeat the purpose of secret memory mappings. Prevent hibernation whenever there are active secret memory users. Link: https://lkml.kernel.org/r/20210518072034.31572-6-rppt@kernel.org Signed-off-by: Mike Rapoport Acked-by: David Hildenbrand Acked-by: James Bottomley Cc: Alexander Viro Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christopher Lameter Cc: Dan Williams Cc: Dave Hansen Cc: David Hildenbrand Cc: Elena Reshetova Cc: Hagen Paul Pfeifer Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: James Bottomley Cc: "Kirill A. Shutemov" Cc: Mark Rutland Cc: Matthew Wilcox Cc: Michael Kerrisk Cc: Palmer Dabbelt Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Rick Edgecombe Cc: Roman Gushchin Cc: Shakeel Butt Cc: Shuah Khan Cc: Thomas Gleixner Cc: Tycho Andersen Cc: Will Deacon Cc: kernel test robot Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/secretmem.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/secretmem.h b/include/linux/secretmem.h index e617b4afcc62..21c3771e6a56 100644 --- a/include/linux/secretmem.h +++ b/include/linux/secretmem.h @@ -30,6 +30,7 @@ static inline bool page_is_secretmem(struct page *page) } bool vma_is_secretmem(struct vm_area_struct *vma); +bool secretmem_active(void); #else @@ -43,6 +44,11 @@ static inline bool page_is_secretmem(struct page *page) return false; } +static inline bool secretmem_active(void) +{ + return false; +} + #endif /* CONFIG_SECRETMEM */ #endif /* _LINUX_SECRETMEM_H */ -- cgit v1.2.3 From 7bb7f2ac24a028b20fca466b9633847b289b156a Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 7 Jul 2021 18:08:11 -0700 Subject: arch, mm: wire up memfd_secret system call where relevant Wire up memfd_secret system call on architectures that define ARCH_HAS_SET_DIRECT_MAP, namely arm64, risc-v and x86. Link: https://lkml.kernel.org/r/20210518072034.31572-7-rppt@kernel.org Signed-off-by: Mike Rapoport Acked-by: Palmer Dabbelt Acked-by: Arnd Bergmann Acked-by: Catalin Marinas Acked-by: David Hildenbrand Acked-by: James Bottomley Cc: Alexander Viro Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Christopher Lameter Cc: Dan Williams Cc: Dave Hansen Cc: David Hildenbrand Cc: Elena Reshetova Cc: Hagen Paul Pfeifer Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: James Bottomley Cc: "Kirill A. Shutemov" Cc: Mark Rutland Cc: Matthew Wilcox Cc: Michael Kerrisk Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Rick Edgecombe Cc: Roman Gushchin Cc: Shakeel Butt Cc: Shuah Khan Cc: Thomas Gleixner Cc: Tycho Andersen Cc: Will Deacon Cc: kernel test robot Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 586128d5c3b8..69c9a7010081 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1050,6 +1050,7 @@ asmlinkage long sys_landlock_create_ruleset(const struct landlock_ruleset_attr _ asmlinkage long sys_landlock_add_rule(int ruleset_fd, enum landlock_rule_type rule_type, const void __user *rule_attr, __u32 flags); asmlinkage long sys_landlock_restrict_self(int ruleset_fd, __u32 flags); +asmlinkage long sys_memfd_secret(unsigned int flags); /* * Architecture-specific system calls -- cgit v1.2.3 From 06c8839815ac7aa2b44ea3bb3ee1820b08418f55 Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Wed, 7 Jul 2021 18:08:19 -0700 Subject: mm: fix spelling mistakes in header files Fix some spelling mistakes in comments: successfull ==> successful potentialy ==> potentially alloced ==> allocated indicies ==> indices wont ==> won't resposible ==> responsible dirtyness ==> dirtiness droppped ==> dropped alread ==> already occured ==> occurred interupts ==> interrupts extention ==> extension slighly ==> slightly Dont't ==> Don't Link: https://lkml.kernel.org/r/20210531034849.9549-2-thunder.leizhen@huawei.com Signed-off-by: Zhen Lei Cc: Jerome Glisse Cc: Mike Kravetz Cc: Dennis Zhou Cc: Tejun Heo Cc: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 4 ++-- include/linux/hmm.h | 2 +- include/linux/hugetlb.h | 6 +++--- include/linux/list_lru.h | 4 ++-- include/linux/mmu_notifier.h | 8 ++++---- include/linux/percpu-defs.h | 2 +- include/linux/shrinker.h | 2 +- include/linux/vmalloc.h | 4 ++-- 8 files changed, 16 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 4221888bdcd6..c24098c7acca 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -35,12 +35,12 @@ enum compact_result { COMPACT_CONTINUE, /* - * The full zone was compacted scanned but wasn't successfull to compact + * The full zone was compacted scanned but wasn't successful to compact * suitable pages. */ COMPACT_COMPLETE, /* - * direct compaction has scanned part of the zone but wasn't successfull + * direct compaction has scanned part of the zone but wasn't successful * to compact suitable pages. */ COMPACT_PARTIAL_SKIPPED, diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 866a0fa104c4..2fd2e91d5107 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -113,7 +113,7 @@ int hmm_range_fault(struct hmm_range *range); * HMM_RANGE_DEFAULT_TIMEOUT - default timeout (ms) when waiting for a range * * When waiting for mmu notifiers we need some kind of time out otherwise we - * could potentialy wait for ever, 1000ms ie 1s sounds like a long time to + * could potentially wait for ever, 1000ms ie 1s sounds like a long time to * wait already. */ #define HMM_RANGE_DEFAULT_TIMEOUT 1000 diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 8e0f32f935bd..f7ca1a3870ea 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -51,7 +51,7 @@ struct hugepage_subpool { long count; long max_hpages; /* Maximum huge pages or -1 if no maximum. */ long used_hpages; /* Used count against maximum, includes */ - /* both alloced and reserved pages. */ + /* both allocated and reserved pages. */ struct hstate *hstate; long min_hpages; /* Minimum huge pages or -1 if no minimum. */ long rsv_hpages; /* Pages reserved against global pool to */ @@ -85,7 +85,7 @@ struct resv_map { * by a resv_map's lock. The set of regions within the resv_map represent * reservations for huge pages, or huge pages that have already been * instantiated within the map. The from and to elements are huge page - * indicies into the associated mapping. from indicates the starting index + * indices into the associated mapping. from indicates the starting index * of the region. to represents the first index past the end of the region. * * For example, a file region structure with from == 0 and to == 4 represents @@ -797,7 +797,7 @@ static inline bool hugepage_migration_supported(struct hstate *h) * It determines whether or not a huge page should be placed on * movable zone or not. Movability of any huge page should be * required only if huge page size is supported for migration. - * There wont be any reason for the huge page to be movable if + * There won't be any reason for the huge page to be movable if * it is not migratable to start with. Also the size of the huge * page should be large enough to be placed under a movable zone * and still feasible enough to be migratable. Just the presence diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index 9dcaa3e582c9..1b5fceb565df 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -146,7 +146,7 @@ typedef enum lru_status (*list_lru_walk_cb)(struct list_head *item, * @lru: the lru pointer. * @nid: the node id to scan from. * @memcg: the cgroup to scan from. - * @isolate: callback function that is resposible for deciding what to do with + * @isolate: callback function that is responsible for deciding what to do with * the item currently being scanned * @cb_arg: opaque type that will be passed to @isolate * @nr_to_walk: how many items to scan. @@ -172,7 +172,7 @@ unsigned long list_lru_walk_one(struct list_lru *lru, * @lru: the lru pointer. * @nid: the node id to scan from. * @memcg: the cgroup to scan from. - * @isolate: callback function that is resposible for deciding what to do with + * @isolate: callback function that is responsible for deciding what to do with * the item currently being scanned * @cb_arg: opaque type that will be passed to @isolate * @nr_to_walk: how many items to scan. diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 6692da8d121d..45fc2c81e370 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -33,7 +33,7 @@ struct mmu_interval_notifier; * * @MMU_NOTIFY_SOFT_DIRTY: soft dirty accounting (still same page and same * access flags). User should soft dirty the page in the end callback to make - * sure that anyone relying on soft dirtyness catch pages that might be written + * sure that anyone relying on soft dirtiness catch pages that might be written * through non CPU mappings. * * @MMU_NOTIFY_RELEASE: used during mmu_interval_notifier invalidate to signal @@ -167,7 +167,7 @@ struct mmu_notifier_ops { * decrease the refcount. If the refcount is decreased on * invalidate_range_start() then the VM can free pages as page * table entries are removed. If the refcount is only - * droppped on invalidate_range_end() then the driver itself + * dropped on invalidate_range_end() then the driver itself * will drop the last refcount but it must take care to flush * any secondary tlb before doing the final free on the * page. Pages will no longer be referenced by the linux @@ -196,7 +196,7 @@ struct mmu_notifier_ops { * If invalidate_range() is used to manage a non-CPU TLB with * shared page-tables, it not necessary to implement the * invalidate_range_start()/end() notifiers, as - * invalidate_range() alread catches the points in time when an + * invalidate_range() already catches the points in time when an * external TLB range needs to be flushed. For more in depth * discussion on this see Documentation/vm/mmu_notifier.rst * @@ -369,7 +369,7 @@ mmu_interval_read_retry(struct mmu_interval_notifier *interval_sub, * mmu_interval_read_retry() will return true. * * False is not reliable and only suggests a collision may not have - * occured. It can be called many times and does not have to hold the user + * occurred. It can be called many times and does not have to hold the user * provided lock. * * This call can be used as part of loops and other expensive operations to diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index dff7040f629a..af1071535de8 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -412,7 +412,7 @@ do { \ * instead. * * If there is no other protection through preempt disable and/or disabling - * interupts then one of these RMW operations can show unexpected behavior + * interrupts then one of these RMW operations can show unexpected behavior * because the execution thread was rescheduled on another processor or an * interrupt occurred and the same percpu variable was modified from the * interrupt context. diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 1eac79ce57d4..9814fff58a69 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -4,7 +4,7 @@ /* * This struct is used to pass information from page reclaim to the shrinkers. - * We consolidate the values for easier extention later. + * We consolidate the values for easier extension later. * * The 'gfpmask' refers to the allocation we are currently trying to * fulfil. diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 1dabd6f22486..2644425b6dce 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -29,7 +29,7 @@ struct notifier_block; /* in notifier.h */ #define VM_NO_HUGE_VMAP 0x00000400 /* force PAGE_SIZE pte mapping */ /* - * VM_KASAN is used slighly differently depending on CONFIG_KASAN_VMALLOC. + * VM_KASAN is used slightly differently depending on CONFIG_KASAN_VMALLOC. * * If IS_ENABLED(CONFIG_KASAN_VMALLOC), VM_KASAN is set on a vm_struct after * shadow memory has been mapped. It's used to handle allocation errors so that @@ -247,7 +247,7 @@ static inline void set_vm_flush_reset_perms(void *addr) extern long vread(char *buf, char *addr, unsigned long count); /* - * Internals. Dont't use.. + * Internals. Don't use.. */ extern struct list_head vmap_area_list; extern __init void vm_area_add_early(struct vm_struct *vm); -- cgit v1.2.3 From 5748fbc533a32459582535b759887c45ca0fe556 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Wed, 7 Jul 2021 18:08:22 -0700 Subject: mm: add setup_initial_init_mm() helper Patch series "init_mm: cleanup ARCH's text/data/brk setup code", v3. Add setup_initial_init_mm() helper, then use it to cleanup the text, data and brk setup code. This patch (of 15): Add setup_initial_init_mm() helper to setup kernel text, data and brk. Link: https://lkml.kernel.org/r/20210608083418.137226-1-wangkefeng.wang@huawei.com Link: https://lkml.kernel.org/r/20210608083418.137226-2-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Cc: Souptick Joarder Cc: Christophe Leroy Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Ungerer Cc: Guo Ren Cc: Heiko Carstens Cc: Ingo Molnar Cc: Jonas Bonn Cc: Ley Foon Tan Cc: Michael Ellerman Cc: Nick Hu Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Rich Felker Cc: Russell King (Oracle) Cc: Stafford Horne Cc: Stefan Kristiansson Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vineet Gupta Cc: Will Deacon Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 788a0b1323d0..57453dba41b9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -238,6 +238,9 @@ int __add_to_page_cache_locked(struct page *page, struct address_space *mapping, #define lru_to_page(head) (list_entry((head)->prev, struct page, lru)) +void setup_initial_init_mm(void *start_code, void *end_code, + void *end_data, void *brk); + /* * Linux kernel virtual memory manager primitives. * The idea being to have a "virtual" mm in the same way -- cgit v1.2.3 From 7eaf3cf3b7c5a49b3ca60e1ceb3d1d7430cc9d0e Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Wed, 7 Jul 2021 18:09:10 -0700 Subject: buildid: add API to parse build ID out of buffer Add an API that can parse the build ID out of a buffer, instead of a vma, to support printing a kernel module's build ID for stack traces. Link: https://lkml.kernel.org/r/20210511003845.2429846-3-swboyd@chromium.org Signed-off-by: Stephen Boyd Cc: Jiri Olsa Cc: Alexei Starovoitov Cc: Jessica Yu Cc: Evan Green Cc: Hsin-Yi Wang Cc: Andy Shevchenko Cc: Baoquan He Cc: Borislav Petkov Cc: Catalin Marinas Cc: Dave Young Cc: Ingo Molnar Cc: Konstantin Khlebnikov Cc: Matthew Wilcox Cc: Petr Mladek Cc: Rasmus Villemoes Cc: Sasha Levin Cc: Sergey Senozhatsky Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Vivek Goyal Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/buildid.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/buildid.h b/include/linux/buildid.h index 40232f90db6e..ebce93f26d06 100644 --- a/include/linux/buildid.h +++ b/include/linux/buildid.h @@ -8,5 +8,6 @@ int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id, __u32 *size); +int build_id_parse_buf(const void *buf, unsigned char *build_id, u32 buf_size); #endif -- cgit v1.2.3 From 83cc6fa0049d7c5333a53f4d959a9457340284ea Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Wed, 7 Jul 2021 18:09:13 -0700 Subject: buildid: stash away kernels build ID on init Parse the kernel's build ID at initialization so that other code can print a hex format string representation of the running kernel's build ID. This will be used in the kdump and dump_stack code so that developers can easily locate the vmlinux debug symbols for a crash/stacktrace. [swboyd@chromium.org: fix implicit declaration of init_vmlinux_build_id()] Link: https://lkml.kernel.org/r/CAE-0n51UjTbay8N9FXAyE7_aR2+ePrQnKSRJ0gbmRsXtcLBVaw@mail.gmail.com Link: https://lkml.kernel.org/r/20210511003845.2429846-4-swboyd@chromium.org Signed-off-by: Stephen Boyd Acked-by: Baoquan He Cc: Jiri Olsa Cc: Alexei Starovoitov Cc: Jessica Yu Cc: Evan Green Cc: Hsin-Yi Wang Cc: Dave Young Cc: Vivek Goyal Cc: Andy Shevchenko Cc: Borislav Petkov Cc: Catalin Marinas Cc: Ingo Molnar Cc: Konstantin Khlebnikov Cc: Matthew Wilcox Cc: Petr Mladek Cc: Rasmus Villemoes Cc: Sasha Levin Cc: Sergey Senozhatsky Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/buildid.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/buildid.h b/include/linux/buildid.h index ebce93f26d06..f375900cf9ed 100644 --- a/include/linux/buildid.h +++ b/include/linux/buildid.h @@ -10,4 +10,7 @@ int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id, __u32 *size); int build_id_parse_buf(const void *buf, unsigned char *build_id, u32 buf_size); +extern unsigned char vmlinux_build_id[BUILD_ID_SIZE_MAX]; +void init_vmlinux_build_id(void); + #endif -- cgit v1.2.3 From 22f4e66df79d0a730fcd6c17f3403b5ab8c72ced Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Wed, 7 Jul 2021 18:09:17 -0700 Subject: dump_stack: add vmlinux build ID to stack traces Add the running kernel's build ID[1] to the stacktrace information header. This makes it simpler for developers to locate the vmlinux with full debuginfo for a particular kernel stacktrace. Combined with scripts/decode_stracktrace.sh, a developer can download the correct vmlinux from a debuginfod[2] server and find the exact file and line number for the functions plus offsets in a stacktrace. This is especially useful for pstore crash debugging where the kernel crashes are recorded in the pstore logs and the recovery kernel is different or the debuginfo doesn't exist on the device due to space concerns (the data can be large and a security concern). The stacktrace can be analyzed after the crash by using the build ID to find the matching vmlinux and understand where in the function something went wrong. Example stacktrace from lkdtm: WARNING: CPU: 4 PID: 3255 at drivers/misc/lkdtm/bugs.c:83 lkdtm_WARNING+0x28/0x30 [lkdtm] Modules linked in: lkdtm rfcomm algif_hash algif_skcipher af_alg xt_cgroup uinput xt_MASQUERADE CPU: 4 PID: 3255 Comm: bash Not tainted 5.11 #3 aa23f7a1231c229de205662d5a9e0d4c580f19a1 Hardware name: Google Lazor (rev3+) with KB Backlight (DT) pstate: 00400009 (nzcv daif +PAN -UAO -TCO BTYPE=--) pc : lkdtm_WARNING+0x28/0x30 [lkdtm] The hex string aa23f7a1231c229de205662d5a9e0d4c580f19a1 is the build ID, following the kernel version number. Put it all behind a config option, STACKTRACE_BUILD_ID, so that kernel developers can remove this information if they decide it is too much. Link: https://lkml.kernel.org/r/20210511003845.2429846-5-swboyd@chromium.org Link: https://fedoraproject.org/wiki/Releases/FeatureBuildId [1] Link: https://sourceware.org/elfutils/Debuginfod.html [2] Signed-off-by: Stephen Boyd Cc: Jiri Olsa Cc: Alexei Starovoitov Cc: Jessica Yu Cc: Evan Green Cc: Hsin-Yi Wang Cc: Petr Mladek Cc: Steven Rostedt Cc: Andy Shevchenko Cc: Matthew Wilcox Cc: Baoquan He Cc: Borislav Petkov Cc: Catalin Marinas Cc: Dave Young Cc: Ingo Molnar Cc: Konstantin Khlebnikov Cc: Rasmus Villemoes Cc: Sasha Levin Cc: Sergey Senozhatsky Cc: Thomas Gleixner Cc: Vivek Goyal Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/buildid.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/buildid.h b/include/linux/buildid.h index f375900cf9ed..3e8d77a93ec4 100644 --- a/include/linux/buildid.h +++ b/include/linux/buildid.h @@ -10,7 +10,11 @@ int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id, __u32 *size); int build_id_parse_buf(const void *buf, unsigned char *build_id, u32 buf_size); +#if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID) extern unsigned char vmlinux_build_id[BUILD_ID_SIZE_MAX]; void init_vmlinux_build_id(void); +#else +static inline void init_vmlinux_build_id(void) { } +#endif #endif -- cgit v1.2.3 From 9294523e3768030ae8afb84110bcecc66425a647 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Wed, 7 Jul 2021 18:09:20 -0700 Subject: module: add printk formats to add module build ID to stacktraces Let's make kernel stacktraces easier to identify by including the build ID[1] of a module if the stacktrace is printing a symbol from a module. This makes it simpler for developers to locate a kernel module's full debuginfo for a particular stacktrace. Combined with scripts/decode_stracktrace.sh, a developer can download the matching debuginfo from a debuginfod[2] server and find the exact file and line number for the functions plus offsets in a stacktrace that match the module. This is especially useful for pstore crash debugging where the kernel crashes are recorded in something like console-ramoops and the recovery kernel/modules are different or the debuginfo doesn't exist on the device due to space concerns (the debuginfo can be too large for space limited devices). Originally, I put this on the %pS format, but that was quickly rejected given that %pS is used in other places such as ftrace where build IDs aren't meaningful. There was some discussions on the list to put every module build ID into the "Modules linked in:" section of the stacktrace message but that quickly becomes very hard to read once you have more than three or four modules linked in. It also provides too much information when we don't expect each module to be traversed in a stacktrace. Having the build ID for modules that aren't important just makes things messy. Splitting it to multiple lines for each module quickly explodes the number of lines printed in an oops too, possibly wrapping the warning off the console. And finally, trying to stash away each module used in a callstack to provide the ID of each symbol printed is cumbersome and would require changes to each architecture to stash away modules and return their build IDs once unwinding has completed. Instead, we opt for the simpler approach of introducing new printk formats '%pS[R]b' for "pointer symbolic backtrace with module build ID" and '%pBb' for "pointer backtrace with module build ID" and then updating the few places in the architecture layer where the stacktrace is printed to use this new format. Before: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm] direct_entry+0x16c/0x1b4 [lkdtm] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 After: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] direct_entry+0x16c/0x1b4 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 [akpm@linux-foundation.org: fix build with CONFIG_MODULES=n, tweak code layout] [rdunlap@infradead.org: fix build when CONFIG_MODULES is not set] Link: https://lkml.kernel.org/r/20210513171510.20328-1-rdunlap@infradead.org [akpm@linux-foundation.org: make kallsyms_lookup_buildid() static] [cuibixuan@huawei.com: fix build error when CONFIG_SYSFS is disabled] Link: https://lkml.kernel.org/r/20210525105049.34804-1-cuibixuan@huawei.com Link: https://lkml.kernel.org/r/20210511003845.2429846-6-swboyd@chromium.org Link: https://fedoraproject.org/wiki/Releases/FeatureBuildId [1] Link: https://sourceware.org/elfutils/Debuginfod.html [2] Signed-off-by: Stephen Boyd Signed-off-by: Bixuan Cui Signed-off-by: Randy Dunlap Cc: Jiri Olsa Cc: Alexei Starovoitov Cc: Jessica Yu Cc: Evan Green Cc: Hsin-Yi Wang Cc: Petr Mladek Cc: Steven Rostedt Cc: Sergey Senozhatsky Cc: Andy Shevchenko Cc: Rasmus Villemoes Cc: Matthew Wilcox Cc: Baoquan He Cc: Borislav Petkov Cc: Catalin Marinas Cc: Dave Young Cc: Ingo Molnar Cc: Konstantin Khlebnikov Cc: Sasha Levin Cc: Thomas Gleixner Cc: Vivek Goyal Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kallsyms.h | 21 +++++++++++++++++++-- include/linux/module.h | 9 ++++++++- 2 files changed, 27 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index 465060acc981..a1d6fc82d7f0 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -7,6 +7,7 @@ #define _LINUX_KALLSYMS_H #include +#include #include #include #include @@ -15,8 +16,10 @@ #include #define KSYM_NAME_LEN 128 -#define KSYM_SYMBOL_LEN (sizeof("%s+%#lx/%#lx [%s]") + (KSYM_NAME_LEN - 1) + \ - 2*(BITS_PER_LONG*3/10) + (MODULE_NAME_LEN - 1) + 1) +#define KSYM_SYMBOL_LEN (sizeof("%s+%#lx/%#lx [%s %s]") + \ + (KSYM_NAME_LEN - 1) + \ + 2*(BITS_PER_LONG*3/10) + (MODULE_NAME_LEN - 1) + \ + (BUILD_ID_SIZE_MAX * 2) + 1) struct cred; struct module; @@ -91,8 +94,10 @@ const char *kallsyms_lookup(unsigned long addr, /* Look up a kernel symbol and return it in a text buffer. */ extern int sprint_symbol(char *buffer, unsigned long address); +extern int sprint_symbol_build_id(char *buffer, unsigned long address); extern int sprint_symbol_no_offset(char *buffer, unsigned long address); extern int sprint_backtrace(char *buffer, unsigned long address); +extern int sprint_backtrace_build_id(char *buffer, unsigned long address); int lookup_symbol_name(unsigned long addr, char *symname); int lookup_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name); @@ -128,6 +133,12 @@ static inline int sprint_symbol(char *buffer, unsigned long addr) return 0; } +static inline int sprint_symbol_build_id(char *buffer, unsigned long address) +{ + *buffer = '\0'; + return 0; +} + static inline int sprint_symbol_no_offset(char *buffer, unsigned long addr) { *buffer = '\0'; @@ -140,6 +151,12 @@ static inline int sprint_backtrace(char *buffer, unsigned long addr) return 0; } +static inline int sprint_backtrace_build_id(char *buffer, unsigned long addr) +{ + *buffer = '\0'; + return 0; +} + static inline int lookup_symbol_name(unsigned long addr, char *symname) { return -ERANGE; diff --git a/include/linux/module.h b/include/linux/module.h index 8100bb477d86..8a298d820dbc 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -11,6 +11,7 @@ #include #include +#include #include #include #include @@ -369,6 +370,11 @@ struct module { /* Unique handle for this module */ char name[MODULE_NAME_LEN]; +#ifdef CONFIG_STACKTRACE_BUILD_ID + /* Module build ID */ + unsigned char build_id[BUILD_ID_SIZE_MAX]; +#endif + /* Sysfs stuff. */ struct module_kobject mkobj; struct module_attribute *modinfo_attrs; @@ -636,7 +642,7 @@ void *dereference_module_function_descriptor(struct module *mod, void *ptr); const char *module_address_lookup(unsigned long addr, unsigned long *symbolsize, unsigned long *offset, - char **modname, + char **modname, const unsigned char **modbuildid, char *namebuf); int lookup_module_symbol_name(unsigned long addr, char *symname); int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name); @@ -740,6 +746,7 @@ static inline const char *module_address_lookup(unsigned long addr, unsigned long *symbolsize, unsigned long *offset, char **modname, + const unsigned char **modbuildid, char *namebuf) { return NULL; -- cgit v1.2.3 From 44e8a5e9120bf4fc1ab046b648b0598e6652c36e Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Wed, 7 Jul 2021 18:09:49 -0700 Subject: kdump: use vmlinux_build_id to simplify We can use the vmlinux_build_id array here now instead of open coding it. This mostly consolidates code. Link: https://lkml.kernel.org/r/20210511003845.2429846-14-swboyd@chromium.org Signed-off-by: Stephen Boyd Cc: Jiri Olsa Cc: Alexei Starovoitov Cc: Jessica Yu Cc: Evan Green Cc: Hsin-Yi Wang Cc: Dave Young Cc: Baoquan He Cc: Vivek Goyal Cc: Andy Shevchenko Cc: Borislav Petkov Cc: Catalin Marinas Cc: Ingo Molnar Cc: Konstantin Khlebnikov Cc: Matthew Wilcox Cc: Petr Mladek Cc: Rasmus Villemoes Cc: Sasha Levin Cc: Sergey Senozhatsky Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/buildid.h | 2 +- include/linux/crash_core.h | 12 ++++++------ 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/buildid.h b/include/linux/buildid.h index 3e8d77a93ec4..3b7a0ff4642f 100644 --- a/include/linux/buildid.h +++ b/include/linux/buildid.h @@ -10,7 +10,7 @@ int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id, __u32 *size); int build_id_parse_buf(const void *buf, unsigned char *build_id, u32 buf_size); -#if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID) +#if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID) || IS_ENABLED(CONFIG_CRASH_CORE) extern unsigned char vmlinux_build_id[BUILD_ID_SIZE_MAX]; void init_vmlinux_build_id(void); #else diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h index 206bde8308b2..de62a722431e 100644 --- a/include/linux/crash_core.h +++ b/include/linux/crash_core.h @@ -38,8 +38,12 @@ phys_addr_t paddr_vmcoreinfo_note(void); #define VMCOREINFO_OSRELEASE(value) \ vmcoreinfo_append_str("OSRELEASE=%s\n", value) -#define VMCOREINFO_BUILD_ID(value) \ - vmcoreinfo_append_str("BUILD-ID=%s\n", value) +#define VMCOREINFO_BUILD_ID() \ + ({ \ + static_assert(sizeof(vmlinux_build_id) == 20); \ + vmcoreinfo_append_str("BUILD-ID=%20phN\n", vmlinux_build_id); \ + }) + #define VMCOREINFO_PAGESIZE(value) \ vmcoreinfo_append_str("PAGESIZE=%ld\n", value) #define VMCOREINFO_SYMBOL(name) \ @@ -69,10 +73,6 @@ extern unsigned char *vmcoreinfo_data; extern size_t vmcoreinfo_size; extern u32 *vmcoreinfo_note; -/* raw contents of kernel .notes section */ -extern const void __start_notes __weak; -extern const void __stop_notes __weak; - Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type, void *data, size_t data_len); void final_note(Elf_Word *buf); -- cgit v1.2.3 From 9cf6fa2458443118b84090aa1bf7a3630b5940e8 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 7 Jul 2021 18:09:53 -0700 Subject: mm: rename pud_page_vaddr to pud_pgtable and make it return pmd_t * No functional change in this patch. [aneesh.kumar@linux.ibm.com: fix] Link: https://lkml.kernel.org/r/87wnqtnb60.fsf@linux.ibm.com [sfr@canb.auug.org.au: another fix] Link: https://lkml.kernel.org/r/20210619134410.89559-1-aneesh.kumar@linux.ibm.com Link: https://lkml.kernel.org/r/20210615110859.320299-1-aneesh.kumar@linux.ibm.com Link: https://lore.kernel.org/linuxppc-dev/CAHk-=wi+J+iodze9FtjM3Zi4j4OeS+qqbKxME9QN4roxPEXH9Q@mail.gmail.com/ Signed-off-by: Aneesh Kumar K.V Signed-off-by: Stephen Rothwell Cc: Christophe Leroy Cc: Hugh Dickins Cc: Joel Fernandes Cc: Kalesh Singh Cc: Kirill A. Shutemov Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pgtable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index e82660f7b9e4..c7c992ada1fe 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -106,7 +106,7 @@ static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address) #ifndef pmd_offset static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) { - return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(address); + return pud_pgtable(*pud) + pmd_index(address); } #define pmd_offset pmd_offset #endif -- cgit v1.2.3 From dc4875f0e791de554bdc45aa1dbd6e45e107e50f Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 7 Jul 2021 18:09:56 -0700 Subject: mm: rename p4d_page_vaddr to p4d_pgtable and make it return pud_t * No functional change in this patch. [aneesh.kumar@linux.ibm.com: m68k build error reported by kernel robot] Link: https://lkml.kernel.org/r/87tulxnb2v.fsf@linux.ibm.com Link: https://lkml.kernel.org/r/20210615110859.320299-2-aneesh.kumar@linux.ibm.com Link: https://lore.kernel.org/linuxppc-dev/CAHk-=wi+J+iodze9FtjM3Zi4j4OeS+qqbKxME9QN4roxPEXH9Q@mail.gmail.com/ Signed-off-by: Aneesh Kumar K.V Cc: Christophe Leroy Cc: Hugh Dickins Cc: Joel Fernandes Cc: Kalesh Singh Cc: Kirill A. Shutemov Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pgtable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index c7c992ada1fe..d147480cdefc 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -114,7 +114,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) #ifndef pud_offset static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address) { - return (pud_t *)p4d_page_vaddr(*p4d) + pud_index(address); + return p4d_pgtable(*p4d) + pud_index(address); } #define pud_offset pud_offset #endif -- cgit v1.2.3 From f263a81451c12da5a342d90572e317e611846f2c Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Wed, 7 Jul 2021 15:38:47 -0700 Subject: bpf: Track subprog poke descriptors correctly and fix use-after-free Subprograms are calling map_poke_track(), but on program release there is no hook to call map_poke_untrack(). However, on program release, the aux memory (and poke descriptor table) is freed even though we still have a reference to it in the element list of the map aux data. When we run map_poke_run(), we then end up accessing free'd memory, triggering KASAN in prog_array_map_poke_run(): [...] [ 402.824689] BUG: KASAN: use-after-free in prog_array_map_poke_run+0xc2/0x34e [ 402.824698] Read of size 4 at addr ffff8881905a7940 by task hubble-fgs/4337 [ 402.824705] CPU: 1 PID: 4337 Comm: hubble-fgs Tainted: G I 5.12.0+ #399 [ 402.824715] Call Trace: [ 402.824719] dump_stack+0x93/0xc2 [ 402.824727] print_address_description.constprop.0+0x1a/0x140 [ 402.824736] ? prog_array_map_poke_run+0xc2/0x34e [ 402.824740] ? prog_array_map_poke_run+0xc2/0x34e [ 402.824744] kasan_report.cold+0x7c/0xd8 [ 402.824752] ? prog_array_map_poke_run+0xc2/0x34e [ 402.824757] prog_array_map_poke_run+0xc2/0x34e [ 402.824765] bpf_fd_array_map_update_elem+0x124/0x1a0 [...] The elements concerned are walked as follows: for (i = 0; i < elem->aux->size_poke_tab; i++) { poke = &elem->aux->poke_tab[i]; [...] The access to size_poke_tab is a 4 byte read, verified by checking offsets in the KASAN dump: [ 402.825004] The buggy address belongs to the object at ffff8881905a7800 which belongs to the cache kmalloc-1k of size 1024 [ 402.825008] The buggy address is located 320 bytes inside of 1024-byte region [ffff8881905a7800, ffff8881905a7c00) The pahole output of bpf_prog_aux: struct bpf_prog_aux { [...] /* --- cacheline 5 boundary (320 bytes) --- */ u32 size_poke_tab; /* 320 4 */ [...] In general, subprograms do not necessarily manage their own data structures. For example, BTF func_info and linfo are just pointers to the main program structure. This allows reference counting and cleanup to be done on the latter which simplifies their management a bit. The aux->poke_tab struct, however, did not follow this logic. The initial proposed fix for this use-after-free bug further embedded poke data tracking into the subprogram with proper reference counting. However, Daniel and Alexei questioned why we were treating these objects special; I agree, its unnecessary. The fix here removes the per subprogram poke table allocation and map tracking and instead simply points the aux->poke_tab pointer at the main programs poke table. This way, map tracking is simplified to the main program and we do not need to manage them per subprogram. This also means, bpf_prog_free_deferred(), which unwinds the program reference counting and kfrees objects, needs to ensure that we don't try to double free the poke_tab when free'ing the subprog structures. This is easily solved by NULL'ing the poke_tab pointer. The second detail is to ensure that per subprogram JIT logic only does fixups on poke_tab[] entries it owns. To do this, we add a pointer in the poke structure to point at the subprogram value so JITs can easily check while walking the poke_tab structure if the current entry belongs to the current program. The aux pointer is stable and therefore suitable for such comparison. On the jit_subprogs() error path, we omit cleaning up the poke->aux field because these are only ever referenced from the JIT side, but on error we will never make it to the JIT, so its fine to leave them dangling. Removing these pointers would complicate the error path for no reason. However, we do need to untrack all poke descriptors from the main program as otherwise they could race with the freeing of JIT memory from the subprograms. Lastly, a748c6975dea3 ("bpf: propagate poke descriptors to subprograms") had an off-by-one on the subprogram instruction index range check as it was testing 'insn_idx >= subprog_start && insn_idx <= subprog_end'. However, subprog_end is the next subprogram's start instruction. Fixes: a748c6975dea3 ("bpf: propagate poke descriptors to subprograms") Signed-off-by: John Fastabend Signed-off-by: Alexei Starovoitov Co-developed-by: Daniel Borkmann Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210707223848.14580-2-john.fastabend@gmail.com --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f309fc1509f2..e8e2b0393ca9 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -780,6 +780,7 @@ struct bpf_jit_poke_descriptor { void *tailcall_target; void *tailcall_bypass; void *bypass_addr; + void *aux; union { struct { struct bpf_map *map; -- cgit v1.2.3 From a5de4be0aaaa66a2fa98e8a33bdbed3bd0682804 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Sun, 11 Jul 2021 18:38:15 +0200 Subject: net: phy: marvell10g: fix differentiation of 88X3310 from 88X3340 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It seems that we cannot differentiate 88X3310 from 88X3340 by simply looking at bit 3 of revision ID. This only works on revisions A0 and A1. On revision B0, this bit is always 1. Instead use the 3.d00d register for differentiation, since this register contains information about number of ports on the device. Fixes: 9885d016ffa9 ("net: phy: marvell10g: add separate structure for 88X3340") Signed-off-by: Marek Behún Reported-by: Matteo Croce Tested-by: Matteo Croce Signed-off-by: David S. Miller --- include/linux/marvell_phy.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h index acee44b9db26..0f06c2287b52 100644 --- a/include/linux/marvell_phy.h +++ b/include/linux/marvell_phy.h @@ -22,14 +22,10 @@ #define MARVELL_PHY_ID_88E1545 0x01410ea0 #define MARVELL_PHY_ID_88E1548P 0x01410ec0 #define MARVELL_PHY_ID_88E3016 0x01410e60 +#define MARVELL_PHY_ID_88X3310 0x002b09a0 #define MARVELL_PHY_ID_88E2110 0x002b09b0 #define MARVELL_PHY_ID_88X2222 0x01410f10 -/* PHY IDs and mask for Alaska 10G PHYs */ -#define MARVELL_PHY_ID_88X33X0_MASK 0xfffffff8 -#define MARVELL_PHY_ID_88X3310 0x002b09a0 -#define MARVELL_PHY_ID_88X3340 0x002b09a8 - /* Marvel 88E1111 in Finisar SFP module with modified PHY ID */ #define MARVELL_PHY_ID_88E1111_FINISAR 0x01ff0cc0 -- cgit v1.2.3 From 0238bcf80e972f2ce25d767e54f89a9e49773f6e Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Mon, 5 Jul 2021 22:42:47 +0300 Subject: ASoC: ti: davinci-mcasp: Add support for the OMAP4 version of McASP There is a single McASP on OMAP4 (and OMAP5) which is configured to only support DIT playback mode on a single serializer. Add 0x200 offset to DAT port address as the TRM suggests it. Signed-off-by: Peter Ujfalusi Link: https://lore.kernel.org/r/20210705194249.2385-4-peter.ujfalusi@gmail.com Signed-off-by: Mark Brown --- include/linux/platform_data/davinci_asp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/davinci_asp.h b/include/linux/platform_data/davinci_asp.h index 5d1fb0d78a22..76b13ef67562 100644 --- a/include/linux/platform_data/davinci_asp.h +++ b/include/linux/platform_data/davinci_asp.h @@ -96,6 +96,7 @@ enum { MCASP_VERSION_2, /* DA8xx/OMAPL1x */ MCASP_VERSION_3, /* TI81xx/AM33xx */ MCASP_VERSION_4, /* DRA7xxx */ + MCASP_VERSION_OMAP, /* OMAP4/5 */ }; enum mcbsp_clk_input_pin { -- cgit v1.2.3 From 4ff75a29976590bc7afe3ed75d547c1f2a924c75 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Fri, 25 Jun 2021 15:23:22 +0300 Subject: regulator: devres: remove devm_regulator_unregister() function This API hook isn't used anywhere and most-likely exists because of the general principle of C APIs, where if an API function does an allocation/registration, it must also have an equivalent deallocation/deregistration counterpart. For devm_ functions this isn't all that true (for all cases), as the idea of these function is to provide an auto-cleanup logic on drivers/system de-init. Removing this also discourages any weird logic that could be created with such an API function. Signed-off-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20210625122324.327585-3-aardelean@deviqon.com Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 4aec20387857..5447a6b33fa0 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -645,7 +645,6 @@ devm_regulator_register(struct device *dev, const struct regulator_desc *regulator_desc, const struct regulator_config *config); void regulator_unregister(struct regulator_dev *rdev); -void devm_regulator_unregister(struct device *dev, struct regulator_dev *rdev); int regulator_notifier_call_chain(struct regulator_dev *rdev, unsigned long event, void *data); -- cgit v1.2.3 From eed43b96ede9c3f018ad24149de83f24b86ad729 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Fri, 25 Jun 2021 15:23:23 +0300 Subject: regulator: devres: remove devm_regulator_bulk_unregister_supply_alias() This API hook isn't used anywhere and most-likely exists because of the general principle of C APIs, where if an API function does an allocation/registration, it must also have an equivalent deallocation/deregistration counterpart. For devm_ functions this isn't all that true (for all cases), as the idea of these function is to provide an auto-cleanup logic on drivers/system de-init. Removing this also discourages any weird logic that could be created with such an API function. Signed-off-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20210625122324.327585-4-aardelean@deviqon.com Signed-off-by: Mark Brown --- include/linux/regulator/consumer.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index f72ca73631be..98518b3f2828 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -230,9 +230,6 @@ int devm_regulator_bulk_register_supply_alias(struct device *dev, struct device *alias_dev, const char *const *alias_id, int num_id); -void devm_regulator_bulk_unregister_supply_alias(struct device *dev, - const char *const *id, - int num_id); /* regulator output control and status */ int __must_check regulator_enable(struct regulator *regulator); @@ -422,11 +419,6 @@ static inline int devm_regulator_bulk_register_supply_alias(struct device *dev, return 0; } -static inline void devm_regulator_bulk_unregister_supply_alias( - struct device *dev, const char *const *id, int num_id) -{ -} - static inline int regulator_enable(struct regulator *regulator) { return 0; -- cgit v1.2.3 From 4d9f4d1de3ceb84fa6ce68177a26b8fac6a71290 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Fri, 25 Jun 2021 15:23:24 +0300 Subject: regulator: devres: unexport devm_regulator_unregister_supply_alias() This API hook isn't used anywhere outside of the regulator devres code. This function is needed for the devm_regulator_bulk_register_supply_alias() function on the error path, to cleanup any previously registered supply aliases. This change makes the devm_regulator_unregister_supply_alias() local to the regulator core framework, to avoid it being used in any weird logic. It's also removing the doc-string for devm_regulator_unregister_supply_alias(), since it doesn't need to be documented anymore, as no other external consumer should use it. Signed-off-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20210625122324.327585-5-aardelean@deviqon.com Signed-off-by: Mark Brown --- include/linux/regulator/consumer.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 98518b3f2828..bbf6590a6dec 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -222,8 +222,6 @@ void regulator_bulk_unregister_supply_alias(struct device *dev, int devm_regulator_register_supply_alias(struct device *dev, const char *id, struct device *alias_dev, const char *alias_id); -void devm_regulator_unregister_supply_alias(struct device *dev, - const char *id); int devm_regulator_bulk_register_supply_alias(struct device *dev, const char *const *id, @@ -405,11 +403,6 @@ static inline int devm_regulator_register_supply_alias(struct device *dev, return 0; } -static inline void devm_regulator_unregister_supply_alias(struct device *dev, - const char *id) -{ -} - static inline int devm_regulator_bulk_register_supply_alias(struct device *dev, const char *const *id, struct device *alias_dev, -- cgit v1.2.3 From 6eb891cf73bd2ecc877e9916951a19f3e4f3c493 Mon Sep 17 00:00:00 2001 From: ChiYuan Huang Date: Tue, 6 Jul 2021 14:45:39 +0800 Subject: regulator: rt5033: Use linear ranges to map all voltage selection Instead of linear mapping, Use linear range to map all voltage selection. Signed-off-by: ChiYuan Huang Reviewed-by: Axel Lin Acked-by: Lee Jones Link: https://lore.kernel.org/r/1625553939-9109-1-git-send-email-u0084500@gmail.com Signed-off-by: Mark Brown --- include/linux/mfd/rt5033-private.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/rt5033-private.h b/include/linux/mfd/rt5033-private.h index 40a0c2dfb80f..2d1895c3efbf 100644 --- a/include/linux/mfd/rt5033-private.h +++ b/include/linux/mfd/rt5033-private.h @@ -200,13 +200,13 @@ enum rt5033_reg { #define RT5033_REGULATOR_BUCK_VOLTAGE_MIN 1000000U #define RT5033_REGULATOR_BUCK_VOLTAGE_MAX 3000000U #define RT5033_REGULATOR_BUCK_VOLTAGE_STEP 100000U -#define RT5033_REGULATOR_BUCK_VOLTAGE_STEP_NUM 21 +#define RT5033_REGULATOR_BUCK_VOLTAGE_STEP_NUM 32 /* RT5033 regulator LDO output voltage uV */ #define RT5033_REGULATOR_LDO_VOLTAGE_MIN 1200000U #define RT5033_REGULATOR_LDO_VOLTAGE_MAX 3000000U #define RT5033_REGULATOR_LDO_VOLTAGE_STEP 100000U -#define RT5033_REGULATOR_LDO_VOLTAGE_STEP_NUM 19 +#define RT5033_REGULATOR_LDO_VOLTAGE_STEP_NUM 32 /* RT5033 regulator SAFE LDO output voltage uV */ #define RT5033_REGULATOR_SAFE_LDO_VOLTAGE 4900000U -- cgit v1.2.3 From 78bbb7c345ab630cfe8b272c6179bf8b19a6c8aa Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 27 Jun 2021 18:54:22 -0700 Subject: regulator: machine.h: fix kernel-doc "bad line" Fix warning caused by a blank/empty line: ../include/linux/regulator/machine.h:115: warning: bad line: Signed-off-by: Randy Dunlap Link: https://lore.kernel.org/r/20210628015422.8845-1-rdunlap@infradead.org Signed-off-by: Mark Brown --- include/linux/regulator/machine.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h index 68b4a514a410..621b7f4a3639 100644 --- a/include/linux/regulator/machine.h +++ b/include/linux/regulator/machine.h @@ -112,7 +112,7 @@ struct notification_limit { * @over_voltage_limits: Limits for acting on over voltage. * @under_voltage_limits: Limits for acting on under voltage. * @temp_limits: Limits for acting on over temperature. - + * * @max_spread: Max possible spread between coupled regulators * @max_uV_step: Max possible step change in voltage * @valid_modes_mask: Mask of modes which may be configured by consumers. -- cgit v1.2.3 From 8dd591ad0104593f315b6b2ab636a18c002f7d86 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 28 Jun 2021 14:05:20 -0700 Subject: spi: : add missing struct kernel-doc entry Fix kernel-doc warning in spi.h by adding the missing kernel-doc entry and also correct the original comment so that they both indicate the correct polarity of the flag. ../include/linux/spi/spi.h:673: warning: Function parameter or member 'devm_allocated' not described in 'spi_controller' Fixes: 794aaf01444d ("spi: Fix use-after-free with devm_spi_alloc_*") Signed-off-by: Randy Dunlap Cc: William A. Kennington III Cc: Mark Brown Cc: linux-spi@vger.kernel.org Cc: Lukas Wunner Reviewed-by: Lukas Wunner Link: https://lore.kernel.org/r/20210628210520.5712-1-rdunlap@infradead.org Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 97b8d12b5f2b..3a81b5d1c3cb 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -339,6 +339,7 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * @max_speed_hz: Highest supported transfer speed * @flags: other constraints relevant to this driver * @slave: indicates that this is an SPI slave controller + * @devm_allocated: whether the allocation of this struct is devres-managed * @max_transfer_size: function that returns the max transfer size for * a &spi_device; may be %NULL, so the default %SIZE_MAX will be used. * @max_message_size: function that returns the max message size for @@ -511,7 +512,7 @@ struct spi_controller { #define SPI_MASTER_GPIO_SS BIT(5) /* GPIO CS must select slave */ - /* flag indicating this is a non-devres managed controller */ + /* flag indicating if the allocation of this struct is devres-managed */ bool devm_allocated; /* flag indicating this is an SPI slave controller */ -- cgit v1.2.3 From ce7d0008c2356626f69f37ef1afce8fbc83fe142 Mon Sep 17 00:00:00 2001 From: Wesley Cheng Date: Sat, 10 Jul 2021 02:13:10 -0700 Subject: usb: gadget: udc: core: Introduce check_config to verify USB configuration Some UDCs may have constraints on how many high bandwidth endpoints it can support in a certain configuration. This API allows for the composite driver to pass down the total number of endpoints to the UDC so it can verify it has the required resources to support the configuration. Signed-off-by: Wesley Cheng Link: https://lore.kernel.org/r/1625908395-5498-2-git-send-email-wcheng@codeaurora.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/gadget.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 75c7538e350a..776851e57741 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -329,6 +329,7 @@ struct usb_gadget_ops { struct usb_ep *(*match_ep)(struct usb_gadget *, struct usb_endpoint_descriptor *, struct usb_ss_ep_comp_descriptor *); + int (*check_config)(struct usb_gadget *gadget); }; /** @@ -608,6 +609,7 @@ int usb_gadget_connect(struct usb_gadget *gadget); int usb_gadget_disconnect(struct usb_gadget *gadget); int usb_gadget_deactivate(struct usb_gadget *gadget); int usb_gadget_activate(struct usb_gadget *gadget); +int usb_gadget_check_config(struct usb_gadget *gadget); #else static inline int usb_gadget_frame_number(struct usb_gadget *gadget) { return 0; } @@ -631,6 +633,8 @@ static inline int usb_gadget_deactivate(struct usb_gadget *gadget) { return 0; } static inline int usb_gadget_activate(struct usb_gadget *gadget) { return 0; } +static inline int usb_gadget_check_config(struct usb_gadget *gadget) +{ return 0; } #endif /* CONFIG_USB_GADGET */ /*-------------------------------------------------------------------------*/ -- cgit v1.2.3 From fe794e39548308e77e570fdf645d516554b3f873 Mon Sep 17 00:00:00 2001 From: Wesley Cheng Date: Sat, 10 Jul 2021 02:13:13 -0700 Subject: of: Add stub for of_add_property() If building with OF Kconfig disabled, this can lead to errors for drivers utilizing of_add_property(). Add a stub for the add API, as it exists for the remove variant as well, and to avoid compliation issues. Also, export this API so that it can be used by modules. Signed-off-by: Wesley Cheng Link: https://lore.kernel.org/r/1625908395-5498-5-git-send-email-wcheng@codeaurora.org Signed-off-by: Greg Kroah-Hartman --- include/linux/of.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 9c2e71e202d1..0e786b60bd5d 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -946,6 +946,11 @@ static inline int of_machine_is_compatible(const char *compat) return 0; } +static inline int of_add_property(struct device_node *np, struct property *prop) +{ + return 0; +} + static inline int of_remove_property(struct device_node *np, struct property *prop) { return 0; -- cgit v1.2.3 From 79789db03fdd77510cfb35cb4b3bd52b6c50c901 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 12 Jul 2021 16:32:07 +0100 Subject: mm: Make copy_huge_page() always available Rewrite copy_huge_page() and move it into mm/util.c so it's always available. Fixes an exposure of uninitialised memory on configurations with HUGETLB and UFFD enabled and MIGRATION disabled. Fixes: 8cc5fcbb5be8 ("mm, hugetlb: fix racy resv_huge_pages underflow on UFFDIO_COPY") Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Mike Kravetz Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 5 ----- include/linux/mm.h | 1 + 2 files changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 9b7b7cd3bae9..23dadf7aeba8 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -51,7 +51,6 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page); extern int migrate_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page, int extra_count); -extern void copy_huge_page(struct page *dst, struct page *src); #else static inline void putback_movable_pages(struct list_head *l) {} @@ -77,10 +76,6 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping, { return -ENOSYS; } - -static inline void copy_huge_page(struct page *dst, struct page *src) -{ -} #endif /* CONFIG_MIGRATION */ #ifdef CONFIG_COMPACTION diff --git a/include/linux/mm.h b/include/linux/mm.h index 57453dba41b9..7ca22e6e694a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -906,6 +906,7 @@ void __put_page(struct page *page); void put_pages_list(struct list_head *pages); void split_page(struct page *page, unsigned int order); +void copy_huge_page(struct page *dst, struct page *src); /* * Compound pages have a destructor function. Provide a -- cgit v1.2.3 From b48c7236b13cb5ef1b5fdf744aa8841df0f7b43a Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 29 Jun 2021 15:11:44 -0500 Subject: exit/bdflush: Remove the deprecated bdflush system call The bdflush system call has been deprecated for a very long time. Recently Michael Schmitz tested[1] and found that the last known caller of of the bdflush system call is unaffected by it's removal. Since the code is not needed delete it. [1] https://lkml.kernel.org/r/36123b5d-daa0-6c2b-f2d4-a942f069fd54@gmail.com Link: https://lkml.kernel.org/r/87sg10quue.fsf_-_@disp2133 Tested-by: Michael Schmitz Acked-by: Geert Uytterhoeven Reviewed-by: Arnd Bergmann Acked-by: Cyril Hrubis Signed-off-by: "Eric W. Biederman" --- include/linux/syscalls.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 69c9a7010081..2b47584eb843 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1158,7 +1158,6 @@ asmlinkage long sys_ustat(unsigned dev, struct ustat __user *ubuf); asmlinkage long sys_vfork(void); asmlinkage long sys_recv(int, void __user *, size_t, unsigned); asmlinkage long sys_send(int, void __user *, size_t, unsigned); -asmlinkage long sys_bdflush(int func, long data); asmlinkage long sys_oldumount(char __user *name); asmlinkage long sys_uselib(const char __user *library); asmlinkage long sys_sysfs(int option, -- cgit v1.2.3 From 52f83955aaf91b22f46765b007b4404ce85b2133 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Mon, 12 Jul 2021 14:08:01 +0100 Subject: firmware: arm_scmi: Fix kernel doc warnings Kernel doc validation script is unhappy and complains with the below set of warnings. | Function parameter or member 'fast_switch_possible' not described in 'scmi_perf_proto_ops' | Function parameter or member 'power_scale_mw_get' not described in 'scmi_perf_proto_ops' | cannot understand function prototype: 'struct scmi_sensor_reading ' | cannot understand function prototype: 'struct scmi_range_attrs ' | cannot understand function prototype: 'struct scmi_sensor_axis_info ' | cannot understand function prototype: 'struct scmi_sensor_intervals_info ' Fix them adding appropriate documents or missing keywords. Link: https://lore.kernel.org/r/20210712130801.2436492-2-sudeep.holla@arm.com Reviewed-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 79d0a1237e6c..80e781c51ddc 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -101,6 +101,10 @@ struct scmi_clk_proto_ops { * to sustained performance level mapping * @est_power_get: gets the estimated power cost for a given performance domain * at a given frequency + * @fast_switch_possible: indicates if fast DVFS switching is possible or not + * for a given device + * @power_scale_mw_get: indicates if the power values provided are in milliWatts + * or in some other (abstract) scale */ struct scmi_perf_proto_ops { int (*limits_set)(const struct scmi_protocol_handle *ph, u32 domain, @@ -153,7 +157,7 @@ struct scmi_power_proto_ops { }; /** - * scmi_sensor_reading - represent a timestamped read + * struct scmi_sensor_reading - represent a timestamped read * * Used by @reading_get_timestamped method. * @@ -167,7 +171,7 @@ struct scmi_sensor_reading { }; /** - * scmi_range_attrs - specifies a sensor or axis values' range + * struct scmi_range_attrs - specifies a sensor or axis values' range * @min_range: The minimum value which can be represented by the sensor/axis. * @max_range: The maximum value which can be represented by the sensor/axis. */ @@ -177,7 +181,7 @@ struct scmi_range_attrs { }; /** - * scmi_sensor_axis_info - describes one sensor axes + * struct scmi_sensor_axis_info - describes one sensor axes * @id: The axes ID. * @type: Axes type. Chosen amongst one of @enum scmi_sensor_class. * @scale: Power-of-10 multiplier applied to the axis unit. @@ -205,8 +209,8 @@ struct scmi_sensor_axis_info { }; /** - * scmi_sensor_intervals_info - describes number and type of available update - * intervals + * struct scmi_sensor_intervals_info - describes number and type of available + * update intervals * @segmented: Flag for segmented intervals' representation. When True there * will be exactly 3 intervals in @desc, with each entry * representing a member of a segment in this order: -- cgit v1.2.3 From 5ff6319d46cee22c9cd6f39a377e32c444f9a7b0 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Mon, 12 Jul 2021 11:27:48 +0100 Subject: firmware: arm_scpi: Fix kernel doc warnings Kernel doc validation script is unhappy and complains with the below set of warnings. | Function parameter or member 'device_domain_id' not described in 'scpi_ops' | Function parameter or member 'get_transition_latency' not described in 'scpi_ops' | Function parameter or member 'add_opps_to_device' not described in 'scpi_ops' | Function parameter or member 'sensor_get_capability' not described in 'scpi_ops' | Function parameter or member 'sensor_get_info' not described in 'scpi_ops' | Function parameter or member 'sensor_get_value' not described in 'scpi_ops' | Function parameter or member 'device_get_power_state' not described in 'scpi_ops' | Function parameter or member 'device_set_power_state' not described in 'scpi_ops' Fix them adding appropriate documents or missing keywords. Link: https://lore.kernel.org/r/20210712130801.2436492-1-sudeep.holla@arm.com Reviewed-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scpi_protocol.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/scpi_protocol.h b/include/linux/scpi_protocol.h index afbf8037d8db..d2176a56828a 100644 --- a/include/linux/scpi_protocol.h +++ b/include/linux/scpi_protocol.h @@ -51,6 +51,14 @@ struct scpi_sensor_info { * OPP is an index to the list return by @dvfs_get_info * @dvfs_get_info: returns the DVFS capabilities of the given power * domain. It includes the OPP list and the latency information + * @device_domain_id: gets the scpi domain id for a given device + * @get_transition_latency: gets the DVFS transition latency for a given device + * @add_opps_to_device: adds all the OPPs for a given device + * @sensor_get_capability: get the list of capabilities for the sensors + * @sensor_get_info: get the information of the specified sensor + * @sensor_get_value: gets the current value of the sensor + * @device_get_power_state: gets the power state of a power domain + * @device_set_power_state: sets the power state of a power domain */ struct scpi_ops { u32 (*get_version)(void); -- cgit v1.2.3 From 730633f0b7f951726e87f912a6323641f674ae34 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 28 Jan 2021 19:19:45 +0100 Subject: mm: Protect operations adding pages to page cache with invalidate_lock Currently, serializing operations such as page fault, read, or readahead against hole punching is rather difficult. The basic race scheme is like: fallocate(FALLOC_FL_PUNCH_HOLE) read / fault / .. truncate_inode_pages_range() Now the problem is in this way read / page fault / readahead can instantiate pages in page cache with potentially stale data (if blocks get quickly reused). Avoiding this race is not simple - page locks do not work because we want to make sure there are *no* pages in given range. inode->i_rwsem does not work because page fault happens under mmap_sem which ranks below inode->i_rwsem. Also using it for reads makes the performance for mixed read-write workloads suffer. So create a new rw_semaphore in the address_space - invalidate_lock - that protects adding of pages to page cache for page faults / reads / readahead. Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Jan Kara --- include/linux/fs.h | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 640574294216..90a80de37ad4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -436,6 +436,10 @@ int pagecache_write_end(struct file *, struct address_space *mapping, * struct address_space - Contents of a cacheable, mappable object. * @host: Owner, either the inode or the block_device. * @i_pages: Cached pages. + * @invalidate_lock: Guards coherency between page cache contents and + * file offset->disk block mappings in the filesystem during invalidates. + * It is also used to block modification of page cache contents through + * memory mappings. * @gfp_mask: Memory allocation flags to use for allocating pages. * @i_mmap_writable: Number of VM_SHARED mappings. * @nr_thps: Number of THPs in the pagecache (non-shmem only). @@ -453,6 +457,7 @@ int pagecache_write_end(struct file *, struct address_space *mapping, struct address_space { struct inode *host; struct xarray i_pages; + struct rw_semaphore invalidate_lock; gfp_t gfp_mask; atomic_t i_mmap_writable; #ifdef CONFIG_READ_ONLY_THP_FOR_FS @@ -814,6 +819,33 @@ static inline void inode_lock_shared_nested(struct inode *inode, unsigned subcla down_read_nested(&inode->i_rwsem, subclass); } +static inline void filemap_invalidate_lock(struct address_space *mapping) +{ + down_write(&mapping->invalidate_lock); +} + +static inline void filemap_invalidate_unlock(struct address_space *mapping) +{ + up_write(&mapping->invalidate_lock); +} + +static inline void filemap_invalidate_lock_shared(struct address_space *mapping) +{ + down_read(&mapping->invalidate_lock); +} + +static inline int filemap_invalidate_trylock_shared( + struct address_space *mapping) +{ + return down_read_trylock(&mapping->invalidate_lock); +} + +static inline void filemap_invalidate_unlock_shared( + struct address_space *mapping) +{ + up_read(&mapping->invalidate_lock); +} + void lock_two_nondirectories(struct inode *, struct inode*); void unlock_two_nondirectories(struct inode *, struct inode*); @@ -2487,6 +2519,7 @@ struct file_system_type { struct lock_class_key i_lock_key; struct lock_class_key i_mutex_key; + struct lock_class_key invalidate_lock_key; struct lock_class_key i_mutex_dir_key; }; -- cgit v1.2.3 From a1867f85e06edacd82956d3422caa2b9074f4321 Mon Sep 17 00:00:00 2001 From: Min Li Date: Fri, 18 Jun 2021 12:37:12 -0400 Subject: mfd: Add Renesas Synchronization Management Unit (SMU) support Add support for ClockMatrix(TM) and 82P33xxx families of timing and synchronization devices. The access interface can be either SPI or I2C. Currently, it will create 2 types of MFD devices, which are to be used by the corresponding rsmu character device driver and the PTP hardware clock driver, respectively. Signed-off-by: Min Li Signed-off-by: Lee Jones --- include/linux/mfd/idt82p33_reg.h | 112 ++++++ include/linux/mfd/idt8a340_reg.h | 729 +++++++++++++++++++++++++++++++++++++++ include/linux/mfd/rsmu.h | 36 ++ 3 files changed, 877 insertions(+) create mode 100644 include/linux/mfd/idt82p33_reg.h create mode 100644 include/linux/mfd/idt8a340_reg.h create mode 100644 include/linux/mfd/rsmu.h (limited to 'include/linux') diff --git a/include/linux/mfd/idt82p33_reg.h b/include/linux/mfd/idt82p33_reg.h new file mode 100644 index 000000000000..129a6c078221 --- /dev/null +++ b/include/linux/mfd/idt82p33_reg.h @@ -0,0 +1,112 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Register Map - Based on AN888_SMUforIEEE_SynchEther_82P33xxx_RevH.pdf + * + * Copyright (C) 2021 Integrated Device Technology, Inc., a Renesas Company. + */ +#ifndef HAVE_IDT82P33_REG +#define HAVE_IDT82P33_REG + +/* Register address */ +#define DPLL1_TOD_CNFG 0x134 +#define DPLL2_TOD_CNFG 0x1B4 + +#define DPLL1_TOD_STS 0x10B +#define DPLL2_TOD_STS 0x18B + +#define DPLL1_TOD_TRIGGER 0x115 +#define DPLL2_TOD_TRIGGER 0x195 + +#define DPLL1_OPERATING_MODE_CNFG 0x120 +#define DPLL2_OPERATING_MODE_CNFG 0x1A0 + +#define DPLL1_HOLDOVER_FREQ_CNFG 0x12C +#define DPLL2_HOLDOVER_FREQ_CNFG 0x1AC + +#define DPLL1_PHASE_OFFSET_CNFG 0x143 +#define DPLL2_PHASE_OFFSET_CNFG 0x1C3 + +#define DPLL1_SYNC_EDGE_CNFG 0x140 +#define DPLL2_SYNC_EDGE_CNFG 0x1C0 + +#define DPLL1_INPUT_MODE_CNFG 0x116 +#define DPLL2_INPUT_MODE_CNFG 0x196 + +#define DPLL1_OPERATING_STS 0x102 +#define DPLL2_OPERATING_STS 0x182 + +#define DPLL1_CURRENT_FREQ_STS 0x103 +#define DPLL2_CURRENT_FREQ_STS 0x183 + +#define REG_SOFT_RESET 0X381 + +#define OUT_MUX_CNFG(outn) REG_ADDR(0x6, (0xC * (outn))) + +/* Register bit definitions */ +#define SYNC_TOD BIT(1) +#define PH_OFFSET_EN BIT(7) +#define SQUELCH_ENABLE BIT(5) + +/* Bit definitions for the DPLL_MODE register */ +#define PLL_MODE_SHIFT (0) +#define PLL_MODE_MASK (0x1F) +#define COMBO_MODE_EN BIT(5) +#define COMBO_MODE_SHIFT (6) +#define COMBO_MODE_MASK (0x3) + +/* Bit definitions for DPLL_OPERATING_STS register */ +#define OPERATING_STS_MASK (0x7) +#define OPERATING_STS_SHIFT (0x0) + +/* Bit definitions for DPLL_TOD_TRIGGER register */ +#define READ_TRIGGER_MASK (0xF) +#define READ_TRIGGER_SHIFT (0x0) +#define WRITE_TRIGGER_MASK (0xF0) +#define WRITE_TRIGGER_SHIFT (0x4) + +/* Bit definitions for REG_SOFT_RESET register */ +#define SOFT_RESET_EN BIT(7) + +enum pll_mode { + PLL_MODE_MIN = 0, + PLL_MODE_AUTOMATIC = PLL_MODE_MIN, + PLL_MODE_FORCE_FREERUN = 1, + PLL_MODE_FORCE_HOLDOVER = 2, + PLL_MODE_FORCE_LOCKED = 4, + PLL_MODE_FORCE_PRE_LOCKED2 = 5, + PLL_MODE_FORCE_PRE_LOCKED = 6, + PLL_MODE_FORCE_LOST_PHASE = 7, + PLL_MODE_DCO = 10, + PLL_MODE_WPH = 18, + PLL_MODE_MAX = PLL_MODE_WPH, +}; + +enum hw_tod_trig_sel { + HW_TOD_TRIG_SEL_MIN = 0, + HW_TOD_TRIG_SEL_NO_WRITE = HW_TOD_TRIG_SEL_MIN, + HW_TOD_TRIG_SEL_NO_READ = HW_TOD_TRIG_SEL_MIN, + HW_TOD_TRIG_SEL_SYNC_SEL = 1, + HW_TOD_TRIG_SEL_IN12 = 2, + HW_TOD_TRIG_SEL_IN13 = 3, + HW_TOD_TRIG_SEL_IN14 = 4, + HW_TOD_TRIG_SEL_TOD_PPS = 5, + HW_TOD_TRIG_SEL_TIMER_INTERVAL = 6, + HW_TOD_TRIG_SEL_MSB_PHASE_OFFSET_CNFG = 7, + HW_TOD_TRIG_SEL_MSB_HOLDOVER_FREQ_CNFG = 8, + HW_TOD_WR_TRIG_SEL_MSB_TOD_CNFG = 9, + HW_TOD_RD_TRIG_SEL_LSB_TOD_STS = HW_TOD_WR_TRIG_SEL_MSB_TOD_CNFG, + WR_TRIG_SEL_MAX = HW_TOD_WR_TRIG_SEL_MSB_TOD_CNFG, +}; + +/** @brief Enumerated type listing DPLL operational modes */ +enum dpll_state { + DPLL_STATE_FREERUN = 1, + DPLL_STATE_HOLDOVER = 2, + DPLL_STATE_LOCKED = 4, + DPLL_STATE_PRELOCKED2 = 5, + DPLL_STATE_PRELOCKED = 6, + DPLL_STATE_LOSTPHASE = 7, + DPLL_STATE_MAX +}; + +#endif diff --git a/include/linux/mfd/idt8a340_reg.h b/include/linux/mfd/idt8a340_reg.h new file mode 100644 index 000000000000..92d763230bdf --- /dev/null +++ b/include/linux/mfd/idt8a340_reg.h @@ -0,0 +1,729 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Based on 5.2.0, Family Programming Guide (Sept 30, 2020) + * + * Copyright (C) 2021 Integrated Device Technology, Inc., a Renesas Company. + */ +#ifndef HAVE_IDT8A340_REG +#define HAVE_IDT8A340_REG + +#define PAGE_ADDR_BASE 0x0000 +#define PAGE_ADDR 0x00fc + +#define HW_REVISION 0x8180 +#define REV_ID 0x007a + +#define HW_DPLL_0 (0x8a00) +#define HW_DPLL_1 (0x8b00) +#define HW_DPLL_2 (0x8c00) +#define HW_DPLL_3 (0x8d00) +#define HW_DPLL_4 (0x8e00) +#define HW_DPLL_5 (0x8f00) +#define HW_DPLL_6 (0x9000) +#define HW_DPLL_7 (0x9100) + +#define HW_DPLL_TOD_SW_TRIG_ADDR__0 (0x080) +#define HW_DPLL_TOD_CTRL_1 (0x089) +#define HW_DPLL_TOD_CTRL_2 (0x08A) +#define HW_DPLL_TOD_OVR__0 (0x098) +#define HW_DPLL_TOD_OUT_0__0 (0x0B0) + +#define HW_Q0_Q1_CH_SYNC_CTRL_0 (0xa740) +#define HW_Q0_Q1_CH_SYNC_CTRL_1 (0xa741) +#define HW_Q2_Q3_CH_SYNC_CTRL_0 (0xa742) +#define HW_Q2_Q3_CH_SYNC_CTRL_1 (0xa743) +#define HW_Q4_Q5_CH_SYNC_CTRL_0 (0xa744) +#define HW_Q4_Q5_CH_SYNC_CTRL_1 (0xa745) +#define HW_Q6_Q7_CH_SYNC_CTRL_0 (0xa746) +#define HW_Q6_Q7_CH_SYNC_CTRL_1 (0xa747) +#define HW_Q8_CH_SYNC_CTRL_0 (0xa748) +#define HW_Q8_CH_SYNC_CTRL_1 (0xa749) +#define HW_Q9_CH_SYNC_CTRL_0 (0xa74a) +#define HW_Q9_CH_SYNC_CTRL_1 (0xa74b) +#define HW_Q10_CH_SYNC_CTRL_0 (0xa74c) +#define HW_Q10_CH_SYNC_CTRL_1 (0xa74d) +#define HW_Q11_CH_SYNC_CTRL_0 (0xa74e) +#define HW_Q11_CH_SYNC_CTRL_1 (0xa74f) + +#define SYNC_SOURCE_DPLL0_TOD_PPS 0x14 +#define SYNC_SOURCE_DPLL1_TOD_PPS 0x15 +#define SYNC_SOURCE_DPLL2_TOD_PPS 0x16 +#define SYNC_SOURCE_DPLL3_TOD_PPS 0x17 + +#define SYNCTRL1_MASTER_SYNC_RST BIT(7) +#define SYNCTRL1_MASTER_SYNC_TRIG BIT(5) +#define SYNCTRL1_TOD_SYNC_TRIG BIT(4) +#define SYNCTRL1_FBDIV_FRAME_SYNC_TRIG BIT(3) +#define SYNCTRL1_FBDIV_SYNC_TRIG BIT(2) +#define SYNCTRL1_Q1_DIV_SYNC_TRIG BIT(1) +#define SYNCTRL1_Q0_DIV_SYNC_TRIG BIT(0) + +#define HW_Q8_CTRL_SPARE (0xa7d4) +#define HW_Q11_CTRL_SPARE (0xa7ec) + +/** + * Select FOD5 as sync_trigger for Q8 divider. + * Transition from logic zero to one + * sets trigger to sync Q8 divider. + * + * Unused when FOD4 is driving Q8 divider (normal operation). + */ +#define Q9_TO_Q8_SYNC_TRIG BIT(1) + +/** + * Enable FOD5 as driver for clock and sync for Q8 divider. + * Enable fanout buffer for FOD5. + * + * Unused when FOD4 is driving Q8 divider (normal operation). + */ +#define Q9_TO_Q8_FANOUT_AND_CLOCK_SYNC_ENABLE_MASK (BIT(0) | BIT(2)) + +/** + * Select FOD6 as sync_trigger for Q11 divider. + * Transition from logic zero to one + * sets trigger to sync Q11 divider. + * + * Unused when FOD7 is driving Q11 divider (normal operation). + */ +#define Q10_TO_Q11_SYNC_TRIG BIT(1) + +/** + * Enable FOD6 as driver for clock and sync for Q11 divider. + * Enable fanout buffer for FOD6. + * + * Unused when FOD7 is driving Q11 divider (normal operation). + */ +#define Q10_TO_Q11_FANOUT_AND_CLOCK_SYNC_ENABLE_MASK (BIT(0) | BIT(2)) + +#define RESET_CTRL 0xc000 +#define SM_RESET 0x0012 +#define SM_RESET_V520 0x0013 +#define SM_RESET_CMD 0x5A + +#define GENERAL_STATUS 0xc014 +#define BOOT_STATUS 0x0000 +#define HW_REV_ID 0x000A +#define BOND_ID 0x000B +#define HW_CSR_ID 0x000C +#define HW_IRQ_ID 0x000E +#define MAJ_REL 0x0010 +#define MIN_REL 0x0011 +#define HOTFIX_REL 0x0012 +#define PIPELINE_ID 0x0014 +#define BUILD_ID 0x0018 +#define JTAG_DEVICE_ID 0x001c +#define PRODUCT_ID 0x001e +#define OTP_SCSR_CONFIG_SELECT 0x0022 + +#define STATUS 0xc03c +#define DPLL0_STATUS 0x0018 +#define DPLL1_STATUS 0x0019 +#define DPLL2_STATUS 0x001a +#define DPLL3_STATUS 0x001b +#define DPLL4_STATUS 0x001c +#define DPLL5_STATUS 0x001d +#define DPLL6_STATUS 0x001e +#define DPLL7_STATUS 0x001f +#define DPLL_SYS_STATUS 0x0020 +#define DPLL_SYS_APLL_STATUS 0x0021 +#define DPLL0_FILTER_STATUS 0x0044 +#define DPLL1_FILTER_STATUS 0x004c +#define DPLL2_FILTER_STATUS 0x0054 +#define DPLL3_FILTER_STATUS 0x005c +#define DPLL4_FILTER_STATUS 0x0064 +#define DPLL5_FILTER_STATUS 0x006c +#define DPLL6_FILTER_STATUS 0x0074 +#define DPLL7_FILTER_STATUS 0x007c +#define DPLLSYS_FILTER_STATUS 0x0084 +#define USER_GPIO0_TO_7_STATUS 0x008a +#define USER_GPIO8_TO_15_STATUS 0x008b + +#define GPIO_USER_CONTROL 0xc160 +#define GPIO0_TO_7_OUT 0x0000 +#define GPIO8_TO_15_OUT 0x0001 +#define GPIO0_TO_7_OUT_V520 0x0002 +#define GPIO8_TO_15_OUT_V520 0x0003 + +#define STICKY_STATUS_CLEAR 0xc164 + +#define GPIO_TOD_NOTIFICATION_CLEAR 0xc16c + +#define ALERT_CFG 0xc188 + +#define SYS_DPLL_XO 0xc194 + +#define SYS_APLL 0xc19c + +#define INPUT_0 0xc1b0 +#define INPUT_1 0xc1c0 +#define INPUT_2 0xc1d0 +#define INPUT_3 0xc200 +#define INPUT_4 0xc210 +#define INPUT_5 0xc220 +#define INPUT_6 0xc230 +#define INPUT_7 0xc240 +#define INPUT_8 0xc250 +#define INPUT_9 0xc260 +#define INPUT_10 0xc280 +#define INPUT_11 0xc290 +#define INPUT_12 0xc2a0 +#define INPUT_13 0xc2b0 +#define INPUT_14 0xc2c0 +#define INPUT_15 0xc2d0 + +#define REF_MON_0 0xc2e0 +#define REF_MON_1 0xc2ec +#define REF_MON_2 0xc300 +#define REF_MON_3 0xc30c +#define REF_MON_4 0xc318 +#define REF_MON_5 0xc324 +#define REF_MON_6 0xc330 +#define REF_MON_7 0xc33c +#define REF_MON_8 0xc348 +#define REF_MON_9 0xc354 +#define REF_MON_10 0xc360 +#define REF_MON_11 0xc36c +#define REF_MON_12 0xc380 +#define REF_MON_13 0xc38c +#define REF_MON_14 0xc398 +#define REF_MON_15 0xc3a4 + +#define DPLL_0 0xc3b0 +#define DPLL_CTRL_REG_0 0x0002 +#define DPLL_CTRL_REG_1 0x0003 +#define DPLL_CTRL_REG_2 0x0004 +#define DPLL_TOD_SYNC_CFG 0x0031 +#define DPLL_COMBO_SLAVE_CFG_0 0x0032 +#define DPLL_COMBO_SLAVE_CFG_1 0x0033 +#define DPLL_SLAVE_REF_CFG 0x0034 +#define DPLL_REF_MODE 0x0035 +#define DPLL_PHASE_MEASUREMENT_CFG 0x0036 +#define DPLL_MODE 0x0037 +#define DPLL_MODE_V520 0x003B +#define DPLL_1 0xc400 +#define DPLL_2 0xc438 +#define DPLL_2_V520 0xc43c +#define DPLL_3 0xc480 +#define DPLL_4 0xc4b8 +#define DPLL_4_V520 0xc4bc +#define DPLL_5 0xc500 +#define DPLL_6 0xc538 +#define DPLL_6_V520 0xc53c +#define DPLL_7 0xc580 +#define SYS_DPLL 0xc5b8 +#define SYS_DPLL_V520 0xc5bc + +#define DPLL_CTRL_0 0xc600 +#define DPLL_CTRL_DPLL_MANU_REF_CFG 0x0001 +#define DPLL_CTRL_DPLL_FOD_FREQ 0x001c +#define DPLL_CTRL_COMBO_MASTER_CFG 0x003a +#define DPLL_CTRL_1 0xc63c +#define DPLL_CTRL_2 0xc680 +#define DPLL_CTRL_3 0xc6bc +#define DPLL_CTRL_4 0xc700 +#define DPLL_CTRL_5 0xc73c +#define DPLL_CTRL_6 0xc780 +#define DPLL_CTRL_7 0xc7bc +#define SYS_DPLL_CTRL 0xc800 + +#define DPLL_PHASE_0 0xc818 +/* Signed 42-bit FFO in units of 2^(-53) */ +#define DPLL_WR_PHASE 0x0000 +#define DPLL_PHASE_1 0xc81c +#define DPLL_PHASE_2 0xc820 +#define DPLL_PHASE_3 0xc824 +#define DPLL_PHASE_4 0xc828 +#define DPLL_PHASE_5 0xc82c +#define DPLL_PHASE_6 0xc830 +#define DPLL_PHASE_7 0xc834 + +#define DPLL_FREQ_0 0xc838 +/* Signed 42-bit FFO in units of 2^(-53) */ +#define DPLL_WR_FREQ 0x0000 +#define DPLL_FREQ_1 0xc840 +#define DPLL_FREQ_2 0xc848 +#define DPLL_FREQ_3 0xc850 +#define DPLL_FREQ_4 0xc858 +#define DPLL_FREQ_5 0xc860 +#define DPLL_FREQ_6 0xc868 +#define DPLL_FREQ_7 0xc870 + +#define DPLL_PHASE_PULL_IN_0 0xc880 +#define PULL_IN_OFFSET 0x0000 /* Signed 32 bit */ +#define PULL_IN_SLOPE_LIMIT 0x0004 /* Unsigned 24 bit */ +#define PULL_IN_CTRL 0x0007 +#define DPLL_PHASE_PULL_IN_1 0xc888 +#define DPLL_PHASE_PULL_IN_2 0xc890 +#define DPLL_PHASE_PULL_IN_3 0xc898 +#define DPLL_PHASE_PULL_IN_4 0xc8a0 +#define DPLL_PHASE_PULL_IN_5 0xc8a8 +#define DPLL_PHASE_PULL_IN_6 0xc8b0 +#define DPLL_PHASE_PULL_IN_7 0xc8b8 + +#define GPIO_CFG 0xc8c0 +#define GPIO_CFG_GBL 0x0000 +#define GPIO_0 0xc8c2 +#define GPIO_DCO_INC_DEC 0x0000 +#define GPIO_OUT_CTRL_0 0x0001 +#define GPIO_OUT_CTRL_1 0x0002 +#define GPIO_TOD_TRIG 0x0003 +#define GPIO_DPLL_INDICATOR 0x0004 +#define GPIO_LOS_INDICATOR 0x0005 +#define GPIO_REF_INPUT_DSQ_0 0x0006 +#define GPIO_REF_INPUT_DSQ_1 0x0007 +#define GPIO_REF_INPUT_DSQ_2 0x0008 +#define GPIO_REF_INPUT_DSQ_3 0x0009 +#define GPIO_MAN_CLK_SEL_0 0x000a +#define GPIO_MAN_CLK_SEL_1 0x000b +#define GPIO_MAN_CLK_SEL_2 0x000c +#define GPIO_SLAVE 0x000d +#define GPIO_ALERT_OUT_CFG 0x000e +#define GPIO_TOD_NOTIFICATION_CFG 0x000f +#define GPIO_CTRL 0x0010 +#define GPIO_CTRL_V520 0x0011 +#define GPIO_1 0xc8d4 +#define GPIO_2 0xc8e6 +#define GPIO_3 0xc900 +#define GPIO_4 0xc912 +#define GPIO_5 0xc924 +#define GPIO_6 0xc936 +#define GPIO_7 0xc948 +#define GPIO_8 0xc95a +#define GPIO_9 0xc980 +#define GPIO_10 0xc992 +#define GPIO_11 0xc9a4 +#define GPIO_12 0xc9b6 +#define GPIO_13 0xc9c8 +#define GPIO_14 0xc9da +#define GPIO_15 0xca00 + +#define OUT_DIV_MUX 0xca12 +#define OUTPUT_0 0xca14 +#define OUTPUT_0_V520 0xca20 +/* FOD frequency output divider value */ +#define OUT_DIV 0x0000 +#define OUT_DUTY_CYCLE_HIGH 0x0004 +#define OUT_CTRL_0 0x0008 +#define OUT_CTRL_1 0x0009 +/* Phase adjustment in FOD cycles */ +#define OUT_PHASE_ADJ 0x000c +#define OUTPUT_1 0xca24 +#define OUTPUT_1_V520 0xca30 +#define OUTPUT_2 0xca34 +#define OUTPUT_2_V520 0xca40 +#define OUTPUT_3 0xca44 +#define OUTPUT_3_V520 0xca50 +#define OUTPUT_4 0xca54 +#define OUTPUT_4_V520 0xca60 +#define OUTPUT_5 0xca64 +#define OUTPUT_5_V520 0xca80 +#define OUTPUT_6 0xca80 +#define OUTPUT_6_V520 0xca90 +#define OUTPUT_7 0xca90 +#define OUTPUT_7_V520 0xcaa0 +#define OUTPUT_8 0xcaa0 +#define OUTPUT_8_V520 0xcab0 +#define OUTPUT_9 0xcab0 +#define OUTPUT_9_V520 0xcac0 +#define OUTPUT_10 0xcac0 +#define OUTPUT_10_V520 0xcad0 +#define OUTPUT_11 0xcad0 +#define OUTPUT_11_V520 0xcae0 + +#define SERIAL 0xcae0 +#define SERIAL_V520 0xcaf0 + +#define PWM_ENCODER_0 0xcb00 +#define PWM_ENCODER_1 0xcb08 +#define PWM_ENCODER_2 0xcb10 +#define PWM_ENCODER_3 0xcb18 +#define PWM_ENCODER_4 0xcb20 +#define PWM_ENCODER_5 0xcb28 +#define PWM_ENCODER_6 0xcb30 +#define PWM_ENCODER_7 0xcb38 +#define PWM_DECODER_0 0xcb40 +#define PWM_DECODER_1 0xcb48 +#define PWM_DECODER_1_V520 0xcb4a +#define PWM_DECODER_2 0xcb50 +#define PWM_DECODER_2_V520 0xcb54 +#define PWM_DECODER_3 0xcb58 +#define PWM_DECODER_3_V520 0xcb5e +#define PWM_DECODER_4 0xcb60 +#define PWM_DECODER_4_V520 0xcb68 +#define PWM_DECODER_5 0xcb68 +#define PWM_DECODER_5_V520 0xcb80 +#define PWM_DECODER_6 0xcb70 +#define PWM_DECODER_6_V520 0xcb8a +#define PWM_DECODER_7 0xcb80 +#define PWM_DECODER_7_V520 0xcb94 +#define PWM_DECODER_8 0xcb88 +#define PWM_DECODER_8_V520 0xcb9e +#define PWM_DECODER_9 0xcb90 +#define PWM_DECODER_9_V520 0xcba8 +#define PWM_DECODER_10 0xcb98 +#define PWM_DECODER_10_V520 0xcbb2 +#define PWM_DECODER_11 0xcba0 +#define PWM_DECODER_11_V520 0xcbbc +#define PWM_DECODER_12 0xcba8 +#define PWM_DECODER_12_V520 0xcbc6 +#define PWM_DECODER_13 0xcbb0 +#define PWM_DECODER_13_V520 0xcbd0 +#define PWM_DECODER_14 0xcbb8 +#define PWM_DECODER_14_V520 0xcbda +#define PWM_DECODER_15 0xcbc0 +#define PWM_DECODER_15_V520 0xcbe4 +#define PWM_USER_DATA 0xcbc8 +#define PWM_USER_DATA_V520 0xcbf0 + +#define TOD_0 0xcbcc +#define TOD_0_V520 0xcc00 +/* Enable TOD counter, output channel sync and even-PPS mode */ +#define TOD_CFG 0x0000 +#define TOD_CFG_V520 0x0001 +#define TOD_1 0xcbce +#define TOD_1_V520 0xcc02 +#define TOD_2 0xcbd0 +#define TOD_2_V520 0xcc04 +#define TOD_3 0xcbd2 +#define TOD_3_V520 0xcc06 + +#define TOD_WRITE_0 0xcc00 +#define TOD_WRITE_0_V520 0xcc10 +/* 8-bit subns, 32-bit ns, 48-bit seconds */ +#define TOD_WRITE 0x0000 +/* Counter increments after TOD write is completed */ +#define TOD_WRITE_COUNTER 0x000c +/* TOD write trigger configuration */ +#define TOD_WRITE_SELECT_CFG_0 0x000d +/* TOD write trigger selection */ +#define TOD_WRITE_CMD 0x000f +#define TOD_WRITE_1 0xcc10 +#define TOD_WRITE_1_V520 0xcc20 +#define TOD_WRITE_2 0xcc20 +#define TOD_WRITE_2_V520 0xcc30 +#define TOD_WRITE_3 0xcc30 +#define TOD_WRITE_3_V520 0xcc40 + +#define TOD_READ_PRIMARY_0 0xcc40 +#define TOD_READ_PRIMARY_0_V520 0xcc50 +/* 8-bit subns, 32-bit ns, 48-bit seconds */ +#define TOD_READ_PRIMARY 0x0000 +/* Counter increments after TOD write is completed */ +#define TOD_READ_PRIMARY_COUNTER 0x000b +/* Read trigger configuration */ +#define TOD_READ_PRIMARY_SEL_CFG_0 0x000c +/* Read trigger selection */ +#define TOD_READ_PRIMARY_CMD 0x000e +#define TOD_READ_PRIMARY_CMD_V520 0x000f +#define TOD_READ_PRIMARY_1 0xcc50 +#define TOD_READ_PRIMARY_1_V520 0xcc60 +#define TOD_READ_PRIMARY_2 0xcc60 +#define TOD_READ_PRIMARY_2_V520 0xcc80 +#define TOD_READ_PRIMARY_3 0xcc80 +#define TOD_READ_PRIMARY_3_V520 0xcc90 + +#define TOD_READ_SECONDARY_0 0xcc90 +#define TOD_READ_SECONDARY_0_V520 0xcca0 +#define TOD_READ_SECONDARY_1 0xcca0 +#define TOD_READ_SECONDARY_1_V520 0xccb0 +#define TOD_READ_SECONDARY_2 0xccb0 +#define TOD_READ_SECONDARY_2_V520 0xccc0 +#define TOD_READ_SECONDARY_3 0xccc0 +#define TOD_READ_SECONDARY_3_V520 0xccd0 + +#define OUTPUT_TDC_CFG 0xccd0 +#define OUTPUT_TDC_CFG_V520 0xcce0 +#define OUTPUT_TDC_0 0xcd00 +#define OUTPUT_TDC_1 0xcd08 +#define OUTPUT_TDC_2 0xcd10 +#define OUTPUT_TDC_3 0xcd18 +#define INPUT_TDC 0xcd20 + +#define SCRATCH 0xcf50 +#define SCRATCH_V520 0xcf4c + +#define EEPROM 0xcf68 +#define EEPROM_V520 0xcf64 + +#define OTP 0xcf70 + +#define BYTE 0xcf80 + +/* Bit definitions for the MAJ_REL register */ +#define MAJOR_SHIFT (1) +#define MAJOR_MASK (0x7f) +#define PR_BUILD BIT(0) + +/* Bit definitions for the USER_GPIO0_TO_7_STATUS register */ +#define GPIO0_LEVEL BIT(0) +#define GPIO1_LEVEL BIT(1) +#define GPIO2_LEVEL BIT(2) +#define GPIO3_LEVEL BIT(3) +#define GPIO4_LEVEL BIT(4) +#define GPIO5_LEVEL BIT(5) +#define GPIO6_LEVEL BIT(6) +#define GPIO7_LEVEL BIT(7) + +/* Bit definitions for the USER_GPIO8_TO_15_STATUS register */ +#define GPIO8_LEVEL BIT(0) +#define GPIO9_LEVEL BIT(1) +#define GPIO10_LEVEL BIT(2) +#define GPIO11_LEVEL BIT(3) +#define GPIO12_LEVEL BIT(4) +#define GPIO13_LEVEL BIT(5) +#define GPIO14_LEVEL BIT(6) +#define GPIO15_LEVEL BIT(7) + +/* Bit definitions for the GPIO0_TO_7_OUT register */ +#define GPIO0_DRIVE_LEVEL BIT(0) +#define GPIO1_DRIVE_LEVEL BIT(1) +#define GPIO2_DRIVE_LEVEL BIT(2) +#define GPIO3_DRIVE_LEVEL BIT(3) +#define GPIO4_DRIVE_LEVEL BIT(4) +#define GPIO5_DRIVE_LEVEL BIT(5) +#define GPIO6_DRIVE_LEVEL BIT(6) +#define GPIO7_DRIVE_LEVEL BIT(7) + +/* Bit definitions for the GPIO8_TO_15_OUT register */ +#define GPIO8_DRIVE_LEVEL BIT(0) +#define GPIO9_DRIVE_LEVEL BIT(1) +#define GPIO10_DRIVE_LEVEL BIT(2) +#define GPIO11_DRIVE_LEVEL BIT(3) +#define GPIO12_DRIVE_LEVEL BIT(4) +#define GPIO13_DRIVE_LEVEL BIT(5) +#define GPIO14_DRIVE_LEVEL BIT(6) +#define GPIO15_DRIVE_LEVEL BIT(7) + +/* Bit definitions for the DPLL_TOD_SYNC_CFG register */ +#define TOD_SYNC_SOURCE_SHIFT (1) +#define TOD_SYNC_SOURCE_MASK (0x3) +#define TOD_SYNC_EN BIT(0) + +/* Bit definitions for the DPLL_MODE register */ +#define WRITE_TIMER_MODE BIT(6) +#define PLL_MODE_SHIFT (3) +#define PLL_MODE_MASK (0x7) +#define STATE_MODE_SHIFT (0) +#define STATE_MODE_MASK (0x7) + +/* Bit definitions for the GPIO_CFG_GBL register */ +#define SUPPLY_MODE_SHIFT (0) +#define SUPPLY_MODE_MASK (0x3) + +/* Bit definitions for the GPIO_DCO_INC_DEC register */ +#define INCDEC_DPLL_INDEX_SHIFT (0) +#define INCDEC_DPLL_INDEX_MASK (0x7) + +/* Bit definitions for the GPIO_OUT_CTRL_0 register */ +#define CTRL_OUT_0 BIT(0) +#define CTRL_OUT_1 BIT(1) +#define CTRL_OUT_2 BIT(2) +#define CTRL_OUT_3 BIT(3) +#define CTRL_OUT_4 BIT(4) +#define CTRL_OUT_5 BIT(5) +#define CTRL_OUT_6 BIT(6) +#define CTRL_OUT_7 BIT(7) + +/* Bit definitions for the GPIO_OUT_CTRL_1 register */ +#define CTRL_OUT_8 BIT(0) +#define CTRL_OUT_9 BIT(1) +#define CTRL_OUT_10 BIT(2) +#define CTRL_OUT_11 BIT(3) +#define CTRL_OUT_12 BIT(4) +#define CTRL_OUT_13 BIT(5) +#define CTRL_OUT_14 BIT(6) +#define CTRL_OUT_15 BIT(7) + +/* Bit definitions for the GPIO_TOD_TRIG register */ +#define TOD_TRIG_0 BIT(0) +#define TOD_TRIG_1 BIT(1) +#define TOD_TRIG_2 BIT(2) +#define TOD_TRIG_3 BIT(3) + +/* Bit definitions for the GPIO_DPLL_INDICATOR register */ +#define IND_DPLL_INDEX_SHIFT (0) +#define IND_DPLL_INDEX_MASK (0x7) + +/* Bit definitions for the GPIO_LOS_INDICATOR register */ +#define REFMON_INDEX_SHIFT (0) +#define REFMON_INDEX_MASK (0xf) +/* Active level of LOS indicator, 0=low 1=high */ +#define ACTIVE_LEVEL BIT(4) + +/* Bit definitions for the GPIO_REF_INPUT_DSQ_0 register */ +#define DSQ_INP_0 BIT(0) +#define DSQ_INP_1 BIT(1) +#define DSQ_INP_2 BIT(2) +#define DSQ_INP_3 BIT(3) +#define DSQ_INP_4 BIT(4) +#define DSQ_INP_5 BIT(5) +#define DSQ_INP_6 BIT(6) +#define DSQ_INP_7 BIT(7) + +/* Bit definitions for the GPIO_REF_INPUT_DSQ_1 register */ +#define DSQ_INP_8 BIT(0) +#define DSQ_INP_9 BIT(1) +#define DSQ_INP_10 BIT(2) +#define DSQ_INP_11 BIT(3) +#define DSQ_INP_12 BIT(4) +#define DSQ_INP_13 BIT(5) +#define DSQ_INP_14 BIT(6) +#define DSQ_INP_15 BIT(7) + +/* Bit definitions for the GPIO_REF_INPUT_DSQ_2 register */ +#define DSQ_DPLL_0 BIT(0) +#define DSQ_DPLL_1 BIT(1) +#define DSQ_DPLL_2 BIT(2) +#define DSQ_DPLL_3 BIT(3) +#define DSQ_DPLL_4 BIT(4) +#define DSQ_DPLL_5 BIT(5) +#define DSQ_DPLL_6 BIT(6) +#define DSQ_DPLL_7 BIT(7) + +/* Bit definitions for the GPIO_REF_INPUT_DSQ_3 register */ +#define DSQ_DPLL_SYS BIT(0) +#define GPIO_DSQ_LEVEL BIT(1) + +/* Bit definitions for the GPIO_TOD_NOTIFICATION_CFG register */ +#define DPLL_TOD_SHIFT (0) +#define DPLL_TOD_MASK (0x3) +#define TOD_READ_SECONDARY BIT(2) +#define GPIO_ASSERT_LEVEL BIT(3) + +/* Bit definitions for the GPIO_CTRL register */ +#define GPIO_FUNCTION_EN BIT(0) +#define GPIO_CMOS_OD_MODE BIT(1) +#define GPIO_CONTROL_DIR BIT(2) +#define GPIO_PU_PD_MODE BIT(3) +#define GPIO_FUNCTION_SHIFT (4) +#define GPIO_FUNCTION_MASK (0xf) + +/* Bit definitions for the OUT_CTRL_1 register */ +#define OUT_SYNC_DISABLE BIT(7) +#define SQUELCH_VALUE BIT(6) +#define SQUELCH_DISABLE BIT(5) +#define PAD_VDDO_SHIFT (2) +#define PAD_VDDO_MASK (0x7) +#define PAD_CMOSDRV_SHIFT (0) +#define PAD_CMOSDRV_MASK (0x3) + +/* Bit definitions for the TOD_CFG register */ +#define TOD_EVEN_PPS_MODE BIT(2) +#define TOD_OUT_SYNC_ENABLE BIT(1) +#define TOD_ENABLE BIT(0) + +/* Bit definitions for the TOD_WRITE_SELECT_CFG_0 register */ +#define WR_PWM_DECODER_INDEX_SHIFT (4) +#define WR_PWM_DECODER_INDEX_MASK (0xf) +#define WR_REF_INDEX_SHIFT (0) +#define WR_REF_INDEX_MASK (0xf) + +/* Bit definitions for the TOD_WRITE_CMD register */ +#define TOD_WRITE_SELECTION_SHIFT (0) +#define TOD_WRITE_SELECTION_MASK (0xf) +/* 4.8.7 */ +#define TOD_WRITE_TYPE_SHIFT (4) +#define TOD_WRITE_TYPE_MASK (0x3) + +/* Bit definitions for the TOD_READ_PRIMARY_SEL_CFG_0 register */ +#define RD_PWM_DECODER_INDEX_SHIFT (4) +#define RD_PWM_DECODER_INDEX_MASK (0xf) +#define RD_REF_INDEX_SHIFT (0) +#define RD_REF_INDEX_MASK (0xf) + +/* Bit definitions for the TOD_READ_PRIMARY_CMD register */ +#define TOD_READ_TRIGGER_MODE BIT(4) +#define TOD_READ_TRIGGER_SHIFT (0) +#define TOD_READ_TRIGGER_MASK (0xf) + +/* Bit definitions for the DPLL_CTRL_COMBO_MASTER_CFG register */ +#define COMBO_MASTER_HOLD BIT(0) + +/* Bit definitions for DPLL_SYS_STATUS register */ +#define DPLL_SYS_STATE_MASK (0xf) + +/* Bit definitions for SYS_APLL_STATUS register */ +#define SYS_APLL_LOSS_LOCK_LIVE_MASK BIT(0) +#define SYS_APLL_LOSS_LOCK_LIVE_LOCKED 0 +#define SYS_APLL_LOSS_LOCK_LIVE_UNLOCKED 1 + +/* Bit definitions for the DPLL0_STATUS register */ +#define DPLL_STATE_MASK (0xf) +#define DPLL_STATE_SHIFT (0x0) + +/* Values of DPLL_N.DPLL_MODE.PLL_MODE */ +enum pll_mode { + PLL_MODE_MIN = 0, + PLL_MODE_NORMAL = PLL_MODE_MIN, + PLL_MODE_WRITE_PHASE = 1, + PLL_MODE_WRITE_FREQUENCY = 2, + PLL_MODE_GPIO_INC_DEC = 3, + PLL_MODE_SYNTHESIS = 4, + PLL_MODE_PHASE_MEASUREMENT = 5, + PLL_MODE_DISABLED = 6, + PLL_MODE_MAX = PLL_MODE_DISABLED, +}; + +enum hw_tod_write_trig_sel { + HW_TOD_WR_TRIG_SEL_MIN = 0, + HW_TOD_WR_TRIG_SEL_MSB = HW_TOD_WR_TRIG_SEL_MIN, + HW_TOD_WR_TRIG_SEL_RESERVED = 1, + HW_TOD_WR_TRIG_SEL_TOD_PPS = 2, + HW_TOD_WR_TRIG_SEL_IRIGB_PPS = 3, + HW_TOD_WR_TRIG_SEL_PWM_PPS = 4, + HW_TOD_WR_TRIG_SEL_GPIO = 5, + HW_TOD_WR_TRIG_SEL_FOD_SYNC = 6, + WR_TRIG_SEL_MAX = HW_TOD_WR_TRIG_SEL_FOD_SYNC, +}; + +enum scsr_read_trig_sel { + /* CANCEL CURRENT TOD READ; MODULE BECOMES IDLE - NO TRIGGER OCCURS */ + SCSR_TOD_READ_TRIG_SEL_DISABLE = 0, + /* TRIGGER IMMEDIATELY */ + SCSR_TOD_READ_TRIG_SEL_IMMEDIATE = 1, + /* TRIGGER ON RISING EDGE OF INTERNAL TOD PPS SIGNAL */ + SCSR_TOD_READ_TRIG_SEL_TODPPS = 2, + /* TRGGER ON RISING EDGE OF SELECTED REFERENCE INPUT */ + SCSR_TOD_READ_TRIG_SEL_REFCLK = 3, + /* TRIGGER ON RISING EDGE OF SELECTED PWM DECODER 1PPS OUTPUT */ + SCSR_TOD_READ_TRIG_SEL_PWMPPS = 4, + SCSR_TOD_READ_TRIG_SEL_RESERVED = 5, + /* TRIGGER WHEN WRITE FREQUENCY EVENT OCCURS */ + SCSR_TOD_READ_TRIG_SEL_WRITEFREQUENCYEVENT = 6, + /* TRIGGER ON SELECTED GPIO */ + SCSR_TOD_READ_TRIG_SEL_GPIO = 7, + SCSR_TOD_READ_TRIG_SEL_MAX = SCSR_TOD_READ_TRIG_SEL_GPIO, +}; + +/* Values STATUS.DPLL_SYS_STATUS.DPLL_SYS_STATE */ +enum dpll_state { + DPLL_STATE_MIN = 0, + DPLL_STATE_FREERUN = DPLL_STATE_MIN, + DPLL_STATE_LOCKACQ = 1, + DPLL_STATE_LOCKREC = 2, + DPLL_STATE_LOCKED = 3, + DPLL_STATE_HOLDOVER = 4, + DPLL_STATE_OPEN_LOOP = 5, + DPLL_STATE_MAX = DPLL_STATE_OPEN_LOOP, +}; + +/* 4.8.7 only */ +enum scsr_tod_write_trig_sel { + SCSR_TOD_WR_TRIG_SEL_DISABLE = 0, + SCSR_TOD_WR_TRIG_SEL_IMMEDIATE = 1, + SCSR_TOD_WR_TRIG_SEL_REFCLK = 2, + SCSR_TOD_WR_TRIG_SEL_PWMPPS = 3, + SCSR_TOD_WR_TRIG_SEL_TODPPS = 4, + SCSR_TOD_WR_TRIG_SEL_SYNCFOD = 5, + SCSR_TOD_WR_TRIG_SEL_GPIO = 6, + SCSR_TOD_WR_TRIG_SEL_MAX = SCSR_TOD_WR_TRIG_SEL_GPIO, +}; + +/* 4.8.7 only */ +enum scsr_tod_write_type_sel { + SCSR_TOD_WR_TYPE_SEL_ABSOLUTE = 0, + SCSR_TOD_WR_TYPE_SEL_DELTA_PLUS = 1, + SCSR_TOD_WR_TYPE_SEL_DELTA_MINUS = 2, + SCSR_TOD_WR_TYPE_SEL_MAX = SCSR_TOD_WR_TYPE_SEL_DELTA_MINUS, +}; +#endif diff --git a/include/linux/mfd/rsmu.h b/include/linux/mfd/rsmu.h new file mode 100644 index 000000000000..6870de608233 --- /dev/null +++ b/include/linux/mfd/rsmu.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Core interface for Renesas Synchronization Management Unit (SMU) devices. + * + * Copyright (C) 2021 Integrated Device Technology, Inc., a Renesas Company. + */ + +#ifndef __LINUX_MFD_RSMU_H +#define __LINUX_MFD_RSMU_H + +/* The supported devices are ClockMatrix, Sabre and SnowLotus */ +enum rsmu_type { + RSMU_CM = 0x34000, + RSMU_SABRE = 0x33810, + RSMU_SL = 0x19850, +}; + +/** + * + * struct rsmu_ddata - device data structure for sub devices. + * + * @dev: i2c/spi device. + * @regmap: i2c/spi bus access. + * @lock: mutex used by sub devices to make sure a series of + * bus access requests are not interrupted. + * @type: RSMU device type. + * @page: i2c/spi bus driver internal use only. + */ +struct rsmu_ddata { + struct device *dev; + struct regmap *regmap; + struct mutex lock; + enum rsmu_type type; + u16 page; +}; +#endif /* __LINUX_MFD_RSMU_H */ -- cgit v1.2.3 From 7506ae6a7033f617ca5fea53e356fb1f7bd98010 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 24 May 2021 13:02:30 +0200 Subject: mm: Add functions to lock invalidate_lock for two mappings Some operations such as reflinking blocks among files will need to lock invalidate_lock for two mappings. Add helper functions to do that. Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Jan Kara --- include/linux/fs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 90a80de37ad4..894ff2451793 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -849,6 +849,12 @@ static inline void filemap_invalidate_unlock_shared( void lock_two_nondirectories(struct inode *, struct inode*); void unlock_two_nondirectories(struct inode *, struct inode*); +void filemap_invalidate_lock_two(struct address_space *mapping1, + struct address_space *mapping2); +void filemap_invalidate_unlock_two(struct address_space *mapping1, + struct address_space *mapping2); + + /* * NOTE: in a 32bit arch with a preemptable kernel and * an UP compile the i_size_read/write must be atomic -- cgit v1.2.3 From 69031f500865ee3eee19566a1b9c40a189817eaa Mon Sep 17 00:00:00 2001 From: Claire Chang Date: Sat, 19 Jun 2021 11:40:34 +0800 Subject: swiotlb: Set dev->dma_io_tlb_mem to the swiotlb pool used Always have the pointer to the swiotlb pool used in struct device. This could help simplify the code for other pools. Signed-off-by: Claire Chang Reviewed-by: Christoph Hellwig Tested-by: Stefano Stabellini Tested-by: Will Deacon Acked-by: Stefano Stabellini Signed-off-by: Konrad Rzeszutek Wilk --- include/linux/device.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 59940f1744c1..2a22875238a6 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -423,6 +423,7 @@ struct dev_links_info { * @dma_pools: Dma pools (if dma'ble device). * @dma_mem: Internal for coherent mem override. * @cma_area: Contiguous memory area for dma allocations + * @dma_io_tlb_mem: Pointer to the swiotlb pool used. Not for driver use. * @archdata: For arch-specific additions. * @of_node: Associated device tree node. * @fwnode: Associated device node supplied by platform firmware. @@ -531,6 +532,9 @@ struct device { #ifdef CONFIG_DMA_CMA struct cma *cma_area; /* contiguous memory area for dma allocations */ +#endif +#ifdef CONFIG_SWIOTLB + struct io_tlb_mem *dma_io_tlb_mem; #endif /* arch specific additions */ struct dev_archdata archdata; -- cgit v1.2.3 From 7fd856aa7f4261ddac62ea59d8383fef22a0690e Mon Sep 17 00:00:00 2001 From: Claire Chang Date: Sat, 19 Jun 2021 11:40:35 +0800 Subject: swiotlb: Update is_swiotlb_buffer to add a struct device argument Update is_swiotlb_buffer to add a struct device argument. This will be useful later to allow for different pools. Signed-off-by: Claire Chang Reviewed-by: Christoph Hellwig Tested-by: Stefano Stabellini Tested-by: Will Deacon Acked-by: Stefano Stabellini Signed-off-by: Konrad Rzeszutek Wilk --- include/linux/swiotlb.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 216854a5e513..d1f3d95881cd 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -2,6 +2,7 @@ #ifndef __LINUX_SWIOTLB_H #define __LINUX_SWIOTLB_H +#include #include #include #include @@ -101,9 +102,9 @@ struct io_tlb_mem { }; extern struct io_tlb_mem *io_tlb_default_mem; -static inline bool is_swiotlb_buffer(phys_addr_t paddr) +static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) { - struct io_tlb_mem *mem = io_tlb_default_mem; + struct io_tlb_mem *mem = dev->dma_io_tlb_mem; return mem && paddr >= mem->start && paddr < mem->end; } @@ -115,7 +116,7 @@ bool is_swiotlb_active(void); void __init swiotlb_adjust_size(unsigned long size); #else #define swiotlb_force SWIOTLB_NO_FORCE -static inline bool is_swiotlb_buffer(phys_addr_t paddr) +static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) { return false; } -- cgit v1.2.3 From 6f2beb268a5d35504a636c4a3b7aaa76ec32d96c Mon Sep 17 00:00:00 2001 From: Claire Chang Date: Sat, 19 Jun 2021 11:40:36 +0800 Subject: swiotlb: Update is_swiotlb_active to add a struct device argument Update is_swiotlb_active to add a struct device argument. This will be useful later to allow for different pools. Signed-off-by: Claire Chang Reviewed-by: Christoph Hellwig Tested-by: Stefano Stabellini Tested-by: Will Deacon Acked-by: Stefano Stabellini Signed-off-by: Konrad Rzeszutek Wilk --- include/linux/swiotlb.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index d1f3d95881cd..dd1c30a83058 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -112,7 +112,7 @@ static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) void __init swiotlb_exit(void); unsigned int swiotlb_max_segment(void); size_t swiotlb_max_mapping_size(struct device *dev); -bool is_swiotlb_active(void); +bool is_swiotlb_active(struct device *dev); void __init swiotlb_adjust_size(unsigned long size); #else #define swiotlb_force SWIOTLB_NO_FORCE @@ -132,7 +132,7 @@ static inline size_t swiotlb_max_mapping_size(struct device *dev) return SIZE_MAX; } -static inline bool is_swiotlb_active(void) +static inline bool is_swiotlb_active(struct device *dev) { return false; } -- cgit v1.2.3 From 903cd0f315fe426c6a64c54ed389de0becb663dc Mon Sep 17 00:00:00 2001 From: Claire Chang Date: Thu, 24 Jun 2021 23:55:20 +0800 Subject: swiotlb: Use is_swiotlb_force_bounce for swiotlb data bouncing Propagate the swiotlb_force into io_tlb_default_mem->force_bounce and use it to determine whether to bounce the data or not. This will be useful later to allow for different pools. Signed-off-by: Claire Chang Reviewed-by: Christoph Hellwig Tested-by: Stefano Stabellini Tested-by: Will Deacon Acked-by: Stefano Stabellini Signed-off-by: Konrad Rzeszutek Wilk [v2: Includes Will's fix] --- include/linux/swiotlb.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index dd1c30a83058..da348671b0d5 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -84,6 +84,7 @@ extern enum swiotlb_force swiotlb_force; * unmap calls. * @debugfs: The dentry to debugfs. * @late_alloc: %true if allocated using the page allocator + * @force_bounce: %true if swiotlb bouncing is forced */ struct io_tlb_mem { phys_addr_t start; @@ -94,6 +95,7 @@ struct io_tlb_mem { spinlock_t lock; struct dentry *debugfs; bool late_alloc; + bool force_bounce; struct io_tlb_slot { phys_addr_t orig_addr; size_t alloc_size; @@ -109,6 +111,13 @@ static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) return mem && paddr >= mem->start && paddr < mem->end; } +static inline bool is_swiotlb_force_bounce(struct device *dev) +{ + struct io_tlb_mem *mem = dev->dma_io_tlb_mem; + + return mem && mem->force_bounce; +} + void __init swiotlb_exit(void); unsigned int swiotlb_max_segment(void); size_t swiotlb_max_mapping_size(struct device *dev); @@ -120,6 +129,10 @@ static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) { return false; } +static inline bool is_swiotlb_force_bounce(struct device *dev) +{ + return false; +} static inline void swiotlb_exit(void) { } -- cgit v1.2.3 From f4111e39a52aa5d5136d890bbd1aa87c1c8fe3bc Mon Sep 17 00:00:00 2001 From: Claire Chang Date: Sat, 19 Jun 2021 11:40:40 +0800 Subject: swiotlb: Add restricted DMA alloc/free support Add the functions, swiotlb_{alloc,free} and is_swiotlb_for_alloc to support the memory allocation from restricted DMA pool. The restricted DMA pool is preferred if available. Note that since coherent allocation needs remapping, one must set up another device coherent pool by shared-dma-pool and use dma_alloc_from_dev_coherent instead for atomic coherent allocation. Signed-off-by: Claire Chang Reviewed-by: Christoph Hellwig Tested-by: Stefano Stabellini Tested-by: Will Deacon Acked-by: Stefano Stabellini Signed-off-by: Konrad Rzeszutek Wilk --- include/linux/swiotlb.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index da348671b0d5..3b9454d1e498 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -85,6 +85,7 @@ extern enum swiotlb_force swiotlb_force; * @debugfs: The dentry to debugfs. * @late_alloc: %true if allocated using the page allocator * @force_bounce: %true if swiotlb bouncing is forced + * @for_alloc: %true if the pool is used for memory allocation */ struct io_tlb_mem { phys_addr_t start; @@ -96,6 +97,7 @@ struct io_tlb_mem { struct dentry *debugfs; bool late_alloc; bool force_bounce; + bool for_alloc; struct io_tlb_slot { phys_addr_t orig_addr; size_t alloc_size; @@ -158,4 +160,28 @@ static inline void swiotlb_adjust_size(unsigned long size) extern void swiotlb_print_info(void); extern void swiotlb_set_max_segment(unsigned int); +#ifdef CONFIG_DMA_RESTRICTED_POOL +struct page *swiotlb_alloc(struct device *dev, size_t size); +bool swiotlb_free(struct device *dev, struct page *page, size_t size); + +static inline bool is_swiotlb_for_alloc(struct device *dev) +{ + return dev->dma_io_tlb_mem->for_alloc; +} +#else +static inline struct page *swiotlb_alloc(struct device *dev, size_t size) +{ + return NULL; +} +static inline bool swiotlb_free(struct device *dev, struct page *page, + size_t size) +{ + return false; +} +static inline bool is_swiotlb_for_alloc(struct device *dev) +{ + return false; +} +#endif /* CONFIG_DMA_RESTRICTED_POOL */ + #endif /* __LINUX_SWIOTLB_H */ -- cgit v1.2.3 From 0b84e4f8b793eb4045fd64f6f514165a7974cd16 Mon Sep 17 00:00:00 2001 From: Claire Chang Date: Sat, 19 Jun 2021 11:40:41 +0800 Subject: swiotlb: Add restricted DMA pool initialization Add the initialization function to create restricted DMA pools from matching reserved-memory nodes. Regardless of swiotlb setting, the restricted DMA pool is preferred if available. The restricted DMA pools provide a basic level of protection against the DMA overwriting buffer contents at unexpected times. However, to protect against general data leakage and system memory corruption, the system needs to provide a way to lock down the memory access, e.g., MPU. Signed-off-by: Claire Chang Reviewed-by: Christoph Hellwig Tested-by: Stefano Stabellini Tested-by: Will Deacon Signed-off-by: Konrad Rzeszutek Wilk --- include/linux/swiotlb.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 3b9454d1e498..39284ff2a6cd 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -73,7 +73,8 @@ extern enum swiotlb_force swiotlb_force; * range check to see if the memory was in fact allocated by this * API. * @nslabs: The number of IO TLB blocks (in groups of 64) between @start and - * @end. This is command line adjustable via setup_io_tlb_npages. + * @end. For default swiotlb, this is command line adjustable via + * setup_io_tlb_npages. * @used: The number of used IO TLB block. * @list: The free list describing the number of free entries available * from each index. -- cgit v1.2.3 From fe364a7d95c24e07e9b3f2ab917f01d6d8330bba Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 12 Jul 2021 14:39:40 +0300 Subject: dmaengine: dw: Program xBAR hardware for Elkhart Lake Intel Elkhart Lake PSE DMA implementation is integrated with crossbar IP in order to serve more hardware than there are DMA request lines available. Due to this, program xBAR hardware to make flexible support of PSE peripheral. The Device-to-Device has not been tested and it's not supported by DMA Engine, but it's left in the code for the sake of documenting hardware features. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20210712113940.42753-1-andriy.shevchenko@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/platform_data/dma-dw.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/dma-dw.h b/include/linux/platform_data/dma-dw.h index b34a094b2258..b11b0c8bc5da 100644 --- a/include/linux/platform_data/dma-dw.h +++ b/include/linux/platform_data/dma-dw.h @@ -52,6 +52,7 @@ struct dw_dma_slave { * @max_burst: Maximum value of burst transaction size supported by hardware * per channel (in units of CTL.SRC_TR_WIDTH/CTL.DST_TR_WIDTH). * @protctl: Protection control signals setting per channel. + * @quirks: Optional platform quirks. */ struct dw_dma_platform_data { unsigned int nr_channels; @@ -71,6 +72,8 @@ struct dw_dma_platform_data { #define CHAN_PROTCTL_CACHEABLE BIT(2) #define CHAN_PROTCTL_MASK GENMASK(2, 0) unsigned char protctl; +#define DW_DMA_QUIRK_XBAR_PRESENT BIT(0) + unsigned int quirks; }; #endif /* _PLATFORM_DATA_DMA_DW_H */ -- cgit v1.2.3 From f84d866ab43fcc27b417c86357d6534f157a3d89 Mon Sep 17 00:00:00 2001 From: Mason Zhang Date: Tue, 13 Jul 2021 19:40:49 +0800 Subject: spi: mediatek: add tick_delay support This patch support tick_delay setting, some users need use high-speed spi speed, which can use tick_delay to tuning spi clk timing. Signed-off-by: Mason Zhang Link: https://lore.kernel.org/r/20210713114048.29509-1-mason.zhang@mediatek.com Signed-off-by: Mark Brown --- include/linux/platform_data/spi-mt65xx.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/spi-mt65xx.h b/include/linux/platform_data/spi-mt65xx.h index 65fd5ffd257c..f0db674f07b8 100644 --- a/include/linux/platform_data/spi-mt65xx.h +++ b/include/linux/platform_data/spi-mt65xx.h @@ -12,5 +12,6 @@ /* Board specific platform_data */ struct mtk_chip_config { u32 sample_sel; + u32 tick_delay; }; #endif -- cgit v1.2.3 From d1d488d813703618f0dd93f0e4c4a05928114aa8 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 14 Jul 2021 15:47:50 +0200 Subject: fs: add vfs_parse_fs_param_source() helper Add a simple helper that filesystems can use in their parameter parser to parse the "source" parameter. A few places open-coded this function and that already caused a bug in the cgroup v1 parser that we fixed. Let's make it harder to get this wrong by introducing a helper which performs all necessary checks. Link: https://syzkaller.appspot.com/bug?id=6312526aba5beae046fdae8f00399f87aab48b12 Cc: Christoph Hellwig Cc: Alexander Viro Cc: Dmitry Vyukov Signed-off-by: Christian Brauner Signed-off-by: Linus Torvalds --- include/linux/fs_context.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index 37e1e8f7f08d..e2bc16300c82 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -139,6 +139,8 @@ extern int vfs_parse_fs_string(struct fs_context *fc, const char *key, extern int generic_parse_monolithic(struct fs_context *fc, void *data); extern int vfs_get_tree(struct fs_context *fc); extern void put_fs_context(struct fs_context *fc); +extern int vfs_parse_fs_param_source(struct fs_context *fc, + struct fs_parameter *param); /* * sget() wrappers to be called from the ->get_tree() op. -- cgit v1.2.3 From 2db710cc846d3321a4dc0977fa13769bddba2351 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Wed, 14 Jul 2021 21:26:40 -0700 Subject: kasan: fix build by including kernel.h The header relies on _RET_IP_ being defined, and had been receiving that definition via inclusion of bug.h which includes kernel.h. However, since f39650de687e ("kernel.h: split out panic and oops helpers") that is no longer the case and get the following build error when building CONFIG_KASAN_HW_TAGS on arm64: In file included from arch/arm64/mm/kasan_init.c:10: include/linux/kasan.h: In function 'kasan_slab_free': include/linux/kasan.h:230:39: error: '_RET_IP_' undeclared (first use in this function) 230 | return __kasan_slab_free(s, object, _RET_IP_, init); Fix it by including kernel.h from kasan.h. Link: https://lkml.kernel.org/r/20210705072716.2125074-1-elver@google.com Fixes: f39650de687e ("kernel.h: split out panic and oops helpers") Signed-off-by: Marco Elver Reviewed-by: Andy Shevchenko Reviewed-by: Andrey Konovalov Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Peter Collingbourne Cc: Catalin Marinas Cc: Vincenzo Frascino Cc: Andrey Ryabinin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 5310e217bd74..dd874a1ee862 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -3,6 +3,7 @@ #define _LINUX_KASAN_H #include +#include #include #include -- cgit v1.2.3 From ab7965de1725cd8514f0edbced5c2fb793846078 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 14 Jul 2021 21:26:55 -0700 Subject: mm: fix the try_to_unmap prototype for !CONFIG_MMU Adjust the nommu stub of try_to_unmap to match the changed protype for the full version. Turn it into an inline instead of a macro to generally improve the type checking. Link: https://lkml.kernel.org/r/20210705053944.885828-1-hch@lst.de Fixes: 1fb08ac63bee ("mm: rmap: make try_to_unmap() void function") Signed-off-by: Christoph Hellwig Reviewed-by: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rmap.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 83fb86133fe1..c976cc6de257 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -291,7 +291,9 @@ static inline int page_referenced(struct page *page, int is_locked, return 0; } -#define try_to_unmap(page, refs) false +static inline void try_to_unmap(struct page *page, enum ttu_flags flags) +{ +} static inline int page_mkclean(struct page *page) { -- cgit v1.2.3 From 5c2c85315948c42c6c0258cf9bad596acaa79043 Mon Sep 17 00:00:00 2001 From: Richard Laing Date: Thu, 15 Jul 2021 09:18:05 +1200 Subject: bus: mhi: pci-generic: configurable network interface MRU The MRU value used by the MHI MBIM network interface affects the throughput performance of the interface. Different modem models use different default MRU sizes based on their bandwidth capabilities. Large values generally result in higher throughput for larger packet sizes. In addition if the MRU used by the MHI device is larger than that specified in the MHI net device the data is fragmented and needs to be re-assembled which generates a (single) warning message about the fragmented packets. Setting the MRU on both ends avoids the extra processing to re-assemble the packets. This patch allows the documented MRU for a modem to be automatically set as the MHI net device MRU avoiding fragmentation and improving throughput performance. Signed-off-by: Richard Laing Signed-off-by: David S. Miller --- include/linux/mhi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 944aa3aa3035..beb918328eef 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -356,6 +356,7 @@ struct mhi_controller_config { * @fbc_download: MHI host needs to do complete image transfer (optional) * @wake_set: Device wakeup set flag * @irq_flags: irq flags passed to request_irq (optional) + * @mru: the default MRU for the MHI device * * Fields marked as (required) need to be populated by the controller driver * before calling mhi_register_controller(). For the fields marked as (optional) @@ -448,6 +449,7 @@ struct mhi_controller { bool fbc_download; bool wake_set; unsigned long irq_flags; + u32 mru; }; /** -- cgit v1.2.3 From e48bf29cf9d6d60d810e2af71e54b71a324094e0 Mon Sep 17 00:00:00 2001 From: Ye Xiang Date: Sun, 13 Jun 2021 11:25:07 +0800 Subject: HID: intel-ish-hid: use async resume function ISH IPC driver uses asynchronous workqueue to do resume now, but there is a potential timing issue: when child devices resume before bus driver, it will cause child devices resume failed and cannot be recovered until reboot. The current implementation in this case do wait for IPC to resume but fail to accommodate for a case when there is no ISH reboot and soft resume is taking time. This issue is apparent on Tiger Lake platform with 5.11.13 kernel when doing suspend to idle then resume(s0ix) test. To resolve this issue, we change ISHTP HID client to use asynchronous resume callback too. In the asynchronous resume callback, it waits for the ISHTP resume done event, and then notify ISHTP HID client link ready. Signed-off-by: Ye Xiang Acked-by: Srinivas Pandruvada Signed-off-by: Jiri Kosina --- include/linux/intel-ish-client-if.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel-ish-client-if.h b/include/linux/intel-ish-client-if.h index 25e2b4e80502..aee8ff4739b1 100644 --- a/include/linux/intel-ish-client-if.h +++ b/include/linux/intel-ish-client-if.h @@ -81,6 +81,8 @@ int ishtp_register_event_cb(struct ishtp_cl_device *device, /* Get the device * from ishtp device instance */ struct device *ishtp_device(struct ishtp_cl_device *cl_device); +/* wait for IPC resume */ +bool ishtp_wait_resume(struct ishtp_device *dev); /* Trace interface for clients */ ishtp_print_log ishtp_trace_callback(struct ishtp_cl_device *cl_device); /* Get device pointer of PCI device for DMA acces */ -- cgit v1.2.3 From b00628b1c7d595ae5b544e059c27b1f5828314b4 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 14 Jul 2021 17:54:09 -0700 Subject: bpf: Introduce bpf timers. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce 'struct bpf_timer { __u64 :64; __u64 :64; };' that can be embedded in hash/array/lru maps as a regular field and helpers to operate on it: // Initialize the timer. // First 4 bits of 'flags' specify clockid. // Only CLOCK_MONOTONIC, CLOCK_REALTIME, CLOCK_BOOTTIME are allowed. long bpf_timer_init(struct bpf_timer *timer, struct bpf_map *map, int flags); // Configure the timer to call 'callback_fn' static function. long bpf_timer_set_callback(struct bpf_timer *timer, void *callback_fn); // Arm the timer to expire 'nsec' nanoseconds from the current time. long bpf_timer_start(struct bpf_timer *timer, u64 nsec, u64 flags); // Cancel the timer and wait for callback_fn to finish if it was running. long bpf_timer_cancel(struct bpf_timer *timer); Here is how BPF program might look like: struct map_elem { int counter; struct bpf_timer timer; }; struct { __uint(type, BPF_MAP_TYPE_HASH); __uint(max_entries, 1000); __type(key, int); __type(value, struct map_elem); } hmap SEC(".maps"); static int timer_cb(void *map, int *key, struct map_elem *val); /* val points to particular map element that contains bpf_timer. */ SEC("fentry/bpf_fentry_test1") int BPF_PROG(test1, int a) { struct map_elem *val; int key = 0; val = bpf_map_lookup_elem(&hmap, &key); if (val) { bpf_timer_init(&val->timer, &hmap, CLOCK_REALTIME); bpf_timer_set_callback(&val->timer, timer_cb); bpf_timer_start(&val->timer, 1000 /* call timer_cb2 in 1 usec */, 0); } } This patch adds helper implementations that rely on hrtimers to call bpf functions as timers expire. The following patches add necessary safety checks. Only programs with CAP_BPF are allowed to use bpf_timer. The amount of timers used by the program is constrained by the memcg recorded at map creation time. The bpf_timer_init() helper needs explicit 'map' argument because inner maps are dynamic and not known at load time. While the bpf_timer_set_callback() is receiving hidden 'aux->prog' argument supplied by the verifier. The prog pointer is needed to do refcnting of bpf program to make sure that program doesn't get freed while the timer is armed. This approach relies on "user refcnt" scheme used in prog_array that stores bpf programs for bpf_tail_call. The bpf_timer_set_callback() will increment the prog refcnt which is paired with bpf_timer_cancel() that will drop the prog refcnt. The ops->map_release_uref is responsible for cancelling the timers and dropping prog refcnt when user space reference to a map reaches zero. This uref approach is done to make sure that Ctrl-C of user space process will not leave timers running forever unless the user space explicitly pinned a map that contained timers in bpffs. bpf_timer_init() and bpf_timer_set_callback() will return -EPERM if map doesn't have user references (is not held by open file descriptor from user space and not pinned in bpffs). The bpf_map_delete_elem() and bpf_map_update_elem() operations cancel and free the timer if given map element had it allocated. "bpftool map update" command can be used to cancel timers. The 'struct bpf_timer' is explicitly __attribute__((aligned(8))) because '__u64 :64' has 1 byte alignment of 8 byte padding. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Martin KaFai Lau Acked-by: Andrii Nakryiko Acked-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/bpf/20210715005417.78572-4-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4afbff308ca3..125240b7cefb 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -168,6 +168,7 @@ struct bpf_map { u32 max_entries; u32 map_flags; int spin_lock_off; /* >=0 valid offset, <0 error */ + int timer_off; /* >=0 valid offset, <0 error */ u32 id; int numa_node; u32 btf_key_type_id; @@ -221,6 +222,7 @@ static inline void copy_map_value(struct bpf_map *map, void *dst, void *src) } void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, bool lock_src); +void bpf_timer_cancel_and_free(void *timer); int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size); struct bpf_offload_dev; @@ -314,6 +316,7 @@ enum bpf_arg_type { ARG_PTR_TO_FUNC, /* pointer to a bpf program function */ ARG_PTR_TO_STACK_OR_NULL, /* pointer to stack or NULL */ ARG_PTR_TO_CONST_STR, /* pointer to a null terminated read-only string */ + ARG_PTR_TO_TIMER, /* pointer to bpf_timer */ __BPF_ARG_TYPE_MAX, }; -- cgit v1.2.3 From 68134668c17f31f51930478f75495b552a411550 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 14 Jul 2021 17:54:10 -0700 Subject: bpf: Add map side support for bpf timers. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Restrict bpf timers to array, hash (both preallocated and kmalloced), and lru map types. The per-cpu maps with timers don't make sense, since 'struct bpf_timer' is a part of map value. bpf timers in per-cpu maps would mean that the number of timers depends on number of possible cpus and timers would not be accessible from all cpus. lpm map support can be added in the future. The timers in inner maps are supported. The bpf_map_update/delete_elem() helpers and sys_bpf commands cancel and free bpf_timer in a given map element. Similar to 'struct bpf_spin_lock' BTF is required and it is used to validate that map element indeed contains 'struct bpf_timer'. Make check_and_init_map_value() init both bpf_spin_lock and bpf_timer when map element data is reused in preallocated htab and lru maps. Teach copy_map_value() to support both bpf_spin_lock and bpf_timer in a single map element. There could be one of each, but not more than one. Due to 'one bpf_timer in one element' restriction do not support timers in global data, since global data is a map of single element, but from bpf program side it's seen as many global variables and restriction of single global timer would be odd. The sys_bpf map_freeze and sys_mmap syscalls are not allowed on maps with timers, since user space could have corrupted mmap element and crashed the kernel. The maps with timers cannot be readonly. Due to these restrictions search for bpf_timer in datasec BTF in case it was placed in the global data to report clear error. The previous patch allowed 'struct bpf_timer' as a first field in a map element only. Relax this restriction. Refactor lru map to s/bpf_lru_push_free/htab_lru_push_free/ to cancel and free the timer when lru map deletes an element as a part of it eviction algorithm. Make sure that bpf program cannot access 'struct bpf_timer' via direct load/store. The timer operation are done through helpers only. This is similar to 'struct bpf_spin_lock'. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Acked-by: Martin KaFai Lau Acked-by: Andrii Nakryiko Acked-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/bpf/20210715005417.78572-5-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 44 +++++++++++++++++++++++++++++++++----------- include/linux/btf.h | 1 + 2 files changed, 34 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 125240b7cefb..a9a4a480a6d0 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -198,24 +198,46 @@ static inline bool map_value_has_spin_lock(const struct bpf_map *map) return map->spin_lock_off >= 0; } -static inline void check_and_init_map_lock(struct bpf_map *map, void *dst) +static inline bool map_value_has_timer(const struct bpf_map *map) { - if (likely(!map_value_has_spin_lock(map))) - return; - *(struct bpf_spin_lock *)(dst + map->spin_lock_off) = - (struct bpf_spin_lock){}; + return map->timer_off >= 0; } -/* copy everything but bpf_spin_lock */ +static inline void check_and_init_map_value(struct bpf_map *map, void *dst) +{ + if (unlikely(map_value_has_spin_lock(map))) + *(struct bpf_spin_lock *)(dst + map->spin_lock_off) = + (struct bpf_spin_lock){}; + if (unlikely(map_value_has_timer(map))) + *(struct bpf_timer *)(dst + map->timer_off) = + (struct bpf_timer){}; +} + +/* copy everything but bpf_spin_lock and bpf_timer. There could be one of each. */ static inline void copy_map_value(struct bpf_map *map, void *dst, void *src) { + u32 s_off = 0, s_sz = 0, t_off = 0, t_sz = 0; + if (unlikely(map_value_has_spin_lock(map))) { - u32 off = map->spin_lock_off; + s_off = map->spin_lock_off; + s_sz = sizeof(struct bpf_spin_lock); + } else if (unlikely(map_value_has_timer(map))) { + t_off = map->timer_off; + t_sz = sizeof(struct bpf_timer); + } - memcpy(dst, src, off); - memcpy(dst + off + sizeof(struct bpf_spin_lock), - src + off + sizeof(struct bpf_spin_lock), - map->value_size - off - sizeof(struct bpf_spin_lock)); + if (unlikely(s_sz || t_sz)) { + if (s_off < t_off || !s_sz) { + swap(s_off, t_off); + swap(s_sz, t_sz); + } + memcpy(dst, src, t_off); + memcpy(dst + t_off + t_sz, + src + t_off + t_sz, + s_off - t_off - t_sz); + memcpy(dst + s_off + s_sz, + src + s_off + s_sz, + map->value_size - s_off - s_sz); } else { memcpy(dst, src, map->value_size); } diff --git a/include/linux/btf.h b/include/linux/btf.h index 94a0c976c90f..214fde93214b 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -99,6 +99,7 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, const struct btf_member *m, u32 expected_offset, u32 expected_size); int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t); +int btf_find_timer(const struct btf *btf, const struct btf_type *t); bool btf_type_is_void(const struct btf_type *t); s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind); const struct btf_type *btf_type_skip_modifiers(const struct btf *btf, -- cgit v1.2.3 From 3e8ce29850f1839d0603f925b30be9d8a4329917 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 14 Jul 2021 17:54:11 -0700 Subject: bpf: Prevent pointer mismatch in bpf_timer_init. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit bpf_timer_init() arguments are: 1. pointer to a timer (which is embedded in map element). 2. pointer to a map. Make sure that pointer to a timer actually belongs to that map. Use map_uid (which is unique id of inner map) to reject: inner_map1 = bpf_map_lookup_elem(outer_map, key1) inner_map2 = bpf_map_lookup_elem(outer_map, key2) if (inner_map1 && inner_map2) { timer = bpf_map_lookup_elem(inner_map1); if (timer) // mismatch would have been allowed bpf_timer_init(timer, inner_map2); } Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Martin KaFai Lau Acked-by: Andrii Nakryiko Acked-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/bpf/20210715005417.78572-6-alexei.starovoitov@gmail.com --- include/linux/bpf_verifier.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index e774ecc1cd1f..5d3169b57e6e 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -53,7 +53,14 @@ struct bpf_reg_state { /* valid when type == CONST_PTR_TO_MAP | PTR_TO_MAP_VALUE | * PTR_TO_MAP_VALUE_OR_NULL */ - struct bpf_map *map_ptr; + struct { + struct bpf_map *map_ptr; + /* To distinguish map lookups from outer map + * the map_uid is non-zero for registers + * pointing to inner maps. + */ + u32 map_uid; + }; /* for PTR_TO_BTF_ID */ struct { -- cgit v1.2.3 From bfc6bb74e4f16ab264fa73398a7a79d7d2afac2e Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 14 Jul 2021 17:54:14 -0700 Subject: bpf: Implement verifier support for validation of async callbacks. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit bpf_for_each_map_elem() and bpf_timer_set_callback() helpers are relying on PTR_TO_FUNC infra in the verifier to validate addresses to subprograms and pass them into the helpers as function callbacks. In case of bpf_for_each_map_elem() the callback is invoked synchronously and the verifier treats it as a normal subprogram call by adding another bpf_func_state and new frame in __check_func_call(). bpf_timer_set_callback() doesn't invoke the callback directly. The subprogram will be called asynchronously from bpf_timer_cb(). Teach the verifier to validate such async callbacks as special kind of jump by pushing verifier state into stack and let pop_stack() process it. Special care needs to be taken during state pruning. The call insn doing bpf_timer_set_callback has to be a prune_point. Otherwise short timer callbacks might not have prune points in front of bpf_timer_set_callback() which means is_state_visited() will be called after this call insn is processed in __check_func_call(). Which means that another async_cb state will be pushed to be walked later and the verifier will eventually hit BPF_COMPLEXITY_LIMIT_JMP_SEQ limit. Since push_async_cb() looks like another push_stack() branch the infinite loop detection will trigger false positive. To recognize this case mark such states as in_async_callback_fn. To distinguish infinite loop in async callback vs the same callback called with different arguments for different map and timer add async_entry_cnt to bpf_func_state. Enforce return zero from async callbacks. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Acked-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/bpf/20210715005417.78572-9-alexei.starovoitov@gmail.com --- include/linux/bpf_verifier.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 5d3169b57e6e..242d0b1a0772 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -208,12 +208,19 @@ struct bpf_func_state { * zero == main subprog */ u32 subprogno; + /* Every bpf_timer_start will increment async_entry_cnt. + * It's used to distinguish: + * void foo(void) { for(;;); } + * void foo(void) { bpf_timer_set_callback(,foo); } + */ + u32 async_entry_cnt; + bool in_callback_fn; + bool in_async_callback_fn; /* The following fields should be last. See copy_func_state() */ int acquired_refs; struct bpf_reference_state *refs; int allocated_stack; - bool in_callback_fn; struct bpf_stack_state *stack; }; -- cgit v1.2.3 From 7ddc80a476c2d599246028af5808d15f9e24c109 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 14 Jul 2021 17:54:15 -0700 Subject: bpf: Teach stack depth check about async callbacks. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Teach max stack depth checking algorithm about async callbacks that don't increase bpf program stack size. Also add sanity check that bpf_tail_call didn't sneak into async cb. It's impossible, since PTR_TO_CTX is not available in async cb, hence the program cannot contain bpf_tail_call(ctx,...); Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Acked-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/bpf/20210715005417.78572-10-alexei.starovoitov@gmail.com --- include/linux/bpf_verifier.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 242d0b1a0772..b847e1ccd10f 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -406,6 +406,7 @@ struct bpf_subprog_info { bool has_tail_call; bool tail_call_reachable; bool has_ld_abs; + bool is_async_cb; }; /* single container for all structs -- cgit v1.2.3 From 7ed012969bbcdbd7aef5778a061681e6cbc4b402 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Wed, 14 Jul 2021 17:01:59 +0200 Subject: Compiler Attributes: fix __has_attribute(__no_sanitize_coverage__) for GCC 4 Fix __has_attribute(__no_sanitize_coverage__) for GCC 4 by defining __GCC4_has_attribute___no_sanitize_coverage__. Fixes: 540540d06e9d ("kcov: add __no_sanitize_coverage to fix noinstr for all architectures") Reported-by: Geert Uytterhoeven Signed-off-by: Marco Elver Signed-off-by: Miguel Ojeda --- include/linux/compiler_attributes.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 183ddd5fd072..7b1fa5c30169 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -36,6 +36,7 @@ # define __GCC4_has_attribute___nonstring__ 0 # define __GCC4_has_attribute___no_sanitize_address__ (__GNUC_MINOR__ >= 8) # define __GCC4_has_attribute___no_sanitize_undefined__ (__GNUC_MINOR__ >= 9) +# define __GCC4_has_attribute___no_sanitize_coverage__ 0 # define __GCC4_has_attribute___fallthrough__ 0 #endif -- cgit v1.2.3 From 7e6f3cd89f04a0a577002d5696288b482109d25c Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 14 Jul 2021 11:43:53 +0200 Subject: bpf, x86: Store caller's ip in trampoline stack Storing caller's ip in trampoline's stack. Trampoline programs can reach the IP in (ctx - 8) address, so there's no change in program's arguments interface. The IP address is takes from [fp + 8], which is return address from the initial 'call fentry' call to trampoline. This IP address will be returned via bpf_get_func_ip helper helper, which is added in following patches. Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210714094400.396467-2-jolsa@kernel.org --- include/linux/bpf.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a9a4a480a6d0..94d77dc7ce35 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -579,6 +579,11 @@ struct btf_func_model { */ #define BPF_TRAMP_F_SKIP_FRAME BIT(2) +/* Store IP address of the caller on the trampoline stack, + * so it's available for trampoline's programs. + */ +#define BPF_TRAMP_F_IP_ARG BIT(3) + /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 * bytes on x86. Pick a number to fit into BPF_IMAGE_SIZE / 2 */ -- cgit v1.2.3 From 1e37392cccdea94da635e3c6d16b21865806f619 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 14 Jul 2021 11:43:54 +0200 Subject: bpf: Enable BPF_TRAMP_F_IP_ARG for trampolines with call_get_func_ip Enabling BPF_TRAMP_F_IP_ARG for trampolines that actually need it. The BPF_TRAMP_F_IP_ARG adds extra 3 instructions to trampoline code and is used only by programs with bpf_get_func_ip helper, which is added in following patch and sets call_get_func_ip bit. This patch ensures that BPF_TRAMP_F_IP_ARG flag is used only for trampolines that have programs with call_get_func_ip set. Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210714094400.396467-3-jolsa@kernel.org --- include/linux/filter.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 472f97074da0..ba36989f711a 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -559,7 +559,8 @@ struct bpf_prog { kprobe_override:1, /* Do we override a kprobe? */ has_callchain_buf:1, /* callchain buffer allocated? */ enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */ - call_get_stack:1; /* Do we call bpf_get_stack() or bpf_get_stackid() */ + call_get_stack:1, /* Do we call bpf_get_stack() or bpf_get_stackid() */ + call_get_func_ip:1; /* Do we call get_func_ip() */ enum bpf_prog_type type; /* Type of BPF program */ enum bpf_attach_type expected_attach_type; /* For some prog types */ u32 len; /* Number of filter blocks */ -- cgit v1.2.3 From 17edea21b38d047a10c189296c58aea9875d0d0a Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Sun, 4 Jul 2021 12:02:42 -0700 Subject: sock_map: Relax config dependency to CONFIG_NET Currently sock_map still has Kconfig dependency on CONFIG_INET, but there is no actual functional dependency on it after we introduce ->psock_update_sk_prot(). We have to extend it to CONFIG_NET now as we are going to support AF_UNIX. Signed-off-by: Cong Wang Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210704190252.11866-2-xiyou.wangcong@gmail.com --- include/linux/bpf.h | 38 ++++++++++++++++++++------------------ 1 file changed, 20 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 94d77dc7ce35..d25c16c365e5 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1887,6 +1887,12 @@ void bpf_map_offload_map_free(struct bpf_map *map); int bpf_prog_test_run_syscall(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); + +int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); +int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); +int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags); +void sock_map_unhash(struct sock *sk); +void sock_map_close(struct sock *sk, long timeout); #else static inline int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) @@ -1919,24 +1925,6 @@ static inline int bpf_prog_test_run_syscall(struct bpf_prog *prog, { return -ENOTSUPP; } -#endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ - -#if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) -int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); -int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); -int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags); -void sock_map_unhash(struct sock *sk); -void sock_map_close(struct sock *sk, long timeout); - -void bpf_sk_reuseport_detach(struct sock *sk); -int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, - void *value); -int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, - void *value, u64 map_flags); -#else -static inline void bpf_sk_reuseport_detach(struct sock *sk) -{ -} #ifdef CONFIG_BPF_SYSCALL static inline int sock_map_get_from_fd(const union bpf_attr *attr, @@ -1956,7 +1944,21 @@ static inline int sock_map_update_elem_sys(struct bpf_map *map, void *key, void { return -EOPNOTSUPP; } +#endif /* CONFIG_BPF_SYSCALL */ +#endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ +#if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) +void bpf_sk_reuseport_detach(struct sock *sk); +int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, + void *value); +int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags); +#else +static inline void bpf_sk_reuseport_detach(struct sock *sk) +{ +} + +#ifdef CONFIG_BPF_SYSCALL static inline int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, void *value) { -- cgit v1.2.3 From 56d629af09b9d4db9792257165844287ecce0a98 Mon Sep 17 00:00:00 2001 From: Daisuke Nojiri Date: Wed, 16 Jun 2021 11:51:24 -0700 Subject: power: supply: PCHG: Peripheral device charger This patch adds a driver for PCHG (Peripheral CHarGer). PCHG is a framework managing power supplies for peripheral devices. This driver creates a sysfs node for each peripheral charge port: /sys/class/power_supply/peripheral where is the index of a charge port. For example, when a stylus is connected to a NFC/WLC port, the node returns: /sys/class/power_supply/peripheral0/ capacity=50 charge_type=Standard scope=Device status=Charging type=Battery Signed-off-by: Daisuke Nojiri Signed-off-by: Sebastian Reichel --- include/linux/platform_data/cros_ec_commands.h | 67 ++++++++++++++++++++++++++ 1 file changed, 67 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index 45f53afc46e2..271bd87bff0a 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -4228,6 +4228,7 @@ enum ec_device_event { EC_DEVICE_EVENT_TRACKPAD, EC_DEVICE_EVENT_DSP, EC_DEVICE_EVENT_WIFI, + EC_DEVICE_EVENT_WLC, }; enum ec_device_event_param { @@ -5460,6 +5461,72 @@ struct ec_response_rollback_info { /* Issue AP reset */ #define EC_CMD_AP_RESET 0x0125 +/** + * Get the number of peripheral charge ports + */ +#define EC_CMD_PCHG_COUNT 0x0134 + +#define EC_PCHG_MAX_PORTS 8 + +struct ec_response_pchg_count { + uint8_t port_count; +} __ec_align1; + +/** + * Get the status of a peripheral charge port + */ +#define EC_CMD_PCHG 0x0135 + +struct ec_params_pchg { + uint8_t port; +} __ec_align1; + +struct ec_response_pchg { + uint32_t error; /* enum pchg_error */ + uint8_t state; /* enum pchg_state state */ + uint8_t battery_percentage; + uint8_t unused0; + uint8_t unused1; + /* Fields added in version 1 */ + uint32_t fw_version; + uint32_t dropped_event_count; +} __ec_align2; + +enum pchg_state { + /* Charger is reset and not initialized. */ + PCHG_STATE_RESET = 0, + /* Charger is initialized or disabled. */ + PCHG_STATE_INITIALIZED, + /* Charger is enabled and ready to detect a device. */ + PCHG_STATE_ENABLED, + /* Device is in proximity. */ + PCHG_STATE_DETECTED, + /* Device is being charged. */ + PCHG_STATE_CHARGING, + /* Device is fully charged. It implies DETECTED (& not charging). */ + PCHG_STATE_FULL, + /* In download (a.k.a. firmware update) mode */ + PCHG_STATE_DOWNLOAD, + /* In download mode. Ready for receiving data. */ + PCHG_STATE_DOWNLOADING, + /* Device is ready for data communication. */ + PCHG_STATE_CONNECTED, + /* Put no more entry below */ + PCHG_STATE_COUNT, +}; + +#define EC_PCHG_STATE_TEXT { \ + [PCHG_STATE_RESET] = "RESET", \ + [PCHG_STATE_INITIALIZED] = "INITIALIZED", \ + [PCHG_STATE_ENABLED] = "ENABLED", \ + [PCHG_STATE_DETECTED] = "DETECTED", \ + [PCHG_STATE_CHARGING] = "CHARGING", \ + [PCHG_STATE_FULL] = "FULL", \ + [PCHG_STATE_DOWNLOAD] = "DOWNLOAD", \ + [PCHG_STATE_DOWNLOADING] = "DOWNLOADING", \ + [PCHG_STATE_CONNECTED] = "CONNECTED", \ + } + /*****************************************************************************/ /* Voltage regulator controls */ -- cgit v1.2.3 From e042aa532c84d18ff13291d00620502ce7a38dda Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 16 Jul 2021 09:18:21 +0000 Subject: bpf: Fix pointer arithmetic mask tightening under state pruning In 7fedb63a8307 ("bpf: Tighten speculative pointer arithmetic mask") we narrowed the offset mask for unprivileged pointer arithmetic in order to mitigate a corner case where in the speculative domain it is possible to advance, for example, the map value pointer by up to value_size-1 out-of- bounds in order to leak kernel memory via side-channel to user space. The verifier's state pruning for scalars leaves one corner case open where in the first verification path R_x holds an unknown scalar with an aux->alu_limit of e.g. 7, and in a second verification path that same register R_x, here denoted as R_x', holds an unknown scalar which has tighter bounds and would thus satisfy range_within(R_x, R_x') as well as tnum_in(R_x, R_x') for state pruning, yielding an aux->alu_limit of 3: Given the second path fits the register constraints for pruning, the final generated mask from aux->alu_limit will remain at 7. While technically not wrong for the non-speculative domain, it would however be possible to craft similar cases where the mask would be too wide as in 7fedb63a8307. One way to fix it is to detect the presence of unknown scalar map pointer arithmetic and force a deeper search on unknown scalars to ensure that we do not run into a masking mismatch. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index e774ecc1cd1f..7ba7e800d472 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -414,6 +414,7 @@ struct bpf_verifier_env { u32 used_map_cnt; /* number of used maps */ u32 used_btf_cnt; /* number of used BTF objects */ u32 id_gen; /* used to generate unique reg IDs */ + bool explore_alu_limits; bool allow_ptr_leaks; bool allow_uninit_stack; bool allow_ptr_to_map_access; -- cgit v1.2.3 From e3d18cee258b898017b298b5b93f8134dd62aee3 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Tue, 13 Jul 2021 11:52:51 +0100 Subject: locking/atomic: centralize generated headers The generated atomic headers are only intended to be included directly by , but are spread across include/linux/ and include/asm-generic/, where people mnay be encouraged to include them. This patch centralizes them under include/linux/atomic/. Other than the header guards and hashes, there is no change to any of the generated headers as a result of this patch. Signed-off-by: Mark Rutland Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20210713105253.7615-4-mark.rutland@arm.com --- include/linux/atomic-arch-fallback.h | 2361 --------------------------- include/linux/atomic.h | 7 +- include/linux/atomic/atomic-arch-fallback.h | 2361 +++++++++++++++++++++++++++ include/linux/atomic/atomic-instrumented.h | 1337 +++++++++++++++ include/linux/atomic/atomic-long.h | 1014 ++++++++++++ 5 files changed, 4715 insertions(+), 2365 deletions(-) delete mode 100644 include/linux/atomic-arch-fallback.h create mode 100644 include/linux/atomic/atomic-arch-fallback.h create mode 100644 include/linux/atomic/atomic-instrumented.h create mode 100644 include/linux/atomic/atomic-long.h (limited to 'include/linux') diff --git a/include/linux/atomic-arch-fallback.h b/include/linux/atomic-arch-fallback.h deleted file mode 100644 index a3dba31df01e..000000000000 --- a/include/linux/atomic-arch-fallback.h +++ /dev/null @@ -1,2361 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -// Generated by scripts/atomic/gen-atomic-fallback.sh -// DO NOT MODIFY THIS FILE DIRECTLY - -#ifndef _LINUX_ATOMIC_FALLBACK_H -#define _LINUX_ATOMIC_FALLBACK_H - -#include - -#ifndef arch_xchg_relaxed -#define arch_xchg_acquire arch_xchg -#define arch_xchg_release arch_xchg -#define arch_xchg_relaxed arch_xchg -#else /* arch_xchg_relaxed */ - -#ifndef arch_xchg_acquire -#define arch_xchg_acquire(...) \ - __atomic_op_acquire(arch_xchg, __VA_ARGS__) -#endif - -#ifndef arch_xchg_release -#define arch_xchg_release(...) \ - __atomic_op_release(arch_xchg, __VA_ARGS__) -#endif - -#ifndef arch_xchg -#define arch_xchg(...) \ - __atomic_op_fence(arch_xchg, __VA_ARGS__) -#endif - -#endif /* arch_xchg_relaxed */ - -#ifndef arch_cmpxchg_relaxed -#define arch_cmpxchg_acquire arch_cmpxchg -#define arch_cmpxchg_release arch_cmpxchg -#define arch_cmpxchg_relaxed arch_cmpxchg -#else /* arch_cmpxchg_relaxed */ - -#ifndef arch_cmpxchg_acquire -#define arch_cmpxchg_acquire(...) \ - __atomic_op_acquire(arch_cmpxchg, __VA_ARGS__) -#endif - -#ifndef arch_cmpxchg_release -#define arch_cmpxchg_release(...) \ - __atomic_op_release(arch_cmpxchg, __VA_ARGS__) -#endif - -#ifndef arch_cmpxchg -#define arch_cmpxchg(...) \ - __atomic_op_fence(arch_cmpxchg, __VA_ARGS__) -#endif - -#endif /* arch_cmpxchg_relaxed */ - -#ifndef arch_cmpxchg64_relaxed -#define arch_cmpxchg64_acquire arch_cmpxchg64 -#define arch_cmpxchg64_release arch_cmpxchg64 -#define arch_cmpxchg64_relaxed arch_cmpxchg64 -#else /* arch_cmpxchg64_relaxed */ - -#ifndef arch_cmpxchg64_acquire -#define arch_cmpxchg64_acquire(...) \ - __atomic_op_acquire(arch_cmpxchg64, __VA_ARGS__) -#endif - -#ifndef arch_cmpxchg64_release -#define arch_cmpxchg64_release(...) \ - __atomic_op_release(arch_cmpxchg64, __VA_ARGS__) -#endif - -#ifndef arch_cmpxchg64 -#define arch_cmpxchg64(...) \ - __atomic_op_fence(arch_cmpxchg64, __VA_ARGS__) -#endif - -#endif /* arch_cmpxchg64_relaxed */ - -#ifndef arch_try_cmpxchg_relaxed -#ifdef arch_try_cmpxchg -#define arch_try_cmpxchg_acquire arch_try_cmpxchg -#define arch_try_cmpxchg_release arch_try_cmpxchg -#define arch_try_cmpxchg_relaxed arch_try_cmpxchg -#endif /* arch_try_cmpxchg */ - -#ifndef arch_try_cmpxchg -#define arch_try_cmpxchg(_ptr, _oldp, _new) \ -({ \ - typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ - ___r = arch_cmpxchg((_ptr), ___o, (_new)); \ - if (unlikely(___r != ___o)) \ - *___op = ___r; \ - likely(___r == ___o); \ -}) -#endif /* arch_try_cmpxchg */ - -#ifndef arch_try_cmpxchg_acquire -#define arch_try_cmpxchg_acquire(_ptr, _oldp, _new) \ -({ \ - typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ - ___r = arch_cmpxchg_acquire((_ptr), ___o, (_new)); \ - if (unlikely(___r != ___o)) \ - *___op = ___r; \ - likely(___r == ___o); \ -}) -#endif /* arch_try_cmpxchg_acquire */ - -#ifndef arch_try_cmpxchg_release -#define arch_try_cmpxchg_release(_ptr, _oldp, _new) \ -({ \ - typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ - ___r = arch_cmpxchg_release((_ptr), ___o, (_new)); \ - if (unlikely(___r != ___o)) \ - *___op = ___r; \ - likely(___r == ___o); \ -}) -#endif /* arch_try_cmpxchg_release */ - -#ifndef arch_try_cmpxchg_relaxed -#define arch_try_cmpxchg_relaxed(_ptr, _oldp, _new) \ -({ \ - typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ - ___r = arch_cmpxchg_relaxed((_ptr), ___o, (_new)); \ - if (unlikely(___r != ___o)) \ - *___op = ___r; \ - likely(___r == ___o); \ -}) -#endif /* arch_try_cmpxchg_relaxed */ - -#else /* arch_try_cmpxchg_relaxed */ - -#ifndef arch_try_cmpxchg_acquire -#define arch_try_cmpxchg_acquire(...) \ - __atomic_op_acquire(arch_try_cmpxchg, __VA_ARGS__) -#endif - -#ifndef arch_try_cmpxchg_release -#define arch_try_cmpxchg_release(...) \ - __atomic_op_release(arch_try_cmpxchg, __VA_ARGS__) -#endif - -#ifndef arch_try_cmpxchg -#define arch_try_cmpxchg(...) \ - __atomic_op_fence(arch_try_cmpxchg, __VA_ARGS__) -#endif - -#endif /* arch_try_cmpxchg_relaxed */ - -#ifndef arch_atomic_read_acquire -static __always_inline int -arch_atomic_read_acquire(const atomic_t *v) -{ - return smp_load_acquire(&(v)->counter); -} -#define arch_atomic_read_acquire arch_atomic_read_acquire -#endif - -#ifndef arch_atomic_set_release -static __always_inline void -arch_atomic_set_release(atomic_t *v, int i) -{ - smp_store_release(&(v)->counter, i); -} -#define arch_atomic_set_release arch_atomic_set_release -#endif - -#ifndef arch_atomic_add_return_relaxed -#define arch_atomic_add_return_acquire arch_atomic_add_return -#define arch_atomic_add_return_release arch_atomic_add_return -#define arch_atomic_add_return_relaxed arch_atomic_add_return -#else /* arch_atomic_add_return_relaxed */ - -#ifndef arch_atomic_add_return_acquire -static __always_inline int -arch_atomic_add_return_acquire(int i, atomic_t *v) -{ - int ret = arch_atomic_add_return_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic_add_return_acquire arch_atomic_add_return_acquire -#endif - -#ifndef arch_atomic_add_return_release -static __always_inline int -arch_atomic_add_return_release(int i, atomic_t *v) -{ - __atomic_release_fence(); - return arch_atomic_add_return_relaxed(i, v); -} -#define arch_atomic_add_return_release arch_atomic_add_return_release -#endif - -#ifndef arch_atomic_add_return -static __always_inline int -arch_atomic_add_return(int i, atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = arch_atomic_add_return_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic_add_return arch_atomic_add_return -#endif - -#endif /* arch_atomic_add_return_relaxed */ - -#ifndef arch_atomic_fetch_add_relaxed -#define arch_atomic_fetch_add_acquire arch_atomic_fetch_add -#define arch_atomic_fetch_add_release arch_atomic_fetch_add -#define arch_atomic_fetch_add_relaxed arch_atomic_fetch_add -#else /* arch_atomic_fetch_add_relaxed */ - -#ifndef arch_atomic_fetch_add_acquire -static __always_inline int -arch_atomic_fetch_add_acquire(int i, atomic_t *v) -{ - int ret = arch_atomic_fetch_add_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic_fetch_add_acquire arch_atomic_fetch_add_acquire -#endif - -#ifndef arch_atomic_fetch_add_release -static __always_inline int -arch_atomic_fetch_add_release(int i, atomic_t *v) -{ - __atomic_release_fence(); - return arch_atomic_fetch_add_relaxed(i, v); -} -#define arch_atomic_fetch_add_release arch_atomic_fetch_add_release -#endif - -#ifndef arch_atomic_fetch_add -static __always_inline int -arch_atomic_fetch_add(int i, atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = arch_atomic_fetch_add_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic_fetch_add arch_atomic_fetch_add -#endif - -#endif /* arch_atomic_fetch_add_relaxed */ - -#ifndef arch_atomic_sub_return_relaxed -#define arch_atomic_sub_return_acquire arch_atomic_sub_return -#define arch_atomic_sub_return_release arch_atomic_sub_return -#define arch_atomic_sub_return_relaxed arch_atomic_sub_return -#else /* arch_atomic_sub_return_relaxed */ - -#ifndef arch_atomic_sub_return_acquire -static __always_inline int -arch_atomic_sub_return_acquire(int i, atomic_t *v) -{ - int ret = arch_atomic_sub_return_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic_sub_return_acquire arch_atomic_sub_return_acquire -#endif - -#ifndef arch_atomic_sub_return_release -static __always_inline int -arch_atomic_sub_return_release(int i, atomic_t *v) -{ - __atomic_release_fence(); - return arch_atomic_sub_return_relaxed(i, v); -} -#define arch_atomic_sub_return_release arch_atomic_sub_return_release -#endif - -#ifndef arch_atomic_sub_return -static __always_inline int -arch_atomic_sub_return(int i, atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = arch_atomic_sub_return_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic_sub_return arch_atomic_sub_return -#endif - -#endif /* arch_atomic_sub_return_relaxed */ - -#ifndef arch_atomic_fetch_sub_relaxed -#define arch_atomic_fetch_sub_acquire arch_atomic_fetch_sub -#define arch_atomic_fetch_sub_release arch_atomic_fetch_sub -#define arch_atomic_fetch_sub_relaxed arch_atomic_fetch_sub -#else /* arch_atomic_fetch_sub_relaxed */ - -#ifndef arch_atomic_fetch_sub_acquire -static __always_inline int -arch_atomic_fetch_sub_acquire(int i, atomic_t *v) -{ - int ret = arch_atomic_fetch_sub_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic_fetch_sub_acquire arch_atomic_fetch_sub_acquire -#endif - -#ifndef arch_atomic_fetch_sub_release -static __always_inline int -arch_atomic_fetch_sub_release(int i, atomic_t *v) -{ - __atomic_release_fence(); - return arch_atomic_fetch_sub_relaxed(i, v); -} -#define arch_atomic_fetch_sub_release arch_atomic_fetch_sub_release -#endif - -#ifndef arch_atomic_fetch_sub -static __always_inline int -arch_atomic_fetch_sub(int i, atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = arch_atomic_fetch_sub_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic_fetch_sub arch_atomic_fetch_sub -#endif - -#endif /* arch_atomic_fetch_sub_relaxed */ - -#ifndef arch_atomic_inc -static __always_inline void -arch_atomic_inc(atomic_t *v) -{ - arch_atomic_add(1, v); -} -#define arch_atomic_inc arch_atomic_inc -#endif - -#ifndef arch_atomic_inc_return_relaxed -#ifdef arch_atomic_inc_return -#define arch_atomic_inc_return_acquire arch_atomic_inc_return -#define arch_atomic_inc_return_release arch_atomic_inc_return -#define arch_atomic_inc_return_relaxed arch_atomic_inc_return -#endif /* arch_atomic_inc_return */ - -#ifndef arch_atomic_inc_return -static __always_inline int -arch_atomic_inc_return(atomic_t *v) -{ - return arch_atomic_add_return(1, v); -} -#define arch_atomic_inc_return arch_atomic_inc_return -#endif - -#ifndef arch_atomic_inc_return_acquire -static __always_inline int -arch_atomic_inc_return_acquire(atomic_t *v) -{ - return arch_atomic_add_return_acquire(1, v); -} -#define arch_atomic_inc_return_acquire arch_atomic_inc_return_acquire -#endif - -#ifndef arch_atomic_inc_return_release -static __always_inline int -arch_atomic_inc_return_release(atomic_t *v) -{ - return arch_atomic_add_return_release(1, v); -} -#define arch_atomic_inc_return_release arch_atomic_inc_return_release -#endif - -#ifndef arch_atomic_inc_return_relaxed -static __always_inline int -arch_atomic_inc_return_relaxed(atomic_t *v) -{ - return arch_atomic_add_return_relaxed(1, v); -} -#define arch_atomic_inc_return_relaxed arch_atomic_inc_return_relaxed -#endif - -#else /* arch_atomic_inc_return_relaxed */ - -#ifndef arch_atomic_inc_return_acquire -static __always_inline int -arch_atomic_inc_return_acquire(atomic_t *v) -{ - int ret = arch_atomic_inc_return_relaxed(v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic_inc_return_acquire arch_atomic_inc_return_acquire -#endif - -#ifndef arch_atomic_inc_return_release -static __always_inline int -arch_atomic_inc_return_release(atomic_t *v) -{ - __atomic_release_fence(); - return arch_atomic_inc_return_relaxed(v); -} -#define arch_atomic_inc_return_release arch_atomic_inc_return_release -#endif - -#ifndef arch_atomic_inc_return -static __always_inline int -arch_atomic_inc_return(atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = arch_atomic_inc_return_relaxed(v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic_inc_return arch_atomic_inc_return -#endif - -#endif /* arch_atomic_inc_return_relaxed */ - -#ifndef arch_atomic_fetch_inc_relaxed -#ifdef arch_atomic_fetch_inc -#define arch_atomic_fetch_inc_acquire arch_atomic_fetch_inc -#define arch_atomic_fetch_inc_release arch_atomic_fetch_inc -#define arch_atomic_fetch_inc_relaxed arch_atomic_fetch_inc -#endif /* arch_atomic_fetch_inc */ - -#ifndef arch_atomic_fetch_inc -static __always_inline int -arch_atomic_fetch_inc(atomic_t *v) -{ - return arch_atomic_fetch_add(1, v); -} -#define arch_atomic_fetch_inc arch_atomic_fetch_inc -#endif - -#ifndef arch_atomic_fetch_inc_acquire -static __always_inline int -arch_atomic_fetch_inc_acquire(atomic_t *v) -{ - return arch_atomic_fetch_add_acquire(1, v); -} -#define arch_atomic_fetch_inc_acquire arch_atomic_fetch_inc_acquire -#endif - -#ifndef arch_atomic_fetch_inc_release -static __always_inline int -arch_atomic_fetch_inc_release(atomic_t *v) -{ - return arch_atomic_fetch_add_release(1, v); -} -#define arch_atomic_fetch_inc_release arch_atomic_fetch_inc_release -#endif - -#ifndef arch_atomic_fetch_inc_relaxed -static __always_inline int -arch_atomic_fetch_inc_relaxed(atomic_t *v) -{ - return arch_atomic_fetch_add_relaxed(1, v); -} -#define arch_atomic_fetch_inc_relaxed arch_atomic_fetch_inc_relaxed -#endif - -#else /* arch_atomic_fetch_inc_relaxed */ - -#ifndef arch_atomic_fetch_inc_acquire -static __always_inline int -arch_atomic_fetch_inc_acquire(atomic_t *v) -{ - int ret = arch_atomic_fetch_inc_relaxed(v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic_fetch_inc_acquire arch_atomic_fetch_inc_acquire -#endif - -#ifndef arch_atomic_fetch_inc_release -static __always_inline int -arch_atomic_fetch_inc_release(atomic_t *v) -{ - __atomic_release_fence(); - return arch_atomic_fetch_inc_relaxed(v); -} -#define arch_atomic_fetch_inc_release arch_atomic_fetch_inc_release -#endif - -#ifndef arch_atomic_fetch_inc -static __always_inline int -arch_atomic_fetch_inc(atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = arch_atomic_fetch_inc_relaxed(v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic_fetch_inc arch_atomic_fetch_inc -#endif - -#endif /* arch_atomic_fetch_inc_relaxed */ - -#ifndef arch_atomic_dec -static __always_inline void -arch_atomic_dec(atomic_t *v) -{ - arch_atomic_sub(1, v); -} -#define arch_atomic_dec arch_atomic_dec -#endif - -#ifndef arch_atomic_dec_return_relaxed -#ifdef arch_atomic_dec_return -#define arch_atomic_dec_return_acquire arch_atomic_dec_return -#define arch_atomic_dec_return_release arch_atomic_dec_return -#define arch_atomic_dec_return_relaxed arch_atomic_dec_return -#endif /* arch_atomic_dec_return */ - -#ifndef arch_atomic_dec_return -static __always_inline int -arch_atomic_dec_return(atomic_t *v) -{ - return arch_atomic_sub_return(1, v); -} -#define arch_atomic_dec_return arch_atomic_dec_return -#endif - -#ifndef arch_atomic_dec_return_acquire -static __always_inline int -arch_atomic_dec_return_acquire(atomic_t *v) -{ - return arch_atomic_sub_return_acquire(1, v); -} -#define arch_atomic_dec_return_acquire arch_atomic_dec_return_acquire -#endif - -#ifndef arch_atomic_dec_return_release -static __always_inline int -arch_atomic_dec_return_release(atomic_t *v) -{ - return arch_atomic_sub_return_release(1, v); -} -#define arch_atomic_dec_return_release arch_atomic_dec_return_release -#endif - -#ifndef arch_atomic_dec_return_relaxed -static __always_inline int -arch_atomic_dec_return_relaxed(atomic_t *v) -{ - return arch_atomic_sub_return_relaxed(1, v); -} -#define arch_atomic_dec_return_relaxed arch_atomic_dec_return_relaxed -#endif - -#else /* arch_atomic_dec_return_relaxed */ - -#ifndef arch_atomic_dec_return_acquire -static __always_inline int -arch_atomic_dec_return_acquire(atomic_t *v) -{ - int ret = arch_atomic_dec_return_relaxed(v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic_dec_return_acquire arch_atomic_dec_return_acquire -#endif - -#ifndef arch_atomic_dec_return_release -static __always_inline int -arch_atomic_dec_return_release(atomic_t *v) -{ - __atomic_release_fence(); - return arch_atomic_dec_return_relaxed(v); -} -#define arch_atomic_dec_return_release arch_atomic_dec_return_release -#endif - -#ifndef arch_atomic_dec_return -static __always_inline int -arch_atomic_dec_return(atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = arch_atomic_dec_return_relaxed(v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic_dec_return arch_atomic_dec_return -#endif - -#endif /* arch_atomic_dec_return_relaxed */ - -#ifndef arch_atomic_fetch_dec_relaxed -#ifdef arch_atomic_fetch_dec -#define arch_atomic_fetch_dec_acquire arch_atomic_fetch_dec -#define arch_atomic_fetch_dec_release arch_atomic_fetch_dec -#define arch_atomic_fetch_dec_relaxed arch_atomic_fetch_dec -#endif /* arch_atomic_fetch_dec */ - -#ifndef arch_atomic_fetch_dec -static __always_inline int -arch_atomic_fetch_dec(atomic_t *v) -{ - return arch_atomic_fetch_sub(1, v); -} -#define arch_atomic_fetch_dec arch_atomic_fetch_dec -#endif - -#ifndef arch_atomic_fetch_dec_acquire -static __always_inline int -arch_atomic_fetch_dec_acquire(atomic_t *v) -{ - return arch_atomic_fetch_sub_acquire(1, v); -} -#define arch_atomic_fetch_dec_acquire arch_atomic_fetch_dec_acquire -#endif - -#ifndef arch_atomic_fetch_dec_release -static __always_inline int -arch_atomic_fetch_dec_release(atomic_t *v) -{ - return arch_atomic_fetch_sub_release(1, v); -} -#define arch_atomic_fetch_dec_release arch_atomic_fetch_dec_release -#endif - -#ifndef arch_atomic_fetch_dec_relaxed -static __always_inline int -arch_atomic_fetch_dec_relaxed(atomic_t *v) -{ - return arch_atomic_fetch_sub_relaxed(1, v); -} -#define arch_atomic_fetch_dec_relaxed arch_atomic_fetch_dec_relaxed -#endif - -#else /* arch_atomic_fetch_dec_relaxed */ - -#ifndef arch_atomic_fetch_dec_acquire -static __always_inline int -arch_atomic_fetch_dec_acquire(atomic_t *v) -{ - int ret = arch_atomic_fetch_dec_relaxed(v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic_fetch_dec_acquire arch_atomic_fetch_dec_acquire -#endif - -#ifndef arch_atomic_fetch_dec_release -static __always_inline int -arch_atomic_fetch_dec_release(atomic_t *v) -{ - __atomic_release_fence(); - return arch_atomic_fetch_dec_relaxed(v); -} -#define arch_atomic_fetch_dec_release arch_atomic_fetch_dec_release -#endif - -#ifndef arch_atomic_fetch_dec -static __always_inline int -arch_atomic_fetch_dec(atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = arch_atomic_fetch_dec_relaxed(v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic_fetch_dec arch_atomic_fetch_dec -#endif - -#endif /* arch_atomic_fetch_dec_relaxed */ - -#ifndef arch_atomic_fetch_and_relaxed -#define arch_atomic_fetch_and_acquire arch_atomic_fetch_and -#define arch_atomic_fetch_and_release arch_atomic_fetch_and -#define arch_atomic_fetch_and_relaxed arch_atomic_fetch_and -#else /* arch_atomic_fetch_and_relaxed */ - -#ifndef arch_atomic_fetch_and_acquire -static __always_inline int -arch_atomic_fetch_and_acquire(int i, atomic_t *v) -{ - int ret = arch_atomic_fetch_and_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic_fetch_and_acquire arch_atomic_fetch_and_acquire -#endif - -#ifndef arch_atomic_fetch_and_release -static __always_inline int -arch_atomic_fetch_and_release(int i, atomic_t *v) -{ - __atomic_release_fence(); - return arch_atomic_fetch_and_relaxed(i, v); -} -#define arch_atomic_fetch_and_release arch_atomic_fetch_and_release -#endif - -#ifndef arch_atomic_fetch_and -static __always_inline int -arch_atomic_fetch_and(int i, atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = arch_atomic_fetch_and_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic_fetch_and arch_atomic_fetch_and -#endif - -#endif /* arch_atomic_fetch_and_relaxed */ - -#ifndef arch_atomic_andnot -static __always_inline void -arch_atomic_andnot(int i, atomic_t *v) -{ - arch_atomic_and(~i, v); -} -#define arch_atomic_andnot arch_atomic_andnot -#endif - -#ifndef arch_atomic_fetch_andnot_relaxed -#ifdef arch_atomic_fetch_andnot -#define arch_atomic_fetch_andnot_acquire arch_atomic_fetch_andnot -#define arch_atomic_fetch_andnot_release arch_atomic_fetch_andnot -#define arch_atomic_fetch_andnot_relaxed arch_atomic_fetch_andnot -#endif /* arch_atomic_fetch_andnot */ - -#ifndef arch_atomic_fetch_andnot -static __always_inline int -arch_atomic_fetch_andnot(int i, atomic_t *v) -{ - return arch_atomic_fetch_and(~i, v); -} -#define arch_atomic_fetch_andnot arch_atomic_fetch_andnot -#endif - -#ifndef arch_atomic_fetch_andnot_acquire -static __always_inline int -arch_atomic_fetch_andnot_acquire(int i, atomic_t *v) -{ - return arch_atomic_fetch_and_acquire(~i, v); -} -#define arch_atomic_fetch_andnot_acquire arch_atomic_fetch_andnot_acquire -#endif - -#ifndef arch_atomic_fetch_andnot_release -static __always_inline int -arch_atomic_fetch_andnot_release(int i, atomic_t *v) -{ - return arch_atomic_fetch_and_release(~i, v); -} -#define arch_atomic_fetch_andnot_release arch_atomic_fetch_andnot_release -#endif - -#ifndef arch_atomic_fetch_andnot_relaxed -static __always_inline int -arch_atomic_fetch_andnot_relaxed(int i, atomic_t *v) -{ - return arch_atomic_fetch_and_relaxed(~i, v); -} -#define arch_atomic_fetch_andnot_relaxed arch_atomic_fetch_andnot_relaxed -#endif - -#else /* arch_atomic_fetch_andnot_relaxed */ - -#ifndef arch_atomic_fetch_andnot_acquire -static __always_inline int -arch_atomic_fetch_andnot_acquire(int i, atomic_t *v) -{ - int ret = arch_atomic_fetch_andnot_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic_fetch_andnot_acquire arch_atomic_fetch_andnot_acquire -#endif - -#ifndef arch_atomic_fetch_andnot_release -static __always_inline int -arch_atomic_fetch_andnot_release(int i, atomic_t *v) -{ - __atomic_release_fence(); - return arch_atomic_fetch_andnot_relaxed(i, v); -} -#define arch_atomic_fetch_andnot_release arch_atomic_fetch_andnot_release -#endif - -#ifndef arch_atomic_fetch_andnot -static __always_inline int -arch_atomic_fetch_andnot(int i, atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = arch_atomic_fetch_andnot_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic_fetch_andnot arch_atomic_fetch_andnot -#endif - -#endif /* arch_atomic_fetch_andnot_relaxed */ - -#ifndef arch_atomic_fetch_or_relaxed -#define arch_atomic_fetch_or_acquire arch_atomic_fetch_or -#define arch_atomic_fetch_or_release arch_atomic_fetch_or -#define arch_atomic_fetch_or_relaxed arch_atomic_fetch_or -#else /* arch_atomic_fetch_or_relaxed */ - -#ifndef arch_atomic_fetch_or_acquire -static __always_inline int -arch_atomic_fetch_or_acquire(int i, atomic_t *v) -{ - int ret = arch_atomic_fetch_or_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic_fetch_or_acquire arch_atomic_fetch_or_acquire -#endif - -#ifndef arch_atomic_fetch_or_release -static __always_inline int -arch_atomic_fetch_or_release(int i, atomic_t *v) -{ - __atomic_release_fence(); - return arch_atomic_fetch_or_relaxed(i, v); -} -#define arch_atomic_fetch_or_release arch_atomic_fetch_or_release -#endif - -#ifndef arch_atomic_fetch_or -static __always_inline int -arch_atomic_fetch_or(int i, atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = arch_atomic_fetch_or_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic_fetch_or arch_atomic_fetch_or -#endif - -#endif /* arch_atomic_fetch_or_relaxed */ - -#ifndef arch_atomic_fetch_xor_relaxed -#define arch_atomic_fetch_xor_acquire arch_atomic_fetch_xor -#define arch_atomic_fetch_xor_release arch_atomic_fetch_xor -#define arch_atomic_fetch_xor_relaxed arch_atomic_fetch_xor -#else /* arch_atomic_fetch_xor_relaxed */ - -#ifndef arch_atomic_fetch_xor_acquire -static __always_inline int -arch_atomic_fetch_xor_acquire(int i, atomic_t *v) -{ - int ret = arch_atomic_fetch_xor_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic_fetch_xor_acquire arch_atomic_fetch_xor_acquire -#endif - -#ifndef arch_atomic_fetch_xor_release -static __always_inline int -arch_atomic_fetch_xor_release(int i, atomic_t *v) -{ - __atomic_release_fence(); - return arch_atomic_fetch_xor_relaxed(i, v); -} -#define arch_atomic_fetch_xor_release arch_atomic_fetch_xor_release -#endif - -#ifndef arch_atomic_fetch_xor -static __always_inline int -arch_atomic_fetch_xor(int i, atomic_t *v) -{ - int ret; - __atomic_pre_full_fence(); - ret = arch_atomic_fetch_xor_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic_fetch_xor arch_atomic_fetch_xor -#endif - -#endif /* arch_atomic_fetch_xor_relaxed */ - -#ifndef arch_atomic_xchg_relaxed -#define arch_atomic_xchg_acquire arch_atomic_xchg -#define arch_atomic_xchg_release arch_atomic_xchg -#define arch_atomic_xchg_relaxed arch_atomic_xchg -#else /* arch_atomic_xchg_relaxed */ - -#ifndef arch_atomic_xchg_acquire -static __always_inline int -arch_atomic_xchg_acquire(atomic_t *v, int i) -{ - int ret = arch_atomic_xchg_relaxed(v, i); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic_xchg_acquire arch_atomic_xchg_acquire -#endif - -#ifndef arch_atomic_xchg_release -static __always_inline int -arch_atomic_xchg_release(atomic_t *v, int i) -{ - __atomic_release_fence(); - return arch_atomic_xchg_relaxed(v, i); -} -#define arch_atomic_xchg_release arch_atomic_xchg_release -#endif - -#ifndef arch_atomic_xchg -static __always_inline int -arch_atomic_xchg(atomic_t *v, int i) -{ - int ret; - __atomic_pre_full_fence(); - ret = arch_atomic_xchg_relaxed(v, i); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic_xchg arch_atomic_xchg -#endif - -#endif /* arch_atomic_xchg_relaxed */ - -#ifndef arch_atomic_cmpxchg_relaxed -#define arch_atomic_cmpxchg_acquire arch_atomic_cmpxchg -#define arch_atomic_cmpxchg_release arch_atomic_cmpxchg -#define arch_atomic_cmpxchg_relaxed arch_atomic_cmpxchg -#else /* arch_atomic_cmpxchg_relaxed */ - -#ifndef arch_atomic_cmpxchg_acquire -static __always_inline int -arch_atomic_cmpxchg_acquire(atomic_t *v, int old, int new) -{ - int ret = arch_atomic_cmpxchg_relaxed(v, old, new); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic_cmpxchg_acquire arch_atomic_cmpxchg_acquire -#endif - -#ifndef arch_atomic_cmpxchg_release -static __always_inline int -arch_atomic_cmpxchg_release(atomic_t *v, int old, int new) -{ - __atomic_release_fence(); - return arch_atomic_cmpxchg_relaxed(v, old, new); -} -#define arch_atomic_cmpxchg_release arch_atomic_cmpxchg_release -#endif - -#ifndef arch_atomic_cmpxchg -static __always_inline int -arch_atomic_cmpxchg(atomic_t *v, int old, int new) -{ - int ret; - __atomic_pre_full_fence(); - ret = arch_atomic_cmpxchg_relaxed(v, old, new); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic_cmpxchg arch_atomic_cmpxchg -#endif - -#endif /* arch_atomic_cmpxchg_relaxed */ - -#ifndef arch_atomic_try_cmpxchg_relaxed -#ifdef arch_atomic_try_cmpxchg -#define arch_atomic_try_cmpxchg_acquire arch_atomic_try_cmpxchg -#define arch_atomic_try_cmpxchg_release arch_atomic_try_cmpxchg -#define arch_atomic_try_cmpxchg_relaxed arch_atomic_try_cmpxchg -#endif /* arch_atomic_try_cmpxchg */ - -#ifndef arch_atomic_try_cmpxchg -static __always_inline bool -arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new) -{ - int r, o = *old; - r = arch_atomic_cmpxchg(v, o, new); - if (unlikely(r != o)) - *old = r; - return likely(r == o); -} -#define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg -#endif - -#ifndef arch_atomic_try_cmpxchg_acquire -static __always_inline bool -arch_atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) -{ - int r, o = *old; - r = arch_atomic_cmpxchg_acquire(v, o, new); - if (unlikely(r != o)) - *old = r; - return likely(r == o); -} -#define arch_atomic_try_cmpxchg_acquire arch_atomic_try_cmpxchg_acquire -#endif - -#ifndef arch_atomic_try_cmpxchg_release -static __always_inline bool -arch_atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) -{ - int r, o = *old; - r = arch_atomic_cmpxchg_release(v, o, new); - if (unlikely(r != o)) - *old = r; - return likely(r == o); -} -#define arch_atomic_try_cmpxchg_release arch_atomic_try_cmpxchg_release -#endif - -#ifndef arch_atomic_try_cmpxchg_relaxed -static __always_inline bool -arch_atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) -{ - int r, o = *old; - r = arch_atomic_cmpxchg_relaxed(v, o, new); - if (unlikely(r != o)) - *old = r; - return likely(r == o); -} -#define arch_atomic_try_cmpxchg_relaxed arch_atomic_try_cmpxchg_relaxed -#endif - -#else /* arch_atomic_try_cmpxchg_relaxed */ - -#ifndef arch_atomic_try_cmpxchg_acquire -static __always_inline bool -arch_atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) -{ - bool ret = arch_atomic_try_cmpxchg_relaxed(v, old, new); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic_try_cmpxchg_acquire arch_atomic_try_cmpxchg_acquire -#endif - -#ifndef arch_atomic_try_cmpxchg_release -static __always_inline bool -arch_atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) -{ - __atomic_release_fence(); - return arch_atomic_try_cmpxchg_relaxed(v, old, new); -} -#define arch_atomic_try_cmpxchg_release arch_atomic_try_cmpxchg_release -#endif - -#ifndef arch_atomic_try_cmpxchg -static __always_inline bool -arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new) -{ - bool ret; - __atomic_pre_full_fence(); - ret = arch_atomic_try_cmpxchg_relaxed(v, old, new); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg -#endif - -#endif /* arch_atomic_try_cmpxchg_relaxed */ - -#ifndef arch_atomic_sub_and_test -/** - * arch_atomic_sub_and_test - subtract value from variable and test result - * @i: integer value to subtract - * @v: pointer of type atomic_t - * - * Atomically subtracts @i from @v and returns - * true if the result is zero, or false for all - * other cases. - */ -static __always_inline bool -arch_atomic_sub_and_test(int i, atomic_t *v) -{ - return arch_atomic_sub_return(i, v) == 0; -} -#define arch_atomic_sub_and_test arch_atomic_sub_and_test -#endif - -#ifndef arch_atomic_dec_and_test -/** - * arch_atomic_dec_and_test - decrement and test - * @v: pointer of type atomic_t - * - * Atomically decrements @v by 1 and - * returns true if the result is 0, or false for all other - * cases. - */ -static __always_inline bool -arch_atomic_dec_and_test(atomic_t *v) -{ - return arch_atomic_dec_return(v) == 0; -} -#define arch_atomic_dec_and_test arch_atomic_dec_and_test -#endif - -#ifndef arch_atomic_inc_and_test -/** - * arch_atomic_inc_and_test - increment and test - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -static __always_inline bool -arch_atomic_inc_and_test(atomic_t *v) -{ - return arch_atomic_inc_return(v) == 0; -} -#define arch_atomic_inc_and_test arch_atomic_inc_and_test -#endif - -#ifndef arch_atomic_add_negative -/** - * arch_atomic_add_negative - add and test if negative - * @i: integer value to add - * @v: pointer of type atomic_t - * - * Atomically adds @i to @v and returns true - * if the result is negative, or false when - * result is greater than or equal to zero. - */ -static __always_inline bool -arch_atomic_add_negative(int i, atomic_t *v) -{ - return arch_atomic_add_return(i, v) < 0; -} -#define arch_atomic_add_negative arch_atomic_add_negative -#endif - -#ifndef arch_atomic_fetch_add_unless -/** - * arch_atomic_fetch_add_unless - add unless the number is already a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as @v was not already @u. - * Returns original value of @v - */ -static __always_inline int -arch_atomic_fetch_add_unless(atomic_t *v, int a, int u) -{ - int c = arch_atomic_read(v); - - do { - if (unlikely(c == u)) - break; - } while (!arch_atomic_try_cmpxchg(v, &c, c + a)); - - return c; -} -#define arch_atomic_fetch_add_unless arch_atomic_fetch_add_unless -#endif - -#ifndef arch_atomic_add_unless -/** - * arch_atomic_add_unless - add unless the number is already a given value - * @v: pointer of type atomic_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, if @v was not already @u. - * Returns true if the addition was done. - */ -static __always_inline bool -arch_atomic_add_unless(atomic_t *v, int a, int u) -{ - return arch_atomic_fetch_add_unless(v, a, u) != u; -} -#define arch_atomic_add_unless arch_atomic_add_unless -#endif - -#ifndef arch_atomic_inc_not_zero -/** - * arch_atomic_inc_not_zero - increment unless the number is zero - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1, if @v is non-zero. - * Returns true if the increment was done. - */ -static __always_inline bool -arch_atomic_inc_not_zero(atomic_t *v) -{ - return arch_atomic_add_unless(v, 1, 0); -} -#define arch_atomic_inc_not_zero arch_atomic_inc_not_zero -#endif - -#ifndef arch_atomic_inc_unless_negative -static __always_inline bool -arch_atomic_inc_unless_negative(atomic_t *v) -{ - int c = arch_atomic_read(v); - - do { - if (unlikely(c < 0)) - return false; - } while (!arch_atomic_try_cmpxchg(v, &c, c + 1)); - - return true; -} -#define arch_atomic_inc_unless_negative arch_atomic_inc_unless_negative -#endif - -#ifndef arch_atomic_dec_unless_positive -static __always_inline bool -arch_atomic_dec_unless_positive(atomic_t *v) -{ - int c = arch_atomic_read(v); - - do { - if (unlikely(c > 0)) - return false; - } while (!arch_atomic_try_cmpxchg(v, &c, c - 1)); - - return true; -} -#define arch_atomic_dec_unless_positive arch_atomic_dec_unless_positive -#endif - -#ifndef arch_atomic_dec_if_positive -static __always_inline int -arch_atomic_dec_if_positive(atomic_t *v) -{ - int dec, c = arch_atomic_read(v); - - do { - dec = c - 1; - if (unlikely(dec < 0)) - break; - } while (!arch_atomic_try_cmpxchg(v, &c, dec)); - - return dec; -} -#define arch_atomic_dec_if_positive arch_atomic_dec_if_positive -#endif - -#ifdef CONFIG_GENERIC_ATOMIC64 -#include -#endif - -#ifndef arch_atomic64_read_acquire -static __always_inline s64 -arch_atomic64_read_acquire(const atomic64_t *v) -{ - return smp_load_acquire(&(v)->counter); -} -#define arch_atomic64_read_acquire arch_atomic64_read_acquire -#endif - -#ifndef arch_atomic64_set_release -static __always_inline void -arch_atomic64_set_release(atomic64_t *v, s64 i) -{ - smp_store_release(&(v)->counter, i); -} -#define arch_atomic64_set_release arch_atomic64_set_release -#endif - -#ifndef arch_atomic64_add_return_relaxed -#define arch_atomic64_add_return_acquire arch_atomic64_add_return -#define arch_atomic64_add_return_release arch_atomic64_add_return -#define arch_atomic64_add_return_relaxed arch_atomic64_add_return -#else /* arch_atomic64_add_return_relaxed */ - -#ifndef arch_atomic64_add_return_acquire -static __always_inline s64 -arch_atomic64_add_return_acquire(s64 i, atomic64_t *v) -{ - s64 ret = arch_atomic64_add_return_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic64_add_return_acquire arch_atomic64_add_return_acquire -#endif - -#ifndef arch_atomic64_add_return_release -static __always_inline s64 -arch_atomic64_add_return_release(s64 i, atomic64_t *v) -{ - __atomic_release_fence(); - return arch_atomic64_add_return_relaxed(i, v); -} -#define arch_atomic64_add_return_release arch_atomic64_add_return_release -#endif - -#ifndef arch_atomic64_add_return -static __always_inline s64 -arch_atomic64_add_return(s64 i, atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = arch_atomic64_add_return_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic64_add_return arch_atomic64_add_return -#endif - -#endif /* arch_atomic64_add_return_relaxed */ - -#ifndef arch_atomic64_fetch_add_relaxed -#define arch_atomic64_fetch_add_acquire arch_atomic64_fetch_add -#define arch_atomic64_fetch_add_release arch_atomic64_fetch_add -#define arch_atomic64_fetch_add_relaxed arch_atomic64_fetch_add -#else /* arch_atomic64_fetch_add_relaxed */ - -#ifndef arch_atomic64_fetch_add_acquire -static __always_inline s64 -arch_atomic64_fetch_add_acquire(s64 i, atomic64_t *v) -{ - s64 ret = arch_atomic64_fetch_add_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic64_fetch_add_acquire arch_atomic64_fetch_add_acquire -#endif - -#ifndef arch_atomic64_fetch_add_release -static __always_inline s64 -arch_atomic64_fetch_add_release(s64 i, atomic64_t *v) -{ - __atomic_release_fence(); - return arch_atomic64_fetch_add_relaxed(i, v); -} -#define arch_atomic64_fetch_add_release arch_atomic64_fetch_add_release -#endif - -#ifndef arch_atomic64_fetch_add -static __always_inline s64 -arch_atomic64_fetch_add(s64 i, atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = arch_atomic64_fetch_add_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic64_fetch_add arch_atomic64_fetch_add -#endif - -#endif /* arch_atomic64_fetch_add_relaxed */ - -#ifndef arch_atomic64_sub_return_relaxed -#define arch_atomic64_sub_return_acquire arch_atomic64_sub_return -#define arch_atomic64_sub_return_release arch_atomic64_sub_return -#define arch_atomic64_sub_return_relaxed arch_atomic64_sub_return -#else /* arch_atomic64_sub_return_relaxed */ - -#ifndef arch_atomic64_sub_return_acquire -static __always_inline s64 -arch_atomic64_sub_return_acquire(s64 i, atomic64_t *v) -{ - s64 ret = arch_atomic64_sub_return_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic64_sub_return_acquire arch_atomic64_sub_return_acquire -#endif - -#ifndef arch_atomic64_sub_return_release -static __always_inline s64 -arch_atomic64_sub_return_release(s64 i, atomic64_t *v) -{ - __atomic_release_fence(); - return arch_atomic64_sub_return_relaxed(i, v); -} -#define arch_atomic64_sub_return_release arch_atomic64_sub_return_release -#endif - -#ifndef arch_atomic64_sub_return -static __always_inline s64 -arch_atomic64_sub_return(s64 i, atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = arch_atomic64_sub_return_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic64_sub_return arch_atomic64_sub_return -#endif - -#endif /* arch_atomic64_sub_return_relaxed */ - -#ifndef arch_atomic64_fetch_sub_relaxed -#define arch_atomic64_fetch_sub_acquire arch_atomic64_fetch_sub -#define arch_atomic64_fetch_sub_release arch_atomic64_fetch_sub -#define arch_atomic64_fetch_sub_relaxed arch_atomic64_fetch_sub -#else /* arch_atomic64_fetch_sub_relaxed */ - -#ifndef arch_atomic64_fetch_sub_acquire -static __always_inline s64 -arch_atomic64_fetch_sub_acquire(s64 i, atomic64_t *v) -{ - s64 ret = arch_atomic64_fetch_sub_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic64_fetch_sub_acquire arch_atomic64_fetch_sub_acquire -#endif - -#ifndef arch_atomic64_fetch_sub_release -static __always_inline s64 -arch_atomic64_fetch_sub_release(s64 i, atomic64_t *v) -{ - __atomic_release_fence(); - return arch_atomic64_fetch_sub_relaxed(i, v); -} -#define arch_atomic64_fetch_sub_release arch_atomic64_fetch_sub_release -#endif - -#ifndef arch_atomic64_fetch_sub -static __always_inline s64 -arch_atomic64_fetch_sub(s64 i, atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = arch_atomic64_fetch_sub_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic64_fetch_sub arch_atomic64_fetch_sub -#endif - -#endif /* arch_atomic64_fetch_sub_relaxed */ - -#ifndef arch_atomic64_inc -static __always_inline void -arch_atomic64_inc(atomic64_t *v) -{ - arch_atomic64_add(1, v); -} -#define arch_atomic64_inc arch_atomic64_inc -#endif - -#ifndef arch_atomic64_inc_return_relaxed -#ifdef arch_atomic64_inc_return -#define arch_atomic64_inc_return_acquire arch_atomic64_inc_return -#define arch_atomic64_inc_return_release arch_atomic64_inc_return -#define arch_atomic64_inc_return_relaxed arch_atomic64_inc_return -#endif /* arch_atomic64_inc_return */ - -#ifndef arch_atomic64_inc_return -static __always_inline s64 -arch_atomic64_inc_return(atomic64_t *v) -{ - return arch_atomic64_add_return(1, v); -} -#define arch_atomic64_inc_return arch_atomic64_inc_return -#endif - -#ifndef arch_atomic64_inc_return_acquire -static __always_inline s64 -arch_atomic64_inc_return_acquire(atomic64_t *v) -{ - return arch_atomic64_add_return_acquire(1, v); -} -#define arch_atomic64_inc_return_acquire arch_atomic64_inc_return_acquire -#endif - -#ifndef arch_atomic64_inc_return_release -static __always_inline s64 -arch_atomic64_inc_return_release(atomic64_t *v) -{ - return arch_atomic64_add_return_release(1, v); -} -#define arch_atomic64_inc_return_release arch_atomic64_inc_return_release -#endif - -#ifndef arch_atomic64_inc_return_relaxed -static __always_inline s64 -arch_atomic64_inc_return_relaxed(atomic64_t *v) -{ - return arch_atomic64_add_return_relaxed(1, v); -} -#define arch_atomic64_inc_return_relaxed arch_atomic64_inc_return_relaxed -#endif - -#else /* arch_atomic64_inc_return_relaxed */ - -#ifndef arch_atomic64_inc_return_acquire -static __always_inline s64 -arch_atomic64_inc_return_acquire(atomic64_t *v) -{ - s64 ret = arch_atomic64_inc_return_relaxed(v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic64_inc_return_acquire arch_atomic64_inc_return_acquire -#endif - -#ifndef arch_atomic64_inc_return_release -static __always_inline s64 -arch_atomic64_inc_return_release(atomic64_t *v) -{ - __atomic_release_fence(); - return arch_atomic64_inc_return_relaxed(v); -} -#define arch_atomic64_inc_return_release arch_atomic64_inc_return_release -#endif - -#ifndef arch_atomic64_inc_return -static __always_inline s64 -arch_atomic64_inc_return(atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = arch_atomic64_inc_return_relaxed(v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic64_inc_return arch_atomic64_inc_return -#endif - -#endif /* arch_atomic64_inc_return_relaxed */ - -#ifndef arch_atomic64_fetch_inc_relaxed -#ifdef arch_atomic64_fetch_inc -#define arch_atomic64_fetch_inc_acquire arch_atomic64_fetch_inc -#define arch_atomic64_fetch_inc_release arch_atomic64_fetch_inc -#define arch_atomic64_fetch_inc_relaxed arch_atomic64_fetch_inc -#endif /* arch_atomic64_fetch_inc */ - -#ifndef arch_atomic64_fetch_inc -static __always_inline s64 -arch_atomic64_fetch_inc(atomic64_t *v) -{ - return arch_atomic64_fetch_add(1, v); -} -#define arch_atomic64_fetch_inc arch_atomic64_fetch_inc -#endif - -#ifndef arch_atomic64_fetch_inc_acquire -static __always_inline s64 -arch_atomic64_fetch_inc_acquire(atomic64_t *v) -{ - return arch_atomic64_fetch_add_acquire(1, v); -} -#define arch_atomic64_fetch_inc_acquire arch_atomic64_fetch_inc_acquire -#endif - -#ifndef arch_atomic64_fetch_inc_release -static __always_inline s64 -arch_atomic64_fetch_inc_release(atomic64_t *v) -{ - return arch_atomic64_fetch_add_release(1, v); -} -#define arch_atomic64_fetch_inc_release arch_atomic64_fetch_inc_release -#endif - -#ifndef arch_atomic64_fetch_inc_relaxed -static __always_inline s64 -arch_atomic64_fetch_inc_relaxed(atomic64_t *v) -{ - return arch_atomic64_fetch_add_relaxed(1, v); -} -#define arch_atomic64_fetch_inc_relaxed arch_atomic64_fetch_inc_relaxed -#endif - -#else /* arch_atomic64_fetch_inc_relaxed */ - -#ifndef arch_atomic64_fetch_inc_acquire -static __always_inline s64 -arch_atomic64_fetch_inc_acquire(atomic64_t *v) -{ - s64 ret = arch_atomic64_fetch_inc_relaxed(v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic64_fetch_inc_acquire arch_atomic64_fetch_inc_acquire -#endif - -#ifndef arch_atomic64_fetch_inc_release -static __always_inline s64 -arch_atomic64_fetch_inc_release(atomic64_t *v) -{ - __atomic_release_fence(); - return arch_atomic64_fetch_inc_relaxed(v); -} -#define arch_atomic64_fetch_inc_release arch_atomic64_fetch_inc_release -#endif - -#ifndef arch_atomic64_fetch_inc -static __always_inline s64 -arch_atomic64_fetch_inc(atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = arch_atomic64_fetch_inc_relaxed(v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic64_fetch_inc arch_atomic64_fetch_inc -#endif - -#endif /* arch_atomic64_fetch_inc_relaxed */ - -#ifndef arch_atomic64_dec -static __always_inline void -arch_atomic64_dec(atomic64_t *v) -{ - arch_atomic64_sub(1, v); -} -#define arch_atomic64_dec arch_atomic64_dec -#endif - -#ifndef arch_atomic64_dec_return_relaxed -#ifdef arch_atomic64_dec_return -#define arch_atomic64_dec_return_acquire arch_atomic64_dec_return -#define arch_atomic64_dec_return_release arch_atomic64_dec_return -#define arch_atomic64_dec_return_relaxed arch_atomic64_dec_return -#endif /* arch_atomic64_dec_return */ - -#ifndef arch_atomic64_dec_return -static __always_inline s64 -arch_atomic64_dec_return(atomic64_t *v) -{ - return arch_atomic64_sub_return(1, v); -} -#define arch_atomic64_dec_return arch_atomic64_dec_return -#endif - -#ifndef arch_atomic64_dec_return_acquire -static __always_inline s64 -arch_atomic64_dec_return_acquire(atomic64_t *v) -{ - return arch_atomic64_sub_return_acquire(1, v); -} -#define arch_atomic64_dec_return_acquire arch_atomic64_dec_return_acquire -#endif - -#ifndef arch_atomic64_dec_return_release -static __always_inline s64 -arch_atomic64_dec_return_release(atomic64_t *v) -{ - return arch_atomic64_sub_return_release(1, v); -} -#define arch_atomic64_dec_return_release arch_atomic64_dec_return_release -#endif - -#ifndef arch_atomic64_dec_return_relaxed -static __always_inline s64 -arch_atomic64_dec_return_relaxed(atomic64_t *v) -{ - return arch_atomic64_sub_return_relaxed(1, v); -} -#define arch_atomic64_dec_return_relaxed arch_atomic64_dec_return_relaxed -#endif - -#else /* arch_atomic64_dec_return_relaxed */ - -#ifndef arch_atomic64_dec_return_acquire -static __always_inline s64 -arch_atomic64_dec_return_acquire(atomic64_t *v) -{ - s64 ret = arch_atomic64_dec_return_relaxed(v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic64_dec_return_acquire arch_atomic64_dec_return_acquire -#endif - -#ifndef arch_atomic64_dec_return_release -static __always_inline s64 -arch_atomic64_dec_return_release(atomic64_t *v) -{ - __atomic_release_fence(); - return arch_atomic64_dec_return_relaxed(v); -} -#define arch_atomic64_dec_return_release arch_atomic64_dec_return_release -#endif - -#ifndef arch_atomic64_dec_return -static __always_inline s64 -arch_atomic64_dec_return(atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = arch_atomic64_dec_return_relaxed(v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic64_dec_return arch_atomic64_dec_return -#endif - -#endif /* arch_atomic64_dec_return_relaxed */ - -#ifndef arch_atomic64_fetch_dec_relaxed -#ifdef arch_atomic64_fetch_dec -#define arch_atomic64_fetch_dec_acquire arch_atomic64_fetch_dec -#define arch_atomic64_fetch_dec_release arch_atomic64_fetch_dec -#define arch_atomic64_fetch_dec_relaxed arch_atomic64_fetch_dec -#endif /* arch_atomic64_fetch_dec */ - -#ifndef arch_atomic64_fetch_dec -static __always_inline s64 -arch_atomic64_fetch_dec(atomic64_t *v) -{ - return arch_atomic64_fetch_sub(1, v); -} -#define arch_atomic64_fetch_dec arch_atomic64_fetch_dec -#endif - -#ifndef arch_atomic64_fetch_dec_acquire -static __always_inline s64 -arch_atomic64_fetch_dec_acquire(atomic64_t *v) -{ - return arch_atomic64_fetch_sub_acquire(1, v); -} -#define arch_atomic64_fetch_dec_acquire arch_atomic64_fetch_dec_acquire -#endif - -#ifndef arch_atomic64_fetch_dec_release -static __always_inline s64 -arch_atomic64_fetch_dec_release(atomic64_t *v) -{ - return arch_atomic64_fetch_sub_release(1, v); -} -#define arch_atomic64_fetch_dec_release arch_atomic64_fetch_dec_release -#endif - -#ifndef arch_atomic64_fetch_dec_relaxed -static __always_inline s64 -arch_atomic64_fetch_dec_relaxed(atomic64_t *v) -{ - return arch_atomic64_fetch_sub_relaxed(1, v); -} -#define arch_atomic64_fetch_dec_relaxed arch_atomic64_fetch_dec_relaxed -#endif - -#else /* arch_atomic64_fetch_dec_relaxed */ - -#ifndef arch_atomic64_fetch_dec_acquire -static __always_inline s64 -arch_atomic64_fetch_dec_acquire(atomic64_t *v) -{ - s64 ret = arch_atomic64_fetch_dec_relaxed(v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic64_fetch_dec_acquire arch_atomic64_fetch_dec_acquire -#endif - -#ifndef arch_atomic64_fetch_dec_release -static __always_inline s64 -arch_atomic64_fetch_dec_release(atomic64_t *v) -{ - __atomic_release_fence(); - return arch_atomic64_fetch_dec_relaxed(v); -} -#define arch_atomic64_fetch_dec_release arch_atomic64_fetch_dec_release -#endif - -#ifndef arch_atomic64_fetch_dec -static __always_inline s64 -arch_atomic64_fetch_dec(atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = arch_atomic64_fetch_dec_relaxed(v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic64_fetch_dec arch_atomic64_fetch_dec -#endif - -#endif /* arch_atomic64_fetch_dec_relaxed */ - -#ifndef arch_atomic64_fetch_and_relaxed -#define arch_atomic64_fetch_and_acquire arch_atomic64_fetch_and -#define arch_atomic64_fetch_and_release arch_atomic64_fetch_and -#define arch_atomic64_fetch_and_relaxed arch_atomic64_fetch_and -#else /* arch_atomic64_fetch_and_relaxed */ - -#ifndef arch_atomic64_fetch_and_acquire -static __always_inline s64 -arch_atomic64_fetch_and_acquire(s64 i, atomic64_t *v) -{ - s64 ret = arch_atomic64_fetch_and_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic64_fetch_and_acquire arch_atomic64_fetch_and_acquire -#endif - -#ifndef arch_atomic64_fetch_and_release -static __always_inline s64 -arch_atomic64_fetch_and_release(s64 i, atomic64_t *v) -{ - __atomic_release_fence(); - return arch_atomic64_fetch_and_relaxed(i, v); -} -#define arch_atomic64_fetch_and_release arch_atomic64_fetch_and_release -#endif - -#ifndef arch_atomic64_fetch_and -static __always_inline s64 -arch_atomic64_fetch_and(s64 i, atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = arch_atomic64_fetch_and_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic64_fetch_and arch_atomic64_fetch_and -#endif - -#endif /* arch_atomic64_fetch_and_relaxed */ - -#ifndef arch_atomic64_andnot -static __always_inline void -arch_atomic64_andnot(s64 i, atomic64_t *v) -{ - arch_atomic64_and(~i, v); -} -#define arch_atomic64_andnot arch_atomic64_andnot -#endif - -#ifndef arch_atomic64_fetch_andnot_relaxed -#ifdef arch_atomic64_fetch_andnot -#define arch_atomic64_fetch_andnot_acquire arch_atomic64_fetch_andnot -#define arch_atomic64_fetch_andnot_release arch_atomic64_fetch_andnot -#define arch_atomic64_fetch_andnot_relaxed arch_atomic64_fetch_andnot -#endif /* arch_atomic64_fetch_andnot */ - -#ifndef arch_atomic64_fetch_andnot -static __always_inline s64 -arch_atomic64_fetch_andnot(s64 i, atomic64_t *v) -{ - return arch_atomic64_fetch_and(~i, v); -} -#define arch_atomic64_fetch_andnot arch_atomic64_fetch_andnot -#endif - -#ifndef arch_atomic64_fetch_andnot_acquire -static __always_inline s64 -arch_atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) -{ - return arch_atomic64_fetch_and_acquire(~i, v); -} -#define arch_atomic64_fetch_andnot_acquire arch_atomic64_fetch_andnot_acquire -#endif - -#ifndef arch_atomic64_fetch_andnot_release -static __always_inline s64 -arch_atomic64_fetch_andnot_release(s64 i, atomic64_t *v) -{ - return arch_atomic64_fetch_and_release(~i, v); -} -#define arch_atomic64_fetch_andnot_release arch_atomic64_fetch_andnot_release -#endif - -#ifndef arch_atomic64_fetch_andnot_relaxed -static __always_inline s64 -arch_atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v) -{ - return arch_atomic64_fetch_and_relaxed(~i, v); -} -#define arch_atomic64_fetch_andnot_relaxed arch_atomic64_fetch_andnot_relaxed -#endif - -#else /* arch_atomic64_fetch_andnot_relaxed */ - -#ifndef arch_atomic64_fetch_andnot_acquire -static __always_inline s64 -arch_atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) -{ - s64 ret = arch_atomic64_fetch_andnot_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic64_fetch_andnot_acquire arch_atomic64_fetch_andnot_acquire -#endif - -#ifndef arch_atomic64_fetch_andnot_release -static __always_inline s64 -arch_atomic64_fetch_andnot_release(s64 i, atomic64_t *v) -{ - __atomic_release_fence(); - return arch_atomic64_fetch_andnot_relaxed(i, v); -} -#define arch_atomic64_fetch_andnot_release arch_atomic64_fetch_andnot_release -#endif - -#ifndef arch_atomic64_fetch_andnot -static __always_inline s64 -arch_atomic64_fetch_andnot(s64 i, atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = arch_atomic64_fetch_andnot_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic64_fetch_andnot arch_atomic64_fetch_andnot -#endif - -#endif /* arch_atomic64_fetch_andnot_relaxed */ - -#ifndef arch_atomic64_fetch_or_relaxed -#define arch_atomic64_fetch_or_acquire arch_atomic64_fetch_or -#define arch_atomic64_fetch_or_release arch_atomic64_fetch_or -#define arch_atomic64_fetch_or_relaxed arch_atomic64_fetch_or -#else /* arch_atomic64_fetch_or_relaxed */ - -#ifndef arch_atomic64_fetch_or_acquire -static __always_inline s64 -arch_atomic64_fetch_or_acquire(s64 i, atomic64_t *v) -{ - s64 ret = arch_atomic64_fetch_or_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic64_fetch_or_acquire arch_atomic64_fetch_or_acquire -#endif - -#ifndef arch_atomic64_fetch_or_release -static __always_inline s64 -arch_atomic64_fetch_or_release(s64 i, atomic64_t *v) -{ - __atomic_release_fence(); - return arch_atomic64_fetch_or_relaxed(i, v); -} -#define arch_atomic64_fetch_or_release arch_atomic64_fetch_or_release -#endif - -#ifndef arch_atomic64_fetch_or -static __always_inline s64 -arch_atomic64_fetch_or(s64 i, atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = arch_atomic64_fetch_or_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic64_fetch_or arch_atomic64_fetch_or -#endif - -#endif /* arch_atomic64_fetch_or_relaxed */ - -#ifndef arch_atomic64_fetch_xor_relaxed -#define arch_atomic64_fetch_xor_acquire arch_atomic64_fetch_xor -#define arch_atomic64_fetch_xor_release arch_atomic64_fetch_xor -#define arch_atomic64_fetch_xor_relaxed arch_atomic64_fetch_xor -#else /* arch_atomic64_fetch_xor_relaxed */ - -#ifndef arch_atomic64_fetch_xor_acquire -static __always_inline s64 -arch_atomic64_fetch_xor_acquire(s64 i, atomic64_t *v) -{ - s64 ret = arch_atomic64_fetch_xor_relaxed(i, v); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic64_fetch_xor_acquire arch_atomic64_fetch_xor_acquire -#endif - -#ifndef arch_atomic64_fetch_xor_release -static __always_inline s64 -arch_atomic64_fetch_xor_release(s64 i, atomic64_t *v) -{ - __atomic_release_fence(); - return arch_atomic64_fetch_xor_relaxed(i, v); -} -#define arch_atomic64_fetch_xor_release arch_atomic64_fetch_xor_release -#endif - -#ifndef arch_atomic64_fetch_xor -static __always_inline s64 -arch_atomic64_fetch_xor(s64 i, atomic64_t *v) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = arch_atomic64_fetch_xor_relaxed(i, v); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic64_fetch_xor arch_atomic64_fetch_xor -#endif - -#endif /* arch_atomic64_fetch_xor_relaxed */ - -#ifndef arch_atomic64_xchg_relaxed -#define arch_atomic64_xchg_acquire arch_atomic64_xchg -#define arch_atomic64_xchg_release arch_atomic64_xchg -#define arch_atomic64_xchg_relaxed arch_atomic64_xchg -#else /* arch_atomic64_xchg_relaxed */ - -#ifndef arch_atomic64_xchg_acquire -static __always_inline s64 -arch_atomic64_xchg_acquire(atomic64_t *v, s64 i) -{ - s64 ret = arch_atomic64_xchg_relaxed(v, i); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic64_xchg_acquire arch_atomic64_xchg_acquire -#endif - -#ifndef arch_atomic64_xchg_release -static __always_inline s64 -arch_atomic64_xchg_release(atomic64_t *v, s64 i) -{ - __atomic_release_fence(); - return arch_atomic64_xchg_relaxed(v, i); -} -#define arch_atomic64_xchg_release arch_atomic64_xchg_release -#endif - -#ifndef arch_atomic64_xchg -static __always_inline s64 -arch_atomic64_xchg(atomic64_t *v, s64 i) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = arch_atomic64_xchg_relaxed(v, i); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic64_xchg arch_atomic64_xchg -#endif - -#endif /* arch_atomic64_xchg_relaxed */ - -#ifndef arch_atomic64_cmpxchg_relaxed -#define arch_atomic64_cmpxchg_acquire arch_atomic64_cmpxchg -#define arch_atomic64_cmpxchg_release arch_atomic64_cmpxchg -#define arch_atomic64_cmpxchg_relaxed arch_atomic64_cmpxchg -#else /* arch_atomic64_cmpxchg_relaxed */ - -#ifndef arch_atomic64_cmpxchg_acquire -static __always_inline s64 -arch_atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) -{ - s64 ret = arch_atomic64_cmpxchg_relaxed(v, old, new); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic64_cmpxchg_acquire arch_atomic64_cmpxchg_acquire -#endif - -#ifndef arch_atomic64_cmpxchg_release -static __always_inline s64 -arch_atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) -{ - __atomic_release_fence(); - return arch_atomic64_cmpxchg_relaxed(v, old, new); -} -#define arch_atomic64_cmpxchg_release arch_atomic64_cmpxchg_release -#endif - -#ifndef arch_atomic64_cmpxchg -static __always_inline s64 -arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) -{ - s64 ret; - __atomic_pre_full_fence(); - ret = arch_atomic64_cmpxchg_relaxed(v, old, new); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic64_cmpxchg arch_atomic64_cmpxchg -#endif - -#endif /* arch_atomic64_cmpxchg_relaxed */ - -#ifndef arch_atomic64_try_cmpxchg_relaxed -#ifdef arch_atomic64_try_cmpxchg -#define arch_atomic64_try_cmpxchg_acquire arch_atomic64_try_cmpxchg -#define arch_atomic64_try_cmpxchg_release arch_atomic64_try_cmpxchg -#define arch_atomic64_try_cmpxchg_relaxed arch_atomic64_try_cmpxchg -#endif /* arch_atomic64_try_cmpxchg */ - -#ifndef arch_atomic64_try_cmpxchg -static __always_inline bool -arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) -{ - s64 r, o = *old; - r = arch_atomic64_cmpxchg(v, o, new); - if (unlikely(r != o)) - *old = r; - return likely(r == o); -} -#define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg -#endif - -#ifndef arch_atomic64_try_cmpxchg_acquire -static __always_inline bool -arch_atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) -{ - s64 r, o = *old; - r = arch_atomic64_cmpxchg_acquire(v, o, new); - if (unlikely(r != o)) - *old = r; - return likely(r == o); -} -#define arch_atomic64_try_cmpxchg_acquire arch_atomic64_try_cmpxchg_acquire -#endif - -#ifndef arch_atomic64_try_cmpxchg_release -static __always_inline bool -arch_atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) -{ - s64 r, o = *old; - r = arch_atomic64_cmpxchg_release(v, o, new); - if (unlikely(r != o)) - *old = r; - return likely(r == o); -} -#define arch_atomic64_try_cmpxchg_release arch_atomic64_try_cmpxchg_release -#endif - -#ifndef arch_atomic64_try_cmpxchg_relaxed -static __always_inline bool -arch_atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) -{ - s64 r, o = *old; - r = arch_atomic64_cmpxchg_relaxed(v, o, new); - if (unlikely(r != o)) - *old = r; - return likely(r == o); -} -#define arch_atomic64_try_cmpxchg_relaxed arch_atomic64_try_cmpxchg_relaxed -#endif - -#else /* arch_atomic64_try_cmpxchg_relaxed */ - -#ifndef arch_atomic64_try_cmpxchg_acquire -static __always_inline bool -arch_atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) -{ - bool ret = arch_atomic64_try_cmpxchg_relaxed(v, old, new); - __atomic_acquire_fence(); - return ret; -} -#define arch_atomic64_try_cmpxchg_acquire arch_atomic64_try_cmpxchg_acquire -#endif - -#ifndef arch_atomic64_try_cmpxchg_release -static __always_inline bool -arch_atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) -{ - __atomic_release_fence(); - return arch_atomic64_try_cmpxchg_relaxed(v, old, new); -} -#define arch_atomic64_try_cmpxchg_release arch_atomic64_try_cmpxchg_release -#endif - -#ifndef arch_atomic64_try_cmpxchg -static __always_inline bool -arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) -{ - bool ret; - __atomic_pre_full_fence(); - ret = arch_atomic64_try_cmpxchg_relaxed(v, old, new); - __atomic_post_full_fence(); - return ret; -} -#define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg -#endif - -#endif /* arch_atomic64_try_cmpxchg_relaxed */ - -#ifndef arch_atomic64_sub_and_test -/** - * arch_atomic64_sub_and_test - subtract value from variable and test result - * @i: integer value to subtract - * @v: pointer of type atomic64_t - * - * Atomically subtracts @i from @v and returns - * true if the result is zero, or false for all - * other cases. - */ -static __always_inline bool -arch_atomic64_sub_and_test(s64 i, atomic64_t *v) -{ - return arch_atomic64_sub_return(i, v) == 0; -} -#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test -#endif - -#ifndef arch_atomic64_dec_and_test -/** - * arch_atomic64_dec_and_test - decrement and test - * @v: pointer of type atomic64_t - * - * Atomically decrements @v by 1 and - * returns true if the result is 0, or false for all other - * cases. - */ -static __always_inline bool -arch_atomic64_dec_and_test(atomic64_t *v) -{ - return arch_atomic64_dec_return(v) == 0; -} -#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test -#endif - -#ifndef arch_atomic64_inc_and_test -/** - * arch_atomic64_inc_and_test - increment and test - * @v: pointer of type atomic64_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -static __always_inline bool -arch_atomic64_inc_and_test(atomic64_t *v) -{ - return arch_atomic64_inc_return(v) == 0; -} -#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test -#endif - -#ifndef arch_atomic64_add_negative -/** - * arch_atomic64_add_negative - add and test if negative - * @i: integer value to add - * @v: pointer of type atomic64_t - * - * Atomically adds @i to @v and returns true - * if the result is negative, or false when - * result is greater than or equal to zero. - */ -static __always_inline bool -arch_atomic64_add_negative(s64 i, atomic64_t *v) -{ - return arch_atomic64_add_return(i, v) < 0; -} -#define arch_atomic64_add_negative arch_atomic64_add_negative -#endif - -#ifndef arch_atomic64_fetch_add_unless -/** - * arch_atomic64_fetch_add_unless - add unless the number is already a given value - * @v: pointer of type atomic64_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, so long as @v was not already @u. - * Returns original value of @v - */ -static __always_inline s64 -arch_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) -{ - s64 c = arch_atomic64_read(v); - - do { - if (unlikely(c == u)) - break; - } while (!arch_atomic64_try_cmpxchg(v, &c, c + a)); - - return c; -} -#define arch_atomic64_fetch_add_unless arch_atomic64_fetch_add_unless -#endif - -#ifndef arch_atomic64_add_unless -/** - * arch_atomic64_add_unless - add unless the number is already a given value - * @v: pointer of type atomic64_t - * @a: the amount to add to v... - * @u: ...unless v is equal to u. - * - * Atomically adds @a to @v, if @v was not already @u. - * Returns true if the addition was done. - */ -static __always_inline bool -arch_atomic64_add_unless(atomic64_t *v, s64 a, s64 u) -{ - return arch_atomic64_fetch_add_unless(v, a, u) != u; -} -#define arch_atomic64_add_unless arch_atomic64_add_unless -#endif - -#ifndef arch_atomic64_inc_not_zero -/** - * arch_atomic64_inc_not_zero - increment unless the number is zero - * @v: pointer of type atomic64_t - * - * Atomically increments @v by 1, if @v is non-zero. - * Returns true if the increment was done. - */ -static __always_inline bool -arch_atomic64_inc_not_zero(atomic64_t *v) -{ - return arch_atomic64_add_unless(v, 1, 0); -} -#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero -#endif - -#ifndef arch_atomic64_inc_unless_negative -static __always_inline bool -arch_atomic64_inc_unless_negative(atomic64_t *v) -{ - s64 c = arch_atomic64_read(v); - - do { - if (unlikely(c < 0)) - return false; - } while (!arch_atomic64_try_cmpxchg(v, &c, c + 1)); - - return true; -} -#define arch_atomic64_inc_unless_negative arch_atomic64_inc_unless_negative -#endif - -#ifndef arch_atomic64_dec_unless_positive -static __always_inline bool -arch_atomic64_dec_unless_positive(atomic64_t *v) -{ - s64 c = arch_atomic64_read(v); - - do { - if (unlikely(c > 0)) - return false; - } while (!arch_atomic64_try_cmpxchg(v, &c, c - 1)); - - return true; -} -#define arch_atomic64_dec_unless_positive arch_atomic64_dec_unless_positive -#endif - -#ifndef arch_atomic64_dec_if_positive -static __always_inline s64 -arch_atomic64_dec_if_positive(atomic64_t *v) -{ - s64 dec, c = arch_atomic64_read(v); - - do { - dec = c - 1; - if (unlikely(dec < 0)) - break; - } while (!arch_atomic64_try_cmpxchg(v, &c, dec)); - - return dec; -} -#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive -#endif - -#endif /* _LINUX_ATOMIC_FALLBACK_H */ -// cca554917d7ea73d5e3e7397dd70c484cad9b2c4 diff --git a/include/linux/atomic.h b/include/linux/atomic.h index ed1d3ffd5b9d..1896a58b5aba 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -77,9 +77,8 @@ __ret; \ }) -#include -#include - -#include +#include +#include +#include #endif /* _LINUX_ATOMIC_H */ diff --git a/include/linux/atomic/atomic-arch-fallback.h b/include/linux/atomic/atomic-arch-fallback.h new file mode 100644 index 000000000000..a3dba31df01e --- /dev/null +++ b/include/linux/atomic/atomic-arch-fallback.h @@ -0,0 +1,2361 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Generated by scripts/atomic/gen-atomic-fallback.sh +// DO NOT MODIFY THIS FILE DIRECTLY + +#ifndef _LINUX_ATOMIC_FALLBACK_H +#define _LINUX_ATOMIC_FALLBACK_H + +#include + +#ifndef arch_xchg_relaxed +#define arch_xchg_acquire arch_xchg +#define arch_xchg_release arch_xchg +#define arch_xchg_relaxed arch_xchg +#else /* arch_xchg_relaxed */ + +#ifndef arch_xchg_acquire +#define arch_xchg_acquire(...) \ + __atomic_op_acquire(arch_xchg, __VA_ARGS__) +#endif + +#ifndef arch_xchg_release +#define arch_xchg_release(...) \ + __atomic_op_release(arch_xchg, __VA_ARGS__) +#endif + +#ifndef arch_xchg +#define arch_xchg(...) \ + __atomic_op_fence(arch_xchg, __VA_ARGS__) +#endif + +#endif /* arch_xchg_relaxed */ + +#ifndef arch_cmpxchg_relaxed +#define arch_cmpxchg_acquire arch_cmpxchg +#define arch_cmpxchg_release arch_cmpxchg +#define arch_cmpxchg_relaxed arch_cmpxchg +#else /* arch_cmpxchg_relaxed */ + +#ifndef arch_cmpxchg_acquire +#define arch_cmpxchg_acquire(...) \ + __atomic_op_acquire(arch_cmpxchg, __VA_ARGS__) +#endif + +#ifndef arch_cmpxchg_release +#define arch_cmpxchg_release(...) \ + __atomic_op_release(arch_cmpxchg, __VA_ARGS__) +#endif + +#ifndef arch_cmpxchg +#define arch_cmpxchg(...) \ + __atomic_op_fence(arch_cmpxchg, __VA_ARGS__) +#endif + +#endif /* arch_cmpxchg_relaxed */ + +#ifndef arch_cmpxchg64_relaxed +#define arch_cmpxchg64_acquire arch_cmpxchg64 +#define arch_cmpxchg64_release arch_cmpxchg64 +#define arch_cmpxchg64_relaxed arch_cmpxchg64 +#else /* arch_cmpxchg64_relaxed */ + +#ifndef arch_cmpxchg64_acquire +#define arch_cmpxchg64_acquire(...) \ + __atomic_op_acquire(arch_cmpxchg64, __VA_ARGS__) +#endif + +#ifndef arch_cmpxchg64_release +#define arch_cmpxchg64_release(...) \ + __atomic_op_release(arch_cmpxchg64, __VA_ARGS__) +#endif + +#ifndef arch_cmpxchg64 +#define arch_cmpxchg64(...) \ + __atomic_op_fence(arch_cmpxchg64, __VA_ARGS__) +#endif + +#endif /* arch_cmpxchg64_relaxed */ + +#ifndef arch_try_cmpxchg_relaxed +#ifdef arch_try_cmpxchg +#define arch_try_cmpxchg_acquire arch_try_cmpxchg +#define arch_try_cmpxchg_release arch_try_cmpxchg +#define arch_try_cmpxchg_relaxed arch_try_cmpxchg +#endif /* arch_try_cmpxchg */ + +#ifndef arch_try_cmpxchg +#define arch_try_cmpxchg(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg */ + +#ifndef arch_try_cmpxchg_acquire +#define arch_try_cmpxchg_acquire(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg_acquire((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg_acquire */ + +#ifndef arch_try_cmpxchg_release +#define arch_try_cmpxchg_release(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg_release((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg_release */ + +#ifndef arch_try_cmpxchg_relaxed +#define arch_try_cmpxchg_relaxed(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg_relaxed((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg_relaxed */ + +#else /* arch_try_cmpxchg_relaxed */ + +#ifndef arch_try_cmpxchg_acquire +#define arch_try_cmpxchg_acquire(...) \ + __atomic_op_acquire(arch_try_cmpxchg, __VA_ARGS__) +#endif + +#ifndef arch_try_cmpxchg_release +#define arch_try_cmpxchg_release(...) \ + __atomic_op_release(arch_try_cmpxchg, __VA_ARGS__) +#endif + +#ifndef arch_try_cmpxchg +#define arch_try_cmpxchg(...) \ + __atomic_op_fence(arch_try_cmpxchg, __VA_ARGS__) +#endif + +#endif /* arch_try_cmpxchg_relaxed */ + +#ifndef arch_atomic_read_acquire +static __always_inline int +arch_atomic_read_acquire(const atomic_t *v) +{ + return smp_load_acquire(&(v)->counter); +} +#define arch_atomic_read_acquire arch_atomic_read_acquire +#endif + +#ifndef arch_atomic_set_release +static __always_inline void +arch_atomic_set_release(atomic_t *v, int i) +{ + smp_store_release(&(v)->counter, i); +} +#define arch_atomic_set_release arch_atomic_set_release +#endif + +#ifndef arch_atomic_add_return_relaxed +#define arch_atomic_add_return_acquire arch_atomic_add_return +#define arch_atomic_add_return_release arch_atomic_add_return +#define arch_atomic_add_return_relaxed arch_atomic_add_return +#else /* arch_atomic_add_return_relaxed */ + +#ifndef arch_atomic_add_return_acquire +static __always_inline int +arch_atomic_add_return_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_add_return_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_add_return_acquire arch_atomic_add_return_acquire +#endif + +#ifndef arch_atomic_add_return_release +static __always_inline int +arch_atomic_add_return_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_add_return_relaxed(i, v); +} +#define arch_atomic_add_return_release arch_atomic_add_return_release +#endif + +#ifndef arch_atomic_add_return +static __always_inline int +arch_atomic_add_return(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_add_return_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_add_return arch_atomic_add_return +#endif + +#endif /* arch_atomic_add_return_relaxed */ + +#ifndef arch_atomic_fetch_add_relaxed +#define arch_atomic_fetch_add_acquire arch_atomic_fetch_add +#define arch_atomic_fetch_add_release arch_atomic_fetch_add +#define arch_atomic_fetch_add_relaxed arch_atomic_fetch_add +#else /* arch_atomic_fetch_add_relaxed */ + +#ifndef arch_atomic_fetch_add_acquire +static __always_inline int +arch_atomic_fetch_add_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_fetch_add_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_add_acquire arch_atomic_fetch_add_acquire +#endif + +#ifndef arch_atomic_fetch_add_release +static __always_inline int +arch_atomic_fetch_add_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_add_relaxed(i, v); +} +#define arch_atomic_fetch_add_release arch_atomic_fetch_add_release +#endif + +#ifndef arch_atomic_fetch_add +static __always_inline int +arch_atomic_fetch_add(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_add_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_add arch_atomic_fetch_add +#endif + +#endif /* arch_atomic_fetch_add_relaxed */ + +#ifndef arch_atomic_sub_return_relaxed +#define arch_atomic_sub_return_acquire arch_atomic_sub_return +#define arch_atomic_sub_return_release arch_atomic_sub_return +#define arch_atomic_sub_return_relaxed arch_atomic_sub_return +#else /* arch_atomic_sub_return_relaxed */ + +#ifndef arch_atomic_sub_return_acquire +static __always_inline int +arch_atomic_sub_return_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_sub_return_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_sub_return_acquire arch_atomic_sub_return_acquire +#endif + +#ifndef arch_atomic_sub_return_release +static __always_inline int +arch_atomic_sub_return_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_sub_return_relaxed(i, v); +} +#define arch_atomic_sub_return_release arch_atomic_sub_return_release +#endif + +#ifndef arch_atomic_sub_return +static __always_inline int +arch_atomic_sub_return(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_sub_return_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_sub_return arch_atomic_sub_return +#endif + +#endif /* arch_atomic_sub_return_relaxed */ + +#ifndef arch_atomic_fetch_sub_relaxed +#define arch_atomic_fetch_sub_acquire arch_atomic_fetch_sub +#define arch_atomic_fetch_sub_release arch_atomic_fetch_sub +#define arch_atomic_fetch_sub_relaxed arch_atomic_fetch_sub +#else /* arch_atomic_fetch_sub_relaxed */ + +#ifndef arch_atomic_fetch_sub_acquire +static __always_inline int +arch_atomic_fetch_sub_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_fetch_sub_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_sub_acquire arch_atomic_fetch_sub_acquire +#endif + +#ifndef arch_atomic_fetch_sub_release +static __always_inline int +arch_atomic_fetch_sub_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_sub_relaxed(i, v); +} +#define arch_atomic_fetch_sub_release arch_atomic_fetch_sub_release +#endif + +#ifndef arch_atomic_fetch_sub +static __always_inline int +arch_atomic_fetch_sub(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_sub_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_sub arch_atomic_fetch_sub +#endif + +#endif /* arch_atomic_fetch_sub_relaxed */ + +#ifndef arch_atomic_inc +static __always_inline void +arch_atomic_inc(atomic_t *v) +{ + arch_atomic_add(1, v); +} +#define arch_atomic_inc arch_atomic_inc +#endif + +#ifndef arch_atomic_inc_return_relaxed +#ifdef arch_atomic_inc_return +#define arch_atomic_inc_return_acquire arch_atomic_inc_return +#define arch_atomic_inc_return_release arch_atomic_inc_return +#define arch_atomic_inc_return_relaxed arch_atomic_inc_return +#endif /* arch_atomic_inc_return */ + +#ifndef arch_atomic_inc_return +static __always_inline int +arch_atomic_inc_return(atomic_t *v) +{ + return arch_atomic_add_return(1, v); +} +#define arch_atomic_inc_return arch_atomic_inc_return +#endif + +#ifndef arch_atomic_inc_return_acquire +static __always_inline int +arch_atomic_inc_return_acquire(atomic_t *v) +{ + return arch_atomic_add_return_acquire(1, v); +} +#define arch_atomic_inc_return_acquire arch_atomic_inc_return_acquire +#endif + +#ifndef arch_atomic_inc_return_release +static __always_inline int +arch_atomic_inc_return_release(atomic_t *v) +{ + return arch_atomic_add_return_release(1, v); +} +#define arch_atomic_inc_return_release arch_atomic_inc_return_release +#endif + +#ifndef arch_atomic_inc_return_relaxed +static __always_inline int +arch_atomic_inc_return_relaxed(atomic_t *v) +{ + return arch_atomic_add_return_relaxed(1, v); +} +#define arch_atomic_inc_return_relaxed arch_atomic_inc_return_relaxed +#endif + +#else /* arch_atomic_inc_return_relaxed */ + +#ifndef arch_atomic_inc_return_acquire +static __always_inline int +arch_atomic_inc_return_acquire(atomic_t *v) +{ + int ret = arch_atomic_inc_return_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_inc_return_acquire arch_atomic_inc_return_acquire +#endif + +#ifndef arch_atomic_inc_return_release +static __always_inline int +arch_atomic_inc_return_release(atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_inc_return_relaxed(v); +} +#define arch_atomic_inc_return_release arch_atomic_inc_return_release +#endif + +#ifndef arch_atomic_inc_return +static __always_inline int +arch_atomic_inc_return(atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_inc_return_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_inc_return arch_atomic_inc_return +#endif + +#endif /* arch_atomic_inc_return_relaxed */ + +#ifndef arch_atomic_fetch_inc_relaxed +#ifdef arch_atomic_fetch_inc +#define arch_atomic_fetch_inc_acquire arch_atomic_fetch_inc +#define arch_atomic_fetch_inc_release arch_atomic_fetch_inc +#define arch_atomic_fetch_inc_relaxed arch_atomic_fetch_inc +#endif /* arch_atomic_fetch_inc */ + +#ifndef arch_atomic_fetch_inc +static __always_inline int +arch_atomic_fetch_inc(atomic_t *v) +{ + return arch_atomic_fetch_add(1, v); +} +#define arch_atomic_fetch_inc arch_atomic_fetch_inc +#endif + +#ifndef arch_atomic_fetch_inc_acquire +static __always_inline int +arch_atomic_fetch_inc_acquire(atomic_t *v) +{ + return arch_atomic_fetch_add_acquire(1, v); +} +#define arch_atomic_fetch_inc_acquire arch_atomic_fetch_inc_acquire +#endif + +#ifndef arch_atomic_fetch_inc_release +static __always_inline int +arch_atomic_fetch_inc_release(atomic_t *v) +{ + return arch_atomic_fetch_add_release(1, v); +} +#define arch_atomic_fetch_inc_release arch_atomic_fetch_inc_release +#endif + +#ifndef arch_atomic_fetch_inc_relaxed +static __always_inline int +arch_atomic_fetch_inc_relaxed(atomic_t *v) +{ + return arch_atomic_fetch_add_relaxed(1, v); +} +#define arch_atomic_fetch_inc_relaxed arch_atomic_fetch_inc_relaxed +#endif + +#else /* arch_atomic_fetch_inc_relaxed */ + +#ifndef arch_atomic_fetch_inc_acquire +static __always_inline int +arch_atomic_fetch_inc_acquire(atomic_t *v) +{ + int ret = arch_atomic_fetch_inc_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_inc_acquire arch_atomic_fetch_inc_acquire +#endif + +#ifndef arch_atomic_fetch_inc_release +static __always_inline int +arch_atomic_fetch_inc_release(atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_inc_relaxed(v); +} +#define arch_atomic_fetch_inc_release arch_atomic_fetch_inc_release +#endif + +#ifndef arch_atomic_fetch_inc +static __always_inline int +arch_atomic_fetch_inc(atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_inc_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_inc arch_atomic_fetch_inc +#endif + +#endif /* arch_atomic_fetch_inc_relaxed */ + +#ifndef arch_atomic_dec +static __always_inline void +arch_atomic_dec(atomic_t *v) +{ + arch_atomic_sub(1, v); +} +#define arch_atomic_dec arch_atomic_dec +#endif + +#ifndef arch_atomic_dec_return_relaxed +#ifdef arch_atomic_dec_return +#define arch_atomic_dec_return_acquire arch_atomic_dec_return +#define arch_atomic_dec_return_release arch_atomic_dec_return +#define arch_atomic_dec_return_relaxed arch_atomic_dec_return +#endif /* arch_atomic_dec_return */ + +#ifndef arch_atomic_dec_return +static __always_inline int +arch_atomic_dec_return(atomic_t *v) +{ + return arch_atomic_sub_return(1, v); +} +#define arch_atomic_dec_return arch_atomic_dec_return +#endif + +#ifndef arch_atomic_dec_return_acquire +static __always_inline int +arch_atomic_dec_return_acquire(atomic_t *v) +{ + return arch_atomic_sub_return_acquire(1, v); +} +#define arch_atomic_dec_return_acquire arch_atomic_dec_return_acquire +#endif + +#ifndef arch_atomic_dec_return_release +static __always_inline int +arch_atomic_dec_return_release(atomic_t *v) +{ + return arch_atomic_sub_return_release(1, v); +} +#define arch_atomic_dec_return_release arch_atomic_dec_return_release +#endif + +#ifndef arch_atomic_dec_return_relaxed +static __always_inline int +arch_atomic_dec_return_relaxed(atomic_t *v) +{ + return arch_atomic_sub_return_relaxed(1, v); +} +#define arch_atomic_dec_return_relaxed arch_atomic_dec_return_relaxed +#endif + +#else /* arch_atomic_dec_return_relaxed */ + +#ifndef arch_atomic_dec_return_acquire +static __always_inline int +arch_atomic_dec_return_acquire(atomic_t *v) +{ + int ret = arch_atomic_dec_return_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_dec_return_acquire arch_atomic_dec_return_acquire +#endif + +#ifndef arch_atomic_dec_return_release +static __always_inline int +arch_atomic_dec_return_release(atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_dec_return_relaxed(v); +} +#define arch_atomic_dec_return_release arch_atomic_dec_return_release +#endif + +#ifndef arch_atomic_dec_return +static __always_inline int +arch_atomic_dec_return(atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_dec_return_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_dec_return arch_atomic_dec_return +#endif + +#endif /* arch_atomic_dec_return_relaxed */ + +#ifndef arch_atomic_fetch_dec_relaxed +#ifdef arch_atomic_fetch_dec +#define arch_atomic_fetch_dec_acquire arch_atomic_fetch_dec +#define arch_atomic_fetch_dec_release arch_atomic_fetch_dec +#define arch_atomic_fetch_dec_relaxed arch_atomic_fetch_dec +#endif /* arch_atomic_fetch_dec */ + +#ifndef arch_atomic_fetch_dec +static __always_inline int +arch_atomic_fetch_dec(atomic_t *v) +{ + return arch_atomic_fetch_sub(1, v); +} +#define arch_atomic_fetch_dec arch_atomic_fetch_dec +#endif + +#ifndef arch_atomic_fetch_dec_acquire +static __always_inline int +arch_atomic_fetch_dec_acquire(atomic_t *v) +{ + return arch_atomic_fetch_sub_acquire(1, v); +} +#define arch_atomic_fetch_dec_acquire arch_atomic_fetch_dec_acquire +#endif + +#ifndef arch_atomic_fetch_dec_release +static __always_inline int +arch_atomic_fetch_dec_release(atomic_t *v) +{ + return arch_atomic_fetch_sub_release(1, v); +} +#define arch_atomic_fetch_dec_release arch_atomic_fetch_dec_release +#endif + +#ifndef arch_atomic_fetch_dec_relaxed +static __always_inline int +arch_atomic_fetch_dec_relaxed(atomic_t *v) +{ + return arch_atomic_fetch_sub_relaxed(1, v); +} +#define arch_atomic_fetch_dec_relaxed arch_atomic_fetch_dec_relaxed +#endif + +#else /* arch_atomic_fetch_dec_relaxed */ + +#ifndef arch_atomic_fetch_dec_acquire +static __always_inline int +arch_atomic_fetch_dec_acquire(atomic_t *v) +{ + int ret = arch_atomic_fetch_dec_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_dec_acquire arch_atomic_fetch_dec_acquire +#endif + +#ifndef arch_atomic_fetch_dec_release +static __always_inline int +arch_atomic_fetch_dec_release(atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_dec_relaxed(v); +} +#define arch_atomic_fetch_dec_release arch_atomic_fetch_dec_release +#endif + +#ifndef arch_atomic_fetch_dec +static __always_inline int +arch_atomic_fetch_dec(atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_dec_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_dec arch_atomic_fetch_dec +#endif + +#endif /* arch_atomic_fetch_dec_relaxed */ + +#ifndef arch_atomic_fetch_and_relaxed +#define arch_atomic_fetch_and_acquire arch_atomic_fetch_and +#define arch_atomic_fetch_and_release arch_atomic_fetch_and +#define arch_atomic_fetch_and_relaxed arch_atomic_fetch_and +#else /* arch_atomic_fetch_and_relaxed */ + +#ifndef arch_atomic_fetch_and_acquire +static __always_inline int +arch_atomic_fetch_and_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_fetch_and_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_and_acquire arch_atomic_fetch_and_acquire +#endif + +#ifndef arch_atomic_fetch_and_release +static __always_inline int +arch_atomic_fetch_and_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_and_relaxed(i, v); +} +#define arch_atomic_fetch_and_release arch_atomic_fetch_and_release +#endif + +#ifndef arch_atomic_fetch_and +static __always_inline int +arch_atomic_fetch_and(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_and_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_and arch_atomic_fetch_and +#endif + +#endif /* arch_atomic_fetch_and_relaxed */ + +#ifndef arch_atomic_andnot +static __always_inline void +arch_atomic_andnot(int i, atomic_t *v) +{ + arch_atomic_and(~i, v); +} +#define arch_atomic_andnot arch_atomic_andnot +#endif + +#ifndef arch_atomic_fetch_andnot_relaxed +#ifdef arch_atomic_fetch_andnot +#define arch_atomic_fetch_andnot_acquire arch_atomic_fetch_andnot +#define arch_atomic_fetch_andnot_release arch_atomic_fetch_andnot +#define arch_atomic_fetch_andnot_relaxed arch_atomic_fetch_andnot +#endif /* arch_atomic_fetch_andnot */ + +#ifndef arch_atomic_fetch_andnot +static __always_inline int +arch_atomic_fetch_andnot(int i, atomic_t *v) +{ + return arch_atomic_fetch_and(~i, v); +} +#define arch_atomic_fetch_andnot arch_atomic_fetch_andnot +#endif + +#ifndef arch_atomic_fetch_andnot_acquire +static __always_inline int +arch_atomic_fetch_andnot_acquire(int i, atomic_t *v) +{ + return arch_atomic_fetch_and_acquire(~i, v); +} +#define arch_atomic_fetch_andnot_acquire arch_atomic_fetch_andnot_acquire +#endif + +#ifndef arch_atomic_fetch_andnot_release +static __always_inline int +arch_atomic_fetch_andnot_release(int i, atomic_t *v) +{ + return arch_atomic_fetch_and_release(~i, v); +} +#define arch_atomic_fetch_andnot_release arch_atomic_fetch_andnot_release +#endif + +#ifndef arch_atomic_fetch_andnot_relaxed +static __always_inline int +arch_atomic_fetch_andnot_relaxed(int i, atomic_t *v) +{ + return arch_atomic_fetch_and_relaxed(~i, v); +} +#define arch_atomic_fetch_andnot_relaxed arch_atomic_fetch_andnot_relaxed +#endif + +#else /* arch_atomic_fetch_andnot_relaxed */ + +#ifndef arch_atomic_fetch_andnot_acquire +static __always_inline int +arch_atomic_fetch_andnot_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_fetch_andnot_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_andnot_acquire arch_atomic_fetch_andnot_acquire +#endif + +#ifndef arch_atomic_fetch_andnot_release +static __always_inline int +arch_atomic_fetch_andnot_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_andnot_relaxed(i, v); +} +#define arch_atomic_fetch_andnot_release arch_atomic_fetch_andnot_release +#endif + +#ifndef arch_atomic_fetch_andnot +static __always_inline int +arch_atomic_fetch_andnot(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_andnot_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_andnot arch_atomic_fetch_andnot +#endif + +#endif /* arch_atomic_fetch_andnot_relaxed */ + +#ifndef arch_atomic_fetch_or_relaxed +#define arch_atomic_fetch_or_acquire arch_atomic_fetch_or +#define arch_atomic_fetch_or_release arch_atomic_fetch_or +#define arch_atomic_fetch_or_relaxed arch_atomic_fetch_or +#else /* arch_atomic_fetch_or_relaxed */ + +#ifndef arch_atomic_fetch_or_acquire +static __always_inline int +arch_atomic_fetch_or_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_fetch_or_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_or_acquire arch_atomic_fetch_or_acquire +#endif + +#ifndef arch_atomic_fetch_or_release +static __always_inline int +arch_atomic_fetch_or_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_or_relaxed(i, v); +} +#define arch_atomic_fetch_or_release arch_atomic_fetch_or_release +#endif + +#ifndef arch_atomic_fetch_or +static __always_inline int +arch_atomic_fetch_or(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_or_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_or arch_atomic_fetch_or +#endif + +#endif /* arch_atomic_fetch_or_relaxed */ + +#ifndef arch_atomic_fetch_xor_relaxed +#define arch_atomic_fetch_xor_acquire arch_atomic_fetch_xor +#define arch_atomic_fetch_xor_release arch_atomic_fetch_xor +#define arch_atomic_fetch_xor_relaxed arch_atomic_fetch_xor +#else /* arch_atomic_fetch_xor_relaxed */ + +#ifndef arch_atomic_fetch_xor_acquire +static __always_inline int +arch_atomic_fetch_xor_acquire(int i, atomic_t *v) +{ + int ret = arch_atomic_fetch_xor_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_fetch_xor_acquire arch_atomic_fetch_xor_acquire +#endif + +#ifndef arch_atomic_fetch_xor_release +static __always_inline int +arch_atomic_fetch_xor_release(int i, atomic_t *v) +{ + __atomic_release_fence(); + return arch_atomic_fetch_xor_relaxed(i, v); +} +#define arch_atomic_fetch_xor_release arch_atomic_fetch_xor_release +#endif + +#ifndef arch_atomic_fetch_xor +static __always_inline int +arch_atomic_fetch_xor(int i, atomic_t *v) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_fetch_xor_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_fetch_xor arch_atomic_fetch_xor +#endif + +#endif /* arch_atomic_fetch_xor_relaxed */ + +#ifndef arch_atomic_xchg_relaxed +#define arch_atomic_xchg_acquire arch_atomic_xchg +#define arch_atomic_xchg_release arch_atomic_xchg +#define arch_atomic_xchg_relaxed arch_atomic_xchg +#else /* arch_atomic_xchg_relaxed */ + +#ifndef arch_atomic_xchg_acquire +static __always_inline int +arch_atomic_xchg_acquire(atomic_t *v, int i) +{ + int ret = arch_atomic_xchg_relaxed(v, i); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_xchg_acquire arch_atomic_xchg_acquire +#endif + +#ifndef arch_atomic_xchg_release +static __always_inline int +arch_atomic_xchg_release(atomic_t *v, int i) +{ + __atomic_release_fence(); + return arch_atomic_xchg_relaxed(v, i); +} +#define arch_atomic_xchg_release arch_atomic_xchg_release +#endif + +#ifndef arch_atomic_xchg +static __always_inline int +arch_atomic_xchg(atomic_t *v, int i) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_xchg_relaxed(v, i); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_xchg arch_atomic_xchg +#endif + +#endif /* arch_atomic_xchg_relaxed */ + +#ifndef arch_atomic_cmpxchg_relaxed +#define arch_atomic_cmpxchg_acquire arch_atomic_cmpxchg +#define arch_atomic_cmpxchg_release arch_atomic_cmpxchg +#define arch_atomic_cmpxchg_relaxed arch_atomic_cmpxchg +#else /* arch_atomic_cmpxchg_relaxed */ + +#ifndef arch_atomic_cmpxchg_acquire +static __always_inline int +arch_atomic_cmpxchg_acquire(atomic_t *v, int old, int new) +{ + int ret = arch_atomic_cmpxchg_relaxed(v, old, new); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_cmpxchg_acquire arch_atomic_cmpxchg_acquire +#endif + +#ifndef arch_atomic_cmpxchg_release +static __always_inline int +arch_atomic_cmpxchg_release(atomic_t *v, int old, int new) +{ + __atomic_release_fence(); + return arch_atomic_cmpxchg_relaxed(v, old, new); +} +#define arch_atomic_cmpxchg_release arch_atomic_cmpxchg_release +#endif + +#ifndef arch_atomic_cmpxchg +static __always_inline int +arch_atomic_cmpxchg(atomic_t *v, int old, int new) +{ + int ret; + __atomic_pre_full_fence(); + ret = arch_atomic_cmpxchg_relaxed(v, old, new); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_cmpxchg arch_atomic_cmpxchg +#endif + +#endif /* arch_atomic_cmpxchg_relaxed */ + +#ifndef arch_atomic_try_cmpxchg_relaxed +#ifdef arch_atomic_try_cmpxchg +#define arch_atomic_try_cmpxchg_acquire arch_atomic_try_cmpxchg +#define arch_atomic_try_cmpxchg_release arch_atomic_try_cmpxchg +#define arch_atomic_try_cmpxchg_relaxed arch_atomic_try_cmpxchg +#endif /* arch_atomic_try_cmpxchg */ + +#ifndef arch_atomic_try_cmpxchg +static __always_inline bool +arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new) +{ + int r, o = *old; + r = arch_atomic_cmpxchg(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg +#endif + +#ifndef arch_atomic_try_cmpxchg_acquire +static __always_inline bool +arch_atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) +{ + int r, o = *old; + r = arch_atomic_cmpxchg_acquire(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic_try_cmpxchg_acquire arch_atomic_try_cmpxchg_acquire +#endif + +#ifndef arch_atomic_try_cmpxchg_release +static __always_inline bool +arch_atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) +{ + int r, o = *old; + r = arch_atomic_cmpxchg_release(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic_try_cmpxchg_release arch_atomic_try_cmpxchg_release +#endif + +#ifndef arch_atomic_try_cmpxchg_relaxed +static __always_inline bool +arch_atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) +{ + int r, o = *old; + r = arch_atomic_cmpxchg_relaxed(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic_try_cmpxchg_relaxed arch_atomic_try_cmpxchg_relaxed +#endif + +#else /* arch_atomic_try_cmpxchg_relaxed */ + +#ifndef arch_atomic_try_cmpxchg_acquire +static __always_inline bool +arch_atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) +{ + bool ret = arch_atomic_try_cmpxchg_relaxed(v, old, new); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic_try_cmpxchg_acquire arch_atomic_try_cmpxchg_acquire +#endif + +#ifndef arch_atomic_try_cmpxchg_release +static __always_inline bool +arch_atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) +{ + __atomic_release_fence(); + return arch_atomic_try_cmpxchg_relaxed(v, old, new); +} +#define arch_atomic_try_cmpxchg_release arch_atomic_try_cmpxchg_release +#endif + +#ifndef arch_atomic_try_cmpxchg +static __always_inline bool +arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new) +{ + bool ret; + __atomic_pre_full_fence(); + ret = arch_atomic_try_cmpxchg_relaxed(v, old, new); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg +#endif + +#endif /* arch_atomic_try_cmpxchg_relaxed */ + +#ifndef arch_atomic_sub_and_test +/** + * arch_atomic_sub_and_test - subtract value from variable and test result + * @i: integer value to subtract + * @v: pointer of type atomic_t + * + * Atomically subtracts @i from @v and returns + * true if the result is zero, or false for all + * other cases. + */ +static __always_inline bool +arch_atomic_sub_and_test(int i, atomic_t *v) +{ + return arch_atomic_sub_return(i, v) == 0; +} +#define arch_atomic_sub_and_test arch_atomic_sub_and_test +#endif + +#ifndef arch_atomic_dec_and_test +/** + * arch_atomic_dec_and_test - decrement and test + * @v: pointer of type atomic_t + * + * Atomically decrements @v by 1 and + * returns true if the result is 0, or false for all other + * cases. + */ +static __always_inline bool +arch_atomic_dec_and_test(atomic_t *v) +{ + return arch_atomic_dec_return(v) == 0; +} +#define arch_atomic_dec_and_test arch_atomic_dec_and_test +#endif + +#ifndef arch_atomic_inc_and_test +/** + * arch_atomic_inc_and_test - increment and test + * @v: pointer of type atomic_t + * + * Atomically increments @v by 1 + * and returns true if the result is zero, or false for all + * other cases. + */ +static __always_inline bool +arch_atomic_inc_and_test(atomic_t *v) +{ + return arch_atomic_inc_return(v) == 0; +} +#define arch_atomic_inc_and_test arch_atomic_inc_and_test +#endif + +#ifndef arch_atomic_add_negative +/** + * arch_atomic_add_negative - add and test if negative + * @i: integer value to add + * @v: pointer of type atomic_t + * + * Atomically adds @i to @v and returns true + * if the result is negative, or false when + * result is greater than or equal to zero. + */ +static __always_inline bool +arch_atomic_add_negative(int i, atomic_t *v) +{ + return arch_atomic_add_return(i, v) < 0; +} +#define arch_atomic_add_negative arch_atomic_add_negative +#endif + +#ifndef arch_atomic_fetch_add_unless +/** + * arch_atomic_fetch_add_unless - add unless the number is already a given value + * @v: pointer of type atomic_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, so long as @v was not already @u. + * Returns original value of @v + */ +static __always_inline int +arch_atomic_fetch_add_unless(atomic_t *v, int a, int u) +{ + int c = arch_atomic_read(v); + + do { + if (unlikely(c == u)) + break; + } while (!arch_atomic_try_cmpxchg(v, &c, c + a)); + + return c; +} +#define arch_atomic_fetch_add_unless arch_atomic_fetch_add_unless +#endif + +#ifndef arch_atomic_add_unless +/** + * arch_atomic_add_unless - add unless the number is already a given value + * @v: pointer of type atomic_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, if @v was not already @u. + * Returns true if the addition was done. + */ +static __always_inline bool +arch_atomic_add_unless(atomic_t *v, int a, int u) +{ + return arch_atomic_fetch_add_unless(v, a, u) != u; +} +#define arch_atomic_add_unless arch_atomic_add_unless +#endif + +#ifndef arch_atomic_inc_not_zero +/** + * arch_atomic_inc_not_zero - increment unless the number is zero + * @v: pointer of type atomic_t + * + * Atomically increments @v by 1, if @v is non-zero. + * Returns true if the increment was done. + */ +static __always_inline bool +arch_atomic_inc_not_zero(atomic_t *v) +{ + return arch_atomic_add_unless(v, 1, 0); +} +#define arch_atomic_inc_not_zero arch_atomic_inc_not_zero +#endif + +#ifndef arch_atomic_inc_unless_negative +static __always_inline bool +arch_atomic_inc_unless_negative(atomic_t *v) +{ + int c = arch_atomic_read(v); + + do { + if (unlikely(c < 0)) + return false; + } while (!arch_atomic_try_cmpxchg(v, &c, c + 1)); + + return true; +} +#define arch_atomic_inc_unless_negative arch_atomic_inc_unless_negative +#endif + +#ifndef arch_atomic_dec_unless_positive +static __always_inline bool +arch_atomic_dec_unless_positive(atomic_t *v) +{ + int c = arch_atomic_read(v); + + do { + if (unlikely(c > 0)) + return false; + } while (!arch_atomic_try_cmpxchg(v, &c, c - 1)); + + return true; +} +#define arch_atomic_dec_unless_positive arch_atomic_dec_unless_positive +#endif + +#ifndef arch_atomic_dec_if_positive +static __always_inline int +arch_atomic_dec_if_positive(atomic_t *v) +{ + int dec, c = arch_atomic_read(v); + + do { + dec = c - 1; + if (unlikely(dec < 0)) + break; + } while (!arch_atomic_try_cmpxchg(v, &c, dec)); + + return dec; +} +#define arch_atomic_dec_if_positive arch_atomic_dec_if_positive +#endif + +#ifdef CONFIG_GENERIC_ATOMIC64 +#include +#endif + +#ifndef arch_atomic64_read_acquire +static __always_inline s64 +arch_atomic64_read_acquire(const atomic64_t *v) +{ + return smp_load_acquire(&(v)->counter); +} +#define arch_atomic64_read_acquire arch_atomic64_read_acquire +#endif + +#ifndef arch_atomic64_set_release +static __always_inline void +arch_atomic64_set_release(atomic64_t *v, s64 i) +{ + smp_store_release(&(v)->counter, i); +} +#define arch_atomic64_set_release arch_atomic64_set_release +#endif + +#ifndef arch_atomic64_add_return_relaxed +#define arch_atomic64_add_return_acquire arch_atomic64_add_return +#define arch_atomic64_add_return_release arch_atomic64_add_return +#define arch_atomic64_add_return_relaxed arch_atomic64_add_return +#else /* arch_atomic64_add_return_relaxed */ + +#ifndef arch_atomic64_add_return_acquire +static __always_inline s64 +arch_atomic64_add_return_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_add_return_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_add_return_acquire arch_atomic64_add_return_acquire +#endif + +#ifndef arch_atomic64_add_return_release +static __always_inline s64 +arch_atomic64_add_return_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_add_return_relaxed(i, v); +} +#define arch_atomic64_add_return_release arch_atomic64_add_return_release +#endif + +#ifndef arch_atomic64_add_return +static __always_inline s64 +arch_atomic64_add_return(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_add_return_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_add_return arch_atomic64_add_return +#endif + +#endif /* arch_atomic64_add_return_relaxed */ + +#ifndef arch_atomic64_fetch_add_relaxed +#define arch_atomic64_fetch_add_acquire arch_atomic64_fetch_add +#define arch_atomic64_fetch_add_release arch_atomic64_fetch_add +#define arch_atomic64_fetch_add_relaxed arch_atomic64_fetch_add +#else /* arch_atomic64_fetch_add_relaxed */ + +#ifndef arch_atomic64_fetch_add_acquire +static __always_inline s64 +arch_atomic64_fetch_add_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_add_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_add_acquire arch_atomic64_fetch_add_acquire +#endif + +#ifndef arch_atomic64_fetch_add_release +static __always_inline s64 +arch_atomic64_fetch_add_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_add_relaxed(i, v); +} +#define arch_atomic64_fetch_add_release arch_atomic64_fetch_add_release +#endif + +#ifndef arch_atomic64_fetch_add +static __always_inline s64 +arch_atomic64_fetch_add(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_add_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_add arch_atomic64_fetch_add +#endif + +#endif /* arch_atomic64_fetch_add_relaxed */ + +#ifndef arch_atomic64_sub_return_relaxed +#define arch_atomic64_sub_return_acquire arch_atomic64_sub_return +#define arch_atomic64_sub_return_release arch_atomic64_sub_return +#define arch_atomic64_sub_return_relaxed arch_atomic64_sub_return +#else /* arch_atomic64_sub_return_relaxed */ + +#ifndef arch_atomic64_sub_return_acquire +static __always_inline s64 +arch_atomic64_sub_return_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_sub_return_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_sub_return_acquire arch_atomic64_sub_return_acquire +#endif + +#ifndef arch_atomic64_sub_return_release +static __always_inline s64 +arch_atomic64_sub_return_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_sub_return_relaxed(i, v); +} +#define arch_atomic64_sub_return_release arch_atomic64_sub_return_release +#endif + +#ifndef arch_atomic64_sub_return +static __always_inline s64 +arch_atomic64_sub_return(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_sub_return_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_sub_return arch_atomic64_sub_return +#endif + +#endif /* arch_atomic64_sub_return_relaxed */ + +#ifndef arch_atomic64_fetch_sub_relaxed +#define arch_atomic64_fetch_sub_acquire arch_atomic64_fetch_sub +#define arch_atomic64_fetch_sub_release arch_atomic64_fetch_sub +#define arch_atomic64_fetch_sub_relaxed arch_atomic64_fetch_sub +#else /* arch_atomic64_fetch_sub_relaxed */ + +#ifndef arch_atomic64_fetch_sub_acquire +static __always_inline s64 +arch_atomic64_fetch_sub_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_sub_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_sub_acquire arch_atomic64_fetch_sub_acquire +#endif + +#ifndef arch_atomic64_fetch_sub_release +static __always_inline s64 +arch_atomic64_fetch_sub_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_sub_relaxed(i, v); +} +#define arch_atomic64_fetch_sub_release arch_atomic64_fetch_sub_release +#endif + +#ifndef arch_atomic64_fetch_sub +static __always_inline s64 +arch_atomic64_fetch_sub(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_sub_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_sub arch_atomic64_fetch_sub +#endif + +#endif /* arch_atomic64_fetch_sub_relaxed */ + +#ifndef arch_atomic64_inc +static __always_inline void +arch_atomic64_inc(atomic64_t *v) +{ + arch_atomic64_add(1, v); +} +#define arch_atomic64_inc arch_atomic64_inc +#endif + +#ifndef arch_atomic64_inc_return_relaxed +#ifdef arch_atomic64_inc_return +#define arch_atomic64_inc_return_acquire arch_atomic64_inc_return +#define arch_atomic64_inc_return_release arch_atomic64_inc_return +#define arch_atomic64_inc_return_relaxed arch_atomic64_inc_return +#endif /* arch_atomic64_inc_return */ + +#ifndef arch_atomic64_inc_return +static __always_inline s64 +arch_atomic64_inc_return(atomic64_t *v) +{ + return arch_atomic64_add_return(1, v); +} +#define arch_atomic64_inc_return arch_atomic64_inc_return +#endif + +#ifndef arch_atomic64_inc_return_acquire +static __always_inline s64 +arch_atomic64_inc_return_acquire(atomic64_t *v) +{ + return arch_atomic64_add_return_acquire(1, v); +} +#define arch_atomic64_inc_return_acquire arch_atomic64_inc_return_acquire +#endif + +#ifndef arch_atomic64_inc_return_release +static __always_inline s64 +arch_atomic64_inc_return_release(atomic64_t *v) +{ + return arch_atomic64_add_return_release(1, v); +} +#define arch_atomic64_inc_return_release arch_atomic64_inc_return_release +#endif + +#ifndef arch_atomic64_inc_return_relaxed +static __always_inline s64 +arch_atomic64_inc_return_relaxed(atomic64_t *v) +{ + return arch_atomic64_add_return_relaxed(1, v); +} +#define arch_atomic64_inc_return_relaxed arch_atomic64_inc_return_relaxed +#endif + +#else /* arch_atomic64_inc_return_relaxed */ + +#ifndef arch_atomic64_inc_return_acquire +static __always_inline s64 +arch_atomic64_inc_return_acquire(atomic64_t *v) +{ + s64 ret = arch_atomic64_inc_return_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_inc_return_acquire arch_atomic64_inc_return_acquire +#endif + +#ifndef arch_atomic64_inc_return_release +static __always_inline s64 +arch_atomic64_inc_return_release(atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_inc_return_relaxed(v); +} +#define arch_atomic64_inc_return_release arch_atomic64_inc_return_release +#endif + +#ifndef arch_atomic64_inc_return +static __always_inline s64 +arch_atomic64_inc_return(atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_inc_return_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_inc_return arch_atomic64_inc_return +#endif + +#endif /* arch_atomic64_inc_return_relaxed */ + +#ifndef arch_atomic64_fetch_inc_relaxed +#ifdef arch_atomic64_fetch_inc +#define arch_atomic64_fetch_inc_acquire arch_atomic64_fetch_inc +#define arch_atomic64_fetch_inc_release arch_atomic64_fetch_inc +#define arch_atomic64_fetch_inc_relaxed arch_atomic64_fetch_inc +#endif /* arch_atomic64_fetch_inc */ + +#ifndef arch_atomic64_fetch_inc +static __always_inline s64 +arch_atomic64_fetch_inc(atomic64_t *v) +{ + return arch_atomic64_fetch_add(1, v); +} +#define arch_atomic64_fetch_inc arch_atomic64_fetch_inc +#endif + +#ifndef arch_atomic64_fetch_inc_acquire +static __always_inline s64 +arch_atomic64_fetch_inc_acquire(atomic64_t *v) +{ + return arch_atomic64_fetch_add_acquire(1, v); +} +#define arch_atomic64_fetch_inc_acquire arch_atomic64_fetch_inc_acquire +#endif + +#ifndef arch_atomic64_fetch_inc_release +static __always_inline s64 +arch_atomic64_fetch_inc_release(atomic64_t *v) +{ + return arch_atomic64_fetch_add_release(1, v); +} +#define arch_atomic64_fetch_inc_release arch_atomic64_fetch_inc_release +#endif + +#ifndef arch_atomic64_fetch_inc_relaxed +static __always_inline s64 +arch_atomic64_fetch_inc_relaxed(atomic64_t *v) +{ + return arch_atomic64_fetch_add_relaxed(1, v); +} +#define arch_atomic64_fetch_inc_relaxed arch_atomic64_fetch_inc_relaxed +#endif + +#else /* arch_atomic64_fetch_inc_relaxed */ + +#ifndef arch_atomic64_fetch_inc_acquire +static __always_inline s64 +arch_atomic64_fetch_inc_acquire(atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_inc_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_inc_acquire arch_atomic64_fetch_inc_acquire +#endif + +#ifndef arch_atomic64_fetch_inc_release +static __always_inline s64 +arch_atomic64_fetch_inc_release(atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_inc_relaxed(v); +} +#define arch_atomic64_fetch_inc_release arch_atomic64_fetch_inc_release +#endif + +#ifndef arch_atomic64_fetch_inc +static __always_inline s64 +arch_atomic64_fetch_inc(atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_inc_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_inc arch_atomic64_fetch_inc +#endif + +#endif /* arch_atomic64_fetch_inc_relaxed */ + +#ifndef arch_atomic64_dec +static __always_inline void +arch_atomic64_dec(atomic64_t *v) +{ + arch_atomic64_sub(1, v); +} +#define arch_atomic64_dec arch_atomic64_dec +#endif + +#ifndef arch_atomic64_dec_return_relaxed +#ifdef arch_atomic64_dec_return +#define arch_atomic64_dec_return_acquire arch_atomic64_dec_return +#define arch_atomic64_dec_return_release arch_atomic64_dec_return +#define arch_atomic64_dec_return_relaxed arch_atomic64_dec_return +#endif /* arch_atomic64_dec_return */ + +#ifndef arch_atomic64_dec_return +static __always_inline s64 +arch_atomic64_dec_return(atomic64_t *v) +{ + return arch_atomic64_sub_return(1, v); +} +#define arch_atomic64_dec_return arch_atomic64_dec_return +#endif + +#ifndef arch_atomic64_dec_return_acquire +static __always_inline s64 +arch_atomic64_dec_return_acquire(atomic64_t *v) +{ + return arch_atomic64_sub_return_acquire(1, v); +} +#define arch_atomic64_dec_return_acquire arch_atomic64_dec_return_acquire +#endif + +#ifndef arch_atomic64_dec_return_release +static __always_inline s64 +arch_atomic64_dec_return_release(atomic64_t *v) +{ + return arch_atomic64_sub_return_release(1, v); +} +#define arch_atomic64_dec_return_release arch_atomic64_dec_return_release +#endif + +#ifndef arch_atomic64_dec_return_relaxed +static __always_inline s64 +arch_atomic64_dec_return_relaxed(atomic64_t *v) +{ + return arch_atomic64_sub_return_relaxed(1, v); +} +#define arch_atomic64_dec_return_relaxed arch_atomic64_dec_return_relaxed +#endif + +#else /* arch_atomic64_dec_return_relaxed */ + +#ifndef arch_atomic64_dec_return_acquire +static __always_inline s64 +arch_atomic64_dec_return_acquire(atomic64_t *v) +{ + s64 ret = arch_atomic64_dec_return_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_dec_return_acquire arch_atomic64_dec_return_acquire +#endif + +#ifndef arch_atomic64_dec_return_release +static __always_inline s64 +arch_atomic64_dec_return_release(atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_dec_return_relaxed(v); +} +#define arch_atomic64_dec_return_release arch_atomic64_dec_return_release +#endif + +#ifndef arch_atomic64_dec_return +static __always_inline s64 +arch_atomic64_dec_return(atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_dec_return_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_dec_return arch_atomic64_dec_return +#endif + +#endif /* arch_atomic64_dec_return_relaxed */ + +#ifndef arch_atomic64_fetch_dec_relaxed +#ifdef arch_atomic64_fetch_dec +#define arch_atomic64_fetch_dec_acquire arch_atomic64_fetch_dec +#define arch_atomic64_fetch_dec_release arch_atomic64_fetch_dec +#define arch_atomic64_fetch_dec_relaxed arch_atomic64_fetch_dec +#endif /* arch_atomic64_fetch_dec */ + +#ifndef arch_atomic64_fetch_dec +static __always_inline s64 +arch_atomic64_fetch_dec(atomic64_t *v) +{ + return arch_atomic64_fetch_sub(1, v); +} +#define arch_atomic64_fetch_dec arch_atomic64_fetch_dec +#endif + +#ifndef arch_atomic64_fetch_dec_acquire +static __always_inline s64 +arch_atomic64_fetch_dec_acquire(atomic64_t *v) +{ + return arch_atomic64_fetch_sub_acquire(1, v); +} +#define arch_atomic64_fetch_dec_acquire arch_atomic64_fetch_dec_acquire +#endif + +#ifndef arch_atomic64_fetch_dec_release +static __always_inline s64 +arch_atomic64_fetch_dec_release(atomic64_t *v) +{ + return arch_atomic64_fetch_sub_release(1, v); +} +#define arch_atomic64_fetch_dec_release arch_atomic64_fetch_dec_release +#endif + +#ifndef arch_atomic64_fetch_dec_relaxed +static __always_inline s64 +arch_atomic64_fetch_dec_relaxed(atomic64_t *v) +{ + return arch_atomic64_fetch_sub_relaxed(1, v); +} +#define arch_atomic64_fetch_dec_relaxed arch_atomic64_fetch_dec_relaxed +#endif + +#else /* arch_atomic64_fetch_dec_relaxed */ + +#ifndef arch_atomic64_fetch_dec_acquire +static __always_inline s64 +arch_atomic64_fetch_dec_acquire(atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_dec_relaxed(v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_dec_acquire arch_atomic64_fetch_dec_acquire +#endif + +#ifndef arch_atomic64_fetch_dec_release +static __always_inline s64 +arch_atomic64_fetch_dec_release(atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_dec_relaxed(v); +} +#define arch_atomic64_fetch_dec_release arch_atomic64_fetch_dec_release +#endif + +#ifndef arch_atomic64_fetch_dec +static __always_inline s64 +arch_atomic64_fetch_dec(atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_dec_relaxed(v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_dec arch_atomic64_fetch_dec +#endif + +#endif /* arch_atomic64_fetch_dec_relaxed */ + +#ifndef arch_atomic64_fetch_and_relaxed +#define arch_atomic64_fetch_and_acquire arch_atomic64_fetch_and +#define arch_atomic64_fetch_and_release arch_atomic64_fetch_and +#define arch_atomic64_fetch_and_relaxed arch_atomic64_fetch_and +#else /* arch_atomic64_fetch_and_relaxed */ + +#ifndef arch_atomic64_fetch_and_acquire +static __always_inline s64 +arch_atomic64_fetch_and_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_and_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_and_acquire arch_atomic64_fetch_and_acquire +#endif + +#ifndef arch_atomic64_fetch_and_release +static __always_inline s64 +arch_atomic64_fetch_and_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_and_relaxed(i, v); +} +#define arch_atomic64_fetch_and_release arch_atomic64_fetch_and_release +#endif + +#ifndef arch_atomic64_fetch_and +static __always_inline s64 +arch_atomic64_fetch_and(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_and_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_and arch_atomic64_fetch_and +#endif + +#endif /* arch_atomic64_fetch_and_relaxed */ + +#ifndef arch_atomic64_andnot +static __always_inline void +arch_atomic64_andnot(s64 i, atomic64_t *v) +{ + arch_atomic64_and(~i, v); +} +#define arch_atomic64_andnot arch_atomic64_andnot +#endif + +#ifndef arch_atomic64_fetch_andnot_relaxed +#ifdef arch_atomic64_fetch_andnot +#define arch_atomic64_fetch_andnot_acquire arch_atomic64_fetch_andnot +#define arch_atomic64_fetch_andnot_release arch_atomic64_fetch_andnot +#define arch_atomic64_fetch_andnot_relaxed arch_atomic64_fetch_andnot +#endif /* arch_atomic64_fetch_andnot */ + +#ifndef arch_atomic64_fetch_andnot +static __always_inline s64 +arch_atomic64_fetch_andnot(s64 i, atomic64_t *v) +{ + return arch_atomic64_fetch_and(~i, v); +} +#define arch_atomic64_fetch_andnot arch_atomic64_fetch_andnot +#endif + +#ifndef arch_atomic64_fetch_andnot_acquire +static __always_inline s64 +arch_atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) +{ + return arch_atomic64_fetch_and_acquire(~i, v); +} +#define arch_atomic64_fetch_andnot_acquire arch_atomic64_fetch_andnot_acquire +#endif + +#ifndef arch_atomic64_fetch_andnot_release +static __always_inline s64 +arch_atomic64_fetch_andnot_release(s64 i, atomic64_t *v) +{ + return arch_atomic64_fetch_and_release(~i, v); +} +#define arch_atomic64_fetch_andnot_release arch_atomic64_fetch_andnot_release +#endif + +#ifndef arch_atomic64_fetch_andnot_relaxed +static __always_inline s64 +arch_atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v) +{ + return arch_atomic64_fetch_and_relaxed(~i, v); +} +#define arch_atomic64_fetch_andnot_relaxed arch_atomic64_fetch_andnot_relaxed +#endif + +#else /* arch_atomic64_fetch_andnot_relaxed */ + +#ifndef arch_atomic64_fetch_andnot_acquire +static __always_inline s64 +arch_atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_andnot_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_andnot_acquire arch_atomic64_fetch_andnot_acquire +#endif + +#ifndef arch_atomic64_fetch_andnot_release +static __always_inline s64 +arch_atomic64_fetch_andnot_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_andnot_relaxed(i, v); +} +#define arch_atomic64_fetch_andnot_release arch_atomic64_fetch_andnot_release +#endif + +#ifndef arch_atomic64_fetch_andnot +static __always_inline s64 +arch_atomic64_fetch_andnot(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_andnot_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_andnot arch_atomic64_fetch_andnot +#endif + +#endif /* arch_atomic64_fetch_andnot_relaxed */ + +#ifndef arch_atomic64_fetch_or_relaxed +#define arch_atomic64_fetch_or_acquire arch_atomic64_fetch_or +#define arch_atomic64_fetch_or_release arch_atomic64_fetch_or +#define arch_atomic64_fetch_or_relaxed arch_atomic64_fetch_or +#else /* arch_atomic64_fetch_or_relaxed */ + +#ifndef arch_atomic64_fetch_or_acquire +static __always_inline s64 +arch_atomic64_fetch_or_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_or_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_or_acquire arch_atomic64_fetch_or_acquire +#endif + +#ifndef arch_atomic64_fetch_or_release +static __always_inline s64 +arch_atomic64_fetch_or_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_or_relaxed(i, v); +} +#define arch_atomic64_fetch_or_release arch_atomic64_fetch_or_release +#endif + +#ifndef arch_atomic64_fetch_or +static __always_inline s64 +arch_atomic64_fetch_or(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_or_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_or arch_atomic64_fetch_or +#endif + +#endif /* arch_atomic64_fetch_or_relaxed */ + +#ifndef arch_atomic64_fetch_xor_relaxed +#define arch_atomic64_fetch_xor_acquire arch_atomic64_fetch_xor +#define arch_atomic64_fetch_xor_release arch_atomic64_fetch_xor +#define arch_atomic64_fetch_xor_relaxed arch_atomic64_fetch_xor +#else /* arch_atomic64_fetch_xor_relaxed */ + +#ifndef arch_atomic64_fetch_xor_acquire +static __always_inline s64 +arch_atomic64_fetch_xor_acquire(s64 i, atomic64_t *v) +{ + s64 ret = arch_atomic64_fetch_xor_relaxed(i, v); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_fetch_xor_acquire arch_atomic64_fetch_xor_acquire +#endif + +#ifndef arch_atomic64_fetch_xor_release +static __always_inline s64 +arch_atomic64_fetch_xor_release(s64 i, atomic64_t *v) +{ + __atomic_release_fence(); + return arch_atomic64_fetch_xor_relaxed(i, v); +} +#define arch_atomic64_fetch_xor_release arch_atomic64_fetch_xor_release +#endif + +#ifndef arch_atomic64_fetch_xor +static __always_inline s64 +arch_atomic64_fetch_xor(s64 i, atomic64_t *v) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_fetch_xor_relaxed(i, v); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_fetch_xor arch_atomic64_fetch_xor +#endif + +#endif /* arch_atomic64_fetch_xor_relaxed */ + +#ifndef arch_atomic64_xchg_relaxed +#define arch_atomic64_xchg_acquire arch_atomic64_xchg +#define arch_atomic64_xchg_release arch_atomic64_xchg +#define arch_atomic64_xchg_relaxed arch_atomic64_xchg +#else /* arch_atomic64_xchg_relaxed */ + +#ifndef arch_atomic64_xchg_acquire +static __always_inline s64 +arch_atomic64_xchg_acquire(atomic64_t *v, s64 i) +{ + s64 ret = arch_atomic64_xchg_relaxed(v, i); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_xchg_acquire arch_atomic64_xchg_acquire +#endif + +#ifndef arch_atomic64_xchg_release +static __always_inline s64 +arch_atomic64_xchg_release(atomic64_t *v, s64 i) +{ + __atomic_release_fence(); + return arch_atomic64_xchg_relaxed(v, i); +} +#define arch_atomic64_xchg_release arch_atomic64_xchg_release +#endif + +#ifndef arch_atomic64_xchg +static __always_inline s64 +arch_atomic64_xchg(atomic64_t *v, s64 i) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_xchg_relaxed(v, i); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_xchg arch_atomic64_xchg +#endif + +#endif /* arch_atomic64_xchg_relaxed */ + +#ifndef arch_atomic64_cmpxchg_relaxed +#define arch_atomic64_cmpxchg_acquire arch_atomic64_cmpxchg +#define arch_atomic64_cmpxchg_release arch_atomic64_cmpxchg +#define arch_atomic64_cmpxchg_relaxed arch_atomic64_cmpxchg +#else /* arch_atomic64_cmpxchg_relaxed */ + +#ifndef arch_atomic64_cmpxchg_acquire +static __always_inline s64 +arch_atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) +{ + s64 ret = arch_atomic64_cmpxchg_relaxed(v, old, new); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_cmpxchg_acquire arch_atomic64_cmpxchg_acquire +#endif + +#ifndef arch_atomic64_cmpxchg_release +static __always_inline s64 +arch_atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) +{ + __atomic_release_fence(); + return arch_atomic64_cmpxchg_relaxed(v, old, new); +} +#define arch_atomic64_cmpxchg_release arch_atomic64_cmpxchg_release +#endif + +#ifndef arch_atomic64_cmpxchg +static __always_inline s64 +arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) +{ + s64 ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_cmpxchg_relaxed(v, old, new); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_cmpxchg arch_atomic64_cmpxchg +#endif + +#endif /* arch_atomic64_cmpxchg_relaxed */ + +#ifndef arch_atomic64_try_cmpxchg_relaxed +#ifdef arch_atomic64_try_cmpxchg +#define arch_atomic64_try_cmpxchg_acquire arch_atomic64_try_cmpxchg +#define arch_atomic64_try_cmpxchg_release arch_atomic64_try_cmpxchg +#define arch_atomic64_try_cmpxchg_relaxed arch_atomic64_try_cmpxchg +#endif /* arch_atomic64_try_cmpxchg */ + +#ifndef arch_atomic64_try_cmpxchg +static __always_inline bool +arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) +{ + s64 r, o = *old; + r = arch_atomic64_cmpxchg(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg +#endif + +#ifndef arch_atomic64_try_cmpxchg_acquire +static __always_inline bool +arch_atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) +{ + s64 r, o = *old; + r = arch_atomic64_cmpxchg_acquire(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic64_try_cmpxchg_acquire arch_atomic64_try_cmpxchg_acquire +#endif + +#ifndef arch_atomic64_try_cmpxchg_release +static __always_inline bool +arch_atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) +{ + s64 r, o = *old; + r = arch_atomic64_cmpxchg_release(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic64_try_cmpxchg_release arch_atomic64_try_cmpxchg_release +#endif + +#ifndef arch_atomic64_try_cmpxchg_relaxed +static __always_inline bool +arch_atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) +{ + s64 r, o = *old; + r = arch_atomic64_cmpxchg_relaxed(v, o, new); + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} +#define arch_atomic64_try_cmpxchg_relaxed arch_atomic64_try_cmpxchg_relaxed +#endif + +#else /* arch_atomic64_try_cmpxchg_relaxed */ + +#ifndef arch_atomic64_try_cmpxchg_acquire +static __always_inline bool +arch_atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) +{ + bool ret = arch_atomic64_try_cmpxchg_relaxed(v, old, new); + __atomic_acquire_fence(); + return ret; +} +#define arch_atomic64_try_cmpxchg_acquire arch_atomic64_try_cmpxchg_acquire +#endif + +#ifndef arch_atomic64_try_cmpxchg_release +static __always_inline bool +arch_atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) +{ + __atomic_release_fence(); + return arch_atomic64_try_cmpxchg_relaxed(v, old, new); +} +#define arch_atomic64_try_cmpxchg_release arch_atomic64_try_cmpxchg_release +#endif + +#ifndef arch_atomic64_try_cmpxchg +static __always_inline bool +arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) +{ + bool ret; + __atomic_pre_full_fence(); + ret = arch_atomic64_try_cmpxchg_relaxed(v, old, new); + __atomic_post_full_fence(); + return ret; +} +#define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg +#endif + +#endif /* arch_atomic64_try_cmpxchg_relaxed */ + +#ifndef arch_atomic64_sub_and_test +/** + * arch_atomic64_sub_and_test - subtract value from variable and test result + * @i: integer value to subtract + * @v: pointer of type atomic64_t + * + * Atomically subtracts @i from @v and returns + * true if the result is zero, or false for all + * other cases. + */ +static __always_inline bool +arch_atomic64_sub_and_test(s64 i, atomic64_t *v) +{ + return arch_atomic64_sub_return(i, v) == 0; +} +#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test +#endif + +#ifndef arch_atomic64_dec_and_test +/** + * arch_atomic64_dec_and_test - decrement and test + * @v: pointer of type atomic64_t + * + * Atomically decrements @v by 1 and + * returns true if the result is 0, or false for all other + * cases. + */ +static __always_inline bool +arch_atomic64_dec_and_test(atomic64_t *v) +{ + return arch_atomic64_dec_return(v) == 0; +} +#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test +#endif + +#ifndef arch_atomic64_inc_and_test +/** + * arch_atomic64_inc_and_test - increment and test + * @v: pointer of type atomic64_t + * + * Atomically increments @v by 1 + * and returns true if the result is zero, or false for all + * other cases. + */ +static __always_inline bool +arch_atomic64_inc_and_test(atomic64_t *v) +{ + return arch_atomic64_inc_return(v) == 0; +} +#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test +#endif + +#ifndef arch_atomic64_add_negative +/** + * arch_atomic64_add_negative - add and test if negative + * @i: integer value to add + * @v: pointer of type atomic64_t + * + * Atomically adds @i to @v and returns true + * if the result is negative, or false when + * result is greater than or equal to zero. + */ +static __always_inline bool +arch_atomic64_add_negative(s64 i, atomic64_t *v) +{ + return arch_atomic64_add_return(i, v) < 0; +} +#define arch_atomic64_add_negative arch_atomic64_add_negative +#endif + +#ifndef arch_atomic64_fetch_add_unless +/** + * arch_atomic64_fetch_add_unless - add unless the number is already a given value + * @v: pointer of type atomic64_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, so long as @v was not already @u. + * Returns original value of @v + */ +static __always_inline s64 +arch_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) +{ + s64 c = arch_atomic64_read(v); + + do { + if (unlikely(c == u)) + break; + } while (!arch_atomic64_try_cmpxchg(v, &c, c + a)); + + return c; +} +#define arch_atomic64_fetch_add_unless arch_atomic64_fetch_add_unless +#endif + +#ifndef arch_atomic64_add_unless +/** + * arch_atomic64_add_unless - add unless the number is already a given value + * @v: pointer of type atomic64_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, if @v was not already @u. + * Returns true if the addition was done. + */ +static __always_inline bool +arch_atomic64_add_unless(atomic64_t *v, s64 a, s64 u) +{ + return arch_atomic64_fetch_add_unless(v, a, u) != u; +} +#define arch_atomic64_add_unless arch_atomic64_add_unless +#endif + +#ifndef arch_atomic64_inc_not_zero +/** + * arch_atomic64_inc_not_zero - increment unless the number is zero + * @v: pointer of type atomic64_t + * + * Atomically increments @v by 1, if @v is non-zero. + * Returns true if the increment was done. + */ +static __always_inline bool +arch_atomic64_inc_not_zero(atomic64_t *v) +{ + return arch_atomic64_add_unless(v, 1, 0); +} +#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero +#endif + +#ifndef arch_atomic64_inc_unless_negative +static __always_inline bool +arch_atomic64_inc_unless_negative(atomic64_t *v) +{ + s64 c = arch_atomic64_read(v); + + do { + if (unlikely(c < 0)) + return false; + } while (!arch_atomic64_try_cmpxchg(v, &c, c + 1)); + + return true; +} +#define arch_atomic64_inc_unless_negative arch_atomic64_inc_unless_negative +#endif + +#ifndef arch_atomic64_dec_unless_positive +static __always_inline bool +arch_atomic64_dec_unless_positive(atomic64_t *v) +{ + s64 c = arch_atomic64_read(v); + + do { + if (unlikely(c > 0)) + return false; + } while (!arch_atomic64_try_cmpxchg(v, &c, c - 1)); + + return true; +} +#define arch_atomic64_dec_unless_positive arch_atomic64_dec_unless_positive +#endif + +#ifndef arch_atomic64_dec_if_positive +static __always_inline s64 +arch_atomic64_dec_if_positive(atomic64_t *v) +{ + s64 dec, c = arch_atomic64_read(v); + + do { + dec = c - 1; + if (unlikely(dec < 0)) + break; + } while (!arch_atomic64_try_cmpxchg(v, &c, dec)); + + return dec; +} +#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive +#endif + +#endif /* _LINUX_ATOMIC_FALLBACK_H */ +// cca554917d7ea73d5e3e7397dd70c484cad9b2c4 diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h new file mode 100644 index 000000000000..f6fe36c428df --- /dev/null +++ b/include/linux/atomic/atomic-instrumented.h @@ -0,0 +1,1337 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Generated by scripts/atomic/gen-atomic-instrumented.sh +// DO NOT MODIFY THIS FILE DIRECTLY + +/* + * This file provides wrappers with KASAN instrumentation for atomic operations. + * To use this functionality an arch's atomic.h file needs to define all + * atomic operations with arch_ prefix (e.g. arch_atomic_read()) and include + * this file at the end. This file provides atomic_read() that forwards to + * arch_atomic_read() for actual atomic operation. + * Note: if an arch atomic operation is implemented by means of other atomic + * operations (e.g. atomic_read()/atomic_cmpxchg() loop), then it needs to use + * arch_ variants (i.e. arch_atomic_read()/arch_atomic_cmpxchg()) to avoid + * double instrumentation. + */ +#ifndef _LINUX_ATOMIC_INSTRUMENTED_H +#define _LINUX_ATOMIC_INSTRUMENTED_H + +#include +#include +#include + +static __always_inline int +atomic_read(const atomic_t *v) +{ + instrument_atomic_read(v, sizeof(*v)); + return arch_atomic_read(v); +} + +static __always_inline int +atomic_read_acquire(const atomic_t *v) +{ + instrument_atomic_read(v, sizeof(*v)); + return arch_atomic_read_acquire(v); +} + +static __always_inline void +atomic_set(atomic_t *v, int i) +{ + instrument_atomic_write(v, sizeof(*v)); + arch_atomic_set(v, i); +} + +static __always_inline void +atomic_set_release(atomic_t *v, int i) +{ + instrument_atomic_write(v, sizeof(*v)); + arch_atomic_set_release(v, i); +} + +static __always_inline void +atomic_add(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_add(i, v); +} + +static __always_inline int +atomic_add_return(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_add_return(i, v); +} + +static __always_inline int +atomic_add_return_acquire(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_add_return_acquire(i, v); +} + +static __always_inline int +atomic_add_return_release(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_add_return_release(i, v); +} + +static __always_inline int +atomic_add_return_relaxed(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_add_return_relaxed(i, v); +} + +static __always_inline int +atomic_fetch_add(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_add(i, v); +} + +static __always_inline int +atomic_fetch_add_acquire(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_add_acquire(i, v); +} + +static __always_inline int +atomic_fetch_add_release(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_add_release(i, v); +} + +static __always_inline int +atomic_fetch_add_relaxed(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_add_relaxed(i, v); +} + +static __always_inline void +atomic_sub(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_sub(i, v); +} + +static __always_inline int +atomic_sub_return(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_sub_return(i, v); +} + +static __always_inline int +atomic_sub_return_acquire(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_sub_return_acquire(i, v); +} + +static __always_inline int +atomic_sub_return_release(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_sub_return_release(i, v); +} + +static __always_inline int +atomic_sub_return_relaxed(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_sub_return_relaxed(i, v); +} + +static __always_inline int +atomic_fetch_sub(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_sub(i, v); +} + +static __always_inline int +atomic_fetch_sub_acquire(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_sub_acquire(i, v); +} + +static __always_inline int +atomic_fetch_sub_release(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_sub_release(i, v); +} + +static __always_inline int +atomic_fetch_sub_relaxed(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_sub_relaxed(i, v); +} + +static __always_inline void +atomic_inc(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_inc(v); +} + +static __always_inline int +atomic_inc_return(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_inc_return(v); +} + +static __always_inline int +atomic_inc_return_acquire(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_inc_return_acquire(v); +} + +static __always_inline int +atomic_inc_return_release(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_inc_return_release(v); +} + +static __always_inline int +atomic_inc_return_relaxed(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_inc_return_relaxed(v); +} + +static __always_inline int +atomic_fetch_inc(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_inc(v); +} + +static __always_inline int +atomic_fetch_inc_acquire(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_inc_acquire(v); +} + +static __always_inline int +atomic_fetch_inc_release(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_inc_release(v); +} + +static __always_inline int +atomic_fetch_inc_relaxed(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_inc_relaxed(v); +} + +static __always_inline void +atomic_dec(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_dec(v); +} + +static __always_inline int +atomic_dec_return(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_dec_return(v); +} + +static __always_inline int +atomic_dec_return_acquire(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_dec_return_acquire(v); +} + +static __always_inline int +atomic_dec_return_release(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_dec_return_release(v); +} + +static __always_inline int +atomic_dec_return_relaxed(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_dec_return_relaxed(v); +} + +static __always_inline int +atomic_fetch_dec(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_dec(v); +} + +static __always_inline int +atomic_fetch_dec_acquire(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_dec_acquire(v); +} + +static __always_inline int +atomic_fetch_dec_release(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_dec_release(v); +} + +static __always_inline int +atomic_fetch_dec_relaxed(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_dec_relaxed(v); +} + +static __always_inline void +atomic_and(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_and(i, v); +} + +static __always_inline int +atomic_fetch_and(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_and(i, v); +} + +static __always_inline int +atomic_fetch_and_acquire(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_and_acquire(i, v); +} + +static __always_inline int +atomic_fetch_and_release(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_and_release(i, v); +} + +static __always_inline int +atomic_fetch_and_relaxed(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_and_relaxed(i, v); +} + +static __always_inline void +atomic_andnot(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_andnot(i, v); +} + +static __always_inline int +atomic_fetch_andnot(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_andnot(i, v); +} + +static __always_inline int +atomic_fetch_andnot_acquire(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_andnot_acquire(i, v); +} + +static __always_inline int +atomic_fetch_andnot_release(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_andnot_release(i, v); +} + +static __always_inline int +atomic_fetch_andnot_relaxed(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_andnot_relaxed(i, v); +} + +static __always_inline void +atomic_or(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_or(i, v); +} + +static __always_inline int +atomic_fetch_or(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_or(i, v); +} + +static __always_inline int +atomic_fetch_or_acquire(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_or_acquire(i, v); +} + +static __always_inline int +atomic_fetch_or_release(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_or_release(i, v); +} + +static __always_inline int +atomic_fetch_or_relaxed(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_or_relaxed(i, v); +} + +static __always_inline void +atomic_xor(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_xor(i, v); +} + +static __always_inline int +atomic_fetch_xor(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_xor(i, v); +} + +static __always_inline int +atomic_fetch_xor_acquire(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_xor_acquire(i, v); +} + +static __always_inline int +atomic_fetch_xor_release(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_xor_release(i, v); +} + +static __always_inline int +atomic_fetch_xor_relaxed(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_xor_relaxed(i, v); +} + +static __always_inline int +atomic_xchg(atomic_t *v, int i) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_xchg(v, i); +} + +static __always_inline int +atomic_xchg_acquire(atomic_t *v, int i) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_xchg_acquire(v, i); +} + +static __always_inline int +atomic_xchg_release(atomic_t *v, int i) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_xchg_release(v, i); +} + +static __always_inline int +atomic_xchg_relaxed(atomic_t *v, int i) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_xchg_relaxed(v, i); +} + +static __always_inline int +atomic_cmpxchg(atomic_t *v, int old, int new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_cmpxchg(v, old, new); +} + +static __always_inline int +atomic_cmpxchg_acquire(atomic_t *v, int old, int new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_cmpxchg_acquire(v, old, new); +} + +static __always_inline int +atomic_cmpxchg_release(atomic_t *v, int old, int new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_cmpxchg_release(v, old, new); +} + +static __always_inline int +atomic_cmpxchg_relaxed(atomic_t *v, int old, int new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_cmpxchg_relaxed(v, old, new); +} + +static __always_inline bool +atomic_try_cmpxchg(atomic_t *v, int *old, int new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); + return arch_atomic_try_cmpxchg(v, old, new); +} + +static __always_inline bool +atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); + return arch_atomic_try_cmpxchg_acquire(v, old, new); +} + +static __always_inline bool +atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); + return arch_atomic_try_cmpxchg_release(v, old, new); +} + +static __always_inline bool +atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); + return arch_atomic_try_cmpxchg_relaxed(v, old, new); +} + +static __always_inline bool +atomic_sub_and_test(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_sub_and_test(i, v); +} + +static __always_inline bool +atomic_dec_and_test(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_dec_and_test(v); +} + +static __always_inline bool +atomic_inc_and_test(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_inc_and_test(v); +} + +static __always_inline bool +atomic_add_negative(int i, atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_add_negative(i, v); +} + +static __always_inline int +atomic_fetch_add_unless(atomic_t *v, int a, int u) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_fetch_add_unless(v, a, u); +} + +static __always_inline bool +atomic_add_unless(atomic_t *v, int a, int u) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_add_unless(v, a, u); +} + +static __always_inline bool +atomic_inc_not_zero(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_inc_not_zero(v); +} + +static __always_inline bool +atomic_inc_unless_negative(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_inc_unless_negative(v); +} + +static __always_inline bool +atomic_dec_unless_positive(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_dec_unless_positive(v); +} + +static __always_inline int +atomic_dec_if_positive(atomic_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_dec_if_positive(v); +} + +static __always_inline s64 +atomic64_read(const atomic64_t *v) +{ + instrument_atomic_read(v, sizeof(*v)); + return arch_atomic64_read(v); +} + +static __always_inline s64 +atomic64_read_acquire(const atomic64_t *v) +{ + instrument_atomic_read(v, sizeof(*v)); + return arch_atomic64_read_acquire(v); +} + +static __always_inline void +atomic64_set(atomic64_t *v, s64 i) +{ + instrument_atomic_write(v, sizeof(*v)); + arch_atomic64_set(v, i); +} + +static __always_inline void +atomic64_set_release(atomic64_t *v, s64 i) +{ + instrument_atomic_write(v, sizeof(*v)); + arch_atomic64_set_release(v, i); +} + +static __always_inline void +atomic64_add(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic64_add(i, v); +} + +static __always_inline s64 +atomic64_add_return(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_add_return(i, v); +} + +static __always_inline s64 +atomic64_add_return_acquire(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_add_return_acquire(i, v); +} + +static __always_inline s64 +atomic64_add_return_release(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_add_return_release(i, v); +} + +static __always_inline s64 +atomic64_add_return_relaxed(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_add_return_relaxed(i, v); +} + +static __always_inline s64 +atomic64_fetch_add(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_add(i, v); +} + +static __always_inline s64 +atomic64_fetch_add_acquire(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_add_acquire(i, v); +} + +static __always_inline s64 +atomic64_fetch_add_release(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_add_release(i, v); +} + +static __always_inline s64 +atomic64_fetch_add_relaxed(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_add_relaxed(i, v); +} + +static __always_inline void +atomic64_sub(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic64_sub(i, v); +} + +static __always_inline s64 +atomic64_sub_return(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_sub_return(i, v); +} + +static __always_inline s64 +atomic64_sub_return_acquire(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_sub_return_acquire(i, v); +} + +static __always_inline s64 +atomic64_sub_return_release(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_sub_return_release(i, v); +} + +static __always_inline s64 +atomic64_sub_return_relaxed(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_sub_return_relaxed(i, v); +} + +static __always_inline s64 +atomic64_fetch_sub(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_sub(i, v); +} + +static __always_inline s64 +atomic64_fetch_sub_acquire(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_sub_acquire(i, v); +} + +static __always_inline s64 +atomic64_fetch_sub_release(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_sub_release(i, v); +} + +static __always_inline s64 +atomic64_fetch_sub_relaxed(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_sub_relaxed(i, v); +} + +static __always_inline void +atomic64_inc(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic64_inc(v); +} + +static __always_inline s64 +atomic64_inc_return(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_inc_return(v); +} + +static __always_inline s64 +atomic64_inc_return_acquire(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_inc_return_acquire(v); +} + +static __always_inline s64 +atomic64_inc_return_release(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_inc_return_release(v); +} + +static __always_inline s64 +atomic64_inc_return_relaxed(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_inc_return_relaxed(v); +} + +static __always_inline s64 +atomic64_fetch_inc(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_inc(v); +} + +static __always_inline s64 +atomic64_fetch_inc_acquire(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_inc_acquire(v); +} + +static __always_inline s64 +atomic64_fetch_inc_release(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_inc_release(v); +} + +static __always_inline s64 +atomic64_fetch_inc_relaxed(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_inc_relaxed(v); +} + +static __always_inline void +atomic64_dec(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic64_dec(v); +} + +static __always_inline s64 +atomic64_dec_return(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_dec_return(v); +} + +static __always_inline s64 +atomic64_dec_return_acquire(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_dec_return_acquire(v); +} + +static __always_inline s64 +atomic64_dec_return_release(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_dec_return_release(v); +} + +static __always_inline s64 +atomic64_dec_return_relaxed(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_dec_return_relaxed(v); +} + +static __always_inline s64 +atomic64_fetch_dec(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_dec(v); +} + +static __always_inline s64 +atomic64_fetch_dec_acquire(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_dec_acquire(v); +} + +static __always_inline s64 +atomic64_fetch_dec_release(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_dec_release(v); +} + +static __always_inline s64 +atomic64_fetch_dec_relaxed(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_dec_relaxed(v); +} + +static __always_inline void +atomic64_and(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic64_and(i, v); +} + +static __always_inline s64 +atomic64_fetch_and(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_and(i, v); +} + +static __always_inline s64 +atomic64_fetch_and_acquire(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_and_acquire(i, v); +} + +static __always_inline s64 +atomic64_fetch_and_release(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_and_release(i, v); +} + +static __always_inline s64 +atomic64_fetch_and_relaxed(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_and_relaxed(i, v); +} + +static __always_inline void +atomic64_andnot(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic64_andnot(i, v); +} + +static __always_inline s64 +atomic64_fetch_andnot(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_andnot(i, v); +} + +static __always_inline s64 +atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_andnot_acquire(i, v); +} + +static __always_inline s64 +atomic64_fetch_andnot_release(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_andnot_release(i, v); +} + +static __always_inline s64 +atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_andnot_relaxed(i, v); +} + +static __always_inline void +atomic64_or(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic64_or(i, v); +} + +static __always_inline s64 +atomic64_fetch_or(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_or(i, v); +} + +static __always_inline s64 +atomic64_fetch_or_acquire(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_or_acquire(i, v); +} + +static __always_inline s64 +atomic64_fetch_or_release(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_or_release(i, v); +} + +static __always_inline s64 +atomic64_fetch_or_relaxed(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_or_relaxed(i, v); +} + +static __always_inline void +atomic64_xor(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic64_xor(i, v); +} + +static __always_inline s64 +atomic64_fetch_xor(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_xor(i, v); +} + +static __always_inline s64 +atomic64_fetch_xor_acquire(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_xor_acquire(i, v); +} + +static __always_inline s64 +atomic64_fetch_xor_release(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_xor_release(i, v); +} + +static __always_inline s64 +atomic64_fetch_xor_relaxed(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_xor_relaxed(i, v); +} + +static __always_inline s64 +atomic64_xchg(atomic64_t *v, s64 i) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_xchg(v, i); +} + +static __always_inline s64 +atomic64_xchg_acquire(atomic64_t *v, s64 i) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_xchg_acquire(v, i); +} + +static __always_inline s64 +atomic64_xchg_release(atomic64_t *v, s64 i) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_xchg_release(v, i); +} + +static __always_inline s64 +atomic64_xchg_relaxed(atomic64_t *v, s64 i) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_xchg_relaxed(v, i); +} + +static __always_inline s64 +atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_cmpxchg(v, old, new); +} + +static __always_inline s64 +atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_cmpxchg_acquire(v, old, new); +} + +static __always_inline s64 +atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_cmpxchg_release(v, old, new); +} + +static __always_inline s64 +atomic64_cmpxchg_relaxed(atomic64_t *v, s64 old, s64 new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_cmpxchg_relaxed(v, old, new); +} + +static __always_inline bool +atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); + return arch_atomic64_try_cmpxchg(v, old, new); +} + +static __always_inline bool +atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); + return arch_atomic64_try_cmpxchg_acquire(v, old, new); +} + +static __always_inline bool +atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); + return arch_atomic64_try_cmpxchg_release(v, old, new); +} + +static __always_inline bool +atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); + return arch_atomic64_try_cmpxchg_relaxed(v, old, new); +} + +static __always_inline bool +atomic64_sub_and_test(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_sub_and_test(i, v); +} + +static __always_inline bool +atomic64_dec_and_test(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_dec_and_test(v); +} + +static __always_inline bool +atomic64_inc_and_test(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_inc_and_test(v); +} + +static __always_inline bool +atomic64_add_negative(s64 i, atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_add_negative(i, v); +} + +static __always_inline s64 +atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_fetch_add_unless(v, a, u); +} + +static __always_inline bool +atomic64_add_unless(atomic64_t *v, s64 a, s64 u) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_add_unless(v, a, u); +} + +static __always_inline bool +atomic64_inc_not_zero(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_inc_not_zero(v); +} + +static __always_inline bool +atomic64_inc_unless_negative(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_inc_unless_negative(v); +} + +static __always_inline bool +atomic64_dec_unless_positive(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_dec_unless_positive(v); +} + +static __always_inline s64 +atomic64_dec_if_positive(atomic64_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic64_dec_if_positive(v); +} + +#define xchg(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_xchg(__ai_ptr, __VA_ARGS__); \ +}) + +#define xchg_acquire(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_xchg_acquire(__ai_ptr, __VA_ARGS__); \ +}) + +#define xchg_release(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_xchg_release(__ai_ptr, __VA_ARGS__); \ +}) + +#define xchg_relaxed(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_xchg_relaxed(__ai_ptr, __VA_ARGS__); \ +}) + +#define cmpxchg(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg(__ai_ptr, __VA_ARGS__); \ +}) + +#define cmpxchg_acquire(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg_acquire(__ai_ptr, __VA_ARGS__); \ +}) + +#define cmpxchg_release(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg_release(__ai_ptr, __VA_ARGS__); \ +}) + +#define cmpxchg_relaxed(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg_relaxed(__ai_ptr, __VA_ARGS__); \ +}) + +#define cmpxchg64(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg64(__ai_ptr, __VA_ARGS__); \ +}) + +#define cmpxchg64_acquire(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg64_acquire(__ai_ptr, __VA_ARGS__); \ +}) + +#define cmpxchg64_release(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg64_release(__ai_ptr, __VA_ARGS__); \ +}) + +#define cmpxchg64_relaxed(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg64_relaxed(__ai_ptr, __VA_ARGS__); \ +}) + +#define try_cmpxchg(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + +#define try_cmpxchg_acquire(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + +#define try_cmpxchg_release(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + +#define try_cmpxchg_relaxed(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + +#define cmpxchg_local(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg_local(__ai_ptr, __VA_ARGS__); \ +}) + +#define cmpxchg64_local(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_cmpxchg64_local(__ai_ptr, __VA_ARGS__); \ +}) + +#define sync_cmpxchg(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + arch_sync_cmpxchg(__ai_ptr, __VA_ARGS__); \ +}) + +#define cmpxchg_double(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, 2 * sizeof(*__ai_ptr)); \ + arch_cmpxchg_double(__ai_ptr, __VA_ARGS__); \ +}) + + +#define cmpxchg_double_local(ptr, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + instrument_atomic_write(__ai_ptr, 2 * sizeof(*__ai_ptr)); \ + arch_cmpxchg_double_local(__ai_ptr, __VA_ARGS__); \ +}) + +#endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ +// 5edd72f105b6f54b7e9492d794abee88e6912d29 diff --git a/include/linux/atomic/atomic-long.h b/include/linux/atomic/atomic-long.h new file mode 100644 index 000000000000..e40e480e175f --- /dev/null +++ b/include/linux/atomic/atomic-long.h @@ -0,0 +1,1014 @@ +// SPDX-License-Identifier: GPL-2.0 + +// Generated by scripts/atomic/gen-atomic-long.sh +// DO NOT MODIFY THIS FILE DIRECTLY + +#ifndef _LINUX_ATOMIC_LONG_H +#define _LINUX_ATOMIC_LONG_H + +#include +#include + +#ifdef CONFIG_64BIT +typedef atomic64_t atomic_long_t; +#define ATOMIC_LONG_INIT(i) ATOMIC64_INIT(i) +#define atomic_long_cond_read_acquire atomic64_cond_read_acquire +#define atomic_long_cond_read_relaxed atomic64_cond_read_relaxed +#else +typedef atomic_t atomic_long_t; +#define ATOMIC_LONG_INIT(i) ATOMIC_INIT(i) +#define atomic_long_cond_read_acquire atomic_cond_read_acquire +#define atomic_long_cond_read_relaxed atomic_cond_read_relaxed +#endif + +#ifdef CONFIG_64BIT + +static __always_inline long +atomic_long_read(const atomic_long_t *v) +{ + return atomic64_read(v); +} + +static __always_inline long +atomic_long_read_acquire(const atomic_long_t *v) +{ + return atomic64_read_acquire(v); +} + +static __always_inline void +atomic_long_set(atomic_long_t *v, long i) +{ + atomic64_set(v, i); +} + +static __always_inline void +atomic_long_set_release(atomic_long_t *v, long i) +{ + atomic64_set_release(v, i); +} + +static __always_inline void +atomic_long_add(long i, atomic_long_t *v) +{ + atomic64_add(i, v); +} + +static __always_inline long +atomic_long_add_return(long i, atomic_long_t *v) +{ + return atomic64_add_return(i, v); +} + +static __always_inline long +atomic_long_add_return_acquire(long i, atomic_long_t *v) +{ + return atomic64_add_return_acquire(i, v); +} + +static __always_inline long +atomic_long_add_return_release(long i, atomic_long_t *v) +{ + return atomic64_add_return_release(i, v); +} + +static __always_inline long +atomic_long_add_return_relaxed(long i, atomic_long_t *v) +{ + return atomic64_add_return_relaxed(i, v); +} + +static __always_inline long +atomic_long_fetch_add(long i, atomic_long_t *v) +{ + return atomic64_fetch_add(i, v); +} + +static __always_inline long +atomic_long_fetch_add_acquire(long i, atomic_long_t *v) +{ + return atomic64_fetch_add_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_add_release(long i, atomic_long_t *v) +{ + return atomic64_fetch_add_release(i, v); +} + +static __always_inline long +atomic_long_fetch_add_relaxed(long i, atomic_long_t *v) +{ + return atomic64_fetch_add_relaxed(i, v); +} + +static __always_inline void +atomic_long_sub(long i, atomic_long_t *v) +{ + atomic64_sub(i, v); +} + +static __always_inline long +atomic_long_sub_return(long i, atomic_long_t *v) +{ + return atomic64_sub_return(i, v); +} + +static __always_inline long +atomic_long_sub_return_acquire(long i, atomic_long_t *v) +{ + return atomic64_sub_return_acquire(i, v); +} + +static __always_inline long +atomic_long_sub_return_release(long i, atomic_long_t *v) +{ + return atomic64_sub_return_release(i, v); +} + +static __always_inline long +atomic_long_sub_return_relaxed(long i, atomic_long_t *v) +{ + return atomic64_sub_return_relaxed(i, v); +} + +static __always_inline long +atomic_long_fetch_sub(long i, atomic_long_t *v) +{ + return atomic64_fetch_sub(i, v); +} + +static __always_inline long +atomic_long_fetch_sub_acquire(long i, atomic_long_t *v) +{ + return atomic64_fetch_sub_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_sub_release(long i, atomic_long_t *v) +{ + return atomic64_fetch_sub_release(i, v); +} + +static __always_inline long +atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v) +{ + return atomic64_fetch_sub_relaxed(i, v); +} + +static __always_inline void +atomic_long_inc(atomic_long_t *v) +{ + atomic64_inc(v); +} + +static __always_inline long +atomic_long_inc_return(atomic_long_t *v) +{ + return atomic64_inc_return(v); +} + +static __always_inline long +atomic_long_inc_return_acquire(atomic_long_t *v) +{ + return atomic64_inc_return_acquire(v); +} + +static __always_inline long +atomic_long_inc_return_release(atomic_long_t *v) +{ + return atomic64_inc_return_release(v); +} + +static __always_inline long +atomic_long_inc_return_relaxed(atomic_long_t *v) +{ + return atomic64_inc_return_relaxed(v); +} + +static __always_inline long +atomic_long_fetch_inc(atomic_long_t *v) +{ + return atomic64_fetch_inc(v); +} + +static __always_inline long +atomic_long_fetch_inc_acquire(atomic_long_t *v) +{ + return atomic64_fetch_inc_acquire(v); +} + +static __always_inline long +atomic_long_fetch_inc_release(atomic_long_t *v) +{ + return atomic64_fetch_inc_release(v); +} + +static __always_inline long +atomic_long_fetch_inc_relaxed(atomic_long_t *v) +{ + return atomic64_fetch_inc_relaxed(v); +} + +static __always_inline void +atomic_long_dec(atomic_long_t *v) +{ + atomic64_dec(v); +} + +static __always_inline long +atomic_long_dec_return(atomic_long_t *v) +{ + return atomic64_dec_return(v); +} + +static __always_inline long +atomic_long_dec_return_acquire(atomic_long_t *v) +{ + return atomic64_dec_return_acquire(v); +} + +static __always_inline long +atomic_long_dec_return_release(atomic_long_t *v) +{ + return atomic64_dec_return_release(v); +} + +static __always_inline long +atomic_long_dec_return_relaxed(atomic_long_t *v) +{ + return atomic64_dec_return_relaxed(v); +} + +static __always_inline long +atomic_long_fetch_dec(atomic_long_t *v) +{ + return atomic64_fetch_dec(v); +} + +static __always_inline long +atomic_long_fetch_dec_acquire(atomic_long_t *v) +{ + return atomic64_fetch_dec_acquire(v); +} + +static __always_inline long +atomic_long_fetch_dec_release(atomic_long_t *v) +{ + return atomic64_fetch_dec_release(v); +} + +static __always_inline long +atomic_long_fetch_dec_relaxed(atomic_long_t *v) +{ + return atomic64_fetch_dec_relaxed(v); +} + +static __always_inline void +atomic_long_and(long i, atomic_long_t *v) +{ + atomic64_and(i, v); +} + +static __always_inline long +atomic_long_fetch_and(long i, atomic_long_t *v) +{ + return atomic64_fetch_and(i, v); +} + +static __always_inline long +atomic_long_fetch_and_acquire(long i, atomic_long_t *v) +{ + return atomic64_fetch_and_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_and_release(long i, atomic_long_t *v) +{ + return atomic64_fetch_and_release(i, v); +} + +static __always_inline long +atomic_long_fetch_and_relaxed(long i, atomic_long_t *v) +{ + return atomic64_fetch_and_relaxed(i, v); +} + +static __always_inline void +atomic_long_andnot(long i, atomic_long_t *v) +{ + atomic64_andnot(i, v); +} + +static __always_inline long +atomic_long_fetch_andnot(long i, atomic_long_t *v) +{ + return atomic64_fetch_andnot(i, v); +} + +static __always_inline long +atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v) +{ + return atomic64_fetch_andnot_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_andnot_release(long i, atomic_long_t *v) +{ + return atomic64_fetch_andnot_release(i, v); +} + +static __always_inline long +atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v) +{ + return atomic64_fetch_andnot_relaxed(i, v); +} + +static __always_inline void +atomic_long_or(long i, atomic_long_t *v) +{ + atomic64_or(i, v); +} + +static __always_inline long +atomic_long_fetch_or(long i, atomic_long_t *v) +{ + return atomic64_fetch_or(i, v); +} + +static __always_inline long +atomic_long_fetch_or_acquire(long i, atomic_long_t *v) +{ + return atomic64_fetch_or_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_or_release(long i, atomic_long_t *v) +{ + return atomic64_fetch_or_release(i, v); +} + +static __always_inline long +atomic_long_fetch_or_relaxed(long i, atomic_long_t *v) +{ + return atomic64_fetch_or_relaxed(i, v); +} + +static __always_inline void +atomic_long_xor(long i, atomic_long_t *v) +{ + atomic64_xor(i, v); +} + +static __always_inline long +atomic_long_fetch_xor(long i, atomic_long_t *v) +{ + return atomic64_fetch_xor(i, v); +} + +static __always_inline long +atomic_long_fetch_xor_acquire(long i, atomic_long_t *v) +{ + return atomic64_fetch_xor_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_xor_release(long i, atomic_long_t *v) +{ + return atomic64_fetch_xor_release(i, v); +} + +static __always_inline long +atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v) +{ + return atomic64_fetch_xor_relaxed(i, v); +} + +static __always_inline long +atomic_long_xchg(atomic_long_t *v, long i) +{ + return atomic64_xchg(v, i); +} + +static __always_inline long +atomic_long_xchg_acquire(atomic_long_t *v, long i) +{ + return atomic64_xchg_acquire(v, i); +} + +static __always_inline long +atomic_long_xchg_release(atomic_long_t *v, long i) +{ + return atomic64_xchg_release(v, i); +} + +static __always_inline long +atomic_long_xchg_relaxed(atomic_long_t *v, long i) +{ + return atomic64_xchg_relaxed(v, i); +} + +static __always_inline long +atomic_long_cmpxchg(atomic_long_t *v, long old, long new) +{ + return atomic64_cmpxchg(v, old, new); +} + +static __always_inline long +atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new) +{ + return atomic64_cmpxchg_acquire(v, old, new); +} + +static __always_inline long +atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new) +{ + return atomic64_cmpxchg_release(v, old, new); +} + +static __always_inline long +atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new) +{ + return atomic64_cmpxchg_relaxed(v, old, new); +} + +static __always_inline bool +atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new) +{ + return atomic64_try_cmpxchg(v, (s64 *)old, new); +} + +static __always_inline bool +atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new) +{ + return atomic64_try_cmpxchg_acquire(v, (s64 *)old, new); +} + +static __always_inline bool +atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new) +{ + return atomic64_try_cmpxchg_release(v, (s64 *)old, new); +} + +static __always_inline bool +atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) +{ + return atomic64_try_cmpxchg_relaxed(v, (s64 *)old, new); +} + +static __always_inline bool +atomic_long_sub_and_test(long i, atomic_long_t *v) +{ + return atomic64_sub_and_test(i, v); +} + +static __always_inline bool +atomic_long_dec_and_test(atomic_long_t *v) +{ + return atomic64_dec_and_test(v); +} + +static __always_inline bool +atomic_long_inc_and_test(atomic_long_t *v) +{ + return atomic64_inc_and_test(v); +} + +static __always_inline bool +atomic_long_add_negative(long i, atomic_long_t *v) +{ + return atomic64_add_negative(i, v); +} + +static __always_inline long +atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) +{ + return atomic64_fetch_add_unless(v, a, u); +} + +static __always_inline bool +atomic_long_add_unless(atomic_long_t *v, long a, long u) +{ + return atomic64_add_unless(v, a, u); +} + +static __always_inline bool +atomic_long_inc_not_zero(atomic_long_t *v) +{ + return atomic64_inc_not_zero(v); +} + +static __always_inline bool +atomic_long_inc_unless_negative(atomic_long_t *v) +{ + return atomic64_inc_unless_negative(v); +} + +static __always_inline bool +atomic_long_dec_unless_positive(atomic_long_t *v) +{ + return atomic64_dec_unless_positive(v); +} + +static __always_inline long +atomic_long_dec_if_positive(atomic_long_t *v) +{ + return atomic64_dec_if_positive(v); +} + +#else /* CONFIG_64BIT */ + +static __always_inline long +atomic_long_read(const atomic_long_t *v) +{ + return atomic_read(v); +} + +static __always_inline long +atomic_long_read_acquire(const atomic_long_t *v) +{ + return atomic_read_acquire(v); +} + +static __always_inline void +atomic_long_set(atomic_long_t *v, long i) +{ + atomic_set(v, i); +} + +static __always_inline void +atomic_long_set_release(atomic_long_t *v, long i) +{ + atomic_set_release(v, i); +} + +static __always_inline void +atomic_long_add(long i, atomic_long_t *v) +{ + atomic_add(i, v); +} + +static __always_inline long +atomic_long_add_return(long i, atomic_long_t *v) +{ + return atomic_add_return(i, v); +} + +static __always_inline long +atomic_long_add_return_acquire(long i, atomic_long_t *v) +{ + return atomic_add_return_acquire(i, v); +} + +static __always_inline long +atomic_long_add_return_release(long i, atomic_long_t *v) +{ + return atomic_add_return_release(i, v); +} + +static __always_inline long +atomic_long_add_return_relaxed(long i, atomic_long_t *v) +{ + return atomic_add_return_relaxed(i, v); +} + +static __always_inline long +atomic_long_fetch_add(long i, atomic_long_t *v) +{ + return atomic_fetch_add(i, v); +} + +static __always_inline long +atomic_long_fetch_add_acquire(long i, atomic_long_t *v) +{ + return atomic_fetch_add_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_add_release(long i, atomic_long_t *v) +{ + return atomic_fetch_add_release(i, v); +} + +static __always_inline long +atomic_long_fetch_add_relaxed(long i, atomic_long_t *v) +{ + return atomic_fetch_add_relaxed(i, v); +} + +static __always_inline void +atomic_long_sub(long i, atomic_long_t *v) +{ + atomic_sub(i, v); +} + +static __always_inline long +atomic_long_sub_return(long i, atomic_long_t *v) +{ + return atomic_sub_return(i, v); +} + +static __always_inline long +atomic_long_sub_return_acquire(long i, atomic_long_t *v) +{ + return atomic_sub_return_acquire(i, v); +} + +static __always_inline long +atomic_long_sub_return_release(long i, atomic_long_t *v) +{ + return atomic_sub_return_release(i, v); +} + +static __always_inline long +atomic_long_sub_return_relaxed(long i, atomic_long_t *v) +{ + return atomic_sub_return_relaxed(i, v); +} + +static __always_inline long +atomic_long_fetch_sub(long i, atomic_long_t *v) +{ + return atomic_fetch_sub(i, v); +} + +static __always_inline long +atomic_long_fetch_sub_acquire(long i, atomic_long_t *v) +{ + return atomic_fetch_sub_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_sub_release(long i, atomic_long_t *v) +{ + return atomic_fetch_sub_release(i, v); +} + +static __always_inline long +atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v) +{ + return atomic_fetch_sub_relaxed(i, v); +} + +static __always_inline void +atomic_long_inc(atomic_long_t *v) +{ + atomic_inc(v); +} + +static __always_inline long +atomic_long_inc_return(atomic_long_t *v) +{ + return atomic_inc_return(v); +} + +static __always_inline long +atomic_long_inc_return_acquire(atomic_long_t *v) +{ + return atomic_inc_return_acquire(v); +} + +static __always_inline long +atomic_long_inc_return_release(atomic_long_t *v) +{ + return atomic_inc_return_release(v); +} + +static __always_inline long +atomic_long_inc_return_relaxed(atomic_long_t *v) +{ + return atomic_inc_return_relaxed(v); +} + +static __always_inline long +atomic_long_fetch_inc(atomic_long_t *v) +{ + return atomic_fetch_inc(v); +} + +static __always_inline long +atomic_long_fetch_inc_acquire(atomic_long_t *v) +{ + return atomic_fetch_inc_acquire(v); +} + +static __always_inline long +atomic_long_fetch_inc_release(atomic_long_t *v) +{ + return atomic_fetch_inc_release(v); +} + +static __always_inline long +atomic_long_fetch_inc_relaxed(atomic_long_t *v) +{ + return atomic_fetch_inc_relaxed(v); +} + +static __always_inline void +atomic_long_dec(atomic_long_t *v) +{ + atomic_dec(v); +} + +static __always_inline long +atomic_long_dec_return(atomic_long_t *v) +{ + return atomic_dec_return(v); +} + +static __always_inline long +atomic_long_dec_return_acquire(atomic_long_t *v) +{ + return atomic_dec_return_acquire(v); +} + +static __always_inline long +atomic_long_dec_return_release(atomic_long_t *v) +{ + return atomic_dec_return_release(v); +} + +static __always_inline long +atomic_long_dec_return_relaxed(atomic_long_t *v) +{ + return atomic_dec_return_relaxed(v); +} + +static __always_inline long +atomic_long_fetch_dec(atomic_long_t *v) +{ + return atomic_fetch_dec(v); +} + +static __always_inline long +atomic_long_fetch_dec_acquire(atomic_long_t *v) +{ + return atomic_fetch_dec_acquire(v); +} + +static __always_inline long +atomic_long_fetch_dec_release(atomic_long_t *v) +{ + return atomic_fetch_dec_release(v); +} + +static __always_inline long +atomic_long_fetch_dec_relaxed(atomic_long_t *v) +{ + return atomic_fetch_dec_relaxed(v); +} + +static __always_inline void +atomic_long_and(long i, atomic_long_t *v) +{ + atomic_and(i, v); +} + +static __always_inline long +atomic_long_fetch_and(long i, atomic_long_t *v) +{ + return atomic_fetch_and(i, v); +} + +static __always_inline long +atomic_long_fetch_and_acquire(long i, atomic_long_t *v) +{ + return atomic_fetch_and_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_and_release(long i, atomic_long_t *v) +{ + return atomic_fetch_and_release(i, v); +} + +static __always_inline long +atomic_long_fetch_and_relaxed(long i, atomic_long_t *v) +{ + return atomic_fetch_and_relaxed(i, v); +} + +static __always_inline void +atomic_long_andnot(long i, atomic_long_t *v) +{ + atomic_andnot(i, v); +} + +static __always_inline long +atomic_long_fetch_andnot(long i, atomic_long_t *v) +{ + return atomic_fetch_andnot(i, v); +} + +static __always_inline long +atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v) +{ + return atomic_fetch_andnot_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_andnot_release(long i, atomic_long_t *v) +{ + return atomic_fetch_andnot_release(i, v); +} + +static __always_inline long +atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v) +{ + return atomic_fetch_andnot_relaxed(i, v); +} + +static __always_inline void +atomic_long_or(long i, atomic_long_t *v) +{ + atomic_or(i, v); +} + +static __always_inline long +atomic_long_fetch_or(long i, atomic_long_t *v) +{ + return atomic_fetch_or(i, v); +} + +static __always_inline long +atomic_long_fetch_or_acquire(long i, atomic_long_t *v) +{ + return atomic_fetch_or_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_or_release(long i, atomic_long_t *v) +{ + return atomic_fetch_or_release(i, v); +} + +static __always_inline long +atomic_long_fetch_or_relaxed(long i, atomic_long_t *v) +{ + return atomic_fetch_or_relaxed(i, v); +} + +static __always_inline void +atomic_long_xor(long i, atomic_long_t *v) +{ + atomic_xor(i, v); +} + +static __always_inline long +atomic_long_fetch_xor(long i, atomic_long_t *v) +{ + return atomic_fetch_xor(i, v); +} + +static __always_inline long +atomic_long_fetch_xor_acquire(long i, atomic_long_t *v) +{ + return atomic_fetch_xor_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_xor_release(long i, atomic_long_t *v) +{ + return atomic_fetch_xor_release(i, v); +} + +static __always_inline long +atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v) +{ + return atomic_fetch_xor_relaxed(i, v); +} + +static __always_inline long +atomic_long_xchg(atomic_long_t *v, long i) +{ + return atomic_xchg(v, i); +} + +static __always_inline long +atomic_long_xchg_acquire(atomic_long_t *v, long i) +{ + return atomic_xchg_acquire(v, i); +} + +static __always_inline long +atomic_long_xchg_release(atomic_long_t *v, long i) +{ + return atomic_xchg_release(v, i); +} + +static __always_inline long +atomic_long_xchg_relaxed(atomic_long_t *v, long i) +{ + return atomic_xchg_relaxed(v, i); +} + +static __always_inline long +atomic_long_cmpxchg(atomic_long_t *v, long old, long new) +{ + return atomic_cmpxchg(v, old, new); +} + +static __always_inline long +atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new) +{ + return atomic_cmpxchg_acquire(v, old, new); +} + +static __always_inline long +atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new) +{ + return atomic_cmpxchg_release(v, old, new); +} + +static __always_inline long +atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new) +{ + return atomic_cmpxchg_relaxed(v, old, new); +} + +static __always_inline bool +atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new) +{ + return atomic_try_cmpxchg(v, (int *)old, new); +} + +static __always_inline bool +atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new) +{ + return atomic_try_cmpxchg_acquire(v, (int *)old, new); +} + +static __always_inline bool +atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new) +{ + return atomic_try_cmpxchg_release(v, (int *)old, new); +} + +static __always_inline bool +atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) +{ + return atomic_try_cmpxchg_relaxed(v, (int *)old, new); +} + +static __always_inline bool +atomic_long_sub_and_test(long i, atomic_long_t *v) +{ + return atomic_sub_and_test(i, v); +} + +static __always_inline bool +atomic_long_dec_and_test(atomic_long_t *v) +{ + return atomic_dec_and_test(v); +} + +static __always_inline bool +atomic_long_inc_and_test(atomic_long_t *v) +{ + return atomic_inc_and_test(v); +} + +static __always_inline bool +atomic_long_add_negative(long i, atomic_long_t *v) +{ + return atomic_add_negative(i, v); +} + +static __always_inline long +atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) +{ + return atomic_fetch_add_unless(v, a, u); +} + +static __always_inline bool +atomic_long_add_unless(atomic_long_t *v, long a, long u) +{ + return atomic_add_unless(v, a, u); +} + +static __always_inline bool +atomic_long_inc_not_zero(atomic_long_t *v) +{ + return atomic_inc_not_zero(v); +} + +static __always_inline bool +atomic_long_inc_unless_negative(atomic_long_t *v) +{ + return atomic_inc_unless_negative(v); +} + +static __always_inline bool +atomic_long_dec_unless_positive(atomic_long_t *v) +{ + return atomic_dec_unless_positive(v); +} + +static __always_inline long +atomic_long_dec_if_positive(atomic_long_t *v) +{ + return atomic_dec_if_positive(v); +} + +#endif /* CONFIG_64BIT */ +#endif /* _LINUX_ATOMIC_LONG_H */ +// c5552b5d78a0c7584dfd03cba985e78a1a86bbed -- cgit v1.2.3 From 67d1b0de258ad066e1fc85d0ceaa75e107fb45bb Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Tue, 13 Jul 2021 11:52:52 +0100 Subject: locking/atomic: add arch_atomic_long*() Now that all architectures provide arch_{atomic,atomic64}_*(), we can build arch_atomic_long_*() atop these, which can be safely used in noinstr code. The regular atomic_long_*() wrappers are built atop these, as we do for {atomic,atomic64}_*() atop arch_{atomic,atomic64}_*(). We don't provide arch_* versions of the cond_read*() variants, as we don't have arch_* versions of the underlying atomic/atomic64 functions (nor the smp_cond_load*() helpers these are typically based on). Note that the headers in this patch under include/linux/atomic/ are generated by the scripts in scripts/atomic/. Signed-off-by: Mark Rutland Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20210713105253.7615-5-mark.rutland@arm.com --- include/linux/atomic.h | 2 +- include/linux/atomic/atomic-instrumented.h | 580 ++++++++++++++++++++++++- include/linux/atomic/atomic-long.h | 658 ++++++++++++++--------------- 3 files changed, 909 insertions(+), 331 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 1896a58b5aba..8dd57c3a99e9 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -78,7 +78,7 @@ }) #include -#include #include +#include #endif /* _LINUX_ATOMIC_H */ diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h index f6fe36c428df..a0f654370da3 100644 --- a/include/linux/atomic/atomic-instrumented.h +++ b/include/linux/atomic/atomic-instrumented.h @@ -1177,6 +1177,584 @@ atomic64_dec_if_positive(atomic64_t *v) return arch_atomic64_dec_if_positive(v); } +static __always_inline long +atomic_long_read(const atomic_long_t *v) +{ + instrument_atomic_read(v, sizeof(*v)); + return arch_atomic_long_read(v); +} + +static __always_inline long +atomic_long_read_acquire(const atomic_long_t *v) +{ + instrument_atomic_read(v, sizeof(*v)); + return arch_atomic_long_read_acquire(v); +} + +static __always_inline void +atomic_long_set(atomic_long_t *v, long i) +{ + instrument_atomic_write(v, sizeof(*v)); + arch_atomic_long_set(v, i); +} + +static __always_inline void +atomic_long_set_release(atomic_long_t *v, long i) +{ + instrument_atomic_write(v, sizeof(*v)); + arch_atomic_long_set_release(v, i); +} + +static __always_inline void +atomic_long_add(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_long_add(i, v); +} + +static __always_inline long +atomic_long_add_return(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_add_return(i, v); +} + +static __always_inline long +atomic_long_add_return_acquire(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_add_return_acquire(i, v); +} + +static __always_inline long +atomic_long_add_return_release(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_add_return_release(i, v); +} + +static __always_inline long +atomic_long_add_return_relaxed(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_add_return_relaxed(i, v); +} + +static __always_inline long +atomic_long_fetch_add(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_add(i, v); +} + +static __always_inline long +atomic_long_fetch_add_acquire(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_add_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_add_release(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_add_release(i, v); +} + +static __always_inline long +atomic_long_fetch_add_relaxed(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_add_relaxed(i, v); +} + +static __always_inline void +atomic_long_sub(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_long_sub(i, v); +} + +static __always_inline long +atomic_long_sub_return(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_sub_return(i, v); +} + +static __always_inline long +atomic_long_sub_return_acquire(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_sub_return_acquire(i, v); +} + +static __always_inline long +atomic_long_sub_return_release(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_sub_return_release(i, v); +} + +static __always_inline long +atomic_long_sub_return_relaxed(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_sub_return_relaxed(i, v); +} + +static __always_inline long +atomic_long_fetch_sub(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_sub(i, v); +} + +static __always_inline long +atomic_long_fetch_sub_acquire(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_sub_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_sub_release(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_sub_release(i, v); +} + +static __always_inline long +atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_sub_relaxed(i, v); +} + +static __always_inline void +atomic_long_inc(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_long_inc(v); +} + +static __always_inline long +atomic_long_inc_return(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_inc_return(v); +} + +static __always_inline long +atomic_long_inc_return_acquire(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_inc_return_acquire(v); +} + +static __always_inline long +atomic_long_inc_return_release(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_inc_return_release(v); +} + +static __always_inline long +atomic_long_inc_return_relaxed(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_inc_return_relaxed(v); +} + +static __always_inline long +atomic_long_fetch_inc(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_inc(v); +} + +static __always_inline long +atomic_long_fetch_inc_acquire(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_inc_acquire(v); +} + +static __always_inline long +atomic_long_fetch_inc_release(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_inc_release(v); +} + +static __always_inline long +atomic_long_fetch_inc_relaxed(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_inc_relaxed(v); +} + +static __always_inline void +atomic_long_dec(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_long_dec(v); +} + +static __always_inline long +atomic_long_dec_return(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_dec_return(v); +} + +static __always_inline long +atomic_long_dec_return_acquire(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_dec_return_acquire(v); +} + +static __always_inline long +atomic_long_dec_return_release(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_dec_return_release(v); +} + +static __always_inline long +atomic_long_dec_return_relaxed(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_dec_return_relaxed(v); +} + +static __always_inline long +atomic_long_fetch_dec(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_dec(v); +} + +static __always_inline long +atomic_long_fetch_dec_acquire(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_dec_acquire(v); +} + +static __always_inline long +atomic_long_fetch_dec_release(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_dec_release(v); +} + +static __always_inline long +atomic_long_fetch_dec_relaxed(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_dec_relaxed(v); +} + +static __always_inline void +atomic_long_and(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_long_and(i, v); +} + +static __always_inline long +atomic_long_fetch_and(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_and(i, v); +} + +static __always_inline long +atomic_long_fetch_and_acquire(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_and_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_and_release(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_and_release(i, v); +} + +static __always_inline long +atomic_long_fetch_and_relaxed(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_and_relaxed(i, v); +} + +static __always_inline void +atomic_long_andnot(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_long_andnot(i, v); +} + +static __always_inline long +atomic_long_fetch_andnot(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_andnot(i, v); +} + +static __always_inline long +atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_andnot_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_andnot_release(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_andnot_release(i, v); +} + +static __always_inline long +atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_andnot_relaxed(i, v); +} + +static __always_inline void +atomic_long_or(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_long_or(i, v); +} + +static __always_inline long +atomic_long_fetch_or(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_or(i, v); +} + +static __always_inline long +atomic_long_fetch_or_acquire(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_or_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_or_release(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_or_release(i, v); +} + +static __always_inline long +atomic_long_fetch_or_relaxed(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_or_relaxed(i, v); +} + +static __always_inline void +atomic_long_xor(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + arch_atomic_long_xor(i, v); +} + +static __always_inline long +atomic_long_fetch_xor(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_xor(i, v); +} + +static __always_inline long +atomic_long_fetch_xor_acquire(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_xor_acquire(i, v); +} + +static __always_inline long +atomic_long_fetch_xor_release(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_xor_release(i, v); +} + +static __always_inline long +atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_xor_relaxed(i, v); +} + +static __always_inline long +atomic_long_xchg(atomic_long_t *v, long i) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_xchg(v, i); +} + +static __always_inline long +atomic_long_xchg_acquire(atomic_long_t *v, long i) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_xchg_acquire(v, i); +} + +static __always_inline long +atomic_long_xchg_release(atomic_long_t *v, long i) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_xchg_release(v, i); +} + +static __always_inline long +atomic_long_xchg_relaxed(atomic_long_t *v, long i) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_xchg_relaxed(v, i); +} + +static __always_inline long +atomic_long_cmpxchg(atomic_long_t *v, long old, long new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_cmpxchg(v, old, new); +} + +static __always_inline long +atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_cmpxchg_acquire(v, old, new); +} + +static __always_inline long +atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_cmpxchg_release(v, old, new); +} + +static __always_inline long +atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_cmpxchg_relaxed(v, old, new); +} + +static __always_inline bool +atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); + return arch_atomic_long_try_cmpxchg(v, old, new); +} + +static __always_inline bool +atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); + return arch_atomic_long_try_cmpxchg_acquire(v, old, new); +} + +static __always_inline bool +atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); + return arch_atomic_long_try_cmpxchg_release(v, old, new); +} + +static __always_inline bool +atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) +{ + instrument_atomic_read_write(v, sizeof(*v)); + instrument_atomic_read_write(old, sizeof(*old)); + return arch_atomic_long_try_cmpxchg_relaxed(v, old, new); +} + +static __always_inline bool +atomic_long_sub_and_test(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_sub_and_test(i, v); +} + +static __always_inline bool +atomic_long_dec_and_test(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_dec_and_test(v); +} + +static __always_inline bool +atomic_long_inc_and_test(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_inc_and_test(v); +} + +static __always_inline bool +atomic_long_add_negative(long i, atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_add_negative(i, v); +} + +static __always_inline long +atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_fetch_add_unless(v, a, u); +} + +static __always_inline bool +atomic_long_add_unless(atomic_long_t *v, long a, long u) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_add_unless(v, a, u); +} + +static __always_inline bool +atomic_long_inc_not_zero(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_inc_not_zero(v); +} + +static __always_inline bool +atomic_long_inc_unless_negative(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_inc_unless_negative(v); +} + +static __always_inline bool +atomic_long_dec_unless_positive(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_dec_unless_positive(v); +} + +static __always_inline long +atomic_long_dec_if_positive(atomic_long_t *v) +{ + instrument_atomic_read_write(v, sizeof(*v)); + return arch_atomic_long_dec_if_positive(v); +} + #define xchg(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ @@ -1334,4 +1912,4 @@ atomic64_dec_if_positive(atomic64_t *v) }) #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ -// 5edd72f105b6f54b7e9492d794abee88e6912d29 +// 2a9553f0a9d5619f19151092df5cabbbf16ce835 diff --git a/include/linux/atomic/atomic-long.h b/include/linux/atomic/atomic-long.h index e40e480e175f..800b8c35992d 100644 --- a/include/linux/atomic/atomic-long.h +++ b/include/linux/atomic/atomic-long.h @@ -24,991 +24,991 @@ typedef atomic_t atomic_long_t; #ifdef CONFIG_64BIT static __always_inline long -atomic_long_read(const atomic_long_t *v) +arch_atomic_long_read(const atomic_long_t *v) { - return atomic64_read(v); + return arch_atomic64_read(v); } static __always_inline long -atomic_long_read_acquire(const atomic_long_t *v) +arch_atomic_long_read_acquire(const atomic_long_t *v) { - return atomic64_read_acquire(v); + return arch_atomic64_read_acquire(v); } static __always_inline void -atomic_long_set(atomic_long_t *v, long i) +arch_atomic_long_set(atomic_long_t *v, long i) { - atomic64_set(v, i); + arch_atomic64_set(v, i); } static __always_inline void -atomic_long_set_release(atomic_long_t *v, long i) +arch_atomic_long_set_release(atomic_long_t *v, long i) { - atomic64_set_release(v, i); + arch_atomic64_set_release(v, i); } static __always_inline void -atomic_long_add(long i, atomic_long_t *v) +arch_atomic_long_add(long i, atomic_long_t *v) { - atomic64_add(i, v); + arch_atomic64_add(i, v); } static __always_inline long -atomic_long_add_return(long i, atomic_long_t *v) +arch_atomic_long_add_return(long i, atomic_long_t *v) { - return atomic64_add_return(i, v); + return arch_atomic64_add_return(i, v); } static __always_inline long -atomic_long_add_return_acquire(long i, atomic_long_t *v) +arch_atomic_long_add_return_acquire(long i, atomic_long_t *v) { - return atomic64_add_return_acquire(i, v); + return arch_atomic64_add_return_acquire(i, v); } static __always_inline long -atomic_long_add_return_release(long i, atomic_long_t *v) +arch_atomic_long_add_return_release(long i, atomic_long_t *v) { - return atomic64_add_return_release(i, v); + return arch_atomic64_add_return_release(i, v); } static __always_inline long -atomic_long_add_return_relaxed(long i, atomic_long_t *v) +arch_atomic_long_add_return_relaxed(long i, atomic_long_t *v) { - return atomic64_add_return_relaxed(i, v); + return arch_atomic64_add_return_relaxed(i, v); } static __always_inline long -atomic_long_fetch_add(long i, atomic_long_t *v) +arch_atomic_long_fetch_add(long i, atomic_long_t *v) { - return atomic64_fetch_add(i, v); + return arch_atomic64_fetch_add(i, v); } static __always_inline long -atomic_long_fetch_add_acquire(long i, atomic_long_t *v) +arch_atomic_long_fetch_add_acquire(long i, atomic_long_t *v) { - return atomic64_fetch_add_acquire(i, v); + return arch_atomic64_fetch_add_acquire(i, v); } static __always_inline long -atomic_long_fetch_add_release(long i, atomic_long_t *v) +arch_atomic_long_fetch_add_release(long i, atomic_long_t *v) { - return atomic64_fetch_add_release(i, v); + return arch_atomic64_fetch_add_release(i, v); } static __always_inline long -atomic_long_fetch_add_relaxed(long i, atomic_long_t *v) +arch_atomic_long_fetch_add_relaxed(long i, atomic_long_t *v) { - return atomic64_fetch_add_relaxed(i, v); + return arch_atomic64_fetch_add_relaxed(i, v); } static __always_inline void -atomic_long_sub(long i, atomic_long_t *v) +arch_atomic_long_sub(long i, atomic_long_t *v) { - atomic64_sub(i, v); + arch_atomic64_sub(i, v); } static __always_inline long -atomic_long_sub_return(long i, atomic_long_t *v) +arch_atomic_long_sub_return(long i, atomic_long_t *v) { - return atomic64_sub_return(i, v); + return arch_atomic64_sub_return(i, v); } static __always_inline long -atomic_long_sub_return_acquire(long i, atomic_long_t *v) +arch_atomic_long_sub_return_acquire(long i, atomic_long_t *v) { - return atomic64_sub_return_acquire(i, v); + return arch_atomic64_sub_return_acquire(i, v); } static __always_inline long -atomic_long_sub_return_release(long i, atomic_long_t *v) +arch_atomic_long_sub_return_release(long i, atomic_long_t *v) { - return atomic64_sub_return_release(i, v); + return arch_atomic64_sub_return_release(i, v); } static __always_inline long -atomic_long_sub_return_relaxed(long i, atomic_long_t *v) +arch_atomic_long_sub_return_relaxed(long i, atomic_long_t *v) { - return atomic64_sub_return_relaxed(i, v); + return arch_atomic64_sub_return_relaxed(i, v); } static __always_inline long -atomic_long_fetch_sub(long i, atomic_long_t *v) +arch_atomic_long_fetch_sub(long i, atomic_long_t *v) { - return atomic64_fetch_sub(i, v); + return arch_atomic64_fetch_sub(i, v); } static __always_inline long -atomic_long_fetch_sub_acquire(long i, atomic_long_t *v) +arch_atomic_long_fetch_sub_acquire(long i, atomic_long_t *v) { - return atomic64_fetch_sub_acquire(i, v); + return arch_atomic64_fetch_sub_acquire(i, v); } static __always_inline long -atomic_long_fetch_sub_release(long i, atomic_long_t *v) +arch_atomic_long_fetch_sub_release(long i, atomic_long_t *v) { - return atomic64_fetch_sub_release(i, v); + return arch_atomic64_fetch_sub_release(i, v); } static __always_inline long -atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v) +arch_atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v) { - return atomic64_fetch_sub_relaxed(i, v); + return arch_atomic64_fetch_sub_relaxed(i, v); } static __always_inline void -atomic_long_inc(atomic_long_t *v) +arch_atomic_long_inc(atomic_long_t *v) { - atomic64_inc(v); + arch_atomic64_inc(v); } static __always_inline long -atomic_long_inc_return(atomic_long_t *v) +arch_atomic_long_inc_return(atomic_long_t *v) { - return atomic64_inc_return(v); + return arch_atomic64_inc_return(v); } static __always_inline long -atomic_long_inc_return_acquire(atomic_long_t *v) +arch_atomic_long_inc_return_acquire(atomic_long_t *v) { - return atomic64_inc_return_acquire(v); + return arch_atomic64_inc_return_acquire(v); } static __always_inline long -atomic_long_inc_return_release(atomic_long_t *v) +arch_atomic_long_inc_return_release(atomic_long_t *v) { - return atomic64_inc_return_release(v); + return arch_atomic64_inc_return_release(v); } static __always_inline long -atomic_long_inc_return_relaxed(atomic_long_t *v) +arch_atomic_long_inc_return_relaxed(atomic_long_t *v) { - return atomic64_inc_return_relaxed(v); + return arch_atomic64_inc_return_relaxed(v); } static __always_inline long -atomic_long_fetch_inc(atomic_long_t *v) +arch_atomic_long_fetch_inc(atomic_long_t *v) { - return atomic64_fetch_inc(v); + return arch_atomic64_fetch_inc(v); } static __always_inline long -atomic_long_fetch_inc_acquire(atomic_long_t *v) +arch_atomic_long_fetch_inc_acquire(atomic_long_t *v) { - return atomic64_fetch_inc_acquire(v); + return arch_atomic64_fetch_inc_acquire(v); } static __always_inline long -atomic_long_fetch_inc_release(atomic_long_t *v) +arch_atomic_long_fetch_inc_release(atomic_long_t *v) { - return atomic64_fetch_inc_release(v); + return arch_atomic64_fetch_inc_release(v); } static __always_inline long -atomic_long_fetch_inc_relaxed(atomic_long_t *v) +arch_atomic_long_fetch_inc_relaxed(atomic_long_t *v) { - return atomic64_fetch_inc_relaxed(v); + return arch_atomic64_fetch_inc_relaxed(v); } static __always_inline void -atomic_long_dec(atomic_long_t *v) +arch_atomic_long_dec(atomic_long_t *v) { - atomic64_dec(v); + arch_atomic64_dec(v); } static __always_inline long -atomic_long_dec_return(atomic_long_t *v) +arch_atomic_long_dec_return(atomic_long_t *v) { - return atomic64_dec_return(v); + return arch_atomic64_dec_return(v); } static __always_inline long -atomic_long_dec_return_acquire(atomic_long_t *v) +arch_atomic_long_dec_return_acquire(atomic_long_t *v) { - return atomic64_dec_return_acquire(v); + return arch_atomic64_dec_return_acquire(v); } static __always_inline long -atomic_long_dec_return_release(atomic_long_t *v) +arch_atomic_long_dec_return_release(atomic_long_t *v) { - return atomic64_dec_return_release(v); + return arch_atomic64_dec_return_release(v); } static __always_inline long -atomic_long_dec_return_relaxed(atomic_long_t *v) +arch_atomic_long_dec_return_relaxed(atomic_long_t *v) { - return atomic64_dec_return_relaxed(v); + return arch_atomic64_dec_return_relaxed(v); } static __always_inline long -atomic_long_fetch_dec(atomic_long_t *v) +arch_atomic_long_fetch_dec(atomic_long_t *v) { - return atomic64_fetch_dec(v); + return arch_atomic64_fetch_dec(v); } static __always_inline long -atomic_long_fetch_dec_acquire(atomic_long_t *v) +arch_atomic_long_fetch_dec_acquire(atomic_long_t *v) { - return atomic64_fetch_dec_acquire(v); + return arch_atomic64_fetch_dec_acquire(v); } static __always_inline long -atomic_long_fetch_dec_release(atomic_long_t *v) +arch_atomic_long_fetch_dec_release(atomic_long_t *v) { - return atomic64_fetch_dec_release(v); + return arch_atomic64_fetch_dec_release(v); } static __always_inline long -atomic_long_fetch_dec_relaxed(atomic_long_t *v) +arch_atomic_long_fetch_dec_relaxed(atomic_long_t *v) { - return atomic64_fetch_dec_relaxed(v); + return arch_atomic64_fetch_dec_relaxed(v); } static __always_inline void -atomic_long_and(long i, atomic_long_t *v) +arch_atomic_long_and(long i, atomic_long_t *v) { - atomic64_and(i, v); + arch_atomic64_and(i, v); } static __always_inline long -atomic_long_fetch_and(long i, atomic_long_t *v) +arch_atomic_long_fetch_and(long i, atomic_long_t *v) { - return atomic64_fetch_and(i, v); + return arch_atomic64_fetch_and(i, v); } static __always_inline long -atomic_long_fetch_and_acquire(long i, atomic_long_t *v) +arch_atomic_long_fetch_and_acquire(long i, atomic_long_t *v) { - return atomic64_fetch_and_acquire(i, v); + return arch_atomic64_fetch_and_acquire(i, v); } static __always_inline long -atomic_long_fetch_and_release(long i, atomic_long_t *v) +arch_atomic_long_fetch_and_release(long i, atomic_long_t *v) { - return atomic64_fetch_and_release(i, v); + return arch_atomic64_fetch_and_release(i, v); } static __always_inline long -atomic_long_fetch_and_relaxed(long i, atomic_long_t *v) +arch_atomic_long_fetch_and_relaxed(long i, atomic_long_t *v) { - return atomic64_fetch_and_relaxed(i, v); + return arch_atomic64_fetch_and_relaxed(i, v); } static __always_inline void -atomic_long_andnot(long i, atomic_long_t *v) +arch_atomic_long_andnot(long i, atomic_long_t *v) { - atomic64_andnot(i, v); + arch_atomic64_andnot(i, v); } static __always_inline long -atomic_long_fetch_andnot(long i, atomic_long_t *v) +arch_atomic_long_fetch_andnot(long i, atomic_long_t *v) { - return atomic64_fetch_andnot(i, v); + return arch_atomic64_fetch_andnot(i, v); } static __always_inline long -atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v) +arch_atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v) { - return atomic64_fetch_andnot_acquire(i, v); + return arch_atomic64_fetch_andnot_acquire(i, v); } static __always_inline long -atomic_long_fetch_andnot_release(long i, atomic_long_t *v) +arch_atomic_long_fetch_andnot_release(long i, atomic_long_t *v) { - return atomic64_fetch_andnot_release(i, v); + return arch_atomic64_fetch_andnot_release(i, v); } static __always_inline long -atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v) +arch_atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v) { - return atomic64_fetch_andnot_relaxed(i, v); + return arch_atomic64_fetch_andnot_relaxed(i, v); } static __always_inline void -atomic_long_or(long i, atomic_long_t *v) +arch_atomic_long_or(long i, atomic_long_t *v) { - atomic64_or(i, v); + arch_atomic64_or(i, v); } static __always_inline long -atomic_long_fetch_or(long i, atomic_long_t *v) +arch_atomic_long_fetch_or(long i, atomic_long_t *v) { - return atomic64_fetch_or(i, v); + return arch_atomic64_fetch_or(i, v); } static __always_inline long -atomic_long_fetch_or_acquire(long i, atomic_long_t *v) +arch_atomic_long_fetch_or_acquire(long i, atomic_long_t *v) { - return atomic64_fetch_or_acquire(i, v); + return arch_atomic64_fetch_or_acquire(i, v); } static __always_inline long -atomic_long_fetch_or_release(long i, atomic_long_t *v) +arch_atomic_long_fetch_or_release(long i, atomic_long_t *v) { - return atomic64_fetch_or_release(i, v); + return arch_atomic64_fetch_or_release(i, v); } static __always_inline long -atomic_long_fetch_or_relaxed(long i, atomic_long_t *v) +arch_atomic_long_fetch_or_relaxed(long i, atomic_long_t *v) { - return atomic64_fetch_or_relaxed(i, v); + return arch_atomic64_fetch_or_relaxed(i, v); } static __always_inline void -atomic_long_xor(long i, atomic_long_t *v) +arch_atomic_long_xor(long i, atomic_long_t *v) { - atomic64_xor(i, v); + arch_atomic64_xor(i, v); } static __always_inline long -atomic_long_fetch_xor(long i, atomic_long_t *v) +arch_atomic_long_fetch_xor(long i, atomic_long_t *v) { - return atomic64_fetch_xor(i, v); + return arch_atomic64_fetch_xor(i, v); } static __always_inline long -atomic_long_fetch_xor_acquire(long i, atomic_long_t *v) +arch_atomic_long_fetch_xor_acquire(long i, atomic_long_t *v) { - return atomic64_fetch_xor_acquire(i, v); + return arch_atomic64_fetch_xor_acquire(i, v); } static __always_inline long -atomic_long_fetch_xor_release(long i, atomic_long_t *v) +arch_atomic_long_fetch_xor_release(long i, atomic_long_t *v) { - return atomic64_fetch_xor_release(i, v); + return arch_atomic64_fetch_xor_release(i, v); } static __always_inline long -atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v) +arch_atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v) { - return atomic64_fetch_xor_relaxed(i, v); + return arch_atomic64_fetch_xor_relaxed(i, v); } static __always_inline long -atomic_long_xchg(atomic_long_t *v, long i) +arch_atomic_long_xchg(atomic_long_t *v, long i) { - return atomic64_xchg(v, i); + return arch_atomic64_xchg(v, i); } static __always_inline long -atomic_long_xchg_acquire(atomic_long_t *v, long i) +arch_atomic_long_xchg_acquire(atomic_long_t *v, long i) { - return atomic64_xchg_acquire(v, i); + return arch_atomic64_xchg_acquire(v, i); } static __always_inline long -atomic_long_xchg_release(atomic_long_t *v, long i) +arch_atomic_long_xchg_release(atomic_long_t *v, long i) { - return atomic64_xchg_release(v, i); + return arch_atomic64_xchg_release(v, i); } static __always_inline long -atomic_long_xchg_relaxed(atomic_long_t *v, long i) +arch_atomic_long_xchg_relaxed(atomic_long_t *v, long i) { - return atomic64_xchg_relaxed(v, i); + return arch_atomic64_xchg_relaxed(v, i); } static __always_inline long -atomic_long_cmpxchg(atomic_long_t *v, long old, long new) +arch_atomic_long_cmpxchg(atomic_long_t *v, long old, long new) { - return atomic64_cmpxchg(v, old, new); + return arch_atomic64_cmpxchg(v, old, new); } static __always_inline long -atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new) +arch_atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new) { - return atomic64_cmpxchg_acquire(v, old, new); + return arch_atomic64_cmpxchg_acquire(v, old, new); } static __always_inline long -atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new) +arch_atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new) { - return atomic64_cmpxchg_release(v, old, new); + return arch_atomic64_cmpxchg_release(v, old, new); } static __always_inline long -atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new) +arch_atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new) { - return atomic64_cmpxchg_relaxed(v, old, new); + return arch_atomic64_cmpxchg_relaxed(v, old, new); } static __always_inline bool -atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new) +arch_atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new) { - return atomic64_try_cmpxchg(v, (s64 *)old, new); + return arch_atomic64_try_cmpxchg(v, (s64 *)old, new); } static __always_inline bool -atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new) +arch_atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new) { - return atomic64_try_cmpxchg_acquire(v, (s64 *)old, new); + return arch_atomic64_try_cmpxchg_acquire(v, (s64 *)old, new); } static __always_inline bool -atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new) +arch_atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new) { - return atomic64_try_cmpxchg_release(v, (s64 *)old, new); + return arch_atomic64_try_cmpxchg_release(v, (s64 *)old, new); } static __always_inline bool -atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) +arch_atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) { - return atomic64_try_cmpxchg_relaxed(v, (s64 *)old, new); + return arch_atomic64_try_cmpxchg_relaxed(v, (s64 *)old, new); } static __always_inline bool -atomic_long_sub_and_test(long i, atomic_long_t *v) +arch_atomic_long_sub_and_test(long i, atomic_long_t *v) { - return atomic64_sub_and_test(i, v); + return arch_atomic64_sub_and_test(i, v); } static __always_inline bool -atomic_long_dec_and_test(atomic_long_t *v) +arch_atomic_long_dec_and_test(atomic_long_t *v) { - return atomic64_dec_and_test(v); + return arch_atomic64_dec_and_test(v); } static __always_inline bool -atomic_long_inc_and_test(atomic_long_t *v) +arch_atomic_long_inc_and_test(atomic_long_t *v) { - return atomic64_inc_and_test(v); + return arch_atomic64_inc_and_test(v); } static __always_inline bool -atomic_long_add_negative(long i, atomic_long_t *v) +arch_atomic_long_add_negative(long i, atomic_long_t *v) { - return atomic64_add_negative(i, v); + return arch_atomic64_add_negative(i, v); } static __always_inline long -atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) +arch_atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) { - return atomic64_fetch_add_unless(v, a, u); + return arch_atomic64_fetch_add_unless(v, a, u); } static __always_inline bool -atomic_long_add_unless(atomic_long_t *v, long a, long u) +arch_atomic_long_add_unless(atomic_long_t *v, long a, long u) { - return atomic64_add_unless(v, a, u); + return arch_atomic64_add_unless(v, a, u); } static __always_inline bool -atomic_long_inc_not_zero(atomic_long_t *v) +arch_atomic_long_inc_not_zero(atomic_long_t *v) { - return atomic64_inc_not_zero(v); + return arch_atomic64_inc_not_zero(v); } static __always_inline bool -atomic_long_inc_unless_negative(atomic_long_t *v) +arch_atomic_long_inc_unless_negative(atomic_long_t *v) { - return atomic64_inc_unless_negative(v); + return arch_atomic64_inc_unless_negative(v); } static __always_inline bool -atomic_long_dec_unless_positive(atomic_long_t *v) +arch_atomic_long_dec_unless_positive(atomic_long_t *v) { - return atomic64_dec_unless_positive(v); + return arch_atomic64_dec_unless_positive(v); } static __always_inline long -atomic_long_dec_if_positive(atomic_long_t *v) +arch_atomic_long_dec_if_positive(atomic_long_t *v) { - return atomic64_dec_if_positive(v); + return arch_atomic64_dec_if_positive(v); } #else /* CONFIG_64BIT */ static __always_inline long -atomic_long_read(const atomic_long_t *v) +arch_atomic_long_read(const atomic_long_t *v) { - return atomic_read(v); + return arch_atomic_read(v); } static __always_inline long -atomic_long_read_acquire(const atomic_long_t *v) +arch_atomic_long_read_acquire(const atomic_long_t *v) { - return atomic_read_acquire(v); + return arch_atomic_read_acquire(v); } static __always_inline void -atomic_long_set(atomic_long_t *v, long i) +arch_atomic_long_set(atomic_long_t *v, long i) { - atomic_set(v, i); + arch_atomic_set(v, i); } static __always_inline void -atomic_long_set_release(atomic_long_t *v, long i) +arch_atomic_long_set_release(atomic_long_t *v, long i) { - atomic_set_release(v, i); + arch_atomic_set_release(v, i); } static __always_inline void -atomic_long_add(long i, atomic_long_t *v) +arch_atomic_long_add(long i, atomic_long_t *v) { - atomic_add(i, v); + arch_atomic_add(i, v); } static __always_inline long -atomic_long_add_return(long i, atomic_long_t *v) +arch_atomic_long_add_return(long i, atomic_long_t *v) { - return atomic_add_return(i, v); + return arch_atomic_add_return(i, v); } static __always_inline long -atomic_long_add_return_acquire(long i, atomic_long_t *v) +arch_atomic_long_add_return_acquire(long i, atomic_long_t *v) { - return atomic_add_return_acquire(i, v); + return arch_atomic_add_return_acquire(i, v); } static __always_inline long -atomic_long_add_return_release(long i, atomic_long_t *v) +arch_atomic_long_add_return_release(long i, atomic_long_t *v) { - return atomic_add_return_release(i, v); + return arch_atomic_add_return_release(i, v); } static __always_inline long -atomic_long_add_return_relaxed(long i, atomic_long_t *v) +arch_atomic_long_add_return_relaxed(long i, atomic_long_t *v) { - return atomic_add_return_relaxed(i, v); + return arch_atomic_add_return_relaxed(i, v); } static __always_inline long -atomic_long_fetch_add(long i, atomic_long_t *v) +arch_atomic_long_fetch_add(long i, atomic_long_t *v) { - return atomic_fetch_add(i, v); + return arch_atomic_fetch_add(i, v); } static __always_inline long -atomic_long_fetch_add_acquire(long i, atomic_long_t *v) +arch_atomic_long_fetch_add_acquire(long i, atomic_long_t *v) { - return atomic_fetch_add_acquire(i, v); + return arch_atomic_fetch_add_acquire(i, v); } static __always_inline long -atomic_long_fetch_add_release(long i, atomic_long_t *v) +arch_atomic_long_fetch_add_release(long i, atomic_long_t *v) { - return atomic_fetch_add_release(i, v); + return arch_atomic_fetch_add_release(i, v); } static __always_inline long -atomic_long_fetch_add_relaxed(long i, atomic_long_t *v) +arch_atomic_long_fetch_add_relaxed(long i, atomic_long_t *v) { - return atomic_fetch_add_relaxed(i, v); + return arch_atomic_fetch_add_relaxed(i, v); } static __always_inline void -atomic_long_sub(long i, atomic_long_t *v) +arch_atomic_long_sub(long i, atomic_long_t *v) { - atomic_sub(i, v); + arch_atomic_sub(i, v); } static __always_inline long -atomic_long_sub_return(long i, atomic_long_t *v) +arch_atomic_long_sub_return(long i, atomic_long_t *v) { - return atomic_sub_return(i, v); + return arch_atomic_sub_return(i, v); } static __always_inline long -atomic_long_sub_return_acquire(long i, atomic_long_t *v) +arch_atomic_long_sub_return_acquire(long i, atomic_long_t *v) { - return atomic_sub_return_acquire(i, v); + return arch_atomic_sub_return_acquire(i, v); } static __always_inline long -atomic_long_sub_return_release(long i, atomic_long_t *v) +arch_atomic_long_sub_return_release(long i, atomic_long_t *v) { - return atomic_sub_return_release(i, v); + return arch_atomic_sub_return_release(i, v); } static __always_inline long -atomic_long_sub_return_relaxed(long i, atomic_long_t *v) +arch_atomic_long_sub_return_relaxed(long i, atomic_long_t *v) { - return atomic_sub_return_relaxed(i, v); + return arch_atomic_sub_return_relaxed(i, v); } static __always_inline long -atomic_long_fetch_sub(long i, atomic_long_t *v) +arch_atomic_long_fetch_sub(long i, atomic_long_t *v) { - return atomic_fetch_sub(i, v); + return arch_atomic_fetch_sub(i, v); } static __always_inline long -atomic_long_fetch_sub_acquire(long i, atomic_long_t *v) +arch_atomic_long_fetch_sub_acquire(long i, atomic_long_t *v) { - return atomic_fetch_sub_acquire(i, v); + return arch_atomic_fetch_sub_acquire(i, v); } static __always_inline long -atomic_long_fetch_sub_release(long i, atomic_long_t *v) +arch_atomic_long_fetch_sub_release(long i, atomic_long_t *v) { - return atomic_fetch_sub_release(i, v); + return arch_atomic_fetch_sub_release(i, v); } static __always_inline long -atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v) +arch_atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v) { - return atomic_fetch_sub_relaxed(i, v); + return arch_atomic_fetch_sub_relaxed(i, v); } static __always_inline void -atomic_long_inc(atomic_long_t *v) +arch_atomic_long_inc(atomic_long_t *v) { - atomic_inc(v); + arch_atomic_inc(v); } static __always_inline long -atomic_long_inc_return(atomic_long_t *v) +arch_atomic_long_inc_return(atomic_long_t *v) { - return atomic_inc_return(v); + return arch_atomic_inc_return(v); } static __always_inline long -atomic_long_inc_return_acquire(atomic_long_t *v) +arch_atomic_long_inc_return_acquire(atomic_long_t *v) { - return atomic_inc_return_acquire(v); + return arch_atomic_inc_return_acquire(v); } static __always_inline long -atomic_long_inc_return_release(atomic_long_t *v) +arch_atomic_long_inc_return_release(atomic_long_t *v) { - return atomic_inc_return_release(v); + return arch_atomic_inc_return_release(v); } static __always_inline long -atomic_long_inc_return_relaxed(atomic_long_t *v) +arch_atomic_long_inc_return_relaxed(atomic_long_t *v) { - return atomic_inc_return_relaxed(v); + return arch_atomic_inc_return_relaxed(v); } static __always_inline long -atomic_long_fetch_inc(atomic_long_t *v) +arch_atomic_long_fetch_inc(atomic_long_t *v) { - return atomic_fetch_inc(v); + return arch_atomic_fetch_inc(v); } static __always_inline long -atomic_long_fetch_inc_acquire(atomic_long_t *v) +arch_atomic_long_fetch_inc_acquire(atomic_long_t *v) { - return atomic_fetch_inc_acquire(v); + return arch_atomic_fetch_inc_acquire(v); } static __always_inline long -atomic_long_fetch_inc_release(atomic_long_t *v) +arch_atomic_long_fetch_inc_release(atomic_long_t *v) { - return atomic_fetch_inc_release(v); + return arch_atomic_fetch_inc_release(v); } static __always_inline long -atomic_long_fetch_inc_relaxed(atomic_long_t *v) +arch_atomic_long_fetch_inc_relaxed(atomic_long_t *v) { - return atomic_fetch_inc_relaxed(v); + return arch_atomic_fetch_inc_relaxed(v); } static __always_inline void -atomic_long_dec(atomic_long_t *v) +arch_atomic_long_dec(atomic_long_t *v) { - atomic_dec(v); + arch_atomic_dec(v); } static __always_inline long -atomic_long_dec_return(atomic_long_t *v) +arch_atomic_long_dec_return(atomic_long_t *v) { - return atomic_dec_return(v); + return arch_atomic_dec_return(v); } static __always_inline long -atomic_long_dec_return_acquire(atomic_long_t *v) +arch_atomic_long_dec_return_acquire(atomic_long_t *v) { - return atomic_dec_return_acquire(v); + return arch_atomic_dec_return_acquire(v); } static __always_inline long -atomic_long_dec_return_release(atomic_long_t *v) +arch_atomic_long_dec_return_release(atomic_long_t *v) { - return atomic_dec_return_release(v); + return arch_atomic_dec_return_release(v); } static __always_inline long -atomic_long_dec_return_relaxed(atomic_long_t *v) +arch_atomic_long_dec_return_relaxed(atomic_long_t *v) { - return atomic_dec_return_relaxed(v); + return arch_atomic_dec_return_relaxed(v); } static __always_inline long -atomic_long_fetch_dec(atomic_long_t *v) +arch_atomic_long_fetch_dec(atomic_long_t *v) { - return atomic_fetch_dec(v); + return arch_atomic_fetch_dec(v); } static __always_inline long -atomic_long_fetch_dec_acquire(atomic_long_t *v) +arch_atomic_long_fetch_dec_acquire(atomic_long_t *v) { - return atomic_fetch_dec_acquire(v); + return arch_atomic_fetch_dec_acquire(v); } static __always_inline long -atomic_long_fetch_dec_release(atomic_long_t *v) +arch_atomic_long_fetch_dec_release(atomic_long_t *v) { - return atomic_fetch_dec_release(v); + return arch_atomic_fetch_dec_release(v); } static __always_inline long -atomic_long_fetch_dec_relaxed(atomic_long_t *v) +arch_atomic_long_fetch_dec_relaxed(atomic_long_t *v) { - return atomic_fetch_dec_relaxed(v); + return arch_atomic_fetch_dec_relaxed(v); } static __always_inline void -atomic_long_and(long i, atomic_long_t *v) +arch_atomic_long_and(long i, atomic_long_t *v) { - atomic_and(i, v); + arch_atomic_and(i, v); } static __always_inline long -atomic_long_fetch_and(long i, atomic_long_t *v) +arch_atomic_long_fetch_and(long i, atomic_long_t *v) { - return atomic_fetch_and(i, v); + return arch_atomic_fetch_and(i, v); } static __always_inline long -atomic_long_fetch_and_acquire(long i, atomic_long_t *v) +arch_atomic_long_fetch_and_acquire(long i, atomic_long_t *v) { - return atomic_fetch_and_acquire(i, v); + return arch_atomic_fetch_and_acquire(i, v); } static __always_inline long -atomic_long_fetch_and_release(long i, atomic_long_t *v) +arch_atomic_long_fetch_and_release(long i, atomic_long_t *v) { - return atomic_fetch_and_release(i, v); + return arch_atomic_fetch_and_release(i, v); } static __always_inline long -atomic_long_fetch_and_relaxed(long i, atomic_long_t *v) +arch_atomic_long_fetch_and_relaxed(long i, atomic_long_t *v) { - return atomic_fetch_and_relaxed(i, v); + return arch_atomic_fetch_and_relaxed(i, v); } static __always_inline void -atomic_long_andnot(long i, atomic_long_t *v) +arch_atomic_long_andnot(long i, atomic_long_t *v) { - atomic_andnot(i, v); + arch_atomic_andnot(i, v); } static __always_inline long -atomic_long_fetch_andnot(long i, atomic_long_t *v) +arch_atomic_long_fetch_andnot(long i, atomic_long_t *v) { - return atomic_fetch_andnot(i, v); + return arch_atomic_fetch_andnot(i, v); } static __always_inline long -atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v) +arch_atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v) { - return atomic_fetch_andnot_acquire(i, v); + return arch_atomic_fetch_andnot_acquire(i, v); } static __always_inline long -atomic_long_fetch_andnot_release(long i, atomic_long_t *v) +arch_atomic_long_fetch_andnot_release(long i, atomic_long_t *v) { - return atomic_fetch_andnot_release(i, v); + return arch_atomic_fetch_andnot_release(i, v); } static __always_inline long -atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v) +arch_atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v) { - return atomic_fetch_andnot_relaxed(i, v); + return arch_atomic_fetch_andnot_relaxed(i, v); } static __always_inline void -atomic_long_or(long i, atomic_long_t *v) +arch_atomic_long_or(long i, atomic_long_t *v) { - atomic_or(i, v); + arch_atomic_or(i, v); } static __always_inline long -atomic_long_fetch_or(long i, atomic_long_t *v) +arch_atomic_long_fetch_or(long i, atomic_long_t *v) { - return atomic_fetch_or(i, v); + return arch_atomic_fetch_or(i, v); } static __always_inline long -atomic_long_fetch_or_acquire(long i, atomic_long_t *v) +arch_atomic_long_fetch_or_acquire(long i, atomic_long_t *v) { - return atomic_fetch_or_acquire(i, v); + return arch_atomic_fetch_or_acquire(i, v); } static __always_inline long -atomic_long_fetch_or_release(long i, atomic_long_t *v) +arch_atomic_long_fetch_or_release(long i, atomic_long_t *v) { - return atomic_fetch_or_release(i, v); + return arch_atomic_fetch_or_release(i, v); } static __always_inline long -atomic_long_fetch_or_relaxed(long i, atomic_long_t *v) +arch_atomic_long_fetch_or_relaxed(long i, atomic_long_t *v) { - return atomic_fetch_or_relaxed(i, v); + return arch_atomic_fetch_or_relaxed(i, v); } static __always_inline void -atomic_long_xor(long i, atomic_long_t *v) +arch_atomic_long_xor(long i, atomic_long_t *v) { - atomic_xor(i, v); + arch_atomic_xor(i, v); } static __always_inline long -atomic_long_fetch_xor(long i, atomic_long_t *v) +arch_atomic_long_fetch_xor(long i, atomic_long_t *v) { - return atomic_fetch_xor(i, v); + return arch_atomic_fetch_xor(i, v); } static __always_inline long -atomic_long_fetch_xor_acquire(long i, atomic_long_t *v) +arch_atomic_long_fetch_xor_acquire(long i, atomic_long_t *v) { - return atomic_fetch_xor_acquire(i, v); + return arch_atomic_fetch_xor_acquire(i, v); } static __always_inline long -atomic_long_fetch_xor_release(long i, atomic_long_t *v) +arch_atomic_long_fetch_xor_release(long i, atomic_long_t *v) { - return atomic_fetch_xor_release(i, v); + return arch_atomic_fetch_xor_release(i, v); } static __always_inline long -atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v) +arch_atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v) { - return atomic_fetch_xor_relaxed(i, v); + return arch_atomic_fetch_xor_relaxed(i, v); } static __always_inline long -atomic_long_xchg(atomic_long_t *v, long i) +arch_atomic_long_xchg(atomic_long_t *v, long i) { - return atomic_xchg(v, i); + return arch_atomic_xchg(v, i); } static __always_inline long -atomic_long_xchg_acquire(atomic_long_t *v, long i) +arch_atomic_long_xchg_acquire(atomic_long_t *v, long i) { - return atomic_xchg_acquire(v, i); + return arch_atomic_xchg_acquire(v, i); } static __always_inline long -atomic_long_xchg_release(atomic_long_t *v, long i) +arch_atomic_long_xchg_release(atomic_long_t *v, long i) { - return atomic_xchg_release(v, i); + return arch_atomic_xchg_release(v, i); } static __always_inline long -atomic_long_xchg_relaxed(atomic_long_t *v, long i) +arch_atomic_long_xchg_relaxed(atomic_long_t *v, long i) { - return atomic_xchg_relaxed(v, i); + return arch_atomic_xchg_relaxed(v, i); } static __always_inline long -atomic_long_cmpxchg(atomic_long_t *v, long old, long new) +arch_atomic_long_cmpxchg(atomic_long_t *v, long old, long new) { - return atomic_cmpxchg(v, old, new); + return arch_atomic_cmpxchg(v, old, new); } static __always_inline long -atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new) +arch_atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new) { - return atomic_cmpxchg_acquire(v, old, new); + return arch_atomic_cmpxchg_acquire(v, old, new); } static __always_inline long -atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new) +arch_atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new) { - return atomic_cmpxchg_release(v, old, new); + return arch_atomic_cmpxchg_release(v, old, new); } static __always_inline long -atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new) +arch_atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new) { - return atomic_cmpxchg_relaxed(v, old, new); + return arch_atomic_cmpxchg_relaxed(v, old, new); } static __always_inline bool -atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new) +arch_atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new) { - return atomic_try_cmpxchg(v, (int *)old, new); + return arch_atomic_try_cmpxchg(v, (int *)old, new); } static __always_inline bool -atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new) +arch_atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new) { - return atomic_try_cmpxchg_acquire(v, (int *)old, new); + return arch_atomic_try_cmpxchg_acquire(v, (int *)old, new); } static __always_inline bool -atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new) +arch_atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new) { - return atomic_try_cmpxchg_release(v, (int *)old, new); + return arch_atomic_try_cmpxchg_release(v, (int *)old, new); } static __always_inline bool -atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) +arch_atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) { - return atomic_try_cmpxchg_relaxed(v, (int *)old, new); + return arch_atomic_try_cmpxchg_relaxed(v, (int *)old, new); } static __always_inline bool -atomic_long_sub_and_test(long i, atomic_long_t *v) +arch_atomic_long_sub_and_test(long i, atomic_long_t *v) { - return atomic_sub_and_test(i, v); + return arch_atomic_sub_and_test(i, v); } static __always_inline bool -atomic_long_dec_and_test(atomic_long_t *v) +arch_atomic_long_dec_and_test(atomic_long_t *v) { - return atomic_dec_and_test(v); + return arch_atomic_dec_and_test(v); } static __always_inline bool -atomic_long_inc_and_test(atomic_long_t *v) +arch_atomic_long_inc_and_test(atomic_long_t *v) { - return atomic_inc_and_test(v); + return arch_atomic_inc_and_test(v); } static __always_inline bool -atomic_long_add_negative(long i, atomic_long_t *v) +arch_atomic_long_add_negative(long i, atomic_long_t *v) { - return atomic_add_negative(i, v); + return arch_atomic_add_negative(i, v); } static __always_inline long -atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) +arch_atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) { - return atomic_fetch_add_unless(v, a, u); + return arch_atomic_fetch_add_unless(v, a, u); } static __always_inline bool -atomic_long_add_unless(atomic_long_t *v, long a, long u) +arch_atomic_long_add_unless(atomic_long_t *v, long a, long u) { - return atomic_add_unless(v, a, u); + return arch_atomic_add_unless(v, a, u); } static __always_inline bool -atomic_long_inc_not_zero(atomic_long_t *v) +arch_atomic_long_inc_not_zero(atomic_long_t *v) { - return atomic_inc_not_zero(v); + return arch_atomic_inc_not_zero(v); } static __always_inline bool -atomic_long_inc_unless_negative(atomic_long_t *v) +arch_atomic_long_inc_unless_negative(atomic_long_t *v) { - return atomic_inc_unless_negative(v); + return arch_atomic_inc_unless_negative(v); } static __always_inline bool -atomic_long_dec_unless_positive(atomic_long_t *v) +arch_atomic_long_dec_unless_positive(atomic_long_t *v) { - return atomic_dec_unless_positive(v); + return arch_atomic_dec_unless_positive(v); } static __always_inline long -atomic_long_dec_if_positive(atomic_long_t *v) +arch_atomic_long_dec_if_positive(atomic_long_t *v) { - return atomic_dec_if_positive(v); + return arch_atomic_dec_if_positive(v); } #endif /* CONFIG_64BIT */ #endif /* _LINUX_ATOMIC_LONG_H */ -// c5552b5d78a0c7584dfd03cba985e78a1a86bbed +// e8f0e08ff072b74d180eabe2ad001282b38c2c88 -- cgit v1.2.3 From b1121e2a182dc8f22e7cfa2d8374199505d27ab8 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Mon, 5 Jul 2021 20:42:04 +0800 Subject: ACPI: Add LoongArch support for ACPI_PROCESSOR/ACPI_NUMA We are preparing to add new Loongson (based on LoongArch, not MIPS) support. LoongArch use ACPI other than DT as its boot protocol, so add its support for ACPI_PROCESSOR/ACPI_NUMA. Signed-off-by: Huacai Chen Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 72e4f7fd268c..3e4805619fe0 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -249,7 +249,7 @@ void acpi_table_print_madt_entry (struct acpi_subtable_header *madt); /* the following numa functions are architecture-dependent */ void acpi_numa_slit_init (struct acpi_table_slit *slit); -#if defined(CONFIG_X86) || defined(CONFIG_IA64) +#if defined(CONFIG_X86) || defined(CONFIG_IA64) || defined(CONFIG_LOONGARCH) void acpi_numa_processor_affinity_init (struct acpi_srat_cpu_affinity *pa); #else static inline void -- cgit v1.2.3 From d0b8e398319e5b09f3cb26ee8288ce356646fca6 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 12 Jul 2021 19:25:55 +0200 Subject: ACPI: glue: Eliminate acpi_platform_notify() Get rid of acpi_platform_notify() which is redundant and make device_platform_notify() in the driver core call acpi_device_notify() and acpi_device_notify_remove() directly. No functional impact. Signed-off-by: Rafael J. Wysocki Reviewed-by: Andy Shevchenko --- include/linux/acpi.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 72e4f7fd268c..fdbf6d7d928a 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1380,13 +1380,11 @@ static inline int find_acpi_cpu_cache_topology(unsigned int cpu, int level) #endif #ifdef CONFIG_ACPI -extern int acpi_platform_notify(struct device *dev, enum kobject_action action); +extern void acpi_device_notify(struct device *dev); +extern void acpi_device_notify_remove(struct device *dev); #else -static inline int -acpi_platform_notify(struct device *dev, enum kobject_action action) -{ - return 0; -} +static inline void acpi_device_notify(struct device *dev) { } +static inline void acpi_device_notify_remove(struct device *dev) { } #endif #endif /*_LINUX_ACPI_H*/ -- cgit v1.2.3 From 384f5a857baeba88cf013b36999a97b471e4bd9c Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 12 Jul 2021 19:27:12 +0200 Subject: software nodes: Split software_node_notify() Split software_node_notify_remove) out of software_node_notify() and make device_platform_notify() call the latter on device addition and the former on device removal. While at it, put the headers of the above functions into base.h, because they don't need to be present in a global header file. No intentional functional impact. Signed-off-by: Rafael J. Wysocki Reviewed-by: Greg Kroah-Hartman Reviewed-by: Heikki Krogerus Reviewed-by: Andy Shevchenko --- include/linux/property.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index 073e680c35e2..357513a977e5 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -484,8 +484,6 @@ void software_node_unregister_node_group(const struct software_node **node_group int software_node_register(const struct software_node *node); void software_node_unregister(const struct software_node *node); -int software_node_notify(struct device *dev, unsigned long action); - struct fwnode_handle * fwnode_create_software_node(const struct property_entry *properties, const struct fwnode_handle *parent); -- cgit v1.2.3 From c7603cfa04e7c3a435b31d065f7cbdc829428f6e Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 12 Jul 2021 16:06:15 -0700 Subject: bpf: Add ambient BPF runtime context stored in current b910eaaaa4b8 ("bpf: Fix NULL pointer dereference in bpf_get_local_storage() helper") fixed the problem with cgroup-local storage use in BPF by pre-allocating per-CPU array of 8 cgroup storage pointers to accommodate possible BPF program preemptions and nested executions. While this seems to work good in practice, it introduces new and unnecessary failure mode in which not all BPF programs might be executed if we fail to find an unused slot for cgroup storage, however unlikely it is. It might also not be so unlikely when/if we allow sleepable cgroup BPF programs in the future. Further, the way that cgroup storage is implemented as ambiently-available property during entire BPF program execution is a convenient way to pass extra information to BPF program and helpers without requiring user code to pass around extra arguments explicitly. So it would be good to have a generic solution that can allow implementing this without arbitrary restrictions. Ideally, such solution would work for both preemptable and sleepable BPF programs in exactly the same way. This patch introduces such solution, bpf_run_ctx. It adds one pointer field (bpf_ctx) to task_struct. This field is maintained by BPF_PROG_RUN family of macros in such a way that it always stays valid throughout BPF program execution. BPF program preemption is handled by remembering previous current->bpf_ctx value locally while executing nested BPF program and restoring old value after nested BPF program finishes. This is handled by two helper functions, bpf_set_run_ctx() and bpf_reset_run_ctx(), which are supposed to be used before and after BPF program runs, respectively. Restoring old value of the pointer handles preemption, while bpf_run_ctx pointer being a property of current task_struct naturally solves this problem for sleepable BPF programs by "following" BPF program execution as it is scheduled in and out of CPU. It would even allow CPU migration of BPF programs, even though it's not currently allowed by BPF infra. This patch cleans up cgroup local storage handling as a first application. The design itself is generic, though, with bpf_run_ctx being an empty struct that is supposed to be embedded into a specific struct for a given BPF program type (bpf_cg_run_ctx in this case). Follow up patches are planned that will expand this mechanism for other uses within tracing BPF programs. To verify that this change doesn't revert the fix to the original cgroup storage issue, I ran the same repro as in the original report ([0]) and didn't get any problems. Replacing bpf_reset_run_ctx(old_run_ctx) with bpf_reset_run_ctx(NULL) triggers the issue pretty quickly (so repro does work). [0] https://lore.kernel.org/bpf/YEEvBUiJl2pJkxTd@krava/ Fixes: b910eaaaa4b8 ("bpf: Fix NULL pointer dereference in bpf_get_local_storage() helper") Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210712230615.3525979-1-andrii@kernel.org --- include/linux/bpf-cgroup.h | 54 ---------------------------------------------- include/linux/bpf.h | 54 +++++++++++++++++++++++++++++----------------- include/linux/sched.h | 3 +++ 3 files changed, 37 insertions(+), 74 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 8b77d08d4b47..a74cd1c3bd87 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -27,19 +27,6 @@ struct task_struct; extern struct static_key_false cgroup_bpf_enabled_key[MAX_BPF_ATTACH_TYPE]; #define cgroup_bpf_enabled(type) static_branch_unlikely(&cgroup_bpf_enabled_key[type]) -#define BPF_CGROUP_STORAGE_NEST_MAX 8 - -struct bpf_cgroup_storage_info { - struct task_struct *task; - struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]; -}; - -/* For each cpu, permit maximum BPF_CGROUP_STORAGE_NEST_MAX number of tasks - * to use bpf cgroup storage simultaneously. - */ -DECLARE_PER_CPU(struct bpf_cgroup_storage_info, - bpf_cgroup_storage_info[BPF_CGROUP_STORAGE_NEST_MAX]); - #define for_each_cgroup_storage_type(stype) \ for (stype = 0; stype < MAX_BPF_CGROUP_STORAGE_TYPE; stype++) @@ -172,44 +159,6 @@ static inline enum bpf_cgroup_storage_type cgroup_storage_type( return BPF_CGROUP_STORAGE_SHARED; } -static inline int bpf_cgroup_storage_set(struct bpf_cgroup_storage - *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) -{ - enum bpf_cgroup_storage_type stype; - int i, err = 0; - - preempt_disable(); - for (i = 0; i < BPF_CGROUP_STORAGE_NEST_MAX; i++) { - if (unlikely(this_cpu_read(bpf_cgroup_storage_info[i].task) != NULL)) - continue; - - this_cpu_write(bpf_cgroup_storage_info[i].task, current); - for_each_cgroup_storage_type(stype) - this_cpu_write(bpf_cgroup_storage_info[i].storage[stype], - storage[stype]); - goto out; - } - err = -EBUSY; - WARN_ON_ONCE(1); - -out: - preempt_enable(); - return err; -} - -static inline void bpf_cgroup_storage_unset(void) -{ - int i; - - for (i = 0; i < BPF_CGROUP_STORAGE_NEST_MAX; i++) { - if (unlikely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current)) - continue; - - this_cpu_write(bpf_cgroup_storage_info[i].task, NULL); - return; - } -} - struct bpf_cgroup_storage * cgroup_storage_lookup(struct bpf_cgroup_storage_map *map, void *key, bool locked); @@ -487,9 +436,6 @@ static inline int cgroup_bpf_prog_query(const union bpf_attr *attr, return -EINVAL; } -static inline int bpf_cgroup_storage_set( - struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) { return 0; } -static inline void bpf_cgroup_storage_unset(void) {} static inline int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *map) { return 0; } static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc( diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 0edff8f5177e..978ebd16ae60 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1142,38 +1142,40 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array, struct bpf_prog *include_prog, struct bpf_prog_array **new_array); +struct bpf_run_ctx {}; + +struct bpf_cg_run_ctx { + struct bpf_run_ctx run_ctx; + struct bpf_prog_array_item *prog_item; +}; + /* BPF program asks to bypass CAP_NET_BIND_SERVICE in bind. */ #define BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE (1 << 0) /* BPF program asks to set CN on the packet. */ #define BPF_RET_SET_CN (1 << 0) -/* For BPF_PROG_RUN_ARRAY_FLAGS and __BPF_PROG_RUN_ARRAY, - * if bpf_cgroup_storage_set() failed, the rest of programs - * will not execute. This should be a really rare scenario - * as it requires BPF_CGROUP_STORAGE_NEST_MAX number of - * preemptions all between bpf_cgroup_storage_set() and - * bpf_cgroup_storage_unset() on the same cpu. - */ #define BPF_PROG_RUN_ARRAY_FLAGS(array, ctx, func, ret_flags) \ ({ \ struct bpf_prog_array_item *_item; \ struct bpf_prog *_prog; \ struct bpf_prog_array *_array; \ + struct bpf_run_ctx *old_run_ctx; \ + struct bpf_cg_run_ctx run_ctx; \ u32 _ret = 1; \ u32 func_ret; \ migrate_disable(); \ rcu_read_lock(); \ _array = rcu_dereference(array); \ _item = &_array->items[0]; \ + old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); \ while ((_prog = READ_ONCE(_item->prog))) { \ - if (unlikely(bpf_cgroup_storage_set(_item->cgroup_storage))) \ - break; \ + run_ctx.prog_item = _item; \ func_ret = func(_prog, ctx); \ _ret &= (func_ret & 1); \ - *(ret_flags) |= (func_ret >> 1); \ - bpf_cgroup_storage_unset(); \ + *(ret_flags) |= (func_ret >> 1); \ _item++; \ } \ + bpf_reset_run_ctx(old_run_ctx); \ rcu_read_unlock(); \ migrate_enable(); \ _ret; \ @@ -1184,6 +1186,8 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array, struct bpf_prog_array_item *_item; \ struct bpf_prog *_prog; \ struct bpf_prog_array *_array; \ + struct bpf_run_ctx *old_run_ctx; \ + struct bpf_cg_run_ctx run_ctx; \ u32 _ret = 1; \ migrate_disable(); \ rcu_read_lock(); \ @@ -1191,17 +1195,13 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array, if (unlikely(check_non_null && !_array))\ goto _out; \ _item = &_array->items[0]; \ - while ((_prog = READ_ONCE(_item->prog))) { \ - if (!set_cg_storage) { \ - _ret &= func(_prog, ctx); \ - } else { \ - if (unlikely(bpf_cgroup_storage_set(_item->cgroup_storage))) \ - break; \ - _ret &= func(_prog, ctx); \ - bpf_cgroup_storage_unset(); \ - } \ + old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);\ + while ((_prog = READ_ONCE(_item->prog))) { \ + run_ctx.prog_item = _item; \ + _ret &= func(_prog, ctx); \ _item++; \ } \ + bpf_reset_run_ctx(old_run_ctx); \ _out: \ rcu_read_unlock(); \ migrate_enable(); \ @@ -1284,6 +1284,20 @@ static inline void bpf_enable_instrumentation(void) migrate_enable(); } +static inline struct bpf_run_ctx *bpf_set_run_ctx(struct bpf_run_ctx *new_ctx) +{ + struct bpf_run_ctx *old_ctx; + + old_ctx = current->bpf_ctx; + current->bpf_ctx = new_ctx; + return old_ctx; +} + +static inline void bpf_reset_run_ctx(struct bpf_run_ctx *old_ctx) +{ + current->bpf_ctx = old_ctx; +} + extern const struct file_operations bpf_map_fops; extern const struct file_operations bpf_prog_fops; extern const struct file_operations bpf_iter_fops; diff --git a/include/linux/sched.h b/include/linux/sched.h index ec8d07d88641..c64119aa2e60 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -42,6 +42,7 @@ struct backing_dev_info; struct bio_list; struct blk_plug; struct bpf_local_storage; +struct bpf_run_ctx; struct capture_control; struct cfs_rq; struct fs_struct; @@ -1379,6 +1380,8 @@ struct task_struct { #ifdef CONFIG_BPF_SYSCALL /* Used by BPF task local storage */ struct bpf_local_storage __rcu *bpf_storage; + /* Used for BPF run context */ + struct bpf_run_ctx *bpf_ctx; #endif #ifdef CONFIG_GCC_PLUGIN_STACKLEAK -- cgit v1.2.3 From ec645dc96699ea6c37b6de86c84d7288ea9a4ddf Mon Sep 17 00:00:00 2001 From: Oleksandr Natalenko Date: Sat, 17 Jul 2021 14:33:28 +0200 Subject: block: increase BLKCG_MAX_POLS After mq-deadline learned to deal with cgroups, the BLKCG_MAX_POLS value became too small for all the elevators to be registered properly. The following issue is seen: ``` calling bfq_init+0x0/0x8b @ 1 blkcg_policy_register: BLKCG_MAX_POLS too small initcall bfq_init+0x0/0x8b returned -28 after 507 usecs ``` which renders BFQ non-functional. Increase BLKCG_MAX_POLS to allow enough space for everyone. Fixes: 08a9ad8bf607 ("block/mq-deadline: Add cgroup support") Link: https://lore.kernel.org/lkml/8988303.mDXGIdCtx8@natalenko.name/ Signed-off-by: Oleksandr Natalenko Link: https://lore.kernel.org/r/20210717123328.945810-1-oleksandr@natalenko.name Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c454fb446fd0..2e12320cb121 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -57,7 +57,7 @@ struct blk_keyslot_manager; * Maximum number of blkcg policies allowed to be registered concurrently. * Defined here to simplify include dependency. */ -#define BLKCG_MAX_POLS 5 +#define BLKCG_MAX_POLS 6 typedef void (rq_end_io_fn)(struct request *, blk_status_t); -- cgit v1.2.3 From 96cd2dd65bb0b94c908f2df32bba7350fc1b954e Mon Sep 17 00:00:00 2001 From: Lior Nahmanson Date: Mon, 28 Dec 2020 10:38:12 +0200 Subject: net/mlx5: Add DCS caps & fields support This fields will be needed when adding a support for DCS offload max_dci_stream_channels - maximum DCI stream channels supported per DCI. max_dci_errored_streams - maximum DCI error stream channels supported per DCI before a DCI move to error state. Signed-off-by: Lior Nahmanson Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index b0009aa3647f..3dd6641e942c 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1651,7 +1651,13 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 max_geneve_tlv_option_data_len[0x5]; u8 reserved_at_570[0x10]; - u8 reserved_at_580[0x33]; + u8 reserved_at_580[0xb]; + u8 log_max_dci_stream_channels[0x5]; + u8 reserved_at_590[0x3]; + u8 log_max_dci_errored_streams[0x5]; + u8 reserved_at_598[0x8]; + + u8 reserved_at_5a0[0x13]; u8 log_max_dek[0x5]; u8 reserved_at_5b8[0x4]; u8 mini_cqe_resp_stride_index[0x1]; @@ -3020,10 +3026,12 @@ struct mlx5_ifc_qpc_bits { u8 reserved_at_3c0[0x8]; u8 next_send_psn[0x18]; - u8 reserved_at_3e0[0x8]; + u8 reserved_at_3e0[0x3]; + u8 log_num_dci_stream_channels[0x5]; u8 cqn_snd[0x18]; - u8 reserved_at_400[0x8]; + u8 reserved_at_400[0x3]; + u8 log_num_dci_errored_streams[0x5]; u8 deth_sqpn[0x18]; u8 reserved_at_420[0x20]; -- cgit v1.2.3 From 337015573718b161891a3473d25f59273f2e626b Mon Sep 17 00:00:00 2001 From: Chris Down Date: Tue, 15 Jun 2021 17:52:53 +0100 Subject: printk: Userspace format indexing support We have a number of systems industry-wide that have a subset of their functionality that works as follows: 1. Receive a message from local kmsg, serial console, or netconsole; 2. Apply a set of rules to classify the message; 3. Do something based on this classification (like scheduling a remediation for the machine), rinse, and repeat. As a couple of examples of places we have this implemented just inside Facebook, although this isn't a Facebook-specific problem, we have this inside our netconsole processing (for alarm classification), and as part of our machine health checking. We use these messages to determine fairly important metrics around production health, and it's important that we get them right. While for some kinds of issues we have counters, tracepoints, or metrics with a stable interface which can reliably indicate the issue, in order to react to production issues quickly we need to work with the interface which most kernel developers naturally use when developing: printk. Most production issues come from unexpected phenomena, and as such usually the code in question doesn't have easily usable tracepoints or other counters available for the specific problem being mitigated. We have a number of lines of monitoring defence against problems in production (host metrics, process metrics, service metrics, etc), and where it's not feasible to reliably monitor at another level, this kind of pragmatic netconsole monitoring is essential. As one would expect, monitoring using printk is rather brittle for a number of reasons -- most notably that the message might disappear entirely in a new version of the kernel, or that the message may change in some way that the regex or other classification methods start to silently fail. One factor that makes this even harder is that, under normal operation, many of these messages are never expected to be hit. For example, there may be a rare hardware bug which one wants to detect if it was to ever happen again, but its recurrence is not likely or anticipated. This precludes using something like checking whether the printk in question was printed somewhere fleetwide recently to determine whether the message in question is still present or not, since we don't anticipate that it should be printed anywhere, but still need to monitor for its future presence in the long-term. This class of issue has happened on a number of occasions, causing unhealthy machines with hardware issues to remain in production for longer than ideal. As a recent example, some monitoring around blk_update_request fell out of date and caused semi-broken machines to remain in production for longer than would be desirable. Searching through the codebase to find the message is also extremely fragile, because many of the messages are further constructed beyond their callsite (eg. btrfs_printk and other module-specific wrappers, each with their own functionality). Even if they aren't, guessing the format and formulation of the underlying message based on the aesthetics of the message emitted is not a recipe for success at scale, and our previous issues with fleetwide machine health checking demonstrate as much. This provides a solution to the issue of silently changed or deleted printks: we record pointers to all printk format strings known at compile time into a new .printk_index section, both in vmlinux and modules. At runtime, this can then be iterated by looking at /printk/index/, which emits the following format, both readable by humans and able to be parsed by machines: $ head -1 vmlinux; shuf -n 5 vmlinux # filename:line function "format" <5> block/blk-settings.c:661 disk_stack_limits "%s: Warning: Device %s is misaligned\n" <4> kernel/trace/trace.c:8296 trace_create_file "Could not create tracefs '%s' entry\n" <6> arch/x86/kernel/hpet.c:144 _hpet_print_config "hpet: %s(%d):\n" <6> init/do_mounts.c:605 prepare_namespace "Waiting for root device %s...\n" <6> drivers/acpi/osl.c:1410 acpi_no_auto_serialize_setup "ACPI: auto-serialization disabled\n" This mitigates the majority of cases where we have a highly-specific printk which we want to match on, as we can now enumerate and check whether the format changed or the printk callsite disappeared entirely in userspace. This allows us to catch changes to printks we monitor earlier and decide what to do about it before it becomes problematic. There is no additional runtime cost for printk callers or printk itself, and the assembly generated is exactly the same. Signed-off-by: Chris Down Cc: Petr Mladek Cc: Jessica Yu Cc: Sergey Senozhatsky Cc: John Ogness Cc: Steven Rostedt Cc: Greg Kroah-Hartman Cc: Johannes Weiner Cc: Kees Cook Reviewed-by: Petr Mladek Tested-by: Petr Mladek Reported-by: kernel test robot Acked-by: Andy Shevchenko Acked-by: Jessica Yu # for module.{c,h} Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/e42070983637ac5e384f17fbdbe86d19c7b212a5.1623775748.git.chris@chrisdown.name --- include/linux/module.h | 5 +++ include/linux/printk.h | 95 +++++++++++++++++++++++++++++++++++++++++++++++--- 2 files changed, 96 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 8a298d820dbc..c9f1200b2312 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -511,6 +511,11 @@ struct module { struct klp_modinfo *klp_info; #endif +#ifdef CONFIG_PRINTK_INDEX + unsigned int printk_index_size; + struct pi_entry **printk_index_start; +#endif + #ifdef CONFIG_MODULE_UNLOAD /* What modules depend on me? */ struct list_head source_list; diff --git a/include/linux/printk.h b/include/linux/printk.h index e834d78f0478..2651b82ed352 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -174,12 +174,12 @@ asmlinkage __printf(1, 0) int vprintk(const char *fmt, va_list args); asmlinkage __printf(1, 2) __cold -int printk(const char *fmt, ...); +int _printk(const char *fmt, ...); /* * Special printk facility for scheduler/timekeeping use only, _DO_NOT_USE_ ! */ -__printf(1, 2) __cold int printk_deferred(const char *fmt, ...); +__printf(1, 2) __cold int _printk_deferred(const char *fmt, ...); /* * Please don't use printk_ratelimit(), because it shares ratelimiting state @@ -218,12 +218,12 @@ int vprintk(const char *s, va_list args) return 0; } static inline __printf(1, 2) __cold -int printk(const char *s, ...) +int _printk(const char *s, ...) { return 0; } static inline __printf(1, 2) __cold -int printk_deferred(const char *s, ...) +int _printk_deferred(const char *s, ...) { return 0; } @@ -348,6 +348,93 @@ extern int kptr_restrict; #define pr_fmt(fmt) fmt #endif +struct module; + +#ifdef CONFIG_PRINTK_INDEX +struct pi_entry { + const char *fmt; + const char *func; + const char *file; + unsigned int line; + + /* + * While printk and pr_* have the level stored in the string at compile + * time, some subsystems dynamically add it at runtime through the + * format string. For these dynamic cases, we allow the subsystem to + * tell us the level at compile time. + * + * NULL indicates that the level, if any, is stored in fmt. + */ + const char *level; + + /* + * The format string used by various subsystem specific printk() + * wrappers to prefix the message. + * + * Note that the static prefix defined by the pr_fmt() macro is stored + * directly in the message format (@fmt), not here. + */ + const char *subsys_fmt_prefix; +} __packed; + +#define __printk_index_emit(_fmt, _level, _subsys_fmt_prefix) \ + do { \ + if (__builtin_constant_p(_fmt) && __builtin_constant_p(_level)) { \ + /* + * We check __builtin_constant_p multiple times here + * for the same input because GCC will produce an error + * if we try to assign a static variable to fmt if it + * is not a constant, even with the outer if statement. + */ \ + static const struct pi_entry _entry \ + __used = { \ + .fmt = __builtin_constant_p(_fmt) ? (_fmt) : NULL, \ + .func = __func__, \ + .file = __FILE__, \ + .line = __LINE__, \ + .level = __builtin_constant_p(_level) ? (_level) : NULL, \ + .subsys_fmt_prefix = _subsys_fmt_prefix,\ + }; \ + static const struct pi_entry *_entry_ptr \ + __used __section(".printk_index") = &_entry; \ + } \ + } while (0) + +#else /* !CONFIG_PRINTK_INDEX */ +#define __printk_index_emit(...) do {} while (0) +#endif /* CONFIG_PRINTK_INDEX */ + +/* + * Some subsystems have their own custom printk that applies a va_format to a + * generic format, for example, to include a device number or other metadata + * alongside the format supplied by the caller. + * + * In order to store these in the way they would be emitted by the printk + * infrastructure, the subsystem provides us with the start, fixed string, and + * any subsequent text in the format string. + * + * We take a variable argument list as pr_fmt/dev_fmt/etc are sometimes passed + * as multiple arguments (eg: `"%s: ", "blah"`), and we must only take the + * first one. + * + * subsys_fmt_prefix must be known at compile time, or compilation will fail + * (since this is a mistake). If fmt or level is not known at compile time, no + * index entry will be made (since this can legitimately happen). + */ +#define printk_index_subsys_emit(subsys_fmt_prefix, level, fmt, ...) \ + __printk_index_emit(fmt, level, subsys_fmt_prefix) + +#define printk_index_wrap(_p_func, _fmt, ...) \ + ({ \ + __printk_index_emit(_fmt, NULL, NULL); \ + _p_func(_fmt, ##__VA_ARGS__); \ + }) + + +#define printk(fmt, ...) printk_index_wrap(_printk, fmt, ##__VA_ARGS__) +#define printk_deferred(fmt, ...) \ + printk_index_wrap(_printk_deferred, fmt, ##__VA_ARGS__) + /** * pr_emerg - Print an emergency-level message * @fmt: format string -- cgit v1.2.3 From ad7d61f159db73974f1b0352f21afe04b0bbd920 Mon Sep 17 00:00:00 2001 From: Chris Down Date: Tue, 15 Jun 2021 17:52:56 +0100 Subject: printk: index: Add indexing support to dev_printk While for most kinds of issues we have counters, tracepoints, or metrics with a stable interface which can reliably be used to indicate issues, in order to react to production issues quickly we sometimes need to work with the interface which most kernel developers naturally use when developing: printk, and printk-esques like dev_printk. dev_printk is by far the most likely custom subsystem printk to benefit from the printk indexing infrastructure, since niche device issues brought about by production changes, firmware upgrades, and the like are one of the most common things that we need printk infrastructure's assistance to monitor. Often these errors were never expected to practically manifest in reality, and exhibit in code without extensive (or any) metrics present. As such, there are typically very few options for issue detection available to those with large fleets at the time the incident happens, and we thus benefit strongly from monitoring netconsole in these instances. As such, add the infrastructure for dev_printk to be indexed in the printk index. Even on a minimal kernel config, the coverage of the base kernel's printk index is significantly improved: Before: [root@ktst ~]# wc -l /sys/kernel/debug/printk/index/vmlinux 4497 /sys/kernel/debug/printk/index/vmlinux After: [root@ktst ~]# wc -l /sys/kernel/debug/printk/index/vmlinux 5573 /sys/kernel/debug/printk/index/vmlinux In terms of implementation, in order to trivially disambiguate them, dev_printk is now a macro which wraps _dev_printk. Signed-off-by: Chris Down Cc: Petr Mladek Cc: Greg Kroah-Hartman Cc: Rasmus Villemoes Reviewed-by: Petr Mladek Tested-by: Petr Mladek Acked-by: Andy Shevchenko Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/959c7aed1017cb2c9de922e0a820d397e29c6a5a.1623775748.git.chris@chrisdown.name --- include/linux/dev_printk.h | 66 ++++++++++++++++++++++++++++++++++------------ 1 file changed, 49 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dev_printk.h b/include/linux/dev_printk.h index 82d3d46005a1..8904063d4c9f 100644 --- a/include/linux/dev_printk.h +++ b/include/linux/dev_printk.h @@ -38,8 +38,8 @@ __printf(3, 4) __cold int dev_printk_emit(int level, const struct device *dev, const char *fmt, ...); __printf(3, 4) __cold -void dev_printk(const char *level, const struct device *dev, - const char *fmt, ...); +void _dev_printk(const char *level, const struct device *dev, + const char *fmt, ...); __printf(2, 3) __cold void _dev_emerg(const struct device *dev, const char *fmt, ...); __printf(2, 3) __cold @@ -69,7 +69,7 @@ static inline void __dev_printk(const char *level, const struct device *dev, struct va_format *vaf) {} static inline __printf(3, 4) -void dev_printk(const char *level, const struct device *dev, +void _dev_printk(const char *level, const struct device *dev, const char *fmt, ...) {} @@ -97,25 +97,57 @@ void _dev_info(const struct device *dev, const char *fmt, ...) #endif +/* + * Need to take variadic arguments even though we don't use them, as dev_fmt() + * may only just have been expanded and may result in multiple arguments. + */ +#define dev_printk_index_emit(level, fmt, ...) \ + printk_index_subsys_emit("%s %s: ", level, fmt) + +#define dev_printk_index_wrap(_p_func, level, dev, fmt, ...) \ + ({ \ + dev_printk_index_emit(level, fmt); \ + _p_func(dev, fmt, ##__VA_ARGS__); \ + }) + +/* + * Some callsites directly call dev_printk rather than going through the + * dev_ infrastructure, so we need to emit here as well as inside those + * level-specific macros. Only one index entry will be produced, either way, + * since dev_printk's `fmt` isn't known at compile time if going through the + * dev_ macros. + * + * dev_fmt() isn't called for dev_printk when used directly, as it's used by + * the dev_ macros internally which already have dev_fmt() processed. + * + * We also can't use dev_printk_index_wrap directly, because we have a separate + * level to process. + */ +#define dev_printk(level, dev, fmt, ...) \ + ({ \ + dev_printk_index_emit(level, fmt); \ + _dev_printk(level, dev, fmt, ##__VA_ARGS__); \ + }) + /* * #defines for all the dev_ macros to prefix with whatever * possible use of #define dev_fmt(fmt) ... */ -#define dev_emerg(dev, fmt, ...) \ - _dev_emerg(dev, dev_fmt(fmt), ##__VA_ARGS__) -#define dev_crit(dev, fmt, ...) \ - _dev_crit(dev, dev_fmt(fmt), ##__VA_ARGS__) -#define dev_alert(dev, fmt, ...) \ - _dev_alert(dev, dev_fmt(fmt), ##__VA_ARGS__) -#define dev_err(dev, fmt, ...) \ - _dev_err(dev, dev_fmt(fmt), ##__VA_ARGS__) -#define dev_warn(dev, fmt, ...) \ - _dev_warn(dev, dev_fmt(fmt), ##__VA_ARGS__) -#define dev_notice(dev, fmt, ...) \ - _dev_notice(dev, dev_fmt(fmt), ##__VA_ARGS__) -#define dev_info(dev, fmt, ...) \ - _dev_info(dev, dev_fmt(fmt), ##__VA_ARGS__) +#define dev_emerg(dev, fmt, ...) \ + dev_printk_index_wrap(_dev_emerg, KERN_EMERG, dev, dev_fmt(fmt), ##__VA_ARGS__) +#define dev_crit(dev, fmt, ...) \ + dev_printk_index_wrap(_dev_crit, KERN_CRIT, dev, dev_fmt(fmt), ##__VA_ARGS__) +#define dev_alert(dev, fmt, ...) \ + dev_printk_index_wrap(_dev_alert, KERN_ALERT, dev, dev_fmt(fmt), ##__VA_ARGS__) +#define dev_err(dev, fmt, ...) \ + dev_printk_index_wrap(_dev_err, KERN_ERR, dev, dev_fmt(fmt), ##__VA_ARGS__) +#define dev_warn(dev, fmt, ...) \ + dev_printk_index_wrap(_dev_warn, KERN_WARNING, dev, dev_fmt(fmt), ##__VA_ARGS__) +#define dev_notice(dev, fmt, ...) \ + dev_printk_index_wrap(_dev_notice, KERN_NOTICE, dev, dev_fmt(fmt), ##__VA_ARGS__) +#define dev_info(dev, fmt, ...) \ + dev_printk_index_wrap(_dev_info, KERN_INFO, dev, dev_fmt(fmt), ##__VA_ARGS__) #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) -- cgit v1.2.3 From ec03f18cc222bb7bec074ce7845c157d1c5195f6 Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Mon, 19 Jul 2021 11:03:17 +0300 Subject: clk: at91: add register definition for sama7g5's master clock Add register definitions for SAMA7G5's master clock. These would be also used by architecture specific power saving code. Signed-off-by: Claudiu Beznea Signed-off-by: Nicolas Ferre Link: https://lore.kernel.org/r/20210719080317.1045832-3-claudiu.beznea@microchip.com --- include/linux/clk/at91_pmc.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk/at91_pmc.h b/include/linux/clk/at91_pmc.h index a4f82e836a7c..ccb3f034bfa9 100644 --- a/include/linux/clk/at91_pmc.h +++ b/include/linux/clk/at91_pmc.h @@ -137,6 +137,32 @@ #define AT91_PMC_PLLADIV2_ON (1 << 12) #define AT91_PMC_H32MXDIV BIT(24) +#define AT91_PMC_MCR_V2 0x30 /* Master Clock Register [SAMA7G5 only] */ +#define AT91_PMC_MCR_V2_ID_MSK (0xF) +#define AT91_PMC_MCR_V2_ID(_id) ((_id) & AT91_PMC_MCR_V2_ID_MSK) +#define AT91_PMC_MCR_V2_CMD (1 << 7) +#define AT91_PMC_MCR_V2_DIV (7 << 8) +#define AT91_PMC_MCR_V2_DIV1 (0 << 8) +#define AT91_PMC_MCR_V2_DIV2 (1 << 8) +#define AT91_PMC_MCR_V2_DIV4 (2 << 8) +#define AT91_PMC_MCR_V2_DIV8 (3 << 8) +#define AT91_PMC_MCR_V2_DIV16 (4 << 8) +#define AT91_PMC_MCR_V2_DIV32 (5 << 8) +#define AT91_PMC_MCR_V2_DIV64 (6 << 8) +#define AT91_PMC_MCR_V2_DIV3 (7 << 8) +#define AT91_PMC_MCR_V2_CSS (0x1F << 16) +#define AT91_PMC_MCR_V2_CSS_MD_SLCK (0 << 16) +#define AT91_PMC_MCR_V2_CSS_TD_SLCK (1 << 16) +#define AT91_PMC_MCR_V2_CSS_MAINCK (2 << 16) +#define AT91_PMC_MCR_V2_CSS_MCK0 (3 << 16) +#define AT91_PMC_MCR_V2_CSS_SYSPLL (5 << 16) +#define AT91_PMC_MCR_V2_CSS_DDRPLL (6 << 16) +#define AT91_PMC_MCR_V2_CSS_IMGPLL (7 << 16) +#define AT91_PMC_MCR_V2_CSS_BAUDPLL (8 << 16) +#define AT91_PMC_MCR_V2_CSS_AUDIOPLL (9 << 16) +#define AT91_PMC_MCR_V2_CSS_ETHPLL (10 << 16) +#define AT91_PMC_MCR_V2_EN (1 << 28) + #define AT91_PMC_XTALF 0x34 /* Main XTAL Frequency Register [SAMA7G5 only] */ #define AT91_PMC_USB 0x38 /* USB Clock Register [some SAM9 only] */ -- cgit v1.2.3 From 0189cb57b96ff92f75e3680b3710a46dacd6509f Mon Sep 17 00:00:00 2001 From: Xiyu Yang Date: Mon, 19 Jul 2021 13:59:45 +0800 Subject: fbmem: Convert from atomic_t to refcount_t on fb_info->count refcount_t type and corresponding API can protect refcounters from accidental underflow and overflow and further use-after-free situations. Signed-off-by: Xiyu Yang Signed-off-by: Xin Tan Signed-off-by: Sam Ravnborg Link: https://patchwork.freedesktop.org/patch/msgid/1626674392-55857-1-git-send-email-xiyuyang19@fudan.edu.cn --- include/linux/fb.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index a8dccd23c249..9023739e9a42 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -2,6 +2,7 @@ #ifndef _LINUX_FB_H #define _LINUX_FB_H +#include #include #include @@ -435,7 +436,7 @@ struct fb_tile_ops { struct fb_info { - atomic_t count; + refcount_t count; int node; int flags; /* -- cgit v1.2.3 From d6371c76e20d7d3f61b05fd67b596af4d14a8886 Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Mon, 19 Jul 2021 09:51:34 +0100 Subject: bpf: Fix OOB read when printing XDP link fdinfo We got the following UBSAN report on one of our testing machines: ================================================================================ UBSAN: array-index-out-of-bounds in kernel/bpf/syscall.c:2389:24 index 6 is out of range for type 'char *[6]' CPU: 43 PID: 930921 Comm: systemd-coredum Tainted: G O 5.10.48-cloudflare-kasan-2021.7.0 #1 Hardware name: Call Trace: dump_stack+0x7d/0xa3 ubsan_epilogue+0x5/0x40 __ubsan_handle_out_of_bounds.cold+0x43/0x48 ? seq_printf+0x17d/0x250 bpf_link_show_fdinfo+0x329/0x380 ? bpf_map_value_size+0xe0/0xe0 ? put_files_struct+0x20/0x2d0 ? __kasan_kmalloc.constprop.0+0xc2/0xd0 seq_show+0x3f7/0x540 seq_read_iter+0x3f8/0x1040 seq_read+0x329/0x500 ? seq_read_iter+0x1040/0x1040 ? __fsnotify_parent+0x80/0x820 ? __fsnotify_update_child_dentry_flags+0x380/0x380 vfs_read+0x123/0x460 ksys_read+0xed/0x1c0 ? __x64_sys_pwrite64+0x1f0/0x1f0 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xa9 ================================================================================ ================================================================================ UBSAN: object-size-mismatch in kernel/bpf/syscall.c:2384:2 From the report, we can infer that some array access in bpf_link_show_fdinfo at index 6 is out of bounds. The obvious candidate is bpf_link_type_strs[BPF_LINK_TYPE_XDP] with BPF_LINK_TYPE_XDP == 6. It turns out that BPF_LINK_TYPE_XDP is missing from bpf_types.h and therefore doesn't have an entry in bpf_link_type_strs: pos: 0 flags: 02000000 mnt_id: 13 link_type: (null) link_id: 4 prog_tag: bcf7977d3b93787c prog_id: 4 ifindex: 1 Fixes: aa8d3a716b59 ("bpf, xdp: Add bpf_link-based XDP attachment API") Signed-off-by: Lorenz Bauer Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210719085134.43325-2-lmb@cloudflare.com --- include/linux/bpf_types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index a9db1eae6796..ae3ac3a2018c 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -134,4 +134,5 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_CGROUP, cgroup) BPF_LINK_TYPE(BPF_LINK_TYPE_ITER, iter) #ifdef CONFIG_NET BPF_LINK_TYPE(BPF_LINK_TYPE_NETNS, netns) +BPF_LINK_TYPE(BPF_LINK_TYPE_XDP, xdp) #endif -- cgit v1.2.3 From c715def51591a874a9fcfdc9a05d543e8797e697 Mon Sep 17 00:00:00 2001 From: Hridya Valsaraju Date: Mon, 12 Jul 2021 21:07:38 -0700 Subject: dma-buf: Delete the DMA-BUF attachment sysfs statistics MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The DMA-BUF attachment statistics form a subset of the DMA-BUF sysfs statistics that recently merged to the drm-misc tree. They are not UABI yet since they have not merged to the upstream Linux kernel. Since there has been a reported a performance regression due to the overhead of sysfs directory creation/teardown during dma_buf_attach()/dma_buf_detach(), this patch deletes the DMA-BUF attachment statistics from sysfs. Fixes: bdb8d06dfefd ("dmabuf: Add the capability to expose DMA-BUF stats in sysfs") Signed-off-by: Hridya Valsaraju Reviewed-by: Christian König Reviewed-by: Greg Kroah-Hartman Link: https://patchwork.freedesktop.org/patch/msgid/20210713040742.2680135-1-hridya@google.com Signed-off-by: Christian König --- include/linux/dma-buf.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 2b814fde0d11..678b2006be78 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -444,15 +444,6 @@ struct dma_buf { struct dma_buf_sysfs_entry { struct kobject kobj; struct dma_buf *dmabuf; - - /** - * @sysfs_entry.attachment_uid: - * - * This is protected by the dma_resv_lock() on @resv and is - * incremented on each attach. - */ - unsigned int attachment_uid; - struct kset *attach_stats_kset; } *sysfs_entry; #endif }; @@ -504,7 +495,6 @@ struct dma_buf_attach_ops { * @importer_ops: importer operations for this attachment, if provided * dma_buf_map/unmap_attachment() must be called with the dma_resv lock held. * @importer_priv: importer specific attachment data. - * @sysfs_entry: For exposing information about this attachment in sysfs. * * This structure holds the attachment information between the dma_buf buffer * and its user device(s). The list contains one attachment struct per device @@ -525,13 +515,6 @@ struct dma_buf_attachment { const struct dma_buf_attach_ops *importer_ops; void *importer_priv; void *priv; -#ifdef CONFIG_DMABUF_SYSFS_STATS - /* for sysfs stats */ - struct dma_buf_attach_sysfs_entry { - struct kobject kobj; - unsigned int map_counter; - } *sysfs_entry; -#endif }; /** -- cgit v1.2.3 From 0fac6aa098edf91ba65370da03811d9aba5715a9 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 19 Jul 2021 20:14:42 +0300 Subject: net: dsa: sja1105: delete the best_effort_vlan_filtering mode Simply put, the best-effort VLAN filtering mode relied on VLAN retagging from a bridge VLAN towards a tag_8021q sub-VLAN in order to be able to decode the source port in the tagger, but the VLAN retagging implementation inside the sja1105 chips is not the best and we were relying on marginal operating conditions. The most notable limitation of the best-effort VLAN filtering mode is its incapacity to treat this case properly: ip link add br0 type bridge vlan_filtering 1 ip link set swp2 master br0 ip link set swp4 master br0 bridge vlan del dev swp4 vid 1 bridge vlan add dev swp4 vid 1 pvid When sending an untagged packet through swp2, the expectation is for it to be forwarded to swp4 as egress-tagged (so it will contain VLAN ID 1 on egress). But the switch will send it as egress-untagged. There was an attempt to fix this here: https://patchwork.kernel.org/project/netdevbpf/patch/20210407201452.1703261-2-olteanv@gmail.com/ but it failed miserably because it broke PTP RX timestamping, in a way that cannot be corrected due to hardware issues related to VLAN retagging. So with either PTP broken or pushing VLAN headers on egress for untagged packets being broken, the sad reality is that the best-effort VLAN filtering code is broken. Delete it. Note that this means there will be a temporary loss of functionality in this driver until it is replaced with something better (network stack RX/TX capability for "mode 2" as described in Documentation/networking/dsa/sja1105.rst, the "port under VLAN-aware bridge" case). We simply cannot keep this code until that driver rework is done, it is super bloated and tangled with tag_8021q. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/dsa/8021q.h | 9 +-------- include/linux/dsa/sja1105.h | 1 - 2 files changed, 1 insertion(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 1587961f1a7b..608607f904a5 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -35,8 +35,6 @@ struct dsa_8021q_context { __be16 proto; }; -#define DSA_8021Q_N_SUBVLAN 8 - int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled); int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port, @@ -50,21 +48,16 @@ int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port, struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, u16 tpid, u16 tci); -void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id, - int *subvlan); +void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id); u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port); u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port); -u16 dsa_8021q_rx_vid_subvlan(struct dsa_switch *ds, int port, u16 subvlan); - int dsa_8021q_rx_switch_id(u16 vid); int dsa_8021q_rx_source_port(u16 vid); -u16 dsa_8021q_rx_subvlan(u16 vid); - bool vid_is_dsa_8021q_rxvlan(u16 vid); bool vid_is_dsa_8021q_txvlan(u16 vid); diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index b6089b88314c..0eadc7ac44ec 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -59,7 +59,6 @@ struct sja1105_skb_cb { ((struct sja1105_skb_cb *)((skb)->cb)) struct sja1105_port { - u16 subvlan_map[DSA_8021Q_N_SUBVLAN]; struct kthread_worker *xmit_worker; struct kthread_work xmit_work; struct sk_buff_head xmit_queue; -- cgit v1.2.3 From 8afbea187d31e4e9beb83b7a316d16b7879c2799 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 19 Jul 2021 20:14:45 +0300 Subject: net: dsa: tag_8021q: remove struct packet_type declaration This is no longer necessary since tag_8021q doesn't register itself as a full-blown tagger anymore. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/dsa/8021q.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 608607f904a5..5f01dea7d5b6 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -11,7 +11,6 @@ struct dsa_switch; struct sk_buff; struct net_device; -struct packet_type; struct dsa_8021q_context; struct dsa_8021q_crosschip_link { -- cgit v1.2.3 From cedf467064b6b8764fdb2ee6b9e3d18bc81a9d8f Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 19 Jul 2021 20:14:46 +0300 Subject: net: dsa: tag_8021q: create dsa_tag_8021q_{register,unregister} helpers In preparation of moving tag_8021q to core DSA, move all initialization and teardown related to tag_8021q which is currently done by drivers in 2 functions called "register" and "unregister". These will gather more functionality in future patches, which will better justify the chosen naming scheme. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/dsa/8021q.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 5f01dea7d5b6..9945898a90c3 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -34,6 +34,12 @@ struct dsa_8021q_context { __be16 proto; }; +struct dsa_8021q_context *dsa_tag_8021q_register(struct dsa_switch *ds, + const struct dsa_8021q_ops *ops, + __be16 proto); + +void dsa_tag_8021q_unregister(struct dsa_8021q_context *ctx); + int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled); int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port, -- cgit v1.2.3 From d7b1fd520d5d4271f4ab9b1671afbdcd868039d3 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 19 Jul 2021 20:14:48 +0300 Subject: net: dsa: let the core manage the tag_8021q context The basic problem description is as follows: Be there 3 switches in a daisy chain topology: | sw0p0 sw0p1 sw0p2 sw0p3 sw0p4 [ user ] [ user ] [ user ] [ dsa ] [ cpu ] | +---------+ | sw1p0 sw1p1 sw1p2 sw1p3 sw1p4 [ user ] [ user ] [ user ] [ dsa ] [ dsa ] | +---------+ | sw2p0 sw2p1 sw2p2 sw2p3 sw2p4 [ user ] [ user ] [ user ] [ user ] [ dsa ] The CPU will not be able to ping through the user ports of the bottom-most switch (like for example sw2p0), simply because tag_8021q was not coded up for this scenario - it has always assumed DSA switch trees with a single switch. To add support for the topology above, we must admit that the RX VLAN of sw2p0 must be added on some ports of switches 0 and 1 as well. This is in fact a textbook example of thing that can use the cross-chip notifier framework that DSA has set up in switch.c. There is only one problem: core DSA (switch.c) is not able right now to make the connection between a struct dsa_switch *ds and a struct dsa_8021q_context *ctx. Right now, it is drivers who call into tag_8021q.c and always provide a struct dsa_8021q_context *ctx pointer, and tag_8021q.c calls them back with the .tag_8021q_vlan_{add,del} methods. But with cross-chip notifiers, it is possible for tag_8021q to call drivers without drivers having ever asked for anything. A good example is right above: when sw2p0 wants to set itself up for tag_8021q, the .tag_8021q_vlan_add method needs to be called for switches 1 and 0, so that they transport sw2p0's VLANs towards the CPU without dropping them. So instead of letting drivers manage the tag_8021q context, add a tag_8021q_ctx pointer inside of struct dsa_switch, which will be populated when dsa_tag_8021q_register() returns success. The patch is fairly long-winded because we are partly reverting commit 5899ee367ab3 ("net: dsa: tag_8021q: add a context structure") which made the driver-facing tag_8021q API use "ctx" instead of "ds". Now that we can access "ctx" directly from "ds", this is no longer needed. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/dsa/8021q.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 9945898a90c3..77939c0c8dd5 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -34,20 +34,20 @@ struct dsa_8021q_context { __be16 proto; }; -struct dsa_8021q_context *dsa_tag_8021q_register(struct dsa_switch *ds, - const struct dsa_8021q_ops *ops, - __be16 proto); +int dsa_tag_8021q_register(struct dsa_switch *ds, + const struct dsa_8021q_ops *ops, + __be16 proto); -void dsa_tag_8021q_unregister(struct dsa_8021q_context *ctx); +void dsa_tag_8021q_unregister(struct dsa_switch *ds); -int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled); +int dsa_8021q_setup(struct dsa_switch *ds, bool enabled); -int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port, - struct dsa_8021q_context *other_ctx, +int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port, + struct dsa_switch *other_ds, int other_port); -int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port, - struct dsa_8021q_context *other_ctx, +int dsa_8021q_crosschip_bridge_leave(struct dsa_switch *ds, int port, + struct dsa_switch *other_ds, int other_port); struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, -- cgit v1.2.3 From 5da11eb407340233a6111c563419e19685a062a4 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 19 Jul 2021 20:14:49 +0300 Subject: net: dsa: make tag_8021q operations part of the core Make tag_8021q a more central element of DSA and move the 2 driver specific operations outside of struct dsa_8021q_context (which is supposed to hold dynamic data and not really constant function pointers). Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/dsa/8021q.h | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 77939c0c8dd5..0bda08fb2f16 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -21,22 +21,14 @@ struct dsa_8021q_crosschip_link { refcount_t refcount; }; -struct dsa_8021q_ops { - int (*vlan_add)(struct dsa_switch *ds, int port, u16 vid, u16 flags); - int (*vlan_del)(struct dsa_switch *ds, int port, u16 vid); -}; - struct dsa_8021q_context { - const struct dsa_8021q_ops *ops; struct dsa_switch *ds; struct list_head crosschip_links; /* EtherType of RX VID, used for filtering on master interface */ __be16 proto; }; -int dsa_tag_8021q_register(struct dsa_switch *ds, - const struct dsa_8021q_ops *ops, - __be16 proto); +int dsa_tag_8021q_register(struct dsa_switch *ds, __be16 proto); void dsa_tag_8021q_unregister(struct dsa_switch *ds); -- cgit v1.2.3 From 328621f6131f667c5c328bb72d45442fd76efb81 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 19 Jul 2021 20:14:50 +0300 Subject: net: dsa: tag_8021q: absorb dsa_8021q_setup into dsa_tag_8021q_{,un}register Right now, setting up tag_8021q is a 2-step operation for a driver, first the context structure needs to be created, then the VLANs need to be installed on the ports. A similar thing is true for teardown. Merge the 2 steps into the register/unregister methods, to be as transparent as possible for the driver as to what tag_8021q does behind the scenes. This also gets rid of the funny "bool setup == true means setup, == false means teardown" API that tag_8021q used to expose. Note that dsa_tag_8021q_register() must be called at least in the .setup() driver method and never earlier (like in the driver probe function). This is because the DSA switch tree is not initialized at probe time, and the cross-chip notifiers will not work. For symmetry with .setup(), the unregister method should be put in .teardown(). Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/dsa/8021q.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 0bda08fb2f16..9cf2c99eb668 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -32,8 +32,6 @@ int dsa_tag_8021q_register(struct dsa_switch *ds, __be16 proto); void dsa_tag_8021q_unregister(struct dsa_switch *ds); -int dsa_8021q_setup(struct dsa_switch *ds, bool enabled); - int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port, struct dsa_switch *other_ds, int other_port); -- cgit v1.2.3 From c64b9c05045a21a5258f6dbd81d94a2a22ff73a2 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 19 Jul 2021 20:14:52 +0300 Subject: net: dsa: tag_8021q: add proper cross-chip notifier support The big problem which mandates cross-chip notifiers for tag_8021q is this: | sw0p0 sw0p1 sw0p2 sw0p3 sw0p4 [ user ] [ user ] [ user ] [ dsa ] [ cpu ] | +---------+ | sw1p0 sw1p1 sw1p2 sw1p3 sw1p4 [ user ] [ user ] [ user ] [ dsa ] [ dsa ] | +---------+ | sw2p0 sw2p1 sw2p2 sw2p3 sw2p4 [ user ] [ user ] [ user ] [ dsa ] [ dsa ] When the user runs: ip link add br0 type bridge ip link set sw0p0 master br0 ip link set sw2p0 master br0 It doesn't work. This is because dsa_8021q_crosschip_bridge_join() assumes that "ds" and "other_ds" are at most 1 hop away from each other, so it is sufficient to add the RX VLAN of {ds, port} into {other_ds, other_port} and vice versa and presto, the cross-chip link works. When there is another switch in the middle, such as in this case switch 1 with its DSA links sw1p3 and sw1p4, somebody needs to tell it about these VLANs too. Which is exactly why the problem is quadratic: when a port joins a bridge, for each port in the tree that's already in that same bridge we notify a tag_8021q VLAN addition of that port's RX VLAN to the entire tree. It is a very complicated web of VLANs. It must be mentioned that currently we install tag_8021q VLANs on too many ports (DSA links - to be precise, on all of them). For example, when sw2p0 joins br0, and assuming sw1p0 was part of br0 too, we add the RX VLAN of sw2p0 on the DSA links of switch 0 too, even though there isn't any port of switch 0 that is a member of br0 (at least yet). In theory we could notify only the switches which sit in between the port joining the bridge and the port reacting to that bridge_join event. But in practice that is impossible, because of the way 'link' properties are described in the device tree. The DSA bindings require DT writers to list out not only the real/physical DSA links, but in fact the entire routing table, like for example switch 0 above will have: sw0p3: port@3 { link = <&sw1p4 &sw2p4>; }; This was done because: /* TODO: ideally DSA ports would have a single dp->link_dp member, * and no dst->rtable nor this struct dsa_link would be needed, * but this would require some more complex tree walking, * so keep it stupid at the moment and list them all. */ but it is a perfect example of a situation where too much information is actively detrimential, because we are now in the position where we cannot distinguish a real DSA link from one that is put there to avoid the 'complex tree walking'. And because DT is ABI, there is not much we can change. And because we do not know which DSA links are real and which ones aren't, we can't really know if DSA switch A is in the data path between switches B and C, in the general case. So this is why tag_8021q RX VLANs are added on all DSA links, and probably why it will never change. On the other hand, at least the number of additions/deletions is well balanced, and this means that once we implement reference counting at the cross-chip notifier level a la fdb/mdb, there is absolutely zero need for a struct dsa_8021q_crosschip_link, it's all self-managing. In fact, with the tag_8021q notifiers emitted from the bridge join notifiers, it becomes so generic that sja1105 does not need to do anything anymore, we can just delete its implementation of the .crosschip_bridge_{join,leave} methods. Among other things we can simply delete is the home-grown implementation of sja1105_notify_crosschip_switches(). The reason why that is wrong is because it is not quadratic - it only covers remote switches to which we have a cross-chip bridging link and that does not cover in-between switches. This deletion is part of the same patch because sja1105 used to poke deep inside the guts of the tag_8021q context in order to do that. Because the cross-chip links went away, so needs the sja1105 code. Last but not least, dsa_8021q_setup_port() is simplified (and also renamed). Because our TAG_8021Q_VLAN_ADD notifier is designed to react on the CPU port too, the four dsa_8021q_vid_apply() calls: - 1 for RX VLAN on user port - 1 for the user port's RX VLAN on the CPU port - 1 for TX VLAN on user port - 1 for the user port's TX VLAN on the CPU port now get squashed into only 2 notifier calls via dsa_port_tag_8021q_vlan_add. And because the notifiers to add and to delete a tag_8021q VLAN are distinct, now we finally break up the port setup and teardown into separate functions instead of relying on a "bool enabled" flag which tells us what to do. Arguably it should have been this way from the get go. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/dsa/8021q.h | 16 +++------------- 1 file changed, 3 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 9cf2c99eb668..ec5abfcdefd1 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -11,19 +11,17 @@ struct dsa_switch; struct sk_buff; struct net_device; -struct dsa_8021q_context; -struct dsa_8021q_crosschip_link { +struct dsa_tag_8021q_vlan { struct list_head list; int port; - struct dsa_8021q_context *other_ctx; - int other_port; + u16 vid; refcount_t refcount; }; struct dsa_8021q_context { struct dsa_switch *ds; - struct list_head crosschip_links; + struct list_head vlans; /* EtherType of RX VID, used for filtering on master interface */ __be16 proto; }; @@ -32,14 +30,6 @@ int dsa_tag_8021q_register(struct dsa_switch *ds, __be16 proto); void dsa_tag_8021q_unregister(struct dsa_switch *ds); -int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port, - struct dsa_switch *other_ds, - int other_port); - -int dsa_8021q_crosschip_bridge_leave(struct dsa_switch *ds, int port, - struct dsa_switch *other_ds, - int other_port); - struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, u16 tpid, u16 tci); -- cgit v1.2.3 From 8b72b301b442907742c1af1b8fcb52e351a2aac1 Mon Sep 17 00:00:00 2001 From: Xu Liang Date: Mon, 19 Jul 2021 13:32:11 +0800 Subject: net: phy: add API to read 802.3-c45 IDs Add API to read 802.3-c45 IDs so that C22/C45 mixed device can use C45 APIs without failing ID checks. Signed-off-by: Xu Liang Acked-by: Hauke Mehrtens Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 3b80dc3ed68b..736e1d1a47c4 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1431,6 +1431,7 @@ static inline int phy_device_register(struct phy_device *phy) static inline void phy_device_free(struct phy_device *phydev) { } #endif /* CONFIG_PHYLIB */ void phy_device_remove(struct phy_device *phydev); +int phy_get_c45_ids(struct phy_device *phydev); int phy_init_hw(struct phy_device *phydev); int phy_suspend(struct phy_device *phydev); int phy_resume(struct phy_device *phydev); -- cgit v1.2.3 From e1ca90b7cc5cb5d3a38321cbb65ad36a59fcb574 Mon Sep 17 00:00:00 2001 From: Naveen Krishna Chatradhi Date: Wed, 30 Jun 2021 20:58:24 +0530 Subject: EDAC/mc: Add new HBM2 memory type Add a new entry to 'enum mem_type' and a new string to 'edac_mem_types[]' for HBM2 (High Bandwidth Memory Gen 2) new memory type. Reviewed-by: Yazen Ghannam Signed-off-by: Muralidhara M K Signed-off-by: Naveen Krishna Chatradhi Signed-off-by: Tony Luck Link: https://lore.kernel.org/r/20210630152828.162659-4-nchatrad@amd.com --- include/linux/edac.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/edac.h b/include/linux/edac.h index 76d3562d3006..4207d06996a4 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -184,6 +184,7 @@ static inline char *mc_event_error_type(const unsigned int err_type) * @MEM_DDR5: Unbuffered DDR5 RAM * @MEM_NVDIMM: Non-volatile RAM * @MEM_WIO2: Wide I/O 2. + * @MEM_HBM2: High bandwidth Memory Gen 2. */ enum mem_type { MEM_EMPTY = 0, @@ -212,6 +213,7 @@ enum mem_type { MEM_DDR5, MEM_NVDIMM, MEM_WIO2, + MEM_HBM2, }; #define MEM_FLAG_EMPTY BIT(MEM_EMPTY) @@ -239,6 +241,7 @@ enum mem_type { #define MEM_FLAG_DDR5 BIT(MEM_DDR5) #define MEM_FLAG_NVDIMM BIT(MEM_NVDIMM) #define MEM_FLAG_WIO2 BIT(MEM_WIO2) +#define MEM_FLAG_HBM2 BIT(MEM_HBM2) /** * enum edac_type - Error Detection and Correction capabilities and mode -- cgit v1.2.3 From fed31a4dd3adb5455df7c704de2abb639a1dc1c0 Mon Sep 17 00:00:00 2001 From: Zhouyi Zhou Date: Tue, 13 Jul 2021 08:56:45 +0800 Subject: rcu: Fix macro name CONFIG_TASKS_RCU_TRACE This commit fixes several typos where CONFIG_TASKS_RCU_TRACE should instead be CONFIG_TASKS_TRACE_RCU. Among other things, these typos could cause CONFIG_TASKS_TRACE_RCU_READ_MB=y kernels to suffer from memory-ordering bugs that could result in false-positive quiescent states and too-short grace periods. Signed-off-by: Zhouyi Zhou Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index d9680b798b21..955c82b4737c 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -167,7 +167,7 @@ void synchronize_rcu_tasks(void); # define synchronize_rcu_tasks synchronize_rcu # endif -# ifdef CONFIG_TASKS_RCU_TRACE +# ifdef CONFIG_TASKS_TRACE_RCU # define rcu_tasks_trace_qs(t) \ do { \ if (!likely(READ_ONCE((t)->trc_reader_checked)) && \ -- cgit v1.2.3 From dc7019b7d0e188d4093b34bd0747ed0d668c63bf Mon Sep 17 00:00:00 2001 From: Jens Wiklander Date: Mon, 14 Jun 2021 17:33:14 -0500 Subject: tee: add tee_shm_alloc_kernel_buf() Adds a new function tee_shm_alloc_kernel_buf() to allocate shared memory from a kernel driver. This function can later be made more lightweight by unnecessary dma-buf export. Cc: stable@vger.kernel.org Reviewed-by: Tyler Hicks Reviewed-by: Sumit Garg Signed-off-by: Jens Wiklander --- include/linux/tee_drv.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index 54269e47ac9a..8990f7628387 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -332,6 +332,7 @@ void *tee_get_drvdata(struct tee_device *teedev); * @returns a pointer to 'struct tee_shm' */ struct tee_shm *tee_shm_alloc(struct tee_context *ctx, size_t size, u32 flags); +struct tee_shm *tee_shm_alloc_kernel_buf(struct tee_context *ctx, size_t size); /** * tee_shm_register() - Register shared memory buffer -- cgit v1.2.3 From 376e4199e327a5cf29b8ec8fb0f64f3d8b429819 Mon Sep 17 00:00:00 2001 From: Sumit Garg Date: Mon, 14 Jun 2021 17:33:15 -0500 Subject: tee: Correct inappropriate usage of TEE_SHM_DMA_BUF flag Currently TEE_SHM_DMA_BUF flag has been inappropriately used to not register shared memory allocated for private usage by underlying TEE driver: OP-TEE in this case. So rather add a new flag as TEE_SHM_PRIV that can be utilized by underlying TEE drivers for private allocation and usage of shared memory. With this corrected, allow tee_shm_alloc_kernel_buf() to allocate a shared memory region without the backing of dma-buf. Cc: stable@vger.kernel.org Signed-off-by: Sumit Garg Co-developed-by: Tyler Hicks Signed-off-by: Tyler Hicks Reviewed-by: Jens Wiklander Reviewed-by: Sumit Garg Signed-off-by: Jens Wiklander --- include/linux/tee_drv.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index 8990f7628387..3ebfea0781f1 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -27,6 +27,7 @@ #define TEE_SHM_USER_MAPPED BIT(4) /* Memory mapped in user space */ #define TEE_SHM_POOL BIT(5) /* Memory allocated from pool */ #define TEE_SHM_KERNEL_MAPPED BIT(6) /* Memory mapped in kernel space */ +#define TEE_SHM_PRIV BIT(7) /* Memory private to TEE driver */ struct device; struct tee_device; -- cgit v1.2.3 From b48f8939b9ff593ebed20433bb53c51199920412 Mon Sep 17 00:00:00 2001 From: Ruslan Bilovol Date: Mon, 12 Jul 2021 14:55:26 +0200 Subject: usb: audio-v2: add ability to define feature unit descriptor Similar to UAC1 spec, UAC2 feature unit descriptor has variable size. Current audio-v2 feature unit descriptor structure is used for parsing descriptors, but can't be used to define your own descriptor. Add a new macro similar to what audio v1 already has. Signed-off-by: Ruslan Bilovol Signed-off-by: Pavel Hofman Link: https://lore.kernel.org/r/20210712125529.76070-2-pavel.hofman@ivitera.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/audio-v2.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/audio-v2.h b/include/linux/usb/audio-v2.h index ead8c9a47c6a..8fc2abd7aecb 100644 --- a/include/linux/usb/audio-v2.h +++ b/include/linux/usb/audio-v2.h @@ -156,6 +156,20 @@ struct uac2_feature_unit_descriptor { __u8 bmaControls[]; /* variable length */ } __attribute__((packed)); +#define UAC2_DT_FEATURE_UNIT_SIZE(ch) (6 + ((ch) + 1) * 4) + +/* As above, but more useful for defining your own descriptors: */ +#define DECLARE_UAC2_FEATURE_UNIT_DESCRIPTOR(ch) \ +struct uac2_feature_unit_descriptor_##ch { \ + __u8 bLength; \ + __u8 bDescriptorType; \ + __u8 bDescriptorSubtype; \ + __u8 bUnitID; \ + __u8 bSourceID; \ + __le32 bmaControls[ch + 1]; \ + __u8 iFeature; \ +} __packed + /* 4.7.2.10 Effect Unit Descriptor */ struct uac2_effect_unit_descriptor { -- cgit v1.2.3 From 77e21b50acab326173716830ef15a2f237f2d198 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 16 Jul 2021 08:16:28 +0200 Subject: vgaarb: remove VGA_DEFAULT_DEVICE MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The define is entirely unused. Signed-off-by: Christoph Hellwig Link: https://patchwork.freedesktop.org/patch/msgid/20210716061634.2446357-2-hch@lst.de Acked-by: Christian König Signed-off-by: Christian König --- include/linux/vgaarb.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vgaarb.h b/include/linux/vgaarb.h index dc6ddce92066..26ec8a057d2a 100644 --- a/include/linux/vgaarb.h +++ b/include/linux/vgaarb.h @@ -42,12 +42,6 @@ #define VGA_RSRC_NORMAL_IO 0x04 #define VGA_RSRC_NORMAL_MEM 0x08 -/* Passing that instead of a pci_dev to use the system "default" - * device, that is the one used by vgacon. Archs will probably - * have to provide their own vga_default_device(); - */ -#define VGA_DEFAULT_DEVICE (NULL) - struct pci_dev; /* For use by clients */ -- cgit v1.2.3 From b0b514abc4cf2841ee1e0833252b2e8a78401276 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 16 Jul 2021 08:16:29 +0200 Subject: vgaarb: remove vga_conflicts MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit vga_conflicts only has a single caller and none of the arch overrides mentioned in the comment. Just remove it and the thus dead check in the caller. Signed-off-by: Christoph Hellwig Link: https://patchwork.freedesktop.org/patch/msgid/20210716061634.2446357-3-hch@lst.de Acked-by: Christian König Signed-off-by: Christian König --- include/linux/vgaarb.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vgaarb.h b/include/linux/vgaarb.h index 26ec8a057d2a..ca5160218538 100644 --- a/include/linux/vgaarb.h +++ b/include/linux/vgaarb.h @@ -122,18 +122,6 @@ static inline void vga_set_default_device(struct pci_dev *pdev) { } static inline int vga_remove_vgacon(struct pci_dev *pdev) { return 0; } #endif -/* - * Architectures should define this if they have several - * independent PCI domains that can afford concurrent VGA - * decoding - */ -#ifndef __ARCH_HAS_VGA_CONFLICT -static inline int vga_conflicts(struct pci_dev *p1, struct pci_dev *p2) -{ - return 1; -} -#endif - #if defined(CONFIG_VGA_ARB) int vga_client_register(struct pci_dev *pdev, void *cookie, void (*irq_set_state)(void *cookie, bool state), -- cgit v1.2.3 From 45549c00d3ff05735e7ceb89b20e302301cd6b14 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 16 Jul 2021 08:16:30 +0200 Subject: vgaarb: move the kerneldoc for vga_set_legacy_decoding to vgaarb.c MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Kerneldoc comments should be at the implementation side, not in the header just declaring the prototype. Signed-off-by: Christoph Hellwig Link: https://patchwork.freedesktop.org/patch/msgid/20210716061634.2446357-4-hch@lst.de Acked-by: Christian König Signed-off-by: Christian König --- include/linux/vgaarb.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vgaarb.h b/include/linux/vgaarb.h index ca5160218538..fdce9007d57e 100644 --- a/include/linux/vgaarb.h +++ b/include/linux/vgaarb.h @@ -46,19 +46,6 @@ struct pci_dev; /* For use by clients */ -/** - * vga_set_legacy_decoding - * - * @pdev: pci device of the VGA card - * @decodes: bit mask of what legacy regions the card decodes - * - * Indicates to the arbiter if the card decodes legacy VGA IOs, - * legacy VGA Memory, both, or none. All cards default to both, - * the card driver (fbdev for example) should tell the arbiter - * if it has disabled legacy decoding, so the card can be left - * out of the arbitration process (and can be safe to take - * interrupts at any time. - */ #if defined(CONFIG_VGA_ARB) extern void vga_set_legacy_decoding(struct pci_dev *pdev, unsigned int decodes); -- cgit v1.2.3 From 6609176f56ad895ba25d4c120c707fb15f45aa4e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 16 Jul 2021 08:16:31 +0200 Subject: vgaarb: cleanup vgaarb.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Merge the different CONFIG_VGA_ARB ifdef blocks, remove superflous externs, and regularize the stubs for !CONFIG_VGA_ARB. Signed-off-by: Christoph Hellwig Link: https://patchwork.freedesktop.org/patch/msgid/20210716061634.2446357-5-hch@lst.de Acked-by: Christian König Signed-off-by: Christian König --- include/linux/vgaarb.h | 90 +++++++++++++++++++++++--------------------------- 1 file changed, 42 insertions(+), 48 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vgaarb.h b/include/linux/vgaarb.h index fdce9007d57e..05171fc7e26a 100644 --- a/include/linux/vgaarb.h +++ b/include/linux/vgaarb.h @@ -33,6 +33,8 @@ #include