diff options
Diffstat (limited to 'include/linux/sched/mm.h')
-rw-r--r-- | include/linux/sched/mm.h | 234 |
1 files changed, 160 insertions, 74 deletions
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index c49257a3b510..2a243616f222 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -8,6 +8,7 @@ #include <linux/mm_types.h> #include <linux/gfp.h> #include <linux/sync_core.h> +#include <linux/ioasid.h> /* * Routines for handling mm_structs @@ -23,12 +24,12 @@ extern struct mm_struct *mm_alloc(void); * will still exist later on and mmget_not_zero() has to be used before * accessing it. * - * This is a preferred way to to pin @mm for a longer/unbounded amount + * This is a preferred way to pin @mm for a longer/unbounded amount * of time. * * Use mmdrop() to release the reference acquired by mmgrab(). * - * See also <Documentation/vm/active_mm.rst> for an in-depth explanation + * See also <Documentation/mm/active_mm.rst> for an in-depth explanation * of &mm_struct.mm_count vs &mm_struct.mm_users. */ static inline void mmgrab(struct mm_struct *mm) @@ -49,31 +50,35 @@ static inline void mmdrop(struct mm_struct *mm) __mmdrop(mm); } +#ifdef CONFIG_PREEMPT_RT /* - * This has to be called after a get_task_mm()/mmget_not_zero() - * followed by taking the mmap_sem for writing before modifying the - * vmas or anything the coredump pretends not to change from under it. - * - * It also has to be called when mmgrab() is used in the context of - * the process, but then the mm_count refcount is transferred outside - * the context of the process to run down_write() on that pinned mm. - * - * NOTE: find_extend_vma() called from GUP context is the only place - * that can modify the "mm" (notably the vm_start/end) under mmap_sem - * for reading and outside the context of the process, so it is also - * the only case that holds the mmap_sem for reading that must call - * this function. Generally if the mmap_sem is hold for reading - * there's no need of this check after get_task_mm()/mmget_not_zero(). - * - * This function can be obsoleted and the check can be removed, after - * the coredump code will hold the mmap_sem for writing before - * invoking the ->core_dump methods. + * RCU callback for delayed mm drop. Not strictly RCU, but call_rcu() is + * by far the least expensive way to do that. */ -static inline bool mmget_still_valid(struct mm_struct *mm) +static inline void __mmdrop_delayed(struct rcu_head *rhp) { - return likely(!mm->core_state); + struct mm_struct *mm = container_of(rhp, struct mm_struct, delayed_drop); + + __mmdrop(mm); } +/* + * Invoked from finish_task_switch(). Delegates the heavy lifting on RT + * kernels via RCU. + */ +static inline void mmdrop_sched(struct mm_struct *mm) +{ + /* Provides a full memory barrier. See mmdrop() */ + if (atomic_dec_and_test(&mm->mm_count)) + call_rcu(&mm->delayed_drop, __mmdrop_delayed); +} +#else +static inline void mmdrop_sched(struct mm_struct *mm) +{ + mmdrop(mm); +} +#endif + /** * mmget() - Pin the address space associated with a &struct mm_struct. * @mm: The address space to pin. @@ -87,7 +92,7 @@ static inline bool mmget_still_valid(struct mm_struct *mm) * * Use mmput() to release the reference acquired by mmget(). * - * See also <Documentation/vm/active_mm.rst> for an in-depth explanation + * See also <Documentation/mm/active_mm.rst> for an in-depth explanation * of &mm_struct.mm_count vs &mm_struct.mm_users. */ static inline void mmget(struct mm_struct *mm) @@ -131,6 +136,14 @@ static inline void mm_update_next_owner(struct mm_struct *mm) #endif /* CONFIG_MEMCG */ #ifdef CONFIG_MMU +#ifndef arch_get_mmap_end +#define arch_get_mmap_end(addr, len, flags) (TASK_SIZE) +#endif + +#ifndef arch_get_mmap_base +#define arch_get_mmap_base(addr, base) (base) +#endif + extern void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack); extern unsigned long @@ -140,6 +153,15 @@ extern unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); + +unsigned long +generic_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags); +unsigned long +generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags); #else static inline void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) {} @@ -165,7 +187,8 @@ static inline bool in_vfork(struct task_struct *tsk) * another oom-unkillable task does this it should blame itself. */ rcu_read_lock(); - ret = tsk->vfork_done && tsk->real_parent->mm == tsk->mm; + ret = tsk->vfork_done && + rcu_dereference(tsk->real_parent)->mm == tsk->mm; rcu_read_unlock(); return ret; @@ -175,40 +198,82 @@ static inline bool in_vfork(struct task_struct *tsk) * Applies per-task gfp context to the given allocation flags. * PF_MEMALLOC_NOIO implies GFP_NOIO * PF_MEMALLOC_NOFS implies GFP_NOFS - * PF_MEMALLOC_NOCMA implies no allocation from CMA region. + * PF_MEMALLOC_PIN implies !GFP_MOVABLE */ static inline gfp_t current_gfp_context(gfp_t flags) { - if (unlikely(current->flags & - (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS | PF_MEMALLOC_NOCMA))) { + unsigned int pflags = READ_ONCE(current->flags); + + if (unlikely(pflags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS | PF_MEMALLOC_PIN))) { /* * NOIO implies both NOIO and NOFS and it is a weaker context * so always make sure it makes precedence */ - if (current->flags & PF_MEMALLOC_NOIO) + if (pflags & PF_MEMALLOC_NOIO) flags &= ~(__GFP_IO | __GFP_FS); - else if (current->flags & PF_MEMALLOC_NOFS) + else if (pflags & PF_MEMALLOC_NOFS) flags &= ~__GFP_FS; -#ifdef CONFIG_CMA - if (current->flags & PF_MEMALLOC_NOCMA) + + if (pflags & PF_MEMALLOC_PIN) flags &= ~__GFP_MOVABLE; -#endif } return flags; } #ifdef CONFIG_LOCKDEP -extern void __fs_reclaim_acquire(void); -extern void __fs_reclaim_release(void); +extern void __fs_reclaim_acquire(unsigned long ip); +extern void __fs_reclaim_release(unsigned long ip); extern void fs_reclaim_acquire(gfp_t gfp_mask); extern void fs_reclaim_release(gfp_t gfp_mask); #else -static inline void __fs_reclaim_acquire(void) { } -static inline void __fs_reclaim_release(void) { } +static inline void __fs_reclaim_acquire(unsigned long ip) { } +static inline void __fs_reclaim_release(unsigned long ip) { } static inline void fs_reclaim_acquire(gfp_t gfp_mask) { } static inline void fs_reclaim_release(gfp_t gfp_mask) { } #endif +/* Any memory-allocation retry loop should use + * memalloc_retry_wait(), and pass the flags for the most + * constrained allocation attempt that might have failed. + * This provides useful documentation of where loops are, + * and a central place to fine tune the waiting as the MM + * implementation changes. + */ +static inline void memalloc_retry_wait(gfp_t gfp_flags) +{ + /* We use io_schedule_timeout because waiting for memory + * typically included waiting for dirty pages to be + * written out, which requires IO. + */ + __set_current_state(TASK_UNINTERRUPTIBLE); + gfp_flags = current_gfp_context(gfp_flags); + if (gfpflags_allow_blocking(gfp_flags) && + !(gfp_flags & __GFP_NORETRY)) + /* Probably waited already, no need for much more */ + io_schedule_timeout(1); + else + /* Probably didn't wait, and has now released a lock, + * so now is a good time to wait + */ + io_schedule_timeout(HZ/50); +} + +/** + * might_alloc - Mark possible allocation sites + * @gfp_mask: gfp_t flags that would be used to allocate + * + * Similar to might_sleep() and other annotations, this can be used in functions + * that might allocate, but often don't. Compiles to nothing without + * CONFIG_LOCKDEP. Includes a conditional might_sleep() if @gfp allows blocking. + */ +static inline void might_alloc(gfp_t gfp_mask) +{ + fs_reclaim_acquire(gfp_mask); + fs_reclaim_release(gfp_mask); + + might_sleep_if(gfpflags_allow_blocking(gfp_mask)); +} + /** * memalloc_noio_save - Marks implicit GFP_NOIO allocation scope. * @@ -232,7 +297,7 @@ static inline unsigned int memalloc_noio_save(void) * @flags: Flags to restore. * * Ends the implicit GFP_NOIO scope started by memalloc_noio_save function. - * Always make sure that that the given flags is the return value from the + * Always make sure that the given flags is the return value from the * pairing memalloc_noio_save call. */ static inline void memalloc_noio_restore(unsigned int flags) @@ -263,7 +328,7 @@ static inline unsigned int memalloc_nofs_save(void) * @flags: Flags to restore. * * Ends the implicit GFP_NOFS scope started by memalloc_nofs_save function. - * Always make sure that that the given flags is the return value from the + * Always make sure that the given flags is the return value from the * pairing memalloc_nofs_save call. */ static inline void memalloc_nofs_restore(unsigned int flags) @@ -283,64 +348,52 @@ static inline void memalloc_noreclaim_restore(unsigned int flags) current->flags = (current->flags & ~PF_MEMALLOC) | flags; } -#ifdef CONFIG_CMA -static inline unsigned int memalloc_nocma_save(void) +static inline unsigned int memalloc_pin_save(void) { - unsigned int flags = current->flags & PF_MEMALLOC_NOCMA; + unsigned int flags = current->flags & PF_MEMALLOC_PIN; - current->flags |= PF_MEMALLOC_NOCMA; + current->flags |= PF_MEMALLOC_PIN; return flags; } -static inline void memalloc_nocma_restore(unsigned int flags) -{ - current->flags = (current->flags & ~PF_MEMALLOC_NOCMA) | flags; -} -#else -static inline unsigned int memalloc_nocma_save(void) +static inline void memalloc_pin_restore(unsigned int flags) { - return 0; + current->flags = (current->flags & ~PF_MEMALLOC_PIN) | flags; } -static inline void memalloc_nocma_restore(unsigned int flags) -{ -} -#endif - #ifdef CONFIG_MEMCG +DECLARE_PER_CPU(struct mem_cgroup *, int_active_memcg); /** - * memalloc_use_memcg - Starts the remote memcg charging scope. + * set_active_memcg - Starts the remote memcg charging scope. * @memcg: memcg to charge. * * This function marks the beginning of the remote memcg charging scope. All the * __GFP_ACCOUNT allocations till the end of the scope will be charged to the * given memcg. * - * NOTE: This function is not nesting safe. + * NOTE: This function can nest. Users must save the return value and + * reset the previous value after their own charging scope is over. */ -static inline void memalloc_use_memcg(struct mem_cgroup *memcg) +static inline struct mem_cgroup * +set_active_memcg(struct mem_cgroup *memcg) { - WARN_ON_ONCE(current->active_memcg); - current->active_memcg = memcg; -} + struct mem_cgroup *old; + + if (!in_task()) { + old = this_cpu_read(int_active_memcg); + this_cpu_write(int_active_memcg, memcg); + } else { + old = current->active_memcg; + current->active_memcg = memcg; + } -/** - * memalloc_unuse_memcg - Ends the remote memcg charging scope. - * - * This function marks the end of the remote memcg charging scope started by - * memalloc_use_memcg(). - */ -static inline void memalloc_unuse_memcg(void) -{ - current->active_memcg = NULL; + return old; } #else -static inline void memalloc_use_memcg(struct mem_cgroup *memcg) -{ -} - -static inline void memalloc_unuse_memcg(void) +static inline struct mem_cgroup * +set_active_memcg(struct mem_cgroup *memcg) { + return NULL; } #endif @@ -352,10 +405,13 @@ enum { MEMBARRIER_STATE_GLOBAL_EXPEDITED = (1U << 3), MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY = (1U << 4), MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE = (1U << 5), + MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY = (1U << 6), + MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ = (1U << 7), }; enum { MEMBARRIER_FLAG_SYNC_CORE = (1U << 0), + MEMBARRIER_FLAG_RSEQ = (1U << 1), }; #ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS @@ -374,6 +430,8 @@ static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm) extern void membarrier_exec_mmap(struct mm_struct *mm); +extern void membarrier_update_current_mm(struct mm_struct *next_mm); + #else #ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS static inline void membarrier_arch_switch_mm(struct mm_struct *prev, @@ -388,6 +446,34 @@ static inline void membarrier_exec_mmap(struct mm_struct *mm) static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm) { } +static inline void membarrier_update_current_mm(struct mm_struct *next_mm) +{ +} +#endif + +#ifdef CONFIG_IOMMU_SVA +static inline void mm_pasid_init(struct mm_struct *mm) +{ + mm->pasid = INVALID_IOASID; +} + +/* Associate a PASID with an mm_struct: */ +static inline void mm_pasid_set(struct mm_struct *mm, u32 pasid) +{ + mm->pasid = pasid; +} + +static inline void mm_pasid_drop(struct mm_struct *mm) +{ + if (pasid_valid(mm->pasid)) { + ioasid_free(mm->pasid); + mm->pasid = INVALID_IOASID; + } +} +#else +static inline void mm_pasid_init(struct mm_struct *mm) {} +static inline void mm_pasid_set(struct mm_struct *mm, u32 pasid) {} +static inline void mm_pasid_drop(struct mm_struct *mm) {} #endif #endif /* _LINUX_SCHED_MM_H */ |