diff options
Diffstat (limited to 'include/linux')
-rw-r--r-- | include/linux/cache.h | 10 | ||||
-rw-r--r-- | include/linux/crash_dump.h | 3 | ||||
-rw-r--r-- | include/linux/dax.h | 1 | ||||
-rw-r--r-- | include/linux/dma-noncoherent.h | 2 | ||||
-rw-r--r-- | include/linux/fs.h | 4 | ||||
-rw-r--r-- | include/linux/hmm.h | 2 | ||||
-rw-r--r-- | include/linux/huge_mm.h | 2 | ||||
-rw-r--r-- | include/linux/hugetlb.h | 2 | ||||
-rw-r--r-- | include/linux/io-mapping.h | 2 | ||||
-rw-r--r-- | include/linux/kallsyms.h | 4 | ||||
-rw-r--r-- | include/linux/kasan.h | 2 | ||||
-rw-r--r-- | include/linux/mempolicy.h | 2 | ||||
-rw-r--r-- | include/linux/mm.h | 13 | ||||
-rw-r--r-- | include/linux/mm_types.h | 4 | ||||
-rw-r--r-- | include/linux/mmap_lock.h | 90 | ||||
-rw-r--r-- | include/linux/mmu_notifier.h | 13 | ||||
-rw-r--r-- | include/linux/pagemap.h | 2 | ||||
-rw-r--r-- | include/linux/pgtable.h | 1438 | ||||
-rw-r--r-- | include/linux/rmap.h | 2 | ||||
-rw-r--r-- | include/linux/sched/debug.h | 3 | ||||
-rw-r--r-- | include/linux/sched/mm.h | 10 | ||||
-rw-r--r-- | include/linux/uaccess.h | 60 |
22 files changed, 1583 insertions, 88 deletions
diff --git a/include/linux/cache.h b/include/linux/cache.h index 750621e41d1c..1aa8009f6d06 100644 --- a/include/linux/cache.h +++ b/include/linux/cache.h @@ -15,8 +15,14 @@ /* * __read_mostly is used to keep rarely changing variables out of frequently - * updated cachelines. If an architecture doesn't support it, ignore the - * hint. + * updated cachelines. Its use should be reserved for data that is used + * frequently in hot paths. Performance traces can help decide when to use + * this. You want __read_mostly data to be tightly packed, so that in the + * best case multiple frequently read variables for a hot path will be next + * to each other in order to reduce the number of cachelines needed to + * execute a critical path. We should be mindful and selective of its use. + * ie: if you're going to use it please supply a *good* justification in your + * commit log */ #ifndef __read_mostly #define __read_mostly diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index bc156285d097..a5192b718dbe 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -5,9 +5,10 @@ #include <linux/kexec.h> #include <linux/proc_fs.h> #include <linux/elf.h> +#include <linux/pgtable.h> #include <uapi/linux/vmcore.h> -#include <asm/pgtable.h> /* for pgprot_t */ +#include <linux/pgtable.h> /* for pgprot_t */ #ifdef CONFIG_CRASH_DUMP #define ELFCORE_ADDR_MAX (-1ULL) diff --git a/include/linux/dax.h b/include/linux/dax.h index d7af5d243f24..6904d4e0b2e0 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -5,7 +5,6 @@ #include <linux/fs.h> #include <linux/mm.h> #include <linux/radix-tree.h> -#include <asm/pgtable.h> /* Flag for synchronous flush */ #define DAXDEV_F_SYNC (1UL << 0) diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h index b59f1b6be3e9..ca09a4e07d2d 100644 --- a/include/linux/dma-noncoherent.h +++ b/include/linux/dma-noncoherent.h @@ -3,7 +3,7 @@ #define _LINUX_DMA_NONCOHERENT_H 1 #include <linux/dma-mapping.h> -#include <asm/pgtable.h> +#include <linux/pgtable.h> #ifdef CONFIG_ARCH_HAS_DMA_COHERENCE_H #include <asm/dma-coherence.h> diff --git a/include/linux/fs.h b/include/linux/fs.h index 01f5d296f9bb..0b026329dbed 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1679,10 +1679,10 @@ static inline int sb_start_write_trylock(struct super_block *sb) * * Since page fault freeze protection behaves as a lock, users have to preserve * ordering of freeze protection and other filesystem locks. It is advised to - * put sb_start_pagefault() close to mmap_sem in lock ordering. Page fault + * put sb_start_pagefault() close to mmap_lock in lock ordering. Page fault * handling code implies lock dependency: * - * mmap_sem + * mmap_lock * -> sb_start_pagefault */ static inline void sb_start_pagefault(struct super_block *sb) diff --git a/include/linux/hmm.h b/include/linux/hmm.h index e912b9dc4633..f4a09ed223ac 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -10,7 +10,7 @@ #define LINUX_HMM_H #include <linux/kconfig.h> -#include <asm/pgtable.h> +#include <linux/pgtable.h> #include <linux/device.h> #include <linux/migrate.h> diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index cfbb0a87c5f0..71f20776b06c 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -248,7 +248,7 @@ static inline int is_swap_pmd(pmd_t pmd) return !pmd_none(pmd) && !pmd_present(pmd); } -/* mmap_sem must be held on entry */ +/* mmap_lock must be held on entry */ static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) { diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 0cced410e0bd..50650d0d01b9 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -9,7 +9,7 @@ #include <linux/cgroup.h> #include <linux/list.h> #include <linux/kref.h> -#include <asm/pgtable.h> +#include <linux/pgtable.h> struct ctl_table; struct user_struct; diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index b336622612f3..0beaa3eba155 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -10,6 +10,7 @@ #include <linux/slab.h> #include <linux/bug.h> #include <linux/io.h> +#include <linux/pgtable.h> #include <asm/page.h> /* @@ -99,7 +100,6 @@ io_mapping_unmap(void __iomem *vaddr) #else #include <linux/uaccess.h> -#include <asm/pgtable.h> /* Create the io_mapping object*/ static inline struct io_mapping * diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index 657a83b943f0..98338dc6b5d2 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -165,9 +165,9 @@ static inline int kallsyms_show_value(void) #endif /*CONFIG_KALLSYMS*/ -static inline void print_ip_sym(unsigned long ip) +static inline void print_ip_sym(const char *loglvl, unsigned long ip) { - printk("[<%px>] %pS\n", (void *) ip, (void *) ip); + printk("%s[<%px>] %pS\n", loglvl, (void *) ip, (void *) ip); } #endif /*_LINUX_KALLSYMS_H*/ diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 31314ca7c635..82522e996c76 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -11,8 +11,8 @@ struct task_struct; #ifdef CONFIG_KASAN +#include <linux/pgtable.h> #include <asm/kasan.h> -#include <asm/pgtable.h> extern unsigned char kasan_early_shadow_page[PAGE_SIZE]; extern pte_t kasan_early_shadow_pte[PTRS_PER_PTE]; diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 8165278c348a..ea9c15b60a96 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -31,7 +31,7 @@ struct mm_struct; * Locking policy for interlave: * In process context there is no locking because only the process accesses * its own state. All vma manipulation is somewhat protected by a down_read on - * mmap_sem. + * mmap_lock. * * Freeing policy: * Mempolicy objects are reference counted. A mempolicy will be freed when diff --git a/include/linux/mm.h b/include/linux/mm.h index 9d6042178ca7..dc7b87310c10 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -15,6 +15,7 @@ #include <linux/atomic.h> #include <linux/debug_locks.h> #include <linux/mm_types.h> +#include <linux/mmap_lock.h> #include <linux/range.h> #include <linux/pfn.h> #include <linux/percpu-refcount.h> @@ -28,6 +29,7 @@ #include <linux/overflow.h> #include <linux/sizes.h> #include <linux/sched.h> +#include <linux/pgtable.h> struct mempolicy; struct anon_vma; @@ -92,7 +94,6 @@ extern int mmap_rnd_compat_bits __read_mostly; #endif #include <asm/page.h> -#include <asm/pgtable.h> #include <asm/processor.h> /* @@ -401,7 +402,7 @@ extern pgprot_t protection_map[16]; * @FAULT_FLAG_WRITE: Fault was a write fault. * @FAULT_FLAG_MKWRITE: Fault was mkwrite of existing PTE. * @FAULT_FLAG_ALLOW_RETRY: Allow to retry the fault if blocked. - * @FAULT_FLAG_RETRY_NOWAIT: Don't drop mmap_sem and wait when retrying. + * @FAULT_FLAG_RETRY_NOWAIT: Don't drop mmap_lock and wait when retrying. * @FAULT_FLAG_KILLABLE: The fault task is in SIGKILL killable region. * @FAULT_FLAG_TRIED: The fault has been tried once. * @FAULT_FLAG_USER: The fault originated in userspace. @@ -451,10 +452,10 @@ extern pgprot_t protection_map[16]; * fault_flag_allow_retry_first - check ALLOW_RETRY the first time * * This is mostly used for places where we want to try to avoid taking - * the mmap_sem for too long a time when waiting for another condition + * the mmap_lock for too long a time when waiting for another condition * to change, in which case we can try to be polite to release the - * mmap_sem in the first round to avoid potential starvation of other - * processes that would also want the mmap_sem. + * mmap_lock in the first round to avoid potential starvation of other + * processes that would also want the mmap_lock. * * Return: true if the page fault allows retry and this is the first * attempt of the fault handling; false otherwise. @@ -581,7 +582,7 @@ struct vm_operations_struct { * (vma,addr) marked as MPOL_SHARED. The shared policy infrastructure * in mm/mempolicy.c will do this automatically. * get_policy() must NOT add a ref if the policy at (vma,addr) is not - * marked as MPOL_SHARED. vma policies are protected by the mmap_sem. + * marked as MPOL_SHARED. vma policies are protected by the mmap_lock. * If no [shared/vma] mempolicy exists at the addr, get_policy() op * must return NULL--i.e., do not "fallback" to task or system default * policy. diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index ef6d3aface8a..64ede5f150dc 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -344,7 +344,7 @@ struct vm_area_struct { * can only be in the i_mmap tree. An anonymous MAP_PRIVATE, stack * or brk vma (with NULL file) can only be in an anon_vma list. */ - struct list_head anon_vma_chain; /* Serialized by mmap_sem & + struct list_head anon_vma_chain; /* Serialized by mmap_lock & * page_table_lock */ struct anon_vma *anon_vma; /* Serialized by page_table_lock */ @@ -440,7 +440,7 @@ struct mm_struct { spinlock_t page_table_lock; /* Protects page tables and some * counters */ - struct rw_semaphore mmap_sem; + struct rw_semaphore mmap_lock; struct list_head mmlist; /* List of maybe swapped mm's. These * are globally strung together off diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h new file mode 100644 index 000000000000..0707671851a8 --- /dev/null +++ b/include/linux/mmap_lock.h @@ -0,0 +1,90 @@ +#ifndef _LINUX_MMAP_LOCK_H +#define _LINUX_MMAP_LOCK_H + +#include <linux/mmdebug.h> + +#define MMAP_LOCK_INITIALIZER(name) \ + .mmap_lock = __RWSEM_INITIALIZER((name).mmap_lock), + +static inline void mmap_init_lock(struct mm_struct *mm) +{ + init_rwsem(&mm->mmap_lock); +} + +static inline void mmap_write_lock(struct mm_struct *mm) +{ + down_write(&mm->mmap_lock); +} + +static inline void mmap_write_lock_nested(struct mm_struct *mm, int subclass) +{ + down_write_nested(&mm->mmap_lock, subclass); +} + +static inline int mmap_write_lock_killable(struct mm_struct *mm) +{ + return down_write_killable(&mm->mmap_lock); +} + +static inline bool mmap_write_trylock(struct mm_struct *mm) +{ + return down_write_trylock(&mm->mmap_lock) != 0; +} + +static inline void mmap_write_unlock(struct mm_struct *mm) +{ + up_write(&mm->mmap_lock); +} + +static inline void mmap_write_downgrade(struct mm_struct *mm) +{ + downgrade_write(&mm->mmap_lock); +} + +static inline void mmap_read_lock(struct mm_struct *mm) +{ + down_read(&mm->mmap_lock); +} + +static inline int mmap_read_lock_killable(struct mm_struct *mm) +{ + return down_read_killable(&mm->mmap_lock); +} + +static inline bool mmap_read_trylock(struct mm_struct *mm) +{ + return down_read_trylock(&mm->mmap_lock) != 0; +} + +static inline void mmap_read_unlock(struct mm_struct *mm) +{ + up_read(&mm->mmap_lock); +} + +static inline bool mmap_read_trylock_non_owner(struct mm_struct *mm) +{ + if (down_read_trylock(&mm->mmap_lock)) { + rwsem_release(&mm->mmap_lock.dep_map, _RET_IP_); + return true; + } + return false; +} + +static inline void mmap_read_unlock_non_owner(struct mm_struct *mm) +{ + up_read_non_owner(&mm->mmap_lock); +} + +static inline void mmap_assert_locked(struct mm_struct *mm) +{ + lockdep_assert_held(&mm->mmap_lock); + VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); +} + +static inline void mmap_assert_write_locked(struct mm_struct *mm) +{ + lockdep_assert_held_write(&mm->mmap_lock); + VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); +} + +#endif /* _LINUX_MMAP_LOCK_H */ diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 736f6918335e..fc68f3570e19 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -5,6 +5,7 @@ #include <linux/list.h> #include <linux/spinlock.h> #include <linux/mm_types.h> +#include <linux/mmap_lock.h> #include <linux/srcu.h> #include <linux/interval_tree.h> @@ -121,7 +122,7 @@ struct mmu_notifier_ops { /* * invalidate_range_start() and invalidate_range_end() must be - * paired and are called only when the mmap_sem and/or the + * paired and are called only when the mmap_lock and/or the * locks protecting the reverse maps are held. If the subsystem * can't guarantee that no additional references are taken to * the pages in the range, it has to implement the @@ -212,13 +213,13 @@ struct mmu_notifier_ops { }; /* - * The notifier chains are protected by mmap_sem and/or the reverse map + * The notifier chains are protected by mmap_lock and/or the reverse map * semaphores. Notifier chains are only changed when all reverse maps and - * the mmap_sem locks are taken. + * the mmap_lock locks are taken. * * Therefore notifier chains can only be traversed when either * - * 1. mmap_sem is held. + * 1. mmap_lock is held. * 2. One of the reverse map locks is held (i_mmap_rwsem or anon_vma->rwsem). * 3. No other concurrent thread can access the list (release) */ @@ -277,9 +278,9 @@ mmu_notifier_get(const struct mmu_notifier_ops *ops, struct mm_struct *mm) { struct mmu_notifier *ret; - down_write(&mm->mmap_sem); + mmap_write_lock(mm); ret = mmu_notifier_get_locked(ops, mm); - up_write(&mm->mmap_sem); + mmap_write_unlock(mm); return ret; } void mmu_notifier_put(struct mmu_notifier *subscription); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 8e085713150c..cf2468da68e9 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -538,7 +538,7 @@ static inline int lock_page_killable(struct page *page) * lock_page_or_retry - Lock the page, unless this would block and the * caller indicated that it can handle a retry. * - * Return value and mmap_sem implications depend on flags; see + * Return value and mmap_lock implications depend on flags; see * __lock_page_or_retry(). */ static inline int lock_page_or_retry(struct page *page, struct mm_struct *mm, diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h new file mode 100644 index 000000000000..32b6c52d41b9 --- /dev/null +++ b/include/linux/pgtable.h @@ -0,0 +1,1438 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_PGTABLE_H +#define _LINUX_PGTABLE_H + +#include <linux/pfn.h> +#include <asm/pgtable.h> + +#ifndef __ASSEMBLY__ +#ifdef CONFIG_MMU + +#include <linux/mm_types.h> +#include <linux/bug.h> +#include <linux/errno.h> +#include <asm-generic/pgtable_uffd.h> + +#if 5 - defined(__PAGETABLE_P4D_FOLDED) - defined(__PAGETABLE_PUD_FOLDED) - \ + defined(__PAGETABLE_PMD_FOLDED) != CONFIG_PGTABLE_LEVELS +#error CONFIG_PGTABLE_LEVELS is not consistent with __PAGETABLE_{P4D,PUD,PMD}_FOLDED +#endif + +/* + * On almost all architectures and configurations, 0 can be used as the + * upper ceiling to free_pgtables(): on many architectures it has the same + * effect as using TASK_SIZE. However, there is one configuration which + * must impose a more careful limit, to avoid freeing kernel pgtables. + */ +#ifndef USER_PGTABLES_CEILING +#define USER_PGTABLES_CEILING 0UL +#endif + +/* + * A page table page can be thought of an array like this: pXd_t[PTRS_PER_PxD] + * + * The pXx_index() functions return the index of the entry in the page + * table page which would control the given virtual address + * + * As these functions may be used by the same code for different levels of + * the page table folding, they are always available, regardless of + * CONFIG_PGTABLE_LEVELS value. For the folded levels they simply return 0 + * because in such cases PTRS_PER_PxD equals 1. + */ + +static inline unsigned long pte_index(unsigned long address) +{ + return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); +} + +#ifndef pmd_index +static inline unsigned long pmd_index(unsigned long address) +{ + return (address >> PMD_SHIFT) & (PTRS_PER_PMD - 1); +} +#define pmd_index pmd_index +#endif + +#ifndef pud_index +static inline unsigned long pud_index(unsigned long address) +{ + return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1); +} +#define pud_index pud_index +#endif + +#ifndef pgd_index +/* Must be a compile-time constant, so implement it as a macro */ +#define pgd_index(a) (((a) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1)) +#endif + +#ifndef pte_offset_kernel +static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address) +{ + return (pte_t *)pmd_page_vaddr(*pmd) + pte_index(address); +} +#define pte_offset_kernel pte_offset_kernel +#endif + +#if defined(CONFIG_HIGHPTE) +#define pte_offset_map(dir, address) \ + ((pte_t *)kmap_atomic(pmd_page(*(dir))) + \ + pte_index((address))) +#define pte_unmap(pte) kunmap_atomic((pte)) +#else +#define pte_offset_map(dir, address) pte_offset_kernel((dir), (address)) +#define pte_unmap(pte) ((void)(pte)) /* NOP */ +#endif + +/* Find an entry in the second-level page table.. */ +#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); +} +#define pmd_offset pmd_offset +#endif + +#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); +} +#define pud_offset pud_offset +#endif + +static inline pgd_t *pgd_offset_pgd(pgd_t *pgd, unsigned long address) +{ + return (pgd + pgd_index(address)); +}; + +/* + * a shortcut to get a pgd_t in a given mm + */ +#ifndef pgd_offset +#define pgd_offset(mm, address) pgd_offset_pgd((mm)->pgd, (address)) +#endif + +/* + * a shortcut which implies the use of the kernel's pgd, instead + * of a process's + */ +#define pgd_offset_k(address) pgd_offset(&init_mm, (address)) + +/* + * In many cases it is known that a virtual address is mapped at PMD or PTE + * level, so instead of traversing all the page table levels, we can get a + * pointer to the PMD entry in user or kernel page table or translate a virtual + * address to the pointer in the PTE in the kernel page tables with simple + * helpers. + */ +static inline pmd_t *pmd_off(struct mm_struct *mm, unsigned long va) +{ + return pmd_offset(pud_offset(p4d_offset(pgd_offset(mm, va), va), va), va); +} + +static inline pmd_t *pmd_off_k(unsigned long va) +{ + return pmd_offset(pud_offset(p4d_offset(pgd_offset_k(va), va), va), va); +} + +static inline pte_t *virt_to_kpte(unsigned long vaddr) +{ + pmd_t *pmd = pmd_off_k(vaddr); + + return pmd_none(*pmd) ? NULL : pte_offset_kernel(pmd, vaddr); +} + +#ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS +extern int ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep, + pte_t entry, int dirty); +#endif + +#ifndef __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +extern int pmdp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, + pmd_t entry, int dirty); +extern int pudp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp, + pud_t entry, int dirty); +#else +static inline int pmdp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, + pmd_t entry, int dirty) +{ + BUILD_BUG(); + return 0; +} +static inline int pudp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp, + pud_t entry, int dirty) +{ + BUILD_BUG(); + return 0; +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif + +#ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG +static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, + pte_t *ptep) +{ + pte_t pte = *ptep; + int r = 1; + if (!pte_young(pte)) + r = 0; + else + set_pte_at(vma->vm_mm, address, ptep, pte_mkold(pte)); + return r; +} +#endif + +#ifndef __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, + pmd_t *pmdp) +{ + pmd_t pmd = *pmdp; + int r = 1; + if (!pmd_young(pmd)) + r = 0; + else + set_pmd_at(vma->vm_mm, address, pmdp, pmd_mkold(pmd)); + return r; +} +#else +static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, + pmd_t *pmdp) +{ + BUILD_BUG(); + return 0; +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif + +#ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH +int ptep_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep); +#endif + +#ifndef __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +extern int pmdp_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); +#else +/* + * Despite relevant to THP only, this API is called from generic rmap code + * under PageTransHuge(), hence needs a dummy implementation for !THP + */ +static inline int pmdp_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp) +{ + BUILD_BUG(); + return 0; +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif + +#ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR +static inline pte_t ptep_get_and_clear(struct mm_struct *mm, + unsigned long address, + pte_t *ptep) +{ + pte_t pte = *ptep; + pte_clear(mm, address, ptep); + return pte; +} +#endif + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR +static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, + unsigned long address, + pmd_t *pmdp) +{ + pmd_t pmd = *pmdp; + pmd_clear(pmdp); + return pmd; +} +#endif /* __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR */ +#ifndef __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR +static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, + unsigned long address, + pud_t *pudp) +{ + pud_t pud = *pudp; + + pud_clear(pudp); + return pud; +} +#endif /* __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR */ +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR_FULL +static inline pmd_t pmdp_huge_get_and_clear_full(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, + int full) +{ + return pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); +} +#endif + +#ifndef __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR_FULL +static inline pud_t pudp_huge_get_and_clear_full(struct mm_struct *mm, + unsigned long address, pud_t *pudp, + int full) +{ + return pudp_huge_get_and_clear(mm, address, pudp); +} +#endif +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +#ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL +static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, + unsigned long address, pte_t *ptep, + int full) +{ + pte_t pte; + pte = ptep_get_and_clear(mm, address, ptep); + return pte; +} +#endif + + +/* + * If two threads concurrently fault at the same page, the thread that + * won the race updates the PTE and its local TLB/Cache. The other thread + * gives up, simply does nothing, and continues; on architectures where + * software can update TLB, local TLB can be updated here to avoid next page + * fault. This function updates TLB only, do nothing with cache or others. + * It is the difference with function update_mmu_cache. + */ +#ifndef __HAVE_ARCH_UPDATE_MMU_TLB +static inline void update_mmu_tlb(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep) +{ +} +#define __HAVE_ARCH_UPDATE_MMU_TLB +#endif + +/* + * Some architectures may be able to avoid expensive synchronization + * primitives when modifications are made to PTE's which are already + * not present, or in the process of an address space destruction. + */ +#ifndef __HAVE_ARCH_PTE_CLEAR_NOT_PRESENT_FULL +static inline void pte_clear_not_present_full(struct mm_struct *mm, + unsigned long address, + pte_t *ptep, + int full) +{ + pte_clear(mm, address, ptep); +} +#endif + +#ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH +extern pte_t ptep_clear_flush(struct vm_area_struct *vma, + unsigned long address, + pte_t *ptep); +#endif + +#ifndef __HAVE_ARCH_PMDP_HUGE_CLEAR_FLUSH +extern pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, + unsigned long address, + pmd_t *pmdp); +extern pud_t pudp_huge_clear_flush(struct vm_area_struct *vma, + unsigned long address, + pud_t *pudp); +#endif + +#ifndef __HAVE_ARCH_PTEP_SET_WRPROTECT +struct mm_struct; +static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep) +{ + pte_t old_pte = *ptep; + set_pte_at(mm, address, ptep, pte_wrprotect(old_pte)); +} +#endif + +/* + * On some architectures hardware does not set page access bit when accessing + * memory page, it is responsibilty of software setting this bit. It brings + * out extra page fault penalty to track page access bit. For optimization page + * access bit can be set during all page fault flow on these arches. + * To be differentiate with macro pte_mkyoung, this macro is used on platforms + * where software maintains page access bit. + */ +#ifndef pte_sw_mkyoung +static inline pte_t pte_sw_mkyoung(pte_t pte) +{ + return pte; +} +#define pte_sw_mkyoung pte_sw_mkyoung +#endif + +#ifndef pte_savedwrite +#define pte_savedwrite pte_write +#endif + +#ifndef pte_mk_savedwrite +#define pte_mk_savedwrite pte_mkwrite +#endif + +#ifndef pte_clear_savedwrite +#define pte_clear_savedwrite pte_wrprotect +#endif + +#ifndef pmd_savedwrite +#define pmd_savedwrite pmd_write +#endif + +#ifndef pmd_mk_savedwrite +#define pmd_mk_savedwrite pmd_mkwrite +#endif + +#ifndef pmd_clear_savedwrite +#define pmd_clear_savedwrite pmd_wrprotect +#endif + +#ifndef __HAVE_ARCH_PMDP_SET_WRPROTECT +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline void pmdp_set_wrprotect(struct mm_struct *mm, + unsigned long address, pmd_t *pmdp) +{ + pmd_t old_pmd = *pmdp; + set_pmd_at(mm, address, pmdp, pmd_wrprotect(old_pmd)); +} +#else +static inline void pmdp_set_wrprotect(struct mm_struct *mm, + unsigned long address, pmd_t *pmdp) +{ + BUILD_BUG(); +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif +#ifndef __HAVE_ARCH_PUDP_SET_WRPROTECT +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +static inline void pudp_set_wrprotect(struct mm_struct *mm, + unsigned long address, pud_t *pudp) +{ + pud_t old_pud = *pudp; + + set_pud_at(mm, address, pudp, pud_wrprotect(old_pud)); +} +#else +static inline void pudp_set_wrprotect(struct mm_struct *mm, + unsigned long address, pud_t *pudp) +{ + BUILD_BUG(); +} +#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ +#endif + +#ifndef pmdp_collapse_flush +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); +#else +static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, + unsigned long address, + pmd_t *pmdp) +{ + BUILD_BUG(); + return *pmdp; +} +#define pmdp_collapse_flush pmdp_collapse_flush +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif + +#ifndef __HAVE_ARCH_PGTABLE_DEPOSIT +extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, + pgtable_t pgtable); +#endif + +#ifndef __HAVE_ARCH_PGTABLE_WITHDRAW +extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); +#endif + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +/* + * This is an implementation of pmdp_establish() that is only suitable for an + * architecture that doesn't have hardware dirty/accessed bits. In this case we + * can't race with CPU which sets these bits and non-atomic aproach is fine. + */ +static inline pmd_t generic_pmdp_establish(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, pmd_t pmd) +{ + pmd_t old_pmd = *pmdp; + set_pmd_at(vma->vm_mm, address, pmdp, pmd); + return old_pmd; +} +#endif + +#ifndef __HAVE_ARCH_PMDP_INVALIDATE +extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmdp); +#endif + +#ifndef __HAVE_ARCH_PTE_SAME +static inline int pte_same(pte_t pte_a, pte_t pte_b) +{ + return pte_val(pte_a) == pte_val(pte_b); +} +#endif + +#ifndef __HAVE_ARCH_PTE_UNUSED +/* + * Some architectures provide facilities to virtualization guests + * so that they can flag allocated pages as unused. This allows the + * host to transparently reclaim unused pages. This function returns + * whether the pte's page is unused. + */ +static inline int pte_unused(pte_t pte) +{ + return 0; +} +#endif + +#ifndef pte_access_permitted +#define pte_access_permitted(pte, write) \ + (pte_present(pte) && (!(write) || pte_write(pte))) +#endif + +#ifndef pmd_access_permitted +#define pmd_access_permitted(pmd, write) \ + (pmd_present(pmd) && (!(write) || pmd_write(pmd))) +#endif + +#ifndef pud_access_permitted +#define pud_access_permitted(pud, write) \ + (pud_present(pud) && (!(write) || pud_write(pud))) +#endif + +#ifndef p4d_access_permitted +#define p4d_access_permitted(p4d, write) \ + (p4d_present(p4d) && (!(write) || p4d_write(p4d))) +#endif + +#ifndef pgd_access_permitted +#define pgd_access_permitted(pgd, write) \ + (pgd_present(pgd) && (!(write) || pgd_write(pgd))) +#endif + +#ifndef __HAVE_ARCH_PMD_SAME +static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) +{ + return pmd_val(pmd_a) == pmd_val(pmd_b); +} + +static inline int pud_same(pud_t pud_a, pud_t pud_b) +{ + return pud_val(pud_a) == pud_val(pud_b); +} +#endif + +#ifndef __HAVE_ARCH_P4D_SAME +static inline int p4d_same(p4d_t p4d_a, p4d_t p4d_b) +{ + return p4d_val(p4d_a) == p4d_val(p4d_b); +} +#endif + +#ifndef __HAVE_ARCH_PGD_SAME +static inline int pgd_same(pgd_t pgd_a, pgd_t pgd_b) +{ + return pgd_val(pgd_a) == pgd_val(pgd_b); +} +#endif + +/* + * Use set_p*_safe(), and elide TLB flushing, when confident that *no* + * TLB flush will be required as a result of the "set". For example, use + * in scenarios where it is known ahead of time that the routine is + * setting non-present entries, or re-setting an existing entry to the + * same value. Otherwise, use the typical "set" helpers and flush the + * TLB. + */ +#define set_pte_safe(ptep, pte) \ +({ \ + WARN_ON_ONCE(pte_present(*ptep) && !pte_same(*ptep, pte)); \ + set_pte(ptep, pte); \ +}) + +#define set_pmd_safe(pmdp, pmd) \ +({ \ + WARN_ON_ONCE(pmd_present(*pmdp) && !pmd_same(*pmdp, pmd)); \ + set_pmd(pmdp, pmd); \ +}) + +#define set_pud_safe(pudp, pud) \ +({ \ + WARN_ON_ONCE(pud_present(*pudp) && !pud_same(*pudp, pud)); \ + set_pud(pudp, pud); \ +}) + +#define set_p4d_safe(p4dp, p4d) \ +({ \ + WARN_ON_ONCE(p4d_present(*p4dp) && !p4d_same(*p4dp, p4d)); \ + set_p4d(p4dp, p4d); \ +}) + +#define set_pgd_safe(pgdp, pgd) \ +({ \ + WARN_ON_ONCE(pgd_present(*pgdp) && !pgd_same(*pgdp, pgd)); \ + set_pgd(pgdp, pgd); \ +}) + +#ifndef __HAVE_ARCH_DO_SWAP_PAGE +/* + * Some architectures support metadata associated with a page. When a + * page is being swapped out, this metadata must be saved so it can be + * restored when the page is swapped back in. SPARC M7 and newer + * processors support an ADI (Application Data Integrity) tag for the + * page as metadata for the page. arch_do_swap_page() can restore this + * metadata when a page is swapped back in. + */ +static inline void arch_do_swap_page(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long addr, + pte_t pte, pte_t oldpte) +{ + +} +#endif + +#ifndef __HAVE_ARCH_UNMAP_ONE +/* + * Some architectures support metadata associated with a page. When a + * page is being swapped out, this metadata must be saved so it can be + * restored when the page is swapped back in. SPARC M7 and newer + * processors support an ADI (Application Data Integrity) tag for the + * page as metadata for the page. arch_unmap_one() can save this + * metadata on a swap-out of a page. + */ +static inline int arch_unmap_one(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long addr, + pte_t orig_pte) +{ + return 0; +} +#endif + +#ifndef __HAVE_ARCH_PGD_OFFSET_GATE +#define pgd_offset_gate(mm, addr) pgd_offset(mm, addr) +#endif + +#ifndef __HAVE_ARCH_MOVE_PTE +#define move_pte(pte, prot, old_addr, new_addr) (pte) +#endif + +#ifndef pte_accessible +# define pte_accessible(mm, pte) ((void)(pte), 1) +#endif + +#ifndef flush_tlb_fix_spurious_fault +#define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address) +#endif + +#ifndef pgprot_nx +#define pgprot_nx(prot) (prot) +#endif + +#ifndef pgprot_noncached +#define pgprot_noncached(prot) (prot) +#endif + +#ifndef pgprot_writecombine +#define pgprot_writecombine pgprot_noncached +#endif + +#ifndef pgprot_writethrough +#define pgprot_writethrough pgprot_noncached +#endif + +#ifndef pgprot_device +#define pgprot_device pgprot_noncached +#endif + +#ifndef pgprot_modify +#define pgprot_modify pgprot_modify +static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) +{ + if (pgprot_val(oldprot) == pgprot_val(pgprot_noncached(oldprot))) + newprot = pgprot_noncached(newprot); + if (pgprot_val(oldprot) == pgprot_val(pgprot_writecombine(oldprot))) + newprot = pgprot_writecombine(newprot); + if (pgprot_val(oldprot) == pgprot_val(pgprot_device(oldprot))) + newprot = pgprot_device(newprot); + return newprot; +} +#endif + +/* + * When walking page tables, get the address of the next boundary, + * or the end address of the range if that comes earlier. Although no + * vma end wraps to 0, rounded up __boundary may wrap to 0 throughout. + */ + +#define pgd_addr_end(addr, end) \ +({ unsigned long __boundary = ((addr) + PGDIR_SIZE) & PGDIR_MASK; \ + (__boundary - 1 < (end) - 1)? __boundary: (end); \ +}) + +#ifndef p4d_addr_end +#define p4d_addr_end(addr, end) \ +({ unsigned long __boundary = ((addr) + P4D_SIZE) & P4D_MASK; \ + (__boundary - 1 < (end) - 1)? __boundary: (end); \ +}) +#endif + +#ifndef pud_addr_end +#define pud_addr_end(addr, end) \ +({ unsigned long __boundary = ((addr) + PUD_SIZE) & PUD_MASK; \ + (__boundary - 1 < (end) - 1)? __boundary: (end); \ +}) +#endif + +#ifndef pmd_addr_end +#define pmd_addr_end(addr, end) \ +({ unsigned long __boundary = ((addr) + PMD_SIZE) & PMD_MASK; \ + (__boundary - 1 < (end) - 1)? __boundary: (end); \ +}) +#endif + +/* + * When walking page tables, we usually want to skip any p?d_none entries; + * and any p?d_bad entries - reporting the error before resetting to none. + * Do the tests inline, but report and clear the bad entry in mm/memory.c. + */ +void pgd_clear_bad(pgd_t *); + +#ifndef __PAGETABLE_P4D_FOLDED +void p4d_clear_bad(p4d_t *); +#else +#define p4d_clear_bad(p4d) do { } while (0) +#endif + +#ifndef __PAGETABLE_PUD_FOLDED +void pud_clear_bad(pud_t *); +#else +#define pud_clear_bad(p4d) do { } while (0) +#endif + +void pmd_clear_bad(pmd_t *); + +static inline int pgd_none_or_clear_bad(pgd_t *pgd) +{ + if (pgd_none(*pgd)) + return 1; + if (unlikely(pgd_bad(*pgd))) { + pgd_clear_bad(pgd); + return 1; + } + return 0; +} + +static inline int p4d_none_or_clear_bad(p4d_t *p4d) +{ + if (p4d_none(*p4d)) + return 1; + if (unlikely(p4d_bad(*p4d))) { + p4d_clear_bad(p4d); + return 1; + } + return 0; +} + +static inline int pud_none_or_clear_bad(pud_t *pud) +{ + if (pud_none(*pud)) + return 1; + if (unlikely(pud_bad(*pud))) { + pud_clear_bad(pud); + return 1; + } + return 0; +} + +static inline int pmd_none_or_clear_bad(pmd_t *pmd) +{ + if (pmd_none(*pmd)) + return 1; + if (unlikely(pmd_bad(*pmd))) { + pmd_clear_bad(pmd); + return 1; + } + return 0; +} + +static inline pte_t __ptep_modify_prot_start(struct vm_area_struct *vma, + unsigned long addr, + pte_t *ptep) +{ + /* + * Get the current pte state, but zero it out to make it + * non-present, preventing the hardware from asynchronously + * updating it. + */ + return ptep_get_and_clear(vma->vm_mm, addr, ptep); +} + +static inline void __ptep_modify_prot_commit(struct vm_area_struct *vma, + unsigned long addr, + pte_t *ptep, pte_t pte) +{ + /* + * The pte is non-present, so there's no hardware state to + * preserve. + */ + set_pte_at(vma->vm_mm, addr, ptep, pte); +} + +#ifndef __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION +/* + * Start a pte protection read-modify-write transaction, which + * protects against asynchronous hardware modifications to the pte. + * The intention is not to prevent the hardware from making pte + * updates, but to prevent any updates it may make from being lost. + * + * This does not protect against other software modifications of the + * pte; the appropriate pte lock must be held over the transation. + * + * Note that this interface is intended to be batchable, meaning that + * ptep_modify_prot_commit may not actually update the pte, but merely + * queue the update to be done at some later time. The update must be + * actually committed before the pte lock is released, however. + */ +static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma, + unsigned long addr, + pte_t *ptep) +{ + return __ptep_modify_prot_start(vma, addr, ptep); +} + +/* + * Commit an update to a pte, leaving any hardware-controlled bits in + * the PTE unmodified. + */ +static inline void ptep_modify_prot_commit(struct vm_area_struct *vma, + unsigned long addr, + pte_t *ptep, pte_t old_pte, pte_t pte) +{ + __ptep_modify_prot_commit(vma, addr, ptep, pte); +} +#endif /* __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION */ +#endif /* CONFIG_MMU */ + +/* + * No-op macros that just return the current protection value. Defined here + * because these macros can be used used even if CONFIG_MMU is not defined. + */ +#ifndef pgprot_encrypted +#define pgprot_encrypted(prot) (prot) +#endif + +#ifndef pgprot_decrypted +#define pgprot_decrypted(prot) (prot) +#endif + +/* + * A facility to provide lazy MMU batching. This allows PTE updates and + * page invalidations to be delayed until a call to leave lazy MMU mode + * is issued. Some architectures may benefit from doing this, and it is + * beneficial for both shadow and direct mode hypervisors, which may batch + * the PTE updates which happen during this window. Note that using this + * interface requires that read hazards be removed from the code. A read + * hazard could result in the direct mode hypervisor case, since the actual + * write to the page tables may not yet have taken place, so reads though + * a raw PTE pointer after it has been modified are not guaranteed to be + * up to date. This mode can only be entered and left under the protection of + * the page table locks for all page tables which may be modified. In the UP + * case, this is required so that preemption is disabled, and in the SMP case, + * it must synchronize the delayed page table writes properly on other CPUs. + */ +#ifndef __HAVE_ARCH_ENTER_LAZY_MMU_MODE +#define arch_enter_lazy_mmu_mode() do {} while (0) +#define arch_leave_lazy_mmu_mode() do {} while (0) +#define arch_flush_lazy_mmu_mode() do {} while (0) +#endif + +/* + * A facility to provide batching of the reload of page tables and + * other process state with the actual context switch code for + * paravirtualized guests. By convention, only one of the batched + * update (lazy) modes (CPU, MMU) should be active at any given time, + * entry should never be nested, and entry and exits should always be + * paired. This is for sanity of maintaining and reasoning about the + * kernel code. In this case, the exit (end of the context switch) is + * in architecture-specific code, and so doesn't need a generic + * definition. + */ +#ifndef __HAVE_ARCH_START_CONTEXT_SWITCH +#define arch_start_context_switch(prev) do {} while (0) +#endif + +#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY +#ifndef CONFIG_ARCH_ENABLE_THP_MIGRATION +static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd) +{ + return pmd; +} + +static inline int pmd_swp_soft_dirty(pmd_t pmd) +{ + return 0; +} + +static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd) +{ + return pmd; +} +#endif +#else /* !CONFIG_HAVE_ARCH_SOFT_DIRTY */ +static inline int pte_soft_dirty(pte_t pte) +{ + return 0; +} + +static inline int pmd_soft_dirty(pmd_t pmd) +{ + return 0; +} + +static inline pte_t pte_mksoft_dirty(pte_t pte) +{ + return pte; +} + +static inline pmd_t pmd_mksoft_dirty(pmd_t pmd) +{ + return pmd; +} + +static inline pte_t pte_clear_soft_dirty(pte_t pte) +{ + return pte; +} + +static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd) +{ + return pmd; +} + +static inline pte_t pte_swp_mksoft_dirty(pte_t pte) +{ + return pte; +} + +static inline int pte_swp_soft_dirty(pte_t pte) +{ + return 0; +} + +static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) +{ + return pte; +} + +static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd) +{ + return pmd; +} + +static inline int pmd_swp_soft_dirty(pmd_t pmd) +{ + return 0; +} + +static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd) +{ + return pmd; +} +#endif + +#ifndef __HAVE_PFNMAP_TRACKING +/* + * Interfaces that can be used by architecture code to keep track of + * memory type of pfn mappings specified by the remap_pfn_range, + * vmf_insert_pfn. + */ + +/* + * track_pfn_remap is called when a _new_ pfn mapping is being established + * by remap_pfn_range() for physical range indicated by pfn and size. + */ +static inline int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, + unsigned long pfn, unsigned long addr, + unsigned long size) +{ + return 0; +} + +/* + * track_pfn_insert is called when a _new_ single pfn is established + * by vmf_insert_pfn(). + */ +static inline void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, + pfn_t pfn) +{ +} + +/* + * track_pfn_copy is called when vma that is covering the pfnmap gets + * copied through copy_page_range(). + */ +static inline int track_pfn_copy(struct vm_area_struct *vma) +{ + return 0; +} + +/* + * untrack_pfn is called while unmapping a pfnmap for a region. + * untrack can be called for a specific region indicated by pfn and size or + * can be for the entire vma (in which case pfn, size are zero). + */ +static inline void untrack_pfn(struct vm_area_struct *vma, + unsigned long pfn, unsigned long size) +{ +} + +/* + * untrack_pfn_moved is called while mremapping a pfnmap for a new region. + */ +static inline void untrack_pfn_moved(struct vm_area_struct *vma) +{ +} +#else +extern int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, + unsigned long pfn, unsigned long addr, + unsigned long size); +extern void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, + pfn_t pfn); +extern int track_pfn_copy(struct vm_area_struct *vma); +extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, + unsigned long size); +extern void untrack_pfn_moved(struct vm_area_struct *vma); +#endif + +#ifdef __HAVE_COLOR_ZERO_PAGE +static inline int is_zero_pfn(unsigned long pfn) +{ + extern unsigned long zero_pfn; + unsigned long offset_from_zero_pfn = pfn - zero_pfn; + return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT); +} + +#define my_zero_pfn(addr) page_to_pfn(ZERO_PAGE(addr)) + +#else +static inline int is_zero_pfn(unsigned long pfn) +{ + extern unsigned long zero_pfn; + return pfn == zero_pfn; +} + +static inline unsigned long my_zero_pfn(unsigned long addr) +{ + extern unsigned long zero_pfn; + return zero_pfn; +} +#endif + +#ifdef CONFIG_MMU + +#ifndef CONFIG_TRANSPARENT_HUGEPAGE +static inline int pmd_trans_huge(pmd_t pmd) +{ + return 0; +} +#ifndef pmd_write +static inline int pmd_write(pmd_t pmd) +{ + BUG(); + return 0; +} +#endif /* pmd_write */ +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +#ifndef pud_write +static inline int pud_write(pud_t pud) +{ + BUG(); + return 0; +} +#endif /* pud_write */ + +#if !defined(CONFIG_ARCH_HAS_PTE_DEVMAP) || !defined(CONFIG_TRANSPARENT_HUGEPAGE) +static inline int pmd_devmap(pmd_t pmd) +{ + return 0; +} +static inline int pud_devmap(pud_t pud) +{ + return 0; +} +static inline int pgd_devmap(pgd_t pgd) +{ + return 0; +} +#endif + +#if !defined(CONFIG_TRANSPARENT_HUGEPAGE) || \ + (defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ + !defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)) +static inline int pud_trans_huge(pud_t pud) +{ + return 0; +} +#endif + +/* See pmd_none_or_trans_huge_or_clear_bad for discussion. */ +static inline int pud_none_or_trans_huge_or_dev_or_clear_bad(pud_t *pud) +{ + pud_t pudval = READ_ONCE(*pud); + + if (pud_none(pudval) || pud_trans_huge(pudval) || pud_devmap(pudval)) + return 1; + if (unlikely(pud_bad(pudval))) { + pud_clear_bad(pud); + return 1; + } + return 0; +} + +/* See pmd_trans_unstable for discussion. */ +static inline int pud_trans_unstable(pud_t *pud) +{ +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ + defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) + return pud_none_or_trans_huge_or_dev_or_clear_bad(pud); +#else + return 0; +#endif +} + +#ifndef pmd_read_atomic +static inline pmd_t pmd_read_atomic(pmd_t *pmdp) +{ + /* + * Depend on compiler for an atomic pmd read. NOTE: this is + * only going to work, if the pmdval_t isn't larger than + * an unsigned long. + */ + return *pmdp; +} +#endif + +#ifndef arch_needs_pgtable_deposit +#define arch_needs_pgtable_deposit() (false) +#endif +/* + * This function is meant to be used by sites walking pagetables with + * the mmap_lock held in read mode to protect against MADV_DONTNEED and + * transhuge page faults. MADV_DONTNEED can convert a transhuge pmd + * into a null pmd and the transhuge page fault can convert a null pmd + * into an hugepmd or into a regular pmd (if the hugepage allocation + * fails). While holding the mmap_lock in read mode the pmd becomes + * stable and stops changing under us only if it's not null and not a + * transhuge pmd. When those races occurs and this function makes a + * difference vs the standard pmd_none_or_clear_bad, the result is + * undefined so behaving like if the pmd was none is safe (because it + * can return none anyway). The compiler level barrier() is critically + * important to compute the two checks atomically on the same pmdval. + * + * For 32bit kernels with a 64bit large pmd_t this automatically takes + * care of reading the pmd atomically to avoid SMP race conditions + * against pmd_populate() when the mmap_lock is hold for reading by the + * caller (a special atomic read not done by "gcc" as in the generic + * version above, is also needed when THP is disabled because the page + * fault can populate the pmd from under us). + */ +static inline int pmd_none_or_trans_huge_or_clear_bad(pmd_t *pmd) +{ + pmd_t pmdval = pmd_read_atomic(pmd); + /* + * The barrier will stabilize the pmdval in a register or on + * the stack so that it will stop changing under the code. + * + * When CONFIG_TRANSPARENT_HUGEPAGE=y on x86 32bit PAE, + * pmd_read_atomic is allowed to return a not atomic pmdval + * (for example pointing to an hugepage that has never been + * mapped in the pmd). The below checks will only care about + * the low part of the pmd with 32bit PAE x86 anyway, with the + * exception of pmd_none(). So the important thing is that if + * the low part of the pmd is found null, the high part will + * be also null or the pmd_none() check below would be + * confused. + */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + barrier(); +#endif + /* + * !pmd_present() checks for pmd migration entries + * + * The complete check uses is_pmd_migration_entry() in linux/swapops.h + * But using that requires moving current function and pmd_trans_unstable() + * to linux/swapops.h to resovle dependency, which is too much code move. + * + * !pmd_present() is equivalent to is_pmd_migration_entry() currently, + * because !pmd_present() pages can only be under migration not swapped + * out. + * + * pmd_none() is preseved for future condition checks on pmd migration + * entries and not confusing with this function name, although it is + * redundant with !pmd_present(). + */ + if (pmd_none(pmdval) || pmd_trans_huge(pmdval) || + (IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION) && !pmd_present(pmdval))) + return 1; + if (unlikely(pmd_bad(pmdval))) { + pmd_clear_bad(pmd); + return 1; + } + return 0; +} + +/* + * This is a noop if Transparent Hugepage Support is not built into + * the kernel. Otherwise it is equivalent to + * pmd_none_or_trans_huge_or_clear_bad(), and shall only be called in + * places that already verified the pmd is not none and they want to + * walk ptes while holding the mmap sem in read mode (write mode don't + * need this). If THP is not enabled, the pmd can't go away under the + * code even if MADV_DONTNEED runs, but if THP is enabled we need to + * run a pmd_trans_unstable before walking the ptes after + * split_huge_pmd returns (because it may have run when the pmd become + * null, but then a page fault can map in a THP and not a regular page). + */ +static inline int pmd_trans_unstable(pmd_t *pmd) +{ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + return pmd_none_or_trans_huge_or_clear_bad(pmd); +#else + return 0; +#endif +} + +#ifndef CONFIG_NUMA_BALANCING +/* + * Technically a PTE can be PROTNONE even when not doing NUMA balancing but + * the only case the kernel cares is for NUMA balancing and is only ever set + * when the VMA is accessible. For PROT_NONE VMAs, the PTEs are not marked + * _PAGE_PROTNONE so by by default, implement the helper as "always no". It + * is the responsibility of the caller to distinguish between PROT_NONE + * protections and NUMA hinting fault protections. + */ +static inline int pte_protnone(pte_t pte) +{ + return 0; +} + +static inline int pmd_protnone(pmd_t pmd) +{ + return 0; +} +#endif /* CONFIG_NUMA_BALANCING */ + +#endif /* CONFIG_MMU */ + +#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP + +#ifndef __PAGETABLE_P4D_FOLDED +int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot); +int p4d_clear_huge(p4d_t *p4d); +#else +static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) +{ + return 0; +} +static inline int p4d_clear_huge(p4d_t *p4d) +{ + return 0; +} +#endif /* !__PAGETABLE_P4D_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); +int pmd_clear_huge(pmd_t *pmd); +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); +#else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */ +static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) +{ + return 0; +} +static inline int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) +{ + return 0; +} +static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) +{ + return 0; +} +static inline int p4d_clear_huge(p4d_t *p4d) +{ + return 0; +} +static inline int pud_clear_huge(pud_t *pud) +{ + return 0; +} +static inline int pmd_clear_huge(pmd_t *pmd) +{ + return 0; +} +static inline int p4d_free_pud_page(p4d_t *p4d, unsigned long addr) +{ + return 0; +} +static inline int pud_free_pmd_page(pud_t *pud, unsigned long addr) +{ + return 0; +} +static inline int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) +{ + return 0; +} +#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ + +#ifndef __HAVE_ARCH_FLUSH_PMD_TLB_RANGE +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +/* + * ARCHes with special requirements for evicting THP backing TLB entries can + * implement this. Otherwise also, it can help optimize normal TLB flush in + * THP regime. stock flush_tlb_range() typically has optimization to nuke the + * entire TLB TLB if flush span is greater than a threshold, which will + * likely be true for a single huge page. Thus a single thp flush will + * invalidate the entire TLB which is not desitable. + * e.g. see arch/arc: flush_pmd_tlb_range + */ +#define flush_pmd_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) +#define flush_pud_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) +#else +#define flush_pmd_tlb_range(vma, addr, end) BUILD_BUG() +#define flush_pud_tlb_range(vma, addr, end) BUILD_BUG() +#endif +#endif + +struct file; +int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, + unsigned long size, pgprot_t *vma_prot); + +#ifndef CONFIG_X86_ESPFIX64 +static inline void init_espfix_bsp(void) { } +#endif + +extern void __init pgtable_cache_init(void); + +#ifndef __HAVE_ARCH_PFN_MODIFY_ALLOWED +static inline bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot) +{ + return true; +} + +static inline bool arch_has_pfn_modify_check(void) +{ + return false; +} +#endif /* !_HAVE_ARCH_PFN_MODIFY_ALLOWED */ + +/* + * Architecture PAGE_KERNEL_* fallbacks + * + * Some architectures don't define certain PAGE_KERNEL_* flags. This is either + * because they really don't support them, or the port needs to be updated to + * reflect the required functionality. Below are a set of relatively safe + * fallbacks, as best effort, which we can count on in lieu of the architectures + * not defining them on their own yet. + */ + +#ifndef PAGE_KERNEL_RO +# define PAGE_KERNEL_RO PAGE_KERNEL +#endif + +#ifndef PAGE_KERNEL_EXEC +# define PAGE_KERNEL_EXEC PAGE_KERNEL +#endif + +/* + * Page Table Modification bits for pgtbl_mod_mask. + * + * These are used by the p?d_alloc_track*() set of functions an in the generic + * vmalloc/ioremap code to track at which page-table levels entries have been + * modified. Based on that the code can better decide when vmalloc and ioremap + * mapping changes need to be synchronized to other page-tables in the system. + */ +#define __PGTBL_PGD_MODIFIED 0 +#define __PGTBL_P4D_MODIFIED 1 +#define __PGTBL_PUD_MODIFIED 2 +#define __PGTBL_PMD_MODIFIED 3 +#define __PGTBL_PTE_MODIFIED 4 + +#define PGTBL_PGD_MODIFIED BIT(__PGTBL_PGD_MODIFIED) +#define PGTBL_P4D_MODIFIED BIT(__PGTBL_P4D_MODIFIED) +#define PGTBL_PUD_MODIFIED BIT(__PGTBL_PUD_MODIFIED) +#define PGTBL_PMD_MODIFIED BIT(__PGTBL_PMD_MODIFIED) +#define PGTBL_PTE_MODIFIED BIT(__PGTBL_PTE_MODIFIED) + +/* Page-Table Modification Mask */ +typedef unsigned int pgtbl_mod_mask; + +#endif /* !__ASSEMBLY__ */ + +#ifndef io_remap_pfn_range +#define io_remap_pfn_range remap_pfn_range +#endif + +#ifndef has_transparent_hugepage +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define has_transparent_hugepage() 1 +#else +#define has_transparent_hugepage() 0 +#endif +#endif + +/* + * On some architectures it depends on the mm if the p4d/pud or pmd + * layer of the page table hierarchy is folded or not. + */ +#ifndef mm_p4d_folded +#define mm_p4d_folded(mm) __is_defined(__PAGETABLE_P4D_FOLDED) +#endif + +#ifndef mm_pud_folded +#define mm_pud_folded(mm) __is_defined(__PAGETABLE_PUD_FOLDED) +#endif + +#ifndef mm_pmd_folded +#define mm_pmd_folded(mm) __is_defined(__PAGETABLE_PMD_FOLDED) +#endif + +/* + * p?d_leaf() - true if this entry is a final mapping to a physical address. + * This differs from p?d_huge() by the fact that they are always available (if + * the architecture supports large pages at the appropriate level) even + * if CONFIG_HUGETLB_PAGE is not defined. + * Only meaningful when called on a valid entry. + */ +#ifndef pgd_leaf +#define pgd_leaf(x) 0 +#endif +#ifndef p4d_leaf +#define p4d_leaf(x) 0 +#endif +#ifndef pud_leaf +#define pud_leaf(x) 0 +#endif +#ifndef pmd_leaf +#define pmd_leaf(x) 0 +#endif + +#endif /* _LINUX_PGTABLE_H */ diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 988d176472df..3a6adfa70fb0 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -77,7 +77,7 @@ struct anon_vma { struct anon_vma_chain { struct vm_area_struct *vma; struct anon_vma *anon_vma; - struct list_head same_vma; /* locked by mmap_sem & page_table_lock */ + struct list_head same_vma; /* locked by mmap_lock & page_table_lock */ struct rb_node rb; /* locked by anon_vma->rwsem */ unsigned long rb_subtree_last; #ifdef CONFIG_DEBUG_VM_RB diff --git a/include/linux/sched/debug.h b/include/linux/sched/debug.h index 95fb9e025247..00c45a0e6abe 100644 --- a/include/linux/sched/debug.h +++ b/include/linux/sched/debug.h @@ -30,7 +30,8 @@ extern void show_regs(struct pt_regs *); * task), SP is the stack pointer of the first frame that should be shown in the back * trace (or NULL if the entire call-chain of the task should be shown). */ -extern void show_stack(struct task_struct *task, unsigned long *sp); +extern void show_stack(struct task_struct *task, unsigned long *sp, + const char *loglvl); extern void sched_show_task(struct task_struct *p); diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index a132d875d351..480a4d1b7dd8 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -53,7 +53,7 @@ void mmdrop(struct mm_struct *mm); /* * This has to be called after a get_task_mm()/mmget_not_zero() - * followed by taking the mmap_sem for writing before modifying the + * followed by taking the mmap_lock 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 @@ -61,14 +61,14 @@ void mmdrop(struct mm_struct *mm); * 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 + * that can modify the "mm" (notably the vm_start/end) under mmap_lock * 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 + * the only case that holds the mmap_lock for reading that must call + * this function. Generally if the mmap_lock 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 + * the coredump code will hold the mmap_lock for writing before * invoking the ->core_dump methods. */ static inline bool mmget_still_valid(struct mm_struct *mm) diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 9861c89f93be..dac1db05bf7e 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -301,62 +301,20 @@ copy_struct_from_user(void *dst, size_t ksize, const void __user *src, return 0; } -/* - * probe_kernel_read(): safely attempt to read from a location - * @dst: pointer to the buffer that shall take the data - * @src: address to read from - * @size: size of the data chunk - * - * Safely read from address @src to the buffer at @dst. If a kernel fault - * happens, handle that and return -EFAULT. - */ -extern long probe_kernel_read(void *dst, const void *src, size_t size); -extern long probe_kernel_read_strict(void *dst, const void *src, size_t size); -extern long __probe_kernel_read(void *dst, const void *src, size_t size); +bool probe_kernel_read_allowed(const void *unsafe_src, size_t size); -/* - * probe_user_read(): safely attempt to read from a location in user space - * @dst: pointer to the buffer that shall take the data - * @src: address to read from - * @size: size of the data chunk - * - * Safely read from address @src to the buffer at @dst. If a kernel fault - * happens, handle that and return -EFAULT. - */ +extern long probe_kernel_read(void *dst, const void *src, size_t size); extern long probe_user_read(void *dst, const void __user *src, size_t size); -extern long __probe_user_read(void *dst, const void __user *src, size_t size); -/* - * probe_kernel_write(): safely attempt to write to a location - * @dst: address to write to - * @src: pointer to the data that shall be written - * @size: size of the data chunk - * - * Safely write to address @dst from the buffer at @src. If a kernel fault - * happens, handle that and return -EFAULT. - */ extern long notrace probe_kernel_write(void *dst, const void *src, size_t size); -extern long notrace __probe_kernel_write(void *dst, const void *src, size_t size); - -/* - * probe_user_write(): safely attempt to write to a location in user space - * @dst: address to write to - * @src: pointer to the data that shall be written - * @size: size of the data chunk - * - * Safely write to address @dst from the buffer at @src. If a kernel fault - * happens, handle that and return -EFAULT. - */ extern long notrace probe_user_write(void __user *dst, const void *src, size_t size); -extern long notrace __probe_user_write(void __user *dst, const void *src, size_t size); - -extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); -extern long strncpy_from_unsafe_strict(char *dst, const void *unsafe_addr, - long count); -extern long __strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); -extern long strncpy_from_unsafe_user(char *dst, const void __user *unsafe_addr, - long count); -extern long strnlen_unsafe_user(const void __user *unsafe_addr, long count); + +long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, + long count); + +long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, + long count); +long strnlen_user_nofault(const void __user *unsafe_addr, long count); /** * probe_kernel_address(): safely attempt to read from a location |