Merge tag 'core-rseq-2025-11-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull rseq updates from Thomas Gleixner:
 "A large overhaul of the restartable sequences and CID management:

  The recent enablement of RSEQ in glibc resulted in regressions which
  are caused by the related overhead. It turned out that the decision to
  invoke the exit to user work was not really a decision. More or less
  each context switch caused that. There is a long list of small issues
  which sums up nicely and results in a 3-4% regression in I/O
  benchmarks.

  The other detail which caused issues due to extra work in context
  switch and task migration is the CID (memory context ID) management.
  It also requires to use a task work to consolidate the CID space,
  which is executed in the context of an arbitrary task and results in
  sporadic uncontrolled exit latencies.

  The rewrite addresses this by:

   - Removing deprecated and long unsupported functionality

   - Moving the related data into dedicated data structures which are
     optimized for fast path processing.

   - Caching values so actual decisions can be made

   - Replacing the current implementation with a optimized inlined
     variant.

   - Separating fast and slow path for architectures which use the
     generic entry code, so that only fault and error handling goes into
     the TIF_NOTIFY_RESUME handler.

   - Rewriting the CID management so that it becomes mostly invisible in
     the context switch path. That moves the work of switching modes
     into the fork/exit path, which is a reasonable tradeoff. That work
     is only required when a process creates more threads than the
     cpuset it is allowed to run on or when enough threads exit after
     that. An artificial thread pool benchmarks which triggers this did
     not degrade, it actually improved significantly.

     The main effect in migration heavy scenarios is that runqueue lock
     held time and therefore contention goes down significantly"

* tag 'core-rseq-2025-11-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (54 commits)
  sched/mmcid: Switch over to the new mechanism
  sched/mmcid: Implement deferred mode change
  irqwork: Move data struct to a types header
  sched/mmcid: Provide CID ownership mode fixup functions
  sched/mmcid: Provide new scheduler CID mechanism
  sched/mmcid: Introduce per task/CPU ownership infrastructure
  sched/mmcid: Serialize sched_mm_cid_fork()/exit() with a mutex
  sched/mmcid: Provide precomputed maximal value
  sched/mmcid: Move initialization out of line
  signal: Move MMCID exit out of sighand lock
  sched/mmcid: Convert mm CID mask to a bitmap
  cpumask: Cache num_possible_cpus()
  sched/mmcid: Use cpumask_weighted_or()
  cpumask: Introduce cpumask_weighted_or()
  sched/mmcid: Prevent pointless work in mm_update_cpus_allowed()
  sched/mmcid: Move scheduler code out of global header
  sched: Fixup whitespace damage
  sched/mmcid: Cacheline align MM CID storage
  sched/mmcid: Use proper data structures
  sched/mmcid: Revert the complex CID management
  ...

Author: torvalds

Documentation/admin-guide/kernel-parameters.txt

@@ -6500,6 +6500,10 @@
 			Memory area to be used by remote processor image,
 			managed by CMA.
 
+	rseq_debug=	[KNL] Enable or disable restartable sequence
+			debug mode. Defaults to CONFIG_RSEQ_DEBUG_DEFAULT_ENABLE.
+			Format: <bool>
+
 	rt_group_sched=	[KNL] Enable or disable SCHED_RR/FIFO group scheduling
 			when CONFIG_RT_GROUP_SCHED=y. Defaults to
 			!CONFIG_RT_GROUP_SCHED_DEFAULT_DISABLED.

arch/arm64/kernel/entry-common.c

@@ -100,7 +100,7 @@ static __always_inline void arm64_enter_from_user_mode(struct pt_regs *regs)
 static __always_inline void arm64_exit_to_user_mode(struct pt_regs *regs)
 {
 	local_irq_disable();
-	exit_to_user_mode_prepare(regs);
+	exit_to_user_mode_prepare_legacy(regs);
 	local_daif_mask();
 	mte_check_tfsr_exit();
 	exit_to_user_mode();

arch/x86/entry/syscall_32.c

@@ -274,9 +274,10 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs)
 	 * fetch EBP before invoking any of the syscall entry work
 	 * functions.
 	 */
-	syscall_enter_from_user_mode_prepare(regs);
+	enter_from_user_mode(regs);
 
 	instrumentation_begin();
+	local_irq_enable();
 	/* Fetch EBP from where the vDSO stashed it. */
 	if (IS_ENABLED(CONFIG_X86_64)) {
 		/*

arch/x86/include/asm/ptrace.h

@@ -187,12 +187,12 @@ convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs);
 extern void send_sigtrap(struct pt_regs *regs, int error_code, int si_code);
 
 
-static inline unsigned long regs_return_value(struct pt_regs *regs)
+static __always_inline unsigned long regs_return_value(struct pt_regs *regs)
 {
 	return regs->ax;
 }
 
-static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
+static __always_inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
 {
 	regs->ax = rc;
 }
@@ -277,34 +277,34 @@ static __always_inline bool ip_within_syscall_gap(struct pt_regs *regs)
 }
 #endif
 
-static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
+static __always_inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
 {
 	return regs->sp;
 }
 
-static inline unsigned long instruction_pointer(struct pt_regs *regs)
+static __always_inline unsigned long instruction_pointer(struct pt_regs *regs)
 {
 	return regs->ip;
 }
 
-static inline void instruction_pointer_set(struct pt_regs *regs,
-		unsigned long val)
+static __always_inline
+void instruction_pointer_set(struct pt_regs *regs, unsigned long val)
 {
 	regs->ip = val;
 }
 
-static inline unsigned long frame_pointer(struct pt_regs *regs)
+static __always_inline unsigned long frame_pointer(struct pt_regs *regs)
 {
 	return regs->bp;
 }
 
-static inline unsigned long user_stack_pointer(struct pt_regs *regs)
+static __always_inline unsigned long user_stack_pointer(struct pt_regs *regs)
 {
 	return regs->sp;
 }
 
-static inline void user_stack_pointer_set(struct pt_regs *regs,
-		unsigned long val)
+static __always_inline
+void user_stack_pointer_set(struct pt_regs *regs, unsigned long val)
 {
 	regs->sp = val;
 }

drivers/hv/mshv_root_main.c

@@ -29,6 +29,7 @@
 #include <linux/crash_dump.h>
 #include <linux/panic_notifier.h>
 #include <linux/vmalloc.h>
+#include <linux/rseq.h>
 
 #include "mshv_eventfd.h"
 #include "mshv.h"
@@ -560,6 +561,8 @@ static long mshv_run_vp_with_root_scheduler(struct mshv_vp *vp)
 		}
 	} while (!vp->run.flags.intercept_suspend);
 
+	rseq_virt_userspace_exit();
+
 	return ret;
 }
 

fs/binfmt_elf.c

@@ -46,7 +46,7 @@
 #include <linux/cred.h>
 #include <linux/dax.h>
 #include <linux/uaccess.h>
-#include <linux/rseq.h>
+#include <uapi/linux/rseq.h>
 #include <asm/param.h>
 #include <asm/page.h>
 

fs/exec.c

@@ -1774,7 +1774,7 @@ static int bprm_execve(struct linux_binprm *bprm)
 		force_fatal_sig(SIGSEGV);
 
 	sched_mm_cid_after_execve(current);
-	rseq_set_notify_resume(current);
+	rseq_force_update();
 	current->in_execve = 0;
 
 	return retval;

include/asm-generic/thread_info_tif.h

@@ -45,4 +45,7 @@
 # define _TIF_RESTORE_SIGMASK	BIT(TIF_RESTORE_SIGMASK)
 #endif
 
+#define TIF_RSEQ		11	// Run RSEQ fast path
+#define _TIF_RSEQ		BIT(TIF_RSEQ)
+
 #endif /* _ASM_GENERIC_THREAD_INFO_TIF_H_ */

include/linux/bitmap.h

@@ -45,6 +45,7 @@ struct device;
  *  bitmap_copy(dst, src, nbits)                *dst = *src
  *  bitmap_and(dst, src1, src2, nbits)          *dst = *src1 & *src2
  *  bitmap_or(dst, src1, src2, nbits)           *dst = *src1 | *src2
+ *  bitmap_weighted_or(dst, src1, src2, nbits)	*dst = *src1 | *src2. Returns Hamming Weight of dst
  *  bitmap_xor(dst, src1, src2, nbits)          *dst = *src1 ^ *src2
  *  bitmap_andnot(dst, src1, src2, nbits)       *dst = *src1 & ~(*src2)
  *  bitmap_complement(dst, src, nbits)          *dst = ~(*src)
@@ -165,6 +166,8 @@ bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
 		 const unsigned long *bitmap2, unsigned int nbits);
 void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
 		 const unsigned long *bitmap2, unsigned int nbits);
+unsigned int __bitmap_weighted_or(unsigned long *dst, const unsigned long *bitmap1,
+				  const unsigned long *bitmap2, unsigned int nbits);
 void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1,
 		  const unsigned long *bitmap2, unsigned int nbits);
 bool __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
@@ -337,6 +340,18 @@ void bitmap_or(unsigned long *dst, const unsigned long *src1,
 		__bitmap_or(dst, src1, src2, nbits);
 }
 
+static __always_inline
+unsigned int bitmap_weighted_or(unsigned long *dst, const unsigned long *src1,
+				const unsigned long *src2, unsigned int nbits)
+{
+	if (small_const_nbits(nbits)) {
+		*dst = *src1 | *src2;
+		return hweight_long(*dst & BITMAP_LAST_WORD_MASK(nbits));
+	} else {
+		return __bitmap_weighted_or(dst, src1, src2, nbits);
+	}
+}
+
 static __always_inline
 void bitmap_xor(unsigned long *dst, const unsigned long *src1,
 		const unsigned long *src2, unsigned int nbits)

include/linux/cleanup.h

@@ -208,7 +208,7 @@
  */
 
 #define DEFINE_FREE(_name, _type, _free) \
-	static inline void __free_##_name(void *p) { _type _T = *(_type *)p; _free; }
+	static __always_inline void __free_##_name(void *p) { _type _T = *(_type *)p; _free; }
 
 #define __free(_name)	__cleanup(__free_##_name)
 
@@ -220,7 +220,7 @@
 		__val;                      \
 	})
 
-static inline __must_check
+static __always_inline __must_check
 const volatile void * __must_check_fn(const volatile void *val)
 { return val; }
 
@@ -278,16 +278,16 @@ const volatile void * __must_check_fn(const volatile void *val)
 
 #define DEFINE_CLASS(_name, _type, _exit, _init, _init_args...)		\
 typedef _type class_##_name##_t;					\
-static inline void class_##_name##_destructor(_type *p)			\
+static __always_inline void class_##_name##_destructor(_type *p)	\
 { _type _T = *p; _exit; }						\
-static inline _type class_##_name##_constructor(_init_args)		\
+static __always_inline _type class_##_name##_constructor(_init_args)	\
 { _type t = _init; return t; }
 
 #define EXTEND_CLASS(_name, ext, _init, _init_args...)			\
 typedef class_##_name##_t class_##_name##ext##_t;			\
-static inline void class_##_name##ext##_destructor(class_##_name##_t *p)\
+static __always_inline void class_##_name##ext##_destructor(class_##_name##_t *p) \
 { class_##_name##_destructor(p); }					\
-static inline class_##_name##_t class_##_name##ext##_constructor(_init_args) \
+static __always_inline class_##_name##_t class_##_name##ext##_constructor(_init_args) \
 { class_##_name##_t t = _init; return t; }
 
 #define CLASS(_name, var)						\
@@ -360,15 +360,15 @@ static __maybe_unused const bool class_##_name##_is_conditional = _is_cond
 	})
 
 #define __DEFINE_GUARD_LOCK_PTR(_name, _exp)                                \
-	static inline void *class_##_name##_lock_ptr(class_##_name##_t *_T) \
+	static __always_inline void *class_##_name##_lock_ptr(class_##_name##_t *_T) \
 	{                                                                   \
 		void *_ptr = (void *)(__force unsigned long)*(_exp);        \
 		if (IS_ERR(_ptr)) {                                         \
 			_ptr = NULL;                                        \
 		}                                                           \
 		return _ptr;                                                \
 	}                                                                   \
-	static inline int class_##_name##_lock_err(class_##_name##_t *_T)   \
+	static __always_inline int class_##_name##_lock_err(class_##_name##_t *_T) \
 	{                                                                   \
 		long _rc = (__force unsigned long)*(_exp);                  \
 		if (!_rc) {                                                 \
@@ -397,9 +397,9 @@ static __maybe_unused const bool class_##_name##_is_conditional = _is_cond
 	EXTEND_CLASS(_name, _ext, \
 		     ({ void *_t = _T; int _RET = (_lock); if (_T && !(_cond)) _t = ERR_PTR(_RET); _t; }), \
 		     class_##_name##_t _T) \
-	static inline void * class_##_name##_ext##_lock_ptr(class_##_name##_t *_T) \
+	static __always_inline void * class_##_name##_ext##_lock_ptr(class_##_name##_t *_T) \
 	{ return class_##_name##_lock_ptr(_T); } \
-	static inline int class_##_name##_ext##_lock_err(class_##_name##_t *_T) \
+	static __always_inline int class_##_name##_ext##_lock_err(class_##_name##_t *_T) \
 	{ return class_##_name##_lock_err(_T); }
 
 /*
@@ -479,23 +479,23 @@ typedef struct {							\
 	__VA_ARGS__;							\
 } class_##_name##_t;							\
 									\
-static inline void class_##_name##_destructor(class_##_name##_t *_T)	\
+static __always_inline void class_##_name##_destructor(class_##_name##_t *_T) \
 {									\
 	if (!__GUARD_IS_ERR(_T->lock)) { _unlock; }			\
 }									\
 									\
 __DEFINE_GUARD_LOCK_PTR(_name, &_T->lock)
 
 #define __DEFINE_LOCK_GUARD_1(_name, _type, _lock)			\
-static inline class_##_name##_t class_##_name##_constructor(_type *l)	\
+static __always_inline class_##_name##_t class_##_name##_constructor(_type *l) \
 {									\
 	class_##_name##_t _t = { .lock = l }, *_T = &_t;		\
 	_lock;								\
 	return _t;							\
 }
 
 #define __DEFINE_LOCK_GUARD_0(_name, _lock)				\
-static inline class_##_name##_t class_##_name##_constructor(void)	\
+static __always_inline class_##_name##_t class_##_name##_constructor(void) \
 {									\
 	class_##_name##_t _t = { .lock = (void*)1 },			\
 			 *_T __maybe_unused = &_t;			\
@@ -521,9 +521,9 @@ __DEFINE_LOCK_GUARD_0(_name, _lock)
 		        if (_T->lock && !(_cond)) _T->lock = ERR_PTR(_RET);\
 			_t; }),						\
 		     typeof_member(class_##_name##_t, lock) l)		\
-	static inline void * class_##_name##_ext##_lock_ptr(class_##_name##_t *_T) \
+	static __always_inline void * class_##_name##_ext##_lock_ptr(class_##_name##_t *_T) \
 	{ return class_##_name##_lock_ptr(_T); } \
-	static inline int class_##_name##_ext##_lock_err(class_##_name##_t *_T) \
+	static __always_inline int class_##_name##_ext##_lock_err(class_##_name##_t *_T) \
 	{ return class_##_name##_lock_err(_T); }
 
 #define DEFINE_LOCK_GUARD_1_COND_3(_name, _ext, _lock) \