From 874f670e6088d3bff3972ecd44c1cb00610f9183 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 23 Sep 2021 18:54:35 +0200 Subject: sched: Clean up the might_sleep() underscore zoo __might_sleep() vs. ___might_sleep() is hard to distinguish. Aside of that the three underscore variant is exposed to provide a checkpoint for rescheduling points which are distinct from blocking points. They are semantically a preemption point which means that scheduling is state preserving. A real blocking operation, e.g. mutex_lock(), wait*(), which cannot preserve a task state which is not equal to RUNNING. While technically blocking on a "sleeping" spinlock in RT enabled kernels falls into the voluntary scheduling category because it has to wait until the contended spin/rw lock becomes available, the RT lock substitution code can semantically be mapped to a voluntary preemption because the RT lock substitution code and the scheduler are providing mechanisms to preserve the task state and to take regular non-lock related wakeups into account. Rename ___might_sleep() to __might_resched() to make the distinction of these functions clear. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210923165357.928693482@linutronix.de --- include/linux/kernel.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 2776423a587e..5e4ae54da73e 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -111,7 +111,7 @@ static __always_inline void might_resched(void) #endif /* CONFIG_PREEMPT_* */ #ifdef CONFIG_DEBUG_ATOMIC_SLEEP -extern void ___might_sleep(const char *file, int line, int preempt_offset); +extern void __might_resched(const char *file, int line, int preempt_offset); extern void __might_sleep(const char *file, int line, int preempt_offset); extern void __cant_sleep(const char *file, int line, int preempt_offset); extern void __cant_migrate(const char *file, int line); @@ -168,8 +168,8 @@ extern void __cant_migrate(const char *file, int line); */ # define non_block_end() WARN_ON(current->non_block_count-- == 0) #else - static inline void ___might_sleep(const char *file, int line, - int preempt_offset) { } + static inline void __might_resched(const char *file, int line, + int preempt_offset) { } static inline void __might_sleep(const char *file, int line, int preempt_offset) { } # define might_sleep() do { might_resched(); } while (0) -- cgit v1.2.3 From 42a387566c567603bafa1ec0c5b71c35cba83e86 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 23 Sep 2021 18:54:38 +0200 Subject: sched: Remove preempt_offset argument from __might_sleep() All callers hand in 0 and never will hand in anything else. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210923165358.054321586@linutronix.de --- include/linux/kernel.h | 7 +++---- kernel/sched/core.c | 4 ++-- mm/memory.c | 2 +- 3 files changed, 6 insertions(+), 7 deletions(-) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 5e4ae54da73e..f95ee786e4ef 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -112,7 +112,7 @@ static __always_inline void might_resched(void) #ifdef CONFIG_DEBUG_ATOMIC_SLEEP extern void __might_resched(const char *file, int line, int preempt_offset); -extern void __might_sleep(const char *file, int line, int preempt_offset); +extern void __might_sleep(const char *file, int line); extern void __cant_sleep(const char *file, int line, int preempt_offset); extern void __cant_migrate(const char *file, int line); @@ -129,7 +129,7 @@ extern void __cant_migrate(const char *file, int line); * supposed to. */ # define might_sleep() \ - do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0) + do { __might_sleep(__FILE__, __LINE__); might_resched(); } while (0) /** * cant_sleep - annotation for functions that cannot sleep * @@ -170,8 +170,7 @@ extern void __cant_migrate(const char *file, int line); #else static inline void __might_resched(const char *file, int line, int preempt_offset) { } - static inline void __might_sleep(const char *file, int line, - int preempt_offset) { } +static inline void __might_sleep(const char *file, int line) { } # define might_sleep() do { might_resched(); } while (0) # define cant_sleep() do { } while (0) # define cant_migrate() do { } while (0) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index c3943aa2f60c..2d790df62ec9 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -9475,7 +9475,7 @@ static inline int preempt_count_equals(int preempt_offset) return (nested == preempt_offset); } -void __might_sleep(const char *file, int line, int preempt_offset) +void __might_sleep(const char *file, int line) { unsigned int state = get_current_state(); /* @@ -9489,7 +9489,7 @@ void __might_sleep(const char *file, int line, int preempt_offset) (void *)current->task_state_change, (void *)current->task_state_change); - __might_resched(file, line, preempt_offset); + __might_resched(file, line, 0); } EXPORT_SYMBOL(__might_sleep); diff --git a/mm/memory.c b/mm/memory.c index 25fc46e87214..1cd1792c00f2 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -5255,7 +5255,7 @@ void __might_fault(const char *file, int line) return; if (pagefault_disabled()) return; - __might_sleep(file, line, 0); + __might_sleep(file, line); #if defined(CONFIG_DEBUG_ATOMIC_SLEEP) if (current->mm) might_lock_read(¤t->mm->mmap_lock); -- cgit v1.2.3 From 50e081b96e35e43b65591f40f7376204decd1cb5 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 23 Sep 2021 18:54:43 +0200 Subject: sched: Make RCU nest depth distinct in __might_resched() For !RT kernels RCU nest depth in __might_resched() is always expected to be 0, but on RT kernels it can be non zero while the preempt count is expected to be always 0. Instead of playing magic games in interpreting the 'preempt_offset' argument, rename it to 'offsets' and use the lower 8 bits for the expected preempt count, allow to hand in the expected RCU nest depth in the upper bits and adopt the __might_resched() code and related checks and printks. The affected call sites are updated in subsequent steps. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210923165358.243232823@linutronix.de --- include/linux/kernel.h | 4 ++-- include/linux/sched.h | 3 +++ kernel/sched/core.c | 28 ++++++++++++++++------------ 3 files changed, 21 insertions(+), 14 deletions(-) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index f95ee786e4ef..e8696e4a45aa 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -111,7 +111,7 @@ static __always_inline void might_resched(void) #endif /* CONFIG_PREEMPT_* */ #ifdef CONFIG_DEBUG_ATOMIC_SLEEP -extern void __might_resched(const char *file, int line, int preempt_offset); +extern void __might_resched(const char *file, int line, unsigned int offsets); extern void __might_sleep(const char *file, int line); extern void __cant_sleep(const char *file, int line, int preempt_offset); extern void __cant_migrate(const char *file, int line); @@ -169,7 +169,7 @@ extern void __cant_migrate(const char *file, int line); # define non_block_end() WARN_ON(current->non_block_count-- == 0) #else static inline void __might_resched(const char *file, int line, - int preempt_offset) { } + unsigned int offsets) { } static inline void __might_sleep(const char *file, int line) { } # define might_sleep() do { might_resched(); } while (0) # define cant_sleep() do { } while (0) diff --git a/include/linux/sched.h b/include/linux/sched.h index 7a989f2487f8..b448c7460577 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2046,6 +2046,9 @@ extern int __cond_resched_lock(spinlock_t *lock); extern int __cond_resched_rwlock_read(rwlock_t *lock); extern int __cond_resched_rwlock_write(rwlock_t *lock); +#define MIGHT_RESCHED_RCU_SHIFT 8 +#define MIGHT_RESCHED_PREEMPT_MASK ((1U << MIGHT_RESCHED_RCU_SHIFT) - 1) + #define cond_resched_lock(lock) ({ \ __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET); \ __cond_resched_lock(lock); \ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 0a27cb8f72a9..8d3fa0768e5b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -9468,12 +9468,6 @@ void __init sched_init(void) } #ifdef CONFIG_DEBUG_ATOMIC_SLEEP -static inline int preempt_count_equals(int preempt_offset) -{ - int nested = preempt_count() + rcu_preempt_depth(); - - return (nested == preempt_offset); -} void __might_sleep(const char *file, int line) { @@ -9505,7 +9499,16 @@ static void print_preempt_disable_ip(int preempt_offset, unsigned long ip) print_ip_sym(KERN_ERR, ip); } -void __might_resched(const char *file, int line, int preempt_offset) +static inline bool resched_offsets_ok(unsigned int offsets) +{ + unsigned int nested = preempt_count(); + + nested += rcu_preempt_depth() << MIGHT_RESCHED_RCU_SHIFT; + + return nested == offsets; +} + +void __might_resched(const char *file, int line, unsigned int offsets) { /* Ratelimiting timestamp: */ static unsigned long prev_jiffy; @@ -9515,7 +9518,7 @@ void __might_resched(const char *file, int line, int preempt_offset) /* WARN_ON_ONCE() by default, no rate limit required: */ rcu_sleep_check(); - if ((preempt_count_equals(preempt_offset) && !irqs_disabled() && + if ((resched_offsets_ok(offsets) && !irqs_disabled() && !is_idle_task(current) && !current->non_block_count) || system_state == SYSTEM_BOOTING || system_state > SYSTEM_RUNNING || oops_in_progress) @@ -9534,11 +9537,11 @@ void __might_resched(const char *file, int line, int preempt_offset) in_atomic(), irqs_disabled(), current->non_block_count, current->pid, current->comm); pr_err("preempt_count: %x, expected: %x\n", preempt_count(), - preempt_offset); + offsets & MIGHT_RESCHED_PREEMPT_MASK); if (IS_ENABLED(CONFIG_PREEMPT_RCU)) { - pr_err("RCU nest depth: %d, expected: 0\n", - rcu_preempt_depth()); + pr_err("RCU nest depth: %d, expected: %u\n", + rcu_preempt_depth(), offsets >> MIGHT_RESCHED_RCU_SHIFT); } if (task_stack_end_corrupted(current)) @@ -9548,7 +9551,8 @@ void __might_resched(const char *file, int line, int preempt_offset) if (irqs_disabled()) print_irqtrace_events(current); - print_preempt_disable_ip(preempt_offset, preempt_disable_ip); + print_preempt_disable_ip(offsets & MIGHT_RESCHED_PREEMPT_MASK, + preempt_disable_ip); dump_stack(); add_taint(TAINT_WARN, LOCKDEP_STILL_OK); -- cgit v1.2.3 From d2635f2012a44e3d469ab9a4022162dbe0e53f21 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 5 Nov 2021 13:40:40 -0700 Subject: mm: create a new system state and fix core_kernel_text() core_kernel_text() considers that until system_state in at least SYSTEM_RUNNING, init memory is valid. But init memory is freed a few lines before setting SYSTEM_RUNNING, so we have a small period of time when core_kernel_text() is wrong. Create an intermediate system state called SYSTEM_FREEING_INIT that is set before starting freeing init memory, and use it in core_kernel_text() to report init memory invalid earlier. Link: https://lkml.kernel.org/r/9ecfdee7dd4d741d172cb93ff1d87f1c58127c9a.1633001016.git.christophe.leroy@csgroup.eu Signed-off-by: Christophe Leroy Cc: Gerald Schaefer Cc: Kefeng Wang Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Heiko Carstens Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 1 + init/main.c | 2 ++ kernel/extable.c | 2 +- 3 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 2776423a587e..471bc0593679 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -248,6 +248,7 @@ extern bool early_boot_irqs_disabled; extern enum system_states { SYSTEM_BOOTING, SYSTEM_SCHEDULING, + SYSTEM_FREEING_INITMEM, SYSTEM_RUNNING, SYSTEM_HALT, SYSTEM_POWER_OFF, diff --git a/init/main.c b/init/main.c index 3c4054a95545..767ee2672176 100644 --- a/init/main.c +++ b/init/main.c @@ -1506,6 +1506,8 @@ static int __ref kernel_init(void *unused) kernel_init_freeable(); /* need to finish all async __init code before freeing the memory */ async_synchronize_full(); + + system_state = SYSTEM_FREEING_INITMEM; kprobe_free_init_mem(); ftrace_free_init_mem(); kgdb_free_init_mem(); diff --git a/kernel/extable.c b/kernel/extable.c index b0ea5eb0c3b4..290661f68e6b 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -76,7 +76,7 @@ int notrace core_kernel_text(unsigned long addr) addr < (unsigned long)_etext) return 1; - if (system_state < SYSTEM_RUNNING && + if (system_state < SYSTEM_FREEING_INITMEM && init_kernel_text(addr)) return 1; return 0; -- cgit v1.2.3 From d2a8ebbf8192b84b11f1b204c4f7c602df32aeac Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 8 Nov 2021 18:32:12 -0800 Subject: kernel.h: split out container_of() and typeof_member() macros kernel.h is being used as a dump for all kinds of stuff for a long time. Here is the attempt cleaning it up by splitting out container_of() and typeof_member() macros. For time being include new header back to kernel.h to avoid twisted indirected includes for existing users. Note, there are _a lot_ of headers and modules that include kernel.h solely for one of these macros and this allows to unburden compiler for the twisted inclusion paths and to make new code cleaner in the future. Link: https://lkml.kernel.org/r/20211013170417.87909-3-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Cc: Boqun Feng Cc: Brendan Higgins Cc: Ingo Molnar Cc: Jonathan Cameron Cc: Laurent Pinchart Cc: Mauro Carvalho Chehab Cc: Miguel Ojeda Cc: Peter Zijlstra Cc: Rasmus Villemoes Cc: Sakari Ailus Cc: Thomas Gleixner Cc: Thorsten Leemhuis Cc: Waiman Long Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/container_of.h | 40 ++++++++++++++++++++++++++++++++++++++++ include/linux/kernel.h | 33 +-------------------------------- 2 files changed, 41 insertions(+), 32 deletions(-) create mode 100644 include/linux/container_of.h (limited to 'include/linux/kernel.h') diff --git a/include/linux/container_of.h b/include/linux/container_of.h new file mode 100644 index 000000000000..dd56019838c6 --- /dev/null +++ b/include/linux/container_of.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_CONTAINER_OF_H +#define _LINUX_CONTAINER_OF_H + +#include +#include + +#define typeof_member(T, m) typeof(((T*)0)->m) + +/** + * container_of - cast a member of a structure out to the containing structure + * @ptr: the pointer to the member. + * @type: the type of the container struct this is embedded in. + * @member: the name of the member within the struct. + * + */ +#define container_of(ptr, type, member) ({ \ + void *__mptr = (void *)(ptr); \ + BUILD_BUG_ON_MSG(!__same_type(*(ptr), ((type *)0)->member) && \ + !__same_type(*(ptr), void), \ + "pointer type mismatch in container_of()"); \ + ((type *)(__mptr - offsetof(type, member))); }) + +/** + * container_of_safe - cast a member of a structure out to the containing structure + * @ptr: the pointer to the member. + * @type: the type of the container struct this is embedded in. + * @member: the name of the member within the struct. + * + * If IS_ERR_OR_NULL(ptr), ptr is returned unchanged. + */ +#define container_of_safe(ptr, type, member) ({ \ + void *__mptr = (void *)(ptr); \ + BUILD_BUG_ON_MSG(!__same_type(*(ptr), ((type *)0)->member) && \ + !__same_type(*(ptr), void), \ + "pointer type mismatch in container_of()"); \ + IS_ERR_OR_NULL(__mptr) ? ERR_CAST(__mptr) : \ + ((type *)(__mptr - offsetof(type, member))); }) + +#endif /* _LINUX_CONTAINER_OF_H */ diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 471bc0593679..ed4465757cec 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -52,8 +53,6 @@ } \ ) -#define typeof_member(T, m) typeof(((T*)0)->m) - #define _RET_IP_ (unsigned long)__builtin_return_address(0) #define _THIS_IP_ ({ __label__ __here; __here: (unsigned long)&&__here; }) @@ -484,36 +483,6 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } #define __CONCAT(a, b) a ## b #define CONCATENATE(a, b) __CONCAT(a, b) -/** - * container_of - cast a member of a structure out to the containing structure - * @ptr: the pointer to the member. - * @type: the type of the container struct this is embedded in. - * @member: the name of the member within the struct. - * - */ -#define container_of(ptr, type, member) ({ \ - void *__mptr = (void *)(ptr); \ - BUILD_BUG_ON_MSG(!__same_type(*(ptr), ((type *)0)->member) && \ - !__same_type(*(ptr), void), \ - "pointer type mismatch in container_of()"); \ - ((type *)(__mptr - offsetof(type, member))); }) - -/** - * container_of_safe - cast a member of a structure out to the containing structure - * @ptr: the pointer to the member. - * @type: the type of the container struct this is embedded in. - * @member: the name of the member within the struct. - * - * If IS_ERR_OR_NULL(ptr), ptr is returned unchanged. - */ -#define container_of_safe(ptr, type, member) ({ \ - void *__mptr = (void *)(ptr); \ - BUILD_BUG_ON_MSG(!__same_type(*(ptr), ((type *)0)->member) && \ - !__same_type(*(ptr), void), \ - "pointer type mismatch in container_of()"); \ - IS_ERR_OR_NULL(__mptr) ? ERR_CAST(__mptr) : \ - ((type *)(__mptr - offsetof(type, member))); }) - /* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */ #ifdef CONFIG_FTRACE_MCOUNT_RECORD # define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD -- cgit v1.2.3 From e52340de11d8bca3ba35e5a72fea4f2a5b6abbbb Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Mon, 8 Nov 2021 18:32:43 -0800 Subject: kernel.h: split out instruction pointer accessors bottom_half.h needs _THIS_IP_ to be standalone, so split that and _RET_IP_ out from kernel.h into the new instruction_pointer.h. kernel.h directly needs them, so include it there and replace the include of kernel.h with this new file in bottom_half.h. Link: https://lkml.kernel.org/r/20211028161248.45232-1-andriy.shevchenko@linux.intel.com Signed-off-by: Stephen Rothwell Signed-off-by: Andy Shevchenko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bottom_half.h | 2 +- include/linux/instruction_pointer.h | 8 ++++++++ include/linux/kernel.h | 4 +--- 3 files changed, 10 insertions(+), 4 deletions(-) create mode 100644 include/linux/instruction_pointer.h (limited to 'include/linux/kernel.h') diff --git a/include/linux/bottom_half.h b/include/linux/bottom_half.h index 11d107d88d03..fc53e0ad56d9 100644 --- a/include/linux/bottom_half.h +++ b/include/linux/bottom_half.h @@ -2,7 +2,7 @@ #ifndef _LINUX_BH_H #define _LINUX_BH_H -#include +#include #include #if defined(CONFIG_PREEMPT_RT) || defined(CONFIG_TRACE_IRQFLAGS) diff --git a/include/linux/instruction_pointer.h b/include/linux/instruction_pointer.h new file mode 100644 index 000000000000..cda1f706eaeb --- /dev/null +++ b/include/linux/instruction_pointer.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_INSTRUCTION_POINTER_H +#define _LINUX_INSTRUCTION_POINTER_H + +#define _RET_IP_ (unsigned long)__builtin_return_address(0) +#define _THIS_IP_ ({ __label__ __here; __here: (unsigned long)&&__here; }) + +#endif /* _LINUX_INSTRUCTION_POINTER_H */ diff --git a/include/linux/kernel.h b/include/linux/kernel.h index ed4465757cec..46ca4404fb93 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -20,6 +20,7 @@ #include #include #include +#include #include #include @@ -53,9 +54,6 @@ } \ ) -#define _RET_IP_ (unsigned long)__builtin_return_address(0) -#define _THIS_IP_ ({ __label__ __here; __here: (unsigned long)&&__here; }) - /** * upper_32_bits - return bits 32-63 of a number * @n: the number we're accessing -- cgit v1.2.3 From a20deb3a348719adaf8c12e1bf4b599bfc51836e Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Mon, 8 Nov 2021 18:33:51 -0800 Subject: sections: move and rename core_kernel_data() to is_kernel_core_data() Move core_kernel_data() into sections.h and rename it to is_kernel_core_data(), also make it return bool value, then update all the callers. Link: https://lkml.kernel.org/r/20210930071143.63410-4-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviewed-by: Sergey Senozhatsky Cc: Arnd Bergmann Cc: Steven Rostedt Cc: Ingo Molnar Cc: "David S. Miller" Cc: Alexander Potapenko Cc: Alexei Starovoitov Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Christophe Leroy Cc: Dmitry Vyukov Cc: Ivan Kokshaysky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Paul Mackerras Cc: Petr Mladek Cc: Richard Henderson Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/sections.h | 16 ++++++++++++++++ include/linux/kernel.h | 1 - kernel/extable.c | 18 ------------------ kernel/trace/ftrace.c | 2 +- net/sysctl_net.c | 2 +- 5 files changed, 18 insertions(+), 21 deletions(-) (limited to 'include/linux/kernel.h') diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h index 614fc809de34..7cba8ff10d3a 100644 --- a/include/asm-generic/sections.h +++ b/include/asm-generic/sections.h @@ -128,6 +128,22 @@ static inline bool init_section_intersects(void *virt, size_t size) return memory_intersects(__init_begin, __init_end, virt, size); } +/** + * is_kernel_core_data - checks if the pointer address is located in the + * .data section + * + * @addr: address to check + * + * Returns: true if the address is located in .data, false otherwise. + * Note: On some archs it may return true for core RODATA, and false + * for others. But will always be true for core RW data. + */ +static inline bool is_kernel_core_data(unsigned long addr) +{ + return addr >= (unsigned long)_sdata && + addr < (unsigned long)_edata; +} + /** * is_kernel_rodata - checks if the pointer address is located in the * .rodata section diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 46ca4404fb93..23f57a2d5a13 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -227,7 +227,6 @@ extern char *next_arg(char *args, char **param, char **val); extern int core_kernel_text(unsigned long addr); extern int init_kernel_text(unsigned long addr); -extern int core_kernel_data(unsigned long addr); 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); diff --git a/kernel/extable.c b/kernel/extable.c index 290661f68e6b..0e3412b48bba 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -82,24 +82,6 @@ int notrace core_kernel_text(unsigned long addr) return 0; } -/** - * core_kernel_data - tell if addr points to kernel data - * @addr: address to test - * - * Returns true if @addr passed in is from the core kernel data - * section. - * - * Note: On some archs it may return true for core RODATA, and false - * for others. But will always be true for core RW data. - */ -int core_kernel_data(unsigned long addr) -{ - if (addr >= (unsigned long)_sdata && - addr < (unsigned long)_edata) - return 1; - return 0; -} - int __kernel_text_address(unsigned long addr) { if (kernel_text_address(addr)) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index feebf57c6458..7aaef2b78760 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -323,7 +323,7 @@ int __register_ftrace_function(struct ftrace_ops *ops) if (!ftrace_enabled && (ops->flags & FTRACE_OPS_FL_PERMANENT)) return -EBUSY; - if (!core_kernel_data((unsigned long)ops)) + if (!is_kernel_core_data((unsigned long)ops)) ops->flags |= FTRACE_OPS_FL_DYNAMIC; add_ftrace_ops(&ftrace_ops_list, ops); diff --git a/net/sysctl_net.c b/net/sysctl_net.c index f6cb0d4d114c..4b45ed631eb8 100644 --- a/net/sysctl_net.c +++ b/net/sysctl_net.c @@ -144,7 +144,7 @@ static void ensure_safe_net_sysctl(struct net *net, const char *path, addr = (unsigned long)ent->data; if (is_module_address(addr)) where = "module"; - else if (core_kernel_data(addr)) + else if (is_kernel_core_data(addr)) where = "kernel"; else continue; -- cgit v1.2.3 From b9ad8fe7b8cab3814d1de41e8ddca602b2646f4b Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Mon, 8 Nov 2021 18:33:54 -0800 Subject: sections: move is_kernel_inittext() into sections.h The is_kernel_inittext() and init_kernel_text() are with same functionality, let's just keep is_kernel_inittext() and move it into sections.h, then update all the callers. Link: https://lkml.kernel.org/r/20210930071143.63410-5-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviewed-by: Sergey Senozhatsky Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Arnd Bergmann Cc: Alexander Potapenko Cc: Alexei Starovoitov Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Christophe Leroy Cc: "David S. Miller" Cc: Dmitry Vyukov Cc: Ivan Kokshaysky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Paul Mackerras Cc: Petr Mladek Cc: Richard Henderson Cc: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kernel/unwind_orc.c | 2 +- include/asm-generic/sections.h | 14 ++++++++++++++ include/linux/kallsyms.h | 8 -------- include/linux/kernel.h | 1 - kernel/extable.c | 12 ++---------- 5 files changed, 17 insertions(+), 20 deletions(-) (limited to 'include/linux/kernel.h') diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index a1202536fc57..d92ec2ced059 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -175,7 +175,7 @@ static struct orc_entry *orc_find(unsigned long ip) } /* vmlinux .init slow lookup: */ - if (init_kernel_text(ip)) + if (is_kernel_inittext(ip)) return __orc_find(__start_orc_unwind_ip, __start_orc_unwind, __stop_orc_unwind_ip - __start_orc_unwind_ip, ip); diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h index 7cba8ff10d3a..f82806ca8756 100644 --- a/include/asm-generic/sections.h +++ b/include/asm-generic/sections.h @@ -158,4 +158,18 @@ static inline bool is_kernel_rodata(unsigned long addr) addr < (unsigned long)__end_rodata; } +/** + * is_kernel_inittext - checks if the pointer address is located in the + * .init.text section + * + * @addr: address to check + * + * Returns: true if the address is located in .init.text, false otherwise. + */ +static inline bool is_kernel_inittext(unsigned long addr) +{ + return addr >= (unsigned long)_sinittext && + addr < (unsigned long)_einittext; +} + #endif /* _ASM_GENERIC_SECTIONS_H_ */ diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index 62ce22b27ea8..bb5d9ec78e13 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -24,14 +24,6 @@ struct cred; struct module; -static inline int is_kernel_inittext(unsigned long addr) -{ - if (addr >= (unsigned long)_sinittext - && addr < (unsigned long)_einittext) - return 1; - return 0; -} - static inline int is_kernel_text(unsigned long addr) { if ((addr >= (unsigned long)_stext && addr < (unsigned long)_etext)) diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 23f57a2d5a13..be84ab369650 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -226,7 +226,6 @@ extern bool parse_option_str(const char *str, const char *option); extern char *next_arg(char *args, char **param, char **val); extern int core_kernel_text(unsigned long addr); -extern int init_kernel_text(unsigned long addr); 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); diff --git a/kernel/extable.c b/kernel/extable.c index 0e3412b48bba..6505207aa7e6 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -62,14 +62,6 @@ const struct exception_table_entry *search_exception_tables(unsigned long addr) return e; } -int init_kernel_text(unsigned long addr) -{ - if (addr >= (unsigned long)_sinittext && - addr < (unsigned long)_einittext) - return 1; - return 0; -} - int notrace core_kernel_text(unsigned long addr) { if (addr >= (unsigned long)_stext && @@ -77,7 +69,7 @@ int notrace core_kernel_text(unsigned long addr) return 1; if (system_state < SYSTEM_FREEING_INITMEM && - init_kernel_text(addr)) + is_kernel_inittext(addr)) return 1; return 0; } @@ -94,7 +86,7 @@ int __kernel_text_address(unsigned long addr) * Since we are after the module-symbols check, there's * no danger of address overlap: */ - if (init_kernel_text(addr)) + if (is_kernel_inittext(addr)) return 1; return 0; } -- cgit v1.2.3 From a8b76910e465d718effce0cad306a21fa4f3526b Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Wed, 10 Nov 2021 20:24:44 +0000 Subject: preempt: Restore preemption model selection configs Commit c597bfddc9e9 ("sched: Provide Kconfig support for default dynamic preempt mode") changed the selectable config names for the preemption model. This means a config file must now select CONFIG_PREEMPT_BEHAVIOUR=y rather than CONFIG_PREEMPT=y to get a preemptible kernel. This means all arch config files would need to be updated - right now they'll all end up with the default CONFIG_PREEMPT_NONE_BEHAVIOUR. Rather than touch a good hundred of config files, restore usage of CONFIG_PREEMPT{_NONE, _VOLUNTARY}. Make them configure: o The build-time preemption model when !PREEMPT_DYNAMIC o The default boot-time preemption model when PREEMPT_DYNAMIC Add siblings of those configs with the _BUILD suffix to unconditionally designate the build-time preemption model (PREEMPT_DYNAMIC is built with the "highest" preemption model it supports, aka PREEMPT). Downstream configs should by now all be depending / selected by CONFIG_PREEMPTION rather than CONFIG_PREEMPT, so only a few sites need patching up. Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Acked-by: Marco Elver Link: https://lore.kernel.org/r/20211110202448.4054153-2-valentin.schneider@arm.com --- include/linux/kernel.h | 2 +- include/linux/vermagic.h | 2 +- init/Makefile | 2 +- kernel/Kconfig.preempt | 42 +++++++++++++++++++++--------------------- kernel/sched/core.c | 6 +++--- 5 files changed, 27 insertions(+), 27 deletions(-) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 968b4c4fe65b..77755ac3e189 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -85,7 +85,7 @@ struct completion; struct user; -#ifdef CONFIG_PREEMPT_VOLUNTARY +#ifdef CONFIG_PREEMPT_VOLUNTARY_BUILD extern int __cond_resched(void); # define might_resched() __cond_resched() diff --git a/include/linux/vermagic.h b/include/linux/vermagic.h index 1eaaa93c37bf..329d63babaeb 100644 --- a/include/linux/vermagic.h +++ b/include/linux/vermagic.h @@ -15,7 +15,7 @@ #else #define MODULE_VERMAGIC_SMP "" #endif -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPT_BUILD #define MODULE_VERMAGIC_PREEMPT "preempt " #elif defined(CONFIG_PREEMPT_RT) #define MODULE_VERMAGIC_PREEMPT "preempt_rt " diff --git a/init/Makefile b/init/Makefile index 2846113677ee..04eeee12c076 100644 --- a/init/Makefile +++ b/init/Makefile @@ -30,7 +30,7 @@ $(obj)/version.o: include/generated/compile.h quiet_cmd_compile.h = CHK $@ cmd_compile.h = \ $(CONFIG_SHELL) $(srctree)/scripts/mkcompile_h $@ \ - "$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)" \ + "$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT_BUILD)" \ "$(CONFIG_PREEMPT_RT)" $(CONFIG_CC_VERSION_TEXT) "$(LD)" include/generated/compile.h: FORCE diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt index 60f1bfc3c7b2..ce77f0265660 100644 --- a/kernel/Kconfig.preempt +++ b/kernel/Kconfig.preempt @@ -1,12 +1,23 @@ # SPDX-License-Identifier: GPL-2.0-only +config PREEMPT_NONE_BUILD + bool + +config PREEMPT_VOLUNTARY_BUILD + bool + +config PREEMPT_BUILD + bool + select PREEMPTION + select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK + choice prompt "Preemption Model" - default PREEMPT_NONE_BEHAVIOUR + default PREEMPT_NONE -config PREEMPT_NONE_BEHAVIOUR +config PREEMPT_NONE bool "No Forced Preemption (Server)" - select PREEMPT_NONE if !PREEMPT_DYNAMIC + select PREEMPT_NONE_BUILD if !PREEMPT_DYNAMIC help This is the traditional Linux preemption model, geared towards throughput. It will still provide good latencies most of the @@ -18,10 +29,10 @@ config PREEMPT_NONE_BEHAVIOUR raw processing power of the kernel, irrespective of scheduling latencies. -config PREEMPT_VOLUNTARY_BEHAVIOUR +config PREEMPT_VOLUNTARY bool "Voluntary Kernel Preemption (Desktop)" depends on !ARCH_NO_PREEMPT - select PREEMPT_VOLUNTARY if !PREEMPT_DYNAMIC + select PREEMPT_VOLUNTARY_BUILD if !PREEMPT_DYNAMIC help This option reduces the latency of the kernel by adding more "explicit preemption points" to the kernel code. These new @@ -37,10 +48,10 @@ config PREEMPT_VOLUNTARY_BEHAVIOUR Select this if you are building a kernel for a desktop system. -config PREEMPT_BEHAVIOUR +config PREEMPT bool "Preemptible Kernel (Low-Latency Desktop)" depends on !ARCH_NO_PREEMPT - select PREEMPT + select PREEMPT_BUILD help This option reduces the latency of the kernel by making all kernel code (that is not executing in a critical section) @@ -58,7 +69,7 @@ config PREEMPT_BEHAVIOUR config PREEMPT_RT bool "Fully Preemptible Kernel (Real-Time)" - depends on EXPERT && ARCH_SUPPORTS_RT && !PREEMPT_DYNAMIC + depends on EXPERT && ARCH_SUPPORTS_RT select PREEMPTION help This option turns the kernel into a real-time kernel by replacing @@ -75,17 +86,6 @@ config PREEMPT_RT endchoice -config PREEMPT_NONE - bool - -config PREEMPT_VOLUNTARY - bool - -config PREEMPT - bool - select PREEMPTION - select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK - config PREEMPT_COUNT bool @@ -95,8 +95,8 @@ config PREEMPTION config PREEMPT_DYNAMIC bool "Preemption behaviour defined on boot" - depends on HAVE_PREEMPT_DYNAMIC - select PREEMPT + depends on HAVE_PREEMPT_DYNAMIC && !PREEMPT_RT + select PREEMPT_BUILD default y help This option allows to define the preemption model on the kernel diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 862af1db22ab..3c9b0fda64ac 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6628,13 +6628,13 @@ __setup("preempt=", setup_preempt_mode); static void __init preempt_dynamic_init(void) { if (preempt_dynamic_mode == preempt_dynamic_undefined) { - if (IS_ENABLED(CONFIG_PREEMPT_NONE_BEHAVIOUR)) { + if (IS_ENABLED(CONFIG_PREEMPT_NONE)) { sched_dynamic_update(preempt_dynamic_none); - } else if (IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY_BEHAVIOUR)) { + } else if (IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY)) { sched_dynamic_update(preempt_dynamic_voluntary); } else { /* Default static call setting, nothing to do */ - WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT_BEHAVIOUR)); + WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT)); preempt_dynamic_mode = preempt_dynamic_full; pr_info("Dynamic Preempt: full\n"); } -- cgit v1.2.3 From cead18552660702a4a46f58e65188fe5f36e9dfe Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 22 Nov 2021 11:15:19 -0600 Subject: exit: Rename complete_and_exit to kthread_complete_and_exit Update complete_and_exit to call kthread_exit instead of do_exit. Change the name to reflect this change in functionality. All of the users of complete_and_exit are causing the current kthread to exit so this change makes it clear what is happening. Move the implementation of kthread_complete_and_exit from kernel/exit.c to to kernel/kthread.c. As this function is kthread specific it makes most sense to live with the kthread functions. There are no functional change. Signed-off-by: "Eric W. Biederman" --- drivers/net/wireless/rsi/rsi_91x_coex.c | 2 +- drivers/net/wireless/rsi/rsi_91x_main.c | 2 +- drivers/net/wireless/rsi/rsi_91x_sdio_ops.c | 2 +- drivers/net/wireless/rsi/rsi_91x_usb_ops.c | 2 +- drivers/pnp/pnpbios/core.c | 6 +++--- drivers/staging/rts5208/rtsx.c | 16 ++++++++-------- drivers/usb/atm/usbatm.c | 2 +- drivers/usb/gadget/function/f_mass_storage.c | 2 +- fs/jffs2/background.c | 2 +- include/linux/kernel.h | 1 - include/linux/kthread.h | 1 + kernel/exit.c | 9 --------- kernel/kthread.c | 21 +++++++++++++++++++++ lib/kunit/try-catch.c | 4 ++-- tools/objtool/check.c | 2 +- 15 files changed, 43 insertions(+), 31 deletions(-) (limited to 'include/linux/kernel.h') diff --git a/drivers/net/wireless/rsi/rsi_91x_coex.c b/drivers/net/wireless/rsi/rsi_91x_coex.c index a0c5d02ae88c..8a3d86897ea8 100644 --- a/drivers/net/wireless/rsi/rsi_91x_coex.c +++ b/drivers/net/wireless/rsi/rsi_91x_coex.c @@ -63,7 +63,7 @@ static void rsi_coex_scheduler_thread(struct rsi_common *common) rsi_coex_sched_tx_pkts(coex_cb); } while (atomic_read(&coex_cb->coex_tx_thread.thread_done) == 0); - complete_and_exit(&coex_cb->coex_tx_thread.completion, 0); + kthread_complete_and_exit(&coex_cb->coex_tx_thread.completion, 0); } int rsi_coex_recv_pkt(struct rsi_common *common, u8 *msg) diff --git a/drivers/net/wireless/rsi/rsi_91x_main.c b/drivers/net/wireless/rsi/rsi_91x_main.c index f1bf71e6c608..c7f5cec5e446 100644 --- a/drivers/net/wireless/rsi/rsi_91x_main.c +++ b/drivers/net/wireless/rsi/rsi_91x_main.c @@ -260,7 +260,7 @@ static void rsi_tx_scheduler_thread(struct rsi_common *common) if (common->init_done) rsi_core_qos_processor(common); } while (atomic_read(&common->tx_thread.thread_done) == 0); - complete_and_exit(&common->tx_thread.completion, 0); + kthread_complete_and_exit(&common->tx_thread.completion, 0); } #ifdef CONFIG_RSI_COEX diff --git a/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c b/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c index 8ace1874e5cb..b2b47a0abcbf 100644 --- a/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c +++ b/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c @@ -75,7 +75,7 @@ void rsi_sdio_rx_thread(struct rsi_common *common) rsi_dbg(INFO_ZONE, "%s: Terminated SDIO RX thread\n", __func__); atomic_inc(&sdev->rx_thread.thread_done); - complete_and_exit(&sdev->rx_thread.completion, 0); + kthread_complete_and_exit(&sdev->rx_thread.completion, 0); } /** diff --git a/drivers/net/wireless/rsi/rsi_91x_usb_ops.c b/drivers/net/wireless/rsi/rsi_91x_usb_ops.c index 4ffcdde1acb1..5130b0e72adc 100644 --- a/drivers/net/wireless/rsi/rsi_91x_usb_ops.c +++ b/drivers/net/wireless/rsi/rsi_91x_usb_ops.c @@ -56,6 +56,6 @@ void rsi_usb_rx_thread(struct rsi_common *common) out: rsi_dbg(INFO_ZONE, "%s: Terminated thread\n", __func__); skb_queue_purge(&dev->rx_q); - complete_and_exit(&dev->rx_thread.completion, 0); + kthread_complete_and_exit(&dev->rx_thread.completion, 0); } diff --git a/drivers/pnp/pnpbios/core.c b/drivers/pnp/pnpbios/core.c index 669ef4700c1a..f7e86ae9f72f 100644 --- a/drivers/pnp/pnpbios/core.c +++ b/drivers/pnp/pnpbios/core.c @@ -160,7 +160,7 @@ static int pnp_dock_thread(void *unused) * No dock to manage */ case PNP_FUNCTION_NOT_SUPPORTED: - complete_and_exit(&unload_sem, 0); + kthread_complete_and_exit(&unload_sem, 0); case PNP_SYSTEM_NOT_DOCKED: d = 0; break; @@ -170,7 +170,7 @@ static int pnp_dock_thread(void *unused) default: pnpbios_print_status("pnp_dock_thread", status); printk(KERN_WARNING "PnPBIOS: disabling dock monitoring.\n"); - complete_and_exit(&unload_sem, 0); + kthread_complete_and_exit(&unload_sem, 0); } if (d != docked) { if (pnp_dock_event(d, &now) == 0) { @@ -183,7 +183,7 @@ static int pnp_dock_thread(void *unused) } } } - complete_and_exit(&unload_sem, 0); + kthread_complete_and_exit(&unload_sem, 0); } static int pnpbios_get_resources(struct pnp_dev *dev) diff --git a/drivers/staging/rts5208/rtsx.c b/drivers/staging/rts5208/rtsx.c index 91fcf85e150a..5a58dac76c88 100644 --- a/drivers/staging/rts5208/rtsx.c +++ b/drivers/staging/rts5208/rtsx.c @@ -450,13 +450,13 @@ skip_for_abort: * after the down() -- that's necessary for the thread-shutdown * case. * - * complete_and_exit() goes even further than this -- it is safe in - * the case that the thread of the caller is going away (not just - * the structure) -- this is necessary for the module-remove case. - * This is important in preemption kernels, which transfer the flow - * of execution immediately upon a complete(). + * kthread_complete_and_exit() goes even further than this -- + * it is safe in the case that the thread of the caller is going away + * (not just the structure) -- this is necessary for the module-remove + * case. This is important in preemption kernels, which transfer the + * flow of execution immediately upon a complete(). */ - complete_and_exit(&dev->control_exit, 0); + kthread_complete_and_exit(&dev->control_exit, 0); } static int rtsx_polling_thread(void *__dev) @@ -501,7 +501,7 @@ static int rtsx_polling_thread(void *__dev) mutex_unlock(&dev->dev_mutex); } - complete_and_exit(&dev->polling_exit, 0); + kthread_complete_and_exit(&dev->polling_exit, 0); } /* @@ -682,7 +682,7 @@ static int rtsx_scan_thread(void *__dev) /* Should we unbind if no devices were detected? */ } - complete_and_exit(&dev->scanning_done, 0); + kthread_complete_and_exit(&dev->scanning_done, 0); } static void rtsx_init_options(struct rtsx_chip *chip) diff --git a/drivers/usb/atm/usbatm.c b/drivers/usb/atm/usbatm.c index da17be1ef64e..e3a49d837609 100644 --- a/drivers/usb/atm/usbatm.c +++ b/drivers/usb/atm/usbatm.c @@ -969,7 +969,7 @@ static int usbatm_do_heavy_init(void *arg) instance->thread = NULL; mutex_unlock(&instance->serialize); - complete_and_exit(&instance->thread_exited, ret); + kthread_complete_and_exit(&instance->thread_exited, ret); } static int usbatm_heavy_init(struct usbatm_data *instance) diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c index 752439690fda..46dd11dcb3a8 100644 --- a/drivers/usb/gadget/function/f_mass_storage.c +++ b/drivers/usb/gadget/function/f_mass_storage.c @@ -2547,7 +2547,7 @@ static int fsg_main_thread(void *common_) up_write(&common->filesem); /* Let fsg_unbind() know the thread has exited */ - complete_and_exit(&common->thread_notifier, 0); + kthread_complete_and_exit(&common->thread_notifier, 0); } diff --git a/fs/jffs2/background.c b/fs/jffs2/background.c index 2b4d5013dc5d..6da92ecaf66d 100644 --- a/fs/jffs2/background.c +++ b/fs/jffs2/background.c @@ -161,5 +161,5 @@ static int jffs2_garbage_collect_thread(void *_c) spin_lock(&c->erase_completion_lock); c->gc_task = NULL; spin_unlock(&c->erase_completion_lock); - complete_and_exit(&c->gc_thread_exit, 0); + kthread_complete_and_exit(&c->gc_thread_exit, 0); } diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 77755ac3e189..055eb203c00e 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -187,7 +187,6 @@ static inline void might_fault(void) { } #endif void do_exit(long error_code) __noreturn; -void complete_and_exit(struct completion *, long) __noreturn; extern int num_to_str(char *buf, int size, unsigned long long num, unsigned int width); diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 22c43d419687..d86a7e3b9a52 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -71,6 +71,7 @@ int kthread_park(struct task_struct *k); void kthread_unpark(struct task_struct *k); void kthread_parkme(void); void kthread_exit(long result) __noreturn; +void kthread_complete_and_exit(struct completion *, long) __noreturn; int kthreadd(void *unused); extern struct task_struct *kthreadd_task; diff --git a/kernel/exit.c b/kernel/exit.c index 57afac845a0a..6c4b04531f17 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -891,15 +891,6 @@ void __noreturn make_task_dead(int signr) do_exit(signr); } -void complete_and_exit(struct completion *comp, long code) -{ - if (comp) - complete(comp); - - do_exit(code); -} -EXPORT_SYMBOL(complete_and_exit); - SYSCALL_DEFINE1(exit, int, error_code) { do_exit((error_code&0xff)<<8); diff --git a/kernel/kthread.c b/kernel/kthread.c index 77b7c3f23f18..4388d6694a7f 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -283,6 +283,27 @@ void __noreturn kthread_exit(long result) do_exit(result); } +/** + * kthread_complete_and exit - Exit the current kthread. + * @comp: Completion to complete + * @code: The integer value to return to kthread_stop(). + * + * If present complete @comp and the reuturn code to kthread_stop(). + * + * A kernel thread whose module may be removed after the completion of + * @comp can use this function exit safely. + * + * Does not return. + */ +void __noreturn kthread_complete_and_exit(struct completion *comp, long code) +{ + if (comp) + complete(comp); + + kthread_exit(code); +} +EXPORT_SYMBOL(kthread_complete_and_exit); + static int kthread(void *_create) { static const struct sched_param param = { .sched_priority = 0 }; diff --git a/lib/kunit/try-catch.c b/lib/kunit/try-catch.c index 0dd434e40487..be38a2c5ecc2 100644 --- a/lib/kunit/try-catch.c +++ b/lib/kunit/try-catch.c @@ -17,7 +17,7 @@ void __noreturn kunit_try_catch_throw(struct kunit_try_catch *try_catch) { try_catch->try_result = -EFAULT; - complete_and_exit(try_catch->try_completion, -EFAULT); + kthread_complete_and_exit(try_catch->try_completion, -EFAULT); } EXPORT_SYMBOL_GPL(kunit_try_catch_throw); @@ -27,7 +27,7 @@ static int kunit_generic_run_threadfn_adapter(void *data) try_catch->try(try_catch->context); - complete_and_exit(try_catch->try_completion, 0); + kthread_complete_and_exit(try_catch->try_completion, 0); } static unsigned long kunit_test_timeout(void) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 120e9598c11a..282273a1ffa5 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -171,7 +171,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "kthread_exit", "make_task_dead", "__module_put_and_kthread_exit", - "complete_and_exit", + "kthread_complete_and_exit", "__reiserfs_panic", "lbug_with_loc", "fortify_panic", -- cgit v1.2.3 From 40cbf09f060c8febef64541c463d4dd526abe445 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 19 Jan 2022 18:08:16 -0800 Subject: kernel.h: include a note to discourage people from including it in headers Include a note at the top to discourage people from including it in headers. Link: https://lkml.kernel.org/r/20211209150803.4473-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux/kernel.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 77755ac3e189..36a612d82956 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -1,4 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0 */ +/* + * NOTE: + * + * This header has combined a lot of unrelated to each other stuff. + * The process of splitting its content is in progress while keeping + * backward compatibility. That's why it's highly recommended NOT to + * include this header inside another header file, especially under + * generic or architectural include/ directory. + */ #ifndef _LINUX_KERNEL_H #define _LINUX_KERNEL_H -- cgit v1.2.3